CN115529581B - Off-network user identification method and device - Google Patents

Abstract

The invention discloses an off-network user identification method and device, relates to the technical field of communication, and aims to solve the problem that the conversion rate is low due to the fact that the off-network user identification is not accurate enough in the related technology. The method comprises the following steps: acquiring a first communication object set of an off-network user in a first preset time period; acquiring different network communication objects of all first communication objects in a first communication object set in a second preset time period to obtain a second communication object set; acquiring a third communication object set of each second communication object in a third preset time period in the second communication object set; and respectively comparing the similarity of each third communication object set with the first communication object set, and determining that the target second communication object corresponding to the third communication object set with the highest similarity of the first communication object set is the object changed by the off-network user. Therefore, the information after the change of the off-network user is accurately identified based on the communication data of the off-network user, so that the identification accuracy and conversion rate of the off-network user can be improved.

Description

Off-network user identification method and device

Technical Field

The present invention relates to the field of communication technology, and in particular to an off-network user identification method and device.

Background technique

At present, domestic telecommunications services have become generalized and saturated. When the personalized needs of users do not match the services provided by operators, it is easy to cause user loss, that is, causing existing network users to leave the network. After users leave the network, they change their mobile phone numbers to the original operators, making it difficult for operators to carry out secondary marketing to them.

In the related technology, the main method is to carry out indiscriminate marketing to off-network users, that is, by obtaining a list of off-network users in a certain area, indiscriminate promotion is carried out to them. However, this method is not accurate enough in identifying off-network users, resulting in a very low conversion rate.

Summary of the invention

The embodiments of the present invention provide an off-network user identification method and device to solve the problem that the related art is not accurate enough in identifying off-network users, resulting in a very low conversion rate.

In a first aspect, an embodiment of the present invention provides an off-network user identification method, comprising:

Acquire a first communication object set of the off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency;

Acquire all the communication objects of the first communication object in the first communication object set in the second preset time period to obtain a second communication object set;

Acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency;

The similarity between each third communication object set and the first communication object set is compared respectively, and the target second communication object corresponding to the third communication object set having the highest similarity to the first communication object set is determined as the changed object of the off-network user.

Optionally, obtaining a first communication object set of the off-network user within a first preset time period includes:

Acquire communication data of the off-network user within a first preset time period, the communication data including a communication object and a communication frequency;

According to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are on the same network, the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency are determined to obtain a first communication object set.

Optionally, after acquiring the communication data of the off-network user within the first preset time period, the method further includes:

Constructing a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user;

The determining, according to the communication frequency between each communication object and the off-network user, and whether each communication object and the off-network user are on the same network, a same-network communication object whose communication frequency with the off-network user is higher than a first preset frequency, comprises:

The communication objects in different networks from the off-network user and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency are eliminated from the communication network hypergraph to obtain a close communication network hypergraph of the off-network user.

Optionally, the comparing the similarity of each third communication object set with the first communication object set respectively includes:

Based on the number of identical communication objects in the first communication object set and each third communication object set, the similarity between the off-network user and each second communication object is determined.

Optionally, after determining that the target second communication object corresponding to the third communication object set having the highest similarity to the first communication object set is the changed object of the off-network user, the method further includes:

Determining the permanent location information of the off-network user;

The information of the target second communication object and the resident location information are pushed to the marketing terminal.

In a second aspect, an embodiment of the present invention further provides an off-network user identification device, comprising:

A first acquisition module, used to acquire a first communication object set of an off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency;

A second acquisition module, configured to acquire all communication objects of the first communication object in the first communication object set within a second preset time period, to obtain a second communication object set;

A third acquisition module, used to acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency;

The first determining module is used to compare the similarity of each third communication object set with the first communication object set respectively, and determine that the target second communication object corresponding to the third communication object set with the highest similarity to the first communication object set is the changed object of the off-network user.

Optionally, the first acquisition module includes:

An acquisition unit, configured to acquire communication data of an off-network user within a first preset time period, wherein the communication data includes a communication object and a communication frequency;

The determination unit is used to determine the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency according to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are same-network users, so as to obtain a first communication object set.

Optionally, the first acquisition module further includes:

A construction unit, configured to construct a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user;

The determining unit is used to eliminate the communication objects in the communication network hypergraph that are in different networks from the off-network user, and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency, to obtain a close communication network hypergraph of the off-network user.

