WO2021164294A1

WO2021164294A1 - Behavior-analysis-based configuration update method and apparatus, and device and storage medium

Info

Publication number: WO2021164294A1
Application number: PCT/CN2020/123417
Authority: WO
Inventors: 曾祥辉; 郝彬彬
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-02-17
Filing date: 2020-10-23
Publication date: 2021-08-26
Also published as: CN111459993B; CN111459993A

Abstract

A behavior-analysis-based configuration update method and apparatus, and a device and a storage medium, which relate to the field of intelligent decision making, and realize automatic configuration of a work flow according to user operation behaviors. The method comprises: acquiring event tracking record data of a target user terminal, wherein the event tracking record data comprises respective statistical data of a plurality of event tracking events (S110); on the basis of a function completion rate model of each target event node, determining a function completion rate of each target event node according to the statistical data in the event tracking record data, wherein the target event node is an event node in a decision tree model (S120); on the basis of the decision tree model, determining a target event flow according to the function completion rate of each target event node, wherein the target event flow comprises at least one target event node (S130); and according to the target event flow, determining configuration data, and sending the configuration data to the target user terminal, such that the target user terminal updates a configuration according to the configuration data (S140).

Description

Configuration update method, device, equipment and storage medium based on behavior analysis

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on February 17, 2020 with the application number 202010097864.5 and the invention title "Configuration update method, device, equipment and storage medium based on behavior analysis", and its entire content Incorporated in this application by reference.

Technical field

This application relates to the field of intelligent decision-making, and in particular to a configuration update method, device, device, and storage medium based on user behavior analysis.

Background technique

Nowadays, big data is developing rapidly. Many industries, such as finance, investment, and e-commerce, have begun to use big data to mirror data collection, analysis, and mining, and through various user analysis and modeling, to guide industry strategy formulation and decision-making. In terms of application product design, it also began to iterate on products using the results of big data user behavior analysis, optimize functions and processes, and design application products that are more suitable for user needs.

The inventor realizes that the existing process design in the industry often goes through a cyclical process of "research-function and process combing-development-release-re-investigation-re-organization-development iteration-re-release". This process often takes a long time. The function and process combing relies on the research results, and the development also relies on the combing design of the functional process. Frequent releases also affect the user experience to a certain extent, and even affect the execution of tasks. The operation flow cannot be dynamically configured according to the user's operating behavior or habits, resulting in the flow being not intelligent enough, affecting the operation experience and the operation flow.

Summary of the invention

The embodiments of the present application provide a configuration update method, device, device, and storage medium based on behavior analysis, so as to realize automatic configuration of a work flow based on user operation behavior.

In the first aspect, this application provides a configuration update method based on behavior analysis, and the method includes:

Acquiring burial point record data of the target user terminal, where the burial point record data includes respective statistical data of multiple burial point events;

Determine the function completion rate of each target event node based on the function completion rate model of each target event node according to the statistical data in the buried point record data, where the target event node is an event node in the decision tree model;

Based on the decision tree model, determining a target event process according to the function completion rate of each target event node, where the target event process includes at least one of the target event nodes;

The configuration data is determined according to the target event flow, and the configuration data is sent to the target user terminal, so that the target user terminal updates the configuration according to the configuration data.

In a second aspect, the present application provides a configuration update device, the configuration update device includes:

The data acquisition module is used to acquire the burial point record data of the target user terminal, the burial point record data including the respective statistical data of multiple burial point events;

The completion rate determination module is used to determine the function completion rate of each target event node based on the function completion rate model of each target event node and the statistical data in the buried point record data, where the target event node is a decision tree Event nodes in the model;

A process determining module, configured to determine a target event process according to the function completion rate of each target event node based on the decision tree model, the target event process including at least one of the target event nodes;

The configuration update module is configured to determine configuration data according to the target event flow, and send the configuration data to the user terminal, so that the target user terminal updates the configuration according to the configuration data.

In a third aspect, the present application provides a computer device, the computer device includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and when the computer is executed The following methods are implemented in the program:

Based on the function completion rate model of each target event node, determine the function completion rate of each target event node based on statistical data in the buried point record data, where the target event node is an event node in the decision tree model;

In a fourth aspect, this application provides a computer-readable storage medium that stores a computer program, and if the computer program is executed by a processor, the following method is implemented:

This application calculates the function completion rate of each process node according to the user's behavior habit data, and determines the process matching the user's current behavior habit according to the decision tree model, that is, the target event process; then, the relevant configuration corresponding to the target event process is sent to the user terminal , So that the operation flow of the user terminal is dynamically configured and updated according to the user's operation behavior or habits. At the same time, the technical means of determining the target event process adopted in this application can effectively improve the accuracy of user behavior analysis, and thereby improve the efficiency of mobile terminal software configuration.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative work, other drawings can be obtained from these drawings.

