CN111953763B

CN111953763B - Business data pushing method and device and storage medium

Info

Publication number: CN111953763B
Application number: CN202010784149.9A
Authority: CN
Inventors: 马坚鸿
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-08-06
Filing date: 2020-08-06
Publication date: 2021-06-25
Anticipated expiration: 2040-08-06
Also published as: CN111953763A

Abstract

The embodiment of the invention discloses a business data pushing method, a business data pushing device and a storage medium, wherein the method comprises the following steps: acquiring a behavior log table of a game user in a game client, and extracting key behavior data information associated with the game user from the behavior log table; performing user portrait analysis on the key behavior data information to obtain user portrait information for representing the game user; when it is determined that a game user meets a data pushing condition based on user portrait information, business data information of K business types matched with the user portrait information is obtained, and prompt information corresponding to the business data information of the K business types is pushed to a game terminal corresponding to the game user, so that the game terminal displays the prompt information in a game display interface corresponding to a game client; k is a positive integer. By adopting the invention, the main contact of the prompt message can be realized, and the accuracy of data recommendation can be improved based on the user portrait information.

Description

Business data pushing method and device and storage medium

Technical Field

The present invention relates to the field of internet technologies, and in particular, to a method, an apparatus, and a storage medium for pushing service data.

Background

When recommending service data information (e.g., internet information such as articles, songs, game items, etc.) to a user, an existing question-answering system needs to recommend the service data information according to a question text currently entered by the user in a text entry field, where the service data information generally refers to an answer text corresponding to the current question text. This means that the existing question answering system belongs to a passive recommendation system, and the active touch of information is difficult to realize.

In addition, when data recommendation is performed to different users (for example, a user a and a user B), related text information (for example, a text information 1 entered by the user a and a text information 2 entered by the user B) entered by the user a and the user B in corresponding text entry areas is referred to as question texts of the two users, and then when a text label of the text information 1 is similar to a text label of the text information 2, the same answer text is pushed to the two users indiscriminately in the existing question-answering system. Obviously, in a game scene, a targeted answer text cannot be provided for different users, for example, the existing question and answer system does not provide targeted game strategies for the two users (i.e., the user a and the user B) in different game stages, thereby reducing the accuracy of data recommendation.

Disclosure of Invention

Embodiments of the present invention provide a method, an apparatus, and a storage medium for pushing service data, which can implement active triggering of a prompt message and improve accuracy of data recommendation.

An embodiment of the present invention provides a method for pushing service data, where the method includes:

acquiring a behavior log table of a game user in a game client, and extracting key behavior data information associated with the game user from the behavior log table;

performing user portrait analysis on the key behavior data information to obtain user portrait information for representing game users;

when it is determined that a game user meets a data pushing condition based on user portrait information, business data information of K business types matched with the user portrait information is obtained, and prompt information corresponding to the business data information of the K business types is pushed to a game client so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer.

An embodiment of the present invention provides a service data pushing apparatus, where the apparatus includes:

the log table acquisition module is used for acquiring a behavior log table of a game user in the game client and extracting key behavior data information associated with the game user from the behavior log table;

the portrait analysis module is used for carrying out user portrait analysis on the key behavior data information to obtain user portrait information for representing game users;

the service data pushing module is used for acquiring service data information of K service types matched with the user portrait information when the game user is determined to meet a data pushing condition based on the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to the game client so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer.

Wherein, log table obtains the module and includes:

the system comprises a first pulling unit, a second pulling unit and a third pulling unit, wherein the first pulling unit is used for pulling a first login log table of a game user in a game client within a first duration from a log management system corresponding to the game client;

the table name acquisition unit is used for taking the first login log table as a behavior log table of the game user and acquiring a target table name field corresponding to the behavior log table;

the game system comprises a key field acquisition unit, a behavior log table acquisition unit and a game interaction unit, wherein the key field acquisition unit is used for extracting a target key field corresponding to historical game interaction behaviors of a game user in a first time length from the behavior log table;

and the key data determining unit is used for determining key behavior data information associated with the game user based on the target table name field and the target key field.

Wherein, the target key field comprises at least one of the following fields: the game client comprises identification information of game users, the names of the roles of the game users in the game client, gender information of the game users, the role levels of the game users in the game client and the competitive levels of the game users in the game client.

Wherein, the device still includes:

the key data packaging module is used for determining a target event type corresponding to the key behavior data information, packaging the key behavior data information based on an interface packaging rule corresponding to the target event type to obtain a service interface corresponding to the key behavior data information, and storing the service interface to a user portrait system associated with the log management system;

and the service interface calling module is used for calling the service interface to acquire the key behavior data information of the game user in the user representation system.

Wherein, portrait analysis module includes:

the user model acquisition unit is used for acquiring a user portrait model corresponding to the game client from the user portrait system;

the data analysis unit is used for inputting the key behavior data information into a user portrait model corresponding to the game client, and performing data analysis on the key behavior data information by using the user portrait model to obtain a data analysis result corresponding to the key behavior data information;

and the user portrait construction unit is used for constructing user portrait information used for representing game users based on the user behavior labels corresponding to the key behavior data information indicated by the data analysis result.

Wherein the user portrait model comprises a feature extractor and a classifier;

the data analysis unit includes:

the characteristic extraction subunit is used for inputting the key behavior data information into the user portrait model, and a characteristic extractor in the user portrait model extracts behavior characteristic vectors corresponding to the key behavior data information;

the matching degree determining subunit is used for inputting the characteristic behavior vector into a classifier in the user portrait model, and performing data analysis on the key behavior data information by the classifier in the user portrait model to obtain the matching degree between the characteristic behavior vector and the sample attribute characteristics in the classifier;

the user label determining subunit is used for taking the sample attribute feature of which the characteristic behavior vector has the maximum matching degree as the target sample attribute feature in the matching degree and taking the sample label corresponding to the target sample attribute feature as the user behavior label of the behavior feature vector;

and the analysis result determining subunit is used for taking the user behavior label as a data analysis result corresponding to the user portrait model.

Wherein, portrait analysis module still includes:

the history table pulling unit is used for pulling a second login log table of the game user in a second time length from the log management system; the second duration is the last duration of the first duration;

a field extraction unit, which is used for extracting a history table name field associated with the game user and a history key field associated with the history table name field from the second login log table;

and the portrait model training unit is used for training an initial portrait model in the user portrait system based on the training behavior data information by taking the historical table name field and the historical key field as the training behavior data information, and taking the trained initial portrait model as the user portrait model.

Wherein, the service data pushing module comprises:

the backflow detection unit is used for determining an access behavior of a game user accessing the game client through the target game account information as a user backflow behavior in a next behavior recording period of the continuous M behavior recording periods if a first type of user behavior tag exists in the user image information and indicates that a user access behavior of the game user accessing the game client through the target game account information is not detected in the continuous M behavior recording periods; m is greater than or equal to the access time interval;

the reflow event determining unit is used for taking an event type corresponding to the reflow behavior of the user as a reflow event type based on the reflow behavior of the user and the target game account information, and determining that the game user meets the data push condition when the reflow event type is detected to hit the target event type in the data push condition;

and the data recommendation unit is used for acquiring a recommendation network model corresponding to the game client, acquiring the service data information of K service types matched with the first type of user behavior tag in the user image information by using the recommendation network model, and pushing prompt information corresponding to the service data information of the K service types to the game client.

Wherein, the service data pushing module comprises:

the activity detection unit is used for taking the access behavior of the game user accessing the game client through the target game account information as the first target user behavior in the next behavior recording period of the single behavior recording period if a second type of user behavior tag exists in the user portrait information and indicates that the average activity obtained by the game user participating in the first type of task through the target game account information in the single behavior recording period is within the activity threshold range; the activity threshold range comprises a first activity threshold and a second activity threshold, and the second activity threshold is smaller than the second activity threshold;

the game system comprises a first event determining unit, a data pushing unit and a data pushing unit, wherein the first event determining unit is used for determining a first event type corresponding to a first target user behavior based on the first target user behavior, target game account information and auxiliary identification information associated with the target game account information, and determining that a game user meets a data pushing condition when the first event type hits a target event type in the data pushing condition;

the first pushing unit is used for acquiring a recommended network model corresponding to the game client, acquiring service data information of K service types matched with the user behavior tags of the second type in the user image information by the recommended network model, and pushing prompt information corresponding to the service data information of the K service types to the game client.

Wherein, the service data pushing module comprises:

the task detection unit is used for taking the user behavior of re-executing the second type of task as a second target user behavior when the game user re-executes the second type of task through the target game account information if the user behavior tag of the third type exists in the user portrait information and indicates that the game user does not complete the second type of task in the game client through the target game account information;

the second event determining unit is used for determining a second event type corresponding to a second target user behavior based on the target user behavior, the target game account information and auxiliary identification information associated with the target game account information, and determining that the game user meets the data push condition when the second event type hits the target event type in the data push condition;

and the second pushing unit is used for acquiring a recommended network model corresponding to the game client, acquiring service data information of K service types matched with the user behavior tag of the third type in the user image information by the recommended network model, and pushing prompt information corresponding to the service data information of the K service types to the game client.

The service data information of the K service types comprises service data information corresponding to a target service type; the service data information corresponding to the target service type comprises service auxiliary dimensions;

the device still includes:

the request receiving module is used for receiving a service data request sent by the game terminal aiming at the service auxiliary dimension under the target service type and acquiring L pieces of service auxiliary information associated with the service auxiliary dimension from a service database associated with the target service type based on the service data request;

and the auxiliary information output module is used for taking the L pieces of service auxiliary information as the conversation texts corresponding to the service auxiliary dimensions and outputting the conversation texts to a conversation display interface of the game client.

Wherein, the device still includes:

the interactive behavior determining module is used for recording a first trigger operation executed aiming at a target service type and a second trigger operation executed aiming at a service auxiliary dimension when the target service type sent by the game terminal and the service auxiliary dimension under the target service type are obtained, and respectively taking the first trigger operation and the second trigger operation as interactive behavior data between a game client and the game client;

the behavior path determining module is used for forming a user behavior path of the game user based on the interactive behavior data and determining a game node where the game client is located in the game environment of the game client based on the user behavior path;

and the dialogue text adjusting module is used for identifying the interaction intention of the game user based on the game node, adjusting the dialogue text associated with the game node based on the interaction intention, and outputting the adjusted dialogue text to a dialogue display interface corresponding to the game node.

An embodiment of the present invention provides a computer device, including: a processor, a memory, and a network interface;

the processor is coupled to the memory and the network interface, wherein the network interface is configured to provide data communication functionality, the memory is configured to store program code, and the processor is configured to call the program code to perform a method according to an aspect of an embodiment of the present invention.

An aspect of the embodiments of the present invention provides a computer-readable storage medium, in which a computer program is stored, where the computer program includes program instructions, and the program instructions, when executed by a processor, perform a method according to an aspect of the embodiments of the present invention.

