CN111400568B

CN111400568B - Behavior intention analysis method and device, electronic equipment and storage medium

Info

Publication number: CN111400568B
Application number: CN202010174696.5A
Authority: CN
Inventors: 冯志祥
Original assignee: Shenzhen Tencent Computer Systems Co Ltd
Current assignee: Shenzhen Tencent Computer Systems Co Ltd
Priority date: 2020-03-13
Filing date: 2020-03-13
Publication date: 2021-06-08
Anticipated expiration: 2040-03-13
Also published as: CN111400568A

Abstract

The present disclosure provides a behavior intention analysis method, apparatus, electronic device, and storage medium, the method comprising: acquiring active behavior data of a user; performing first classification on the active behavior data in a time dimension based on time attribute information corresponding to the active behavior data; performing second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data; and aggregating the active behavior data based on the first classification and the second classification, and analyzing the behavior intention of the user based on an aggregation result. The method and the device can improve the accuracy of behavior intention analysis.

Description

Behavior intention analysis method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of data analysis, and in particular, to a behavior intention analysis method and apparatus, an electronic device, and a storage medium.

Background

With the rapid development of information technology, various daily activities of a large number of users can generate corresponding behavior data. For each industry, it is significant to analyze the behavior intention of the user more accurately, and further provide more personalized or more targeted services for the user. In order to realize more accurate behavior intention analysis, it is undoubtedly important how to dig more information from the collected behavior data as the basis of the behavior intention analysis. In the prior art, collected behavior data are processed too sidedly, so that the accuracy of behavior intention analysis is low.

Disclosure of Invention

An object of the present disclosure is to provide a behavior intention analysis method, apparatus, electronic device, and storage medium, which can improve the accuracy of behavior intention analysis.

According to an aspect of an embodiment of the present disclosure, a behavior intent analysis method is disclosed, the method including:

acquiring active behavior data of a user;

performing first classification on the active behavior data in a time dimension based on time attribute information corresponding to the active behavior data;

performing second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data;

and aggregating the active behavior data based on the first classification and the second classification, and analyzing the behavior intention of the user based on an aggregation result.

In an exemplary embodiment of the present disclosure, acquiring active behavior data of a user includes: and acquiring active behavior data of the user within a preset time period by the current time point every preset time period.

In an exemplary embodiment of the present disclosure, each time zone for the first classification is previously divided, and each object class describing a class to which a behavior object belongs is previously divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

acquiring time attribute information of the active behavior data, and determining a time region to which the time attribute information belongs;

determining various similar behavior objects which are the same as the category to which the behavior object belongs based on the object category corresponding to the behavior object;

and determining the data which is in the time region to which the behavior object belongs and is exposed to the user by the same type behavior object as the passive behavior data.

In an exemplary embodiment of the present disclosure, the spatial regions for the second classification are previously divided, and the object classes describing the classes to which the behavior objects belong are previously divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

acquiring spatial attribute information of the active behavior data, and determining a spatial region to which the spatial attribute information belongs;

and determining data related to the behavior objects and the same type behavior objects exposed to the user in the space region to which the behavior objects belong as the passive behavior data.

In an exemplary embodiment of the present disclosure, each time region for the first classification and each space region for the second classification are previously divided, and each object class describing a class to which a behavior object belongs is previously divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

and determining data related to the behavior objects and the same type behavior objects exposed to the user in the belonged time region and the belonged space region as the passive behavior data.

According to an aspect of an embodiment of the present disclosure, there is disclosed a behavior intention analysis apparatus, the apparatus including:

the acquisition module is configured to acquire active behavior data of a user;

the first classification module is configured to perform first classification on the active behavior data in a time dimension based on time attribute information corresponding to the active behavior data;

the second classification module is configured to perform second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data;

and the aggregation analysis module is configured to aggregate the active behavior data based on the first classification and the second classification, and analyze the behavior intention of the user based on an aggregation result.

In an exemplary embodiment of the disclosure, the obtaining module is configured to obtain active behavior data of the user within a preset time period by a current time point every preset time period.

In an exemplary embodiment of the present disclosure, each time region for the first classification and each space region for the second classification are divided in advance. The first classification module is configured to: determining a time region to which the time attribute information belongs as a first category of the active behavior data in a time dimension; the second classification module is configured to: determining a space region to which the space attribute information belongs as a second category of the active behavior data in a space dimension; the aggregation analysis module is configured to: aggregating the proactive behavior data based on the first category and the second category.

In an exemplary embodiment of the disclosure, the aggregation analysis module is configured to:

aggregating the active behavior data of the same first category;

and aggregating the active behavior data with the same second category.

In an exemplary embodiment of the disclosure, the aggregation analysis module is configured to: aggregating the active behavior data of the same first category and the same second category.

In an exemplary embodiment of the disclosure, the apparatus is configured to:

performing third classification on the active behavior data in service dimension based on the service attribute information corresponding to the active behavior data;

aggregating the active behavior data based on the first classification, the second classification, and the third classification.

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining passive behavior data corresponding to the active behavior data;

determining an aggregation weight for the active behavior data based on the first number of passive behavior data;

aggregating the proactive behavior data based on the first classification, the second classification, and the aggregation weight.

In an exemplary embodiment of the present disclosure, each time zone for the first classification is divided in advance. The apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

acquiring time attribute information of the active behavior data, and determining a time region to which the active behavior data belongs based on the time attribute information;

and determining data related to the behavior object exposed to the user in the belonged time zone as the passive behavior data.

In an exemplary embodiment of the present disclosure, each time zone for the first classification is previously divided, and each object class describing a class to which a behavior object belongs is previously divided. The apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining a second number of the active behavior data within the belonging time zone;

acquiring a preset function for determining the aggregation weight in the scene based on the scene of behavior intention analysis;

the first number and the second number are used as inputs of the function, and an output of the function is determined as the aggregation weight.

In an exemplary embodiment of the present disclosure, each spatial region for the second classification is divided in advance. The apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

acquiring spatial attribute information of the active behavior data, and determining a spatial region to which the active behavior data belongs based on the spatial attribute information;

and determining data related to the behavior object exposed to the user in the space region as the passive behavior data.

In an exemplary embodiment of the present disclosure, the spatial regions for the second classification are previously divided, and the object classes describing the classes to which the behavior objects belong are previously divided. The apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining a second number of the active behavior data within the spatial region to which it belongs;

In an exemplary embodiment of the present disclosure, each time region for the first classification and each space region for the second classification are divided in advance. The apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

and determining data related to the behavior object exposed to the user in the belonged time region and the belonged space region as the passive behavior data.

