CN106817472B - A communication account determination method, terminal device and server - Google Patents

Abstract

The invention discloses a communication account determination method, a terminal device and a server, which are used to solve the problems of manually setting a blacklist or a whitelist in the prior art, the scale of setting rules cannot be controlled, and the communication control is not ideal. According to the second communication account in the control list, the terminal device adaptively filters out the similarity with the second communication account in the control list from the communication accounts of other contacts in the address book except all the second communication accounts. A higher communication account is recommended to the user as the communication account to be added to the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

Description

A communication account determination method, terminal device and server

technical field

The present invention relates to the field of communication technologies, and in particular, to a method for determining a communication account, a terminal device and a server.

Background technique

With the development of communication technology, users can not only communicate with other contacts through traditional communication methods (such as calling through mobile phones), but also communicate with other contacts through various communication applications (such as WeChat, Fetion, Tencent chat application QQ, etc.) people communicate.

However, in practical applications, the user may encounter the following situations. Therefore, it is necessary to control the communication of the terminal device: the user does not want to be disturbed for a certain period of time, and is worried about missing calls from important communication contacts; or, the user does not Willing to be disturbed by the designated communication contact, etc.

In order to realize the user's control of communication, the user can set a blacklist or whitelist in various terminal devices or communication applications, wherein setting a blacklist can make the terminal device or communication application permanently or within a specified period of time to prohibit The communication contacts in the blacklist communicate with the user; and by setting a whitelist, the terminal device or communication application can be made to allow only the communication contacts in the whitelist to communicate with the user permanently or within a specified period of time.

For example, a do not disturb mode is set on a smartphone. In the do not disturb mode, the user can manually set the do not disturb time and add a whitelist. The communication contacts in the whitelist can be the user's parents, important leaders, designated communication Communication contacts corresponding to the account, etc. For another example, a blacklist is set in the smart phone, and the accounts of the communication contacts in the blacklist are identified as a designated region or a designated group.

However, since the blacklist or whitelist is manually set, the scale of setting rules cannot be controlled, so that some communication contacts may be omitted or wrongly added in the blacklist or whitelist, which is not ideal for communication control.

SUMMARY OF THE INVENTION

The present invention provides a communication account determination method, terminal equipment and server, which are used to solve the problems in the prior art that a blacklist or a whitelist is manually set, the scale of the setting rules cannot be controlled, and the communication control is not ideal.

The specific technical scheme provided by the present invention is as follows:

In a first aspect, a method for determining a communication account is provided, including:

The terminal device obtains a set control list, the control list is set for the first communication account corresponding to the terminal device, and includes at least one second communication account, and the control list is a blacklist or a whitelist, and each second The communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device;

obtaining, by the terminal device, a historical communication record of the first communication account;

The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, wherein the feature in the feature vector includes any one or combination of the following: The number of times the first communication account calls the contact's communication account, the number of times the contact's communication account calls the first communication account, and the total communication between the first communication account and the contact's communication account times; and combine all the generated feature vectors to generate the first feature set;

The terminal device performs normalization processing on each of the features in the first feature set to generate a second feature set;

The terminal device determines, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

According to the determined similarity, the terminal device selects a preset first number of communication accounts among the communication accounts of the contacts in the address book, and uses the selected communication accounts as the communication accounts to be added to the control list. communication account.

In this way, according to the second communication account in the control list, the terminal device can adaptively filter out the communication accounts of other contacts in the address book except all the second communication accounts, which are related to the second communication account in the control list. A communication account with a higher similarity of the communication accounts is recommended to the user as the communication account to be added to the control list, which meets the user's needs and improves the efficiency of the user's communication control.

With reference to the first aspect, in a first possible implementation manner of the first aspect, before the terminal device generates a feature vector for the communication account of each contact in the address book, the method further includes:

The terminal device obtains the set Do Not Disturb time;

The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, including:

The terminal device generates a feature vector for the communication account of each contact in the address book according to the acquired historical communication record and the do not disturb time;

The features in the feature vector also include any one or a combination of the following: the number of times the first communication account calls the contact's communication account during the do not disturb time, the first communication account outside the do not disturb time. The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account within the do not disturb time, the number of times the communication account of the contact calls the first communication account outside the do not disturb time. The number of times of the first communication account, the total number of communication between the first communication account and the contact's communication account during the do not disturb time, and the first communication account and the contact outside the do not disturb time. The total number of communications between the contact's communications accounts.

With reference to the first aspect or the first possible implementation manner of the first aspect, in the second possible implementation manner of the first aspect, the terminal device is directed to the communication account of each contact in the address book , before generating the feature vector, also includes:

The terminal device obtains the corresponding account information of the communication account of each contact in the address book, and the account information includes any one or a combination of the following: a contact identifier, an identifier of the work unit to which the contact belongs, and a group to which the contact belongs. group ID;

The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, including:

Converting each of the account information by the terminal device includes: converting, by the terminal device, the contact identifier in each of the account information into a digital number according to a preset correspondence between the contact identifier and the digital number; and According to the preset correspondence between the identification of the work unit to which the contact belongs and the numerical number, the identification of the work unit to which the contact belongs in each of the account information is converted into a numerical number; and according to the preset identification of the group to which the contact belongs and the number The corresponding relationship of the numbers, converting the group identification to which the contact person belongs in each described account information into a digital number;

The terminal device generates a feature vector for each contact communication account in the address book according to the obtained historical communication record and the converted information of each account;

The features in the feature vector further include: the digital number converted from the contact identifier, the converted digital number from the work unit identifier to which the contact belongs, and the converted digital number from the group identifier to which the contact belongs.

With reference to any one of the first aspect, the first possible implementation manner of the first aspect, and the second possible implementation manner, in a third possible implementation manner of the first aspect, the terminal device determines that the second In the feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts includes:

The terminal device calculates, in the second feature set, the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

The terminal device determines the feature vector corresponding to the communication account of each contact according to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each of the second communication accounts Similarity of feature vectors corresponding to each of the second communication accounts.

In combination with the third possible implementation manner of the first aspect, in the fourth possible implementation manner of the first aspect, the terminal device is associated with each of the The distance between the feature vectors corresponding to the second communication accounts, and determining the similarity between the feature vectors corresponding to the communication accounts of each of the contacts and the feature vectors corresponding to each of the second communication accounts, including:

The terminal device performs the following steps for the distance between the feature vector corresponding to the communication account of each of the contacts and the corresponding feature vector of each of the second communication accounts:

Taking the quotient of the number of features in the feature vector corresponding to the distance and the communication account of the contact as a similarity parameter;

The difference between 1 and the similarity parameter is taken as the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account.

With reference to the first aspect and any one of the first to fourth possible implementation manners of the first aspect, in a fifth possible implementation manner of the first aspect, the terminal device is based on the determined similarity degree, in the communication account of the contact person of the said address book, select the communication account of preset first number, including:

The terminal device performs the following steps for the communication account of each contact except all the second communication accounts in the address book:

Sorting the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filtering out the similarity of the preset second number with the highest value; and

Taking the average value of the similarity of the screened out second number as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

The terminal device compares the average value of the similarity between the feature vector corresponding to the communication account of each contact except all the second communication accounts in the address book and the feature vector corresponding to all the second communication accounts in the control list. Sorting, filtering out the average similarity of the first number with the highest value;

The terminal device determines the communication account of the contact corresponding to each of the filtered average similarity degrees.

With reference to the first aspect and any one of the first to fifth possible implementations of the first aspect, in the sixth possible implementation of the first aspect, when the number of the second communication accounts is When there are at least two, after the terminal device determines the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account in the second feature set, the method further includes:

The terminal device performs the following steps for each second communication account:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the highest preset third number; and

Taking the average value of the similarity of the screened out third number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

The terminal device sorts the average value of the similarity between the feature vector corresponding to each of the second communication accounts and the feature vectors corresponding to all other second communication accounts, and filters out the similarity of the fourth number with the lowest value. average value;

The terminal device determines the second communication account corresponding to each of the filtered average similarity degrees, and uses the determined second communication account as the communication account to be deleted in the control list.

In this way, the terminal can also adaptively screen out a communication account with a low similarity to other second communication accounts in the control list, and recommend it to the user as the communication account to be deleted in the control list, so that , which can remind the user whether there is a communication account added to the control list by mistake in the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

With reference to the first aspect and any one of the first to fourth possible implementation manners of the first aspect, in a seventh possible implementation manner of the first aspect, the terminal device selects the first Before the number of communication accounts, it also includes:

receiving, by the terminal device, the importance index of the communication account of each contact to the first communication account sent by the server;

According to the determined similarity, the terminal device selects a preset first number of communication accounts among the communication accounts of the contacts in the address book, including:

The terminal device is based on the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, and the importance index of the communication account of each contact to the first communication account. , in the communication accounts of the contacts in the address book, select a preset first number of communication accounts.

With reference to the seventh possible implementation manner of the first aspect, in the eighth possible implementation manner of the first aspect, when the control list is a white list, the terminal device, according to the determined similarity, and The importance index of the communication account of each contact to the first communication account, among the communication accounts of the contacts in the address book, selecting a preset first number of communication accounts, including:

The terminal device performs the following steps for the communication account of each contact except all the second communication accounts in the address book:

Sort the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filter out the similarity of the highest preset fifth number; and

Taking the average value of the similarity of the fifth number screened out as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

The average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the control list, and the difference between the communication account of the contact and the first communication account. The product of the importance index is used as the recommendation weight of the contact;

The terminal device sorts the recommendation weights of each contact except all the second communication accounts in the address book, and filters out the first number of recommendation weights with the highest value;

The terminal device determines the communication account of the contact corresponding to each of the selected recommendation weights.

In this way, when the control list is a white list, the terminal device may, according to the second communication account in the control list, among the communication accounts of other contacts except all the second communication accounts in the address book, comprehensively consider the The similarity of the second communication account and the importance to the first communication account are adaptively screened out to have a high similarity with the second communication account in the control list, and the importance of the first communication account to the first communication account. The communication account with high reliability is recommended to the user as the communication account to be added to the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

In combination with the seventh or eighth possible implementation manner of the first aspect, in the ninth possible implementation manner of the first aspect, when the control list is a white list, and the number of the second communication accounts is at least When there are two, after the terminal device receives the importance index of each contact's communication account to the first communication account sent by the server, it further includes:

The terminal device performs the following steps for each second communication account:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the preset sixth number with the highest value; and

Taking the average value of the similarity of the screened sixth number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

The terminal device is the product of the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the importance index of the second communication account to the first communication account, as the deletion weight of the second communication account;

The terminal device sorts the deletion weights of each second communication account, and filters out the seventh number of deletion weights with the lowest value;

The terminal device determines the second communication account corresponding to each of the selected deletion weights, and uses the determined second communication account as the communication account to be deleted in the control list.

In this way, when the control control list is a white list, the terminal device can comprehensively consider the similarity with other second communication accounts and the importance to the first communication account in the control list, and adapt to the Screening out a communication account with a low degree of similarity with other second communication accounts and a relatively low importance to the first communication account, and recommending it to the user as the communication account to be deleted in the control list. In this way, it is possible to The user is reminded whether there is a communication account wrongly added to the control list in the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

In a second aspect, a method for determining a communication account is provided, including:

The server determines the communication information between the communication accounts of every two contacts in the address book, where the address book is the first communication account corresponding to a terminal device, and the communication information includes any one of the following: The total number of communication between the communication accounts of the two contacts, the number of times that the third communication account in the communication accounts of the two contacts calls the fourth communication account, the communication account of the two contacts calls the fourth communication account The number of third communication accounts;

For the communication account of each contact person in the address book, the server generates an importance vector according to the communication information between the communication account of the contact person and the communication account including all contacts; The sex vectors are combined to generate a third feature set;

The server normalizes the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set;

The server calculates, according to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account, the relationship between the communication account of each contact and the first communication account. Account importance index;

The server sends the importance index of each contact's communication account to the first communication account to the terminal device.