In the embodiment of the present invention, when acquiring the behavior log table of the game user at the game client, the computer device may comb out the key behavior data information associated with the game user through the behavior log table of the game user, for example, may comb out a table name of the behavior log table and a target key field recorded in the behavior log table, and may further collectively refer to the combed table name and the target key field as the key behavior data information associated with the game user. Further, the computer device may perform user representation analysis on the key behavior data information to obtain user representation information characterizing the game user. It should be appreciated that the user representation information described in the embodiments of the present application is determined by the user behavior tags obtained by classifying user behaviors (e.g., historical user behaviors) through a user representation model. Therefore, the game user can judge whether the game user meets the data recommendation condition through the user portrait information of the game user, if so, the service data information of K service types matched with the user behavior tag in the user portrait information can be actively acquired, so that service data information which is different in dimensionality and fits the interest of the game user is provided for the game user. Wherein K may be a positive integer. In this way, when the game user is in the game environment of the game client, for example, when the game user accesses the game client or executes a game task in the game client, the computer device may actively intervene for the game client in the game environment, and may further actively push the prompt information (for example, in the form of a red dot, a pop-up window, a mail, or the like) corresponding to the service data information of the K service types to the game terminal running the game client, so as to implement active contact of the prompt information. It should be understood that when the value of K is greater than 1, personalized multidimensional service data information can be provided for the game user, and the service data information can be text data prepared for the game user by a computer device in advance based on user portrait information of the game user. It should be understood that for different game users, different user portrait information can be obtained through portrayal based on the behavior log table, and therefore when data recommendation is carried out based on the user portrait information, thousands of people can be achieved, and accuracy of data recommendation can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a network architecture according to an embodiment of the present invention;

fig. 2 is a schematic view of a scenario for actively contacting provisioning information according to an embodiment of the present application;

fig. 3 is a schematic flowchart of a service data pushing method according to an embodiment of the present invention;

fig. 4 is a scene schematic diagram of a behavior log table provided in an embodiment of the present application;

FIG. 5a is a schematic diagram of a trigger relationship of recording data according to an embodiment of the present invention;

FIG. 5b is a schematic view of a scenario of an event configuration interface according to an embodiment of the present application;

FIG. 6 is a schematic view of a scenario where a prompt message is output in a game terminal according to an embodiment of the present application;

fig. 7 is a scene schematic diagram of switching a game scene into a question-answering scene according to an embodiment of the present application;

fig. 8 is a flowchart illustrating a method for pushing service data according to an embodiment of the present invention;

fig. 9 is a schematic view of a scene of service data information with different dimensions provided in an embodiment of the present application;

fig. 10 is a schematic view of a scenario for switching service dimensions according to an embodiment of the present application;

fig. 11 is a schematic view of a scenario for acquiring L pieces of service assistance information associated with a service assistance dimension according to an embodiment of the present application;

FIG. 12 is a schematic flowchart illustrating interaction between a service server and a game terminal according to an embodiment of the present disclosure;

fig. 13 is a schematic structural diagram of a service data pushing apparatus according to an embodiment of the present invention;

fig. 14 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a network architecture according to an embodiment of the present invention. As shown in fig. 1, the network architecture can be applied to an intelligent robot system in a game scenario. The intelligent robot system may specifically include the service server 2000 and the user terminal cluster shown in fig. 1. The user terminal cluster may specifically include one or more user terminals, and here, the number of the user terminals in the user terminal cluster is not limited. As shown in fig. 1, the plurality of user terminals may specifically include a user terminal 3000a, a user terminal 3000b, user terminals 3000c, …, a user terminal 3000 n; as shown in fig. 1, the user terminal 3000a, the user terminal 3000b, the user terminals 3000c, …, and the user terminal 3000n may be respectively in network connection with the service server 2000, so that each user terminal may perform data interaction with the service server 2000 through the network connection.

The service server 2000 shown in fig. 1 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, and a big data and artificial intelligence platform.

It should be understood that each user terminal in the user terminal cluster shown in fig. 1 may be installed with a target client (in a game scenario, the target client may specifically be an entertainment client), and when the target client runs in each user terminal, data interaction may be performed with the service server 2000 shown in fig. 1. The entertainment client can be a game client, and the game client can comprise a racing game client, a running game client, a shooting game client, a chess and card game client and the like. For convenience of understanding, in the embodiment of the present application, one user terminal may be selected from the plurality of user terminals shown in fig. 1 as a target user terminal, and the target user terminal may include: the intelligent terminal comprises an intelligent terminal with a multimedia data loading function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer and an intelligent television. For example, the user terminal 3000a shown in fig. 1 may be used as a target user terminal in the embodiment of the present application, and the target user terminal may be collectively referred to as a game terminal in the embodiment of the present application, where the game terminal may specifically include a hand-game terminal.

It is understood that, in the intelligent robot system, the intelligent robot may be respectively disposed in the game terminal (e.g., the user terminal 3000a in the embodiment corresponding to fig. 1) and the background server (e.g., the service server 2000 in the embodiment corresponding to fig. 1). In this way, the business data processing method provided by the embodiment of the application can relate to the machine learning direction in the field of artificial intelligence. It is understood that by Artificial Intelligence (AI), we mean a new technology science that uses a digital computer or data computer controlled computer device (e.g., server 2000 shown in fig. 1) to simulate, extend and extend human Intelligence. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Machine Learning (ML) is a multi-field cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis and algorithm complexity theory. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal education learning.

It can be understood that, in the embodiment of the present application, the game terminal may be used as a front end of an intelligent robot that executes a service data processing method, and the service server 2000 may be used as a background (i.e., the aforementioned background server) of the intelligent robot, so that after the service server 2000 acquires a behavior log table of a game user in the game terminal, historical game behaviors of the game user in a historical duration may be combed in the behavior log table to comb user behavior tags of the game user in a game scene, and further, user portrait information for representing the game user may be carved based on the user behavior tags. Therefore, when the game user performs data interaction in the game environment of the game client, help can be actively provided for the game user based on the user portrait information so as to perform intelligent intervention on the game user currently in the game environment. For example, the service server 2000 may perform role guidance, data recommendation, multiple rounds of conversations, and the like for different nodes where the game user is located in the current game environment.

For ease of understanding, please refer to fig. 2, and fig. 2 is a schematic diagram of a scenario in which providing information is actively contacted according to an embodiment of the present application. For convenience of understanding, in the embodiment of the present application, the user terminal 3000a shown in fig. 1 is taken as an example of the game terminal, so as to describe a specific process of data interaction between the service server shown in fig. 2 and the game terminal.

It is understood that the log management system 10 shown in fig. 2 may specifically include a plurality of databases, and the plurality of databases may specifically include the database 10a, the databases 10b, …, and the database 10n shown in fig. 2. This means that the log management system 10 can be used to store log logs of different game users in an entertainment client (e.g., game client X). For example, database 10a may be used to store the log of game user A shown in FIG. 2, database 10B may be used to store the log of other game users (e.g., game user B, not shown), …, and database 10N may be used to store the log of other game users (e.g., game user N, not shown).

It is to be understood that, for convenience of understanding, the log logs of different game users in the game client X, which are acquired by the service server within the first time period, may be collectively referred to as a behavior log table in the embodiment of the present application. In this way, for different game users who are currently performing data interaction with the game client X, the behavior log table of the corresponding game user in the first duration may be acquired from the corresponding database shown in fig. 2, and then the game interaction behavior of the corresponding game user may be continuously combed in the acquired behavior log table of the corresponding game user in the first duration, so that user image information of each game user may be obtained subsequently, and then a multidimensional question-and-answer strategy may be provided for different game users in a targeted manner based on the user image information, so that accuracy of data recommendation may be achieved.

For convenience of understanding, in the embodiment of the present application, a game user currently in a game scene of the game client X is taken as an example of the game user a shown in fig. 2, so as to describe a specific process of providing information initiative contact for the game user a. As shown in fig. 2, when acquiring the behavior log table (for example, the behavior log table 20a, the behavior log table 20b, …, and the behavior log table 20n shown in fig. 2) of the game user a in the first time period, the service server may further extract a table name and key fields from the behavior log table, so as to acquire the key behavior data information of the game user a in the first time period. As shown in fig. 2, the service server may further input the key behavior data information into the user portrait model shown in fig. 2, so that the user portrait model (which may be the currently trained network model 1) can perform data analysis on the historical game interaction behaviors within the first duration through the key behavior data information, so as to construct the user portrait information shown in fig. 2 through the user behavior tags corresponding to the historical game interaction behaviors. The user portrait information may specifically include, but is not limited to: a first type of user behavior tag (e.g., an old player reflow tag), a second type of user behavior tag (e.g., a day-average activity tag), and a third type of user behavior tag (e.g., a duplicate clearance failure tag).

Further, the service server in fig. 2 may further intervene some game nodes (for example, game nodes R) in the current game environment (that is, the virtual environment where the virtual object shown in fig. 2 is located) of the game user a shown in fig. 2 according to the user portrait information, for example, when it is detected that the target game interaction behavior executed by the game user 2 at the game node R satisfies the game recommendation condition, the prompt information corresponding to the service data information of the K service types shown in fig. 2 may be pushed to the game terminal corresponding to the game user a shown in fig. 2, so as to display the prompt information with the active intervention function in the game terminal shown in fig. 2, so as to implement the active contact of the prompt information. It can be understood that, with the embodiment of the present application, it is not necessary for the game user a to send a request to the service server shown in fig. 2 when encountering a problem (i.e. it is not necessary to send a data acquisition request to the service server for consulting to obtain the service data information of the K service types), service data information of K service types which may be required at the game node R may be prepared in advance for the user directly based on the user profile information, and the service data information of the K service types, outputting the presentation style of the prompt message shown in fig. 2 to the icon area where the intelligent robot shown in fig. 2 is located, so as to provide a reliable and efficient question answering strategy for the game user a, the problem solution strategy may be a problem solution strategy of at least one service type intelligently provided by the service server for the game user a under the current game node.

It can be understood that the value of K here may be 1, which means that when data recommendation is performed through the user portrait information in the embodiment of the present application, service data information under a service type having the highest matching degree with the user portrait information may be recommended to the game user a, so as to ensure accuracy of data recommendation. Optionally, the value of K may also be a positive integer greater than or equal to 2, which means that when data recommendation is performed through the user portrait information in the embodiment of the present application, service data information with different dimensions may be provided for the game user a, so that the currently recommended service data information may more comprehensively meet the question and answer requirements of the game user, and further a more reliable game solution policy may be provided for the game user a.

It can be understood that the first duration in the embodiment of the present application may specifically include: a first access timestamp (e.g., time T1) and a second access timestamp (e.g., time T2); it is understood that there may be a certain time interval between the first access time stamp and the second access time stamp, for example, the second access time stamp may be a next access time stamp of the first access time stamp, that is, the first access time stamp and the second access time stamp may be used to distinguish the sequence of accesses to the game client. For example, the time T2 may be the access time of the game user a accessing the game client X this time; the time T1 may be the last access time of the game user a to the game client X, i.e., the time T1 may be the last access time of the time T2. It should be understood that an access time interval of not accessing the game client X may be included between the time T1 and the time T2, and the access time interval may be determined by M behavior record periods of continuously not accessing the game client X, where M may be an integer.

It is to be understood that the log management system 10 shown in fig. 1 may establish a log-in log table (i.e., a behavior log table) for each game user accessing the game client X (e.g., the game user a shown in fig. 2) in a single behavior recording period (e.g., day is a unit of the behavior recording period), for example, the log management system 10 may establish a log-in log table for the game user a when detecting that the game user a accesses the game client X for the first time of the day, at which time an access time stamp (e.g., the above-mentioned time T2) of the current access to the game client X is recorded in the log-in log table, which means that there is no other historical interaction behavior before the current access time (e.g., the above-mentioned time T2) in the log-in table. Further, the log management system 10 may add the log table (e.g., the behavior log table 20a shown in fig. 2) established for the game user a to the corresponding database (e.g., the database 10a shown in fig. 2) for storage when the current behavior recording period reaches the recording period threshold. Thus, when the game user a accesses the game client X during the new behavior record period, the timestamps of accessing the game clients at the new access timestamp (e.g., time T3) may be collectively referred to as the third access timestamp during the behavior period. Therefore, when the game user a successfully accesses the game client X at time T3 and an interaction behavior is generated with the game client X, the interaction behavior between the game user a and the game client X at time T3 can be recorded in the new behavior recording period through the newly created login log table.

Based on this, it can be understood that each behavior log table (i.e. the behavior log table 20a, the behavior log table 20b, …, and the behavior log table 20n shown in fig. 2) obtained by the service server shown in fig. 2 from the database 10a may correspond to a behavior recording period, that is, the behavior recording period herein may record the interaction behavior of the game user a shown in fig. 2 in the client X in units of days.

In this embodiment, an access timestamp of the game user a accessing the game client X last time may be referred to as a first timestamp, the first timestamp may be represented as the time T1, the time T1 may be a timestamp in a behavior detection period (e.g., a behavior detection period 1), a log table corresponding to the behavior detection period 1 may be the behavior log table 20b in fig. 2, and the behavior log table 20b may be used to record historical game interaction behaviors of the game user a with the game client X in the behavior detection period 1.