Optionally, the first determining module is used to determine the similarity between the off-network user and each second communication object based on the number of identical communication objects in the first communication object set and each third communication object set.

Optionally, the off-grid user identification device further includes:

A second determination module is used to determine the permanent location information of the off-network user;

The push module is used to push the information of the target second communication object and the permanent location information to the marketing terminal.

In a third aspect, an embodiment of the present invention further provides an off-network user identification device, comprising: a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the off-network user identification method as described above when executing the computer program.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the off-network user identification method as described above are implemented.

In an embodiment of the present invention, a first communication object set of an off-network user within a first preset time period is obtained, wherein the first communication object set is a set of communication objects on the same network whose communication frequency with the off-network user is higher than the first preset frequency; all communication objects on different networks of the first communication objects in the first communication object set within a second preset time period are obtained to obtain a second communication object set; a third communication object set of each second communication object in the second communication object set within a third preset time period is obtained, wherein the third communication object set of each second communication object is a set of communication objects on different networks whose communication frequency with the second communication object is higher than the second preset frequency; each third communication object set is respectively compared with the first communication object set for similarity, and the target second communication object corresponding to the third communication object set with the highest similarity to the first communication object set is determined to be the object after the off-network user is changed. In this way, by accurately identifying the changed information of the off-network user based on the communication data of the off-network user, the identification accuracy of the off-network user can be improved, and then the off-network user can be promoted in a targeted manner to improve the conversion rate.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

FIG1 is a flow chart of an off-network user identification method provided by an embodiment of the present invention;

FIG2 is a schematic diagram of a communication social network hypergraph of an off-network user provided by an embodiment of the present invention;

FIG3 is a schematic diagram of a close social network hypergraph of an off-network user provided by an embodiment of the present invention;

FIG4 is a schematic diagram of a communication social network hypergraph of close social circle friends of an off-network user provided by an embodiment of the present invention;

FIG5 is a structural diagram of an off-network user identification device provided in an embodiment of the present invention;

6 is a second structural diagram of an off-network user identification device provided in an embodiment of the present invention;

Detailed ways

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Referring to FIG. 1 , FIG. 1 is a flow chart of an off-network user identification method provided by an embodiment of the present invention. As shown in FIG. 1 , the method comprises the following steps:

Step 101: Acquire a first communication object set of an off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency.

The off-network user may refer to a target operator number that is deregistered or shut down, and the target operator may be an operator that needs to identify the off-network user. The first preset time period may be a period of time before the off-network user leaves the network, such as one month or three months before leaving the network. The communication object may refer to an object that has communication with the off-network user, such as a call or text message record.

For example, when you want to identify an off-network user of the first operator, you can obtain the communication and social data of the off-network user within three months before leaving the network, and obtain the communication object set of the off-network user from it.

After obtaining the communication object set of the off-network user within the first preset time period, the communication object set can be further screened and eliminated to retain the same-network communication objects with which the user has closer interactions, such as removing communication objects with which the off-network user has a lower communication frequency, and removing communication objects from different networks, that is, the same-network communication objects with which the off-network user has a communication frequency higher than the first preset frequency can be retained to obtain the first communication object set, wherein the first preset frequency can be a frequency set according to demand, such as deleting communication objects that have communicated with the off-network user less than 3 times within the first preset time period, or deleting communication objects that have not communicated with the off-network user in nearly 1 month. The different-network communication objects may refer to communication objects of a different operator from that of the off-network user, and the same-network communication objects refer to communication objects of the same operator as that of the off-network user.

Optionally, step 101 includes:

Acquire communication data of the off-network user within a first preset time period, the communication data including a communication object and a communication frequency;

According to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are on the same network, the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency are determined to obtain a first communication object set.

That is, in one implementation, the communication data of the off-network user within the first preset time period can be first obtained, and the communication data includes the communication object, the communication frequency with each communication object, the communication method, etc., wherein the communication object includes ordinary users and institutional users, etc., and the communication method includes telephone, text message, 5G message, etc. The communication data can also include active and passive party information, such as actively calling other users, actively initiating 5G messages, receiving text messages from an organization, etc.

