CN112492534B - Message processing method, device and equipment - Google Patents

Abstract

Embodiments of the present application provide a message processing method, apparatus, and device, including: determining a second message set in a first message set, where the messages in the second message set are of a preset type; according to the second message set The second message set is divided into at least one third message set, and the similarity between the messages in the third message set is greater than or equal to the first threshold; obtain the A first account corresponding to each message in the third message set; determining the number of first messages corresponding to each first account in the first message set, and the number of first accounts corresponding to the first account in the third message set The second number of messages, the number of third messages included in the third message set, and the target account are determined in the account set, and the account set includes accounts corresponding to the messages in the second message set. This improves the operator's identification accuracy for mobile phone numbers that send spam text messages.

Description

Message processing method, device and device

technical field

The present application relates to the field of communication technologies, and in particular, to a message processing method, apparatus, and device.

Background technique

At present, the senders of spam messages usually hold a large number of mobile phone cards, and in order to improve the efficiency of sending spam messages, the same phone card is usually used to send spam messages with similar text content. Banned to prevent users from receiving a large number of spam text messages on their mobile phones.

In the prior art, the operator usually determines the mobile phone number to be banned according to the number of spam short messages sent by the mobile phone number within a period of time. For example, within an hour, when the number of spam text messages sent by the same mobile phone number is greater than the preset value, the operator will block the mobile phone number. However, in order to avoid the wrong blocking of mobile phone numbers, the preset value set by the operator is usually larger, and the sender of spam messages will ensure that the number of spam messages sent by the same mobile phone number is less than the preset value set by the operator within an hour. The value of this value makes the sending number of the spam short message unrecognized by the operator in a short period of time, which in turn causes the operator to have a low identification accuracy of the mobile phone number that sends the spam short message.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a message processing method, apparatus, and device, which are used to solve the technical problem in the prior art that the identification accuracy of mobile phone numbers of spam short messages is low.

In a first aspect, an embodiment of the present application provides a message processing method, which includes:

determining a second message set in the first message set, the first message set includes messages received by at least one terminal device within a preset time period, and the messages in the second message set are of a preset type;

According to the similarity between the messages in the second message set, the second message set is divided into at least one third message set, and the similarity between the messages in the third message set is greater than or equal to first threshold;

obtaining a first account corresponding to each message in the third message set, where the first account is an account used by the terminal device to send the message;

In the first message set, determine the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, and the number of messages included in the third message set For the third number of messages, the target account is determined in the account set, and the account set includes the accounts corresponding to the messages in the second message set.

In a possible implementation manner, according to the similarity between the messages in the second message set, the second message set is divided into at least one third message set, including:

obtaining the similarity between the messages in the second message set;

According to the similarity, clustering processing is performed on the messages in the second message set, so as to divide the second message set into at least one third message set.

In a possible implementation manner, acquiring the similarity between the messages in the second message set includes:

Acquire character attributes of each message in the second message set, where the character attributes include at least one of the following: the number of characters included in the message or the number of strokes of characters included in the message;

According to the character attribute, the similarity between the messages in the second message set is determined.

In a possible implementation manner, determining the similarity between the messages in the second message set according to the character attribute, including:

According to the character attribute, determine the edit distance between the messages in the second message set;

According to the edit distance, the similarity between the messages in the second message set is determined.

In a possible implementation manner, in the first message set, the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, The number of third messages included in the third message set, and the target account number is determined in the account set, including:

determining a second threshold according to the number of the first messages and the number of the third messages;

A target account is determined in the account set according to the second message quantity and the second threshold.

In a possible implementation manner, determining the second threshold according to the first message quantity and the third message quantity includes:

acquiring a first preset relationship, where the first preset relationship includes a plurality of message quantities and a proportional coefficient corresponding to each message quantity;

determining a proportional coefficient according to the first message quantity and the first preset relationship;

A second threshold is determined according to the first number of messages, the scaling factor and the third number of messages.

In a possible implementation manner, according to the second message quantity and the second threshold, determining the target account in the account set, including:

judging whether the number of the second messages is greater than a second threshold;

If so, determine the first account as the target account in the account set.

