CN110557351A

CN110557351A - Method and apparatus for generating information

Info

Publication number: CN110557351A
Application number: CN201810539414.XA
Authority: CN
Inventors: 郑桦炯; 刘玉娇
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Baidu Online Network Technology Beijing Co Ltd; Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2018-05-30
Filing date: 2018-05-30
Publication date: 2019-12-10
Anticipated expiration: 2038-05-30
Also published as: CN110557351B

Abstract

the embodiment of the application discloses a method and a device for generating information. One embodiment of the method comprises: aiming at a target application in at least one target application, acquiring a user login account information subset and/or a user behavior information subset in the target application in a target time period as a user information subset; selecting user information aiming at the same user side from the user information set for aggregation based on the cache data identification set and/or the equipment identification set; and for a user side in at least one user side related to the aggregated user information, determining whether a natural person using the user side changes or not based on the aggregated user information for the user side, and if so, generating information for representing that the natural person using the user side changes. The embodiment can accurately identify whether the natural person using the user terminal is changed.

Description

Method and apparatus for generating information

Technical Field

the embodiment of the application relates to the technical field of computers, in particular to a method and a device for generating information.

Background

Currently, as mobile devices are updated, users are increasingly replacing mobile devices (e.g., cell phones, smartwatches, etc.). The same user end may be used by multiple user ends, and the same user end may also be used by multiple natural persons, because when the natural person using the user end changes, the information pushed to the user end will also change. Therefore, it is important to accurately identify whether a natural person using the user terminal has changed.

Disclosure of Invention

The embodiment of the application provides a method and a device for generating information.

in a first aspect, an embodiment of the present application provides a method for generating information, including: for a target application in at least one target application, acquiring a user login account information subset and/or a user behavior information subset in the target application as a user information subset in a target time period, wherein the user login account information comprises a user login account and a device identifier of a user side associated with the user login account, and the user behavior information comprises behavior information and at least one of the following items associated with the behavior information: using the cache data identification of the cache data stored by the user side of the target application and the equipment identification of the user side using the target application; selecting user information aiming at the same user side from a user information set for aggregation based on a cache data identification set and/or an equipment identification set, wherein the user information set is composed of at least one user information subset acquired from at least one target application; and for a user side in at least one user side related to the aggregated user information, determining whether a natural person using the user side changes or not based on the aggregated user information for the user side, and if so, generating information for representing that the natural person using the user side changes.

In some embodiments, determining whether a natural person using the user terminal has changed based on the aggregated user information for the user terminal includes: extracting a characteristic vector from the behavior information in the aggregated user behavior information for the user side, and inputting the characteristic vector into a pre-trained natural person change recognition model to obtain a natural person change recognition result of the user side, wherein the natural person change recognition model is used for representing the corresponding relationship between the characteristic vector and the natural person change recognition result, and the natural person change recognition result is used for indicating whether a natural person using the user side is changed or not.

In some embodiments, the natural person alteration recognition model is trained by: acquiring a training sample set, wherein the training sample comprises a characteristic vector extracted from the behavior information aiming at the sample user side and a natural person change recognition result of the sample user side; and taking the feature vectors in the training samples in the training sample set as input, taking the natural person change recognition result of the sample user side corresponding to the input feature vectors as output, and training to obtain a natural person change recognition model.

In some embodiments, after selecting the user information for the same user terminal in the user information set for aggregation, the method further includes: for a user terminal of at least one user terminal related to the aggregated user information, determining a use time period in which the user terminal is used for a target application of at least one target application as a first time period, and executing the following account number selection steps: selecting a user login account with the longest login days in a first time period from at least one user login account for performing account login by using the user side, and determining the user login account with the longest login days as a first target account corresponding to a second time period, wherein the second time period is a time period formed by the earliest use time and the latest use time of the user login account with the longest login days in the first time period; selecting a user login account meeting preset login conditions in a second time period from at least one user login account as a second target account corresponding to the second time period; determining whether a time period other than the second time period exists within the first time period; in response to determining that no time period other than the second time period exists in the first time period, generating a corresponding relation table of the user side, wherein the corresponding relation table comprises corresponding relations between the second time period and the first target account and between the second time period and the second target account; and in response to determining that time periods other than the second time period exist in the first time period, determining the determined time period as the first time period, and continuing to execute the account selecting step.

In some embodiments, after generating the correspondence table of the user terminal, the method further includes: in response to determining that at least two second time periods exist in the corresponding relation table, determining whether the same second target account exists in at least two second target accounts corresponding to the at least two second time periods; and in response to determining that the same second target account exists, determining at least two first target accounts corresponding to the same second target account as user login accounts of the same natural person.

In some embodiments, determining whether a natural person using the user terminal has changed based on the aggregated user information for the user terminal includes: acquiring a corresponding relation table of other user sides except the user side in at least one user side; determining whether a first target account in a corresponding relation table of the user side exists in the corresponding relation tables of other user sides; in response to determining that the first target account exists in the corresponding relationship table of the user side, determining that a natural person using the user side is changed if at least one of the following conditions is met: the determined login days of the first target account on other user sides are larger than the determined login days of the first target account on the user side, wherein the determined login days of the first target account on other user sides are obtained in advance; in the corresponding relation table of the user side, the determined first target account does not exist in at least one first target account corresponding to a target second time period, wherein the target second time period comprises a second time period which is later than the target time in at least one second time period in the corresponding relation table of the user side, the target time comprises a login starting time when the determined first target account logs in on other user sides, and the login starting time is obtained in advance.

In some embodiments, the device identification of the user end comprises at least one of: media access control address of the user terminal, advertisement identifier of the user terminal and mobile phone serial number of the user terminal; and selecting user information aiming at the same user side from the user information set for aggregation based on the cache data identification set and/or the equipment identification set, wherein the method comprises the following steps: selecting at least one user behavior information including a device identifier from the user information set, selecting the user behavior information aiming at the same user side from the at least one user behavior information by utilizing a preset device information table, and aggregating the selected user behavior information, wherein the device information table is used for representing the corresponding relation among a media access control address of the user side, an advertisement identifier of the user side and a mobile phone serial number of the user side.

in some embodiments, selecting, based on the cached data identification set and/or the device identification set, user information for the same user side from the user information sets for aggregation includes: for a target application in at least one target application, determining whether a cache data identifier of a user in other target applications, which is associated with user identification information in the target application, is included in a log of the target application, and if so, aggregating user behavior information including the determined user identification information and user behavior information including the determined cache data identifier, wherein the user identification information includes at least one of the following: the other target applications are target applications except the target application in at least one target application.

In some embodiments, the behavior information includes at least one of positioning information of the user terminal in a preset first time period and positioning information of the user terminal in a preset second time period, a resident internet protocol address of the user terminal in the preset first time period and a resident internet protocol address of the user terminal in the preset second time period, network information of a wireless network to which the user terminal is connected in the preset first time period, and network information of a wireless network to which the user terminal is connected in the preset second time period, wherein the resident internet protocol address includes an internet protocol address meeting a preset condition in at least one internet protocol address allocated to the user terminal.

