Group analysis method and device based on dynamic age and computer equipment

Abstract

The invention relates to a group analysis method and device based on dynamic age and computer equipment, and the method comprises the steps: generating a user group meeting a first preset condition based on an obtained activity data table; the behavior track information of each target user in the user group is matched with a first preset condition; analyzing the behavior track information of each target user according to a preset constraint chain rule to obtain a dynamic behavior age of each target user; the constraint chain rule is composed of a plurality of behavior conditions used for defining key nodes in the user behavior track; and based on the dynamic behavior age of each target user, performing aggregation analysis on each target user to obtain an aggregation index. Through the method and the device, the problem that the analysis result is distorted due to the fact that the staged features of the user behaviors cannot be accurately reflected and multi-dimensional group analysis is not supported is solved, the staged features of the user behaviors are accurately reflected, the multi-dimensional group analysis is supported, and the accuracy of the analysis result is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, apparatus, and computer device for group analysis based on dynamic age. Background Art

[0002] With the rise of data-driven decision-making, user behavior analysis has become a core task in many fields, including business and education. Group analysis, a key method, divides users into different groups and observes the changing trends of user behavior in each group over time. This provides a basis for decision-making, helping users accurately grasp user dynamics and optimize strategies.

[0003] However, in existing group analysis methods, different user ages are usually defined at fixed time intervals, which cannot accurately reflect the stage characteristics of user behavior, and does not support multi-dimensional group analysis. The analysis method lacks flexibility, resulting in distorted analysis results.

[0004] Currently, no effective solution has been proposed to address the problems in related technologies, such as the inability to accurately reflect the stage characteristics of user behavior, the lack of support for multi-dimensional group analysis, and the lack of flexibility in analysis methods, which leads to distorted analysis results. Summary of the Invention

[0005] In this embodiment, a dynamic age-based group analysis method, apparatus, and computer device are provided to address the problems in related technologies that the method cannot accurately reflect the stage characteristics of user behavior, does not support multi-dimensional group analysis, and lacks flexibility in analysis methods, resulting in distorted analysis results.

[0006] First, in this embodiment, a dynamic age-based group analysis method is provided, including:

[0007] Based on the acquired activity data table, a user group meeting a first preset condition is generated; the behavior trajectory information of each target user in the user group matches the first preset condition;

[0008] Analyzing the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of multiple behavior conditions for defining key nodes in the user behavior trajectory;

[0009] Based on the dynamic behavior age of each target user, an aggregate analysis is performed on each target user to obtain a corresponding aggregate index.

[0010] In some embodiments, generating a user group that meets a first preset condition based on the acquired activity data table includes:

[0011] Based on the obtained activity data table, a plurality of target users meeting the first preset condition are screened out; the first preset condition is used to indicate the time when the user first meets the preset behavior event;

[0012] Based on the plurality of target users meeting the first preset condition, the corresponding user group is generated.

[0013] In some embodiments, before screening out the plurality of target users that meet the first preset condition based on the obtained activity data table, the method further includes:

[0014] Based on a plurality of predefined user behavior categories, the behavior trajectory information of each user is generated; the behavior trajectory information includes at least a user identifier, a behavior category, a behavior time, and dimension data and measurement data associated with the user behavior.

[0015] In some embodiments, analyzing the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user includes:

[0016] According to the preset constraint chain rules, the behavior trajectory information of each target user in the user group is analyzed by a dynamic age calculation model to obtain the dynamic behavior age of each target user;

[0017] The dynamic age calculation model is used to determine the dynamic behavioral age of the target user according to the number of times the target user meets the behavioral condition specified by the constraint chain rule.

[0018] In some embodiments, performing aggregate analysis on each target user based on the dynamic behavior age of each target user to obtain corresponding aggregate indicators includes:

[0019] Based on the dynamic behavior age of each target user, dividing each target user into a plurality of first groups;

[0020] Aggregate analysis is performed on the target users in different first groups to obtain the aggregation index corresponding to each first group.

[0021] In some embodiments, dividing each target user into a plurality of first groups based on the dynamic behavior age of each target user includes:

[0022] Based on a second preset condition, each of the target users is divided into a plurality of second groups;

[0023] The target users in each of the second groups are divided into a plurality of first groups based on the dynamic behavior age of each of the target users.

[0024] In some embodiments, the method further comprises:

[0025] Preprocessing the behavior trajectory information; the preprocessing includes dictionary compression and difference coding;

[0026] The pre-processed behavior trajectory information is stored in column format.