Similarly, the access timestamp of the game user a accessing the game client X at this time may also be referred to as a second timestamp, the second timestamp may be represented as the time T2, the time T2 may be a timestamp in another behavior detection period (for example, the behavior detection period 2 is the next behavior detection period of the behavior detection period 1), the log table corresponding to the behavior detection period 2 may be the behavior log table 20a of fig. 2 (i.e., the behavior log table 20a may be a log table newly constructed for the game user a), and the behavior log table 20a may be used to record the target game interaction behavior of the game user a, that is, the game user a will interact with the game client X in the behavior detection period 2. It is understood that, upon detecting that the target game interaction behavior of the game user a at the time T3 satisfies the data pushing condition (the data pushing condition may be equivalent to an active care condition), the service server may push the prompt information shown in fig. 2 to the game terminal corresponding to the game user a.

It should be understood that the service server shown in fig. 2 may intelligently implement the main movement of the prompt information shown in fig. 2 for each game user (e.g., game user a and other game users) in the game client X when detecting that each game user (e.g., game user a and other game users) in the game client X satisfies the data pushing condition, for example, when the event corresponding to the interaction behavior (i.e., the target game interaction behavior) of each game user in the game environment hits the target event in the data pushing condition, so that before the game users in the game environment encounter a problem, the service server may actively recommend service data information of multiple dimensions for the corresponding game users based on the pre-carved user portrait information, and it is understood that the specific implementation manner in which the service server pushes service data information of multiple dimensions for other game users, reference may also be made to the description of the specific process for pushing the service data information of K service types for the game user a in the embodiment corresponding to fig. 2, which will not be further described here. K here may be a positive integer greater than or equal to 2.

It can be understood that, as shown in fig. 2, after the game user a performs a trigger operation on the icon of the intelligent robot shown in fig. 2, the game terminal corresponding to the game user a may generate a system switching instruction based on the trigger operation, where the system switching instruction may be used to instruct the game terminal to switch a current game environment (i.e., a game scene) to a question-and-answer environment (i.e., a question-and-answer scene), that is, the game system may be switched from the current running system to the question-and-answer system in the game terminal, and then the display interface corresponding to the intelligent robot shown in fig. 2 may be controlled in the question-and-answer system to quickly output the service data information of the K service types prepared for the game user a.

It should be understood that in the embodiment of the present application, by introducing the user portrait information, thousands of people can be achieved, so that when data recommendation is performed based on the portrayed user portrait information, the accuracy of data recommendation can be improved. Therefore, the embodiment of the application can be used for describing the user portrait information (namely the game behavior portrait of the game user) for representing the game client by combining the historical game user behaviors (namely the interactive behaviors in the continuous time period before the T3) of the game user in the game environment, and further can help the game user to intelligently realize personalized information initiative and reach under certain game nodes (for example, a card point, a pain point, a high-difficulty game copy node and the like) of the current game environment, so that the problem can be solved for the game user at the first time. For example, the embodiment of the application can provide customized multidimensional dialogue answers (i.e., the aforementioned K-dimensional service data information) for game users, so as to better help the game users to experience the intellectualization of the intelligent robot in the game scene, to increase the user viscosity between the game users and the game clients, and further to enable the intelligent robot to improve the game experience of the game users in the form of game partners in the intelligent robot system.

The specific processes of the service server obtaining the key behavior data information, determining the user portrait information, and pushing the prompt information corresponding to the service data information of the K service types may be as follows in the embodiments corresponding to fig. 3 to fig. 12.

Further, please refer to fig. 3, where fig. 3 is a schematic flow chart of a service data pushing method according to an embodiment of the present invention. As shown in fig. 3, the method may be executed by a computer device, which may be a game terminal running the entertainment client, and the game terminal may be the game terminal in the embodiment corresponding to fig. 2; optionally, the computer device may also be a background server corresponding to the entertainment client, and the background server may be the service server in the embodiment corresponding to fig. 2. In other words, the method according to the embodiment of the present application may be executed by a game terminal corresponding to a game user, may be executed by a service server, or may be executed by both the game terminal and the service server. For the convenience of understanding, the present embodiment is described by taking the service server (for example, the service server in the embodiment corresponding to fig. 2) as an example, so as to illustrate a specific process of acquiring service data information of K service types matching with user portrait information in the service server. Wherein, the method at least comprises the following steps S101-S103: the method at least comprises the following steps:

step S101, acquiring a behavior log table of a game user in a game client, and extracting key behavior data information associated with the game user from the behavior log table;

specifically, the service server may pull a first log table of a game user in the game client within a first duration from a log management system corresponding to the game client; further, the service server may use the first log table as a behavior log table of the game user, and may obtain a target table name field corresponding to the behavior log table; further, the business server can extract a target key field corresponding to the historical game interaction behavior of the game user in the first time length from the behavior log table; further, the computer device may determine key behavior data information associated with the game user based on the target table name field and the target key field.

In a game scene, it can be understood that the target key fields extracted from the behavior log table of the i game user at least include the following fields: identification information of the game user (e.g., openid), the name of the game user's character in the game client (e.g., the name of the virtual object that the game picks up in the fire fighter for participation in the competition, which is commonly referred to as a gamer role name), gender information of the game user (e.g., men), the game user's character rating in the game client (e.g., V0), and the game user's competition rating in the game client (e.g., level 17).

It can be understood that the game client may be the game client X in the embodiment corresponding to fig. 2, and for convenience of understanding, the embodiment of the present application is described by taking the game client as an example of an athletic game client, for example, the athletic game client may be a client corresponding to a "fire fighter", and the client corresponding to the "fire fighter" may be the target client. It should be understood that, in this embodiment of the present application, the service server may be a background server of the game client, and the game client may be run on a game terminal corresponding to a game user (for example, game user a in the embodiment corresponding to fig. 2 described above).

It is to be understood that the log management system herein may be the log management system 10 in the embodiment corresponding to fig. 2, and the behavior log table of the game user (for example, the game user a) pulled by the service server from the log management system may specifically be the behavior log table 20a, the behavior log tables 20b and …, and the behavior log table 20n in the embodiment corresponding to fig. 2. The behavior log tables may form a time series corresponding to the behavior recording periods (e.g., in days). The behavior recording periods under the time sequence correspond to a behavior log table.

Among them, it should be understood that in the embodiment of the present application, the construction time stamp of the behavior log table 20a will be later than that of the behavior log table 20 b. By analogy, the build timestamp of behavior log table 20(n-1) (not shown in FIG. 2 above) will be later than the build timestamp of behavior log table 20 n. It is understood that the construction time stamp of the behavior log table 20a may be the access time stamp at the time T2, i.e., the time when the game client is accessed for the first time in the behavior detection period 2. Similarly, the construction time stamp of the behavior log table 20b may be the access time stamp at the time T1, that is, when the game client is accessed for the first time in the behavior detection period 1. By analogy, the construction time stamp of the other behavior log table can be an access time stamp of the game user (for example, the game user a) accessing the game client for the first time in the corresponding behavior recording period, and is not listed here. Based on this, the embodiment of the present application may collectively refer to the first login log table of the game user in the first duration, which is pulled by the service server from the log management system, as the behavior log table, where the number of the pulled first login log tables is not limited here.

For convenience of understanding, in the embodiment of the present application, the behavior log table in the first duration acquired by the service server from the log management system is taken as the behavior log table 20a and the behavior log table 20b, which are taken as examples, so as to describe a specific process of determining the key behavior data information from the behavior log tables. Further, please refer to fig. 4, where fig. 4 is a scene schematic diagram of a behavior log table according to an embodiment of the present application. The behavior log table shown in fig. 4 may be the behavior log table 20b, that is, the behavior log table shown in fig. 4 may be used to record the interaction behavior generated between the game user and the game client in the last behavior recording period (i.e., in the behavior detection period 1).

Here, the field a1 shown in fig. 4 may be a table name of the behavior log table shown in fig. 4, for example, in a reflow scenario, the field a1 may be a field "PlayerLogin", and in this case, the field "PlayerLogin" may be a table name described in the behavior log table constructed by the game user in the behavior detection period 1. The field B1 shown in fig. 4 may be a field of the behavior log table shown in fig. 4, for example, in a reflow scenario, the field B1 may be a field "gamesvrld", and at this time, the field "gamesvrld" may be a process instance address recorded in the behavior log table built by the game user in the behavior detection period 1, for example, a string length of the process instance address may be 25 bits, and the string length of the 25 bits may be used to identify a load address of a process in a certain game copy. The field B2 shown in fig. 4 may be a field of the behavior log table shown in fig. 4, for example, in a reflow scenario, the field B2 may be a field "dtEventTime", and at this time, the field "dtEventTime" may be a time of a game event recorded in the behavior log table constructed by the game user in the behavior detection period 1, for example, the time of the game event may be recorded according to the following format: 2020-07-2019:28:10. The field B3 shown in fig. 4 may be a field of the behavior log table shown in fig. 4, for example, in a reflow scenario, the field B3 may be a field "vGameAppId", and at this time, the field "vGameAppId" may be a game client identification number recorded in the behavior log table constructed by the game user in the behavior detection period 1, for example, the length of the game client identification number may be a character string of 32 bits. The field B4 shown in fig. 4 may be a field of the behavior log table shown in fig. 4, for example, in a reflow scenario, the field B4 may be a field "izonearea id, and at this time, the field" izonearea id "may be a number of a logged-in game server recorded in the behavior log table constructed by the game user in the behavior detection period 1, for example, the number of the logged-in game server may be an integer value, such as: region 935. The field B5 shown in fig. 4 may be a field of the behavior log table shown in fig. 4, for example, in a reflow scenario, the field B5 may be a field "vopendid", and at this time, the field "vopendid" may be a user identification number recorded in the behavior log table constructed by the game user in the behavior detection period 1, for example, the user identification number may be unique identification information of the game user in the game client, and a string length of the user identification number may be 256 bits. By analogy, the field Bn shown in fig. 4 may be a field of the behavior log table shown in fig. 4, for example, in a backflow scenario, the field Bn may be a field "highestZhanli", and at this time, the field "highestZhanli" may be a historical highest fighting power recorded in the behavior log table constructed by the game user in the behavior detection period 1, for example, the historical highest fighting power may be a maximum fighting power value, which is obtained when the game user performs a competition in the game client and is expressed in an integer type, for example, 162412.

As shown in fig. 4, after the service server obtains the behavior log table shown in fig. 4, it may comb it to screen out fields associated with important nodes that need to intervene in the behavior log table. For example, the fields of the important nodes that need to be intervened may be identified in the behavior log table in advance according to the event type (for example, the fields may be identified by a dotted underline manner shown in fig. 4), and the service server may be further assisted to determine which fields corresponding to the interaction behaviors in the behavior log table need to be intervened, so that the service server may be assisted to quickly extract the key behavior data information corresponding to the corresponding event type from the behavior log table. In other words, in the fields extracted in the behavior log table, the fields carrying the identifiers and associated with the corresponding event types may be further used as key fields, where the key fields are the key behavior data information. As shown in fig. 4, in a reflow scenario, the key behavior data information corresponding to the reflow event type may specifically include the table name field "field a 1" shown in fig. 4 and a plurality of key fields, for example, the field B1, the field B3, the fields B5, …, and Bn shown in fig. 4.

Further, it can be understood that, after the service server selects a table name field (simply referred to as a table name) and a field associated with the corresponding event type from the behavior log table, the service server may further perform interface development on the table name and the field provided in the behavior log table, that is, may perform encapsulation processing on the key behavior data information shown in fig. 4 extracted from the behavior log table to obtain a service interface of the key behavior data information corresponding to the reflow event type. It is understood that in the embodiment of the present application, an event type may be allowed to correspond to a service interface, so that when a certain interactive action performed by a game user in a game client triggers the corresponding event type, the service server can make an active contact quickly.