In a second aspect, an embodiment of the present application provides an apparatus for generating information, including: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is configured to acquire a user login account information subset and/or a user behavior information subset in a target application as a user information subset in a target time period, the user login account information comprises a user login account and a device identifier of a user terminal associated with the user login account, and the user behavior information comprises behavior information and at least one of the following items associated with the behavior information: using the cache data identification of the cache data stored by the user side of the target application and the equipment identification of the user side using the target application; the aggregation unit is configured to select user information aiming at the same user side from the user information sets for aggregation based on the cache data identification set and/or the equipment identification set, wherein the user information sets are composed of at least one user information subset acquired from at least one target application; and the generating unit is configured to determine whether the natural person using the user side changes or not according to the aggregated user information of the user side, and if so, generate information for representing that the natural person using the user side changes.

In some embodiments, the generating unit is further configured to determine whether a natural person using the user terminal is changed based on the aggregated user information for the user terminal as follows: extracting a characteristic vector from the behavior information in the aggregated user behavior information for the user side, and inputting the characteristic vector into a pre-trained natural person change recognition model to obtain a natural person change recognition result of the user side, wherein the natural person change recognition model is used for representing the corresponding relationship between the characteristic vector and the natural person change recognition result, and the natural person change recognition result is used for indicating whether a natural person using the user side is changed or not.

in some embodiments, the apparatus further comprises an account selecting unit configured to: for a user terminal of at least one user terminal related to the aggregated user information, determining a use time period in which the user terminal is used for a target application of at least one target application as a first time period, and executing the following account number selection steps: selecting a user login account with the longest login days in a first time period from at least one user login account for performing account login by using the user side, and determining the user login account with the longest login days as a first target account corresponding to a second time period, wherein the second time period is a time period formed by the earliest use time and the latest use time of the user login account with the longest login days in the first time period; selecting a user login account meeting preset login conditions in a second time period from at least one user login account as a second target account corresponding to the second time period; determining whether a time period other than the second time period exists within the first time period; in response to determining that no time period other than the second time period exists in the first time period, generating a corresponding relation table of the user side, wherein the corresponding relation table comprises corresponding relations between the second time period and the first target account and between the second time period and the second target account; and in response to determining that time periods other than the second time period exist in the first time period, determining the determined time period as the first time period, and continuing to execute the account selecting step.

In some embodiments, the account number selecting unit is further configured to: in response to determining that at least two second time periods exist in the corresponding relation table, determining whether the same second target account exists in at least two second target accounts corresponding to the at least two second time periods; and in response to determining that the same second target account exists, determining at least two first target accounts corresponding to the same second target account as user login accounts of the same natural person.

In some embodiments, the generating unit is further configured to determine whether a natural person using the user terminal is changed based on the aggregated user information for the user terminal as follows: acquiring a corresponding relation table of other user sides except the user side in at least one user side; determining whether a first target account in a corresponding relation table of the user side exists in the corresponding relation tables of other user sides; in response to determining that the first target account exists in the corresponding relationship table of the user side, determining that a natural person using the user side is changed if at least one of the following conditions is met: the determined login days of the first target account on other user sides are larger than the determined login days of the first target account on the user side, wherein the determined login days of the first target account on other user sides are obtained in advance; in the corresponding relation table of the user side, the determined first target account does not exist in at least one first target account corresponding to a target second time period, wherein the target second time period comprises a second time period which is later than the target time in at least one second time period in the corresponding relation table of the user side, the target time comprises a login starting time when the determined first target account logs in on other user sides, and the login starting time is obtained in advance.

In some embodiments, the device identification of the user end comprises at least one of: media access control address of the user terminal, advertisement identifier of the user terminal and mobile phone serial number of the user terminal; and the aggregation unit is further used for selecting the user information aiming at the same user terminal from the user information set for aggregation based on the cache data identification set and/or the equipment identification set as follows: selecting at least one user behavior information including a device identifier from the user information set, selecting the user behavior information aiming at the same user side from the at least one user behavior information by utilizing a preset device information table, and aggregating the selected user behavior information, wherein the device information table is used for representing the corresponding relation among a media access control address of the user side, an advertisement identifier of the user side and a mobile phone serial number of the user side.

In some embodiments, the aggregation unit is further configured to select, based on the cached data identification set and/or the device identification set, user information for the same user terminal from among the user information sets to aggregate, as follows: for a target application in at least one target application, determining whether a cache data identifier of a user in other target applications, which is associated with user identification information in the target application, is included in a log of the target application, and if so, aggregating user behavior information including the determined user identification information and user behavior information including the determined cache data identifier, wherein the user identification information includes at least one of the following: the other target applications are target applications except the target application in at least one target application.

in a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement a method as in any embodiment of a method for generating information.

In a fourth aspect, embodiments of the present application provide a computer-readable medium on which a computer program is stored, which when executed by a processor, implements a method as in any one of the embodiments of the method for generating information.

according to the method and the device for generating information, by aiming at a target application in at least one target application, a user login account information subset and/or a user behavior information subset in the target application are/is firstly acquired as a user information subset in a target time period. And then, based on the cache data identification set and/or the equipment identification set, selecting the user information aiming at the same user terminal from the user information set consisting of at least one user information subset acquired from the at least one target application for aggregation. And finally, for a user side in at least one user side related to the aggregated user information, determining whether a natural person using the user side changes or not based on the aggregated user information for the user side, and if so, generating information for representing that the natural person using the user side changes. Therefore, the user login account and/or the user behavior information on the user side are effectively utilized, and whether the natural person using the user side is changed or not is accurately identified.

drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for generating information according to the present application;

FIG. 3 is a schematic illustration of an application scenario of a method for generating information according to the present application;

FIG. 4 is a flow diagram of yet another embodiment of a method for generating information according to the present application;

FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for generating information according to the present application;

FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing an electronic device according to embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Fig. 1 shows an exemplary system architecture 100 to which embodiments of the method for generating information or the apparatus for generating information of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include clients 1011, 1012, 1013, networks 1021, 1022, a generation server 103, and an application server 104. A medium in which a network 1021 is used to provide communication links between clients 1011, 1012, 1013 and a generation server 1031; network 1022 is the medium used to provide communication links between generation server 103 and application server 104. The networks 1021, 1022 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

the generation server 103 may interact with the clients 1011, 1012, 1013 via the network 1021 to send or receive messages and the like. The clients 1011, 1012, 1013 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, social platform software, and the like.

The clients 1011, 1012, 1013 may be hardware or software. When the user terminals 1011, 1012, 1013 are hardware, they may be various electronic devices having a display screen and supporting information interaction, including but not limited to smart phones, smart watches, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop computers, and so on. When the clients 1011, 1012, 1013 are software, the software can be installed in the electronic devices listed above. It may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.

the generation server 103 may be a server providing various services, such as a background server analyzing the user login account information subset and/or the user behavior information subset in the target application acquired from the user terminals 1011, 1012, 1013 and the application server 104. The background server may perform processing such as analysis on the acquired user login account information subset and/or the acquired user behavior information subset, and generate a processing result (e.g., information used for representing that a natural person using the user side changes).

The production server 103 may interact with the application server 104 via the network 1022 to send or receive messages and the like. The application server 104 may store therein a subset of user login account information and/or a subset of user behavior information in the target application.

it should be noted that the method for generating information provided in the embodiment of the present application is generally executed by the generation server 103, and accordingly, the apparatus for generating information is generally disposed in the generation server 103.