[0027] In a second aspect, this embodiment provides a dynamic age-based group analysis device, including:

[0028] A generating module, configured to generate a user group that meets a first preset condition based on the acquired activity data table; wherein the behavior trajectory information of each target user in the user group matches the first preset condition;

[0029] an analysis module, configured to analyze the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of a plurality of behavior conditions for defining key nodes in the user behavior trajectory;

[0030] The aggregation module is used to perform aggregation analysis on each target user based on the dynamic behavior age of each target user to obtain a corresponding aggregation index.

[0031] In a third aspect, a computer device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the dynamic age-based group analysis method described in the first aspect is implemented.

[0032] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored. When the program is executed by a processor, the dynamic age-based group analysis method described in the first aspect is implemented.

[0033] Compared with related technologies, the dynamic age-based group analysis method, device and computer equipment provided in this embodiment generate a user group that meets the first preset condition based on the obtained activity data table; the behavior trajectory information of each target user in the user group matches the first preset condition; according to the preset constraint chain rule, the behavior trajectory information of each target user in the user group is analyzed to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of multiple behavior conditions for defining key nodes in the user behavior trajectory; based on the dynamic behavior age of each target user, each target user is aggregated and analyzed to obtain corresponding aggregation indicators, which solves the problem of not being able to accurately reflect the stage characteristics of user behavior, not supporting multi-dimensional group analysis, and lacking flexibility in analysis methods, resulting in distorted analysis results. It realizes the accurate reflection of the stage characteristics of user behavior through dynamic age calculation, while supporting multi-dimensional group analysis and improving the accuracy of analysis results.

[0034] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0036] Figure 1 This is a hardware structure block diagram of a terminal device for a dynamic age-based group analysis method provided in one embodiment of the present application;

[0037] Figure 2 is a flow chart of a group analysis method based on dynamic age provided in one embodiment of the present application;

[0038] Figure 3 This is a flowchart of the operator fusion process provided by an embodiment of the present application;

[0039] Figure 4 This is a flow chart of a method for initially dividing user groups provided in one embodiment of the present application;

[0040] Figure 5 This is a flow chart of a group analysis method based on dynamic age provided in a preferred embodiment of the present application;

[0041] Figure 6 4 is a structural block diagram of a dynamic age-based group analysis device provided in one embodiment of the present application.

[0042] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 10, generation module; 20, analysis module; 30, aggregation module. DETAILED DESCRIPTION

[0043] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0044] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "an", "a", "the", "these" and the like in this application do not indicate quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0045] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a block diagram of the hardware structure of the terminal of the dynamic age-based group analysis method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0046] Memory 104 can be used to store computer programs, such as software programs and modules for application software, such as the computer program corresponding to the dynamic age-based cohort analysis method in this embodiment. Processor 102 executes the computer program stored in memory 104 to execute various functional applications and data processing, thereby implementing the above-mentioned method. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located relative to processor 102, and such remote memory may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0047] The transmission device 106 is used to receive or send data via a network. The network may include a wireless network provided by the terminal's telecommunications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0048] In this embodiment, a group analysis method based on dynamic age is provided. Figure 2 is a flow chart of the dynamic age-based group analysis method of this embodiment, as shown in FIG. Figure 2 As shown, the process includes the following steps:

[0049] Step S210: generating a user group that meets a first preset condition based on the acquired activity data table; the behavior trajectory information of each target user in the user group matches the first preset condition;

[0050] Step S220: Analyze the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of multiple behavior conditions used to define key nodes in the user's behavior trajectory;

[0051] Step S230 : performing aggregation analysis on each target user based on the dynamic behavior age of each target user to obtain a corresponding aggregation index.

[0052] Specifically, the behavioral data of each user is obtained. The behavioral data includes the user's specific behavior, the time when the behavior occurred, etc. Based on the behavioral data of each user, an activity data table of the corresponding user is constructed. The activity data table is used to record the user's behavioral trajectory information. The main fields include but are not limited to user ID, behavior category, behavior time, and dimension data and measurement data associated with user behavior. Among them, the user ID is used to uniquely identify the corresponding user; the behavior category is used to record the specific category of each user's behavior. For example, in the case of website shopping, the specific categories of user behavior include login, purchase, comment, etc.; the behavior time is used to record the execution time of each user's behavior; the dimension data and measurement data associated with user behavior include the context information of the user behavior (such as product category, operating device), the result data of the user behavior (such as amount, rating), etc.