In a second aspect, an embodiment of the present application provides a message processing device, the device includes a first determination module, a division module, an acquisition module, and a second determination module, wherein:

The first determining module is configured to determine a second message set from the first message set, where the first message set includes messages received by at least one terminal device within a preset time period, and the messages in the second message set are The message is a preset type;

The dividing module is configured to, according to the similarity between the messages in the second message set, divide the second message set into at least one third message set, where each message in the third message set is divided into at least one third message set. The similarity between them is greater than or equal to the first threshold;

The obtaining module is configured to obtain a first account corresponding to each message in the third message set, where the first account is an account used by the terminal device to send the message;

The second determining module is configured to determine, in the first message set, the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, For the number of third messages included in the third message set, the target account is determined in the account set, and the account set includes accounts corresponding to the messages in the second message set.

In a possible implementation manner, the dividing module is specifically used for:

obtaining the similarity between the messages in the second message set;

According to the similarity, clustering processing is performed on the messages in the second message set, so as to divide the second message set into at least one third message set.

In a possible implementation manner, the dividing module is specifically used for:

Acquire character attributes of each message in the second message set, where the character attributes include at least one of the following: the number of characters included in the message or the number of strokes of characters included in the message;

According to the character attribute, the similarity between the messages in the second message set is determined.

In a possible implementation manner, the dividing module is specifically used for:

According to the character attribute, determine the edit distance between the messages in the second message set;

According to the edit distance, the similarity between the messages in the second message set is determined.

In a possible implementation manner, the second determining module is specifically configured to:

determining a second threshold according to the number of the first messages and the number of the third messages;

A target account is determined in the account set according to the second message quantity and the second threshold.

In a possible implementation manner, the second determining module is specifically configured to:

acquiring a first preset relationship, where the first preset relationship includes a plurality of message quantities and a proportional coefficient corresponding to each message quantity;

determining a proportional coefficient according to the first message quantity and the first preset relationship;

A second threshold is determined according to the first number of messages, the scaling factor and the third number of messages.

In a possible implementation manner, the second determining module is specifically configured to:

judging whether the number of the second messages is greater than a second threshold;

If so, determine the first account as the target account in the account set.

In a third aspect, an embodiment of the present application provides a message processing device, including: a memory, a processor, and a communication interface, where the memory is used for storing program instructions, and the processor is used for invoking the program instructions in the memory to execute the execution as in the first aspect Any one of the message processing methods.

In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a computer program is stored on the readable storage medium; the computer program is used to implement the message processing method according to any one of the first aspect.

Embodiments of the present application provide a message processing method, apparatus, and device, where a second message set is determined in a first message set, where the first message set includes messages received by at least one terminal device within a preset time period, and the first message set includes messages received by at least one terminal device within a preset time period. The messages in the second message set are of a preset type. dividing the second message set into at least one third message set according to the similarity between the messages in the second message set, wherein the similarity between the messages in the third message set is greater than or equal to the first threshold, Acquire a first account corresponding to each message in the third message set, where the first account is an account used by the terminal device to send messages. In the first message set, determine the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, and the number of third messages included in the third message set, and determine in the account set The target account is determined in the set of accounts, wherein the set of accounts includes accounts corresponding to the messages in the second set of messages. In the above method, according to the similarity between the messages in the second message set, messages with similar text content can be accurately divided into the same third message set, and sent in the first message set according to the first account number The number of messages in the third message set, the number of messages included in the third message set, and the number of messages sent by the first account in the third message set can accurately determine whether the first account is the target account, thereby improving the operator's ability to send spam short messages. The recognition accuracy of mobile phone numbers.

Description of drawings

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

2 is a schematic flowchart of a message processing method provided by an embodiment of the present application;

3 is a schematic diagram of a process for obtaining a third message set according to an embodiment of the present application;

4 is a schematic flowchart of another message processing method provided by an embodiment of the present application;

FIG. 5 is a schematic process diagram of a message processing method provided by an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a message processing apparatus provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of a hardware structure of a message processing device according to an embodiment of the present application.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

For ease of understanding, the application scenarios of the embodiments of the present application are first introduced.

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application. See Figure 1, including phone A, phone B, and the operator. The mobile phone A can send a short message to the mobile phone B, the mobile phone B can receive the short message sent by the mobile phone A, and the mobile phone A and the mobile phone B can exchange data with the operator.

When mobile phone A sends a spam short message to mobile phone B, the operator can obtain the sender of the spam short message received by mobile phone B. For example, the operator can determine the sender of the spam short message according to the mobile phone number corresponding to the spam short message. When the operator determines that mobile phone A is the sender of the spam short message, the operator can block the number of mobile phone A, so that mobile phone A cannot send spam short messages to mobile phone B.