In an exemplary embodiment of the present disclosure, each time region for the first classification and each space region for the second classification are previously divided, and each object class describing a class to which a behavior object belongs is previously divided. The apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining a second number of the proactive behavior data within the belonging temporal region and within the belonging spatial region;

According to an aspect of an embodiment of the present disclosure, an electronic device for behavioral intent analysis is disclosed, including: a memory storing computer readable instructions; a processor reading computer readable instructions stored by the memory to perform the method of any of the preceding claims.

According to an aspect of an embodiment of the present disclosure, a computer program medium is disclosed, having computer readable instructions stored thereon, which, when executed by a processor of a computer, cause the computer to perform the method of any of the preceding claims.

In the embodiment of the disclosure, the active behavior data of the user is subjected to first classification in a time dimension and second classification in a space dimension, and then the active behavior data is aggregated, so that the behavior intention of the user is analyzed based on the aggregation result. According to the method, the first classification in the time dimension and the second classification in the space dimension are introduced, so that the data aggregation process in behavior intention analysis can embody the data characteristics in the space-time dimension, the information content of aggregated data is improved, and the accuracy of behavior intention analysis is improved.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

FIG. 1 illustrates an application scenario of behavioral intent analysis according to one embodiment of the present disclosure.

FIG. 2 illustrates an application scenario of behavioral intent analysis according to one embodiment of the present disclosure.

FIG. 3 shows a flow diagram of a behavioral intent analysis method according to one embodiment of the present disclosure.

Fig. 4 shows a block diagram of a behavioral intent analysis apparatus according to one embodiment of the present disclosure.

FIG. 5 illustrates a hardware diagram of a behavioral intent analysis electronic device, according to one embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments. In the following description, numerous specific details are provided to give a thorough understanding of example embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, steps, and so forth. In other instances, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.

Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

First, a part of the concept involved in the embodiments of the present disclosure will be briefly explained below.

The behavior intention analysis refers to a process of analyzing behavior habits and behavior tendencies of the user. For example: the process of analyzing the shopping tendency of the user according to the shopping history data of the user on the shopping website since one year.

Active behavior data refers to data that describes a behavior about a user actively responding, or actively making a response. For example: data is described about the type of activity that a user actively clicks on an advertisement; data is described about the type of activity in which a user actively collects articles on the public. And the behavior object corresponding to the active behavior data refers to an action receiver of the active behavior. For example: an advertisement clicked on by a user.

Passive behavior data refers to data that describes a behavior about a user responding passively, or passively. For example: data is described about the act of exposing an advertisement to a user, i.e. the user passively sees the advertisement; data is described about the act of pushing public articles to a user, i.e., the user passively receiving the public articles.

Aggregation refers to a process of determining a category distribution of data according to the divided categories of data. For example: the predetermined shopping data can be classified into three categories of "diet", "entertainment", and "clothes". The shopping history data of the user on the shopping website is collected since one year, and after the shopping history data is classified, the process of determining how many times of shopping in the shopping history data is related to diet, how many times of shopping is related to entertainment, and how many times of shopping is related to clothes is determined, which is an example of aggregation.

It should be noted that the user in the embodiment of the present disclosure may be a set of a plurality of specific users, or may be a single specific user.

For example: in one embodiment, the user refers to a user set consisting of Xiaoming, Xiaohong and Xiao just. In this embodiment, active behavior data of the user set, that is, mingmy active behavior data, reddish active behavior data, and young active behavior data, is obtained; performing a first classification on a time dimension and a second classification on a space dimension on the active behavior data of the user set; and aggregating on the basis, and analyzing the behavior intention of the user set.

In another embodiment, the user refers to twilight. In this embodiment, small and clear active behavior data is acquired; performing first classification on time dimension and second classification on space dimension on the small and clear active behavior data; on the basis, aggregation is carried out, and the obvious behavior intention is analyzed.

Fig. 1 illustrates an application scenario of behavioral intent analysis of an embodiment of the present disclosure.

In this embodiment, the advertisement server 10 is used as an execution subject of the behavior intention analysis method, and is mainly used for analyzing the behavior intention of the users in the friend group clicking the advertisement. Specifically, the circle of friends user can be connected to the circle of friends server 20 through the corresponding user terminal 30, and receive the circle of friends service provided by the circle of friends server 20. Meanwhile, the advertisement server 10 may place advertisements to each user terminal 30 through the circle of friends server 20. If a friend circle user clicks on an advertisement on his/her user terminal 30, advertisement click behavior data corresponding to the advertisement click is obtained by the advertisement server 10 via the friend circle server 20. Further, the advertisement server 10 may perform a first classification in a time dimension and a second classification in a space dimension according to the acquired advertisement click behavior data, thereby aggregating the acquired advertisement click behavior data, and analyzing a behavior intention of the user for clicking the advertisement based on the aggregated result.

It should be noted that the embodiment is only an exemplary illustration, and should not limit the function and the scope of the disclosure. It will be appreciated that at the physical level, the advertisement server 10 and the friend circle server 20 may be located in the same physical machine. The architecture of the service level is shown in this embodiment.

Fig. 2 illustrates an application scenario of behavioral intent analysis of an embodiment of the present disclosure.

In this embodiment, the shopping platform server 10 is used as an execution subject of the behavior intention analysis method, and is mainly used for analyzing the behavior intention of the platform user for shopping. Specifically, the platform user may be connected to the shopping platform server 10 through the corresponding user terminal 30 to receive the shopping service provided by the shopping platform server 10. If a platform user purchases a commodity through the user terminal 30, the shopping behavior data corresponding to the shopping behavior is obtained by the shopping platform server 10. Further, the shopping platform server 10 can perform a first classification in a time dimension and a second classification in a space dimension according to the acquired shopping behavior data, thereby aggregating the acquired shopping behavior data, and analyzing the behavior intention of the user for shopping based on the aggregated result.

It should be noted that the embodiment is only an exemplary illustration, and should not limit the function and the scope of the disclosure. It will be appreciated that the shopping platform server 10 may cooperate with other terminals in performing the above-described functions, and does not represent that the shopping platform server 10 and the user terminal 30 are only connected according to the architecture shown in FIG. 2.

Specific implementations of embodiments of the present disclosure are described in detail below.