In this way, after the server sends the importance index of each contact's communication account to the first communication account to the terminal device, the terminal device can, when the control list is a white list, The second communication account in the control list, among the communication accounts of other contacts except all the second communication accounts in the address book, comprehensively consider the similarity with the second communication account and the importance to the first communication account , and adaptively screen out a communication account with a higher similarity to the second communication account in the control list and a higher importance to the first communication account, and use it as a communication account to be added to the control list The account is recommended to the user, which meets the user's needs and improves the efficiency of the user's communication control.

With reference to the second aspect, in a first possible implementation manner of the second aspect, the server determines, according to the fourth feature set, and the preset importance of the communication account of each contact to the first communication account The initial value of the sex index is used to calculate the importance index of each contact's communication account to the first communication account, including:

According to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account, the server initially calculates the relationship between the communication account of each contact and the first communication account. Account importance index;

When the initial value of the importance index of each contact's communication account to the first communication account obtained by initial calculation is different from the preset initial value of the importance index of each contact's communication account to the first communication account , the server, according to the fourth feature set, and the importance index of each contact's communication account to the first communication account obtained by the initial calculation, continues to calculate the next time the communication account of each contact is to the described first communication account. The importance index of the first communication account is repeated until the calculated importance index of each contact's communication account to the first communication account no longer changes;

The server will calculate the importance index of the communication account of each contact that does not change to the first communication account as the final importance of the communication account of each contact to the first communication account index.

In combination with the first possible implementation manner of the second aspect, in the second possible implementation manner of the second aspect, the server initially calculates the importance index of the communication account of each contact to the first communication account , the importance index of each contact's communication account to the first communication account obtained by the initial calculation satisfies the following formula:

R ^new =IE*(1-d)/N+d*TR*R ^old

Wherein, R ^new is the importance index of the communication account of each contact obtained by the initial calculation to the first communication account, d is the disturbance factor, and N is the number of communication accounts of the contact in the address book, TR is the fourth feature set, and R ^old is a preset initial value of the importance index of each contact's communication account to the first communication account.

In a third aspect, a terminal device is provided. The terminal device has a function of implementing the behavior of the terminal device in the above communication account determination method. The hardware or software includes one or more modules corresponding to the above functions.

In a possible implementation manner, the terminal device includes a transceiver, a processor, a bus, and a memory, and the transceiver, the processor, and the memory are connected to each other through a bus, wherein:

the transceiver, used for data communication with the server;

The processor is configured to obtain a set control list, where the control list is set for the first communication account corresponding to the terminal device, including at least one second communication account, and the control list is a blacklist or a whitelist , each second communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device;

obtaining the historical communication record of the first communication account;

According to the acquired historical communication records, a feature vector is generated for the communication account of each contact in the address book, wherein the features in the feature vector include any one or a combination of the following: the first The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account, and the total number of communication between the first communication account and the communication account of the contact; and All the generated feature vectors are combined to generate the first feature set;

normalizing each of the features in the first feature set to generate a second feature set;

Determine, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

According to the determined similarity, among the communication accounts of the contacts in the address book, a preset first number of communication accounts are selected, and the selected communication account is used as the communication account to be added to the control list;

The memory is used to store programs.

In another possible implementation manner, the terminal device includes:

The obtaining unit is configured to obtain a set control list, the control list is set for the first communication account corresponding to the terminal device, and includes at least one second communication account, and the control list is a blacklist or a whitelist, and each control list is a blacklist or a whitelist. A second communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device; and

obtaining the historical communication record of the first communication account;

A processing unit, configured to generate a feature vector for the communication account of each contact person in the address book according to the obtained historical communication record, wherein the feature in the feature vector includes any one or combination of the following : the number of times the first communication account calls the contact’s communication account, the number of times the contact’s communication account calls the first communication account, and the total number of times between the first communication account and the contact’s communication account the number of communications; and combine all the generated feature vectors to generate the first feature set; and

normalizing each of the features in the first feature set to generate a second feature set; and

Determine, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

A selection unit, configured to select a preset first number of communication accounts from among the communication accounts of the contacts in the address book according to the determined similarity, and use the selected communication account as a communication account to be added to the control List of communication accounts.

In a fourth aspect, a server is provided, the server has a function of implementing the server behavior in the above communication account determination method, the function can be implemented by hardware, or can be implemented by executing corresponding software through hardware, the hardware or software can be implemented. It includes one or more modules corresponding to the above functions.

In a possible implementation manner, the server includes a transceiver, a processor, a bus, and a memory, and the transceiver, the processor, and the memory are connected to each other through a bus, wherein:

the transceiver, used for data communication with the terminal device;

The processor is configured to determine the communication information between the communication accounts of every two contacts in the address book, where the address book is the first communication account corresponding to a terminal device, and the communication information includes any one of the following: Item: the total number of communication between the communication accounts of the two contacts, the number of times the third communication account calls the fourth communication account in the communication accounts of the two contacts, the number of times described in the communication accounts of the two contacts 4. The number of times the communication account calls the third communication account;

For the communication account of each contact in the address book, an importance vector is generated according to the communication information between the communication account of the contact and the communication account including all contacts; and all the generated importance vectors are combined to generate a third feature set;

Normalizing the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set;

Calculate the importance of each contact's communication account to the first communication account according to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account Sex index;

sending the importance index of each contact's communication account to the first communication account to the terminal device;

The memory is used to store programs.

In another possible implementation manner, the server includes:

A determining unit, configured to determine the communication information between the communication accounts of every two contacts in the address book, where the address book is a first communication account corresponding to a terminal device, and the communication information includes any of the following: The total number of communications between the communication accounts of the two contacts, the number of times the third communication account in the communication accounts of the two contacts calls the fourth communication account, the fourth communication in the communication accounts of the two contacts The number of times the account calls the third communication account;

The processing unit is used to generate an importance vector for the communication account of each contact person in the address book according to the communication information between the communication account of the contact person and the communication account including all contacts; all importance vectors are combined to generate a third feature set; and

Normalizing the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set; and

Calculate the importance of each contact's communication account to the first communication account according to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account Sex index;

A sending unit, configured to send the importance index of each contact's communication account to the first communication account to the terminal device.

With the method for determining a communication account provided by the present invention, the terminal device can adaptively filter out the communication accounts of other contacts except all the second communication accounts in the address book according to the second communication account in the control list. A communication account with a higher similarity in the second communication account in the control list is recommended to the user as the communication account to be added to the control list, which meets the user's needs and improves the efficiency of the user's communication control.

Description of drawings

1 is a network architecture diagram for realizing a method for determining a communication account according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a terminal device according to an embodiment of the present invention;

3 is a schematic structural diagram of a server according to an embodiment of the present invention;

4 is a flowchart of a method for determining a communication account provided by an embodiment of the present invention;

5 is a flowchart of a method for determining a communication account provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram of a terminal device according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Embodiments of the present invention provide a communication account determination method and terminal device, which are used to solve the problems in the prior art that a blacklist or a whitelist is manually set, the scale of setting rules cannot be controlled, and communication control is not ideal. Wherein, the method and the controller of the present invention are based on the same inventive concept. Since the principles of the method and the device for solving problems are similar, the implementation of the device and the method can be referred to each other, and repeated descriptions will not be repeated here.

In this embodiment of the present invention, the terminal device corresponding to the first communication account acquires a control list, wherein the control list includes at least one second communication account, and each second communication account is an address book of the first communication account The communication account of the contact person in the contact list; the terminal device generates a feature vector for the communication account of each contact person in the address book according to the historical communication record of the first communication account, and performs all the generated feature vectors for combined to generate a first feature set; after normalizing each feature in the first feature set, a second feature set is generated, and the terminal device determines that in the second feature set, each contact The similarity between the feature vector corresponding to the communication account and the feature vector corresponding to each of the second communication accounts; and according to the determined similarity, in the communication account of the contact person in the address book, select the preset No. A number of communication accounts, and the selected communication account is used as the communication account to be added to the control list. In this way, the terminal device can generate a first feature set according to the features in the historical communication records, and after normalizing each feature in the first feature set, generate a second feature set; In the feature set, the feature vector corresponding to each contact in the address book is similar to the feature vector corresponding to each second communication account in the control list, and the first number of communication accounts are screened out as the terminal adaptive The communication account to be added to the control list is calculated and recommended, and the recommended communication account has a high similarity with the second communication account in the control list, which meets the needs of the user and can better control communication.

The method for determining a communication account provided by the embodiment of the present invention is applicable to the communication network architecture shown in FIG. 1 . The network architecture includes: a server 101 and a plurality of terminal devices, such as the computer 102 , the mobile communication device 103 and the Tablet 104, etc., wherein,

The server 101 is used to process the call initiated by the terminal device, and save the communication information between the two terminal devices after the connection is established, such as the communication duration between the communication accounts of the two terminals, the number of times of communication, etc.;

The terminal device may be a computer 102 as shown in the figure, a mobile communication device 103, or other devices, such as a tablet computer 104, a fixed phone, and the like. Wherein, when the terminal device is a handheld mobile device (such as a mobile communication device 103, a tablet computer 104, etc.), a connection is established between the terminal device and the server 101 through a wireless link, and when the terminal device is When it is a computer 102 or other network devices that require physical connection, the terminal device and the server 101 are connected through a physical link.

Wherein, when the terminal device calls other terminal devices through the mobile communication service, the terminal device is a mobile communication device 103, a fixed telephone, etc., and the server 101 is a network device in mobile communication; The terminal device calls other terminal devices corresponding to another communication account through various types of applications, the terminal device is the computer 102 or various types of intelligent terminal devices, and the server is the server of the various types of applications.

Referring to FIG. 2, an embodiment of the present invention provides a terminal device. The terminal device 200 includes: a transceiver 201, a processor 202, a bus 203, and a memory 204, wherein:

The transceiver 201, the processor 202 and the memory 204 are connected to each other through a bus 203; the bus 203 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 2, but it does not mean that there is only one bus or one type of bus.

The transceiver 201 is used for data communication with other devices such as other terminal devices and servers.

The processor 202 is configured to implement a method for determining a communication account, including:

Obtain a set control list, the control list is set for the first communication account corresponding to the terminal device 200, including at least one second communication account, the control list is a blacklist or a whitelist, and each second communication The account is the communication account of the contact person in the address book of the first communication account saved by the terminal device 200;

obtaining the historical communication record of the first communication account;

According to the acquired historical communication records, a feature vector is generated for the communication account of each contact in the address book, wherein the features in the feature vector include any one or a combination of the following: the first The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account, and the total number of communication between the first communication account and the communication account of the contact; and All the generated feature vectors are combined to generate the first feature set;

normalizing each of the features in the first feature set to generate a second feature set;

Determine, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

According to the determined similarity, among the communication accounts of the contacts in the address book, a preset first number of communication accounts are selected, and the selected communication accounts are used as the communication accounts to be added to the control list.