Then, according to the communication frequency between each communication object and the off-network user, and whether each communication object and the off-network user are users of the same network, whether the communication object is an institutional user, etc., some communication objects with whom there is not close contact can be removed, such as removing institutional users, removing communication objects on different networks, and removing communication objects with low communication frequency, so as to obtain the close friends set of the off-network user on the same network, that is, to determine the communication objects on the same network whose communication frequency with the off-network user is higher than the first preset frequency, and obtain the first communication object set. In this way, the close communication object set of the off-network user can be quickly determined.

Optionally, after acquiring the communication data of the off-network user within the first preset time period, the method further includes:

Constructing a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user;

The determining, according to the communication frequency between each communication object and the off-network user, and whether each communication object and the off-network user are on the same network, a same-network communication object whose communication frequency with the off-network user is higher than a first preset frequency, comprises:

The communication objects in different networks from the off-network user and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency are eliminated from the communication network hypergraph to obtain a close communication network hypergraph of the off-network user.

In one implementation, after obtaining the communication data of an off-network user, a communication network hypergraph of the off-network user can be constructed based on the communication data. The communication network hypergraph records which communication objects the off-network user has communication exchanges with, as well as the specific communication methods, communication frequency, etc.

For example, as shown in FIG2, a communication social network hypergraph of an off-network user can be constructed based on the communication social data of the off-network user. The communication social network hypergraph can be represented in the form of a structural diagram, such as G = (V, E, W), where G represents a communication social network hypergraph, V is a node set, that is, users or organizations that have established communication intersections with the off-network user, E is an edge set, indicating that there is a communication relationship and contact with the off-network user, and W is an edge weight matrix, indicating the communication frequency. In this way, as shown in FIG2, V = {same network friend 1, same network friend 2, ..., same network friend n, different network friend 1, different network friend 2, ..., different network friend m, organization 1, organization 2, ..., organization t}, E = {off-network user-same network friend 1, off-network user-different network friend 1, off-network user-organization 1, ...}, W = {actively dialed 7 times, received messages 5 times, ...}.

Then, the communication social network hypergraph of the off-network user can be optimized to obtain a close social network hypergraph of the off-network user, including: deleting the user nodes of friends on different networks; deleting non-real user nodes, such as institutional user nodes; deleting weak relationship node users according to dimensions such as communication service time and frequency, such as deleting the user nodes of friends on the same network who have not communicated within 1 month, deleting the users of friends on the same network who have made less than 3 calls in the historical time period, etc. As shown in Figure 2, the area marked by the dotted rectangle is the user node that needs to be deleted, and the close social network hypergraph of the off-network user obtained after optimization is shown in Figure 3.

Through the close social network hypergraph of the off-network user, we can obtain the set of friends in the close social circle of the off-network user, that is, V′={friend 1 on the same network, friend 2 on the same network, …, friend t on the same network}. Corresponding to the close social network hypergraph of the off-network user shown in Figure 3, we can determine V′={friend 1 on the same network, friend 2 on the same network, friend 3 on the same network}.

In this way, by constructing a communication social network hypergraph of off-grid users, the communication object information of off-grid users can be more intuitively understood, making it easier to quickly and intuitively analyze the communication data of off-grid users.

Step 102: Acquire all communication objects in different networks of the first communication objects in the first communication object set within a second preset time period to obtain a second communication object set.

After obtaining the first communication object set of the off-network user, you can further obtain the inter-network communication objects of each first communication object in the first communication object set within a second preset time period to obtain a second communication object set consisting of the inter-network communication objects of all the first communication objects. Specifically, you can determine the inter-network communication objects of each first communication object in the time period by obtaining the communication data of each first communication object in the second preset time period. The second preset time period can be a period of time after the off-network user goes offline, such as one month or three months after going offline.

In this step, by obtaining the inter-network communication objects of all the first communication objects in the first communication object set within the second preset time period, the user range of the off-network user after changing the network can be preliminarily determined. The range of the off-network user can be locked based on the fact that the same user before and after leaving the network will have basically the same circle of friends.

