CN114492612A

CN114492612A - Big data-based user behavior analysis method and server

Info

Publication number: CN114492612A
Application number: CN202210062807.2A
Authority: CN
Inventors: 耿赛
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-03-23
Filing date: 2021-03-23
Publication date: 2022-05-13
Also published as: CN112949746B; CN114580495A; CN112949746A

Abstract

According to the big data-based user behavior analysis method and the server, the user behavior analysis result aiming at the guide type business service and the user behavior analysis result aiming at the interactive type business service can be integrated through the pre-trained analysis result processing model to obtain a global behavior analysis result; and mining the service of the big data service end according to the global behavior analysis result to obtain a corresponding service pre-push directory. Due to the design, the time consumption of the big data service end in service selection at the later stage can be reduced as much as possible, so that the pushing accuracy of the directional service is improved, the interaction efficiency of the service is improved, and unnecessary time consumption is reduced.

Description

Big data-based user behavior analysis method and server

The application is a divisional application with the application number of 202110310724.6, the application date of 2021, 03 and 23, and the application name of a big data processing method and an artificial intelligence server applied to user behavior analysis.

Technical Field

The application relates to the technical field of big data analysis, in particular to a user behavior analysis method and a server based on big data.

Background

With the progress of science and technology, business transaction in various industries gradually develops towards digital processing. Continuous optimization of big data (big data) technology provides a great deal of convenience for handling online business services, and overcomes the defects of traditional region limitation, time limitation and the like, so that handling and interaction of various business services are more intelligent and lower in cost.

At present, with the continuous improvement of the functions of various intelligent terminals, the related technologies already support the service interaction of the intelligent terminals at the cloud, however, on the premise that the scale of the cloud service interaction is continuously enlarged, some service interactions may have the problems of long consumed time, slow response and low equivalent rate. After the inventor researches and analyzes the phenomenon, one of the reasons causing the above problems is that no targeted service push exists between the intelligent terminals in the service interaction process, which results in that the intelligent terminals spend a lot of time to match the corresponding service. Therefore, in order to improve the above problems, a targeted service push for the intelligent terminal is required.

Based on the above, the related art performs service push in the service interaction process of the intelligent terminal, but the effect is not good. Further, after the inventor researches and analyzes the related technologies, the inventor finds that the reason why the pushing effect of the service is not good is that the user behavior of the intelligent terminal is not comprehensively and deeply analyzed. Therefore, how to comprehensively and deeply analyze the user behavior of the intelligent terminal is a technical problem which is continuously improved at present.

Disclosure of Invention

One of the embodiments of the present application provides an artificial intelligence server, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when executed by the processor, the computer program implements the following steps:

acquiring a first service feedback content record and a second service feedback content record, wherein the first service feedback content record is a service feedback content record aiming at a guide type service, and the second service feedback content record is a service feedback content record aiming at an interactive type service; the first service feedback content record and the second service feedback content record are generated by a big data service end and the artificial intelligence server in the service interaction process;

and performing correlation analysis on the first service feedback content record and the second service feedback content record to obtain a user behavior analysis result aiming at the guide type service and a user behavior analysis result aiming at the interactive type service.

Preferably, the obtaining a user behavior analysis result for a guidance-type service and a user behavior analysis result for an interactive-type service by performing correlation analysis on the first service feedback content record and the second service feedback content record includes:

performing service demand identification according to the first service feedback content record and the second service feedback content record to obtain a service demand identification result, performing explicit portrait mining processing on the first service feedback content record according to the service demand identification result to obtain a user behavior analysis result aiming at the guide type service, and performing explicit portrait mining processing on the second service feedback content record according to the service demand identification result to obtain a user behavior analysis result aiming at the interactive type service;

and performing user evaluation identification according to the first service feedback content record and the second service feedback content record to obtain a user evaluation identification result, performing potential portrait mining processing on the first service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result aiming at the guide type service, and performing potential portrait mining processing on the second service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result aiming at the interactive type service.

Preferably, the identifying the service demand according to the first service feedback content record and the second service feedback content record to obtain a service demand identification result includes:

generating first dynamic service feedback content according to the first service feedback content record and a first historical user behavior analysis result, determining a first explicit portrait mining strategy of each service feedback content item in the first service feedback content record according to the first dynamic service feedback content and a plurality of first feedback content updating data, wherein the first historical user behavior analysis result refers to a behavior analysis result obtained after big data analysis is carried out on any one group of service feedback content in the former i groups of service feedback content of the first service feedback content record, i is greater than or equal to 1, and the plurality of first feedback content updating data correspond to the plurality of service feedback content items in the first dynamic service feedback content one to one;

generating second dynamic service feedback content according to the second service feedback content record and a second historical user behavior analysis result, determining a second explicit portrait mining strategy of each service feedback content item in the second service feedback content record according to the second dynamic service feedback content and a plurality of second feedback content updating data, wherein the second historical user behavior analysis result refers to a behavior analysis result obtained after big data analysis is carried out on any one group of service feedback content in the former i groups of service feedback content of the second service feedback content record, and the plurality of second feedback content updating data correspond to the plurality of service feedback content items in the second dynamic service feedback content one to one;

integrating a first explicit portrait mining strategy and a second explicit portrait mining strategy of each service feedback content item to obtain an associated explicit portrait mining strategy of each service feedback content item;

or,

selecting one dominant portrait mining strategy from a first dominant portrait mining strategy and a second dominant portrait mining strategy of each service feedback content item as an associated dominant portrait mining strategy of the corresponding service feedback content item;

the service requirement identification result comprises a first explicit portrait mining strategy of each service feedback content item and/or an associated explicit portrait mining strategy of each service feedback content item.