As shown in fig. 3, a behavior intention analysis method includes:

step S410, acquiring active behavior data of a user;

step S420, performing first classification on the active behavior data in a time dimension based on the time attribute information corresponding to the active behavior data;

step S430, performing second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data;

step S440, aggregating the active behavior data based on the first classification and the second classification, and analyzing the behavior intention of the user based on an aggregation result.

In step S410, active behavior data of the user is acquired.

In the embodiment of the disclosure, the analysis terminal mainly analyzes the behavior intention of the user based on the aggregation of the active behavior data of the user. Specifically, the analysis terminal can monitor the active behavior of each user in real time, and store the generated active behavior data record in the database of the analysis terminal; when the behavioral intention needs to be analyzed, corresponding active behavior data is obtained from a database of the analysis terminal according to the composition of the user (for example, if the user is a single specific user, the active behavior data of the specific user is obtained from the database, and if the user is a user set composed of a plurality of specific users, the active behavior data of the specific users are respectively obtained from the database). The other terminals except the analysis terminal can monitor the active behavior of each user in real time, and the generated active behavior data record is stored in the database of the other terminals; and when the behavior intention needs to be analyzed, making a request to the other terminal, and acquiring corresponding active behavior data from the database of the other terminal according to the composition of the user.

In one embodiment, acquiring active behavior data of a user includes: and acquiring active behavior data of the user within a preset time period by the current time point every preset time period.

In this embodiment, the analysis terminal periodically acquires active behavior data of the user within a certain period of time, and further periodically analyzes the behavior intention of the user. Specifically, the analysis terminal presets a time period for triggering acquisition of the action and a time period for identifying a time range of the active behavior data. For example: the preset time period of the analysis terminal is 1 week, and the preset time period is 1 year. And every 1 week, the analysis terminal acquires active behavior data of the user within 1 year before the current time point, and on the basis, analyzes the behavior intention of the user within 1 year.

The embodiment has the advantages that the dynamic analysis of the behavioral intention is realized by periodically analyzing the behavioral intention of the user, and the timeliness of the analyzed behavioral intention is ensured.

It should be noted that the embodiment is only an exemplary illustration, and should not limit the function and the scope of the disclosure.

In step S420, a first classification is performed on the active behavior data in a time dimension based on the time attribute information corresponding to the active behavior data.

In step S430, a second classification is performed on the active behavior data in the spatial dimension based on the spatial attribute information corresponding to the active behavior data.

In step S440, the active behavior data is aggregated based on the first classification and the second classification, and the behavior intention of the user is analyzed based on the aggregation result.

In the embodiment of the disclosure, after active behavior data of a user is acquired, at least a first classification in a time dimension and a second classification in a space dimension are performed on the active behavior data, so that spatiotemporal information is introduced into aggregation performed on the active behavior data, and thus the accuracy of analysis of behavior intention performed on an aggregation result is improved.

In one embodiment, the temporal regions for the first classification and the spatial regions for the second classification are pre-partitioned.

In this embodiment, in order to perform the first classification in the time dimension, the analysis terminal previously divides each time zone in the time dimension. For example: according to the division standard of working days, 7 time regions, namely Monday, Tuesday, Wednesday, Thursday, Friday, Saturday and Sunday are divided. Alternatively, 1 natural balance is divided into 4 time zones — "00: 00-06: 00 "," 06: 00-12:00 "," 12: 00-18:00 "and" 18:00-24: 00". It can be understood that the time domain division standard can be adjusted according to specific analysis requirements, so as to obtain the corresponding time domain division result.

In this embodiment, in order to perform the second classification in the spatial dimension, the analysis terminal previously divides each spatial region in the spatial dimension. For example: and dividing each provincial level administrative region into a space region according to the division standard of the provincial level administrative regions. Or, according to the classification standard of the city-level administrative areas, each city-level administrative area is divided into a space area.

It is understood that the division of the spatial region may also be performed by combining the existing administrative region with the actual activity range of the user. For example: when the behavioral intention is analyzed for the user set of nationwide users, the actual activity range of the nationwide users extends over each provincial administrative region, and each provincial administrative region can be divided into a spatial region; when analyzing the behavioral intention of a specific user, namely xiao ming, if the actual activity range of xiao ming is only in "guangdong province" and "jiangxi province", the "guangdong province" and the "jiangxi province" can be divided into a space region respectively, and the analysis is not considered except for the "guangdong province" and the "jiangxi province".

In this embodiment, performing a first classification on the active behavior data in a time dimension based on the time attribute information corresponding to the active behavior data includes: and determining the time region to which the time attribute information belongs as a first category of the active behavior data in the time dimension.

In this embodiment, the active behavior data acquired by the analysis terminal includes corresponding time attribute information. Specifically, when the collecting terminal (which may be an analysis terminal or another terminal other than the analysis terminal) collects the active behavior data of the user, the time when the corresponding active behavior occurs is determined, and then the time attribute information describing the time when the active behavior occurs is stored together with the active behavior data. Therefore, after the analysis terminal acquires the active behavior data, corresponding time attribute information can be extracted from the active behavior data, the time of the corresponding active behavior is determined, and the time region to which the active behavior data belongs, namely the first category of the active behavior data in the time dimension, is further determined.

For example: the analysis terminal and the acquisition terminal are shopping platform servers. The user purchases a commodity on the shopping platform at 14 o 'clock 20 o' clock 11/19/2019. The shopping platform server stores the initiative data describing the purchase, and also stores the time attribute information "2019/11/19-14: 20 "are stored with the active behavior data. If the pre-divided time zone is- "00: 00-06: 00 "," 06: 00-12:00 "," 12: 00-18:00 "and" 18:00-24: 00', in the process of analyzing the behavior intention by the shopping platform server, after the active behavior data is acquired, it can be determined that the first category of the active behavior data in the time dimension is — "12: 00-18: 00".

In this embodiment, performing a second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data includes: and determining the space region to which the space attribute information belongs as a second category of the active behavior data in the space dimension.

In this embodiment, the active behavior data acquired by the analysis terminal includes corresponding spatial attribute information. Specifically, when the collection terminal collects the active behavior data of the user, the place where the corresponding active behavior occurs is determined, and then the spatial attribute information describing the place where the active behavior occurs is stored together with the active behavior data. Therefore, after the analysis terminal acquires the active behavior data, the analysis terminal can extract corresponding spatial attribute information from the active behavior data, determine the place where the corresponding active behavior occurs, and further determine the affiliated spatial region, namely, the second category of the active behavior data in the spatial dimension.