It should be noted that in this step, a communication social network hypergraph of the off-network user's close social circle friends can also be constructed based on the communication data of the off-network user's close social circle friends determined in the aforementioned implementation mode, and the communication social network hypergraph can also be represented in the form of a structural diagram, such as G′＝(V, E, W), where G′ represents the communication social network hypergraph, V is a node set, that is, users or institutions with communication intersections established with the off-network user's close social circle friends, E is an edge set, indicating that there are communication relationships and exchanges with the off-network user's close social circle friends, and W is an edge weight matrix, indicating the number and attributes of various communication behaviors. The communication social network hypergraph of the off-network user's close social circle friends can be shown in Figure 4. In this way, based on the communication social network hypergraph of the off-network user's close social circle friends, the node set of all users in different networks in Figure 4 can be obtained, that is, V-different network＝{different network friend 1, different network friend 2, ..., different network friend g}, and the area marked by the dotted rectangular box in Figure 4 is the different network user node.

Step 103: Obtain a third communication object set for each second communication object in the second communication object set within a third preset time period, wherein the third communication object set for each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency.

For each second communication object in the second communication object set, the inter-network communication objects with which each second communication object communicates with the second communication object at a frequency higher than the second preset frequency within the third preset time period can be obtained respectively, to obtain the third communication object set for each second communication object, wherein the third preset time period can be a period of time after leaving the network, such as one month or three months after leaving the network, and the third preset time period can be the same as or different from the second preset time period. That is, in this step, the close inter-network communication object set of each second communication object can be obtained respectively.

That is to say, the nodes of heterogeneous users as shown in FIG. 4 can be calculated in turn using the method of constructing the user's close social network hypergraph, and a set of close social network hypergraphs of all heterogeneous users can be obtained, namely, a close social network hypergraph of G-heterogeneous users, where the close social network hypergraph of G-heterogeneous users = {G-the close social network hypergraph of heterogeneous user 1, G-the close social network hypergraph of heterogeneous user 2, ..., G-the close social network hypergraph of heterogeneous user g}.

Step 104: Compare the similarity of each third communication object set with the first communication object set respectively, and determine that the target second communication object corresponding to the third communication object set having the highest similarity with the first communication object set is the changed object of the off-network user.

In the embodiment of the present invention, since the changed number of the off-network user is likely to be a second communication object in the second communication object set, it is possible to determine whether the off-network user is the same user before and after leaving the network by comparing the close communication objects of the off-network user and each second communication object to see whether there are many common friends.

Specifically, the close inter-network communication objects of each second communication object can be compared with the close intra-network communication objects of the off-network user, that is, the similarity between each third communication object set and the first communication object set can be compared. If the similarity between a third communication object set and the first communication object set is greater, it means that the communication objects in the two are more consistent. Correspondingly, the possibility that the second communication object corresponding to the third communication object set is the same user as the off-network user is also greater. Therefore, after comparing each third communication object set with the first communication object set respectively, the target second communication object corresponding to the third communication object set with the highest similarity to the first communication object set can be determined as the changed object of the off-network user.

Optionally, the comparing the similarity of each third communication object set with the first communication object set respectively includes:

Based on the number of identical communication objects in the first communication object set and each third communication object set, the similarity between the off-network user and each second communication object is determined.

In one implementation, the similarity between the off-network user and each second communication object can be determined by comparing the number of identical communication objects in the first communication object set and each third communication object set. Specifically, the more identical communication objects, or common friends, the higher the similarity between the two, and vice versa. For example, when comparing the first communication object set with each communication object in each third communication object set, if it is found that the number of communication objects with the same number as that in the first communication object set and a certain third communication object set is the largest, it can be determined that the second communication object corresponding to the third communication object set is the changed number of the off-network user.

Of course, when comparing the similarity of two communication object sets, we can further compare the communication frequency between each second communication object and the common friend. The higher the communication frequency, the higher the similarity, and the greater the possibility that it is the same user before and after leaving the network.

In this way, by determining the similarity between the off-network user and each second communication object based on the number of common friends in the two communication object sets, it is possible to ensure that the comparison result is relatively accurate.

That is, when comparing the similarity between the off-network user and each second communication object, the off-network user's close social network hypergraph can be matched one by one with each subgraph in the close social network hypergraph of the G-different network user to complete the similarity calculation, and the most similar one is the off-network user node.