FIG. 1 is a schematic flowchart of a configuration update method based on behavior analysis according to an embodiment of this application;

FIG. 2 is a schematic diagram of a sub-process for obtaining buried point record data according to an embodiment;

FIG. 3 is a schematic diagram of a sub-process for determining a function completion rate according to an embodiment;

4 is a schematic structural diagram of a decision tree model provided by an embodiment of this application;

FIG. 5 is a schematic flowchart of a method for training a function completion rate model provided by an embodiment of the application;

FIG. 6 is a schematic diagram of a sub-process of determining a function completion rate model of an embodiment;

FIG. 7 is a schematic structural diagram of a configuration update apparatus provided by an embodiment of this application;

FIG. 8 is a schematic structural diagram of a configuration update apparatus provided by another embodiment of this application;

FIG. 9 is a schematic structural diagram of a computer device provided by an embodiment of this application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The flowchart shown in the drawings is only an example, and does not necessarily include all contents and operations/steps, nor does it have to be executed in the described order. For example, some operations/steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to actual conditions. In addition, although functional modules are divided in the schematic diagram of the device, in some cases, they may be divided into different modules from the schematic diagram of the device.

It should be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should also be understood that the term "and/or" used in the specification and appended claims of this application refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

The technical solution of this application can be applied to the fields of artificial intelligence, blockchain and/or big data technology, and can perform data mining on user behavior. Optionally, the data involved in this application, such as buried point record data, can be stored in a database, or can be stored in a blockchain, which is not limited in this application.

The embodiments of the present application provide a configuration update method, device, device, and storage medium based on behavior analysis. Among them, the configuration update method based on behavior analysis can be used to effectively improve the accuracy of user behavior analysis, thereby improving the efficiency of mobile terminal software configuration.

Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

Referring to FIG. 1, an embodiment of the present application provides a configuration update method based on behavior analysis. The configuration update method can be applied to a server, for example.

The configuration update method based on behavior analysis is to obtain the user's behavior habits from the user's mobile terminal, such as the order in which the user operates the software interface, the order in which the buttons on the software interface are clicked, and other data, so as to be based on the user's current behavior habits and behaviors. The correlation between the calculation of the function completion rate of each process node, and according to the decision tree model to determine the process that matches the user’s current behavior habits, that is, the target event process; then the relevant configuration corresponding to the target event process is sent to the user terminal to make The work flow of the user terminal is dynamically configured according to the user's operating behavior or habits.

Specifically, the user terminal may be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device.

As shown in FIG. 1, the configuration update method based on behavior analysis specifically includes the following steps S110 to S140.

S110. Obtain burial point record data of the target user terminal, where the burial point record data includes respective statistical data of multiple burial point events.

In some implementations, the server obtains the operation behavior of the target user terminal through a burying behavior. The burying point is to collect some information in a specific process of the application, which is used to track the usage status of the application, and subsequently used to further optimize the product or provide operational data support. For example, for a map APP, all user operation behaviors involved in the existing map APP interface are counted and classified. Specifically, by predicting all possible operating behaviors of the user, and processing the operating behaviors, to obtain the buried point record data of at least one user terminal in different time periods, and the buried point record data includes a plurality of buried points. Click the statistics of the event.

In some embodiments, as shown in FIG. 2, the acquisition of the buried point record data of the target user terminal specifically includes step S1101 to step S1103.

Step S1101: Acquire initial burial point record data from the target user terminal, where the initial burial point record data includes respective initial statistical data of multiple burial point events.

The purpose of users using the Map APP is to obtain relevant geographic location information, along with the use of other auxiliary functions, such as driving route navigation, subway and bus route query, carpooling, traveling, etc. Different users also have deviations in the functional requirements of the map APP. For example, the frequency of using the driving route navigation function of car users is significantly higher than the frequency of using the subway bus route query function. According to the frequency of the operation behavior, the user's operation behavior can be analyzed to obtain the user's behavior operation habits and preferences.

In some embodiments, the initial statistical data of the buried event includes, for example, the number of times the function point is used, the page flow status (the number of pages jumped), the flow sequence of the process (normal or abnormal), the stay time, the function completion rate, etc.

Exemplarily, data such as the order in which the software interface jumps when the user operates the application, the frequency of use of the interface, and the order in which buttons on the software interface are clicked are obtained from the user's mobile terminal.

Step S1102: Perform numerical processing on the initial statistical data of each buried point event in the initial buried point record data to obtain the statistical data of each buried point event.

In some embodiments, the acquired initial burial point record data includes five burial point events, for example, burial point events A, B, C, D, and E, respectively. For burial point events A, B, C, D, The initial statistical data corresponding to E is processed numerically. Exemplarily, the number of occurrences of the buried point events A, B, C, D, and E in the initial buried point record data are summarized to obtain statistical data of each of the buried point events, as shown in Table 1.

Table 1 Statistics of buried point incidents

埋点记录数据Buried point record data	埋点事件ABuried point incident A	埋点事件BBuried point incident B	埋点事件CBuried point incident C	埋点事件DBuried point event D	埋点事件EBuried point event E
统计数据Statistical data	AsAs	BsBs	CsCs	DsDs	EsEs

Step S1103: Generate buried point record data according to the statistical data of each of the buried point events.