Optionally, before generating a feature vector for the communication account of each contact person in the address book, the method further includes:

Get the set Do Not Disturb time;

According to the obtained historical communication records, a feature vector is generated for the communication account of each contact in the address book, including:

According to the obtained historical communication record and the Do Not Disturb time, a feature vector is generated for the communication account of each contact in the address book;

The features in the feature vector also include any one or a combination of the following: the number of times the first communication account calls the contact's communication account during the do not disturb time, the first communication account outside the do not disturb time. The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account within the do not disturb time, the number of times the communication account of the contact calls the first communication account outside the do not disturb time. The number of times of the first communication account, the total number of communication between the first communication account and the contact's communication account during the do not disturb time, and the first communication account and the contact outside the do not disturb time. The total number of communications between the contact's communications accounts.

Optionally, before generating a feature vector for the communication account of each contact person in the address book, the method further includes:

Obtain the corresponding account information of the communication account of each contact in the address book, where the account information includes any one or a combination of the following: a contact identifier, an identifier of a work unit to which the contact belongs, and an identifier of a group to which the contact belongs;

According to the obtained historical communication records, a feature vector is generated for the communication account of each contact in the address book, including:

Converting each of the account information by the terminal device includes: converting the contact identifier in each of the account information into a digital number according to the preset correspondence between the contact identifier and the digital number; The corresponding relationship between the identification of the work unit to which the contact belongs and the numerical number, converting the identification of the work unit to which the contact belongs in each of the account information into a numerical number; and according to the preset corresponding relationship between the identification of the group to which the contact belongs and the numerical number , convert the group identification to which the contact person belongs in each described account information into a digital number;

According to the obtained historical communication records and the converted account information, a feature vector is generated for each contact communication account in the address book;

The features in the feature vector further include: the digital number converted from the contact identifier, the converted digital number from the work unit identifier to which the contact belongs, and the converted digital number from the group identifier to which the contact belongs.

Optionally, determine the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts in the second feature set, including:

Calculate, in the second feature set, the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

According to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, determine the feature vector corresponding to the communication account of each contact and each The similarity of the feature vector corresponding to the second communication account.

Optionally, according to the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts, determine the feature vector corresponding to the communication account of each of the contacts The similarity of the feature vector corresponding to each of the second communication accounts, including:

The terminal device performs the following steps for the distance between the feature vector corresponding to the communication account of each of the contacts and the corresponding feature vector of each of the second communication accounts:

Taking the quotient of the number of features in the feature vector corresponding to the distance and the communication account of the contact as a similarity parameter;

The difference between 1 and the similarity parameter is taken as the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account.

Optionally, according to the determined similarity, among the communication accounts of the contacts in the address book, a preset first number of communication accounts are selected, including:

For the communication accounts of each contact in the address book except all the second communication accounts, perform the following steps:

Sorting the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filtering out the similarity of the preset second number with the highest value; and

Taking the average value of the similarity of the screened out second number as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

Sort the feature vectors corresponding to the communication accounts of each contact person except all second communication accounts in the address book and the average similarity of the feature vectors corresponding to all the second communication accounts in the control list, and filter out take the average value of the similarity of the first number with the highest value;

Determine the communication account of the contact corresponding to each of the filtered average similarity degrees.

Optionally, when the number of the second communication accounts is at least two, it is determined that in the second feature set, the feature vector corresponding to the communication account of each contact and the feature corresponding to each second communication account After the similarity of the vectors, it also includes:

For each secondary communication account, perform the following steps:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the highest preset third number; and

Taking the average value of the similarity of the screened out third number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

Sort the feature vector corresponding to each second communication account with the average similarity of the feature vectors corresponding to all other second communication accounts, and filter out the average similarity of the fourth number with the lowest value;

Determining the second communication account corresponding to each of the filtered average similarity degrees, and using the determined second communication account as the communication account to be deleted in the control list.

Optionally, before selecting the first number of communication accounts, the method further includes:

receiving the importance index of each contact's communication account to the first communication account sent by the server;

According to the determined similarity, among the communication accounts of the contacts in the address book, a preset first number of communication accounts are selected, including:

According to the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, and the importance of the communication account of each contact to the first communication account Sex index, select a preset first number of communication accounts among the communication accounts of the contacts in the address book.

Optionally, when the control list is a white list, according to the determined similarity and the importance index of the communication account of each contact to the first communication account, in the address book In the communication accounts of the contact, select the preset first number of communication accounts, including:

For the communication accounts of each contact in the address book except all the second communication accounts, perform the following steps:

Sort the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filter out the similarity of the highest preset fifth number; and

Taking the average value of the similarity of the fifth number screened out as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

The average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the control list, and the value of the importance index of the communication account of the contact to the first communication account. The product is used as the recommendation weight of the contact;

Sorting the recommendation weights of each contact except all the second communication accounts in the address book, and filtering out the first number of recommendation weights with the highest value;

The communication account of the contact corresponding to each of the selected recommendation weights is determined.

Optionally, when the control list is a white list and the number of the second communication accounts is at least two, after receiving the communication account of each contact sent by the server to the first communication account. After the importance index, it also includes:

For each secondary communication account, perform the following steps:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the preset sixth number with the highest value; and

Taking the average value of the similarity of the screened sixth number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

The average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the product of the importance index of the second communication account to the first communication account, as the second communication account. The deletion weight of the communication account;

Sort the deletion weights of each second communication account, and filter out the seventh number of deletion weights with the lowest value;

A second communication account corresponding to each of the selected deletion weights is determined, and the determined second communication account is used as the communication account to be deleted in the control list.

The terminal device 200 further includes a memory 204 for storing programs and the like. Specifically, the program may include program code, the program code including computer operation instructions. The memory 204 may include random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. The processor 202 executes the application program stored in the memory 204 to realize the communication account determination method.

Referring to FIG. 3, an embodiment of the present invention provides a server. The server 300 includes: a transceiver 301, a processor 302, a bus 303, and a memory 304, wherein:

The transceiver 301, the processor 302 and the memory 304 are connected to each other through a bus 303; the bus 303 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 3, but it does not mean that there is only one bus or one type of bus.

The transceiver 301 is used for data communication with the terminal device, such as sending the importance index of the communication account of each contact in the address book of the first communication account corresponding to a terminal device to the first communication account to the said first communication account. Terminal Equipment.

The processor 302 is configured to implement a method for determining a communication account, including:

Determine the communication information between the communication accounts of every two contacts in the address book, where the address book is a first communication account corresponding to a terminal device, and the communication information includes any one of the following: the two contacts The total number of communication between the communication accounts of the two contacts, the number of times that the third communication account in the communication accounts of the two contacts calls the fourth communication account, the communication account of the two contacts The fourth communication account calls the fourth communication account. 3. The number of communication accounts;

For the communication account of each contact in the address book, an importance vector is generated according to the communication information between the communication account of the contact and the communication account including all contacts; and all the generated importance vectors are combined to generate a third feature set;

Normalizing the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set;

Calculate the importance of each contact's communication account to the first communication account according to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account Sex index;

The importance index of each contact's communication account to the first communication account is sent to the terminal device.

Optionally, according to the fourth feature set and the preset initial value of the importance index of the communication account of each contact to the first communication account, calculate the value of the communication account of each contact to the first communication account. The importance index of the communication account, including:

According to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account, the importance of each contact's communication account to the first communication account is initially calculated. Sex index;

When the initial value of the importance index of each contact's communication account to the first communication account obtained by initial calculation is different from the preset initial value of the importance index of each contact's communication account to the first communication account , according to the fourth feature set, and the importance index of the communication account of each contact person to the first communication account obtained by the initial calculation, continue to calculate the communication account of each contact person to the first communication account next time The importance index of the account is repeated until the calculated importance index of each contact's communication account to the first communication account no longer changes;

The calculated importance index of each contact's communication account to the first communication account that does not change is used as the final importance index of each contact's communication account to the first communication account.

Optionally, when calculating the importance index of the communication account of each contact to the first communication account for the first time, the importance index of the communication account of each contact obtained by the initial calculation to the first communication account , which satisfies the following formula:

R ^new =IE*(1-d)/N+d*TR*R ^old

Wherein, R ^new is the importance index of the communication account of each contact obtained by the initial calculation to the first communication account, d is the disturbance factor, and N is the number of communication accounts of the contact in the address book, TR is the fourth feature set, and R ^old is a preset initial value of the importance index of each contact's communication account to the first communication account.

The server 300 also includes a memory 304 for storing programs and the like. Specifically, the program may include program code, the program code including computer operation instructions. Memory 304 may include RAM and may also include non-volatile memory, such as at least one disk storage. The processor 302 executes the application program stored in the memory 304 to implement the communication account determination method.

Referring to FIG. 4 , a method for determining a communication account provided by an embodiment of the present invention is applied to the communication network architecture shown in FIG. 1 , and the method is applicable to terminal devices in the network architecture. The processing flow of the method includes: :

Step 401: The terminal device obtains a set control list, the control list is set for the first communication account corresponding to the terminal device, and includes at least one second communication account, the control list is a blacklist or a whitelist, and each control list is a blacklist or a whitelist. The second communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device.

Usually, when the user controls the communication of the terminal device, the user sets a control list to the terminal device, and the control list can be a blacklist or a whitelist. Permanently or within a specified period of time, prohibit the second communication account in the blacklist from communicating with the first communication account; and setting a whitelist can make the terminal device or communication application permanently or within a specified period of time, only allow the whitelist The second communication account in communicates with the first communication account.

Step 402: The terminal device acquires the historical communication record of the first communication account.

Traditionally, after the first communication account communicates with any other communication account, the terminal device corresponding to the first communication account will update the historical communication record of the first communication account, A new communication record is added, for example, the new communication record includes: the first communication account calls the other communication accounts, the communication time, and the communication duration.

Step 403: According to the acquired historical communication records, the terminal device generates a feature vector for the communication account of each contact in the address book, wherein the features in the feature vector include any of the following: Or a combination of: the number of times the first communication account calls the contact’s communication account, the number of times the contact’s communication account calls the first communication account, and the difference between the first communication account and the contact’s communication account The total number of communications; and all the generated feature vectors are combined to generate the first feature set.

Optionally, before the terminal device generates a feature vector for the communication account of each contact in the address book, the method further includes:

The terminal device obtains the set Do Not Disturb time;

The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, including:

The terminal device generates a feature vector for the communication account of each contact in the address book according to the acquired historical communication record and the do not disturb time;

The features in the feature vector also include any one or a combination of the following: the number of times the first communication account calls the contact's communication account during the do not disturb time, the first communication account outside the do not disturb time. The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account within the do not disturb time, the number of times the communication account of the contact calls the first communication account outside the do not disturb time. The number of times of the first communication account, the total number of communication between the first communication account and the contact's communication account during the do not disturb time, and the first communication account and the contact outside the do not disturb time. The total number of communications between the contact's communications accounts.

Optionally, the terminal device can also obtain other do not disturb setting information such as the do not disturb location, so that after the record about the do not disturb location and other information is saved in the historical communication record, the terminal device can The historical communication records, Do Not Disturb locations and other Do Not Disturb setting information, such as the historical communication records, do not disturb, generate a feature vector for the communication account of each contact person in the address book, which is not limited in the present invention.