The generation server 103 and the application server 104 may be hardware or software. When the generation server 103 and the application server 104 are hardware, they may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of user terminals, networks, generation servers, and application servers in fig. 1 are merely illustrative. There may be any number of clients, networks, production servers, and application servers, as desired for implementation.

With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating information in accordance with the present application is shown. The method for generating information comprises the following steps:

Step 201, for a target application of at least one target application, acquiring a user login account information subset and/or a user behavior information subset of the target application as a user information subset in a target time period.

In this embodiment, an executing subject (e.g., the generating server 103 shown in fig. 1) of the method for generating information may acquire, as the user information subset, a user login account information subset and/or a user behavior information subset in at least one target application within a target time period for the target application. The target application may be an application designated by a user, and it should be noted that the target application may include a browser. For a target application in at least one target application, the execution subject may obtain a user login account information subset and/or a user behavior information subset from a server of the target application, or may obtain the user login account information subset and/or the user behavior information subset from a user side where the target application is installed. The target time period may be a time period set according to a set of logic, e.g., the last month, the last three months, etc.; it may also be a time period designated by a person, for example, the next half of the last year, 9 months of the last year to 3 months of the present year, etc.

In this embodiment, the user login account information may include a user login account and a device identifier of a user terminal associated with the user login account. When a login request including a user login account is received, a device identifier of a user side sending the login request can be acquired, and the acquired device identifier of the user side can be determined as a device identifier of the user side associated with the user login account in the received login request. The user behavior information may include behavior information and at least one of the following associated with the behavior information: a cache data identification of the cache data (cookie) stored at the user side using the target application and a device identification of the user side using the target application. The behavior information may be related information characterizing the behavior of the user, for example, search behavior information, browse behavior information, and the like of the user in the target application. The cache data is a very small text file placed on the hard disk of the user side by the web server when the user browses a certain web site, and can record the user Identification (ID), password, browsed web page, dwell time and other information of the user. Generally speaking, for a certain target application, the cache data identifiers of the cache data stored by different user terminals are different. As an example, the first user behavior information obtained from the navigation class application may include behavior information "navigation route searched by user" and cache data identification "14367"; the second user behavior information obtained from the first browser may include behavior information "search information searched by the user" and a device identification "MAC (Media Access Control) address of the user side of 00-27-5A-12-99-43".

It should be noted that the user behavior information may further include a time period in which the behavior information occurs.

In some optional implementations of this embodiment, the behavior information may include at least one of: the method includes the steps of setting positioning information of a user side in a preset first time period, setting positioning information of the user side in a preset second time period, setting a resident Internet Protocol Address (IP Address) of the user side in the preset first time period, setting the resident Internet Protocol Address of the user side in the preset second time period, setting network information of a wireless network connected with the user side in the preset first time period, and setting network information of the wireless network connected with the user side in the preset second time period. The preset first period may be a period of working hours, for example, 9 am to 6 pm on a weekday. The preset second time period may be a rest time period, for example, 9 pm on weekdays to 8 am the following day. The resident ip address of the ue may include an ip address satisfying a predetermined condition among at least one ip address allocated by the ue. When the ue performs network connection, the ue is usually assigned an ip address, and the predetermined condition may include the ip address assigned by the ue with the highest frequency. The network information of the wireless network to which the user terminal is connected may include, but is not limited to, at least one of the following: the MAC address of the router to which the user terminal is connected and the name of the wireless network to which the user terminal is connected.

Step 202, based on the cache data identification set and/or the device identification set, selecting user information for the same user side from the user information set for aggregation.

In this embodiment, the execution main body may select, based on the cache data identifier set and/or the device identifier set, user information for the same user side from the user information sets for aggregation, where the user information set may be composed of at least one user information subset acquired in the at least one target application. The cache data identifier set is composed of cache data identifiers in the user behavior information including the cache data identifiers acquired in step 201. The device identifier in the device identifier set is composed of the device identifier in the user login account information acquired in step 201 and the device identifier in the user behavior information including the device identifier. For the cached data identifier in the cached data identifier set, the execution main body may aggregate the user information including the cached data identifier, and determine the aggregated user information as the user information for the same user side. For the device identifier in the device identifier set, the execution main body may aggregate the user information including the device identifier, and determine the aggregated user information as the user information for the same user side. In some optional implementations of this embodiment, the device identifier of the user end may include at least one of: a media access control address of the user terminal, an Identifier (IDFA) of the user terminal, and a Mobile phone serial number (IMEI) of the user terminal. The advertisement identifier of the user terminal is a unique identifier related to the equipment, and can be used for opening advertisements among different applications. The serial number of the Mobile phone at the user end may also be called an international Mobile equipment identity (imsi), which is used to identify each individual Mobile phone in a Global System for Mobile Communication (GSM).

In some optional implementations of this embodiment, the executing body may first select at least one piece of user behavior information including the device identifier in the user information set, that is, select at least one piece of user behavior information associated with the device identifier in the user information set. Then, the execution main body may select the user behavior information for the same user side from the selected at least one piece of user behavior information by using a preset device information table. The device information table may be used to represent a corresponding relationship between the mac address of the user side, the advertisement identifier of the user side, and the cell phone serial number of the user side, and it should be noted that the mac address of the user side, the advertisement identifier of the user side, and the cell phone serial number of the user side having the corresponding relationship are used to indicate the same user side. The execution main body may select the user behavior information having the correspondence relationship with the included device identifier, and aggregate the selected user behavior information, where the selected user behavior information is the user behavior information for the same user side.

As an example, the first user behavior information includes a device identifier of the user side as "MAC address 00-27-5A-12-99-43", the second user behavior information includes a device identifier of the user side as "advertisement identifier 1E2DFA89-496A-47FD-9941-DF1FC4E 6484A", the third user behavior information includes a device identifier of the user side as "mobile phone serial number 355065053311001/01", the execution subject finds, using the device information table, that there is a correspondence between the MAC address "00-27-5A-12-99-43", the advertisement identifier "1E 2DFA89-496A-47FD-9941-DF1FC4E 6484A" and the mobile phone serial number "355065053311001/01", and then the first user behavior information, the second user behavior information, and the third user behavior information are user behavior information for the same user side, the first user behavior information, the second user behavior information, and the third user behavior information may be aggregated.

in some optional implementations of the embodiment, for a target application in the at least one target application, the execution main body may first obtain a log in the target application. Thereafter, it may be determined whether cached data identifications of the user in other target applications associated with the user identification information of the user in the target application are included in the log of the target application. In some application scenarios, a user clicks a certain piece of information in a browser at a user side, if the information is from a certain application and the application is installed in the user side, a cache data identifier of cache data in the browser is sent to the application, and then the user side invokes the application to present the information clicked by the user, at this time, an association relationship between user identifier information of the user in the application and the cache data identifier of the cache data in the browser is recorded in a log of the application. Then, in response to determining that the log of the target application includes the cached data identifiers of the users in other target applications associated with the user identification information in the target application, the executing body may aggregate the user behavior information including the determined user identification information and the user behavior information including the determined cached data identifiers, where the user identification information may include at least one of: the cache data identification of the cache data stored in the user terminal and the equipment identification of the user terminal. As an example, if it is determined that the cache data of the first browser, which includes the cache data of the user associated with the MAC address "00-27-5A-12-99-43" of the user end in the first social application, in the log of the first social application is "16478", the executing entity may aggregate the user behavior information including the MAC address "00-27-5A-12-99-43" of the user end and the user behavior information including the cache data identification "16478". The other target application may be a target application other than the target application in the at least one target application.

it should be noted that, if the user behavior information includes a cache data identifier of cache data stored in the user side using the target application and a device identifier of the user side using the target application, the execution main body may aggregate a first user information subset obtained by aggregating using the device identifier and a second user information subset obtained by aggregating using the cache data identifier.