In some embodiments, it includes preprocessing the statistical data of each of the buried point events. For example, perform verification, denoise, check the completeness and consistency of data, eliminate illegal and invalid data, and add corresponding fields in custom events. According to the pre-processed statistical data of each of the buried point events, the buried point record data is generated. Exemplarily, the buried point data corresponding to the buried point event A is Q _A , the buried point data corresponding to the buried point event B is Q _B , and the buried point data corresponding to the buried point event C is Q _C.

S120. Based on the function completion rate model of each target event node, determine the function completion rate of each target event node according to the statistical data in the buried point record data, where the target event node is an event node in the decision tree model .

According to the event nodes corresponding to the statistical data in the buried point record data, they are respectively substituted into the pre-trained function completion rate model of each target event node to obtain the function completion rate of each target event node, wherein the target The event node is the event node in the pre-trained decision tree model.

In some embodiments, the training of the decision tree model includes the following steps:

Acquire a training sample set of the decision tree model, where the training sample set includes a variety of event processes and the function completion rate of each target event node in each of the event processes, and each event process includes at least one of the target event nodes The jump relationship between the target event node and the target event node; the decision tree model is determined according to the training sample set.

In some embodiments, as shown in FIG. 3, the function completion rate model based on each target event node, according to the statistical data in the buried point record data, to determine the function completion rate of the event node specifically includes the steps S1201 to step S1203.

S1201. Obtain a weight coefficient of an associated event node of the target event node based on the function completion rate model of the target event node, where the associated event node is an event node related to the target event node.

Specifically, the pre-trained function completion rate model of the target event node includes the weight coefficient of the event node related to the target event node.

Exemplarily, the function completion rate model of the target event node E is:

Q _E =λ _A Q _A +λ _B Q _B +λ _C Q _C

Among them, Q _A , Q _B , and Q _C represent event nodes A, B, and C related to the target event node E, that is, the buried point data corresponding to the associated event nodes A, B, and C of the target event node E, and the coefficient λ _A is The weight coefficient corresponding to the event node A, the coefficient λ _B is the weight coefficient corresponding to the event node B, and the coefficient λ _C is the weight coefficient corresponding to the event node C.

S1202. Obtain the buried point data of the associated event node from the buried point record data.

In some embodiments, a matching search is performed in the buried point record data according to the event node related to the target event node, and the buried point data corresponding to the event node in the buried point record data is obtained.

For example, as shown in Table 1, if the event nodes related to the target event node are A, B, and C, find the buried point data corresponding to the event nodes A, B, and C in the buried point record data, that is, buried point data Q _A , Q _B , Q _C.

S1203: Perform a weighted summation on the statistical data of the event nodes related to the target event node of the associated event node according to the weight coefficient to obtain the function completion rate of the target event node.

In some embodiments, the weight coefficient of the event node related to the target event node and the statistical data of the event node related to the target event node are substituted into the function completion rate model of the target event node, and a weighted sum is performed to obtain the target event node Function completion rate.

S130: Based on the decision tree model, determine a target event process according to the function completion rate of each target event node, where the target event process includes at least one target event node.

According to the current use situation of the user terminal, that is, the function completion rate of each target event node, a decision tree analysis is performed to obtain the main process node, and the optimal process plan corresponding to the current usage habit, that is, the target event process, is determined.

In some embodiments, the decision tree model is shown in FIG. 4 and includes 5 event nodes, namely S1, S2, S3, S4, and S5. Bring the function completion rate of each event node into the branch condition of each event node in the decision tree, and determine the event node after each event node in the target event process, that is, the leaf node.

Exemplarily, if the function completion rate of the event node S1 is greater than 0.5, the event node after the event node S1 is the event node S2; if the function completion rate of the event node S2 is greater than 0.3, the event node after the event node S2 is the event node S3. Thus, according to the optimal branch of the decision tree, the target event process can be determined, that is, the target event process is S1-S2-S3-S4.

Exemplarily, if the function completion rate of the event node S1 is less than 0.5, the event node after the event node S1 is the event node S4; if the function completion rate of the event node S4 is greater than 0.6, the event node after the event node S4 is the event node S2. Therefore, according to the optimal branch of the decision tree, the target event flow can be determined, that is, the target event flow is S1-S4-S2-S5.

S140: Determine configuration data according to the target event process, and send the configuration data to the target user terminal, so that the target user terminal updates the configuration according to the configuration data.

According to the optimal process plan, that is, the target event process, the configuration data is determined, and the configuration data is sent to the user terminal so that the user terminal can update the configuration. After the server generates a corresponding configuration instruction according to the configuration data, it sends the configuration instruction to the application in a push form. The configuration instruction includes a function change instruction, a process change instruction, and an interface element change instruction. According to the configuration instruction, a corresponding modification configuration is performed on the application to optimize the operation flow.