In the related art, because the sender of the spam message usually changes the text content of the spam message without affecting the reading, and the number of spam messages sent by the same mobile phone number within a period of time is less than that set by the operator The upper limit of sending spam text messages, so that operators cannot identify the mobile phone numbers that send spam text messages in a short period of time, resulting in lower recognition accuracy of mobile phone numbers that send spam text messages.

In order to solve the technical problem in the related art that the operator's identification accuracy of the mobile phone number for sending spam short messages is low, in this embodiment of the present application, the first set of spam short messages in all short messages sent by the terminal device within a period of time is determined, and According to the similarity between the spam short messages in the first spam short message set, the spam short messages are divided into second spam short message sets of different types. Determine the mobile phone number corresponding to the spam short message in the second spam short message set, and according to the number of all short messages sent by the mobile phone number within a period of time and the number of this type of spam short message sent, and the number of the second spam short message set of this type. The total number of spam text messages, to determine whether the mobile phone number is a mobile phone number that sends spam text messages. In the above method, according to the similarity between the spam short messages in the spam short message set, the spam short messages with similar text content can be accurately divided into the same second spam short message set. If multiple spam text messages are spam text messages sent from the same mobile phone number, the mobile phone number is the number for sending spam text messages, and the mobile phone number can be blocked. .

Hereinafter, the technical solutions shown in the embodiments of the present application will be described in detail through specific embodiments. It should be noted that the following embodiments may exist alone or may be combined with each other, and the same or similar content will not be repeated in different embodiments.

FIG. 2 is a schematic flowchart of a message processing method provided by an embodiment of the present application. Referring to Figure 2, the method can include:

S201. Determine a second message set in the first message set.

The execution body of the embodiment of the present application may be a server, or may be a message processing apparatus provided in the server. Optionally, the message processing apparatus may be implemented by software, or may be implemented by a combination of software and hardware.

The first set of messages includes messages received by at least one terminal device within a preset time period. The terminal device may be any device with a message receiving function. For example, the terminal device may be a mobile phone, a computer, or other devices. For example, when the terminal device is a mobile phone, the first message set may be a set of messages such as short messages and WeChat messages received by at least one mobile phone within a preset time period.

The messages in the second message set are of a preset type. Optionally, the preset type can be spam. The spam message may be a message that the user does not want to receive, which is sent to the user without the user's consent. For example, spam messages may include spam text messages, spam emails, and the like.

Optionally, the second message set may be a spam message set. For example, the first message set is a short message received by at least one mobile phone within a preset time period, wherein the set formed by the spam short messages in the first message set is the second message set. Optionally, the spam messages may also include spam WeChat messages, spam notification messages, and the like received by the mobile phone.

Optionally, the second message set may be a spam set. For example, the first message set is emails received by at least one mailbox within a preset time period, and the set formed by spam emails in the first message set is the second message set.

Optionally, the second message set may be determined in the first message set according to the following feasible implementation manner: determine the keywords of the messages in the second message set, and determine the second message set in the first message set according to the keywords. For example, when the second message set is a spam short message set, the keywords of the spam short messages are determined, and according to the keyword filtering algorithm, short messages satisfying the spam short message keywords are screened out from the first message set to form the second message set.

Optionally, the second message set may be determined from the first message set according to an artificial intelligence machine learning algorithm. For example, when the second message set is a spam short message set, the model can be trained according to the sample spam short message and the sample normal short message, the spam short message is identified according to the trained model, and the second message set is determined in the first message set.

S202. Divide the second message set into at least one third message set according to the similarity between the messages in the second message set.

The third message set is a preset type of message set. For example, when the preset type is spam, the second message set is a spam set, and the third message set divided according to the second message set is also a spam set.

Optionally, the similarity between the messages in the third message set is greater than or equal to the first threshold. For example, when the messages in the third message set are spam messages, the degree of similarity of the text content between the spam messages is greater than or equal to the first threshold.

The second message set may be divided into at least one third message set according to the following feasible manner: obtaining the similarity between the messages in the second message set. The similarity refers to the degree of similarity of text content between messages. For example, if the text content in the short message A and the short message B is the same, the similarity between the short message A and the short message B is 100%. Clustering processing is performed on the messages in the second message set according to the similarity, so as to divide the second message set into at least one third message set.