Furthermore, the service server can store the developed service interface corresponding to the event type to a user representation system associated with the log management system, and then can call a corresponding service interface to acquire corresponding key behavior data information of the game user within the first duration in the user representation system.

It can be understood that, according to the target event type in the game environment, the embodiment of the present application may pre-develop a corresponding service interface for the key node that needs to intervene in the game environment. For example, for the case that the target event type is a reflow event type, the key behavior data information (e.g., key behavior data information 1) associated with the reflow event type may be extracted from the behavior log table. For another example, for a target event type that is a high difficulty duplicate pacifying event type, the key behavior data information (e.g., key behavior data information 2) associated with the high difficulty duplicate pacifying event type may be extracted from the behavior log table. For another example, for a target event type that is a daily average activity reminding event type, the key behavior data information (e.g., key behavior data information 3) associated with the daily average activity reminding event can be extracted from the behavior log table.

For easy understanding, please refer to fig. 5a, and fig. 5a is a schematic view of a scenario in which an interface is developed according to an interface encapsulation rule according to an embodiment of the present application. As shown in fig. 5a, the interface 1 is obtained by, when the type of the target event is a high-difficulty copy pacifying event, encapsulating the key behavior data information (the key behavior data information may be the key behavior data information 2) according to an interface encapsulation rule corresponding to the high-difficulty copy pacifying event. For example, as shown in fig. 5a, the table name obtained by the service server from the behavior log table may be the table name field C1 in the area 30a shown in fig. 5a, and the table name field C1 in the area 30a may be collectively referred to as the target table name field obtained from the behavior log table in the embodiment of the present application. Similarly, as shown in fig. 5a, the field selected by the service server from the behavior log table may be a key field in the area 30a shown in fig. 5a, for example, the key field may specifically be the identity number of the high difficulty copy shown in fig. 5a (107011 (instant aesthetics), 110012 (deity speaker), 107001 (whirlpool, coming back), 107003 (sand and dawn fight), and the like; and the competition results of the game user under the high-difficulty copy systems are all failed, that is, the embodiment of the application can use 0 to indicate that the task state participating in the high-difficulty copy task is failure. It should be understood that the embodiments of the present application may collectively refer to these key fields in the area 30a as target key fields retrieved from the behavior log table.

For another example, the interface 2 shown in fig. 5a may be obtained by, when the type of the target event is a daily-activity-level reminding event, encapsulating another piece of key behavior data information (the key behavior data information may be the key behavior data information 3) according to an interface encapsulation rule corresponding to the daily-activity-level reminding event. For example, as shown in fig. 5a, the table name obtained by the service server from the behavior log table may be the table name field C2 in the area 30b shown in fig. 5a, and the table name field C2 in the area 30a may be collectively referred to as the target table name field obtained from the behavior log table in the embodiment of the present application. Similarly, as shown in fig. 5a, the field selected by the service server from the behavior log table may be a key field in the area 30b shown in fig. 5a, for example, the key field may specifically be the average daily activity shown in fig. 5 a; and the average daily activity of the game user during the last activity recording period (e.g., yesterday) is within an activity threshold range, which may comprise a first activity threshold value (e.g., "0" as shown in fig. 5 a) and a second activity threshold value (e.g., "40" as shown in fig. 5 a). That is, the embodiment of the present application may collectively refer to the key fields in the area 30b as the target key fields obtained from the behavior log table.

Based on this, the service server may store the service interfaces (for example, interface 1 and interface 2 shown in fig. 5 a) corresponding to the event types obtained by the development to the user representation system associated with the log management system, and may further invoke the corresponding service interfaces in the user representation system to obtain the corresponding key behavior data information of the game user within the first duration. It is understood that the interface packaging rule according to the embodiment of the present application may roughly include the event type, the push condition, the influence on the user game, the rule identification, the pushed event identification, the push frequency, the validation time, the input field, and the like shown in fig. 5 a.

It is understood that the user representation system refers to an information system established for a game user, which can be used for collecting, managing, analyzing and utilizing game information, in the user representation system, the embodiment of the application can take the user representation information as a core, so as to record various interactive behaviors of the user in the game process and the states of participating in various tasks (for example, participating in activities) through the user representation information. In addition, it will be appreciated that the user representation system may be further configured to provide various types of data models (e.g., user representation models required in step S102, described below), and may further provide support for later user representation analysis and multidimensional dialogue.

It can be understood that, after the service interface corresponding to the target service event is encapsulated, the configuration of the key information of the target service event can be further performed on the operation and maintenance platform corresponding to the intelligent robot in the embodiment of the present application. For easy understanding, please refer to fig. 5b, and fig. 5b is a schematic view of a scenario of an event configuration interface according to an embodiment of the present application. As shown in fig. 5b, the service server may respond to the event entry operation of the operation and maintenance person corresponding to the operation and maintenance platform in the corresponding area in the configuration interface shown in fig. 5 b. For example, as shown in fig. 5b, during the process of configuring the target business event, the operation and maintenance staff may fill a corresponding Tlog log interface in a region a shown in fig. 5b, and fill a log table name that can be called through the Tlog log interface in a region b shown in fig. 5b, for example, the log table name is that the game user accesses a role log table of the game client in the world war field region, an event identification number of the user behavior event (i.e., the target business event) is written in a region c shown in fig. 5b, an event type of the user behavior event (i.e., the target business event) is written in a region d and a region e shown in fig. 5b (e.g., an event type of fire offline-reflow is entered in a region d, and an important field extracted from the behavior log table is entered in a region e), a frequency of the event is written in a region f shown in fig. 5b (e, once a month), writing the statistical logic shown in fig. 5b in the area g shown in fig. 5b, writing the valid time of the target event type in the area h shown in fig. 5b, writing the corresponding field tags and question and answer settings for describing the user image information in the area i shown in fig. 5b, wherein the tag fields are realized by the last step of interface development. Therefore, when the user executes a corresponding game interaction behavior (for example, an access behavior of accessing the game client during reflow) in the game client, an interface call behavior corresponding to the reflow event type is triggered, that is, a terminal (i.e., a service server) corresponding to the intelligent robot obtains an instruction that needs to be actively triggered, so as to actively reach the user, and a multi-turn question-and-answer mechanism can be further provided according to a set question-and-answer tag, so as to help the game user provide a reliable problem solving policy at a corresponding game node of the game client.

Step S102, carrying out user portrait analysis on the key behavior data information to obtain user portrait information for representing game users;

specifically, the service server can obtain a user portrait model corresponding to the game client from the constructed user portrait system; furthermore, the business server can input the key behavior data information into a user portrait model corresponding to the game client, and the user portrait model performs data analysis on the key behavior data information to obtain a data analysis result corresponding to the key behavior data information; further, the service server may construct user portrait information used for representing the game user based on the user behavior tag corresponding to the key behavior data information indicated by the data analysis result.

It can be understood that the specific process of obtaining the data analysis result corresponding to the key behavior data information by the service server through the key behavior data information and the user portrait model can be described as follows: the service server can input the key behavior data information into the user portrait model, where the user portrait model can be the trained user portrait model in the embodiment corresponding to fig. 2, at this time, the service server can extract the behavior feature vector corresponding to the key behavior data information by the feature extractor in the user portrait model, and further can further input the feature behavior vector into the classifier in the user portrait model, and the classifier in the user portrait model continues to perform data analysis on the key behavior data information to obtain the matching degree between the feature behavior vector and the sample attribute feature in the classifier; further, the service server may use, in the matching degree, a sample attribute feature of which the feature behavior vector has the maximum matching degree as a target sample attribute feature, and use a sample tag corresponding to the target sample attribute feature as a user behavior tag of the behavior feature vector; further, the service server may use the user behavior tag as a data analysis result corresponding to the user portrait model.

It can be understood that, as time changes, the user portrait information of the game user in the game client changes with time, and therefore, in order to obtain the user portrait information capable of accurately describing the game user, the portrait model for portrait analysis may be continuously iteratively trained based on the obtained historical login table in the second duration, so as to ensure that the latest user portrait information is used when data recommendation is performed in the current first duration. For convenience of understanding, in the embodiments of the present application, the image model before training may be collectively referred to as an initial image model, and the initial image model after training may be collectively referred to as user image information. Based on this, it can be understood that before the service server outputs the user portrait information of the game user based on the user portrait model, the service server needs to train the initial portrait model to use the trained initial portrait model as the user portrait model for predicting the user portrait information. For example, the service server may pull a second log table of the game user in a second duration from the log management system; the second duration here may be a duration immediately preceding the first duration; further, the service server can extract a history table name field associated with the game user and a history key field associated with the history table name field from the second login log table; furthermore, the service server may use the historical table name field and the historical key field as training behavior data information, and may further train the initial portrait model in the user portrait system based on the training behavior data information, so as to use the trained initial portrait model as the user portrait model.

It is to be understood that, in the embodiment of the present application, the user portrait information may be composed of a series of user behavior tag information. For example, for the reflow event type, the user representation information may specifically include a first type of user behavior tag, which may be an old player reflow tag. For example, when the behavior log table acquired by the service server includes the behavior log table 20b corresponding to the behavior recording period 2 and the behavior log table 20a corresponding to the behavior recording period 1, the service server may indirectly obtain that M behavior recording periods continuously do not access the game client exist between the two access timestamps when it is determined that the access time intervals greater than or equal to the time interval threshold (for example, 14 days) exist in the access timestamps corresponding to the two behavior recording periods. For example, when the service server does not detect a user access behavior of a game user accessing the game client through the target game account information in the M behavior record periods, the service server may obtain the first type of user behavior tag through the user representation model, and further obtain user representation information describing the game user according to the currently obtained user behavior tag, so that the following step S103 may be subsequently performed.

For example, if there are M consecutive behavior record periods between the access time stamp for the game client described in the behavior log table 20a (i.e., the T2) and the access time stamp for the game client described in the behavior log table 20b (i.e., the T1), M may be greater than or equal to the preset time interval threshold. In other words, the service server can quickly determine that the game user belongs to the reflow user through the user representation information output by the user representation model (the user representation model may be a neural network model in any form), that is, the service server can indirectly analyze the access time interval existing between the time T1 and the time T2 through the behavior log table, and further can determine whether M behavior record periods indicated by the access time interval are greater than or equal to the time interval threshold corresponding to the reflow event type, and if the determination is negative, it indicates that the game user currently accessing the game client temporarily does not belong to the reflow user; optionally, if the judgment result is yes, it indicates that the game user currently accessing the game client belongs to the reflow user temporarily. It can be understood that the preset time interval threshold for the reflow event type may be 14 days, and of course, the value of the preset time interval threshold may also be adjusted according to the actual service requirement in the game scene in the embodiment of the present application, which is not listed here.

Such as: the service server can obtain the following information by calling a corresponding service interface in the user representation system: the access timestamp (i.e., T2) of the game user currently accessing the game client may be 2 pm at 7/20/2020, and the service server may know, by analyzing the behavior log table, that the T2 time of the game user last accessing the game client is 2 pm at 7/2/2020. At this time, the service server may determine that the access time interval between the time T1 and the time T2 may be ((20-2) -1) ═ 17 days, which means that the game client X has not been accessed for 17 consecutive days before this access.

Alternatively, similarly, taking the example that the time T1 is 2020, 7, 20, pm, 2, pm, and the time T2 at which the game user last accessed the game client is 2020, 7, 19, pm, 2, pm, as an example, the service server may obtain, in the user representation system, the key behavior data information in the behavior log table by calling a corresponding interface, and further may determine, based on the key behavior data information in the behavior log table, that the number of intervals (e.g., M) of the behavior recording period between the time T1 and the time T2 may be (20-19-1) 0 days, which means that the game client is not accessed after 0 days before the game client X is accessed this time. In other words, this indicates that the game user has accessed the game client for 2 consecutive days.

Optionally, it is understood that, for the activity reminding event type, the user representation information herein may specifically include the second type of user behavior tag, and the second type of user behavior tag may be a daily activity tag. Similarly, after obtaining the second type of user behavior tag through the user profile model, the service server may construct another user profile information for representing the game user based on the second type of user behavior tag.