For example: the analysis terminal is an advertisement server, and the acquisition terminal is a friend circle server. When a user travels in the Guangdong, the user clicks an advertisement in the friend circle on the mobile phone. When the circle of friends server stores the active behavior data describing the click behavior, the circle of friends server also stores the spatial attribute information "Guangdong" describing the place where the click behavior occurs together with the active behavior data through Location Based Services (LBS) information of the mobile phone. If the pre-divided spatial regions are- "guangdong province" and "jiangxi province", the second category of the active behavior data in the spatial dimension can be determined to be- "guangdong province" after the active behavior data is acquired from the friend circle server in the process of intent analysis by the advertisement server.

In this embodiment, aggregating the proactive behavior data based on the first classification and the second classification includes: aggregating the active behavior data based on the first category and the second category.

In this embodiment, after the first category is obtained based on the pre-divided time region and the second category is obtained based on the pre-divided space region, the active behavior data may be aggregated according to the obtained first category and the obtained second category, and further, the behavior intention of the user may be analyzed based on the aggregation result.

It should be noted that the embodiment is only an exemplary illustration, and should not limit the function and the scope of the disclosure. It is to be understood that, when performing the first classification and the second classification, the time region for the first classification and the space region for the second classification are pre-divided, which is only an optional implementation manner in the embodiment of the present disclosure. Specifically, the time region for the first classification and the space region for the second classification may be divided in advance, and after the active behavior data is acquired, the time range of the acquired active behavior data is determined according to the time attribute information, so that the time region is divided within the time range; and determining the space range of the acquired active behavior data according to the space attribute information, and further dividing the space region within the space range.

In one embodiment, aggregating the active behavior data based on the first category and the second category includes:

aggregating the active behavior data of the same first category;

and aggregating the active behavior data of the second category.

In this embodiment, the analysis terminal aggregates the active behavior data in a manner that the time dimension and the space dimension are independent from each other, so that the data features of the time dimension and the data features of the space dimension are independently introduced into the behavior intention analysis process. Specifically, the analysis terminal independently introduces data characteristics of time dimension by aggregating the same active behavior data of the first class; and aggregating the active behavior data of the second category, so as to independently introduce the data characteristics of the spatial dimension.

The embodiment has the advantage that by the method, the data characteristics of the time dimension and the data characteristics of the space dimension can be clearly and independently embodied by the aggregation result.

In one embodiment, aggregating the active behavior data based on the first category and the second category includes: and aggregating the active behavior data with the same first category and the same second category.

In this embodiment, the analysis terminal aggregates the active behavior data in a manner that the time dimension is coupled with the space dimension, so that the data characteristics of the time dimension and the data characteristics of the space dimension are coupled with each other and introduced into the process of intent analysis. Specifically, the analysis terminal considers the first category and the second category simultaneously, and only the active behavior data with the same first category and the same second category are aggregated together, so that the data feature of the time dimension and the data feature of the space dimension are coupled and introduced into the process of intention analysis.

For example: the time region pre-marked by the analysis terminal is '00: 00-07: 00', '07: 00-18: 00', '18: 00-24: 00'; the pre-divided space region is named as Guangzhou and Shenzhen; the analysis of the behavioral intention is to be performed by a set of users consisting of three specific users- "Xiaoming", "Xiaohong", "Xiao just".

When the behavioral intention analysis is carried out aiming at the advertisement clicking behavior of the user, the analysis terminal establishes a matrix A of 3 x 6 with 0 elements.

Each row of the matrix A represents a specific user, each column represents a specific space-time dimension, and each increment of 1 in the value of an element represents that the corresponding specific user carries out an advertisement click on the specific space-time dimension. Specifically, the first row of the matrix a represents "small light", the second row represents "small red", and the third row represents "small steel"; the first column represents "00: guangzhou, 00-07:00, the second column represents "00: shenzhen from 00-07:00, and what the third column represents is "07: guangzhou 00-18:00, column four represents "07: shenzhen from 00-18:00, column five represents "18: guangzhou 00-24:00, column six represents "18: shenzhen "of 00-24: 00.

If the analysis terminal determines that the Xiaoming carries out one advertisement click in Guangzhou of 00:00-07:00 after acquiring the active behavior data; reddish color at 07: shenzhen of 00-18:00 carries out two advertisement clicks; small steel is 18: one click of an advertisement was made in Guangzhou at 00-24: 00. The analysis terminal may obtain a matrix B describing the above advertisement click behavior on the basis of the matrix a.

Therefore, the analysis terminal can perform corresponding processing on the matrix B to realize aggregation of active behavior data with the same first category and the same second category. Specifically, the analysis terminal can directly add the row vectors of the matrix B, so as to aggregate the vectors [ 0,1,0,2,1,0 ] of the user set without distinguishing the difference between specific user individuals, and further analyze the behavior intention of the user set on the basis of the vectors (for example, whether the user set is biased to perform advertisement clicking in Guangzhou or Shenzhen, whether the user set is biased to perform advertisement clicking in 00:00-07:00 or 07:00-18: 00); the analysis terminal can also perform deformation or compression in other forms on the matrix B based on the property of the matrix to obtain matrix information reflecting the difference among specific user individuals, and further can dig out personalized information among the specific user individuals while analyzing the behavior intention of the user set on the basis of the matrix information.

The embodiment has the advantage that in the process of mutually coupling the data characteristics of the time dimension and the data characteristics of the space dimension, the hidden relation between the time information and the space information is displayed to a certain extent, so that the information content contained in the aggregation result is further improved.

In an embodiment, the method further comprises: and performing third classification on the active behavior data in service dimension based on the service attribute information corresponding to the active behavior data.

Aggregating the active behavior data based on the first classification and the second classification, comprising: aggregating the active behavior data based on the first classification, the second classification, and the third classification.

In this embodiment, in addition to introducing the first classification in the time dimension and the second classification in the space dimension, so that the data aggregation process in the behavioral intent analysis can embody data features in the space-time dimension, the analysis terminal also introduces the third classification in the business dimension, so that the data aggregation process in the behavioral intent analysis can embody data features in the business dimension. Specifically, the service attribute information describes the service to which the active behavior data belongs.