Preferably, the performing explicit portrait mining on the first service feedback content record according to the service requirement identification result to obtain the user behavior analysis result for the guided service, and performing explicit portrait mining on the second service feedback content record according to the service requirement identification result to obtain the user behavior analysis result for the interactive service includes:

performing explicit portrait mining on the first service feedback content record according to a first explicit portrait mining strategy of each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and performing explicit portrait mining on the second service feedback content record according to the first explicit portrait mining strategy of each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service;

or performing explicit portrait mining on the first service feedback content record according to a first explicit portrait mining strategy of each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and performing explicit portrait mining on the second service feedback content record according to a related explicit portrait mining strategy of each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service;

or performing explicit portrait mining processing on the first service feedback content record according to the associated explicit portrait mining strategy of each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and performing explicit portrait mining processing on the second service feedback content record according to the associated explicit portrait mining strategy of each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service.

Preferably, the performing user evaluation identification according to the first service feedback content record and the second service feedback content record to obtain a user evaluation identification result includes:

determining a first potential portrait mining strategy of each service feedback content item in the first service feedback content record through a pre-trained content item identification model;

determining a second potential portrait mining strategy of each service feedback content item in the second service feedback content record through a pre-trained content item identification model;

extracting content associated identification information from the first service feedback content record through a pre-trained content item recognition model to obtain first content associated identification information, and extracting content associated identification information from the second service feedback content record to obtain second content associated identification information;

determining an associated potential portrait mining strategy corresponding to each service feedback content item according to the first potential portrait mining strategy, the second potential portrait mining strategy, the first content associated identification information and the second content associated identification information; wherein the user evaluation identification result comprises a first potential portrait mining strategy and/or an associated potential portrait mining strategy of each service feedback content item;

the potential portrait mining processing is performed on the first service feedback content record according to the user evaluation and identification result to obtain the user behavior analysis result for the guided service, and the potential portrait mining processing is performed on the second service feedback content record according to the user evaluation and identification result to obtain the user behavior analysis result for the interactive service, including:

performing potential portrait mining processing on the first service feedback content record according to a first potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and performing potential portrait mining processing on the second service feedback content record according to a first potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service;

or performing potential portrait mining processing on the first service feedback content record according to a first potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and performing potential portrait mining processing on the second service feedback content record according to an associated potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service;

or performing potential portrait mining processing on the first service feedback content record according to the associated potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and performing potential portrait mining processing on the second service feedback content record according to the associated potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service.

Preferably, the performing the correlation analysis on the first service feedback content record and the second service feedback content record to obtain a user behavior analysis result for a guided service and a user behavior analysis result for an interactive service includes:

performing service demand identification according to the first service feedback content record and the second service feedback content record to obtain a service demand identification result, performing explicit portrait mining on the first service feedback content record according to the service demand identification result to obtain a user behavior analysis result corresponding to a first explicit portrait, and performing explicit portrait mining on the second service feedback content record according to the service demand identification result to obtain a user behavior analysis result corresponding to a second explicit portrait;

performing user evaluation and identification according to a user behavior analysis result corresponding to the first dominant portrait and a user behavior analysis result corresponding to the second dominant portrait to obtain a user evaluation and identification result, performing potential portrait mining on the user behavior analysis result corresponding to the first dominant portrait according to the user evaluation and identification result to obtain a user behavior analysis result aiming at the guide type service, and performing potential portrait mining on the user behavior analysis result corresponding to the second dominant portrait according to the user evaluation and identification result to obtain a user behavior analysis result aiming at the interactive type service;

or,

performing user evaluation identification according to the first service feedback content record and the second service feedback content record to obtain a user evaluation identification result, performing potential portrait mining on the first service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result corresponding to a first potential portrait, and performing potential portrait mining on the second service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result corresponding to a second potential portrait;

and performing service demand identification according to the user behavior analysis result corresponding to the first potential portrait and the user behavior analysis result corresponding to the second potential portrait to obtain a service demand identification result, performing explicit portrait mining on the user behavior analysis result corresponding to the first potential portrait according to the service demand identification result to obtain the user behavior analysis result aiming at the guide type service, and performing explicit portrait mining on the user behavior analysis result corresponding to the second potential portrait according to the service demand identification result to obtain the user behavior analysis result aiming at the interactive type service.

Preferably, the computer program when executed by the processor further implements the steps of:

and integrating the user behavior analysis result aiming at the guide type business service and the user behavior analysis result aiming at the interactive type business service through a pre-trained analysis result processing model to obtain a global behavior analysis result.

and mining the service of the big data service end according to the global behavior analysis result to obtain a corresponding service pre-push directory.

Preferably, the mining the service for the big data service end according to the global behavior analysis result to obtain a corresponding service pre-push directory includes:

performing behavior intention information identification on a target service behavior event in the global behavior analysis result to obtain a behavior intention information set of the target service behavior event, wherein the behavior intention information set comprises a plurality of service behavior intention information;

acquiring target service reference data associated with the global behavior analysis result from a preset database, wherein the target service reference data comprises: local behavior analysis results and local interaction behavior service information of the local behavior analysis results;

determining behavior intention information fragments from the behavior intention information set according to the local interaction behavior service information, and determining intention tendency evaluation results of service behavior intention information in the behavior intention information fragments in the global behavior analysis results;

determining a business service mining strategy for the big data business end for the local behavior analysis result according to the intention tendency evaluation result of each piece of service behavior intention information in the global behavior analysis result, and fusing the local behavior analysis result in the global behavior analysis result according to the business service mining strategy for the big data business end to obtain a behavior analysis result to be processed;

adopting a preset big data mining algorithm to mine the business service of the analysis result of the behavior to be processed to obtain a business service mining result; and generating the business service pre-push directory according to the business service mining result.