Optionally, for the type of the high-difficulty copy pacifying event, the user portrait information may specifically include the third type of user behavior tag, and the third type of user behavior tag may be a high-difficulty copy clearance failure tag. Similarly, after obtaining the third type of user behavior tag through the user profile model, the service server may construct further user profile information for characterizing the game user based on the third type of user behavior tag.

Step S103, when the game user is determined to meet the data pushing condition based on the user portrait information, acquiring service data information of K service types matched with the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to a game client so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer.

Specifically, the user representation information may include one or more of the first type of user behavior tag, the second type of user behavior tag, and the third type of user behavior tag, and the type of the user behavior tag output by the user representation model is not specifically limited herein. For example, if a first type of user behavior tag exists in the user image information, and the first type of user behavior tag indicates that a user access behavior of a game user accessing the game client through the target game account information is not detected in all of M consecutive behavior recording periods, the service server may determine, as a user reflow behavior, an access behavior of the game user accessing the game client through the target game account information in a next behavior recording period (i.e., a current behavior recording period) of the M consecutive behavior recording periods; m may be greater than or equal to a preset access time interval; further, the service server may use an event type corresponding to the user reflow behavior as a reflow event type based on the user reflow behavior and the target game account information, and determine that the game user satisfies the data push condition when it is detected that the reflow event type hits a target event type in the data push condition; further, the service server may obtain a recommended network model corresponding to the game client, obtain, by the recommended network model, service data information of K service types that is matched with the user behavior tag of the first type in the user image information, and push prompt information corresponding to the service data information of the K service types to the game client.

For convenience of understanding, in the embodiment of the present application, the user image information includes the user behavior tag of the first type as an example, so as to describe a specific process of pushing the prompt information to the game terminal for displaying. Further, please refer to fig. 6, where fig. 6 is a schematic view of a scene for outputting the prompt information in the game terminal according to the embodiment of the present application. As shown in fig. 6, after obtaining the user portrait information depicting the game user in step S102, the service server may determine, when it is determined that the user portrait information includes the user behavior tag of the first type, that an access behavior of the game user accessing the game client through the target game account information this time is determined as a user reflow behavior in a current behavior recording period (i.e., a next behavior recording period of the above-mentioned M consecutive behavior recording periods), and may further determine, according to the user reflow behavior and the target game account information (e.g., an account name X in the display interface 100a shown in fig. 6), an event type corresponding to the user reflow behavior as a reflow event type.

It can be understood that, if the service server detects that the currently determined backflow event type belongs to the main dynamic contact event, that is, when it is detected that the backflow event type hits a target event type in the data push conditions under the main dynamic contact event, it may be determined that a game user satisfies the data push conditions, and then, when a recommended network model for the game client is obtained, service data information of K service types matched with the user behavior tag of the first type may be obtained through the recommended network model, and then, when prompt information of the service data information of the K service types is obtained, the prompt information may be pushed to the game terminal shown in fig. 6.

It can be understood that, when the service server obtains the service data information of the K service types, the service data information of the K service types may be packaged according to a specific presentation style, and then the packaged service data information with the specific presentation style may be used as the prompt information to be pushed to the game terminal. Further, as shown in fig. 6, when the game terminal shown in fig. 6 allows the game client, a game top page (i.e., a game display interface) of the game client shown in fig. 6 can be obtained, that is, the game top page can be the display interface 100a shown in fig. 6. As shown in fig. 6, the display interface 100a may contain system trigger controls for accessing different systems. For example, the system trigger control 40a shown in fig. 6 may be used to switch the current game environment to the system corresponding to the leaderboard of the game client. The system trigger control 40b shown in fig. 6 may be used to switch the current game environment to the system corresponding to the organization of the game client. The system trigger control 40c shown in fig. 6 may be used to switch the current game environment to the system corresponding to a certain arena (e.g., the trial floor shown in fig. 6) of the game client. The system trigger control 40dd shown in fig. 6 can be used to switch the current game environment to the system corresponding to the other arena of the game client (e.g., the ninja challenge shown in fig. 6), and the game systems in the display interface 100a will not be enumerated here.

The display interface 100a may include the intelligent robot shown in fig. 6, and when the game terminal obtains the prompt information pushed by the service server, the prompt information may be output and displayed on the intelligent robot according to a specific display style, for example, as shown in fig. 6, the prompt information may be displayed by a dot with a specific color (e.g., a red dot). Optionally, the specific display style described in this embodiment of the application may include dots of a specific color, and may also include styles such as mails and pop-ups, and the display style of the prompt message is not listed here.

It is to be understood that the service data information of K service types herein may be answer texts with a certain timeliness prepared in advance for the game node (e.g., game node 1) of the game user at the next time (e.g., time T3) by the service server according to the latest user portrait information obtained by the user within a specific time (e.g., the first time), so that when the game environment of the game client runs to the game node 1 (e.g., time T3), the prompt information corresponding to the predicted answer texts may be output on the intelligent robot shown in fig. 6 to achieve the main triggering of the prompt information.

It can be understood that, in the embodiment of the present application, the game user may quickly switch the service scenario of the game client from the current game scenario to the question-and-answer scenario by triggering the area where the prompt information is located (i.e., triggering the intelligent robot control embedded in the game client), so that the game user may quickly acquire the answer text required by the game user at this time (i.e., at time T3) in the question-and-answer scenario.

For easy understanding, please refer to fig. 7, and fig. 7 is a scene schematic diagram of switching a game scene into a question and answer scene according to an embodiment of the present application. The game user a shown in fig. 7 may be a user who accesses the game client (e.g., fire fighter) through the game account information 60b shown in fig. 7. As shown in fig. 7, the game character selected by the game user a in the game client may be a virtual object 60a shown in fig. 7. The task starting control 50a shown in fig. 7 may be configured to start a scenario copy system in the game client, so that the game user a may obtain a virtual item for improving fighting capacity in a game environment corresponding to a corresponding scenario copy system through the virtual object 60a shown in fig. 7, and may also obtain a corresponding number of virtual assets, for example, the virtual asset may be a game chip that can be used to purchase a corresponding virtual item on a virtual mall.

It can be understood that, with the embodiment of the present application, content requirements of the game user under some important nodes in the game client can be intelligently identified through the user portrait information, so that user intentions of the game user under the important nodes can be intelligently identified, further content information (i.e., the service data information of the above-mentioned K service types) which may be needed can be prepared in advance for the game user under the corresponding game node based on the identified user intentions, and further the prepared service data information of the K service types can be packaged, so that the prompt information obtained by packaging can be subsequently output to the game terminal shown in fig. 7 for display. As shown in fig. 7, when the game user a performs a trigger operation on the icon area where the intelligent robot for displaying the prompt information shown in fig. 7 is located, the game terminal may respond to the trigger operation performed on the intelligent icon area to switch the service scenario of the game client from the display interface 100a shown in fig. 7 (i.e., the game home page in the game scenario) to the display interface 200a shown in fig. 7 (i.e., the friend interface in the question and answer scenario). It can be understood that, in the embodiment of the present application, the intelligent robot may be regarded as an intelligent partner of the game user a in the game client, so as to provide service data information of different dimensions for the game user a under the corresponding game node intelligently.

As shown in fig. 7, the display interface 200a may include a region 70a and a region 70b shown in fig. 7. The area 70a is a display area corresponding to the smart friend 90a (i.e., the smart friend) shown in fig. 7, and the area 70b is a display area corresponding to the game users 80a and … and the game user 80b shown in fig. 7. It will be appreciated that the game users 80a, …, 80b shown in FIG. 7 may be game friends under the same access server. The same access server may be a competition server corresponding to a certain competition area (e.g., a P area shown in fig. 7, where P is the number of the competition area, that is, P may be a positive integer) in the same login channel. The login channel may specifically be a social login channel, for example, a WeChat account login channel or a QQ account login channel.

For convenience of understanding, a login channel is taken as a wechat account login channel in the present application as an example, when the game client is accessed by using the wechat account login channel, the game client may be authorized to obtain login account information of the game user a, for example, the login account information may be game account information 60b shown in fig. 7 (for example, account name X shown in fig. 7). The P area shown in fig. 7 may be a sports area (e.g., WeChat 935 area) selected by the game user a in accessing the game client through the WeChat account login channel. It is understood that when the service server detects that there are other game users (e.g., game user 80b shown in fig. 7) having an interactive relationship (e.g., a friend relationship) with the game user a under the same server, the service server may automatically add the game user 80b as a game friend of the current game user a to present the output of the game user 80b on a friend list 80b shown in fig. 7. As shown in fig. 7, the number of game buddies in the area 70b may be n shown in fig. 7, and the value of n may be less than or equal to the buddy upper limit threshold (e.g., 200) shown in fig. 7.

In the embodiment of the present application, a login channel may include a plurality of competition areas, and one competition area may correspond to one competition server. It is understood that when the game user a performs the trigger operation with respect to the area 70a shown in fig. 7, the game terminal may be controlled to output service data information of different dimensions recommended for the game user a.

For example, for the game user belonging to the reflow user, some dynamically changing service events that occur during the period of absence of the game user (i.e., the access time interval formed by the M behavior record periods) may be prepared for the game user, that is, service data information of the plurality of service types may be recommended in advance for the game user carrying the old player reflow tag.

For another example, optionally, if the user image information includes a second type of user behavior tag, and the second type of user behavior tag indicates that the average activity obtained by the game user participating in the first type of task through the target game account information in the single behavior recording period is within the activity threshold range, the service server may take, in a next behavior recording period of the single behavior recording period, an access behavior in which the game user accesses the game client through the target game account information as a first target user behavior; the activity threshold range comprises a first activity threshold and a second activity threshold, and the second activity threshold is smaller than the second activity threshold; further, the service server may determine, based on the first target user behavior, the target game account information, and the auxiliary identification information associated with the target game account information, a first event type corresponding to the first target user behavior, and when the first event type hits a target event type in the data push conditions, determine that the game user satisfies the data push conditions; further, the service server may obtain a recommended network model corresponding to the game client, obtain, by the recommended network model, service data information of K service types that is matched with the user behavior tag of the second type in the user portrait information, and push prompt information corresponding to the service data information of the K service types to the game client.

Similarly, optionally, if a third type of user behavior tag exists in the user portrait information and the third type of user behavior tag indicates that the game user has not completed the second type of task in the game client through the target game account information, the service server may take the user behavior of re-executing the second type of task as a second target user behavior when the game user re-executes the second type of task through the target game account information; further, the service server may determine, based on the target user behavior, the target game account information, and the auxiliary identification information associated with the target game account information, a second event type corresponding to a second target user behavior, and when the second event type hits a target event type in the data push conditions, determine that the game user satisfies the data push conditions; further, the service server may obtain a recommended network model corresponding to the game client, obtain, by the recommended network model, service data information of K service types that is matched with the user behavior tag of the third type in the user portrait information, and push prompt information corresponding to the service data information of the K service types to the game client.

In the embodiment of the present invention, when the game user is in the game environment of the game client, for example, when the game user accesses the game client or executes a game task in the game client, active intervention may be performed for the game client in the game environment, and then the prompt information (for example, in the form of a red dot, a pop-up window, a mail, or the like) of the service data information of the K service types may be actively pushed to the game client, so as to implement active contact of the prompt information. It should be understood that K may take 1 or more values. For example, when the value of K is greater than 1, personalized multidimensional service data information may be provided for the game user, where the service data information may be text data prepared by a computer device for the game user in advance based on user portrait information of the game user. It should be understood that for different game users, different user portrait information can be obtained through portrayal based on the obtained behavior log table of the corresponding game user, and therefore when data recommendation is carried out based on the user portrait information, thousands of people can be achieved, and accuracy of data recommendation can be improved.