Exemplarily, the map APP optimizes the process according to the configuration instructions sent by the server, and adjusts the page layout according to the user's behavior habits, such as adjusting the position of the button that the user frequently clicks, through the position, size, color, etc. of the button The form distinguishes its importance; in the process change, the process plan that is optimized for the current user is realized. For example, after analysis, it is found that the function frequently used by the user is the bus and subway route query, and the target event process corresponding to the user is the address search and the bus and subway query, and then the configuration data is determined. The server generates a configuration instruction according to the configuration data and sends it to the application, and makes corresponding changes to the application according to the configuration instruction, so as to achieve the effect of immediately jumping to the bus and subway route display after the user enters the search address, and improves the application Ease of use.

Please refer to FIG. 5, which is a schematic flowchart of a training method for a function completion rate model provided by an embodiment of the present application. The training method is used to train to obtain the aforementioned function completion rate model.

As shown in Fig. 5, the training method includes step S210 to step S240.

S210. Acquire multiple burial point record data from at least one user terminal, where the burial point record data includes statistical data of multiple burial point events.

Specifically, it is possible to obtain the buried point record data of a user terminal in different time periods; or obtain the buried point record data of different user terminals in a certain period of time; or obtain the buried point record data of different user terminals in different time periods.

S220: Perform numerical processing on the statistical data of each buried point event in the buried point record data to obtain the statistical value of each buried point event.

In some embodiments, the initial burial point record data of the three user terminals A, B, and C are obtained from three user terminals such as A, B, and C, and each initial burial point record data includes the initial burial point event AE. Statistical data. After digitizing the initial statistical data, the statistical values of each buried point event are obtained, as shown in Table 2 below:

Table 2 Statistics of incidents of target user terminal buried points

埋点记录数据Buried point record data	甲First	乙Second	丙C
埋点事件ABuried point incident A	A1A1	A2A2	A3A3
埋点事件BBuried point incident B	B1B1	B2B2	B3B3
埋点事件CBuried point incident C	C1C1	C2C2	C3C3
埋点事件DBuried point event D	D1D1	D2D2	D3D3
埋点事件EBuried point event E	E1E1	E2E2	E3E3

S230: Perform correlation analysis on the multiple buried point events according to the respective statistical values of the multiple buried point events to obtain correlation coefficients between different buried point events.

In some embodiments, according to the statistical value of each buried point event, the correlation analysis of the multiple buried point events is performed by drawing a scatter diagram to obtain the correlation coefficient between different buried point events,

For example, taking the buried point event A as the independent variable and the buried point event E as the dependent variable, a scatter diagram is drawn based on the statistical values of the buried point events A and E in the multiple buried point record data. From the distribution of data points, we can find the trend of change between the independent variable and the dependent variable, and determine the correlation coefficient between buried point events A and E, such as Pearson product difference correlation, Spearman rank correlation or Kendall rank correlation coefficient.

The significance check of the buried events is performed according to the correlation coefficient. If the significance level between the two buried events is less than 0.05, it indicates that the two buried events are significantly correlated.

S240. Determine a function completion rate model of each target event node according to the correlation coefficient.

The event node related to the target event node is determined according to the correlation coefficient, and the weight coefficient of the event node related to the target event node is obtained to obtain a function completion rate model of the target event node.

In some embodiments, referring to FIG. 6, determining the function completion rate model of each target event node according to the correlation coefficient specifically includes step S2401 to step S2403.

S2401. If the correlation coefficient between an event node and the target event node is greater than a preset threshold, determine that the event node is an associated event node of the target event node.

Exemplarily, if the event nodes are A, B, C, D, and E, and the target event node is E, the correlation coefficient between the event nodes A, B, C, D and the target event node E is obtained. If the correlation coefficient between the event nodes A, B, C and the target event node E is greater than the preset threshold 0.4, and if the correlation coefficient between the event node D and the target event node E is less than the preset threshold 0.4, then the event nodes A, B , C is the event node E related to the target event node.

S2402: Determine the weight coefficient of the associated event node according to the correlation coefficient between the associated event node of the target event node and the target event node.

In some embodiments, for the target event node E, the event nodes related to the target event node are event nodes A, B, and C. Determine the weight coefficients of the event nodes related to the target event node according to the correlation coefficients between the event nodes A, B, C related to the target event node and the target event node E, namely λ _A , λ _B , λ _C . Among them, the weight coefficient λ _{A is} determined according to the correlation coefficient between buried point events A and E, the weight coefficient λ _{B is} determined according to the correlation coefficient between buried point events B and E, and the weight coefficient λ _{C is} determined according to the difference between buried point events C and E. Determination of the correlation coefficient between

Specifically, if the correlation coefficient between the buried events A and E is a, the correlation coefficient between the buried events B and E is b, and the correlation coefficient between the buried events C and E is c, then:

λ _A ＝a÷(a+b+c)λ _B ＝b÷(a+b+c)λ _C ＝c÷(a+b+c)

S2403: Determine a function completion rate model of the target event node according to the weight coefficient of the associated event node of the target event node.