One of the embodiments of the present application provides a big data-based user behavior analysis method, which is applied to an artificial intelligence server, and the method includes:

In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.

Drawings

The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and like reference numerals refer to like structures throughout these embodiments.

FIG. 1 is a schematic diagram of the hardware and software components of an artificial intelligence server according to some embodiments of the invention.

FIG. 2 is a flow diagram illustrating a big data based user behavior analysis method according to some embodiments of the invention.

FIG. 3 is another flow diagram illustrating a big data based user behavior analysis method according to some embodiments of the invention.

FIG. 4 is a block diagram of an exemplary big data based user behavior analysis apparatus, according to some embodiments of the invention;

FIG. 5 is a block diagram of an exemplary big data based user behavior analysis system, according to some embodiments of the invention.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" are intended to cover only the explicitly identified steps or elements as not constituting an exclusive list and that the method or apparatus may comprise further steps or elements.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

In order to improve the technical problems in the background art, the inventor purposefully provides a big data-based user behavior analysis method and a server.

Referring to fig. 1, a block diagram of an artificial intelligence server 100 is shown, the artificial intelligence server 100 may include a memory 110, a processor 120, and a computer program 130 stored on the memory 110 and operable on the processor 120, the computer program 130 implementing the big data based user behavior analysis method of the present application when executed by the processor 120.

The Memory 110 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 110 is configured to store a computer program 130, and the processor 120 executes the computer program 130 after receiving the execution instruction.

Processor 120 may process the relevant information and/or data to perform one or more of the functions described herein. For example, in some embodiments, processor 120 may include at least one processor (e.g., a single-core processor or a multi-core processor). Merely by way of example, the Processor 120 may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

It will be appreciated that the configuration shown in FIG. 1 is merely illustrative and that the artificial intelligence server 100 may include more or fewer components than shown in FIG. 1 or may have a different configuration than shown in FIG. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.

On the basis of fig. 1, please refer to fig. 2 in conjunction with fig. 1, which shows a flowchart of a big data-based user behavior analysis method implemented when the computer program 130 is executed by the processor 120, and the method may include the following steps S210 and S220.

S210: a first service feedback content record and a second service feedback content record are obtained.

In an embodiment of the present application, the first service feedback content record is a service feedback content record for a guided service, and the second service feedback content record is a service feedback content record for an interactive service. And the first service feedback content record and the second service feedback content record are generated by a big data service end and the artificial intelligence server in the service interaction process. In practical application, the big data service end may be an intelligent terminal, such as a mobile phone, a tablet computer, or a notebook computer. Further, the guided business service and the interactive business service are distinguished by the participants of the business service. For example, the participants of the guided business service may only include the artificial intelligence server and the big data business end, that is, the artificial intelligence server provides related guiding service items for the big data business end, such as some government and enterprise affairs. The interactive business service participants can comprise an artificial intelligence server, a big data business terminal and a big data interactive terminal. The big data interaction end can also be an intelligent terminal, such as a mobile phone, a tablet computer or a notebook computer, and in the interactive business service, the big data business end and the big data interaction end interact with each other through an artificial intelligence server. On the basis, different service feedback content records can be distinguished through different content tags, for example, the content tag of a first service feedback content record can be "1", and the content tag of a second service feedback content record can be "2", so that a large number of service feedback content records can be effectively distinguished. In addition, the service feedback content record may be text content or video image content, and is not limited herein.

In this embodiment, the manner of obtaining the first service feedback content record and the second service feedback content record may be that the artificial intelligence server obtains the first service feedback content record and the second service feedback content record in real time, for example, each time the big data service end generates one service feedback content record, the artificial intelligence server obtains one service feedback content record, and then step S220 is executed when the respective quantities of the first service feedback content record and the second service feedback content record obtained by the artificial intelligence server reach corresponding threshold values. Of course, the manner of obtaining the first service feedback content record and the second service feedback content record may be that the artificial intelligence server obtains the first service feedback content record and the second service feedback content record at a time interval, for example, the artificial intelligence server obtains the corresponding service feedback content record from the big data service end every set time interval, and then the step S220 is executed when the respective numbers of the first service feedback content record and the second service feedback content record obtained by the artificial intelligence server reach the corresponding threshold values. It can be understood that, regardless of the guided service or the interactive service, the big data service end needs to communicate with the artificial intelligence server, and therefore, the first service feedback content record and the second service feedback content record may be regarded as generated by the big data service end and the artificial intelligence server during service interaction.

S220: and performing correlation analysis on the first service feedback content record and the second service feedback content record to obtain a user behavior analysis result aiming at the guide type service and a user behavior analysis result aiming at the interactive type service.

In the embodiment of the present application, there may be a correlation between the first service feedback content record and the second service feedback content record, and therefore, in order to accurately determine a user behavior analysis result for a guided service and a user behavior analysis result for an interactive service, correlation analysis needs to be performed on the first service feedback content record and the second service feedback content record, so that correlation and influence between different service modes are taken into consideration, and thus different user behavior analysis results are determined differentially, so as to provide an accurate and reliable analysis basis for subsequent service mining.