Optionally, before the terminal device generates a feature vector for the communication account of each contact in the address book, the method further includes:

The terminal device obtains the corresponding account information of the communication account of each contact in the address book, and the account information includes any one or a combination of the following: a contact identifier, an identifier of the work unit to which the contact belongs, and a group to which the contact belongs. Group identification; wherein, the contact identification may be a digital number of a communication account, such as a mobile phone number, a qq number and other numbers, or a contact name and the like.

The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, including:

Converting each of the account information by the terminal device includes: converting, by the terminal device, the contact identifier in each of the account information into a digital number according to a preset correspondence between the contact identifier and the digital number; and According to the preset correspondence between the identification of the work unit to which the contact belongs and the numerical number, the identification of the work unit to which the contact belongs in each of the account information is converted into a numerical number; and according to the preset identification of the group to which the contact belongs and the number The corresponding relationship of the numbers, converting the group identification to which the contact person belongs in each described account information into a digital number;

The terminal device generates a feature vector for each contact communication account in the address book according to the obtained historical communication record and the converted information of each account;

The features in the feature vector further include: the digital number converted from the contact identifier, the converted digital number from the work unit identifier to which the contact belongs, and the converted digital number from the group identifier to which the contact belongs.

Wherein, when the terminal device converts the contact identifier, the work unit identifier to which the contact belongs, and the group identifier to which the contact belongs to a digital number, it uses the preset correspondence between the contact identifier and the digital number, and the work to which the contact belongs. The correspondence between the unit identifier and the numerical number, and the correspondence between the group identifier and the numerical number of the contact person are converted. In the correspondence between any item of account information and a digital number, a digital number corresponds to a unique value among the values of the account information.

Step 404: The terminal device normalizes each of the features in the first feature set to generate a second feature set.

Optionally, the terminal device may use various traditional normalization methods to normalize each of the features in the first feature set, such as a linear function conversion method, a logarithmic function conversion method, an inverse Cotangent function conversion method, subtracting the mean value, multiplying by the variance, dividing by the maximum value... This is not limited in the present invention, and the terminal device can use any of the above methods to perform the first feature set. The features are normalized, so that the value of each feature in the feature vector corresponding to the communication account of each contact in the generated second feature set belongs to the interval [0,1].

Step 405: The terminal device determines the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account in the second feature set.

Optionally, calculate the similarity of two vectors. Traditionally, it can be reflected by calculating various indicators of the two vectors, for example, calculating the distance between the two vectors (including Euclidean distance, Manhattan distance, Chebyshev distance) distance, Minkowski distance, normalized Euclidean distance, Mahalanobis distance, Hamming distance, Jaccard distance, etc.), methods such as calculating the cosine of the angle between two vectors, which are not limited in the present invention.

Optionally, when the similarity between the two vectors is represented by the distance between the two vectors, when the terminal device performs step 405, the following steps are included:

The terminal device calculates, in the second feature set, the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

The terminal device determines the feature vector corresponding to the communication account of each contact according to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each of the second communication accounts Similarity of feature vectors corresponding to each of the second communication accounts.

The terminal device determines the feature vector corresponding to the communication account of each contact according to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each of the second communication accounts The similarity of the feature vector corresponding to each of the second communication accounts, including:

The terminal device performs the following steps for the distance between the feature vector corresponding to the communication account of each of the contacts and the corresponding feature vector of each of the second communication accounts:

Taking the quotient of the number of features in the feature vector corresponding to the distance and the communication account of the contact as a similarity parameter;

The difference between 1 and the similarity parameter is taken as the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account.

Optionally, the distance between the feature vector corresponding to the communication account of any contact and the feature vector corresponding to each of the second communication accounts can be any one of the above distance indicators, where the Euclidean distance is example:

The terminal device uses formula 1 to calculate the distance between the feature vector corresponding to the communication account of any contact and the feature vector corresponding to any second communication account in the second feature set:

公式一

Formula one

L is the Euclidean distance between the two feature vectors, x _i is the i-th element in the feature vector corresponding to the communication account of the contact, y _i is the eigenvector corresponding to the second communication account The i-th element, n is the number of elements in the feature vector corresponding to the communication account of the contact.

The terminal device uses formula 2 to calculate the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account:

公式二

Formula two

Wherein, S is the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account.

Optionally, when the similarity between the two vectors is represented by the distance between the two vectors, when the terminal device performs step 405, the following steps are included:

The terminal device calculates, in the second feature set, the cosine of the included angle between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account;

The terminal device uses the cosine of the included angle between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account as the feature vector corresponding to the communication account of each contact and each second communication account. The similarity of the feature vectors corresponding to the two communication accounts.

Optionally, the terminal device can use formula 3 to calculate the cosine of the included angle between the feature vector corresponding to the communication account of any contact and the feature vector corresponding to any second communication account:

公式三

Formula three

Wherein, cosθ is the cosine of the included angle between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account, and x _i is the first eigenvector in the feature vector corresponding to the communication account of the contact i elements, y _i is the ith element in the feature vector corresponding to the second communication account, and n is the number of elements in the feature vector corresponding to the communication account of the contact.

Step 406: According to the determined similarity, the terminal device selects a preset first number of communication accounts from the communication accounts of the contacts in the address book, and uses the selected communication account as the communication account to be added to all the communication accounts. The communication account of the control list mentioned above.

Optionally, when the terminal device performs step 406, it includes:

The terminal device performs the following steps for the communication account of each contact except all the second communication accounts in the address book:

Sorting the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filtering out the similarity of the preset second number with the highest value; and

Taking the average value of the similarity of the screened out second number as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

The terminal device compares the average value of the similarity between the feature vector corresponding to the communication account of each contact except all the second communication accounts in the address book and the feature vector corresponding to all the second communication accounts in the control list. Sort, and filter out the similarity average value of the first number with the highest value;

The terminal device determines the communication account of the contact corresponding to each of the filtered average similarity degrees.

Through the above steps, the terminal device can, according to the second communication account in the control list, adaptively filter out the communication accounts of other contacts in the address book except all the second communication accounts, which are related to the control list. A communication account with a higher similarity of the second communication account is recommended to the user as the communication account to be added to the control list, which meets the user's needs and improves the efficiency of the user's communication control.

Optionally, in the method for determining a communication account provided by the embodiment of the present invention, when the number of the second communication accounts is at least two, in step 405, the terminal device determines that in the second feature set, each After the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, it may further include:

The terminal device performs the following steps for each second communication account:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the highest preset third number; and

Taking the average value of the similarity of the screened out third number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

The terminal device sorts the average value of the similarity between the feature vector corresponding to each of the second communication accounts and the feature vectors corresponding to all other second communication accounts, and filters out the similarity of the fourth number with the lowest value. average value;

The terminal device determines the second communication account corresponding to each of the filtered average similarity degrees, and uses the determined second communication account as the communication account to be deleted in the control list.

Through the above steps, the terminal device can adaptively screen out a communication account with a low similarity to other second communication accounts in the control list, and recommend it to the user as the communication account to be deleted in the control list , in this way, the user can be reminded whether there is a communication account wrongly added to the control list in the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

Optionally, when the terminal device is connected to the server, and the server determines, by using the communication information between the communication accounts of every two contacts in the address book of the first communication account, When the importance index of each of the contact's communication accounts to the first communication account, then, in the communication account determination method provided by the embodiment of the present invention, in step 406, the terminal device selects the first number of communication accounts Before the account, it also includes:

receiving, by the terminal device, the importance index of the communication account of each contact to the first communication account sent by the server;

When the terminal device performs step 406, the following steps are included:

According to the determined similarity and the importance index of the communication account of each contact to the first communication account, the terminal device selects a preset among the communication accounts of the contacts in the address book. The first number of communication accounts.

Optionally, when the control list is a white list, the terminal device, according to the determined similarity, and the importance index of the communication account of each contact to the first communication account, in the From the communication accounts of the contacts in the address book, select a preset first number of communication accounts, including:

The terminal device performs the following steps for the communication account of each contact except all the second communication accounts in the address book:

Sort the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filter out the similarity of the highest preset fifth number; and

Taking the average value of the similarity of the fifth number screened out as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

The average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the control list, and the difference between the communication account of the contact and the first communication account. The product of the importance index is used as the recommendation weight of the contact;

The terminal device sorts the recommendation weights of each contact except all the second communication accounts in the address book, and filters out the first number of recommendation weights with the highest value;

The terminal device determines the communication account of the contact corresponding to each of the selected recommendation weights.

Through the above steps, when the control list is a white list, according to the second communication account in the control list, in the communication accounts of other contacts except all the second communication accounts in the address book, comprehensively Considering the similarity with the second communication account and the importance to the first communication account, adaptively filter out the similarity with the second communication account in the control list is higher, and the first communication account The communication account with high importance is recommended to the user as the communication account to be added to the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

When the control list is a blacklist, the terminal device may also comprehensively consider the similarity with the second communication account and the importance to the first communication account, and adaptively filter out the first communication account in the control list. The two communication accounts with high similarity and low importance to the first communication account are recommended to the user as the communication account to be added to the control list, which meets the needs of the user and improves the Efficiency of user control over communication.

Optionally, when the control list is a white list and the number of the second communication accounts is at least two, the terminal device receives the communication account of each contact sent by the server to the second communication account. After the importance index of a newsletter account, it also includes:

The terminal device performs the following steps for each second communication account:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the preset sixth number with the highest value; and

Taking the average value of the similarity of the screened sixth number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

The terminal device is the product of the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the importance index of the second communication account to the first communication account, as the deletion weight of the second communication account;

The terminal device sorts the deletion weights of each second communication account, and filters out the seventh number of deletion weights with the lowest value;

The terminal device determines the second communication account corresponding to each of the selected deletion weights, and uses the determined second communication account as the communication account to be deleted in the control list.

Through the above steps, when the control control list is a white list, the terminal device can comprehensively consider the similarity with other second communication accounts and the importance to the first communication account in the control list, Self-adaptively screen out a communication account with a low degree of similarity with other second communication accounts and a low importance to the first communication account, and recommend it to the user as the communication account to be deleted in the control list, so that , which can remind the user whether there is a communication account added to the control list by mistake in the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

When the control list is a blacklist, the terminal device may also comprehensively consider the similarity with other second communication accounts and the importance to the first communication account, and adaptively filter out the similarity with other second communication accounts. A communication account with a low degree of similarity and low importance to the first communication account is recommended to the user as the communication account to be deleted in the control list, so that the user can be reminded whether the control list is The wrong communication account added to the control list meets the user's needs and improves the efficiency of the user's communication control.