Further, please refer to fig. 8, where fig. 8 is a schematic flow chart of a service data pushing method according to an embodiment of the present invention. As shown in fig. 8, the method may be executed by a computer device, which may be a game terminal running the entertainment client, and the game terminal may be the game terminal in the embodiment corresponding to fig. 2; optionally, the computer device may also be a background server corresponding to the entertainment client, and the background server may be the service server in the embodiment corresponding to fig. 2. In other words, the method according to the embodiment of the present application may be executed by a game terminal corresponding to a game user, may be executed by a service server, or may be executed by both the game terminal and the service server. For convenience of understanding, the present embodiment is described by taking as an example that the method is executed by a service server (for example, the service server in the embodiment corresponding to fig. 2), and the method may include:

step S201, obtaining a behavior log table of a game user in a game client, and extracting key behavior data information associated with the game user from the behavior log table;

step S202, performing user portrait analysis on the key behavior data information to obtain user portrait information for representing game users;

step S203, when it is determined that the game user meets the data pushing condition based on the user portrait information, service data information of K service types matched with the user portrait information is obtained, and prompt information corresponding to the service data information of the K service types is pushed to the game client so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer.

For specific implementation of steps S201 to S203, reference may be made to the description of steps S101 to S103 in the embodiment corresponding to fig. 3, which will not be described herein again. The service data information of the K service types can contain service data information corresponding to the target service type; the service data information corresponding to the target service type comprises service auxiliary dimensions; at this time, the computer apparatus may continue to perform step S204 described below after performing step S203.

It can be understood that, after the service server executes the above S203, the game terminal running the game client can be ensured to display the prompt information issued by the service server on the game display interface (for example, the game home page) to which the game terminal is corresponding; specifically, reference may be made to the description of the prompt information in the embodiment corresponding to fig. 6, and details will not be further described here.

For easy understanding, please refer to fig. 9, and fig. 9 is a schematic view of a scene of service data information of different dimensions provided by an embodiment of the present application. As shown in fig. 9, it can be understood that, when a game user performs a trigger operation on the prompt information in the game display interface, the display interface of the game terminal may be switched from the game display interface (e.g., the display interface 100a shown in fig. 7) to a friend display interface (e.g., the display interface 200b shown in fig. 9). At this time, after the game user performs a trigger operation on an area (for example, the area 71a in the embodiment corresponding to fig. 9) where the intelligent companion (which may also be referred to as intelligent friend) in the friend display interface (i.e., the display interface 200b) is located, the display interface of the game terminal may be further switched from the friend display interface to a dialog display interface, for example, here, the display interface is an intelligent question and answer interface, which may be the display interface 300a shown in fig. 9. At this time, the game terminal may display, in the intelligent question-answering interface, service data information of K service types that the service server previously pushed for the game user. For example, the K service types may be 4 service types as shown in fig. 9, each of the 4 service types may be referred to as a dimension, and each dimension may correspond to a service data information list, which means that in one service data information list, a plurality of service data information associated with the same service type may exist.

For example, the 4 dimensions (i.e., multiple service types) shown in fig. 9 may specifically include dimension a, dimension B, dimension C, and dimension D shown in fig. 9. For example, taking the game client as a fire breaker as an example, the dimension a may be a version update dimension, and the version update dimension may be used to describe what service content updates exist in the game client running in the game terminal during the period of departure of the game character a, for example, the upper limit of the character level is increased to 140 levels (previously 130 levels), a breaker prop is added, and the like. Similarly, dimension B can be a Caprifier thematic dimension, which can be used to describe the business content associated with a Caprifier character during the time that game character A left, such as which Caprifier characters were newly online, etc. Similarly, dimension 3 here can be a strength-up dimension, which can be used to describe which game friends have increased their battle effectiveness during the time that the game character a leaves, and so on. Similarly, dimension 4 here may be a reflow reward dimension that may be used to describe which play objects are currently available to the game user, how to obtain the play objects, and so on. It can be understood that the present application can help the game user a having the first type of user behavior tag shown in fig. 9 to quickly familiarize with the latest version content when accessing the game client by intelligently recommending the service data information of different service types for the game user, and how to quickly follow up most of the battles under the same server (for example, the above-mentioned P zone) after the regression, so as to customize a personalized multidimensional question and answer solution for the game user a.

The service data information list corresponding to the dimension a may be a list 1, and the list 1 may include a plurality of service data information associated with the dimension a; the plurality of service data information may specifically be three service data information shown in fig. 9 (for example, service data information 1, service data information 2, and service data information 3 shown in fig. 9), and each service data information in the list 1 may include one service assistance dimension. As shown in fig. 9, in the process of outputting the service data information systems of the K service types in the display interface 300a, the game terminal may default to the dimension a shown in fig. 9 as the target service dimension, so as to output the service data information (i.e., the service data information 1, the service data information 2, and the service data information 3) corresponding to the target service dimension in the display interface shown in fig. 9, so that the following step S204 may be further executed.

Alternatively, it is understood that dimension B shown in FIG. 9 can be the new target business type when game user A triggers another dimension (e.g., dimension B) in the display interface 300 a. Further, the triggering operation executed for the dimension B may be referred to as a first triggering operation, and at this time, the game terminal may send a text corresponding to the first triggering operation as a problem text to the intelligent friend (that is, to the intelligent friend), so that the intelligent friend may perform intelligent adjustment on the service data information in the corresponding dimension prepared in advance based on the interaction behavior between the game user and the game client.

For ease of understanding, please refer to fig. 10, where fig. 10 is a schematic view of a scenario for switching service dimensions according to an embodiment of the present application. As shown in fig. 10, when the game user a triggers another dimension (for example, dimension B shown in fig. 10) in the display interface 300a shown in fig. 10, dimension B shown in fig. 10 may be taken as a new target business type, and text content (for example, the above-mentioned "earner specials") corresponding to the new target business type may be taken as a question text of the game user a, which may be a question text 1 displayed in the display interface 500a shown in fig. 10. It is understood that the display interface 300a and the display interface 500a shown in fig. 10 may be dialog display interfaces when the game user has a dialog with the game friend at different times. As shown in fig. 10, after the game user a sends the question text 1 shown in fig. 10 to the smart friend shown in fig. 10, the terminal corresponding to the smart friend (i.e., the service server) may pull an answer text (which may also be referred to as a dialog text) corresponding to the question text 1 for the game friend, replace the service data information in the dimension B prepared in advance with the pulled answer text, and then push the replaced service data information in the dimension B to the game terminal, so that the game terminal may output a plurality of pieces of service data information in the dimension B (i.e., the service data information B shown in fig. 10) in the display 500a shown in fig. 10, so as to improve the accuracy of text output. It is understood that the dimension B (i.e. the new target service dimension) output in the game terminal may also correspond to a service data information list, for example, list 2, and similarly, a plurality of service data information associated with the dimension B may exist in the list 2. Each service data message in the list 2 may contain a service assistance dimension, so that the following step S204 may be performed.

Optionally, in this embodiment of the application, when the game user a triggers another dimension (for example, the dimension B shown in fig. 10) in the display interface 300a shown in fig. 10, the dimension B shown in fig. 10 may be quickly used as a new target service type, and text content (for example, the above-mentioned "special issue of the ninja") corresponding to the new target service type may be used as a question text of the game user a, and the question text is sent to the intelligent friend shown in fig. 10, so that a terminal (that is, the above-mentioned service server) corresponding to the intelligent friend may notify the game terminal, so that the game terminal uses service data information corresponding to the dimension B locally stored by the game terminal as an answer text of the question text, and quickly outputs and displays the answer text in the display interface 500a shown in fig. 10, so as to improve efficiency of text output.

Step S204, receiving a service data request sent by the game terminal aiming at the service auxiliary dimension under the target service type, and acquiring L pieces of service auxiliary information associated with the service auxiliary dimension from a service database associated with the target service type based on the service data request;

step S205, outputting the L pieces of service auxiliary information to a dialogue display interface of the game client;

for ease of understanding, please refer to fig. 11, where fig. 11 is a schematic diagram of a scenario for acquiring L pieces of service assistance information associated with a service assistance dimension according to an embodiment of the present application. The display interface 500b shown in fig. 10 may be a dialog display interface in the embodiment corresponding to fig. 10. The dialog text 1 associated with the dimension B may be the service data information B in the embodiment corresponding to fig. 10. As shown in fig. 11, when the target service type is the dimension B shown in fig. 11, the game user a may perform a second trigger operation on the service assistant dimension (e.g., the assistant dimension B2 shown in fig. 11) in the dimension B, so as to use the text indicated by the second trigger operation (i.e., the assistant dimension B2) as a new question text, where the new question text may be the question text 2 shown in fig. 11, which means that at this time, the game terminal may send a service data request to the terminal corresponding to the intelligent friend shown in fig. 11 for the service assistant dimension (i.e., the assistant dimension B2) in the target service type shown in fig. 11.

Based on this, the terminal corresponding to the game friend shown in fig. 11 (i.e., the service server described above) may receive the service data request sent by the game terminal for the assistant dimension B2 shown in fig. 11, and may obtain, based on the received service data request, L pieces of service assistance information associated with the assistant dimension B2 from a service database (referred to as a question-answer database herein) associated with the dimension B, and may further use the obtained L pieces of service assistance information as the dialog text 2 (i.e., answer text) corresponding to the assistant dimension B2 shown in fig. 11, so as to return the dialog text 2 to the game terminal, so that the game terminal may output the dialog text 2 in the display interface 500c shown in fig. 11.

It is to be understood that, if the auxiliary dimension b2 is the game character "Chao hand { Bai Hao }" in the game client, the service server may pull the text information (e.g., the dialog text 2 shown in fig. 11) associated with the game character "Chao hand { Bai Hao }" from the corresponding service database, and may also obtain the video (e.g., the video of the auxiliary dimension b2 shown in fig. 11) associated with the game character "Chao hand { Bai Hao }". In this way, the L pieces of service assistance information associated with the service assistance dimension acquired by the game terminal may specifically include the dialog text 2 shown in fig. 11 and the video of the assistance dimension b2 shown in fig. 11, and then the two pieces of service assistance information may be output and displayed in the display interface 500c shown in fig. 11.

Step S206, when a target service type sent by the game terminal and a service auxiliary dimension under the target service type are obtained, recording a first trigger operation executed aiming at the target service type and a second trigger operation executed aiming at the service auxiliary dimension, and respectively using the first trigger operation and the second trigger operation as interactive behavior data between the game client and the game client;

step S207, forming a user behavior path of the game user based on the interactive behavior data, and determining a game node of the game client in the game environment of the game client based on the user behavior path;

and S208, identifying the interaction intention of the game user based on the game node, adjusting the dialog text associated with the game node based on the interaction intention, and outputting the adjusted dialog text to a dialog display interface corresponding to the game node.

Wherein, it can be understood that, in the embodiment of the present application, by recording the interaction behavior data between the game user and the game client in the game client, the service server can be helped to obtain the user behavior path of the game user, namely, the service server can reversely push out the game node where the game user is located in the game environment by recording the interactive behavior of the user in the corresponding dialog display interface, the interactive intention of the game user can be further recognized by the game nodes obtained by reverse reasoning, so that the game user can be helped to carry out multiple context-related conversations in the conversation display interface, and therefore, when the service server obtains the service data request of the game user, the service server can dynamically adjust the service data information configured in advance, and intelligent adjustment of the recommended text content can be realized, so that the adjusted text content can be ensured to fit the interaction intention of the user as much as possible.

For ease of understanding, please refer to fig. 12, where fig. 12 is a schematic flowchart illustrating an interaction between a service server and a game terminal according to an embodiment of the present application. The service server shown in fig. 12 may be the service server in the embodiment corresponding to fig. 2. As shown in fig. 12, when the service server executes step S11, the service server may acquire a game log of the game user (i.e., the behavior log table), and further execute step S12 to screen important node fields (i.e., the key behavior data information) that need to be intervened from the acquired game log. At this time, the service server may perform step S13 to encapsulate the screened important node fields into an interface, and further may perform step S14 to configure a trigger condition in the background according to the encapsulated interface (where the trigger condition may be the data push condition). In this way, when the game terminal shown in fig. 12 performs step S15, various behaviors generated in the game may occur to the service server shown in fig. 12, so that the service server may perform step S14 according to the acquired behaviors to determine whether the current game interaction behaviors of the game user satisfy the reach conditions, and further, when the reach conditions are satisfied, step S17 may be performed to help the game user solve the problem in the corresponding game node in a manner of active reach. Optionally, after the step S14 is executed, when it is determined that the current game interaction behaviors of the game user do not satisfy the touch condition, the embodiment of the application may continue to jump to execute the step S11 to obtain a new game log.