In related embodiments, since the correlation analysis for different service feedback content records may involve intersection of different service interactions, in order to take various service correlation situations into account, the following several embodiments are provided in the embodiments of the present application to perform correlation analysis on the first service feedback content record and the second service feedback content record to obtain a user behavior analysis result for a guided service and a user behavior analysis result for an interactive service. Of course, the specific implementation process is not limited to the following embodiments.

In a first embodiment, the step "obtaining a user behavior analysis result for a guidance-type service and a user behavior analysis result for an interaction-type service by performing association analysis on the first service feedback content record and the second service feedback content record" may be implemented by the following steps S2211 and S2212.

S2211: and performing service demand identification according to the first service feedback content record and the second service feedback content record to obtain a service demand identification result, performing explicit portrait mining processing on the first service feedback content record according to the service demand identification result to obtain a user behavior analysis result aiming at the guide type service, and performing explicit portrait mining processing on the second service feedback content record according to the service demand identification result to obtain a user behavior analysis result aiming at the interactive type service.

In a related embodiment, the service requirement identification may be used for mining a user portrait, and the explicit portrait may be understood as a user portrait that can be directly determined through the first service feedback content record, and may be generally referred to as a surface portrait or a direct portrait. In S2211, the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service can be obtained by analyzing the service requirement level of the first service feedback content record and the second service feedback content record and combining explicit portrait mining, so that the service requirement information and the explicit portrait information of the big data service end can be ensured to be included in the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service, thereby increasing the content covered by the user behavior analysis result.

In a related embodiment, the step "performing service requirement identification according to the first service feedback content record and the second service feedback content record to obtain a service requirement identification result" may include the following steps S22111 to S22113.

S22111: and generating first dynamic service feedback content according to the first service feedback content record and a first historical user behavior analysis result, and determining a first dominant portrait mining strategy of each service feedback content item in the first service feedback content record according to the first dynamic service feedback content and a plurality of first feedback content updating data.

In a related embodiment, the first historical user behavior analysis result refers to a behavior analysis result obtained by performing big data analysis on any one group of service feedback contents in the previous i groups of service feedback contents recorded by the first service feedback content, i is greater than or equal to 1, and the plurality of first feedback content update data are in one-to-one correspondence with a plurality of service feedback content items in the first dynamic service feedback content.

In a related embodiment, the first historical user behavior analysis result may be a user behavior analysis result corresponding to a previous time node, for example, if the current time period is t4, the first historical user behavior analysis result may be a user behavior analysis result corresponding to time period t3, and accordingly, the dynamic service feedback content may be obtained according to a differentiated analysis of the first service feedback content record and the first historical user behavior analysis result, it may be understood that the user behavior analysis results in different time periods may be different, and the dynamic service feedback content may also represent different service feedback contents. Further, the feedback content update data may be used to indicate an update situation or a change situation of the feedback content. Since the plurality of first feedback content update data and the plurality of service feedback content items in the first dynamic service feedback content are in one-to-one correspondence, the degree of distinction between each first explicit portrait mining policy can be ensured. In the embodiment of the application, the first explicit portrait mining strategy is used for indicating guiding information for explicit portrait mining, such as path indication information for decision tree mining, and model parameter adjustment information based on neural network mining, for example.

S22112: and generating second dynamic service feedback content according to the second service feedback content record and a second historical user behavior analysis result, determining a second explicit portrait mining strategy of each service feedback content item in the second service feedback content record according to the second dynamic service feedback content and a plurality of second feedback content updating data, wherein the second historical user behavior analysis result refers to a behavior analysis result obtained by performing big data analysis on any one group of service feedback contents in the former i groups of service feedback contents of the second service feedback content record, and the plurality of second feedback content updating data correspond to the plurality of service feedback content items in the second dynamic service feedback content one to one.

In related embodiments, the description of S22112 can refer to the description of S22111, which is not repeated herein. It can be understood that, by using the above-mentioned S22111 and S22112, different explicit portrait mining strategies can be determined based on different business service types, and it can be understood that, when performing subsequent analysis, the pertinence of analysis processing for different service feedback content items can be improved.

S22113: integrating a first explicit portrait mining strategy and a second explicit portrait mining strategy of each service feedback content item to obtain an associated explicit portrait mining strategy of each service feedback content item; or selecting one explicit portrait mining strategy from a first explicit portrait mining strategy and a second explicit portrait mining strategy of each service feedback content item as an associated explicit portrait mining strategy of the corresponding service feedback content item; the service requirement identification result comprises a first explicit portrait mining strategy of each service feedback content item and/or an associated explicit portrait mining strategy of each service feedback content item.

In a related embodiment, the method for determining the associated explicit portrait mining strategy may include two methods, the first method is to integrate a first explicit portrait mining strategy and a second explicit portrait mining strategy for each service feedback content item to obtain the associated explicit portrait mining strategy for each service feedback content item, and the second method is to select one explicit portrait mining strategy from the first explicit portrait mining strategy and the second explicit portrait mining strategy for each service feedback content item as the associated explicit portrait mining strategy for the corresponding service feedback content item. By the design, the guide type business service mode can be considered emphatically, so that the pertinence of subsequent business service mining is improved. Accordingly, the business requirement identification result comprises the first explicit portrait mining strategy of each service feedback content item and/or the associated explicit portrait mining strategy of each service feedback content item, so that the accuracy and the reliability of explicit portrait mining can be ensured when explicit portrait mining processing is subsequently performed.