Specifically, the off-network user node can be recorded as x. For each off-network user node y, the similarity between the two user nodes can be calculated based on common friends. The calculation formula is as follows: Among them, _Sxy is the similarity, Γ(x) is the set of close friends of the off-network user node x, Γ(y) is the set of close friends of the off-network user node y, k(x) is the number of close friends of the off-network user node x, k(y) is the number of close friends of the off-network user node y, that is, the more common friends two nodes have and the greater the weight of the edges with common friends, the more similar the two nodes are, and the greater the possibility that they are the same user before and after leaving the network.

Optionally, after step 104, the method further includes:

Determining the permanent location information of the off-network user;

The information of the target second communication object and the resident location information are pushed to the marketing terminal.

That is, after determining the changed off-network user information, the off-network user's permanent location information can be further obtained. Specifically, the user's nighttime permanent location can be calculated based on the terminal positioning data used by the off-network user within a certain period, such as one month before leaving the network, and then the grid information or cell information of the user can be determined. Then, the off-network user's permanent location information and the target second communication object's information, such as the mobile phone number, can be sent to a marketing terminal, such as a grid manager, so that the target operator can carry out accurate secondary business promotion for the identified off-network users and ensure the scale of the current user volume.

Of course, in order to improve service quality, the background data of off-grid users can be further analyzed, such as analysis based on user behavior data and network quality data before leaving the network, to obtain the reasons for leaving the network, and push the reasons to the grid manager to facilitate subsequent targeted improvement of service quality and avoid the loss of existing network customers.

The off-network user identification method of the embodiment of the present invention obtains the first communication object set of the off-network user within the first preset time period, wherein the first communication object set is a set of same-network communication objects whose communication frequency with the off-network user is higher than the first preset frequency; obtains the different-network communication objects of all the first communication objects in the first communication object set within the second preset time period to obtain the second communication object set; obtains the third communication object set of each second communication object in the second communication object set within the third preset time period, wherein the third communication object set of each second communication object is a set of different-network communication objects whose communication frequency with the second communication object is higher than the second preset frequency; and compares the similarity of each third communication object set with the first communication object set respectively, and determines that the target second communication object corresponding to the third communication object set with the highest similarity to the first communication object set is the object after the off-network user is changed. In this way, by accurately identifying the changed information of the off-network user based on the communication data of the off-network user, the identification accuracy of the off-network user can be improved, and then the off-network user can be promoted in a targeted manner to improve the conversion rate.

The embodiment of the present invention further provides an off-network user identification device. See FIG5 , which is a structural diagram of the off-network user identification device provided by the embodiment of the present invention. Since the principle of solving the problem by the off-network user identification device is similar to the off-network user identification method in the embodiment of the present invention, the implementation of the off-network user identification device can refer to the implementation of the method, and the repeated parts will not be repeated.

As shown in FIG5 , the off-network user identification device 500 includes:

A first acquisition module 501 is used to acquire a first communication object set of an off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency;

A second acquisition module 502 is used to acquire all the first communication objects in the first communication object set within a second preset time period to obtain a second communication object set;

A third acquisition module 503 is used to acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency;

The first determining module 504 is used to compare the similarity between each third communication object set and the first communication object set, and determine that the target second communication object corresponding to the third communication object set with the highest similarity to the first communication object set is the changed object of the off-network user.

Optionally, the first acquisition module 501 includes:

An acquisition unit, configured to acquire communication data of an off-network user within a first preset time period, wherein the communication data includes a communication object and a communication frequency;

The determination unit is used to determine the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency according to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are same-network users, so as to obtain a first communication object set.

Optionally, the first acquisition module 501 further includes:

A construction unit, configured to construct a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user;

The determining unit is used to eliminate the communication objects in the communication network hypergraph that are in different networks from the off-network user, and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency, to obtain a close communication network hypergraph of the off-network user.

Optionally, the first determining module 504 is configured to determine the similarity between the off-network user and each second communication object based on the number of identical communication objects in the first communication object set and each third communication object set.

Optionally, the off-network user identification device 500 further includes:

A second determination module is used to determine the permanent location information of the off-network user;

The push module is used to push the information of the target second communication object and the permanent location information to the marketing terminal.

The off-network user identification device provided in the embodiment of the present invention can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated in this embodiment.