With the method for determining a communication account in the above-mentioned embodiment of the present invention, the terminal device can, according to the second communication account in the control list, self-adaptive among the communication accounts of other contacts in the address book except all the second communication accounts Screening out a communication account with a higher degree of similarity with the second communication account in the control list, and recommending it to the user as the communication account to be added to the control list, which meets the user's needs and improves the user's control over communication The terminal can also adaptively screen out a communication account with a lower similarity with other second communication accounts in the control list, and recommend it to the user as the communication account to be deleted in the control list, In this way, the user can be reminded whether there is a communication account wrongly added to the control list in the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

Referring to FIG. 5 , a method for determining a communication account provided by an embodiment of the present invention is applied to the communication network architecture shown in FIG. 1 , and the method is applicable to a server in the network architecture. The processing flow of the method includes:

Step 501: The server determines the communication information between the communication accounts of every two contacts in the address book, where the address book is the first communication account corresponding to a terminal device, and the communication information includes any one of the following: the The total number of communications between the communication accounts of the two contacts, the number of times the third communication account calls the fourth communication account in the communication accounts of the two contacts, the fourth communication account in the communication accounts of the two contacts the number of calls to the third communication account;

Step 502: the server generates an importance vector for the communication account of each contact in the address book according to the communication information between the communication account of the contact and the communication account including all contacts; and will generate an importance vector. All importance vectors of are combined to generate the third feature set;

Step 503: The server normalizes the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set;

Step 504: According to the fourth feature set and the preset initial value of the importance index of the communication account of each contact to the first communication account, the server calculates the value of the communication account of each contact to the first communication account. The importance index of the first communication account;

When calculating the importance index of each contact's communication account to the first communication account, traditionally, methods such as a page ranking (PageRank) method, an expert ranking (ExpertRank) method, etc. may be used.

Optionally, when the server performs step 504, the following steps are included:

According to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account, the server initially calculates the relationship between the communication account of each contact and the first communication account. Account importance index;

When the initial value of the importance index of each contact's communication account to the first communication account obtained by initial calculation is different from the preset initial value of the importance index of each contact's communication account to the first communication account , the server, according to the fourth feature set, and the importance index of each contact's communication account to the first communication account obtained by the initial calculation, continues to calculate the next time the communication account of each contact is to the described first communication account. The importance index of the first communication account is repeated until the calculated importance index of each contact's communication account to the first communication account no longer changes;

The server will calculate the importance index of the communication account of each contact that does not change to the first communication account as the final importance of the communication account of each contact to the first communication account index.

Optionally, when the server uses the PageRank method to calculate the importance index of the communication account of each contact to the first communication account, the server first calculates the value of the communication account of each contact to the first communication account. In the case of the importance index of the communication account, the importance index of the communication account of each contact obtained by the initial calculation to the first communication account satisfies the following formula 4:

R ^new =IE*(1-d)/N+d*TR*R ^old Formula 4

Wherein, R ^new is the importance index of the communication account of each contact obtained by the initial calculation to the first communication account, d is the disturbance factor, and N is the number of communication accounts of the contact in the address book, TR is the fourth feature set, and R ^old is a preset initial value of the importance index of each contact's communication account to the first communication account.

When the server subsequently iteratively calculates the importance index of each contact's communication account to the first communication account, formula 4 is still used, where R ^old is the communication of each contact obtained by the previous calculation. The importance index of the account to the first communication account; R ^new is the importance index of the communication account of each contact obtained by the current calculation to the first communication account.

Step 505: The server sends the importance index of each contact's communication account to the first communication account to the terminal device.

When step 505 is performed, the server can send the importance index of each contact's communication account to the first communication account to the terminal device only when the server is connected to the terminal device.

With the method provided by the embodiment of the present invention, after the server sends the importance index of each contact's communication account to the first communication account to the terminal device, the terminal device can control the When the list is a white list, according to the second communication account in the control list, in the communication accounts of other contacts except all the second communication accounts in the address book, comprehensively consider the similarity with the second communication account and the The importance of the first communication account, adaptively screen out a communication account with a higher similarity to the second communication account in the control list and a higher importance to the first communication account, and use it as a to-be-added communication account The communication accounts in the control list are recommended to the user, which meets the needs of the user and improves the efficiency of the user's communication control.

Based on the above embodiment, the present invention provides an example of determining a communication account. The current user's own first communication account is U, and in the terminal device corresponding to U, the saved communication account of the contact person in U's address book includes: A, B, C, D, E, F, G, H and I. After the current user enables the do not disturb mode in the terminal device, set the second communication accounts C, D and F in the address book as a whitelist, and set the do not disturb time to 9:00-17:00;

The terminal device obtains the historical communication record of U, as shown below:

2015.6.1 Monday 8:30am A call U

2015.6.1 Monday 9:24am B call U

2015.6.1 Monday 10:04am B call U

…

2016.6.5 Friday 14:20pm U call H

2015.6.6 Sat 12:45pm U call F

2015.6.6 Saturday 19:14pm H call U

2015.6.6 Saturday 20:08pm U call F

2015.6.7 Sunday 10:22am U call H

In order to save space, the embodiment of the present invention omits some communication record entries in the above-mentioned historical communication records, but it does not mean that there are only 8 communication records displayed above, and the displayed 8 communication records are part of the entries in the historical communication records.

The terminal device generates a feature vector for the communication account of each contact in the address book according to the acquired historical communication records, wherein the features in the feature vector include: between 9:00 and 17:00 : The total number of communications between U and the contact's communication account within 00, the total number of communications between U and the contact's communication account outside 9:00 to 17:00, and the call to the contact's communication account by U The number of times the contact’s communication account calls U. For example, for A, a feature vector [5, 0, 4, 1] is generated. It should be noted that the feature vector is generated based on the entire historical communication record, while Not only through the 8 communication records shown above.

A. The terminal device combines all the generated feature vectors to generate a first feature set, as shown in Table 1:

Table 1 The first feature set

Among them, one column in Table 1 is a feature, and the other is a feature vector of a contact.

B. The terminal device normalizes each feature in the first feature set to generate a second feature set. In the embodiment of the present invention, taking the linear function conversion method as an example, in this step, the terminal device performs normalization processing on any feature in the first feature set by formula 5:

公式五

Formula five

Among them, x is the value of any one of the features in the first feature set, X is the normalized result, x _min is the minimum value of the features in the first feature set, x _max is the maximum value among the features in the first feature set.

Finally, the generated second feature set is shown in Table 2:

Table 2 Second feature set

C. The terminal device determines the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account in the second feature set. In the embodiment of the present invention, taking the calculation of the Euclidean distance between two vectors as an example, in this step, the terminal device calculates the communication account number of each contact in the second feature set by formula 1 The distance between the corresponding feature vector and the feature vector corresponding to each second communication account, as shown in Table 3; and by formula 2, calculate the feature vector corresponding to the communication account of each contact and each second communication account The similarity of the corresponding feature vectors is shown in Table 4:

Table 3 The distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account

Table 4 Similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account

D1. When the terminal device is not connected to the server, according to the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, the terminal device is in the address book Among the communication accounts of the contact, a preset first number of communication accounts are selected, and the selected communication account is used as the communication account to be added to the white list.

Specifically, for the communication account of each contact except C, D and F, the terminal device executes: the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account Sort the similarity of the second number with the highest value, and the obtained results are shown in Table 5. In the embodiment of the present invention, only the second number is 1 as an example. Since the second number is 1, it is not necessary to calculate The similarity average, that is, the similarity average is equal to the filtered similarity:

table 5

The terminal device sorts the filtered similarity, filters out the first number of similarity averages with the highest value, and determines the communication account of the contact corresponding to each of the filtered similarity averages, and selects the The communication account is used as the communication account to be added to the whitelist. In the embodiment of the present invention, the first number is set to 3, and the average value of each similarity and the communication account of the corresponding contact are screened out, as shown in Table 6:

Table 6

Communication accounts A, H and I may be recommended to the user as communication accounts to be added to the white list, and the user is reminded to add to the white list.

E1. For each second communication account, the terminal device sorts the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and selects the preset value with the highest value. The similarity of the third number, and the average value of the similarity is obtained, as shown in Table 7. The embodiment of the present invention only takes the third number as 1 as an example. Since the third number is 1, it is not necessary to calculate the average similarity, that is, the average similarity is equal to the filtered similarity:

Table 7

Second communication account similarity C 0.974375 D 0.974375 F 0.756825

F1. The terminal device sorts the average value of the similarity between the feature vector corresponding to each second communication account and the feature vectors corresponding to all other second communication accounts, and selects the similarity of the fourth number with the lowest value. the average value; the terminal device determines the second communication account corresponding to each of the filtered average similarity degrees, and uses the determined second communication account as the communication account to be deleted in the white list. In the embodiment of the present invention, the fourth number is set to 2, then the average value of each similarity and the corresponding second communication account are screened out, as shown in Table 8:

Table 8

Second communication account similarity F 0.756825 D 0.974375

The communication accounts F and D may be recommended to the user as the communication accounts to be deleted in the white list, and the user is reminded to delete the white list.

D2. When the terminal device is connected to the server, the terminal device will receive the importance index to U of the communication account of each contact in the address book sent by the server; The similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, and the importance index of the communication account of each contact to U, the communication of the contacts in the address book In Accounts, select the preset first number of communication accounts.

Wherein, when the server determines the importance index to U of the communication account of each contact in the address book, it includes:

The server determines the communication information between the communication accounts of every two contacts in the address book, and the communication information includes any one of the following: the total number of communication between the communication accounts of the two contacts, the The number of times that the third communication account in the communication accounts of the two contacts calls the fourth communication account, and the number of times that the fourth communication account in the communication accounts of the two contacts calls the third communication account;

For the communication account of each contact person in the address book, the server generates an importance vector according to the communication information between the communication account of the contact person and the communication account including all contacts; The sex vectors are combined to generate a third feature set;

For example, if the communication information stored in the server, the number of times A calls B, C, D, E, F, G, H, and I are 4, 4, 6, 1, 0, 2, 0, 1, and the number of times A calls A is 0. Therefore, the importance vector generated by the server for A is [0, 4, 4, 6, 1, 0, 2, 0, 1]. Three feature sets, as shown in Table 9:

Table 9 The third feature set

Wherein, each column in Table 9 is an importance vector generated for the communication account of the contact.

The server normalizes the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set.

In this step, the server normalizes each importance vector in the third feature set, and various methods may also be used. In this embodiment of the present invention, the following method is used as an example: In the importance vector, the ratio of the communication account of the calling contact to the communication account of each called contact; still taking the importance vector generated for A as an example, the total number of times A calls the communication accounts of other contacts M=0+4+4+6+1+0+2+0+1=18, wherein, the number of times A calls B is 4, then the ratio of A calling B is X=4/18=2/9. The final generated fourth feature set is shown in Table 10:

Table 10 Fourth feature set

The server calculates the importance index of each contact's communication account to U according to the fourth feature set and a preset initial value of the importance index of each contact's communication account to U.

Since there are many traditional methods for calculating the importance index, in the embodiment of the present invention, only the PageRank method is used as an example. Assuming that the preset initial value of the importance index of each contact's communication account to U is 1/9, the column vector composed of the initial value of the importance index of each contact's communication account to U is R ⁱⁿⁱ =[ 1/9,1/9,1/9,1/9,1/9,1/9,1/9,1/9,1/9] ^T , then according to the fourth feature set, and R ⁱⁿⁱ , calculate the importance index of each contact’s communication account to U for the first time according to formula 4, R ^new =IE*(1-d)/N+d*TR*R ⁱⁿⁱ , where d is the disturbance factor, and the The value is specifically set according to the specific application scenario. In the embodiment of the present invention, only 0.85 is taken as an example, N is the number of communication accounts of the contacts in the address book, obviously N=9, and TR is the fourth feature Set, unit vector IE=[1,1,1,1,1,1,1,1,1] ^T , then

It can be obtained that the column vector composed of the importance index of each contact's communication account to the first communication account obtained by the initial calculation is:

R ^new = [0.094, 0.079, 0.189, 0.206, 0.037, 0.111, 0.062, 0.111, 0.111] ^T

Because R ^new is different from the preset column vector composed of the initial value of the importance index of each contact's communication account to the first communication account, the server calculates according to the fourth feature set and the The importance index of the communication account of each contact to the first communication account, continue to calculate the importance index of the communication account of each contact to the first communication account next time, and repeat this until every calculated The importance index of each contact's communication account to the first communication account does not change. In the iterative process, the importance index of each contact's communication account to the first communication account calculated each time is shown in Table 11:

Table 11

As can be seen from the above table, the importance index of the communication account of each contact obtained in the sixth iteration to the first communication account and the communication account of each contact calculated in the seventh iteration are the same as the first communication account. The importance index of a communication account is the same and will not change. Therefore, when the iteration is stopped, the result obtained by the sixth or seventh calculation can be the final importance index of the communication account of each contact to U, such as Table 12 shows:

Table 12

The server sends the importance index of each contact's communication account to U to the terminal device.