On the basis, the step "performing explicit portrait mining on the first service feedback content record according to the service requirement identification result to obtain the user behavior analysis result for the guided service, and performing explicit portrait mining on the second service feedback content record according to the service requirement identification result to obtain the user behavior analysis result for the interactive service" may be implemented by any one of the following implementation manners a, B, and C.

In embodiment a, explicit portrait mining is performed on the first service feedback content record according to the first explicit portrait mining policy for each service feedback content item to obtain the user behavior analysis result for the guided service, and explicit portrait mining is performed on the second service feedback content record according to the first explicit portrait mining policy for each service feedback content item to obtain the user behavior analysis result for the interactive service.

In embodiment a, the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service may be determined according to the first explicit portrait mining policy for each service feedback content item.

In embodiment B, explicit portrait mining is performed on the first service feedback content record according to a first explicit portrait mining policy for each service feedback content item to obtain the user behavior analysis result for the guided service, and explicit portrait mining is performed on the second service feedback content record according to an associated explicit portrait mining policy for each service feedback content item to obtain the user behavior analysis result for the interactive service.

In embodiment B, the determination of the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service may be obtained according to different explicit portrait mining strategies, for example, by performing explicit portrait mining on the first service feedback content record according to a first explicit portrait mining strategy for each service feedback content item to obtain the user behavior analysis result for the guided service, and performing explicit portrait mining on the second service feedback content record according to an associated explicit portrait mining strategy for each service feedback content item to obtain the user behavior analysis result for the interactive service, so that different service feedback content records are respectively subjected to explicit portrait mining by the first explicit portrait mining strategy and the associated explicit portrait mining strategy, the method can ensure that certain relevance can be ensured on the premise that different user behavior analysis results are different.

In embodiment C, explicit portrait mining is performed on the first service feedback content record according to the associated explicit portrait mining policy of each service feedback content item to obtain the user behavior analysis result for the guided service, and explicit portrait mining is performed on the second service feedback content record according to the associated explicit portrait mining policy of each service feedback content item to obtain the user behavior analysis result for the interactive service.

In embodiment C, the user behavior analysis result determined for the guided service and the user behavior analysis result determined for the interactive service may both be obtained according to an associated explicit portrait mining policy of each service feedback content item.

It is to be understood that the above embodiments a-C may be alternatively implemented in the implementation process, and are not limited herein.

S2212: and performing user evaluation identification according to the first service feedback content record and the second service feedback content record to obtain a user evaluation identification result, performing potential portrait mining processing on the first service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result aiming at the guide type service, and performing potential portrait mining processing on the second service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result aiming at the interactive type service.

In related embodiments, the determining of the user evaluation recognition result may be implemented according to a machine learning model trained in advance, for example, the step "performing user evaluation recognition according to the first service feedback content record and the second service feedback content record to obtain a user evaluation recognition result" may be implemented by the following contents described in steps S22121 to S22124.

S22121: determining a first potential portrait mining strategy for each service feedback content item in the first service feedback content record through a pre-trained content item recognition model.

S22122: determining a second potential portrait mining strategy for each service feedback content item in the second service feedback content record through a pre-trained content item recognition model.

In the above, the latent portrait mining strategy is used for mining latent portraits, which are opposite to explicit portraits, and in general, the latent portraits include the business requirement information of a big data business end in a later and deeper level, and are generally difficult to be directly obtained by identifying the business requirement. Therefore, in the embodiment, the content item recognition model may be trained in advance, and then the content item recognition model is used to determine the potential portrait mining strategy, so as to ensure the accuracy of the subsequent potential portrait mining.

S22123: and extracting content associated identification information from the first service feedback content record through a pre-trained content item recognition model to obtain first content associated identification information, and extracting content associated identification information from the second service feedback content record to obtain second content associated identification information.

In a related embodiment, the content association identification information may be used to characterize association between different contents in the service feedback content record, and the content association identification information may be expressed in the form of an array, for example, the content association identification information [ content1, x, content2] may represent association between the content1 and the content2 in the service feedback content record.

S22124: determining an associated potential portrait mining strategy corresponding to each service feedback content item according to the first potential portrait mining strategy, the second potential portrait mining strategy, the first content associated identification information and the second content associated identification information; wherein the user evaluation recognition result comprises a first potential portrait mining strategy and/or an associated potential portrait mining strategy of each service feedback content item.

In the related embodiment, when determining the associated potential portrait mining policy corresponding to each service feedback content item, different potential portrait mining policies and different content associated identification information can be comprehensively considered, so that the associated potential portrait mining policies can be ensured to fuse the different potential portrait mining policies and the different content associated identification information as much as possible. For example, the first potential portrait mining policy and the second potential portrait mining policy may be bound or reassembled according to the first content association identification information and the second content association identification information, so as to obtain an associated potential portrait mining policy corresponding to each service feedback content item. It will be appreciated that since the potential portrait mining policy is a mining policy that addresses the deep level of needs of business users, the first potential portrait mining policy and/or the associated potential portrait mining policy may also be included in the user evaluation identification.