Step 203, for a user side of the at least one user side related to the aggregated user information, determining whether a natural person using the user side is changed based on the aggregated user information for the user side.

In this embodiment, for a ue of the at least one ue to which the aggregated ue information relates, the executing entity may determine whether a natural person using the ue is changed based on the aggregated ue information for the ue. Specifically, if the aggregated user information includes user login account information and user behavior information, the execution main body may first determine whether a matching degree between behavior information in user behavior information in a later preset time period and behavior information in user behavior information in a earlier preset time period is less than a preset matching degree threshold, and if the matching degree is less than the matching degree threshold, then, for a target application of the at least one target application, it may be determined whether a user login account with the highest login frequency or the highest login days in the target application in a preset time period after the time is the same as a user login account with the highest login frequency or the highest login days in the target application in a preset time period before the time is the same, and if the user login accounts are different, it may be determined whether a natural person using the user side has changed.

in some optional implementations of the embodiment, after the execution main body selects, in the user information set, user information for the same user terminal to aggregate, for a user terminal of at least one user terminal to which the aggregated user information relates, the execution main body may determine, as the first time period, a usage time period for using, by the user terminal, a target application in the at least one target application, where the usage time period is generally a usage time period for using, by the user terminal, all target applications installed by the user terminal and existing in the at least one target application. The executing subject may execute the following account selecting step:

Step one, selecting a user login account with the longest login days in a first time period from at least one user login account for performing account login by using the user side, and determining the user login account with the longest login days as a first target account corresponding to a second time period, wherein the second time period is a time period formed by the earliest use time and the latest use time of the user login account with the longest login days in the first time period. The earliest use time is generally the use time of the first use of the user login account in the first time period, wherein the login days of the user login account are the longest. The latest use time is generally the use time of the last use of the user login account in the first time period, wherein the login days are longest. The first target account number may also be referred to as a primary account number, and may be considered as an account number that is used most frequently and for the longest time by the user. As an example, if the first time period is 1 month and 1 day to 5 months and 31 days, the user login accounts logged in by using the user side are account a, account B, account C, account D and account E, if the login day number of account a is 20 days, the login day number of account B is 10 days, the login day number of account C is 60 days, the login day number of account D is 90 days, and the login day number of account E is 8 days, the execution main body may select account D with the longest login day number in a period from 1 month and 1 day to 5 months and 31 days, if the earliest use time of account D in a period from 1 month and 1 day to 5 months and 31 days is 1 month and the latest use time is 4 months and 30 days, the second time period is 1 month and 4 months and 30 days, the execution main body may determine account D as the first target account corresponding to 1 month and 1 day to 4 months and 30 days.

And step two, the execution subject can select a user login account meeting preset login conditions in a second time period from the at least one user login account as a second target account corresponding to the second time period. The second target account number may also be referred to as a small number, which may be an occasional account number. The preset login condition may include that a ratio of login days of the user login account in the second time period to total login days at the user side is greater than a preset login day ratio threshold, and may also include that the login days are greater than a preset login day ratio threshold. For example, if the preset threshold value of the percentage of login days is 0.6, and if the total login days of the account a at the user terminal is 20 days, the ratio 1 of the 20 login days of the account a from 1 month and 1 day to 4 months and 30 days to the 20 login days at the user terminal is greater than the threshold value of the percentage of login days 0.6, and the executing entity may select the account a as the second target account corresponding to 1 month and 1 day to 4 months and 30 days.

step three, the executing body can determine whether time periods except the second time period exist in the first time period. As an example, if the first period is 1 month 1 day to 5 months 31 days and the second period is 1 month 1 day to 4 months 30 days, there are periods 5 months 1 day to 5 months 31 days other than the second period within the first period.

In response to determining that no time period other than the second time period exists in the first time period, the executing entity may generate a corresponding relationship table of the user side, where the corresponding relationship table may include a corresponding relationship between the second time period and the first target account number and the second target account number, that is, the corresponding relationship table includes a corresponding relationship between the time period, the primary account number in the time period, and the trumpet.

Here, in response to determining that a time period other than the second time period exists in the first time period, the executing entity may determine the determined time period as the first time period, and continue to execute the account selecting step, that is, continue to execute the first step, the second step, the third step, and the fourth step. As an example, the executing entity may determine the determined time period from 5 months 1 to 5 months 31 as the first time period, and continue to execute the account selecting step.

In some optional implementations of this embodiment, after generating the correspondence table of the user end, in response to determining that at least two second time periods exist in the correspondence table, the executing entity may determine whether the same second target account exists in at least two second target accounts corresponding to the at least two second time periods, that is, determine whether the small numbers corresponding to at least two different time periods of the user end are the same; in response to determining that the same second target account exists, the executing entity may determine at least two first target accounts corresponding to the same second target account as user login accounts of the same natural person, that is, if it is determined that the small numbers corresponding to at least two different time periods of the user terminal are the same, the primary accounts corresponding to the at least two different time periods may be determined as user login accounts of the same natural person.

In some optional implementation manners of this embodiment, the execution main body may first obtain the corresponding relationship table of the at least one ue excluding other ues. And then, determining whether the first target account in the corresponding relation table of the user side exists in the corresponding relation tables of the other user sides, namely determining whether the primary account which logs in at the user side logs in at the other user sides. In response to determining that the first target account exists in the correspondence table of the user side, if at least one of the following conditions one and two is satisfied, the executing entity may determine that a natural person using the user side is changed:

The first condition is as follows: the determined login days of the first target account on the other user sides are greater than the determined login days of the first target account on the user side, wherein the determined login days of the first target account on the other user sides are obtained in advance. For example, if the determined number of login days of the first target account on the other user terminal is 75 days, and the determined number of login days of the first target account on the user terminal is 60 days, the execution subject may determine that a natural person using the user terminal is changed.

And a second condition: in the correspondence table of the user side, the determined first target account does not exist in at least one first target account corresponding to a target second time period, where the target second time period includes a second time period after a target time in at least one second time period in the correspondence table of the user side, the target time includes a login start time at which the determined first target account logs in on the other user sides, and the login start time may be obtained in advance. As an example, if the login start time of the determined first target account for logging in the other user terminal is 5 months and 1 day, and three second time periods exist in the correspondence table of the user terminal, which are 1 month and 1 day to 3 months and 31 days, 4 months and 1 day to 5 months and 2 days, and 5 months and 3 days to 5 months and 31 days, respectively, the target second time period is 5 months and 3 days to 5 months and 31 days, and if the execution subject determines that the determined first target account does not exist in at least one first target account corresponding to 5 months and 3 days to 5 months and 31 days, it is determined that a natural person using the user terminal has changed.