The off-network user identification device 500 of the embodiment of the present invention obtains the first communication object set of the off-network user within the first preset time period, wherein the first communication object set is a set of communication objects on the same network whose communication frequency with the off-network user is higher than the first preset frequency; obtains the communication objects of different networks of all the first communication objects in the first communication object set within the second preset time period to obtain the second communication object set; obtains the third communication object set of each second communication object in the second communication object set within the third preset time period, wherein the third communication object set of each second communication object is a set of communication objects on different networks whose communication frequency with the second communication object is higher than the second preset frequency; respectively compares the similarity of each third communication object set with the first communication object set, and determines that the target second communication object corresponding to the third communication object set with the highest similarity to the first communication object set is the object after the off-network user is changed. In this way, by accurately identifying the changed information of the off-network user based on the communication data of the off-network user, the identification accuracy of the off-network user can be improved, and then the off-network user can be promoted in a targeted manner to improve the conversion rate.

The embodiment of the present invention also provides an off-network user identification device. Since the principle of solving the problem by the off-network user identification device is similar to that of the off-network user identification method in the embodiment of the present invention, the implementation of the off-network user identification device can refer to the implementation of the method, and the repeated parts will not be repeated. As shown in FIG6, the off-network user identification device in the embodiment of the present invention includes: a processor 600, which is used to read the program in the memory 620 and execute the following process:

Acquire a first communication object set of the off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency;

Acquire all the communication objects of the first communication object in the first communication object set in the second preset time period to obtain a second communication object set;

Acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency;

The similarity between each third communication object set and the first communication object set is compared respectively, and the target second communication object corresponding to the third communication object set having the highest similarity to the first communication object set is determined as the changed object of the off-network user.

The transceiver 610 is configured to receive and send data under the control of the processor 600 .

In FIG. 6 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 600 and various circuits of memory represented by memory 620 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 610 may be a plurality of components, namely, a transmitter and a transceiver, providing a unit for communicating with various other devices on a transmission medium. The processor 600 is responsible for managing the bus architecture and general processing, and the memory 620 may store data used by the processor 600 when performing operations.

Optionally, the processor 600 is further configured to read a program in the memory 620 and execute the following steps:

Acquire communication data of the off-network user within a first preset time period, the communication data including a communication object and a communication frequency;

According to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are on the same network, the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency are determined to obtain a first communication object set.

Optionally, the processor 600 is further configured to read a program in the memory 620 and execute the following steps:

Constructing a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user;

The communication objects in different networks from the off-network user and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency are eliminated from the communication network hypergraph to obtain a close communication network hypergraph of the off-network user.

Optionally, the processor 600 is further configured to read a program in the memory 620 and execute the following steps:

Based on the number of identical communication objects in the first communication object set and each third communication object set, the similarity between the off-network user and each second communication object is determined.

Optionally, the processor 600 is further configured to read a program in the memory 620 and execute the following steps:

Determining the permanent location information of the off-network user;

The information of the target second communication object and the resident location information are pushed to the marketing terminal.

The off-network user identification device provided in the embodiment of the present invention can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated in this embodiment.

In addition, the computer-readable storage medium of the embodiment of the present invention is used to store a computer program, and the computer program can be executed by a processor to implement the following steps:

Acquire a first communication object set of the off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency;

Acquire all the communication objects of the first communication object in the first communication object set in the second preset time period to obtain a second communication object set;

Acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency;

The similarity between each third communication object set and the first communication object set is compared respectively, and the target second communication object corresponding to the third communication object set having the highest similarity to the first communication object set is determined as the changed object of the off-network user.

Optionally, obtaining a first communication object set of the off-network user within a first preset time period includes:

Acquire communication data of the off-network user within a first preset time period, the communication data including a communication object and a communication frequency;

According to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are on the same network, the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency are determined to obtain a first communication object set.

Optionally, after acquiring the communication data of the off-network user within the first preset time period, the method further includes:

Constructing a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user;

The determining, according to the communication frequency between each communication object and the off-network user, and whether each communication object and the off-network user are on the same network, a same-network communication object whose communication frequency with the off-network user is higher than a first preset frequency, comprises:

The communication objects in different networks from the off-network user and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency are eliminated from the communication network hypergraph to obtain a close communication network hypergraph of the off-network user.

Optionally, the comparing the similarity of each third communication object set with the first communication object set respectively includes:

Based on the number of identical communication objects in the first communication object set and each third communication object set, the similarity between the off-network user and each second communication object is determined.