According to the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, and the importance index of the communication account of each contact to U, the terminal device is used in the communication From the communication accounts of the contacts in the list, select the preset first number of communication accounts, including:

Specifically, the terminal device performs for the communication account of each contact except C, D and F: the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account Sort the similarity of the fifth number with the highest value, and the obtained results are shown in Table 13. In the embodiment of the present invention, only the fifth number is 1 as an example. Since the fifth number is 1, it is not necessary to calculate The similarity average, that is, the similarity average is equal to the filtered similarity:

Table 13

The terminal device is the product of the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the whitelist, and the importance index of the communication account of the contact to U , as the recommendation weight of the contact, as shown in Table 14:

Table 14

The terminal device sorts the recommendation weights of each contact except all the second communication accounts in the address book, and filters out the first number of recommendation weights with the highest value; The communication account of the contact corresponding to the recommendation weight. The screened recommendation weights and the corresponding communication accounts of the contacts are shown in Table 15:

Table 15

Contact's communication account Recommendation weight I 0.15790625 H 0.10753125 A 0.070155

The communication accounts I, H and A can be recommended to the user as the communication accounts to be added to the white list, and the user is reminded to add to the white list.

E2. For each second communication account, the terminal device sorts the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and selects the preset with the highest value. The similarity of the sixth number; and the average of the similarity is calculated, as shown in Table 16. In this embodiment, the sixth number is 1, so it is not necessary to calculate the average value of the similarity, that is, the average value of the similarity is equal to the selected similarity.

Table 16

Second communication account similarity C 0.974375 D 0.974375 F 0.756825

F2. The terminal device is the product of the average similarity of the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the importance index of the second communication account to U, as the first communication account. The deletion weight of the second communication account is shown in Table 17:

Table 17

Second communication account similarity Importance Index remove weight C 0.974375 0.209 0.2036444 D 0.974375 0.201 0.13894125 F 0.756825 0.111 0.08400758

G2. The terminal device sorts the deletion weights of each second communication account, and filters out the seventh number of deletion weights with the lowest value; the terminal device determines the second deletion weight corresponding to each selected deletion weight. communication account, and use the determined second communication account as the communication account to be deleted in the white list. In the embodiment of the present invention, the seventh number is 2, then the filtered deletion weight, and the corresponding second communication account number, are as shown in Table 18:

Table 18

Second communication account remove weight F 0.08400758 D 0.13894125

The communication accounts F and D may be recommended to the user as the communication accounts to be deleted in the white list, and the user is reminded to delete the white list.

By using the communication account determination method provided by the embodiment of the present invention, the terminal device corresponding to the first communication account can, according to the second communication account in the control list, store the communication accounts of other contacts in the address book except for all the second communication accounts , adaptively screen out a communication account with a higher degree of similarity with the second communication account in the control list, and recommend it to the user as the communication account to be added to the control list, which meets the needs of the user and improves the performance. Efficiency of communication control by the user; the terminal can also adaptively screen out a communication account with a lower similarity to other second communication accounts in the control list, and use it as the communication account to be deleted in the control list Recommended to the user, in this way, the user can be reminded whether there is a communication account wrongly added to the control list in the control list, which meets the needs of the user and improves the efficiency of the user's communication control. When the control list is a white list, and the terminal device can obtain the importance index of the communication account of each contact in the address book to the first communication account, the terminal device comprehensively considers the similarity with the second communication account. degree and importance to the first communication account, adaptively screen out the communication account that has a higher similarity with the second communication account in the control list and is more important to the first communication account , and recommend it to the user as the communication account to be added to the control list, and comprehensively consider the similarity with other second communication accounts and the importance to the first communication account, and adaptively filter out other second communication accounts. A communication account with a low degree of similarity of accounts and low importance to the first communication account is recommended to the user as the communication account to be deleted in the control list, so that the user can be reminded of the control list Whether there is a communication account added to the control list by mistake, it meets the needs of the user and improves the efficiency of the user's communication control.

Based on the above embodiments, the present invention also provides a terminal device, which is used for the communication account determination method shown in FIG. 4 . As shown in FIG. 6 , the terminal device 600 includes: The Do Not Disturb management module 601, the control list storage module 602, the communication filtering module 603, and the smart list recommendation module in the foreground, and the Do Not Disturb setting information receiving module 605, the processing module 606, and the smart list generation module 607 located in the background of the terminal device 600, in,

The Do Not Disturb management module 601 is used to enable the user to perform Do Not Disturb settings on the terminal device 600, and the user interacts with the Do Not Disturb management module 601 through a user interface (User Interface, UI), and the Do Not Disturb management module 601 Specifically, it includes the following sub-modules:

Do not disturb control module 6011, for enabling the do not disturb function of the terminal device 600;

The Do Not Disturb setting module 6012 is used to set the Do Not Disturb setting information such as the Do Not Disturb time and the Do Not Disturb location after the user enables the Do Not Disturb function through the Do Not Disturb control module 6011;

The control list maintenance module 6014 is used to enable the user to add a communication account to the control list, and to manage the control list;

The intelligent control list triggering module 6013 is used to enable the user to activate the intelligent control list recommendation function of the terminal device 600 when the control list contains at least one communication account after the user enables the do not disturb function and sets the do not disturb setting information, and sends the user to the terminal device 600. The user recommends communication accounts to be added to the control list and communication accounts to be deleted from the control list.

The control list storage module 602 is used for storing the control list set by the user.

The communication filtering module 603, when the control list is a blacklist, is used to prohibit the communication accounts in the blacklist from communicating with the terminal device 600 within the do not disturb time; when the control list is a whitelist , for allowing only the communication accounts in the whitelist to communicate with the terminal device 600 during the do not disturb time.

The Do Not Disturb setting information receiving module 605 is configured to receive Do Not Disturb setting information, such as Do Not Disturb time, Do Not Disturb location, etc., sent by the Do Not Disturb management module 601 in the terminal device 600 .

The processing module 606 is configured to obtain the historical communication record of the first communication account corresponding to the terminal device 600 and the corresponding account information of the communication account of each contact in the address book when the terminal device 600 is connected to the server etc., to generate the similarity between the communication account of each contact and each communication account in the control list.

The intelligent list generation module 607 is used to select the communication accounts to be added to the The communication account of the control list, and the communication account to be deleted in the control list is selected from the control list.

When the terminal device 600 is connected to the server, the server receives the do not disturb setting information of the terminal device 600, and determines the communication information between the communication accounts of every two contacts in the address book, and finally generates a The importance index of each contact's communication account to the first communication account, and the generated importance index of each contact's communication account to the first communication account is sent to the terminal device 600. Processing module 606 .

The processing module 606 is further configured to receive the importance index of each contact's communication account to the first communication account sent by the server, and according to each contact's communication account and the information in the control list. The similarity of each communication account, the importance index of the communication account of each contact to the first communication account, calculating the recommendation weight of the communication account of each contact except the control list in the address book, and the Controls the deletion weight of each communication account in the list.

The intelligent list generation module 607 is further configured to select the communication accounts to be added to the control list from among the communication accounts of the contacts in the address book according to the recommendation weight of the communication accounts of each contact person in the address book except the control list. The communication accounts in the control list are selected, and according to the deletion weight of each communication account in the control list, the communication accounts to be deleted in the control list are selected in the control list.

The intelligent list recommendation module 604 is used for recommending the communication accounts to be added to the control list generated by the intelligent list generation module 607 and the communication accounts to be deleted in the control list to the control list maintenance module 6014, Reminders to add or delete control lists.

Based on the above embodiment, the present invention also provides a terminal device. As shown in FIG. 7 , the terminal device 700 includes: an acquisition unit 701, a processing unit 702, and a selection unit 703, wherein,

The obtaining unit 701 is configured to obtain a set control list, the control list is set for the first communication account corresponding to the terminal device 700, including at least one second communication account, and the control list is a blacklist or a whitelist , each second communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device 700; and

obtaining the historical communication record of the first communication account;

The processing unit 702 is configured to generate a feature vector for the communication account of each contact person in the address book according to the obtained historical communication record, wherein the feature in the feature vector includes any one of the following or Combination: the number of times the first communication account calls the contact's communication account, the number of times the contact's communication account calls the first communication account, and the number of times between the first communication account and the contact's communication account. the total number of communications; and combine all the generated feature vectors to generate the first feature set; and

normalizing each of the features in the first feature set to generate a second feature set; and

Determine, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

The selection unit 703 is configured to, according to the determined similarity, select a preset first number of communication accounts from among the communication accounts of the contacts of the address book, and use the selected communication account as the communication account to be added to the Communication accounts that control the list.

Optionally, the obtaining unit 701 is further configured to: obtain the set do not disturb time before generating the feature vector for the communication account of each contact in the address book;

The processing unit 702, when generating a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, is specifically used for:

According to the obtained historical communication record and the Do Not Disturb time, a feature vector is generated for the communication account of each contact in the address book;

The features in the feature vector also include any one or a combination of the following: the number of times the first communication account calls the contact's communication account during the do not disturb time, the first communication account outside the do not disturb time. The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account within the do not disturb time, the number of times the communication account of the contact calls the first communication account outside the do not disturb time. The number of times of the first communication account, the total number of communication between the first communication account and the contact's communication account during the do not disturb time, and the first communication account and the contact outside the do not disturb time. The total number of communications between the contact's communications accounts.

Optionally, the obtaining unit 701 is further configured to: before generating a feature vector for the communication account of each contact in the address book, obtain the correspondence of the communication account of each contact in the address book. The account information, the account information includes any one or a combination of the following: a contact identifier, a work unit identifier to which the contact belongs, and a group identifier to which the contact belongs;

The processing unit 702, when generating a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, is specifically used for:

Converting each of the account information includes: converting the contact identifier in each of the account information into a digital number according to the preset correspondence between the contact identifier and the digital number; and according to the preset work of the contact person The corresponding relationship between the unit identification and the numerical number, converting the work unit identification of the contact person in each of the account information into a numerical number; and according to the preset correspondence between the group identification to which the contact person belongs and the numerical number, each The group identification to which the contact person belongs in the account information is converted into a numerical number;

According to the obtained historical communication records and the converted account information, a feature vector is generated for each contact communication account in the address book;

The features in the feature vector further include: the digital number converted from the contact identifier, the converted digital number from the work unit identifier to which the contact belongs, and the converted digital number from the group identifier to which the contact belongs.

Optionally, the processing unit 702, when determining, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts. , specifically for:

Calculate, in the second feature set, the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts;

According to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, determine the feature vector corresponding to the communication account of each contact and each The similarity of the feature vector corresponding to the second communication account.