[0053] Furthermore, based on the activity data tables of different users, multiple target users that meet the first preset conditions are screened out, the behavioral trajectory information of each target user matches the first preset condition, and each target user constitutes a user group that meets the first preset condition. Among them, the first preset condition is set according to actual application needs. For example, in an e-commerce scenario, the first preset condition is set to indicate the time when the user first meets the preset behavioral event. The preset behavioral events include the first purchase of goods, the first comment, etc. It should be noted that after generating a user group that meets the first preset condition, the current group can be finely divided according to other user attributes. For example, the user group that meets the first preset condition is divided according to specific attributes such as different regions, genders or membership levels, and the divided groups are used as the basis for subsequent analysis.

[0054] Obtain the preset constraint chain rules. The constraint chain rules are composed of multiple behavior conditions used to define key nodes in the user behavior trajectory, that is, the constraint chain rule N =<C1,C2,C3…> For example, consider the constraint chain rule of "completion of order - receipt of review - repurchase," with "completion of order," "receipt of review," and "repurchase" as key nodes in the user's behavior trajectory. Based on the preset constraint chain rule, the behavior trajectory information of each target user in the user group is analyzed, and the dynamic behavior age of each target user is calculated based on the analysis results. The dynamic behavior age reflects the user's behavioral development stage and maturity on the corresponding platform.

[0055] The number of times a target user satisfies the behavioral conditions specified in the constraint chain rules can be analyzed. Each time a user satisfies a behavioral condition in the constraint chain, the user's dynamic behavioral age is automatically updated, thereby calculating the target user's dynamic behavioral age based on the number of times the user satisfies the conditions. For example, when a user purchases a product for the first time, the user's dynamic behavioral age is assigned a value of 1, and when the user purchases the product for the second time, the user's dynamic behavioral age is incremented to 2. Alternatively, based on the dynamic behavioral age calculated based on the number of times the user satisfies the conditions, a weighted operation is performed based on characteristics such as the time interval between when the user satisfies each behavioral condition and the importance of each behavioral condition in the constraint chain rules to obtain the target user's dynamic behavioral age. For example, the behavior weight of "completing an order" is preset to 1, and the behavior weight of "receiving a review" is preset to 2. When a user completes an order for the first time, the dynamic behavioral age is assigned a value of 1, and when the system receives a user review for the corresponding order, the user's dynamic behavioral age is incremented to 3. Alternatively, the user's dynamic behavioral age is assigned based on the order in which the user completes each behavioral condition. When the user completes the behavioral conditions specified in the constraint chain rules in the preset order, the dynamic behavioral age is assigned a larger value, while when the user's actual completion order does not match the preset order, the dynamic behavioral age is assigned a smaller value. In practical applications, there is no specific limitation on the calculation method of dynamic behavior age based on the constraint chain rule.

[0056] Afterwards, based on the dynamic behavior age of each target user, each target user is divided into multiple first groups, and the target users in different first groups are aggregated and analyzed to obtain an aggregate indicator corresponding to each first group. The aggregate indicator is used to describe the characteristics or attributes of the current group. The aggregate indicator category is related to the application scenario, such as the frequency of occurrence of different user behaviors, average purchase amount, average online time, average number of interactions, etc.

[0057] The following uses the online education scenario as an example to explain the group analysis process based on dynamic age in detail. First, obtain the activity data table of each user. The activity data table is used to record the user's first registration, course viewing, course completion and other behavioral data. A first preset condition is set based on the time of the first course viewing, and the target users who first viewed the course within the time range indicated by the first preset condition are screened out. The specific time of the first course viewing is recorded as the "birth time" of the target user. Next, the constraint chain rule is predefined as "view course - complete homework - pass test". According to the constraint chain rule, the behavioral trajectory information of each target user in the user group is analyzed to obtain the dynamic behavioral age of each target user. After obtaining the dynamic behavioral age of each target user, each target user is divided into multiple groups of different behavioral age groups. Aggregate analysis is performed on each target user in each behavioral age group to analyze and obtain aggregate indicators such as the proportion of users in each behavioral age group who complete the course and the average learning time.