Optionally, after determining that the target second communication object corresponding to the third communication object set having the highest similarity to the first communication object set is the changed object of the off-network user, the method further includes:

Determining the permanent location information of the off-network user;

The information of the target second communication object and the resident location information are pushed to the marketing terminal.

In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims (9)

1. A method for identifying an off-network user, comprising: Acquire a first communication object set of the off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency; Acquire all the communication objects of the first communication object in the first communication object set in the second preset time period to obtain a second communication object set; Acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency; Comparing the similarity of each third communication object set with the first communication object set respectively, and determining that the target second communication object corresponding to the third communication object set having the highest similarity with the first communication object set is the changed object of the off-network user; The comparing the similarity between each third communication object set and the first communication object set respectively includes: Determining the similarity between the off-network user and each second communication object based on the number of identical communication objects in the first communication object set and each third communication object set; Among them, the first preset time period is a period of time before the off-network user goes offline; the second preset time period is a period of time after the off-network user goes offline; and the third preset time period is a period of time after the off-network user goes offline. 2. The method according to claim 1, wherein the step of obtaining the first communication object set of the off-network user within the first preset time period comprises: Acquire communication data of the off-network user within a first preset time period, the communication data including a communication object and a communication frequency; According to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are on the same network, the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency are determined to obtain a first communication object set. 3. The method according to claim 2, characterized in that after obtaining the communication data of the off-network user within the first preset time period, the method further comprises: Constructing a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user; The determining, according to the communication frequency between each communication object and the off-network user, and whether each communication object and the off-network user are on the same network, a same-network communication object whose communication frequency with the off-network user is higher than a first preset frequency, comprises: The communication objects in different networks from the off-network user and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency are eliminated from the communication network hypergraph to obtain a close communication network hypergraph of the off-network user. 4. The method according to claim 1, characterized in that after determining that the target second communication object corresponding to the third communication object set having the highest similarity to the first communication object set is the object after the off-network user is changed, the method further comprises: Determining the permanent location information of the off-network user; The information of the target second communication object and the resident location information are pushed to the marketing terminal. 5. An off-network user identification device, comprising: A first acquisition module, used to acquire a first communication object set of an off-network user within a first preset time period, wherein the first communication object set is a collection of same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency; A second acquisition module, configured to acquire all communication objects of the first communication object in the first communication object set within a second preset time period, to obtain a second communication object set; A third acquisition module, used to acquire a third communication object set of each second communication object in the second communication object set within a third preset time period, wherein the third communication object set of each second communication object is a set of communication objects in different networks whose communication frequency with the second communication object is higher than the second preset frequency; A first determination module, configured to compare the similarity of each third communication object set with the first communication object set, and determine that the target second communication object corresponding to the third communication object set having the highest similarity with the first communication object set is the changed object of the off-network user; The first determination module is further used to determine the similarity between the off-network user and each second communication object based on the number of identical communication objects in the first communication object set and each third communication object set; Among them, the first preset time period is a period of time before the off-network user goes offline; the second preset time period is a period of time after the off-network user goes offline; and the third preset time period is a period of time after the off-network user goes offline. 6. The off-network user identification device according to claim 5, characterized in that the first acquisition module comprises: An acquisition unit, configured to acquire communication data of an off-network user within a first preset time period, wherein the communication data includes a communication object and a communication frequency; The determination unit is used to determine the same-network communication objects whose communication frequency with the off-network user is higher than a first preset frequency according to the communication frequency between each communication object and the off-network user and whether each communication object and the off-network user are on the same network, so as to obtain a first communication object set. 7. The off-network user identification device according to claim 6, wherein the first acquisition module further comprises: A construction unit, configured to construct a communication network hypergraph of the off-network user according to the communication data, wherein the communication network hypergraph includes communication objects and communication frequencies between each communication object and the off-network user; The determination unit is used to eliminate the communication objects in the communication network hypergraph that are in different networks from the off-network user, and the communication objects whose communication frequency with the off-network user is lower than or equal to the first preset frequency, to obtain a close communication network hypergraph of the off-network user. 8. An off-network user identification device, comprising: a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor; characterized in that the processor is used to read the program in the memory to implement the steps in the off-network user identification method as described in any one of claims 1 to 4. 9. A computer-readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps in the off-network user identification method according to any one of claims 1 to 4.