Exemplarily, if the target event node is E, the associated event nodes related to the target event node E are A, B, and C, and the weight coefficients corresponding to the associated event nodes A, B, and C are respectively λ _A , λ _B , λ _C , and the buried point data corresponding to the associated event nodes A, B, and C are Q _A , Q _B , and Q _{C, respectively} . According to the weighting coefficients λ _A , λ _B , and λ _C , the function completion rate model of the target event node E is determined, and the function completion rate model is as follows:

Q _E =λ _A Q _A +λ _B Q _B +λ _C Q _C

This application uses a global interface design to access the functions that need to be monitored, the pages and elements involved in the process, and realize the modification and adjustment of functions, process configurations, and interface elements. The main design principles of the interface are as follows: Commanded information reception and processing are mainly divided into function change instructions, process change instructions, interface element change instructions, and program open and close instructions, and perform corresponding change operations according to corresponding instructions.

Changes in application functions and processes involve two aspects, one is the function and process changes within the page, and the other is the function and process changes between multiple pages. The function and process changes in the page are mainly through custom code or custom layout and controls to adjust the interface process; on this basis, multiple pages will be encapsulated by page jumps to modify the page flow. In addition, a switch configuration can be added to realize the dynamic configuration modification of the scheme.

The application discloses a configuration update method based on behavior analysis, which is used to reconstruct the flow of software on a user terminal according to user behavior analysis. Specifically, the function completion rate of each process node is calculated according to the user's current behavior habits and the correlation between the behaviors, and the process matching the user's current behavior habits is determined according to the decision tree model, that is, the target event process; then the target event process The corresponding related configuration is sent to the user terminal, so that the operation flow of the user terminal is dynamically configured according to the user's operation behavior or habit. In the mobile terminal software configuration application scenario, the correlation analysis technical means and target event process determination technical means in this case can effectively improve the accuracy of user behavior analysis, thereby improving the efficiency of mobile terminal software configuration.

Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of a configuration update device provided by an embodiment of the present application. The configuration update device can be configured in a server or a terminal to execute the aforementioned configuration update method based on behavior analysis.

Among them, the server can be an independent server or a server cluster. The terminal can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device.

As shown in FIG. 7, the configuration update apparatus 300 includes: a data acquisition module 301, a completion rate determination module 302, a process determination module 303, and a configuration update module 304.

The data acquisition module 301 is configured to acquire the burial point record data of the target user terminal, and the burial point record data includes respective statistical data of multiple burial point events.

In some embodiments, as shown in FIG. 8, the data acquisition module 301 in the configuration update apparatus 300 includes: a data acquisition sub-module 3011, a data processing sub-module 3012 and a record generation sub-module 3013.

The data acquisition sub-module 3011 is used to acquire initial burial point record data from the target user terminal, where the initial burial point record data includes respective initial statistical data of multiple burial point events.

The data processing sub-module 3012 is used to perform numerical processing on the initial statistical data of each buried point event in the initial buried point record data to obtain the statistical data of each buried point event.

The record generation sub-module 3013 is used to generate buried point record data according to the statistical data of each of the buried point events.

The completion rate determining module 302 is configured to determine the function completion rate of each target event node based on the function completion rate model of each target event node and the statistical data in the buried point record data, where the target event node is a decision Event node in the tree model.

In some embodiments, as shown in FIG. 8, the completion rate determination module 302 in the configuration update apparatus 300 includes: a weight acquisition sub-model 3021, a data matching sub-model 3022, and a weighted sum sub-model 3023.

The weight acquisition sub-model 3021 is used to acquire the weight coefficient of the event node related to the target event node based on the function completion rate model of the target event node. The associated event node is an event node related to the target event node.

The data matching sub-model 3022 is used to obtain statistical data of the event node related to the target event node from the buried point record data.

The weighted sum sub-model 3023 is used to perform weighted summation of the statistical data of the event node related to the target event node according to the weight coefficient to obtain the function completion rate of the target event node.

The process determining module 303 is configured to determine a target event process based on the decision tree model according to the function completion rate of each target event node, and the target event process includes at least one target event node.

Exemplarily, the process determination module 303 is specifically configured to determine that at least one target event node is based on the function completion rate of each target event node and the branch condition of each target event node in the decision tree model The target event node in the target event flow, and the jump relationship between the target event nodes in the target event flow is determined.

The configuration update module 304 is configured to determine configuration data according to the target event flow, and send the configuration data to the user terminal, so that the target user terminal updates the configuration according to the configuration data.

In some embodiments, the configuration update device 300 based on behavior analysis further includes a model training module, which is specifically used for:

Obtain a plurality of buried point record data from at least one user terminal, where the buried point record data includes statistical data of a plurality of buried point events; perform numerical processing on the statistical data of each buried point event in the buried point record data, Obtain the statistical value of each buried point event; perform correlation analysis on the multiple buried point events according to the respective statistical values of the multiple buried point events to obtain the correlation coefficient between different buried point events; The correlation coefficient determines the function completion rate model of each target event node.