For example: the analysis terminal is an advertisement server, and the acquisition terminal is a friend circle server. The user clicks on an advertisement in his circle of friends, which is an advertisement about the attraction and the historic sites, for guiding the user to travel to the location. That is, at the business level, the advertisement is a travel business related advertisement. The friend circle server stores the active behavior data describing the click behavior, and also stores the service attribute information "travel" describing the service to which the click behavior belongs, together with the active behavior data.

In the process of analyzing the intention, the advertisement server obtains the active behavior data from the friend circle server, and then performs a first classification in a time dimension based on the time attribute information and a second classification in a space dimension based on the space attribute information, and further performs a third classification in a business dimension based on the business attribute information "travel".

And aggregating all the acquired active behavior data based on the first classification, the second classification and the third classification of all the acquired active behavior data, and further analyzing the behavior intention of the user based on the aggregation result.

As can be understood, the implementation process of introducing the third classification in the service dimension and then aggregating the active behavior data based on the first classification, the second classification and the third classification is the same as the implementation process of aggregating the active behavior data based on the first classification and the second classification. Therefore, only one embodiment is shown and described herein with respect to the implementation of the aggregation of the proactive behavior data based on the first classification, the second classification and the third classification.

In one embodiment, the time region pre-divided by the analysis terminal is-00: 00-12:00 ', -12: 00-24: 00'; the pre-divided space region is named as Guangzhou and Shenzhen; the service area divided in advance has the functions of 'travel' and 'dress ornament'. The analysis of the behavioral intention is to be performed by a set of users consisting of three specific users- "Xiaoming", "Xiaohong", "Xiao just".

When the behavioral intention analysis is carried out aiming at the advertisement clicking behavior of the user, the analysis terminal establishes a matrix C of 3 x 8, wherein the elements of the matrix C are 0.

Each row of the matrix C represents a specific user, each column represents a specific spatiotemporal dimension, and each increment of 1 by the value of an element represents that the corresponding specific user has performed an advertisement click on the specific spatiotemporal dimension. Specifically, the first row of the matrix C represents "small light", the second row represents "small red", and the third row represents "small steel"; the first column represents "00: guangzhou at 00-12:00, related to travel services ", the second column represents" 12: guangzhou at 00-24:00, relating to travel services ", the third column represents" 00: shenzhen from 00-12:00, relating to travel services, "column four represents" 12: shenzhen from 00-24:00, relating to travel services, "column five represents" 00: guangzhou, 00-12:00, related to apparel business ", column six represents" 12: guangzhou, 00-24:00, related to apparel business ", column seven represents" 00: shenzhen of 00-12:00, related to apparel business ", column 8 represents" 12: shenzhen of 00-24:00, related to dress business ".

If the analysis terminal acquires the active behavior data and determines the first category, the second category and the third category of each active behavior data, determining that the Xiaoming clicks a travel business related advertisement in Guangzhou at 00:00-12: 00; reddish color at 00: shenzhen of 00-12:00 makes one travel business related advertisement click; reddish 12: shenzhen of 00-24:00 makes one time of advertisement click related to clothing business; small steel is 12: guangzhou at 00-24:00 made one click on travel business related advertisements. The analysis terminal may obtain a matrix D describing the above advertisement click behavior on the basis of the matrix C.

Therefore, the analysis terminal can correspondingly process the matrix D to realize the aggregation of the active behavior data, and further analyze the behavior intention of the user set on the aggregation result.

The embodiment has the advantage that the relation between the business information and the time-space information is more intuitively shown by introducing the characteristic data of the business dimension.

The following describes in detail the behavior intent analysis process by introducing aggregation weights through passive behavior data.

In an embodiment, the method further comprises:

determining passive behavior data corresponding to the active behavior data;

an aggregate weight for the active behavior data is determined based on the first number of passive behavior data.

In this embodiment, the analysis terminal may further determine passive behavior data corresponding to the active behavior data, and further determine an aggregation weight of the active behavior data based on the number of the passive behavior data, so as to aggregate the active behavior data in combination with the aggregation weight, and further analyze the behavior intention based on an aggregation result obtained by the aggregation weight.

It can be understood that, in the case that the two acquired active behavior data are different from each other, even if the two acquired active behavior data are the same, the two acquired active behavior data actually have different meanings.

For example: the first active behavior data obtained is "one advertisement click was made by xiaoming in guangzhou (ten advertisements were pushed by xiaoming in the interim)", and the second active behavior data is "one advertisement click was made by xiaoming in guangzhou (two advertisements were pushed by xiaoming in the interim)". Clearly, the two active behavior data are indifferent from the active behavior data only. The results obtained by performing the polymerization and further the behavior intention analysis were also consistent. However, it is obvious that the meaning of "pushed ten clicks once" is obviously different from that of "pushed two clicks once", and the behavior intention of Xiaoming in the two cases is obviously different.

In this embodiment, aggregating the proactive behavior data based on the first classification and the second classification includes: aggregating the active behavior data based on the first classification, the second classification, and the aggregation weight.

In this embodiment, the aggregation weight when the active behavior data is aggregated is determined according to the corresponding passive behavior data, and then the first classification, the second classification and the aggregation weight are combined to aggregate the active behavior data, so that the subsequent behavior intention analysis can reflect the influence of the passive behavior on the active behavior, and the accuracy of the behavior intention analysis is improved.

The embodiment has the advantages that aggregation weight is introduced through the passive behavior data, so that aggregation of the active behavior data is more fit to an actual scene, and the accuracy of information contained in an aggregation result is improved.

The implementation process of determining the aggregation weight mainly from the time dimension by the analysis terminal is described in detail below.

In an embodiment, the time regions for the first classification are pre-divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

and determining the data which is in the belonged time zone and is related to the behavior object and exposed to the user as the passive behavior data.

In the embodiment, the analysis terminal divides a time region in advance; the analysis terminal determines the aggregation weight mainly from the time dimension.

Specifically, after the analysis terminal acquires active behavior data, a corresponding behavior object (for example, an advertisement pushed to a user) is determined; the analysis terminal acquires the time attribute information of the active behavior data, so as to determine a time region to which the time attribute information belongs, namely, the time region to which the active behavior belongs. And the analysis terminal determines the data in the time zone, which describes that the behavior object is exposed to the user, as passive behavior data.

For example: the analysis terminal is divided into time regions of 00:00-12:00 and 12:00-24:00 in advance. After the analysis terminal acquires active behavior data, namely 'Xiaoming clicks the advertisement with the identification number of 0022 in Guangzhou', the behavior object corresponding to the active behavior data can be determined to be the advertisement with the identification number of 0022.