And step 204, responding to the fact that the natural person using the user terminal is changed, and generating information for representing the change of the natural person using the user terminal.

in this embodiment, in response to determining that the natural person using the user terminal has changed in step 203, the execution subject may generate information for characterizing that the natural person using the user terminal has changed. The information for representing the change of the natural person using the user terminal may further include a change time at which the natural person using the user terminal is changed, and the change time may be obtained by inputting a feature vector extracted from behavior information in aggregated user behavior information for the user terminal into a pre-trained natural person change time recognition model. The information for representing the change of the natural person using the user terminal may further include a natural person identifier before the change and a natural person identifier after the change, and the natural person identifier may include at least one of a user login account number for representing the natural person and an equipment identifier for representing the natural person.

With continuing reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method for generating information according to the present embodiment. In the application scenario of fig. 3, the target applications are "first browser" and "second social-class application". The server 301 may first obtain, as a first user information subset 302, a subset of user behavior information in a "first browser" in a period of a target time period "1 month 1 day to 5 months 31 days, where the subset of user behavior information may include first user behavior information and second user behavior information, where the first user behavior information includes behavior information" a first search term set in 1 month 1 day to 3 months 31 days, "a second search term set in 4 months 1 day to 5 months 31 days," and a device identifier of a user terminal using the "first browser" where the MAC address is 00-27-5A-12-99-43, "and the second user behavior information includes behavior information" a first browsed web page information set in 1 month 1 day to 3 months 31 days, "a second browsed web page information set in 4 months 1 day to 5 months 31 days," and a device identifier of a user terminal using the "first browser" where the MAC address is 00-27-5A- 12-99-43". The server 301 obtains a user login account information subset in a "second social application" in a period of "1 month 1 day to 5 months 31 days" in a target time period as a second user information subset 303, where the user login account information subset may include first user login account information and second user login account information, the first user login account information includes a user login account a and a device identifier "MAC address is 00-27-5A-12-99-43" of a user terminal where the user login account a logs in, and the second user login information includes a user login account B and a device identifier "MAC address is 00-27-5A-12-99-43" of a user terminal where the user login account B logs in. Thereafter, the server 301 may select the user information for the same user terminal to aggregate in the user information set composed of the first user information subset 302 and the second user information subset 303 based on the cached data identification set and/or the device identification set 304. Here, since the device identifiers included in the first user behavior information, the second user behavior information, the first user login account information, and the second user login account information are the same, it is indicated that the first user behavior information, the second user behavior information, the first user login account information, and the second user login account information are user information for the same user side, and the server 301 may aggregate the first user behavior information, the second user behavior information, the first user login account information, and the second user login account information as user information (i.e., the user information 305 for the first user side in fig. 3) for a user side with a device identifier "MAC address 00-27-5A-12-99-43". Finally, regarding a user side (first user side) of the device identifier "MAC address is 00-27-5A-12-99-43" as an example for the user side of at least one user side related to the aggregated user information, since the category to which the search word in the first search word set of the first user side in 1 month and 1 day to 3 months and 31 days belongs is a cosmetic category, the category to which the search word in the second search word set of 4 months and 1 day to 5 months and 31 days belongs is a digital category; the category to which the browsing webpage information in the first browsing webpage information set from 1 month and 1 day to 3 months and 31 days belongs is a clothing category, and the category to which the browsing webpage information in the second browsing webpage information set from 4 months and 1 day to 5 months and 31 days belongs is an automobile category; since the user login account a is only logged in during the period from 1 month 1 to 3 months 31 and the user login account B is only logged in during the period from 4 months 1 to 5 months 31, the server 301 can specify that the natural person using the first user side is changed and generate the information 306 of the change of the natural person.

The method provided by the embodiment of the application accurately identifies whether the natural person using the user terminal changes or not by effectively utilizing the user login account and/or the user behavior information on the user terminal.

With further reference to fig. 4, a flow 400 of yet another embodiment of a method for generating information is shown. The flow 400 of the method for generating information comprises the steps of:

Step 401, for a target application of at least one target application, acquiring a user behavior information subset of the target application in a target time period as a user information subset.

And 402, selecting user information aiming at the same user side from the user information set for aggregation based on the cache data identification set and/or the equipment identification set.

In the present embodiment, the operations of steps 401-402 are substantially the same as the operations of steps 201-202, and are not described herein again.

step 403, for a user side of at least one user side related to the aggregated user information, extracting a feature vector from the behavior information in the aggregated user behavior information for the user side, and inputting the feature vector into a pre-trained natural person change recognition model to obtain a natural person change recognition result of the user side.

In this embodiment, for a ue of the at least one ue to which the aggregated ue information relates, the executing entity may first extract the feature vector from the behavior information in the aggregated ue behavior information for the ue. Here, the above feature vector may include differential behavior information between behavior information in a later preset time period and behavior information in a previous preset time period. Then, the execution agent may input the feature vector into a pre-trained natural person change recognition model to obtain a natural person change recognition result of the user end. Here, the obtained natural person change recognition result indicates whether or not the natural person using the user side has changed, and the natural person change recognition result may be a numerical value. The natural person alteration recognition result may include an alteration flag indicating that the natural person using the user side is altered, for example, the alteration flag may be 1. The natural person alteration recognition result may further include an unaltered flag indicating that the natural person using the user side is not altered, for example, the unaltered flag may be 0. The natural person alteration recognition model is used to represent the correspondence between the feature vector and the result of natural person alteration recognition. As an example, the natural person alteration recognition model may be a correspondence table in which correspondence between a plurality of feature vectors and a natural person alteration recognition result is stored, which is prepared in advance by a technician based on statistics of a large number of feature vectors and natural person alteration recognition results.

In some optional implementations of this embodiment, the natural person alteration recognition model may be obtained by training:

First, a training sample set may be obtained, where the training sample includes a feature vector extracted from behavior information for a sample user side and a natural person change recognition result of the sample user side.

Then, a machine learning method may be used to train the feature vectors in the training samples in the training sample set as input, and the natural person change recognition result at the sample user end corresponding to the input feature vectors as output, so as to obtain a natural person change recognition model. Specifically, the electronic device may use a Naive Bayesian Model (NBM) or a Support Vector Machine (SVM) or other models for classification, use a feature Vector in a training sample in the training sample set as an input of the Model, use a result of natural person change recognition at a sample user side corresponding to the input feature Vector as an output of the Model, and train the Model by using a Machine learning method to obtain a natural person change recognition Model.

the natural person change recognition model may be trained in advance by the execution subject; the execution subject may acquire the obtained natural person alteration recognition model from the other electronic device after the other electronic device has trained the natural person alteration recognition model.

Step 404, determining whether the natural person alteration identification result indicates that the natural person using the user terminal is altered.

In this embodiment, the executing entity may determine whether the natural person alteration recognition result obtained in step 403 indicates that the natural person using the user terminal is altered. If the natural person alteration recognition result is the alteration flag, the execution main body may determine that the natural person alteration recognition result indicates that the natural person using the user terminal is altered.

Step 405, in response to determining that the natural person alteration identification result indicates that the natural person using the user terminal is altered, generating information for representing that the natural person using the user terminal is altered.