[0058] It should be noted that in order to support group queries based on dynamic age, this embodiment constructs corresponding operators, specifically including the activity selection operator Initial selection operator and group aggregation operators Among them, for the activity selection operator e is the first behavior, C is the condition that the activity record after the first behavior must meet, is the constraint chain; for the initial selection operator e is the first action, C is used to specify the first preset condition that the first action record should meet; for the group aggregation operator e is the first behavior, The attributes by which users are grouped. is the constraint chain, f A is an aggregation function. The initial selection operator is used to filter user records that meet the first preset condition and generate an initial user group that meets the first preset condition. The age selection operator is used to dynamically calculate the user behavior age based on the constraint chain rule and filter activity records that meet specific conditions. The group aggregation operator is used to dynamically calculate the user behavior age based on the constraint chain rule, group user behaviors according to the specified conditions, and calculate the corresponding aggregation index after grouping activity records according to different behavior ages. Figure 3 As shown, the query process pushes the initial selection and age selection operations down to the data reading stage, so the initial selection operator is Activity selection operator and group aggregation operators And the dynamic age calculation process in the screening and aggregation operations is integrated, and the initial selection operator is finally obtained as The dynamic age calculation operator is Activity Selection Derivation Operator And the group aggregation derivation operator is e is the first behavior, is the constraint chain, C is the condition that the activity record must meet after the first behavior, D g For an activity record table containing an age attribute column, is the attribute used to divide users into groups, f A is an aggregate function, D g An activity record table with an age attribute column is created to avoid repeated calculations and significantly reduce the computational overhead of large-scale data analysis.

[0059] Cohort analysis, as an important method, divides users into different groups and observes the changing trends of user behavior in each group over time. This provides a basis for decision-making, helping users accurately grasp user dynamics and optimize strategies. However, existing cohort analysis methods typically define different user ages at fixed time intervals, which cannot accurately reflect the stage-by-stage characteristics of user behavior. They also lack support for multi-dimensional cohort analysis, lack flexibility in analysis methods, and lead to distorted analysis results.

[0060] Compared with the prior art, the present application generates a user group that meets the first preset condition based on the obtained activity data table; the behavior trajectory information of each target user in the user group matches the first preset condition; according to the preset constraint chain rule, the behavior trajectory information of each target user in the user group is analyzed to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of multiple behavior conditions for defining key nodes in the user behavior trajectory; based on the dynamic behavior age of each target user, each target user is aggregated and analyzed to obtain a corresponding aggregation index. Based on this, by analyzing the behavior trajectory information of each target user according to the preset constraint chain rule to obtain the dynamic situation in which the target user behavior meets the behavior conditions set by the constraint chain rule, the dynamic behavior age of the user can be calculated according to the analysis results, and aggregation analysis is performed on users of different behavior ages to obtain the behavior characteristics and behavior patterns of different user groups, which solves the problem of not being able to accurately reflect the stage characteristics of user behavior, not supporting multi-dimensional group analysis, and lacking flexibility in analysis methods, resulting in distorted analysis results. It achieves the accurate reflection of the stage characteristics of user behavior through dynamic age calculation, while supporting multi-dimensional group analysis and improving the accuracy of analysis results.

[0061] In some of these embodiments, Figure 4 As shown, generating a user group that meets the first preset condition based on the acquired activity data table in step S210 includes the following steps:

[0062] Step S211: Based on the acquired activity data table, a plurality of target users that meet a first preset condition are screened out; the first preset condition is used to indicate the time when the user first meets a preset behavior event;

[0063] Step S212: generating a corresponding user group based on a plurality of target users that meet the first preset condition.

[0064] Specifically, the behavioral data of each user is obtained. The behavioral data includes the user's specific behavior, the time when the behavior occurred, etc., and based on the behavioral data of each user, an activity data table of the corresponding user is constructed. The activity data table is used to record the user's behavioral trajectory information. Accordingly, the main fields of the activity data table include user ID, behavior category, behavior time, and dimension data and measurement data associated with user behavior. The user ID is used to uniquely identify the corresponding user; the behavior category is used to record the specific category of each user's behavior. For example, in the case of website shopping, the specific categories of user behavior include login, purchase, comment, etc.; the behavior time is used to record the execution time of each user's behavior; the dimension data and measurement data associated with user behavior include the context information of the user behavior (such as product category, operating device), the result data of the user behavior (such as amount, rating), etc.

[0065] Furthermore, the activity data tables of different users are analyzed to screen out multiple target users that meet the first preset condition, the behavior trajectory information of each target user matches the first preset condition, and the target users form a user group that meets the first preset condition.

[0066] It should be noted that the above-mentioned first preset condition is set according to actual application needs. For example, in an e-commerce scenario, the first preset condition is set to indicate the time when the user first meets the preset behavior event, which includes the first purchase of a product or the first posting of a comment. In a social media scenario, the first preset condition is set to indicate the number of followers and interaction frequency, the topic of the content posted, etc.