In addition, the step of "performing the potential portrait mining process on the first service feedback content record according to the user evaluation and identification result to obtain the user behavior analysis result for the guidance-type service, and performing the potential portrait mining process on the second service feedback content record according to the user evaluation and identification result to obtain the user behavior analysis result for the interactive-type service" may be implemented by any one of the following embodiment D, embodiment E, and embodiment F, but is not limited to the following embodiment in specific implementation.

In embodiment D, the first service feedback content record is subjected to potential portrait mining according to a first potential portrait mining policy corresponding to each service feedback content item to obtain the user behavior analysis result for the guided service, and the second service feedback content record is subjected to potential portrait mining according to a first potential portrait mining policy corresponding to each service feedback content item to obtain the user behavior analysis result for the interactive service.

In embodiment D, the determination of the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service may be both obtained according to the first potential portrait mining policy of each service feedback content item.

In embodiment E, the first service feedback content record is subjected to potential portrait mining according to a first potential portrait mining policy corresponding to each service feedback content item to obtain the user behavior analysis result for the guided service, and the second service feedback content record is subjected to potential portrait mining according to an associated potential portrait mining policy corresponding to each service feedback content item to obtain the user behavior analysis result for the interactive service.

In embodiment E, determining the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service may be obtained according to different potential portrait mining policies, for example, performing potential portrait mining on the first service feedback content record according to the first potential portrait mining policy of each service feedback content item to obtain the user behavior analysis result for the guided service, and performing potential portrait mining on the second service feedback content record according to the associated potential portrait mining policy of each service feedback content item to obtain the user behavior analysis result for the interactive service, so that the potential portrait mining is performed on different service feedback content records respectively according to the first potential portrait mining policy and the associated potential portrait mining policy, the method can ensure that certain relevance can be ensured on the premise that different user behavior analysis results are different.

In embodiment F, the potential portrait mining process is performed on the first service feedback content record according to the associated potential portrait mining policy corresponding to each service feedback content item to obtain the user behavior analysis result for the guided service, and the potential portrait mining process is performed on the second service feedback content record according to the associated potential portrait mining policy corresponding to each service feedback content item to obtain the user behavior analysis result for the interactive service.

In embodiment F, the user behavior analysis result determined for the guided service and the user behavior analysis result determined for the interactive service may both be obtained according to the associated potential portrait mining policy of each service feedback content item.

In the practical implementation process, the user behavior analysis results of different business services are determined through the implementation mode in the alternative implementation modes A-C and the implementation mode in the alternative implementation modes D-F, so that the explicit portrait and the potential portrait can be simultaneously taken into consideration, and the association and the difference between different business services can be taken into consideration, so that different user behavior analysis results can be determined in a differentiated manner, and accurate and reliable analysis basis is provided for the subsequent business service mining.

In the second embodiment, the step "obtaining a user behavior analysis result for the guided service and a user behavior analysis result for the interactive service by performing association analysis on the first service feedback content record and the second service feedback content record" may also be implemented by: performing service demand identification according to the first service feedback content record and the second service feedback content record to obtain a service demand identification result, performing explicit portrait mining on the first service feedback content record according to the service demand identification result to obtain a user behavior analysis result corresponding to a first explicit portrait, and performing explicit portrait mining on the second service feedback content record according to the service demand identification result to obtain a user behavior analysis result corresponding to a second explicit portrait; and performing user evaluation and identification according to the user behavior analysis result corresponding to the first dominant portrait and the user behavior analysis result corresponding to the second dominant portrait to obtain a user evaluation and identification result, performing potential portrait mining on the user behavior analysis result corresponding to the first dominant portrait according to the user evaluation and identification result to obtain a user behavior analysis result aiming at the guide type business service, and performing potential portrait mining on the user behavior analysis result corresponding to the second dominant portrait according to the user evaluation and identification result to obtain a user behavior analysis result aiming at the interactive type business service.

In a third embodiment, the step "obtaining a user behavior analysis result for a guided service and a user behavior analysis result for an interactive service by performing association analysis on the first service feedback content record and the second service feedback content record" may also be implemented by the following steps: performing user evaluation identification according to the first service feedback content record and the second service feedback content record to obtain a user evaluation identification result, performing potential portrait mining on the first service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result corresponding to a first potential portrait, and performing potential portrait mining on the second service feedback content record according to the user evaluation identification result to obtain a user behavior analysis result corresponding to a second potential portrait; and performing service demand identification according to the user behavior analysis result corresponding to the first potential portrait and the user behavior analysis result corresponding to the second potential portrait to obtain a service demand identification result, performing explicit portrait mining on the user behavior analysis result corresponding to the first potential portrait according to the service demand identification result to obtain the user behavior analysis result aiming at the guide type service, and performing explicit portrait mining on the user behavior analysis result corresponding to the second potential portrait according to the service demand identification result to obtain the user behavior analysis result aiming at the interactive type service.

It is to be understood that the above further description of the second embodiment and the third embodiment may refer to the description of the first embodiment, and is not limited thereto.

On the basis of the above steps S210 and S220, the method may further include the following: and integrating the user behavior analysis result aiming at the guide type business service and the user behavior analysis result aiming at the interactive type business service through a pre-trained analysis result processing model to obtain a global behavior analysis result.

In the related embodiment, different user behavior analysis results are integrated, so that subsequent global business service mining can be facilitated. The analysis result processing model may be obtained based on machine learning model training, including but not limited to Convolutional Neural Networks (CNNs) or Back Propagation Neural Networks (BPNN). In the training process, corresponding model parameters can be adjusted through model indexes (such as loss functions) to realize model training, so that integration of different user behavior analysis results is realized. In the process of integrating different user behavior analysis results, consistency and correlation of the user behavior analysis results on business events and interaction periods can be considered, so that the global behavior analysis results can reflect business behavior interaction conditions of the big data business end from different business events and different interaction periods.