Optionally, the similarity between the messages in the second message set may be acquired in the following feasible manner: acquiring character attributes of each message in the second message set, wherein the character attributes include at least one of the following: The number of characters or strokes of characters included in the message.

According to the character attribute, the similarity between the messages in the second message set is determined. For example, the edit distance between the messages in the second message set is determined according to the character attribute, and the similarity between the messages in the second message set is determined according to the edit distance. Among them, the edit distance refers to the minimum number of editing operations required to convert two texts of text content from one to the other. For example, editing operations may include operations such as replacing a text, inserting a text, deleting a text, and so on. Optionally, the fewer editing operations required for one text to become another, the greater the similarity between the two texts. For example, the number of editing operations required to edit the text "1" into the text "2" is one, then the similarity between the text "1" and the text "2" is high, and the editing required to edit the text "1" into the text "Delete" When the number of operations is six, the similarity between the text "one" and the text "delete" is low. For example, the number of strokes of the text content in spam message A is 100, and the number of strokes in the text content in spam message B is 100, then the similarity between spam message A and spam message B is 100%, and spam message A and spam message B are in in the same third message set.

Optionally, according to the similarity between the messages in the second message set, the Mean-Shift clustering algorithm may be used to perform clustering processing on the messages in the second message set, thereby obtaining at least one third message set. Since the number of message categories cannot be predicted, the unit of the sliding window radius of the Mean-Shift clustering algorithm is the Levenstein distance, which can control the variation of message categories. For example, when the variation range of the message is larger than the sliding window radius, the message is regarded as another kind of message.

The process of dividing the second message set into at least one third message set will be described in detail below with reference to FIG. 3 .

FIG. 3 is a schematic diagram of a process of obtaining a third message set according to an embodiment of the present application. Referring to FIG. 3 , it includes a second message set, a third message set A, a third message set B, and a third message set C. The second message set includes 8 messages (each circle represents a message), the third message set A includes 3 messages, the third message set B includes 2 messages, and the third message set C includes 4 messages messages.

Referring to FIG. 3 , the character attributes of each message in the second message set are acquired, and the similarities of the messages in the second message set are divided according to the character attributes of each message. The higher the similarity between the messages, the closer the distance between the messages, the lower the similarity between the messages, the farther the distance between the messages.

Perform clustering processing on the messages after the similarity division to obtain a third message set A, a third message set B and a third message set C, wherein the similarity between the messages in the third message set A is greater than or equal to The first threshold, the similarity between the messages in the third message set B is greater than or equal to the first threshold, and the similarity between the messages in the third message set C is greater than or equal to the first threshold.

S203: Acquire a first account corresponding to each message in the third message set.

The first account is an account used by the terminal device to send messages. For example, when the terminal device is a mobile phone, the first account for sending SMS messages from the mobile phone is the mobile phone number, the first account for sending WeChat messages from the mobile phone is the WeChat ID number, and the first account for sending emails from the mobile phone is the mailbox account.

Optionally, the first account may be determined according to the correspondence between each message in the third message set and the account. For example, the correspondence between messages and accounts can be as shown in Table 1:

Table 1

information account message 1 Account 1 message 2 Account 2 message 3 Account 3 ... ...

It should be noted that, Table 1 only illustrates the correspondence between messages and accounts in the form of an example, and does not limit the correspondence between messages and accounts.

For example, when the message in the third message set is message 1, the first account is account 1; when the message in the third message set is message 2, the first account is account 2; When the message is message 3, the first account is account 3.

Optionally, when the third message set is a spam short message set, the first account corresponding to each message is the mobile phone number for sending spam short messages, and when the third message set is a spam WeChat set, the first account corresponding to each message is It is a WeChat account for sending spam WeChat, and when the third message set is a spam set, the first account corresponding to each message is the email account for sending spam.

S204. Determine, in the first message set, the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, and the number of third messages included in the third message set, and Determine the target account in the account set.

The first number of messages is the number of messages sent by the first account in the first message set. For example, if the first message set includes 100 messages, 10 of which are messages sent by the first account, the number of the first messages is 10.

Optionally, the number of messages sent by the first account in the first message set may be determined according to the correspondence between each message in the first message set and the account. For example, when the account corresponding to the message in the first message set is the same as the first account, the message is a message sent by the first account in the first message set.