If the time attribute information of the active behavior data acquired by the analysis terminal is "2019/11/19-15: 13", the analysis terminal may determine that the time region to which the time attribute information belongs is "12: 00-24:00 of 11/19/2019". And in the period of 12:00-24:00 of 11/19/2019, each time the advertisement with the identification number of 0022 is pushed to the xiaoming mode, the analysis terminal correspondingly acquires corresponding data describing that the advertisement with the identification number of 0022 is pushed to the xiaoming mode, namely corresponding passive behavior data. The analysis terminal mainly determines the aggregation weight from the time dimension, so that the analysis terminal can determine the advertisement with the identification number of 0022 as a piece of corresponding passive behavior data no matter whether the advertisement is pushed to xiaoming in Guangzhou or pushed to xiaoming in Shenzhen in the period of 12:00-24:00 of 11/19/2019.

In one embodiment, the time zones for the first classification are pre-divided, and object classes describing classes to which behavior objects belong are pre-divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

determining each similar behavior object with the same category as the behavior object based on the object category corresponding to the behavior object;

and determining the data which is in the belonged time zone and is related to the behavior object and the exposure of the same type behavior objects to the user as the passive behavior data.

In the embodiment, the analysis terminal divides a time region in advance; each object category of the category to which the behavior object belongs is described in advance; the analysis terminal determines the aggregation weight mainly from the time dimension. When determining the passive behavior data, the analysis terminal considers the behavior object corresponding to the active behavior data as a reference for selecting the passive behavior data, and also considers the same type of behavior objects corresponding to the active behavior data.

Specifically, after the analysis terminal acquires active behavior data, a corresponding behavior object (for example, an advertisement pushed to a user) is determined; the analysis terminal acquires time attribute information of the active behavior data so as to determine a time region to which the time attribute information belongs, namely the time region to which the active behavior belongs; the analysis terminal determines various similar behavior objects of the same type as the behavior object based on the object type corresponding to the behavior object; and the analysis terminal determines the data which describes the behavior object and exposes the same type of behavior objects to the user in the time region as passive behavior data.

For example: the analysis terminal divides time regions-00: 00-12:00 and 12:00-24:00 in advance; the object categories are classified in advance, i.e., "orange advertisement" and "grapefruit advertisement". After the analysis terminal acquires active behavior data, namely 'Xiaoming clicks the advertisement with the identification number of 0022 in Guangzhou', the behavior object corresponding to the active behavior data can be determined to be the advertisement with the identification number of 0022. Wherein, the advertisement with the identification number of 0022 is an advertisement related to sugar oranges, and belongs to an 'orange advertisement'; also belonging to the "orange advertisement" is an advertisement related to the ugly orange with the identification number of 0023.

If the time attribute information of the active behavior data acquired by the analysis terminal is "2019/11/19-15: 13", the analysis terminal may determine that the time region to which the time attribute information belongs is "12: 00-24:00 of 11/19/2019". And in the period of 12:00-24:00 of 11/19/2019, each time the advertisement with the identification number of 0022 is pushed to the xiaoming mode, the analysis terminal correspondingly acquires corresponding data describing that the advertisement with the identification number of 0022 is pushed to the xiaoming mode, namely corresponding passive behavior data. Meanwhile, during the period of 12:00-24:00 of 11/19/2019, the advertisement with the identification number of 0023 is pushed to the Xiaoming once, and the corresponding data describing that the advertisement with the identification number of 0023 is pushed to the Xiaoming is also determined as a corresponding passive behavior data by the analysis terminal.

An advantage of this embodiment is that the object classes can be divided according to the requirements of the behavioral intent analysis. Specifically, according to the analysis dimension targeted by the demand, the object categories matched with the granularity of the analysis dimension can be correspondingly divided. For example: if the behavior intention of the user about the oranges is analyzed, the object category can be divided into 'sugar orange advertisement' and 'ugly orange advertisement', so that whether the user tends to the sugar oranges or the ugly oranges is analyzed; if an analysis dimension is promoted, to analyze the behavioral intention of the user about fruits, the object categories can be divided into "orange advertisement" and "peach advertisement", so as to analyze whether the user tends to be orange or peach. By the method, the aggregation weight determined on the basis can be dynamically matched with the requirement of behavior intention analysis, and the flexibility of behavior intention analysis is improved.

In one embodiment, determining the aggregate weight for the active behavior data based on the first number of passive behavior data comprises:

determining a second number of the active behavior data in the belonged time zone;

acquiring a preset function for determining the aggregation weight in the scene based on the scene analyzed by the behavior intention;

the first number and the second number are taken as inputs to the function, and an output of the function is determined as the aggregation weight.

In this embodiment, the analysis terminal presets a corresponding function for determining the aggregation weight in a scene based on the scene of behavior intention analysis. For example: and the analysis terminal presets a function for determining the aggregation weight in each scene. Specifically, for a scenario of analyzing the article collection behavior intention, a function for determining the aggregation weight is y ═ exp (-x/g); wherein x is a first number of passive behavior data, g is a second number of active behavior data, y is an aggregation weight, and exp is an exponential function with a natural constant e as a base. Aiming at the scene of advertisement click behavior intention analysis, a function for determining the aggregation weight is that y is g/x; wherein x is a first number of passive behavior data, g is a second number of active behavior data, and y is an aggregation weight. Therefore, when the analysis terminal analyzes the behavior intention aiming at the article collection behavior of the user, the analysis terminal determines the aggregation weight of the active behavior data by adopting a function y as exp (-x/g); when the analysis terminal conducts behavior intention analysis aiming at the advertisement clicking behavior of the user, the analysis terminal determines the aggregation weight of the active behavior data by adopting a function y which is g/x.

After the passive behavior data are obtained, the analysis terminal determines a second number of the active behavior data in a time region corresponding to the passive behavior data; and further taking the first number of the passive behavior data and the second number of the active behavior data as the input of the function, and determining the output of the function as the aggregation weight corresponding to the active behavior data. For example: the analysis terminal obtains active behavior data with time attribute information of '2019/11/19-15: 13', 'Xiaoming performed one advertisement click with identification number of 0022 in Guangzhou'; the analysis terminal determines that the time zone to which the active behavior data belongs is 12:00-24:00 in 11, 19 and 2019; during "12: 00-24:00 of 11/19/2019", the advertisement with identification number 0022 is pushed 10 times to the xiaoming, i.e., the first number of passive behavior data in the time zone is 10. If active behavior data having time attribute information of "2019/11/19-18: 45" — "the ad click with identification number 0022 was made by xiaoming in guangzhou" also exists in the time zone, that is, the second number of the active behavior data in the time zone is 2 (that is, the behavior of the ad with identification number 0022 by xiaoming in guangzhou in the time zone occurs twice), the aggregate weight y of the active behavior data is exp (-10/2) ═ exp (-5).