After determining the global behavior analysis result, the method may further include the following: and mining the service of the big data service end according to the global behavior analysis result to obtain a corresponding service pre-push directory. The business service pre-push directory includes different business service items, such as a business service item 1, a business service item 2, and a business service item 3. Further, the business service items in the business service pre-push directory may be arranged in a descending order of the intention tendency value of the user, taking the business service items 1-3 as an example, the intention tendency value of the business service item 1 is value1, the intention tendency value of the business service item 2 is value2, and the intention tendency value of the business service item 3 is value3, and if value2> value3> value1, the business service items in the business service pre-push directory may be arranged in the order of business service item 2, business service item 1, and business service item 3. Due to the design, the time consumption of the big data service end in service selection at the later stage can be reduced as much as possible, so that the pushing accuracy of the directional service is improved, the interaction efficiency of the service is improved, and unnecessary time consumption is reduced.

In some alternative schemes, please refer to fig. 3 in combination, which shows a step of a further implementation of the step "mining the business service for the big data business end according to the global behavior analysis result to obtain the corresponding business service pre-push directory", where the step may include S310 to S350.

S310, identifying behavior intention information of the target service behavior event in the global behavior analysis result to obtain a behavior intention information set of the target service behavior event, wherein the behavior intention information set comprises a plurality of service behavior intention information.

In related embodiments, the target service behavior event may be a behavior event in which the trigger frequency of the big data service end reaches the set frequency, that is, the trigger end of the target service behavior event is the big data service end. The behavior intention identification is used for analyzing a user intention level of the target service behavior event, and the service behavior intention information can be understood as intention information corresponding to a related event result which is expected to be obtained when the big data service end executes the related behavior event.

S320, obtaining target service reference data associated with the global behavior analysis result from a preset database, where the target service reference data includes: the local behavior analysis result and the local interaction behavior service information of the local behavior analysis result.

In a related embodiment, the default database may be a relational database such as mysql, hive, etc. The local behavior analysis result in the target service reference data is an analysis result of an individual behavior event corresponding to the global behavior analysis result in a service interaction time period, and the local interaction behavior service information records interaction information between the big data service end and the artificial intelligence server.

S330, determining behavior intention information segments from the behavior intention information set according to the local interaction behavior service information, and determining intention tendency evaluation results of service behavior intention information in the behavior intention information segments in the global behavior analysis results.

In a related embodiment, the behavior intention information segment may include a plurality of pieces of service behavior intention information having association, and the intention tendency evaluation result may be represented in a numerical form, for example, if the evaluation result corresponds to a numerical interval of 0 to 10, then the intention tendency evaluation result of different pieces of service behavior intention information in the global behavior analysis result may correspond to a numerical value between 0 and 10.

S340, determining a service mining strategy for the big data service end for the local behavior analysis result according to the intention tendency evaluation result of each service behavior intention information in the global behavior analysis result, and fusing the local behavior analysis result in the global behavior analysis result according to the service mining strategy for the big data service end to obtain a behavior analysis result to be processed.

In related embodiments, through the intention tendency evaluation result, the intention tendency condition of the big data service end relative to different behavior events, that is, which intention tendency exists in the big data service end, can be determined, so that the service mining strategy for the big data service end can be determined for the local behavior analysis result, and the local behavior analysis result is fused in the global behavior analysis result according to the service mining strategy for the big data service end to obtain the behavior analysis result to be processed, and the integrity of the behavior analysis result to be processed can be ensured as much as possible by fusing the local behavior analysis result in the global behavior analysis result. For example, the local behavior analysis result may be iteratively fused to the global behavior analysis result according to a set order according to an item mining priority in a business service mining policy.

S350, performing business service mining on the to-be-processed behavior analysis result by adopting a preset big data mining algorithm to obtain a business service mining result; and generating the business service pre-push directory according to the business service mining result.

In a related embodiment, the predetermined big data mining algorithm includes, but is not limited to, CART, KNN, Naive Bayes, SVM, EM, Apriori, FP-tree, K-Means, and the like. It can be understood that, in the actual implementation process, different big data mining algorithms can be selected according to actual business requirements to perform business service mining, and the mining algorithms are common knowledge in the art, and therefore are not described herein again. After the business service mining result is obtained, a corresponding business service pre-push catalog can be generated according to different business service items in the business service mining result and the intention tendency values of the business service items. The artificial intelligence server can selectively push related business service items to the big data business end according to the business service pre-push catalog, so that the business handling efficiency of the big data business end in subsequent business service interaction is improved.

In summary, according to the scheme provided in the embodiment of the present application, after the first service feedback content record and the second service feedback content record are obtained, a user behavior analysis result for the guidance-type service and a user behavior analysis result for the interactive-type service can be obtained by performing association analysis on the first service feedback content record and the second service feedback content record. Since the first service feedback content record is a service feedback content record for the guided service and the second service feedback content record is a service feedback content record for the interactive service, therefore, when the user behavior analysis is performed, association and influence among different service modes can be considered by performing association analysis on different service feedback content records, so that the determined user behavior analysis results have certain difference and certain association, and the first service feedback content record and the second service feedback content record are generated by the big data service end and the artificial intelligence server in the service interaction process, so that the user behavior analysis of the big data service end can be comprehensively and deeply realized.