The second number of messages is the number of messages sent by the first account in the third message set. For example, if the third message set includes 10 messages, among which 3 messages are messages sent by the first account, the number of the second messages is 3.

Optionally, the number of messages sent by the first account in the third message set may be determined according to the correspondence between each message in the third message set and the account. For example, when the account corresponding to the message in the third message set is the same as the first account, the message is a message sent by the first account in the third message set.

The third number of messages is the number of messages included in the third message set. For example, when the third message set is a set of spam short messages, the total number of spam short messages in the third message set is the number of third messages.

Optionally, the third message quantity may be obtained according to the result of the clustering process. For example, when the messages in the second message set are clustered, the number of messages in each of the divided third message sets can be determined.

The account set includes accounts corresponding to the messages in the second message set. Optionally, an account set corresponding to each message in the second message set may be formed into an account set. For example, if the messages in the second message set are spam short messages, the mobile phone numbers corresponding to all the spam short messages in the second message set are accounts included in the account set.

The target account can be determined in the account set according to the following two feasible implementation methods:

A possible implementation:

The second threshold is determined according to the first number of messages and the third number of messages. The target account is determined in the account set according to the second message quantity and the second threshold. Optionally, the second threshold may be a preset threshold. If the number of second messages corresponding to the first account in the third message set is greater than or equal to the second threshold, the first account is determined in the account set as the target account.

Optionally, when the messages in the third message set are spam short messages, the first account is the mobile phone number for sending the spam short messages, and when the target mobile phone number is determined in the account set, the operator may shut down the target mobile phone number for a period of time, Banning and other processing can reduce the probability of the user's mobile phone receiving spam text messages, thereby improving the user's experience.

Another possible implementation:

The suspicious value of the first account is determined according to the number of first messages corresponding to the first account in the first message set and the number of second messages corresponding to the first account in the third message set. When the suspicious value is greater than or equal to the preset threshold, the first account is determined in the account set as the target account. For example, the suspicious value may be a ratio of the number of first messages to the number of second messages. For example, if the number of first messages corresponding to the first account in the first message set is 100, and the number of second messages corresponding to the first account in the third message set is 30, the suspicious value of the first account is 0.3, and the preset When the threshold is 0.1, the first account is the target account.

In the message processing method provided by the embodiment of the present application, a second message set is determined in a first message set, character attributes of each message in the second message set are acquired, and similarity between messages in the second message set is determined according to the character attribute Spend. According to the similarity, clustering processing is performed on the messages in the second message set, so as to divide the second message set into at least one third message set. Acquire the first account corresponding to each message in the third message set, and determine the number of first messages, the number of second messages, and the number of third messages included in the third message set corresponding to the first account. The second threshold is determined according to the first message quantity and the third message quantity, and the target account is determined in the account set according to the second message quantity and the second threshold. In the above method, according to the character attributes of each message in the second message set, the similarity between the messages in the second message set can be accurately obtained, and then according to the similarity, a plurality of third message sets can be accurately obtained, When the number of messages corresponding to the first account in the third message set is greater than or equal to the second threshold, it means that the first account has sent multiple messages of a preset type with similar character attributes, and the first account can be determined in the account set as the target account number, and then process the target account number, so that the operator can improve the identification accuracy of the mobile phone number that sends the spam short message.

On the basis of the embodiment shown in FIG. 2 , the above message processing method will be described in detail below with reference to FIG. 4 .

FIG. 4 is a schematic flowchart of another message processing method provided by an embodiment of the present application. Referring to Figure 4, the method can include:

S401. Determine a second message set in the first message set.

It should be noted that, for the execution process of S401, reference may be made to the execution process of S201, which will not be repeated here.

S402. Divide the second message set into at least one third message set according to the similarity between the messages in the second message set.

It should be noted that, for the execution process of S403, reference may be made to the execution process of S203, which will not be repeated here.

S403: Acquire a first account corresponding to each message in the third message set.

It should be noted that, for the execution process of S403, reference may be made to the execution process of S203, which will not be repeated here.

S404. Determine, in the first message set, the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, and the number of third messages included in the third message set.

It should be noted that, for the execution process of S404, reference may be made to the execution process of S204, which will not be repeated here.

S405. Acquire a first preset relationship, and determine a proportional coefficient according to the first message quantity and the first preset relationship.