In this embodiment, in response to determining that the natural person alteration recognition result indicates that the natural person using the user terminal is altered in step 404, the execution main body may generate information for characterizing that the natural person using the user terminal is altered. The information for representing the change of the natural person using the user terminal may further include a change time at which the natural person using the user terminal is changed, and the change time may be obtained by inputting a feature vector extracted from behavior information in aggregated user behavior information for the user terminal into a pre-trained natural person change time recognition model. The information for representing the change of the natural person using the user terminal may further include a natural person identifier before the change and a natural person identifier after the change, and the natural person identifier may include at least one of a user login account number for representing the natural person and an equipment identifier for representing the natural person.

As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the flow 400 of the method for generating information in the present embodiment adds a step of determining whether a natural person using a user side has changed using a natural person alteration recognition model. Therefore, the scheme described in the embodiment can effectively solve the problem that whether the natural person changes or not cannot be identified under three conditions that no account is logged before and after the natural person changes, no account is logged after the account is logged before and after the natural person changes, and an account is logged after the account is logged before and after the natural person changes.

with further reference to fig. 5, as an implementation of the method shown in the above figures, the present application provides an embodiment of an apparatus for generating information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.

as shown in fig. 5, the apparatus 500 for generating information of the present embodiment includes: the obtaining unit 501 is configured to, for a target application of at least one target application, obtain, as a user information subset, a subset of user login account information and/or a subset of user behavior information in the target application in a target time period, where the user login account information includes a user login account and a device identifier of a user terminal associated with the user login account, and the user behavior information includes behavior information and at least one of the following items associated with the behavior information: using the cache data identification of the cache data stored by the user side of the target application and the equipment identification of the user side using the target application; the aggregation unit 502 is configured to select, based on the cache data identifier set and/or the device identifier set, user information for the same user side from the user information sets for aggregation, where the user information sets are composed of at least one user information subset acquired in at least one target application; the generating unit 503 is configured to determine, for a user terminal of the at least one user terminal to which the aggregated user information relates, whether a natural person using the user terminal is changed based on the aggregated user information for the user terminal, and if so, generate information for representing that the natural person using the user terminal is changed.

In this embodiment, specific processing of the acquiring unit 501, the aggregating unit 502, and the generating unit 503 of the apparatus 500 for generating information may refer to step 201, step 202, and step 203 in the corresponding embodiment of fig. 2.

In some optional implementations of the embodiment, for a user side of the at least one user side to which the aggregated user information relates, the generating unit 503 may first extract a feature vector from behavior information in the aggregated user behavior information for the user side. Here, the above feature vector may include differential behavior information between behavior information in a later preset time period and behavior information in a previous preset time period. Then, the generating unit 503 may input the feature vector to a pre-trained natural person change recognition model to obtain a natural person change recognition result of the user terminal. Here, the obtained natural person change recognition result indicates whether or not the natural person using the user side has changed, and the natural person change recognition result may be a numerical value. The natural person alteration recognition result may include an alteration flag indicating that the natural person using the user side is altered, for example, the alteration flag may be 1. The natural person alteration recognition result may further include an unaltered flag indicating that the natural person using the user side is not altered, for example, the unaltered flag may be 0. The natural person alteration recognition model is used to represent the correspondence between the feature vector and the result of natural person alteration recognition. As an example, the natural person alteration recognition model may be a correspondence table in which correspondence between a plurality of feature vectors and a natural person alteration recognition result is stored, which is prepared in advance by a technician based on statistics of a large number of feature vectors and natural person alteration recognition results.

In some optional implementations of the embodiment, the apparatus 500 for generating information may further include an account selecting unit (not shown in the figure), and after the user information for the same user terminal is selected from the user information set to be aggregated, for a user terminal of at least one user terminal related to the aggregated user information, the account selecting unit may determine, as the first time period, a usage time period for using the user terminal for a target application of the at least one target application, where the usage time period is generally a usage time period for using all target applications installed by the user terminal and existing in the at least one target application. The account selecting unit may perform the following account selecting steps:

step one, selecting a user login account with the longest login days in a first time period from at least one user login account for performing account login by using the user side, and determining the user login account with the longest login days as a first target account corresponding to a second time period, wherein the second time period is a time period formed by the earliest use time and the latest use time of the user login account with the longest login days in the first time period. The earliest use time is generally the use time of the first use of the user login account in the first time period, wherein the login days of the user login account are the longest. The latest use time is generally the use time of the last use of the user login account in the first time period, wherein the login days are longest. The first target account number may also be referred to as a primary account number, and may be considered as an account number that is used most frequently and for the longest time by the user. As an example, if the first time period is 1 month and 1 day to 5 months and 31 days, the user login accounts logged in by using the user side are account a, account B, account C, account D and account E, if the login days of account a is 20 days, the login days of account B is 10 days, the login days of account C is 60 days, the login days of account D is 90 days, and the login days of account E is 8 days, the account selection unit may select account D with the longest login days in a period from 1 month and 1 day to 5 months and 31 days, if the earliest use time of account D in a period from 1 month and 1 day to 5 months and 31 days is 1 month and the latest use time is 4 months and 30 days, the second time period is 1 month and 1 day to 4 months and 30 days, the account selection unit may determine account D as a first target account corresponding to 1 month and 1 day to 4 months and 30 days.

and step two, the account selecting unit may select, from the at least one user login account, a user login account satisfying a preset login condition in a second time period as a second target account corresponding to the second time period. The second target account number may also be referred to as a small number, which may be an occasional account number. The preset login condition may include that a ratio of login days of the user login account in the second time period to total login days at the user side is greater than a preset login day ratio threshold, and may also include that the login days are greater than a preset login day ratio threshold. For example, if the preset threshold value of the proportion of login days is 0.6, and if the total login days of the account a at the user terminal is 20 days, the ratio 1 of the login days 20 of the account a from 1 month and 1 day to 4 months and 30 days to the total login days 20 at the user terminal is greater than the threshold value of the proportion of login days 0.6, and the account selection unit may select the account a as the second target account corresponding to 1 month and 1 day to 4 months and 30 days.

step three, the account selecting unit may determine whether a time period other than the second time period exists in the first time period. As an example, if the first period is 1 month 1 day to 5 months 31 days and the second period is 1 month 1 day to 4 months 30 days, there are periods 5 months 1 day to 5 months 31 days other than the second period within the first period.

In response to determining that no time period other than the second time period exists in the first time period, the account selection unit may generate a corresponding relationship table of the user side, where the corresponding relationship table may include a corresponding relationship between the second time period and the first target account and the second target account, that is, the corresponding relationship table includes a corresponding relationship between the time period, the primary account and the small number in the time period.