Therefore, the service server can continuously obtain new user portrait information for describing the game user based on the interactive behavior information, so that when the game user is in the game environment of the game client, for example, when the game user accesses the game client or executes a game task in the game client, the service server can perform active intervention for the game client in the game environment, and further can actively push prompt information (for example, in the form of red dots, pop windows, mails and the like) of the service data information of the K service types to the game terminal to realize main contact of the prompt information, and also can provide personalized multidimensional service data information for the game user, wherein the service data information can be based on the new user portrait information (i.e. current user portrait information) of the game user for the service server, the game users are provided with the text data with different dimensions in advance, and it can be understood that different user portrait information can be obtained by depicting based on the behavior log table for different game users, and therefore when data recommendation is carried out based on the user portrait information, thousands of people can be achieved, and accuracy of data recommendation can be improved.

Further, please refer to fig. 13, where fig. 13 is a schematic structural diagram of a service data pushing apparatus according to an embodiment of the present invention. The service data pushing apparatus 1 may be applied to the service server, which may be the service server 2000 in the embodiment corresponding to fig. 1. Further, the service data pushing apparatus 1 may include: a log table acquisition module 10, an image analysis module 20 and a service data pushing module 30; further, the service data pushing apparatus 1 may further include: a key data packaging module 40, a service interface calling module 50, a request receiving module 60, an auxiliary information output module 70, an interactive behavior determining module 80, a behavior path determining module 90 and a dialogue text adjusting module 100;

a log table obtaining module 10, configured to obtain a behavior log table of a game user in a game client, and extract key behavior data information associated with the game user from the behavior log table;

the log table obtaining module 10 includes: a first pulling unit 101, a table name obtaining unit 102, a key field obtaining unit 103 and a key data determining unit 104;

the first pull list 101 is used for pulling a first log list of a game user in a game client within a first time length from a log management system corresponding to the game client;

the table name acquisition unit 102 is configured to use the first login log table as a behavior log table of the game user, and acquire a target table name field corresponding to the behavior log table;

a key field obtaining unit 103, configured to extract, from the behavior log table, a target key field corresponding to a historical game interaction behavior of the game user within a first duration;

and the key data determining unit 104 is used for determining key behavior data information associated with the game user based on the target table name field and the target key field.

For specific implementation manners of the first pulling unit 101, the table name obtaining unit 102, the key field obtaining unit 103, and the key data determining unit 104, reference may be made to the description of step S101 in the embodiment corresponding to fig. 3, and details will not be further described here.

Optionally, the key data encapsulation module 40 is configured to determine a target event type corresponding to the key behavior data information, encapsulate the key behavior data information based on an interface encapsulation rule corresponding to the target event type, obtain a service interface corresponding to the key behavior data information, and store the service interface in a user portrait system associated with the log management system;

and the service interface calling module 50 is used for calling a service interface to acquire the key behavior data information of the game user in the user representation system.

For specific implementation of the key data encapsulation module 40 and the service interface calling module 50, reference may be made to the description of the service interface in the embodiment corresponding to fig. 3, and details will not be further described here.

The portrait analysis module 20 is used for carrying out user portrait analysis on the key behavior data information to obtain user portrait information for representing game users;

wherein, portrait analysis module 20 includes: a user model acquisition unit 201, a data analysis unit 202 and a user portrait construction unit 203; optionally, portrait analysis module 20 may further include: a history table pull unit 204, a field extraction unit 205, and a representation model training unit 206;

a user model obtaining unit 201, configured to obtain a user representation model corresponding to a game client from a user representation system;

the data analysis unit 202 is used for inputting the key behavior data information into a user portrait model corresponding to the game client, and performing data analysis on the key behavior data information by using the user portrait model to obtain a data analysis result corresponding to the key behavior data information;

wherein the user portrait model comprises a feature extractor and a classifier;

the data analysis unit 202 includes: a feature extraction subunit 2021, a matching degree determination subunit 2022, a user tag determination subunit 2023, and an analysis result determination subunit 2024;

the feature extraction subunit 2021 is configured to input the key behavior data information into the user portrait model, and extract a behavior feature vector corresponding to the key behavior data information by using a feature extractor in the user portrait model;

the matching degree determining subunit 2022 is configured to input the feature behavior vector to a classifier in the user portrait model, and perform data analysis on the key behavior data information by the classifier in the user portrait model to obtain a matching degree between the feature behavior vector and a sample attribute feature in the classifier;

the user tag determining subunit 2023 is configured to use, in the matching degree, the sample attribute feature of which the feature behavior vector has the maximum matching degree as a target sample attribute feature, and use a sample tag corresponding to the target sample attribute feature as a user behavior tag of the behavior feature vector;

the analysis result determination subunit 2024 is configured to use the user behavior tag as a data analysis result corresponding to the user portrait model.

For a specific implementation manner of the feature extraction subunit 2021, the matching degree determination subunit 2022, the user tag determination subunit 2023, and the analysis result determination subunit 2024, reference may be made to the description of the specific process for determining the user behavior tag in the embodiment corresponding to fig. 3, which will not be described again.

And the user portrait construction unit 203 is used for constructing user portrait information for representing game users based on the user behavior labels corresponding to the key behavior data information indicated by the data analysis result.

Optionally, the history table pulling unit 204 is configured to pull a second log table of the game user in a second duration from the log management system; the second duration is the last duration of the first duration;

a field extracting unit 205, configured to extract a history table name field associated with the game user and a history key field associated with the history table name field from the second login log table;

and the portrait model training unit 206 is configured to train an initial portrait model in the user portrait system based on the training behavior data information, using the historical table name field and the historical key field as training behavior data information, and using the trained initial portrait model as the user portrait model.

For specific implementation manners of the user model obtaining unit 201, the data analyzing unit 202, and the user portrait constructing unit 203, reference may be made to the description of step S102 in the embodiment corresponding to fig. 3, and details will not be further described here. Optionally, for a specific implementation manner of the history table pulling unit 204, the field extracting unit 205, and the image model training unit 206, reference may be made to the description of the specific process for training the initial image model in the embodiment corresponding to fig. 3, and details will not be further described here.

The service data pushing module 30 is configured to, when it is determined that the game user satisfies the data pushing condition based on the user portrait information, obtain service data information of K service types that is matched with the user portrait information, and push prompt information corresponding to the service data information of the K service types to the game client, so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer.

The service data pushing module 30 includes: a backflow detection unit 301, a backflow event determination unit 302, a data recommendation unit 303; optionally, the service data pushing module 30 may further include: an activity detection unit 304, a first event determination unit 305, a first push unit 306, a task detection unit 307, a second event determination unit 308, and a second push unit 309;

a reflow detection unit 301, configured to determine, in a next behavior recording period of M consecutive behavior recording periods, an access behavior of a game user accessing the game client through the target game account information as a user reflow behavior if a first type of user behavior tag exists in the user image information and indicates that a user access behavior of the game user accessing the game client through the target game account information is not detected in all of the M consecutive behavior recording periods; m is greater than or equal to the access time interval;

a reflow event determining unit 302, configured to use an event type corresponding to a user reflow behavior as a reflow event type based on the user reflow behavior and the target game account information, and determine that a game user satisfies a data pushing condition when it is detected that the reflow event type hits a target event type in the data pushing condition;

the data recommendation unit 303 is configured to obtain a recommendation network model corresponding to the game client, obtain, by the recommendation network model, service data information of K service types that is matched with the user behavior tag of the first type in the user image information, and push prompt information corresponding to the service data information of the K service types to the game client.

Optionally, the activity detection unit 304 is configured to, if a second type of user behavior tag exists in the user portrait information, and the second type of user behavior tag indicates that an average activity obtained by the game user participating in the first type of task through the target game account information in the single behavior recording period is within an activity threshold range, regarding an access behavior of the game user accessing the game client through the target game account information as a first target user behavior in a next behavior recording period of the single behavior recording period; the activity threshold range comprises a first activity threshold and a second activity threshold, and the second activity threshold is smaller than the second activity threshold;

a first event determining unit 305, configured to determine a first event type corresponding to the first target user behavior based on the first target user behavior, the target game account information, and the auxiliary identification information associated with the target game account information, and determine that the game user satisfies the data push condition when the first event type hits a target event type in the data push condition;

the first pushing unit 306 is configured to obtain a recommended network model corresponding to the game client, obtain, by the recommended network model, service data information of K service types that is matched with the user behavior tag of the second type in the user image information, and push prompt information corresponding to the service data information of the K service types to the game client.

Optionally, the task detecting unit 307 is configured to, if a third type of user behavior tag exists in the user portrait information and the third type of user behavior tag indicates that the game user has not completed the second type of task in the game client through the target game account information, regard the user behavior of re-executing the second type of task as a second target user behavior when the game user re-executes the second type of task through the target game account information;

a second event determining unit 308, configured to determine, based on the target user behavior, the target game account information, and the auxiliary identification information associated with the target game account information, a second event type corresponding to the second target user behavior, and when the second event type hits a target event type in the data pushing conditions, determine that the game user satisfies the data pushing conditions;

the second pushing unit 309 is configured to obtain a recommended network model corresponding to the game client, obtain, by the recommended network model, service data information of K service types that is matched with the user behavior tag of the third type in the user image information, and push prompt information corresponding to the service data information of the K service types to the game client.

For specific implementation manners of the backflow detecting unit 301, the backflow event determining unit 302, the data recommending unit 303, the activity detecting unit 304, the first event determining unit 305, the first pushing unit 306, the task detecting unit 307, the second event determining unit 308, and the second pushing unit 309, reference may be made to the description of step S203 in the embodiment corresponding to fig. 3, and details will not be further described here.

Optionally, the service data information of the K service types includes service data information corresponding to the target service type; the service data information corresponding to the target service type comprises service auxiliary dimensions;

a request receiving module 60, configured to receive a service data request sent by a game terminal for a service assistance dimension in a target service type, and obtain L pieces of service assistance information associated with the service assistance dimension from a service database associated with the target service type based on the service data request;

and an auxiliary information output module 70, configured to output the L pieces of service auxiliary information to a dialog display interface of the game client.

Optionally, the interactive behavior determining module 80 is configured to record a first trigger operation executed for the target service type and a second trigger operation executed for the service assistance dimension when the target service type sent by the game terminal and the service assistance dimension under the target service type are obtained, and respectively use the first trigger operation and the second trigger operation as interactive behavior data between the game client and the game client;

a behavior path determining module 90, configured to form a user behavior path of the game user based on the interactive behavior data, and determine a game node where the game client is located in the game environment of the game client based on the user behavior path;

and the dialog text adjusting module 100 is configured to identify an interaction intention of the game user based on the game node, adjust a dialog text associated with the game node based on the interaction intention, and output the adjusted dialog text to a dialog display interface corresponding to the game node.

For a specific implementation manner of the log table obtaining module 10, the image analyzing module 20, and the service data pushing module 30, reference may be made to the description of step S101 to step S103 in the embodiment corresponding to fig. 3, which will not be further described here. Optionally, for specific implementation manners of the key data encapsulation module 40, the service interface calling module 50, the request receiving module 60, the auxiliary information output module 70, the interactive behavior determination module 80, the behavior path determination module 90, and the dialog text adjustment module 100, reference may be made to the description of step S201 to step S208 in the embodiment corresponding to fig. 8, which will not be further described here. In addition, the beneficial effects of the same method are not described in detail.