The first preset relationship includes a plurality of message quantities and a proportional coefficient corresponding to each message quantity. For example, the first preset relationship may be as shown in Table 2:

Table 2

number of messages scale factor Number of messages 1 Scale factor 1 Number of messages 2 Scale factor 2 Number of messages 3 Scale factor 3 ... ...

It should be noted that, Table 2 only illustrates the first preset relationship in the form of an example, and is not a limitation on the first preset relationship.

Optionally, the proportional coefficient may be determined according to the first message quantity and the first preset relationship. For example, when the number of first messages corresponding to the first account in the first message set is the number of messages 1, the corresponding proportional coefficient is the proportional coefficient 1; in the first message set, the number of first messages corresponding to the first account is the number of messages When the value is 2, the corresponding proportional coefficient is the proportional coefficient 2; when the first message quantity corresponding to the first account in the first message set is the message quantity 3, the corresponding proportional coefficient is the proportional coefficient 3.

Optionally, the value of the scale coefficient is between 0 and 1.

S406. Determine a second threshold according to the first message quantity, the proportional coefficient, and the third message quantity.

The second threshold may be determined according to the following feasible implementation manner: the second threshold is determined according to the first message quantity, the proportional coefficient and the third message quantity. For example, the second threshold is obtained by multiplying the ratio of the number of the first messages to the number of the third messages by the proportional coefficient. For example, if the number of first messages corresponding to the first account in the first message set is 100, the number of third messages in the third message set where the first account is located is 10, and the proportional coefficient is 0.3, the second threshold is 3.

S407. Determine whether the number of the second messages is greater than or equal to the second threshold.

If not, execute S408.

If yes, execute S409.

S408. Determine that the first account is not the target account.

S409. Determine, in the account set, that the first account is the target account.

Optionally, in the account set, it is determined that the account that is the same as the first account is the target account.

In the message processing method provided by the embodiment of the present application, a second message set is determined in the first message set, and the second message set is divided into at least one third message combination according to the similarity between the messages in the second message set, Obtain the first account corresponding to each message in the third message set, and determine, in the first message set, the number of first messages corresponding to each first account and the number of second messages corresponding to the first account in the third message set , the number of third messages included in the third message set. Obtain a first preset relationship, determine a proportionality coefficient according to the first message quantity and the first preset relationship, and determine a second threshold according to the first message quantity, the proportionality coefficient, and the third message quantity, when the second message quantity is greater than or equal to At the second threshold, the first account is determined as the target account in the account set. In the above method, according to the similarity between the messages in the second message set, the second message set can be accurately divided into a plurality of third message sets, and then according to the number of first messages, the proportional coefficient and the number of third messages The determinable second threshold can reduce the probability of the operator misblocking the account. At the same time, when the number of the second messages is greater than or equal to the second threshold, it means that the first account has sent multiple messages with high similarity, and can be displayed in the account number. In the collection, the first account is determined as the target account, and then the target account is processed, so that the operator can improve the identification accuracy of the mobile phone number that sends the spam short message.

On the basis of any one of the above-mentioned embodiments, the message processing method will be described in detail below with reference to FIG. 5 through a specific example.

FIG. 5 is a schematic process diagram of a message processing method provided by an embodiment of the present application. Please refer to FIG. 5 , including a first message set, a second message set, a third message set A, and a third message set B, wherein the first message set includes multiple messages, and the second message combination includes 8 preset messages type of message (a circle in FIG. 5 represents a message), the third message set A includes 4 messages of preset types, the third message set B includes 4 messages of preset types, and message 1 is the third message The messages in collection A. The similarity of character attributes between the messages in the third message set A is greater than or equal to the first threshold, and the similarity of character attributes between the messages in the third message set B is greater than or equal to the first threshold.

Referring to FIG. 5 , messages conforming to a preset type are selected from the first message set to form a second message set. Similarity processing is performed between the messages in the second message set according to the character attributes of the messages. The higher the similarity of the messages, the smaller the distance between the circles in FIG. 5 . Perform clustering processing on each message in the second message set to obtain a third message set A and a third message set B, wherein the messages in the third message set A are more similar to the messages in the third message set B. Low.

A first account corresponding to message 1 in the third message set A is determined, and the number of first messages corresponding to the first account in the first message set is determined. The number of messages in the third message set A is 4, the proportional coefficient is determined according to the first preset relationship and the first message number, and the second threshold. Determine the number of second messages corresponding to the first account in the third message set A, and when the number of second messages is greater than or equal to the second threshold, determine the first account in the account set as the target account.