In some embodiments, the configuration update device 300 based on behavior analysis further includes a decision tree training module, which is specifically used for:

It should be noted that those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described device and each module and unit can refer to the corresponding process in the foregoing method embodiment. Here, No longer.

The method and device of the present application can be used in many general or special computing system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, small computers, large computers, including the above Distributed computing environment of any system or device, etc.

Exemplarily, the above-mentioned method and apparatus may be implemented in the form of a computer program, and the computer program may run on the computer device as shown in FIG. 9.

Please refer to FIG. 9, which is a schematic structural diagram of a computer device provided by an embodiment of the present application. The computer equipment can be a server or a terminal. The computer device includes a memory and a processor, the memory can be used to store a computer program, and the processor can be used to execute the computer program and implement the above method when the computer program is executed. Optionally, the computer device includes a processor, a memory, and a network interface connected through a system bus, where the memory may include a non-volatile storage medium and an internal memory.

The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any configuration update method based on behavior analysis.

The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment. The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any configuration update method based on behavior analysis.

The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that the structure of the computer device is only a block diagram of a part of the structure related to the solution of the application, and does not constitute a limitation on the computer device to which the solution of the application is applied. Specifically, the computer device may include More or fewer components are shown in the figure, or some components are combined, or have different component arrangements.

It should be understood that the processor may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), and application specific integrated circuits (Application Specific Integrated Circuits). Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

Wherein, in an embodiment, the processor is used to run a computer program stored in a memory to implement the following steps:

After acquiring the buried point record data of the target user terminal, the buried point record data includes respective statistical data of multiple buried point events;

In some implementation manners, when the processor is configured to obtain the buried point record data of the target user terminal, it realizes:

Acquiring initial burial point record data from the target user terminal, where the initial burial point record data includes respective initial statistical data of multiple burial point events;

Performing numerical processing on the initial statistical data of each buried point event in the initial buried point record data to obtain the statistical data of each buried point event;

According to the statistical data of each buried point event, the buried point record data is generated.

In some embodiments, the processor is used to implement the function completion rate model based on each target event node, and when determining the function completion rate of each target event node according to the statistical data in the buried point record data, it realizes:

Obtaining the weight coefficient of the associated event node of the target event node based on the function completion rate model of the target event node, where the associated event node is an event node related to the target event node;

Acquiring statistical data of the associated event node from the buried point record data;

Perform a weighted summation on the statistical data of the associated event node according to the weight coefficient to obtain the function completion rate of the target event node.

In some embodiments, when the processor is used to implement the configuration update method based on behavior analysis, it implements:

Acquiring multiple burial point record data from at least one user terminal, where the burial point record data includes statistical data of multiple burial point events;

Performing numerical processing on the statistical data of each buried point event in the buried point record data to obtain the statistical value of each buried point event;

Perform correlation analysis on the multiple buried point events according to the respective statistical values of the multiple buried point events to obtain correlation coefficients between different buried point events;

According to the correlation coefficient, a function completion rate model of each target event node is determined.

In some implementation manners, when the server is configured to implement the function completion rate model of each target event node according to the correlation coefficient, the following is achieved:

If the correlation coefficient between an event node and the target event node is greater than a preset threshold, determine that the event node is an associated event node of the target event node;

Determining the weight coefficient of the associated event node according to the correlation coefficient between the associated event node of the target event node and the target event node;

The function completion rate model of the target event node is determined according to the weight coefficient of the associated event node of the target event node.

In some implementation manners, when the server is configured to determine the target event process based on the decision tree model and the function completion rate of each target event node, the following is achieved:

According to the function completion rate of each target event node and the branch condition of each target event node in the decision tree model, it is determined that at least one target event node is a target event node in a target event flow, and the The jump relationship between the target event nodes in the target event process.

Obtain a training sample set of the decision tree model, where the training sample set includes a variety of event processes and the function completion rate of each target event node in each of the event processes, and each event process includes at least one of the target event nodes The jump relationship with the target event node;

The decision tree model is determined according to the training sample set.

From the description of the foregoing implementation manners, it can be known that those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM/RAM, magnetic disk , CD-ROM, etc., including several instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the method described in each embodiment of this application or some parts of the embodiment, such as: a computer A readable storage medium, the computer readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement any of the behavior analysis-based behaviors provided in the embodiments of the present application Configure the update method.

The embodiments of the present application also provide a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, some or all of the steps of the method in the above-mentioned embodiment are implemented, or the computer program is When the processor is executed, the function of each module/unit of the apparatus in the above-mentioned embodiment is realized, which will not be repeated here.

Optionally, the storage medium involved in this application, such as a computer-readable storage medium, may be non-volatile or volatile.