Further, please refer to fig. 14, fig. 14 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 14, the computer device 1000 may be a service server, which may be the service server 2000 in the embodiment corresponding to fig. 1. The computer device 1000 may include: the processor 1001, the network interface 1004, and the memory 1005, and the computer device 1000 may further include: a user interface 1003, and at least one communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The optional user interface 1003 may further include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1004 may be a high-speed RAM memory or a non-volatile memory (e.g., at least one disk memory). The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 14, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a device control application program.

The network interface 1004 in the computer device 1000 may also be connected to the game terminal in the embodiment corresponding to fig. 2 through a network. In the computer device 1000 shown in fig. 14, the network interface 1004 may provide a network communication function; the user interface 1003 is an interface for providing a user with input; and the processor 1001 may be used to invoke a device control application stored in the memory 1005 to implement:

It should be understood that the computer device 1000 described in the embodiment of the present invention may perform the description on the service data pushing method in the embodiment corresponding to fig. 3 or fig. 8, and may also perform the description on the service data pushing apparatus 1 in the embodiment corresponding to fig. 13, which is not described herein again. In addition, the beneficial effects of the same method are not described in detail.

Further, here, it is to be noted that: an embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores the aforementioned computer program executed by the service data pushing apparatus 1, and the computer program includes program instructions, and when the processor executes the program instructions, the description of the service data pushing method in the embodiment corresponding to fig. 3 or fig. 8 can be executed, so that details are not repeated here. In addition, the beneficial effects of the same method are not described in detail. For technical details not disclosed in the embodiments of the computer storage medium to which the present invention relates, reference is made to the description of the method embodiments of the present invention. For technical details not disclosed in embodiments of the computer-readable storage medium referred to in the present application, reference is made to the description of embodiments of the method of the present application. As an example, program instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network, which may comprise a block chain system.

An aspect of the application provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device can execute the description of the service data pushing method in the embodiment corresponding to fig. 3 or fig. 8, which is not described herein again. In addition, the beneficial effects of the same method are not described in detail.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims

1. A method for pushing service data is characterized by comprising the following steps:

acquiring a behavior log table of a game user in a game client within a first time length from a log management system corresponding to the game client, extracting a target table name field and a target key field from the behavior log table, and determining key behavior data information associated with the game user based on the target table name field and the target key field;

determining a target event type corresponding to the key behavior data information, packaging the key behavior data information based on an interface packaging rule corresponding to the target event type to obtain a service interface corresponding to the key behavior data information, and storing the service interface to a user portrait system associated with the log management system;

in the user representation system, calling the service interface to acquire the key behavior data information of the game user;

performing user portrait analysis on the key behavior data information to obtain user portrait information for representing the game user;

when it is determined that the target interaction behavior executed by a game node of the game user in the current game environment meets the target event type in the data pushing condition based on the user portrait information, acquiring service data information of K service types matched with the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to the game client so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer; the service data information of the K service types comprises service data information corresponding to a target service type; the service data information corresponding to the target service type comprises service auxiliary dimensions;

receiving a service data request sent by the game client aiming at the service auxiliary dimension under the target service type, and acquiring L pieces of service auxiliary information associated with the service auxiliary dimension from a service database associated with the target service type based on the service data request;

taking the L pieces of service auxiliary information as a dialog text corresponding to the service auxiliary dimension, and outputting the dialog text to a dialog display interface of the game client;

when the target service type and the service auxiliary dimension under the target service type sent by the game client are obtained, recording a first trigger operation executed aiming at the target service type and a second trigger operation executed aiming at the service auxiliary dimension, and respectively taking the first trigger operation and the second trigger operation as interactive behavior data between the game user and the game client;

forming a user behavior path of the game user based on the interaction behavior data, and determining a game node where the game user is located in a game environment of the game client based on the user behavior path;

and identifying the interaction intention of the game user based on the game node, adjusting the dialog text associated with the game node based on the interaction intention, and outputting the adjusted dialog text to a dialog display interface corresponding to the game node.

2. The method according to claim 1, wherein the obtaining a behavior log table of a game user in a game client within a first duration from a log management system corresponding to the game client, extracting a target table name field and a target key field from the behavior log table, and determining key behavior data information associated with the game user based on the target table name field and the target key field comprises:

pulling a first log table of a game user in a game client within a first time length from a log management system corresponding to the game client;

taking the first log-in log table as a behavior log table of the game user, and acquiring a target table name field corresponding to the behavior log table;

extracting a target key field corresponding to the historical game interaction behavior of the game user in the first time length from the behavior log table;

and determining key behavior data information associated with the game user based on the target table name field and the target key field.

3. The method of claim 2, wherein the target key field comprises at least one of: the game client comprises the identity identification information of the game user, the name of the role of the game user in the game client, the gender information of the game user, the role grade of the game user in the game client and the competitive grade of the game user in the game client.

4. The method of claim 1, wherein the performing user portrayal analysis on the key behavior data information to obtain user portrayal information for characterizing the game user comprises:

acquiring a user portrait model corresponding to the game client from the user portrait system;

inputting the key behavior data information into a user portrait model corresponding to the game client, and performing data analysis on the key behavior data information by using the user portrait model to obtain a data analysis result corresponding to the key behavior data information;

and constructing user portrait information used for representing the game user based on the user behavior label corresponding to the key behavior data information indicated by the data analysis result.

5. The method of claim 4, wherein the user representation model includes a feature extractor and a classifier;

the inputting the key behavior data information into a user portrait model corresponding to the game client, and performing data analysis on the key behavior data information by the user portrait model to obtain a data analysis result corresponding to the key behavior data information includes:

inputting the key behavior data information into the user portrait model, and extracting a behavior feature vector corresponding to the key behavior data information by the feature extractor in the user portrait model;

inputting the characteristic behavior vector into the classifier in the user portrait model, and performing data analysis on the key behavior data information by the classifier in the user portrait model to obtain the matching degree between the characteristic behavior vector and the sample attribute feature in the classifier;

in the matching degree, taking the sample attribute feature of which the characteristic behavior vector has the maximum matching degree as a target sample attribute feature, and taking a sample label corresponding to the target sample attribute feature as a user behavior label of the behavior characteristic vector;

and taking the user behavior tag as a data analysis result corresponding to the user portrait model.

6. The method of claim 4, prior to said obtaining a user representation model corresponding to said game client, further comprising:

pulling a second log table of the game user in a second time length from the log management system; the second duration is the last duration of the first duration;

extracting a history table name field associated with the game user and a history key field associated with the history table name field from the second login log table;

and taking the historical table name field and the historical key field as training behavior data information, training an initial portrait model in the user portrait system based on the training behavior data information, and taking the trained initial portrait model as the user portrait model.

7. The method of claim 1, wherein when it is determined that the target interaction behavior performed by the game user in the game node in the current game environment satisfies the target event type in the data pushing condition based on the user portrait information, acquiring service data information of K service types matching with the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to the game client, comprises:

if a first type of user behavior tag exists in the user image information and indicates that a user access behavior of the game user accessing the game client through the target game account information is not detected in all of M continuous behavior recording periods, determining an access behavior of the game user accessing the game client through the target game account information as a user reflow behavior in a next behavior recording period of the M continuous behavior recording periods; the M is greater than or equal to the access time interval;

based on the user reflow behavior and the target game account information, taking an event type corresponding to the user reflow behavior as a reflow event type, and when detecting that the reflow event type hits the target event type in the data push conditions, determining that the user reflow behavior executed by a game node of the game user in the current game environment meets the data push conditions;

and acquiring a recommended network model corresponding to the game client, acquiring service data information of K service types matched with the first type of user behavior tags in the user portrait information by the recommended network model, and pushing prompt information corresponding to the service data information of the K service types to the game client.

8. The method of claim 1, wherein when it is determined that the target interaction behavior performed by the game user in the game node in the current game environment satisfies the target event type in the data pushing condition based on the user portrait information, acquiring service data information of K service types matching with the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to the game client, comprises:

if a second type of user behavior tag exists in the user portrait information and the second type of user behavior tag indicates that the average activity obtained by the game user participating in a first type of task through target game account information in a single behavior recording period is within an activity threshold range, taking an access behavior of the game user accessing the game client through the target game account information as a first target user behavior in a next behavior recording period of the single behavior recording period; the activity threshold range comprises a first activity threshold and a second activity threshold, and the first activity threshold is smaller than the second activity threshold;

determining a first event type corresponding to the first target user behavior based on the first target user behavior, the target game account information and auxiliary identification information associated with the target game account information, and determining that the first target user behavior executed by a game node of the game user in the current game environment meets the data push condition when the first event type hits the target event type in the data push condition;

and acquiring a recommended network model corresponding to the game client, acquiring service data information of K service types matched with the user behavior tags of the second type in the user portrait information by the recommended network model, and pushing prompt information corresponding to the service data information of the K service types to the game client.

9. The method of claim 1, wherein when it is determined that the target interaction behavior performed by the game user in the game node in the current game environment satisfies the target event type in the data pushing condition based on the user portrait information, acquiring service data information of K service types matching with the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to the game client, comprises:

if a third type of user behavior tag exists in the user portrait information and indicates that the game user has not completed a second type of task in the game client through the target game account information, when the game user re-executes the second type of task through the target game account information, taking the user behavior of re-executing the second type of task as a second target user behavior;

determining a second event type corresponding to the second target user behavior based on the second target user behavior, the target game account information and auxiliary identification information associated with the target game account information, and determining that the second target interactive behavior executed by the game node in the current game environment by the game user meets the data push condition when the second event type hits a target event type in the data push condition;

and acquiring a recommended network model corresponding to the game client, acquiring service data information of K service types matched with the user behavior tag of the third type in the user portrait information by the recommended network model, and pushing prompt information corresponding to the service data information of the K service types to the game client.

10. A service data pushing apparatus, comprising:

the system comprises a log table acquisition module, a log management module and a data processing module, wherein the log table acquisition module is used for acquiring a behavior log table of a game user in a game client within a first time length from a log management system corresponding to the game client, extracting a target table name field and a target key field from the behavior log table, and determining key behavior data information associated with the game user based on the target table name field and the target key field;

a key data encapsulation module, configured to determine a target event type corresponding to the key behavior data information, encapsulate the key behavior data information based on an interface encapsulation rule corresponding to the target event type, obtain a service interface corresponding to the key behavior data information, and store the service interface in a user representation system associated with the log management system;

the service interface calling module is used for calling the service interface to acquire the key behavior data information of the game user in the user representation system;

the portrait analysis module is used for carrying out user portrait analysis on the key behavior data information to obtain user portrait information used for representing the game user;

the service data pushing module is used for acquiring service data information of K service types matched with the user portrait information when it is determined that the target interaction behavior executed by the game node of the game user in the current game environment meets the target event type in the data pushing condition based on the user portrait information, and pushing prompt information corresponding to the service data information of the K service types to the game client so as to display the prompt information in a game display interface corresponding to the game client; k is a positive integer; the service data information of the K service types comprises service data information corresponding to a target service type; the service data information corresponding to the target service type comprises service auxiliary dimensions;

a request receiving module, configured to receive a service data request sent by the game client for the service assistance dimension in the target service type, and obtain, based on the service data request, L pieces of service assistance information associated with the service assistance dimension from a service database associated with the target service type;

the auxiliary information output module is used for taking the L pieces of service auxiliary information as a dialog text corresponding to the service auxiliary dimension and outputting the dialog text to a dialog display interface of the game client;

the interactive behavior determining module is used for recording a first trigger operation executed aiming at the target business type and a second trigger operation executed aiming at the business auxiliary dimension when the target business type sent by the game client and the business auxiliary dimension under the target business type are obtained, and taking the first trigger operation and the second trigger operation as interactive behavior data between the game user and the game client respectively;

a behavior path determining module, configured to form a user behavior path of the game user based on the interactive behavior data, and determine a game node where the game user is located in a game environment of the game client based on the user behavior path;

11. A computer device, comprising: a processor, a memory, a network interface;

the processor is connected to a memory for providing data communication functions, a network interface for storing a computer program, and a processor for calling the computer program to perform the method of any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions which, when executed by a processor, perform the method of any of claims 1-9.