Optionally, the processing unit 702 determines each of the contacts according to the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts. When the similarity between the feature vector corresponding to the communication account and the feature vector corresponding to each of the second communication accounts is specifically used for:

For the distance between the feature vector corresponding to the communication account of each of the contacts and the corresponding feature vector of each of the second communication accounts, the following steps are performed:

Taking the quotient of the number of features in the feature vector corresponding to the distance and the communication account of the contact as a similarity parameter;

The difference between 1 and the similarity parameter is taken as the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account.

Optionally, the selection unit 703 is specifically configured to:

For the communication accounts of each contact in the address book except all the second communication accounts, perform the following steps:

Sorting the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filtering out the similarity of the preset second number with the highest value; and

Taking the average value of the similarity of the screened out second number as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

Sort the feature vectors corresponding to the communication accounts of each contact person except all second communication accounts in the address book and the average similarity of the feature vectors corresponding to all the second communication accounts in the control list, and filter out taking the mean value of the similarity of the first number with the highest value; and

Determine the communication account of the contact corresponding to each of the filtered average similarity degrees.

Optionally, when the number of the second communication accounts is at least two, the selection unit 703 is further configured to:

After the processing unit 702 determines the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account in the second feature set, for each second communication account, Perform the following steps:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the highest preset third number; and

Taking the average value of the similarity of the screened out third number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

Sorting the average value of the similarity between the feature vector corresponding to each of the second communication accounts and the feature vectors corresponding to all other second communication accounts, and filtering out the average value of the similarity of the fourth number with the lowest value; and

Determining the second communication account corresponding to each of the filtered average similarity degrees, and using the determined second communication account as the communication account to be deleted in the control list.

Optionally, the obtaining unit 701 is further configured to:

Before the selection unit 703 selects the first number of communication accounts, receive the importance index of the communication account of each of the contacts sent by the server to the first communication account;

The selecting unit 703, when selecting a preset first number of communication accounts among the communication accounts of the contacts in the address book according to the determined similarity, is specifically used for:

According to the determined similarity and the importance index of the communication account of each contact to the first communication account, among the communication accounts of the contacts in the address book, a preset first number of communication accounts are selected. communication account.

Optionally, when the control list is a white list, the selection unit 703 is specifically configured to:

For the communication accounts of each contact in the address book except all the second communication accounts, perform the following steps:

Sort the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filter out the similarity of the highest preset fifth number; and

Taking the average value of the similarity of the fifth number screened out as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list;

The average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the control list, and the value of the importance index of the communication account of the contact to the first communication account. The product is used as the recommendation weight of the contact;

Sorting the recommendation weights of each contact except all the second communication accounts in the address book, and filtering out the first number of recommendation weights with the highest value; and

The communication account of the contact corresponding to each of the selected recommendation weights is determined.

Optionally, when the control list is a white list and the number of the second communication accounts is at least two, the selection unit 703 is further configured to:

After the obtaining unit 701 receives the importance index of each contact's communication account to the first communication account sent by the server, the following steps are performed for each second communication account:

Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the preset sixth number with the highest value; and

Taking the average value of the similarity of the screened sixth number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts;

The average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the product of the importance index of the second communication account to the first communication account, as the second communication account. The deletion weight of the communication account;

Sort the deletion weights of each second communication account, and filter out the seventh number of deletion weights with the lowest value; and

A second communication account corresponding to each of the selected deletion weights is determined, and the determined second communication account is used as the communication account to be deleted in the control list.

Using the terminal device provided in the embodiment of the present invention, the terminal device can adaptively filter out the communication accounts of other contacts except all the second communication accounts in the address book according to the second communication account in the control list. A communication account with a higher similarity of the second communication account in the control list is recommended to the user as the communication account to be added to the control list, which meets the user's needs and improves the efficiency of the user's communication control; The terminal may also adaptively screen out a communication account with a lower similarity with other second communication accounts in the control list, and recommend it to the user as the communication account to be deleted in the control list, so that it can be The user is reminded whether there is a communication account wrongly added to the control list in the control list, which meets the needs of the user and improves the efficiency of the user's communication control.

Based on the above embodiment, an embodiment of the present invention further provides a server. As shown in FIG. 8 , the server 800 includes: a determining unit 801, a processing unit 802, and a sending unit 803, wherein,

The determining unit 801 is configured to determine the communication information between the communication accounts of every two contacts in the address book, where the address book is the first communication account corresponding to a terminal device, and the communication information includes any one of the following : the total number of communication between the communication accounts of the two contacts, the number of times the third communication account calls the fourth communication account in the communication accounts of the two contacts, the fourth communication account in the communication accounts of the two contacts The number of times the communication account calls the third communication account;

The processing unit 802 is used to generate an importance vector for the communication account of each contact person in the address book according to the communication information between the communication account of the contact person and the communication account including all contacts; and will generate an importance vector All importance vectors of are combined to generate a third feature set; and

Normalizing the importance vector corresponding to the communication account of each contact in the third feature set to generate a fourth feature set; and

Calculate the importance of each contact's communication account to the first communication account according to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account Sex index;

The sending unit 803 is configured to send the importance index of each contact's communication account to the first communication account to the terminal device.

Optionally, when calculating the importance index of the communication account of each contact to the first communication account, the processing unit 802 is specifically used for:

According to the fourth feature set and the preset initial value of the importance index of each contact's communication account to the first communication account, the importance of each contact's communication account to the first communication account is initially calculated. Sex index;

When the initial value of the importance index of each contact's communication account to the first communication account obtained by initial calculation is different from the preset initial value of the importance index of each contact's communication account to the first communication account , according to the fourth feature set, and the importance index of the communication account of each contact person to the first communication account obtained by the initial calculation, continue to calculate the communication account of each contact person to the first communication account next time The importance index of the account is repeated until the calculated importance index of each contact's communication account to the first communication account no longer changes;

The calculated importance index of each contact's communication account to the first communication account that does not change is used as the final importance index of each contact's communication account to the first communication account.

Optionally, when the processing unit 802 initially calculates the importance index of each contact's communication account to the first communication account, the first communication The importance index of the account, which satisfies the following formula:

R ^new =IE*(1-d)/N+d*TR*R ^old

Wherein, R ^new is the importance index of the communication account of each contact obtained by the initial calculation to the first communication account, d is the disturbance factor, and N is the number of communication accounts of the contact in the address book, TR is the fourth feature set, and R ^old is a preset initial value of the importance index of each contact's communication account to the first communication account.

With the server provided in the embodiment of the present invention, after the server sends the importance index of each contact's communication account to the first communication account to the terminal device, the terminal device can control the When the list is a white list, according to the second communication account in the control list, in the communication accounts of other contacts except all the second communication accounts in the address book, comprehensively consider the similarity with the second communication account and the The importance of the first communication account, adaptively screen out a communication account with a higher similarity to the second communication account in the control list and a higher importance to the first communication account, and use it as a to-be-added communication account The communication accounts in the control list are recommended to the user, which meets the needs of the user and improves the efficiency of the user's communication control.

It should be noted that, the division of units in the embodiment of the present invention is schematic, and is only a logical function division, and there may be other division manners in actual implementation. Each functional unit in the embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

To sum up, with the method, terminal device, and server for determining a communication account provided by the embodiments of the present invention, the terminal device may, according to the second communication account in the control list, contact other contacts in the address book except for all the second communication accounts. Among the personal communication accounts, adaptively screen out a communication account with a higher degree of similarity with the second communication account in the control list, and recommend it to the user as the communication account to be added to the control list, which meets the needs of the user , and improve the efficiency of the user's communication control; the terminal can also adaptively screen out the communication accounts with low similarity with other second communication accounts in the control list, and use them as the waiting list in the control list. The deleted communication account is recommended to the user, so that the user can be reminded whether there is a communication account added to the control list by mistake in the control list, which meets the needs of the user and improves the efficiency of the user's communication control; further, After the server sends the importance index of each contact's communication account to the first communication account to the terminal device, the terminal device can, when the control list is a white list, The second communication account in the address book, among the communication accounts of other contacts except all the second communication accounts in the address book, comprehensively consider the similarity with the second communication account and the importance to the first communication account, automatically Adaptively screen out a communication account with a higher similarity to the second communication account in the control list and a higher importance to the first communication account, and recommend it as a communication account to be added to the control list For users, it meets the needs of users, and improves the efficiency of users' control of communication.

Although the preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of the present invention.

Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, provided that these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (20)