Here, in response to determining that a time period other than the second time period exists in the first time period, the account selection unit may determine the determined time period as the first time period, and continue to perform the account selection step, that is, continue to perform the first step, the second step, the third step, and the fourth step. For example, the account selecting unit may determine the determined time period from 5 month 1 day to 5 month 31 day as the first time period, and continue to perform the account selecting step.

in some optional implementation manners of this embodiment, after generating the correspondence table of the user end, in response to determining that at least two second time periods exist in the correspondence table, the account selecting unit may determine whether the same second target account exists in at least two second target accounts corresponding to the at least two second time periods, that is, whether the small numbers corresponding to at least two different time periods of the user end are the same; in response to determining that the same second target account exists, the account selection unit may determine at least two first target accounts corresponding to the same second target account as user login accounts of the same natural person, that is, if it is determined that the small numbers corresponding to at least two different time periods of the user terminal are the same, the primary accounts corresponding to the at least two different time periods may be determined as user login accounts of the same natural person.

in some optional implementation manners of this embodiment, the generating unit 503 may first obtain a corresponding relationship table of other user sides except for the user side in the at least one user side. And then, determining whether the first target account in the corresponding relation table of the user side exists in the corresponding relation tables of the other user sides, namely determining whether the primary account which logs in at the user side logs in at the other user sides. In response to determining that the first target account exists in the correspondence table of the user side, the generating unit 503 may determine that the natural person using the user side is changed if at least one of the following conditions one and two is satisfied:

The first condition is as follows: the determined login days of the first target account on the other user sides are greater than the determined login days of the first target account on the user side, wherein the determined login days of the first target account on the other user sides are obtained in advance. For example, if the number of login days of the determined first target account on the other user side is 75 days, and the number of login days of the determined first target account on the user side is 60 days, the generating unit 503 may determine that the natural person using the user side is changed.

and a second condition: in the correspondence table of the user side, the determined first target account does not exist in at least one first target account corresponding to a target second time period, where the target second time period includes a second time period after a target time in at least one second time period in the correspondence table of the user side, the target time includes a login start time at which the determined first target account logs in on the other user sides, and the login start time may be obtained in advance. As an example, if the login start time of the determined first target account for logging in the other user terminal is 5 month and 1 day, and there are three second time periods in the correspondence table of the user terminal, which are 1 month and 1 day to 3 month and 31 days, 4 month and 1 day to 5 month and 2 days, and 5 month and 3 day to 5 month and 31 days, respectively, the target second time period is 5 month and 3 days to 5 month and 31 days, and if the generating unit 503 determines that there is no determined first target account in at least one first target account corresponding to 5 month and 3 to 5 month and 31 days, it is determined that a natural person using the user terminal has changed.

In some optional implementations of this embodiment, the device identifier of the user end may include at least one of: the media access control address of the user terminal, the advertisement identifier of the user terminal and the mobile phone serial number of the user terminal. The advertisement identifier of the user terminal is a unique identifier related to the equipment, and can be used for opening advertisements among different applications. The serial number of the mobile phone at the user end can also be called International Mobile Equipment Identity (IMEI), and is used for identifying each independent mobile phone in the global system for mobile communications (GSM).

In some optional implementations of this embodiment, the aggregation unit 502 may first select at least one piece of user behavior information including the device identifier from the user information set, that is, select at least one piece of user behavior information associated with the device identifier from the user information set. Then, the aggregation unit 502 may select the user behavior information for the same user side from the at least one selected user behavior information by using a preset device information table. The device information table may be used to represent a corresponding relationship between the mac address of the user side, the advertisement identifier of the user side, and the cell phone serial number of the user side, and it should be noted that the mac address of the user side, the advertisement identifier of the user side, and the cell phone serial number of the user side having the corresponding relationship are used to indicate the same user side. The aggregating unit 502 may select the user behavior information having the corresponding relationship between the included device identifiers, and aggregate the selected user behavior information, where the selected user behavior information is the user behavior information for the same user side.

in some optional implementations of the embodiment, for a target application in the at least one target application, the aggregation unit 502 may first obtain a log in the target application. Thereafter, it may be determined whether cached data identifications of the user in other target applications associated with the user identification information of the user in the target application are included in the log of the target application. In some application scenarios, a user clicks a certain piece of information in a browser at a user side, if the information is from a certain application and the application is installed in the user side, a cache data identifier of cache data in the browser is sent to the application, and then the user side invokes the application to present the information clicked by the user, at this time, an association relationship between user identifier information of the user in the application and the cache data identifier of the cache data in the browser is recorded in a log of the application. Then, in response to determining that the log of the target application includes the cached data identifiers of the users in other target applications, which are associated with the user identification information in the target application, the aggregating unit 502 may aggregate the user behavior information including the determined user identification information and the user behavior information including the determined cached data identifiers, where the user identification information may include at least one of: the cache data identification of the cache data stored in the user terminal and the equipment identification of the user terminal.

In some optional implementations of this embodiment, the behavior information may include at least one of: the positioning information of the user terminal in the preset first time period and the positioning information of the user terminal in the preset second time period, the resident internet protocol address of the user terminal in the preset first time period and the resident internet protocol address of the user terminal in the preset second time period, the network information of the wireless network connected with the user terminal in the preset first time period and the network information of the wireless network connected with the user terminal in the preset second time period. The preset first period may be a period of working hours, for example, 9 am to 6 pm on a weekday. The preset second time period may be a rest time period, for example, 9 pm on weekdays to 8 am the following day. The resident ip address of the ue may include an ip address satisfying a predetermined condition among at least one ip address allocated by the ue. When the ue performs network connection, the ue is usually assigned an ip address, and the predetermined condition may include the ip address assigned by the ue with the highest frequency. The network information of the wireless network to which the user terminal is connected may include, but is not limited to, at least one of the following: the MAC address of the router to which the user terminal is connected and the name of the wireless network to which the user terminal is connected.

Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with an electronic device (e.g., the generation server 103 of FIG. 1) implementing an embodiment of the invention is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Liquid Crystal Display (LCD) and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601. It should be noted that the computer readable medium mentioned above in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present invention may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, an aggregation unit, and a generation unit. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves. For example, the aggregation unit may also be described as "a unit that selects, based on the cached data identification set and/or the device identification set, the user information to be aggregated for the same user terminal in the user information set.

as another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: for a target application in at least one target application, acquiring a user login account information subset and/or a user behavior information subset in the target application as a user information subset in a target time period, wherein the user login account information comprises a user login account and a device identifier of a user side associated with the user login account, and the user behavior information comprises behavior information and at least one of the following items associated with the behavior information: using the cache data identification of the cache data stored by the user side of the target application and the equipment identification of the user side using the target application; selecting user information aiming at the same user side from a user information set for aggregation based on a cache data identification set and/or an equipment identification set, wherein the user information set is composed of at least one user information subset acquired from at least one target application; and for a user side in at least one user side related to the aggregated user information, determining whether a natural person using the user side changes or not based on the aggregated user information for the user side, and if so, generating information for representing that the natural person using the user side changes.

The foregoing description is only exemplary of the preferred embodiments of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention according to the present invention is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the scope of the invention as defined by the appended claims. For example, the above features and (but not limited to) features having similar functions disclosed in the present invention are mutually replaced to form the technical solution.

Claims

1. a method for generating information, comprising:

For a target application in at least one target application, acquiring a user login account information subset and/or a user behavior information subset in the target application as a user information subset in a target time period, wherein the user login account information comprises a user login account and a device identifier of a user side associated with the user login account, and the user behavior information comprises behavior information and at least one of the following items associated with the behavior information: using the cache data identification of the cache data stored by the user side of the target application and the equipment identification of the user side using the target application;

Selecting user information aiming at the same user side from a user information set for aggregation based on a cache data identification set and/or an equipment identification set, wherein the user information set is composed of at least one user information subset acquired from at least one target application;

And for a user side in at least one user side related to the aggregated user information, determining whether a natural person using the user side changes or not based on the aggregated user information for the user side, and if so, generating information for representing that the natural person using the user side changes.