In the embodiment, the aggregation weight is determined mainly from the time dimension, so that the aggregation result can show the information of the active behavior data in the time dimension more accurately and more emphatically.

It should be noted that the embodiment is only an exemplary illustration, and should not limit the function and the scope of the disclosure. It is understood that the preset function may also be a reciprocal square function or other type of function; rather than just the type of function, the inputs to the function may be adjusted according to the analysis requirements.

In an embodiment, the spatial regions for the second classification are pre-divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

and determining the data which is in the affiliated space area and is related to the behavior object and exposed to the user as the passive behavior data.

In this embodiment, the analysis terminal divides a spatial region in advance; the analysis terminal determines the aggregation weight mainly from the spatial dimension. It can be understood that the specific implementation process of this embodiment is the same as the specific implementation process of the above corresponding analysis terminal that determines the aggregation weight mainly from the time dimension, and therefore, the detailed description is omitted here.

In one embodiment, the spatial regions for the second classification are pre-partitioned, and object classes describing classes to which the behavior objects belong are pre-partitioned. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

and determining the data which is in the belonged space area and is related to the behavior object and the exposure of the same type behavior objects to the user as the passive behavior data.

In this embodiment, the analysis terminal divides a spatial region in advance; the analysis terminal determines the aggregation weight mainly from the spatial dimension. When determining the passive behavior data, the analysis terminal considers the behavior object corresponding to the active behavior data as a reference for selecting the passive behavior data, and also considers the same type of behavior objects corresponding to the active behavior data. It can be understood that the specific implementation process of this embodiment is the same as the specific implementation process of the above corresponding analysis terminal that determines the aggregation weight mainly from the time dimension, and therefore, the detailed description is omitted here.

determining a second number of the active behavior data in the spatial region to which the user belongs;

It can be understood that the specific implementation process of this embodiment is the same as the specific implementation process of determining the aggregation weight based on the first number of the passive behavior data, and therefore, the detailed description thereof is omitted here.

In an embodiment, the temporal regions for the first classification and the spatial regions for the second classification are pre-divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

and determining the data which is in the belonged time region and in the belonged space region and is related to the behavior object and exposed to the user as the passive behavior data.

In this embodiment, the analysis terminal divides a time region and a space region in advance; the analysis terminal combines the time dimension and the space dimension, and determines the aggregation weight from the two dimensions. It can be understood that the specific implementation process of this embodiment is the same as the specific implementation process of the above corresponding analysis terminal that determines the aggregation weight mainly from the time dimension, and therefore, the detailed description is omitted here.

In an embodiment, each time region for the first classification and each space region for the second classification are previously divided, and each object class describing a class to which a behavior object belongs is previously divided. Determining passive behavior data corresponding to the active behavior data, including:

determining a behavior object corresponding to the active behavior data;

and determining the data which is in the belonged time region and the belonged space region and is related to the behavior object and the exposure of the same type behavior objects to the user as the passive behavior data.

In this embodiment, the analysis terminal divides a time region and a space region in advance; the analysis terminal combines the time dimension and the space dimension, and determines the aggregation weight from the two dimensions. When determining the passive behavior data, the analysis terminal considers the behavior object corresponding to the active behavior data as a reference for selecting the passive behavior data, and also considers the same type of behavior objects corresponding to the active behavior data. It can be understood that the specific implementation process of this embodiment is the same as the specific implementation process of the above corresponding analysis terminal that determines the aggregation weight mainly from the time dimension, and therefore, the detailed description is omitted here.

determining a second number of the active behavior data within the belonging temporal region and within the belonging spatial region;

The following illustrates a specific implementation of an embodiment to fully demonstrate the general process of introducing aggregate weights for behavioral intent analysis.

In this embodiment, the analysis terminal performs behavior intention analysis for the advertisement click behavior of the user, and the function used for determining the aggregation weight is y ═ g/x. Wherein x is a first number of passive behavior data, g is a second number of active behavior data, and y is an aggregation weight.

Wherein, the time region pre-divided by the analysis terminal is '00: 00-07: 00', '07: 00-18: 00', '18: 00-24: 00'; the pre-divided space region is named as Guangzhou and Shenzhen; the analysis of the behavioral intention is to be performed by a set of users consisting of three specific users- "Xiaoming", "Xiaohong", "Xiao just".

Xiaoming made one click of an advertisement in Guangzhou at 00:00-07:00, and Xiaoming was pushed 5 times during 00:00-07:00 in Guangzhou. That is, if the second number of active behavior data is 1 and the first number of corresponding passive behavior data is 5, the aggregate weight of the active behavior data is 1/5, and the corresponding element in the matrix is recorded as 1 × 1/5 — 1/5.

Reddish color at 07: shenzhen at 00-18:00 has made two advertisement clicks, and Xiaohong has been pushed 8 times during 07:00-18:00 of Shenzhen. That is, if the second number of the active behavior data is 2 and the second number of the corresponding passive behavior data is 8, the aggregate weight of the active behavior data is 1/4, and the corresponding element in the matrix is recorded as 2 × 1/4 — 1/2.

Small steel is 18: one advertisement click was made in Guangzhou at 00-24:00 and the ad was just pushed 3 times during 18:00-24:00 in Guangzhou. That is, if the second number of the active behavior data is 1 and the second number of the corresponding passive behavior data is 3, the aggregate weight of the active behavior data is 1/3, and the corresponding element in the matrix is recorded as 1 × 1/3 — 1/3.

The analysis terminal may obtain the corresponding aggregation weight by introducing the passive behavior data on the basis of the matrix a, and further obtain a matrix B describing the advertisement click behavior.

Therefore, the analysis terminal can correspondingly process the matrix B to realize the aggregation of the active behavior data, and further analyze the behavior intention of the user set on the aggregation result.