The computer-readable storage medium may be the internal storage unit of the computer device described in the foregoing embodiment, for example, the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), or a secure digital (Secure Digital, SD) equipped on the computer device. ) Card, Flash Card, etc.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A configuration update method based on behavior analysis, including:

Acquiring burial point record data of the target user terminal, where the burial point record data includes respective statistical data of multiple burial point events;

Determine the function completion rate of each target event node based on the function completion rate model of each target event node according to the statistical data in the buried point record data, where the target event node is an event node in the decision tree model;

Based on the decision tree model, determining a target event process according to the function completion rate of each target event node, where the target event process includes at least one of the target event nodes;

The configuration data is determined according to the target event flow, and the configuration data is sent to the target user terminal, so that the target user terminal updates the configuration according to the configuration data.
The configuration update method based on behavior analysis according to claim 1, wherein said obtaining the buried point record data of the target user terminal comprises:

Acquiring initial burial point record data from the target user terminal, where the initial burial point record data includes respective initial statistical data of multiple burial point events;

Performing numerical processing on the initial statistical data of each buried point event in the initial buried point record data to obtain the statistical data of each buried point event;

According to the statistical data of each buried point event, the buried point record data is generated.
The configuration update method based on behavior analysis according to claim 1, wherein the function completion rate model based on each target event node determines the performance of each target event node according to statistical data in the buried point record data. Function completion rate, including:

Obtaining the weight coefficient of the associated event node of the target event node based on the function completion rate model of the target event node, where the associated event node is an event node related to the target event node;

Acquiring statistical data of the associated event node from the buried point record data;

Perform a weighted summation on the statistical data of the associated event node according to the weight coefficient to obtain the function completion rate of the target event node.
The configuration update method based on behavior analysis according to any one of claims 1 to 3, wherein the function completion rate model based on each target event node is determined according to the statistical data in the buried point record data Before the function completion rate of each target event node, it also includes:

Acquiring multiple burial point record data from at least one user terminal, where the burial point record data includes statistical data of multiple burial point events;

Performing numerical processing on the statistical data of each buried point event in the buried point record data to obtain the statistical value of each buried point event;

According to the respective statistical values of the multiple buried point events, perform a correlation analysis on the multiple buried point events to obtain correlation coefficients between different buried point events;

According to the correlation coefficient, a function completion rate model of each target event node is determined.
The configuration update method based on behavior analysis according to claim 4, wherein the determining the function completion rate model of each target event node according to the correlation coefficient comprises:

If the correlation coefficient between an event node and the target event node is greater than a preset threshold, determine that the event node is an associated event node of the target event node;

Determining the weight coefficient of the associated event node according to the correlation coefficient between the associated event node of the target event node and the target event node;

The function completion rate model of the target event node is determined according to the weight coefficient of the associated event node of the target event node.
The configuration update method based on behavior analysis according to any one of claims 1 to 3, wherein the determining a target event process based on the decision tree model according to the function completion rate of each target event node comprises:

According to the function completion rate of each target event node and the branch condition of each target event node in the decision tree model, it is determined that at least one target event node is a target event node in a target event flow, and the The jump relationship between the target event nodes in the target event process.
The configuration update method based on behavior analysis according to claim 6, wherein, before determining the target event process based on the decision tree model and according to the function completion rate of each target event node, the method further comprises:

Obtain a training sample set of the decision tree model, where the training sample set includes a variety of event processes and the function completion rate of each target event node in each of the event processes, and each event process includes at least one of the target event nodes The jump relationship with the target event node;

The decision tree model is determined according to the training sample set.
A configuration updating device, wherein the configuration updating device includes:

The data acquisition module is used to acquire the burial point record data of the target user terminal, the burial point record data including the respective statistical data of multiple burial point events;

The completion rate determination module is used to determine the function completion rate of each target event node based on the function completion rate model of each target event node and the statistical data in the buried point record data, where the target event node is a decision tree Event nodes in the model;

A process determining module, configured to determine a target event process according to the function completion rate of each target event node based on the decision tree model, the target event process including at least one of the target event nodes;

The configuration update module is configured to determine configuration data according to the target event flow, and send the configuration data to the user terminal, so that the target user terminal updates the configuration according to the configuration data.
A computer device, wherein the computer device includes a memory and a processor;

The memory is used to store a computer program;

The processor is configured to execute the computer program and implement the following method when the computer program is executed:

Acquiring burial point record data of the target user terminal, where the burial point record data includes respective statistical data of multiple burial point events;

Determine the function completion rate of each target event node based on the function completion rate model of each target event node according to the statistical data in the buried point record data, where the target event node is an event node in the decision tree model;

Based on the decision tree model, determining a target event process according to the function completion rate of each target event node, where the target event process includes at least one of the target event nodes;

The configuration data is determined according to the target event flow, and the configuration data is sent to the target user terminal, so that the target user terminal updates the configuration according to the configuration data.
8. The computer device according to claim 9, wherein when said acquiring the burial point record data of the target user terminal, the specific implementation is as follows:

Acquiring initial burial point record data from the target user terminal, where the initial burial point record data includes respective initial statistical data of multiple burial point events;

Performing numerical processing on the initial statistical data of each buried point event in the initial buried point record data to obtain the statistical data of each buried point event;