2. The method of claim 1, wherein the determining whether the natural person using the ue is changed based on the aggregated ue information for the ue comprises:

Extracting a characteristic vector from behavior information in the aggregated user behavior information for the user side, and inputting the characteristic vector into a pre-trained natural person change recognition model to obtain a natural person change recognition result of the user side, wherein the natural person change recognition model is used for representing the corresponding relationship between the characteristic vector and the natural person change recognition result, and the natural person change recognition result is used for indicating whether a natural person using the user side is changed or not.

3. The method of claim 2, wherein the natural person alteration recognition model is trained by:

acquiring a training sample set, wherein the training sample comprises a characteristic vector extracted from the behavior information aiming at the sample user side and a natural person change recognition result of the sample user side;

and taking the feature vector in the training sample set as input, taking the natural person change recognition result of the sample user side corresponding to the input feature vector as output, and training to obtain a natural person change recognition model.

4. The method of claim 1, wherein after the selecting user information for the same user terminal in the user information set for aggregation, the method further comprises:

For a user terminal of at least one user terminal related to the aggregated user information, determining a use time period in which the user terminal is used for a target application of the at least one target application as a first time period, and executing the following account number selection steps: selecting a user login account with the longest login days in a first time period from at least one user login account for performing account login by using the user side, and determining the user login account with the longest login days as a first target account corresponding to a second time period, wherein the second time period is a time period formed by the earliest use time and the latest use time of the user login account with the longest login days in the first time period; selecting a user login account meeting preset login conditions in a second time period from the at least one user login account as a second target account corresponding to the second time period; determining whether a time period other than the second time period exists within the first time period; in response to determining that no time period except the second time period exists in the first time period, generating a corresponding relation table of the user side, wherein the corresponding relation table comprises corresponding relations between the second time period and the first target account and between the second time period and the second target account;

and in response to determining that time periods other than the second time period exist in the first time period, determining the determined time period as the first time period, and continuing to execute the account selecting step.

5. The method according to claim 4, wherein after the generating the correspondence table of the user terminal, the method further comprises:

In response to determining that at least two second time periods exist in the correspondence table, determining whether the same second target account exists in at least two second target accounts corresponding to the at least two second time periods;

and in response to the fact that the same second target account exists, determining at least two first target accounts corresponding to the same second target account as user login accounts of the same natural person.

6. The method of claim 5, wherein the determining whether the natural person using the ue is changed based on the aggregated ue information for the ue comprises:

Acquiring a corresponding relation table of other user sides except the user side in the at least one user side;

determining whether a first target account in the corresponding relation table of the user side exists in the corresponding relation tables of the other user sides;

In response to determining that the first target account exists in the corresponding relationship table of the user side, determining that a natural person using the user side is changed if at least one of the following conditions is met:

The determined login days of the first target account on the other user sides are larger than the determined login days of the first target account on the user side, wherein the determined login days of the first target account on the other user sides are obtained in advance;

In the correspondence table of the user side, the determined first target account does not exist in at least one first target account corresponding to a target second time period, where the target second time period includes a second time period after a target time in at least one second time period in the correspondence table of the user side, the target time includes a login start time at which the determined first target account logs in on the other user sides, and the login start time is obtained in advance.

7. The method of claim 1, wherein the device identification of the user terminal comprises at least one of: media access control address of the user terminal, advertisement identifier of the user terminal and mobile phone serial number of the user terminal; and

The selecting and aggregating the user information aiming at the same user side from the user information set based on the cache data identification set and/or the equipment identification set comprises:

Selecting at least one user behavior information including a device identifier from a user information set, selecting the user behavior information aiming at the same user side from the at least one user behavior information by utilizing a preset device information table, and aggregating the selected user behavior information, wherein the device information table is used for representing the corresponding relation among a media access control address of the user side, an advertisement identifier of the user side and a mobile phone serial number of the user side.

8. The method according to claim 1, wherein the selecting, for aggregation, user information for the same user terminal from among the user information sets based on the cached data identification set and/or the device identification set includes:

for a target application in the at least one target application, determining whether a cache data identifier of a user in another target application, which is associated with user identification information in the target application, is included in a log of the target application, and if so, aggregating user behavior information including the determined user identification information and user behavior information including the determined cache data identifier, wherein the user identification information includes at least one of the following: the other target applications are target applications except the target application in the at least one target application.

9. the method according to one of claims 1 to 8, wherein the behavior information includes at least one of positioning information of the user terminal in a preset first time period and positioning information of the user terminal in a preset second time period, a resident internet protocol address of the user terminal in the preset first time period and a resident internet protocol address of the user terminal in the preset second time period, network information of a wireless network to which the user terminal is connected in the preset first time period, and network information of a wireless network to which the user terminal is connected in the preset second time period, wherein the resident internet protocol address includes an internet protocol address satisfying a preset condition among at least one internet protocol address allocated to the user terminal.

10. An apparatus for generating information, comprising:

The device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is configured to acquire a user login account information subset and/or a user behavior information subset in a target application as a user information subset in a target time period, the user login account information comprises a user login account and a device identifier of a user terminal associated with the user login account, and the user behavior information comprises behavior information and at least one of the following items associated with the behavior information: using the cache data identification of the cache data stored by the user side of the target application and the equipment identification of the user side using the target application;

the aggregation unit is configured to select user information for the same user side from a user information set for aggregation based on a cache data identification set and/or an equipment identification set, wherein the user information set is composed of at least one user information subset acquired from the at least one target application;

And the generating unit is configured to determine whether the natural person using the user side changes or not according to the aggregated user information of the user side, and if so, generate information for representing that the natural person using the user side changes.

11. The apparatus of claim 10, wherein the generating unit is further configured to determine whether a natural person using the user terminal is changed based on the aggregated user information for the user terminal as follows:

12. the apparatus of claim 11, wherein the natural person alteration recognition model is trained by:

13. The apparatus of claim 10, further comprising an account selection unit configured to:

14. The apparatus of claim 13, wherein the account number selection unit is further configured to:

15. The apparatus of claim 14, wherein the generating unit is further configured to determine whether a natural person using the user terminal is changed based on the aggregated user information for the user terminal as follows:

16. the apparatus of claim 10, wherein the device identification of the user end comprises at least one of: media access control address of the user terminal, advertisement identifier of the user terminal and mobile phone serial number of the user terminal; and

The aggregation unit is further configured to select, based on the cache data identifier set and/or the device identifier set, user information for the same user side from the user information sets to aggregate, as follows:

17. The apparatus according to claim 10, wherein the aggregating unit is further configured to select, based on the cached data identification set and/or the device identification set, user information for a same user terminal from among the user information sets to aggregate, as follows:

18. The apparatus according to one of claims 10 to 17, wherein the behavior information includes at least one of positioning information of the user terminal in a preset first time period and positioning information of the user terminal in a preset second time period, a resident internet protocol address of the user terminal in the preset first time period and a resident internet protocol address of the user terminal in the preset second time period, network information of a wireless network to which the user terminal is connected in the preset first time period, and network information of a wireless network to which the user terminal is connected in the preset second time period, wherein the resident internet protocol address includes an internet protocol address satisfying a preset condition among at least one internet protocol address allocated to the user terminal.

19. An electronic device, comprising:

One or more processors;

a storage device having one or more programs stored thereon,

When executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.

20. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-9.