When the number of messages corresponding to the first account in the third message set A is greater than or equal to the second threshold, it means that the first account has sent multiple messages of preset types with similar character attributes, and it can be determined in the account set that the first account is The target account number is then processed, so that the operator can improve the identification accuracy of the mobile phone number that sends the spam short message.

FIG. 6 is a schematic structural diagram of a message processing apparatus according to an embodiment of the present application. The message processing apparatus may be provided in the terminal device. Referring to FIG. 6, the message processing apparatus 10 includes: a first determination module 11, a division module 12, an acquisition module 13 and a second determination module 14, wherein:

The first determining module 11 is configured to determine a second message set from the first message set, where the first message set includes messages received by at least one terminal device within a preset time period, and the second message set is The message is the default type;

The dividing module 12 is configured to, according to the similarity between the messages in the second message set, divide the second message set into at least one third message set, each message in the third message set The similarity between them is greater than or equal to the first threshold;

The obtaining module 13 is configured to obtain a first account corresponding to each message in the third message set, where the first account is an account used by the terminal device to send the message;

The second determining module 14 is configured to determine, in the first message set, the number of first messages corresponding to each first account and the number of second messages corresponding to the first account in the third message set . The number of third messages included in the third message set, and the target account is determined in the account set, where the account set includes accounts corresponding to the messages in the second message set.

In a possible implementation manner, the dividing module 12 is specifically configured to:

obtaining the similarity between the messages in the second message set;

According to the similarity, clustering processing is performed on the messages in the second message set, so as to divide the second message set into at least one third message set.

In a possible implementation manner, the dividing module 12 is specifically configured to:

Acquire character attributes of each message in the second message set, where the character attributes include at least one of the following: the number of characters included in the message or the number of strokes of characters included in the message;

According to the character attribute, the similarity between the messages in the second message set is determined.

In a possible implementation manner, the dividing module 12 is specifically configured to:

According to the character attribute, determine the edit distance between the messages in the second message set;

According to the edit distance, the similarity between the messages in the second message set is determined.

In a possible implementation manner, the second determining module 14 is specifically configured to:

determining a second threshold according to the number of the first messages and the number of the third messages;

A target account is determined in the account set according to the second message quantity and the second threshold.

In a possible implementation manner, the second determining module 14 is specifically configured to:

acquiring a first preset relationship, where the first preset relationship includes a plurality of message quantities and a proportional coefficient corresponding to each message quantity;

determining a proportional coefficient according to the first message quantity and the first preset relationship;

A second threshold is determined according to the first number of messages, the scaling factor and the third number of messages.

In a possible implementation manner, the second determining module 14 is specifically configured to:

judging whether the number of the second messages is greater than a second threshold;

If so, determine the first account as the target account in the account set.

A message processing apparatus provided by the embodiments of the present application can execute the technical solutions shown in the foregoing method embodiments, and the implementation principles and beneficial effects thereof are similar, which will not be repeated here.

FIG. 7 is a schematic diagram of a hardware structure of a message processing device according to an embodiment of the present application. Referring to FIG. 7 , the message processing device 20 may include: a processor 21 and a memory 22, wherein the processor 21 and the memory 22 can communicate; exemplarily, the processor 21 and the memory 22 communicate through a communication bus 23, and the memory 22 is used to store program instructions, and the processor 21 is used to call the program instructions in the memory to execute the message processing method shown in any of the above method embodiments.

Optionally, the message processing device 20 may further include a communication interface, and the communication interface may include a transmitter and/or a receiver.

Optionally, the above-mentioned processor may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC) )Wait. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

An embodiment of the present application provides a readable storage medium, where a computer program is stored on the readable storage medium; the computer program is used to implement the message processing method described in any of the foregoing embodiments.

An embodiment of the present application provides a computer program product, where the computer program product includes instructions that, when executed, cause a computer to execute the above message processing method.

All or part of the steps for implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a readable memory. When the program is executed, the steps including the above method embodiments are executed; and the aforementioned memory (storage medium) includes: read-only memory (English: read-only memory, abbreviation: ROM), RAM, flash memory, hard disk, Solid state drive, magnetic tape (English: magnetic tape), floppy disk (English: floppydisk), optical disc (English: optical disc) and any combination thereof.