Therefore, after user behavior analysis results aiming at different business service modes are obtained, more accurate business service pushing can be carried out based on the user behavior analysis results, so that the situation that a big data business end spends a large amount of time to match corresponding business services is avoided, and the business processing efficiency is improved.

In view of the foregoing method, an exemplary big data based user behavior analysis apparatus is further provided in the embodiments of the present invention, and as shown in fig. 4, the big data based user behavior analysis apparatus 400 may include the following functional modules.

A record obtaining module 410, configured to obtain a first service feedback content record and a second service feedback content record, where the first service feedback content record is a service feedback content record for a guided service, and the second service feedback content record is a service feedback content record for an interactive service; and the first service feedback content record and the second service feedback content record are generated by a big data service end and the artificial intelligence server in the service interaction process.

And the association analysis module 420 is configured to perform association analysis on the first service feedback content record and the second service feedback content record to obtain a user behavior analysis result for the guided service and a user behavior analysis result for the interactive service.

It is to be understood that for further description of the record obtaining module 410 and the association analysis module 420, reference may be made to the description of the method shown in fig. 2, which is not described herein again.

Based on the above method embodiment and apparatus embodiment, the embodiment of the present invention further provides a system embodiment, please refer to fig. 5, which shows a big data based user behavior analysis system 500, including an artificial intelligence server 100 and a big data service end 200 that communicate with each other, where the artificial intelligence server 100 is configured to obtain a first service feedback content record and a second service feedback content record, where the first service feedback content record is a service feedback content record for a guidance-type service, and the second service feedback content record is a service feedback content record for an interactive-type service; the first service feedback content record and the second service feedback content record are generated by a big data service end and the artificial intelligence server in the service interaction process; and performing correlation analysis on the first service feedback content record and the second service feedback content record to obtain a user behavior analysis result aiming at the guide type service and a user behavior analysis result aiming at the interactive type service. It is understood that for further description of the above system, reference may be made to the description of the method shown in fig. 2, which is not repeated herein.

It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. A big data-based user behavior analysis method is characterized by being applied to an artificial intelligence server and comprising the following steps:

integrating the user behavior analysis result aiming at the guide type business service and the user behavior analysis result aiming at the interactive type business service through a pre-trained analysis result processing model to obtain a global behavior analysis result;

according to the global behavior analysis result, business service mining aiming at the big data business end is carried out, and a corresponding business service pre-push directory is obtained; the business service pre-push directory comprises different business service items.

2. The method as claimed in claim 1, wherein performing business service mining on the big data business end according to the global behavior analysis result to obtain a corresponding business service pre-push directory comprises:

3. The method of claim 1, further comprising:

4. The method as claimed in claim 3, wherein the obtaining of the user behavior analysis result for the guided service and the user behavior analysis result for the interactive service by performing the correlation analysis on the first service feedback content record and the second service feedback content record comprises:

5. The method as claimed in claim 4, wherein said performing service requirement identification according to the first service feedback content record and the second service feedback content record to obtain a service requirement identification result comprises:

integrating a first explicit portrait mining strategy and a second explicit portrait mining strategy of each service feedback content item to obtain an associated explicit portrait mining strategy of each service feedback content item; or selecting one explicit portrait mining strategy from the first explicit portrait mining strategy and the second explicit portrait mining strategy of each service feedback content item as the associated explicit portrait mining strategy of the corresponding service feedback content item.

6. The method as claimed in claim 4, wherein the performing explicit portrait mining on the first service feedback content record according to the service requirement identification result to obtain the user behavior analysis result for the guided service, and performing explicit portrait mining on the second service feedback content record according to the service requirement identification result to obtain the user behavior analysis result for the interactive service comprises:

or performing explicit portrait mining on the first service feedback content record according to the associated explicit portrait mining strategy of each service feedback content item to obtain the user behavior analysis result aiming at the guide type service, and performing explicit portrait mining on the second service feedback content record according to the associated explicit portrait mining strategy of each service feedback content item to obtain the user behavior analysis result aiming at the interactive type service.

7. The method of claim 4, wherein the identifying the user rating according to the first service feedback content record and the second service feedback content record to obtain a user rating identification result comprises:

and determining an associated potential portrait mining strategy corresponding to each service feedback content item according to the first potential portrait mining strategy, the second potential portrait mining strategy, the first content associated identification information and the second content associated identification information.

8. The method as claimed in claim 7, wherein the performing potential portrait mining on the first service feedback content record according to the user evaluation recognition result to obtain the user behavior analysis result for the guided service, and performing potential portrait mining on the second service feedback content record according to the user evaluation recognition result to obtain the user behavior analysis result for the interactive service comprises:

potential portrait mining is carried out on the first service feedback content record according to a first potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the guide type service, and potential portrait mining is carried out on the second service feedback content record according to a first potential portrait mining strategy corresponding to each service feedback content item to obtain a user behavior analysis result aiming at the interactive type service;

or performing potential portrait mining processing on the first service feedback content record according to the associated potential portrait mining strategy corresponding to each service feedback content item to obtain the user behavior analysis result aiming at the guide type service, and performing potential portrait mining processing on the second service feedback content record according to the associated potential portrait mining strategy corresponding to each service feedback content item to obtain the user behavior analysis result aiming at the interactive type service.

9. An artificial intelligence server, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the method of any one of claims 1 to 8.