According to an embodiment of the present disclosure, as shown in fig. 4, there is also provided a behavior intention analysis apparatus, including:

an obtaining module 510 configured to obtain active behavior data of a user;

a first classification module 520, configured to perform a first classification on the active behavior data in a time dimension based on time attribute information corresponding to the active behavior data;

a second classification module 530 configured to perform a second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data;

an aggregation analysis module 540 configured to aggregate the active behavior data based on the first classification and the second classification, and analyze the behavior intention of the user based on an aggregation result.

In an exemplary embodiment of the present disclosure, the obtaining module 510 is configured to obtain the active behavior data of the user within a preset time period by a current time point every preset time period.

In an exemplary embodiment of the present disclosure, each time region for the first classification and each space region for the second classification are divided in advance. The first classification module 520 is configured to: determining a time region to which the time attribute information belongs as a first category of the active behavior data in a time dimension; the second classification module 530 is configured to: determining a space region to which the space attribute information belongs as a second category of the active behavior data in a space dimension; the aggregation analysis module 540 is configured to: aggregating the proactive behavior data based on the first category and the second category.

In an exemplary embodiment of the present disclosure, the aggregation analysis module 540 is configured to:

aggregating the active behavior data of the same first category;

and aggregating the active behavior data with the same second category.

In an exemplary embodiment of the present disclosure, the aggregation analysis module 540 is configured to: aggregating the active behavior data of the same first category and the same second category.

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining passive behavior data corresponding to the active behavior data;

determining a behavior object corresponding to the active behavior data;

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

In an exemplary embodiment of the disclosure, the apparatus is configured to:

determining a behavior object corresponding to the active behavior data;

In an exemplary embodiment of the disclosure, the apparatus is configured to:

The behavioral intent analysis electronic device 60 according to an embodiment of the present disclosure is described below with reference to fig. 5. The behavior intent analysis electronic device 60 shown in fig. 5 is merely an example and should not impose any limitations on the functionality or scope of use of embodiments of the present disclosure.

As shown in fig. 5, the behavioral intent analysis electronic device 60 is embodied in the form of a general purpose computing device. The components of behavioral intent analysis electronic device 60 may include, but are not limited to: the at least one processing unit 610, the at least one memory unit 620, and a bus 630 that couples the various system components including the memory unit 620 and the processing unit 610.

Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the description part of the above exemplary methods of the present specification. For example, the processing unit 610 may perform various steps as shown in fig. 3.

The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.

The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 630 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The behavioral intent analysis electronic device 60 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the behavioral intent analysis electronic device 60, and/or with any device (e.g., router, modem, etc.) that enables the behavioral intent analysis electronic device 60 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. An input/output (I/O) interface 650 is connected to the display unit 640. Also, behavioral intent analysis electronic device 60 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) through network adapter 660. As shown, the network adapter 660 communicates with the other modules of the behavioral intent analysis electronic device 60 over the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with behavioral intent analysis electronics 60, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a processor of a computer, cause the computer to perform the method described in the above method embodiment section.

According to an embodiment of the present disclosure, there is also provided a program product for implementing the method in the above method embodiment, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as JAVA, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A behavioral intent analysis method, the method comprising:

acquiring active behavior data of a user, and determining a behavior object corresponding to the active behavior data;

determining passive behavior data which is used for describing that a user passively makes a response and corresponds to the active behavior data based on the behavior object and the similar behavior objects;

aggregating the active behavior data based on the first classification and the second classification, and analyzing the behavior intention of the user based on an aggregation result;

wherein aggregating the proactive behavior data based on the first classification and the second classification comprises: aggregating the proactive behavior data based on the first classification, the second classification, and the aggregation weight.

2. The method according to claim 1, characterized in that each time region for the first classification and each space region for the second classification are divided in advance;

performing a first classification on the active behavior data in a time dimension based on time attribute information corresponding to the active behavior data, including: determining a time region to which the time attribute information belongs as a first category of the active behavior data in a time dimension;

performing second classification on the active behavior data in a spatial dimension based on the spatial attribute information corresponding to the active behavior data, including: determining a space region to which the space attribute information belongs as a second category of the active behavior data in a space dimension;

aggregating the proactive behavior data based on the first classification and the second classification, comprising: aggregating the proactive behavior data based on the first category and the second category.

3. The method of claim 2, wherein aggregating the proactive behavior data based on the first category and the second category comprises:

aggregating the active behavior data of the same first category;

and aggregating the active behavior data with the same second category.

4. The method of claim 2, wherein aggregating the proactive behavior data based on the first category and the second category comprises: aggregating the active behavior data of the same first category and the same second category.

5. The method of claim 1, further comprising: performing third classification on the active behavior data in service dimension based on the service attribute information corresponding to the active behavior data;

aggregating the proactive behavior data based on the first classification and the second classification, comprising: aggregating the active behavior data based on the first classification, the second classification, and the third classification.

6. The method according to claim 1, characterized in that each time zone for the first classification is divided in advance;

determining passive behavior data, corresponding to the active behavior data and used for describing that the user passively makes a response, based on the behavior object and the similar behavior objects, wherein the passive behavior data comprises:

7. The method of claim 6, wherein determining the aggregate weight for the active behavior data based on the first number of passive behavior data comprises:

8. The method according to claim 1, wherein each spatial region for the second classification is divided in advance;

9. The method of claim 8, wherein determining the aggregate weight for the active behavior data based on the first number of passive behavior data comprises:

10. The method according to claim 1, characterized in that each time region for the first classification and each space region for the second classification are divided in advance;

11. The method of claim 10, wherein determining the aggregate weight for the active behavior data based on the first number of passive behavior data comprises:

12. An apparatus for analyzing behavioral intention, the apparatus comprising:

the acquisition module is configured to acquire active behavior data of a user and determine a behavior object corresponding to the active behavior data;

the first determining module is configured to determine similar behavior objects of the same category as the behavior object based on the object category corresponding to the behavior object;

a second determining module, configured to determine, based on the behavior object and the similar behavior objects, passive behavior data corresponding to the active behavior data and used for describing that a user passively makes a response;

a third determination module configured to determine an aggregate weight for the active behavior data based on the first number of passive behavior data;

an aggregation analysis module configured to aggregate the active behavior data based on the first classification and the second classification, and analyze a behavior intention of the user based on an aggregation result;

13. An electronic device for behavioral intent analysis, comprising:

a memory storing computer readable instructions;

a processor reading computer readable instructions stored by the memory to perform the method of any of claims 1-11.

14. A computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a processor of a computer, cause the computer to perform the method of any one of claims 1-11.