The embodiments of the present application are described with reference to flowcharts and/or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processing unit of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processing unit of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

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

In this application, the term "comprising" and its variants may mean non-limiting inclusion; the term "or" and its variants may mean "and/or". The terms "first", "second" and the like in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. In this application, "plurality" means two or more. "And/or", which describes the association relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are an "or" relationship.

Claims (9)

1. a message processing method, is characterized in that, comprises: determining a second message set in the first message set, the first message set includes messages received by at least one terminal device within a preset time period, and the messages in the second message set are of a preset type; According to the similarity between the messages in the second message set, the second message set is divided into at least one third message set, and the similarity between the messages in the third message set is greater than or equal to first threshold; obtaining a first account corresponding to each message in the third message set, where the first account is an account used by the terminal device to send the message; In the first message set, determine the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, and the number of messages included in the third message set The third number of messages, the target account is determined in the account set, and the account set includes the accounts corresponding to the messages in the second message set; Determining, in the first message set, the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, and the third message set The number of included third messages, the target account is determined in the account set, including: Determine a second threshold according to the number of first messages and the number of third messages; determine a target account in the account set according to the number of second messages and the second threshold; Or, according to the number of first messages corresponding to the first account in the first message set and the number of second messages corresponding to the first account in the third message set, determine the suspicious value of the first account; When the threshold is set, the first account is determined in the account set as the target account; the suspicious value is the ratio of the number of first messages to the number of second messages. 2. The method according to claim 1, wherein, according to the similarity between the messages in the second message set, dividing the second message set into at least one third message set, comprising: obtaining the similarity between the messages in the second message set; According to the similarity, clustering processing is performed on the messages in the second message set, so as to divide the second message set into at least one third message set. 3. The method according to claim 2, wherein obtaining the similarity between the messages in the second message set comprises: Acquire character attributes of each message in the second message set, where the character attributes include at least one of the following: the number of characters included in the message or the number of strokes of characters included in the message; According to the character attribute, the similarity between the messages in the second message set is determined. 4. The method according to claim 3, wherein determining the similarity between the messages in the second message set according to the character attribute, comprising: According to the character attribute, determine the edit distance between the messages in the second message set; According to the edit distance, the similarity between the messages in the second message set is determined. 5 . The method according to claim 1 , wherein determining the second threshold according to the number of the first messages and the number of the third messages, comprising: 6 . acquiring a first preset relationship, where the first preset relationship includes a plurality of message quantities and a proportional coefficient corresponding to each message quantity; determining a proportional coefficient according to the first message quantity and the first preset relationship; A second threshold is determined according to the first number of messages, the scaling factor and the third number of messages. 6. The method according to claim 1, wherein determining a target account in the account set according to the second message quantity and the second threshold, comprising: judging whether the number of the second messages is greater than a second threshold; If so, determine the first account as the target account in the account set. 7. A message processing device, comprising a first determination module, a division module, an acquisition module and a second determination module, wherein: The first determining module is configured to determine a second message set from the first message set, where the first message set includes messages received by at least one terminal device within a preset time period, and the messages in the second message set are The message is a preset type; The dividing module is configured to, according to the similarity between the messages in the second message set, divide the second message set into at least one third message set, where each message in the third message set is divided into at least one third message set. The similarity between them is greater than or equal to the first threshold; The obtaining module is configured to obtain a first account corresponding to each message in the third message set, where the first account is an account used by the terminal device to send the message; The second determining module is configured to determine, in the first message set, the number of first messages corresponding to each first account, the number of second messages corresponding to the first account in the third message set, The number of third messages included in the third message set, the target account is determined in the account set, and the account set includes accounts corresponding to the messages in the second message set; The second determining module is specifically used for: Determine a second threshold according to the number of first messages and the number of third messages; determine a target account in the account set according to the number of second messages and the second threshold The second determining module is also specifically used for: Determine the suspicious value of the first account according to the number of first messages corresponding to the first account in the first message set and the number of second messages corresponding to the first account in the third message set; if the suspicious value is greater than or equal to a preset value When the threshold is set, the first account is determined as the target account in the account set; the suspicious value is the ratio of the number of first messages to the number of second messages. 8. A message processing device, comprising: a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory to implement the message processing method according to any one of claims 1 to 6. 9. A readable storage medium, wherein a device control program is stored on the readable storage medium, and when the device control program is executed by a processor, the device control program according to any one of claims 1 to 6 is implemented. message handling method.

Images