According to the statistical data of each buried point event, the buried point record data is generated.
The computer device according to claim 9, wherein when the function completion rate model of each target event node is based on statistical data in the buried point record data, when the function completion rate of each target event node is determined, Implementation:

Obtaining the weight coefficient of the associated event node of the target event node based on the function completion rate model of the target event node, where the associated event node is an event node related to the target event node;

Acquiring statistical data of the associated event node from the buried point record data;

Perform a weighted summation on the statistical data of the associated event node according to the weight coefficient to obtain the function completion rate of the target event node.
The computer device according to any one of claims 9 to 11, wherein, in the function completion rate model based on each target event node, each target event is determined according to statistical data in the buried point record data Before the function completion rate of the node, the processor is also used to execute the computer program to realize:

Acquiring multiple burial point record data from at least one user terminal, where the burial point record data includes statistical data of multiple burial point events;

Performing numerical processing on the statistical data of each buried point event in the buried point record data to obtain the statistical value of each buried point event;

According to the respective statistical values of the multiple buried point events, perform a correlation analysis on the multiple buried point events to obtain correlation coefficients between different buried point events;

According to the correlation coefficient, a function completion rate model of each target event node is determined.
The computer device according to any one of claims 9 to 11, wherein when the target event process is determined based on the decision tree model and the function completion rate of each target event node, the specific realization is achieved:

According to the function completion rate of each target event node and the branch condition of each target event node in the decision tree model, it is determined that at least one target event node is a target event node in a target event flow, and the The jump relationship between the target event nodes in the target event process.
The computer device according to claim 13, wherein, before determining the target event flow based on the decision tree model and according to the function completion rate of each target event node, the processor is further configured to execute the computer Program realization:

Obtain a training sample set of the decision tree model, where the training sample set includes a variety of event processes and the function completion rate of each target event node in each of the event processes, and each event process includes at least one of the target event nodes The jump relationship with the target event node;

The decision tree model is determined according to the training sample set.
A computer-readable storage medium storing a computer program, wherein: if the computer program is executed by a processor, the following method is implemented:

Acquiring burial point record data of the target user terminal, where the burial point record data includes respective statistical data of multiple burial point events;

Determine the function completion rate of each target event node based on the function completion rate model of each target event node according to the statistical data in the buried point record data, where the target event node is an event node in the decision tree model;

Based on the decision tree model, determining a target event process according to the function completion rate of each target event node, where the target event process includes at least one of the target event nodes;

The configuration data is determined according to the target event flow, and the configuration data is sent to the target user terminal, so that the target user terminal updates the configuration according to the configuration data.
15. The computer-readable storage medium according to claim 15, wherein when said acquiring the buried point record data of the target user terminal, the specific implementation is as follows:

Acquiring initial burial point record data from the target user terminal, where the initial burial point record data includes respective initial statistical data of multiple burial point events;

Performing numerical processing on the initial statistical data of each buried point event in the initial buried point record data to obtain the statistical data of each buried point event;

According to the statistical data of each buried point event, the buried point record data is generated.
The computer-readable storage medium of claim 15, wherein the function completion rate model of each target event node determines that the function completion of each target event node is based on statistical data in the buried point record data. When the rate, the specific realization:

Obtaining the weight coefficient of the associated event node of the target event node based on the function completion rate model of the target event node, where the associated event node is an event node related to the target event node;

Acquiring statistical data of the associated event node from the buried point record data;

Perform a weighted summation on the statistical data of the associated event node according to the weight coefficient to obtain the function completion rate of the target event node.
The computer-readable storage medium according to any one of claims 15 to 17, wherein in the function completion rate model based on each target event node, each location is determined according to statistical data in the buried point record data. Before the function completion rate of the target event node, the computer program is also used to realize when the computer program is executed by the processor:

Acquiring multiple burial point record data from at least one user terminal, where the burial point record data includes statistical data of multiple burial point events;

Performing numerical processing on the statistical data of each buried point event in the buried point record data to obtain the statistical value of each buried point event;

According to the respective statistical values of the multiple buried point events, perform a correlation analysis on the multiple buried point events to obtain correlation coefficients between different buried point events;

According to the correlation coefficient, a function completion rate model of each target event node is determined.
17. The computer-readable storage medium according to any one of claims 15 to 17, wherein when the target event process is determined based on the decision tree model and the function completion rate of each target event node, the specific realization is achieved:

According to the function completion rate of each target event node and the branch condition of each target event node in the decision tree model, it is determined that at least one target event node is a target event node in a target event flow, and the The jump relationship between the target event nodes in the target event process.
The computer-readable storage medium of claim 19, wherein the computer program is executed by a processor before the target event process is determined based on the decision tree model and the function completion rate of each target event node Time is also used to achieve:

Obtain a training sample set of the decision tree model, where the training sample set includes a variety of event processes and the function completion rate of each target event node in each of the event processes, and each event process includes at least one of the target event nodes The jump relationship with the target event node;

The decision tree model is determined according to the training sample set.