1. A method for determining a communication account, comprising: The terminal device obtains a set control list, the control list is set for the first communication account corresponding to the terminal device, and includes at least one second communication account, and the control list is a blacklist or a whitelist, and each second The communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device; obtaining, by the terminal device, a historical communication record of the first communication account; The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, wherein the feature in the feature vector includes any one or combination of the following: The number of times the first communication account calls the contact's communication account, the number of times the contact's communication account calls the first communication account, and the total communication between the first communication account and the contact's communication account times; and combine all the generated feature vectors to generate the first feature set; The terminal device performs normalization processing on each of the features in the first feature set to generate a second feature set; The terminal device determines, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts; According to the determined similarity, the terminal device selects a preset first number of communication accounts among the communication accounts of the contacts in the address book, and uses the selected communication accounts as the communication accounts to be added to the control list. communication account. 2. The method according to claim 1, wherein before the terminal device generates a feature vector for the communication account of each contact person in the address book, the method further comprises: The terminal device obtains the set Do Not Disturb time; The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, including: The terminal device generates a feature vector for the communication account of each contact in the address book according to the acquired historical communication record and the do not disturb time; The features in the feature vector also include any one or a combination of the following: the number of times the first communication account calls the contact's communication account during the do not disturb time, the first communication account outside the do not disturb time. The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account within the do not disturb time, the number of times the communication account of the contact calls the first communication account outside the do not disturb time. The number of times of the first communication account, the total number of communication between the first communication account and the contact's communication account during the do not disturb time, and the first communication account and the contact outside the do not disturb time. The total number of communications between the contact's communications accounts. 3. The method according to claim 1 or 2, wherein before the terminal device generates a feature vector for the communication account of each contact person in the address book, the method further comprises: The terminal device obtains the corresponding account information of the communication account of each contact in the address book, and the account information includes any one or a combination of the following: a contact identifier, an identifier of the work unit to which the contact belongs, and a group to which the contact belongs. group ID; The terminal device generates a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, including: Converting each of the account information by the terminal device includes: converting, by the terminal device, the contact identifier in each of the account information into a digital number according to a preset correspondence between the contact identifier and the digital number; and According to the preset correspondence between the identification of the work unit to which the contact belongs and the numerical number, the identification of the work unit to which the contact belongs in each of the account information is converted into a numerical number; and according to the preset identification of the group to which the contact belongs and the number The corresponding relationship of the numbers, converting the group identification to which the contact person belongs in each described account information into a digital number; The terminal device generates a feature vector for each contact communication account in the address book according to the obtained historical communication record and the converted information of each account; The features in the feature vector further include: the digital number converted from the contact identifier, the converted digital number from the work unit identifier to which the contact belongs, and the converted digital number from the group identifier to which the contact belongs. 4. The method according to claim 1 or 2, wherein the terminal device determines that in the second feature set, the feature vector corresponding to the communication account of each contact is the same as that of each second feature set. The similarity of the feature vector corresponding to the communication account, including: The terminal device calculates, in the second feature set, the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts; The terminal device determines the feature vector corresponding to the communication account of each contact according to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each of the second communication accounts Similarity of feature vectors corresponding to each of the second communication accounts. 5. The method of claim 4, wherein the terminal device is based on the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts , determine the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts, including: The terminal device performs the following steps for the distance between the feature vector corresponding to the communication account of each of the contacts and the corresponding feature vector of each of the second communication accounts: Taking the quotient of the number of features in the feature vector corresponding to the distance and the communication account of the contact as a similarity parameter; The difference between 1 and the similarity parameter is taken as the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account. 6. The method according to any one of claims 1, 2, and 5, wherein, according to the determined similarity, the terminal device selects a preset in the communication account of the contact person in the address book. Set the first number of communication accounts, including: The terminal device performs the following steps for the communication account of each contact except all the second communication accounts in the address book: Sorting the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filtering out the similarity of the preset second number with the highest value; and Taking the average value of the similarity of the screened out second number as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list; The terminal device compares the average value of the similarity between the feature vector corresponding to the communication account of each contact except all the second communication accounts in the address book and the feature vector corresponding to all the second communication accounts in the control list. Sorting, filtering out the average similarity of the first number with the highest value; The terminal device determines the communication account of the contact corresponding to each of the filtered average similarity degrees. 7. The method according to any one of claims 1, 2, and 5, wherein when the number of the second communication accounts is at least two, the terminal device determines that the second feature In the concentration, after the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, it also includes: The terminal device performs the following steps for each second communication account: Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the highest preset third number; and Taking the average value of the similarity of the screened out third number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts; The terminal device sorts the average similarity of the feature vector corresponding to each of the second communication accounts and the feature vectors corresponding to all other second communication accounts, and selects the average similarity of the fourth number with the lowest value. ; The terminal device determines the second communication account corresponding to each of the filtered average similarity degrees, and uses the determined second communication account as the communication account to be deleted in the control list. 8. The method according to any one of claims 1, 2, and 5, wherein before the terminal device selects the first number of communication accounts, the method further comprises: receiving, by the terminal device, the importance index of the communication account of each contact to the first communication account sent by the server; According to the determined similarity, the terminal device selects a preset first number of communication accounts among the communication accounts of the contacts in the address book, including: According to the determined similarity and the importance index of the communication account of each contact to the first communication account, the terminal device selects a preset among the communication accounts of the contacts in the address book. The first number of communication accounts. 9 . The method according to claim 8 , wherein when the control list is a white list, the terminal device determines the similarity according to the determined similarity and the communication account of each of the contacts to the The importance index of the first communication account, among the communication accounts of the contacts in the address book, selecting a preset first number of communication accounts, including: The terminal device performs the following steps for the communication account of each contact except all the second communication accounts in the address book: Sort the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filter out the similarity of the highest preset fifth number; and Taking the average value of the similarity of the fifth number screened out as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list; The average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the control list, and the difference between the communication account of the contact and the first communication account. The product of the importance index is used as the recommendation weight of the contact; The terminal device sorts the recommendation weights of each contact except all the second communication accounts in the address book, and filters out the first number of recommendation weights with the highest value; The terminal device determines the communication account of the contact corresponding to each of the selected recommendation weights. 10. The method according to claim 8, wherein when the control list is a white list and the number of the second communication accounts is at least two, the terminal device receives the information sent by the server. After the importance index of the communication account of each contact to the first communication account, it also includes: The terminal device performs the following steps for each second communication account: Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the preset sixth number with the highest value; and Taking the average value of the similarity of the screened sixth number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts; The terminal device is the product of the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the importance index of the second communication account to the first communication account, as the deletion weight of the second communication account; The terminal device sorts the deletion weights of each second communication account, and filters out the seventh number of deletion weights with the lowest value; The terminal device determines the second communication account corresponding to each of the selected deletion weights, and uses the determined second communication account as the communication account to be deleted in the control list. 11. A terminal device, comprising: The obtaining unit is configured to obtain a set control list, the control list is set for the first communication account corresponding to the terminal device, and includes at least one second communication account, and the control list is a blacklist or a whitelist, and each control list is a blacklist or a whitelist. A second communication account is the communication account of the contact person in the address book of the first communication account saved by the terminal device; and obtaining the historical communication record of the first communication account; A processing unit, configured to generate a feature vector for the communication account of each contact person in the address book according to the obtained historical communication record, wherein the feature in the feature vector includes any one or combination of the following : the number of times the first communication account calls the contact’s communication account, the number of times the contact’s communication account calls the first communication account, and the total number of times between the first communication account and the contact’s communication account the number of communications; and combine all the generated feature vectors to generate the first feature set; and normalizing each of the features in the first feature set to generate a second feature set; and Determine, in the second feature set, the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts; A selection unit, configured to select a preset first number of communication accounts from among the communication accounts of the contacts in the address book according to the determined similarity, and use the selected communication account as a communication account to be added to the control List of communication accounts. 12 . The terminal device according to claim 11 , wherein the obtaining unit is further configured to: obtain the set information before generating a feature vector for the communication account of each contact person in the address book. 13 . disturbance time; The processing unit, when generating a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, is specifically used for: According to the obtained historical communication record and the Do Not Disturb time, a feature vector is generated for the communication account of each contact in the address book; The features in the feature vector also include any one or a combination of the following: the number of times the first communication account calls the contact's communication account during the do not disturb time, the first communication account outside the do not disturb time. The number of times the communication account calls the communication account of the contact, the number of times the communication account of the contact calls the first communication account within the do not disturb time, the number of times the communication account of the contact calls the first communication account outside the do not disturb time. The number of times of the first communication account, the total number of communication between the first communication account and the contact's communication account during the do not disturb time, and the first communication account and the contact outside the do not disturb time. The total number of communications between the contact's communications accounts. 13. The terminal device according to claim 11 or 12, wherein the obtaining unit is further configured to: obtain all the communication accounts of each contact in the address book before generating a feature vector The corresponding account information of the communication account of each contact in the address book, the account information includes any one or combination of the following: a contact identifier, a work unit identifier to which the contact belongs, and a group identifier to which the contact belongs; The processing unit, when generating a feature vector for the communication account of each contact person in the address book according to the acquired historical communication record, is specifically used for: Converting each of the account information includes: converting the contact identifier in each of the account information into a digital number according to the preset correspondence between the contact identifier and the digital number; and according to the preset work of the contact person The corresponding relationship between the unit identification and the numerical number, converting the work unit identification of the contact person in each of the account information into a numerical number; and according to the preset correspondence between the group identification to which the contact person belongs and the numerical number, each The group identification to which the contact person belongs in the account information is converted into a numerical number; According to the obtained historical communication records and the converted account information, a feature vector is generated for each contact communication account in the address book; The features in the feature vector further include: the digital number converted from the contact identifier, the converted digital number from the work unit identifier to which the contact belongs, and the converted digital number from the group identifier to which the contact belongs. 14. The terminal device according to claim 11 or 12, wherein, when the processing unit determines that in the second feature set, the feature vector corresponding to the communication account of each of the contacts is the same as the feature vector of each of the contacts. When the similarity of feature vectors corresponding to a second communication account is used, it is specifically used for: Calculate, in the second feature set, the distance between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts; According to the distance between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account, determine the feature vector corresponding to the communication account of each contact and each The similarity of the feature vector corresponding to the second communication account. 15 . The terminal device according to claim 14 , wherein the processing unit is based on the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts. 15 . When determining the similarity between the feature vector corresponding to the communication account of each of the contacts and the feature vector corresponding to each of the second communication accounts, it is specifically used for: For the distance between the feature vector corresponding to the communication account of each of the contacts and the corresponding feature vector of each of the second communication accounts, the following steps are performed: Taking the quotient of the number of features in the feature vector corresponding to the distance and the communication account of the contact as a similarity parameter; The difference between 1 and the similarity parameter is taken as the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to the second communication account. 16. The terminal device according to any one of claims 11, 12, and 15, wherein the selection unit is specifically configured to: For the communication accounts of each contact in the address book except all the second communication accounts, perform the following steps: Sorting the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filtering out the similarity of the preset second number with the highest value; and Taking the average value of the similarity of the screened out second number as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list; Sort the feature vectors corresponding to the communication accounts of each contact person except all second communication accounts in the address book and the average similarity of the feature vectors corresponding to all the second communication accounts in the control list, and filter out taking the mean value of the similarity of the first number with the highest value; and Determine the communication account of the contact corresponding to each of the filtered average similarity degrees. 17. The terminal device according to any one of claims 11, 12, and 15, wherein when the number of the second communication accounts is at least two, the selection unit is further configured to: After the processing unit determines the similarity between the feature vector corresponding to the communication account of each contact and the feature vector corresponding to each second communication account in the second feature set, for each second communication account, execute The following steps: Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the highest preset third number; and Taking the average value of the similarity of the screened out third number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts; Sorting the average value of the similarity between the feature vector corresponding to each of the second communication accounts and the feature vectors corresponding to all other second communication accounts, and filtering out the average value of the similarity of the fourth number with the lowest value; and Determining the second communication account corresponding to each of the filtered average similarity degrees, and using the determined second communication account as the communication account to be deleted in the control list. 18. The terminal device according to any one of claims 11, 12, and 15, wherein the acquiring unit is further configured to: before the selection unit selects the first number of communication accounts, receiving the importance index of the communication account of each contact to the first communication account sent by the server; The selection unit, when selecting a preset first number of communication accounts among the communication accounts of the contacts in the address book according to the determined similarity, is specifically used for: According to the determined similarity and the importance index of the communication account of each contact to the first communication account, among the communication accounts of the contacts in the address book, a preset first number of communication accounts are selected. communication account. 19. The terminal device according to claim 18, wherein when the control list is a white list, the selection unit is specifically configured to: For the communication accounts of each contact in the address book except all the second communication accounts, perform the following steps: Sort the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to each second communication account, and filter out the similarity of the highest preset fifth number; and Taking the average value of the similarity of the fifth number screened out as the average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vector corresponding to all the second communication accounts in the control list; The average value of the similarity between the feature vector corresponding to the communication account of the contact and the feature vectors corresponding to all the second communication accounts in the control list, and the value of the importance index of the communication account of the contact to the first communication account. The product is used as the recommendation weight of the contact; Sorting the recommendation weights of each contact except all the second communication accounts in the address book, and filtering out the first number of recommendation weights with the highest value; and The communication account of the contact corresponding to each of the selected recommendation weights is determined. 20. The terminal device according to claim 18, wherein when the control list is a white list and the number of the second communication accounts is at least two, the selection unit is further configured to: After the obtaining unit receives the importance index of each contact's communication account to the first communication account sent by the server, the following steps are performed for each second communication account: Sorting the similarity between the feature vector corresponding to the second communication account and the feature vector corresponding to each other second communication account, and filtering out the similarity of the preset sixth number with the highest value; and Taking the average value of the similarity of the screened sixth number as the average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts; The average value of the similarity between the feature vector corresponding to the second communication account and the feature vectors corresponding to all other second communication accounts, and the product of the importance index of the second communication account to the first communication account, as the second communication account. The deletion weight of the communication account; Sort the deletion weights of each second communication account, and filter out the seventh number of deletion weights with the lowest value; and A second communication account corresponding to each of the selected deletion weights is determined, and the determined second communication account is used as the communication account to be deleted in the control list.

Images