[0067] Through this embodiment, based on the obtained activity data table, multiple target users that meet the first preset condition are screened out. The first preset condition is used to indicate the time when the user first meets the preset behavior event. Based on the multiple target users that meet the first preset condition, corresponding user groups are generated, thereby accurately locating the target user group, avoiding untargeted group analysis, improving analysis efficiency, and ensuring the effectiveness of the analysis.

[0068] In some embodiments, before screening out a plurality of target users that meet the first preset condition based on the acquired activity data table, the following steps are further included:

[0069] Based on multiple predefined user behavior categories, behavior trajectory information of each user is generated; the behavior trajectory information includes at least user identification, behavior category, behavior time, and dimension data and measurement data associated with the user behavior.

[0070] Specifically, multiple user behavior categories are predefined, depending on the actual application scenario. For example, in e-commerce scenarios, user behavior categories include logging in, purchasing, and commenting; in social media scenarios, user behavior categories include posting updates, following friends, and forwarding and sharing.

[0071] Furthermore, based on multiple predefined user behavior categories, the user's behavior data is analyzed to determine the behavior category corresponding to the user's specific behavior, thereby generating each user's behavior trajectory information, which includes the user ID, behavior category, behavior time, and dimensional data and measurement data associated with the user's behavior. The dimensional data and measurement data associated with the user's behavior include contextual information of the user's behavior (such as product category, operation device), and the result data of the user's behavior (such as amount, rating), etc.

[0072] Through this embodiment, based on multiple predefined user behavior categories, behavior trajectory information of each user is generated. The behavior trajectory information includes at least user identification, behavior category, behavior time, and dimensional data and measurement data associated with user behavior, which helps to comprehensively and deeply analyze user behavior patterns.

[0073] In some embodiments, step S220 analyzes the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user, including the following steps:

[0074] According to the preset constraint chain rules, the behavior trajectory information of each target user in the user group is analyzed through the dynamic age calculation model to obtain the dynamic behavior age of each target user;

[0075] The dynamic age calculation model is used to determine the dynamic behavioral age of the target user based on the number of times the target user meets the behavioral conditions specified by the constraint chain rules.

[0076] Specifically, a preset constraint chain rule is obtained. The constraint chain rule is composed of multiple behavioral conditions used to define key nodes in the user behavior trajectory. For example, "complete order - receive evaluation - purchase again" is used as a constraint chain rule, and "complete order", "receive evaluation" and "purchase again" are multiple key nodes in the user behavior trajectory.

[0077] Furthermore, based on the preset constraint chain rules, the dynamic age calculation model analyzes the behavioral trajectory information of each target user in the user group to obtain the number of times the target user meets the behavioral conditions specified by the constraint chain rules. Each time a user meets a behavioral condition in the constraint chain, the user's dynamic behavioral age is automatically updated, and the dynamic behavioral age of the target user is calculated based on the number of times the condition is met. For example, when a user purchases a product for the first time, the user's dynamic behavioral age is assigned a value of 1. When the user purchases the product for the second time, the user's dynamic behavioral age increases to 2.

[0078] It should be noted that, on the basis of calculating the dynamic behavior age based on the number of satisfaction, weighted operations can be performed based on characteristics such as the time interval between users satisfying various behavioral conditions and the importance of different behavioral conditions in the constraint chain rules to obtain the dynamic behavior age of the target user. For example, the behavior weight of "completing an order" is pre-set to 1, and the behavior weight of "receiving evaluation" is pre-set to 2. When the user completes an order for the first time, the dynamic behavior age is assigned to 1. When the system receives user evaluation of the corresponding order, the user's dynamic behavior age increases to 3.

[0079] Through this embodiment, according to the preset constraint chain rules, the behavior trajectory information of each target user in the user group is analyzed through the dynamic age calculation model to obtain the dynamic behavioral age of each target user. The dynamic age calculation model is used to determine the dynamic behavioral age of the target user based on the number of times the target user meets the behavioral conditions specified by the constraint chain rules. In this way, the dynamic age calculation model is used to dynamically calculate the user's behavioral age according to the constraint chain rules, thereby improving the accuracy of calculating the user's behavioral age.

[0080] In some embodiments, performing aggregate analysis on each target user based on the dynamic behavior age of each target user to obtain a corresponding aggregate index in step S230 includes the following steps:

[0081] Step S231 , dividing each target user into a plurality of first groups based on the dynamic behavior age of each target user;

[0082] Step S232: performing aggregation analysis on target users in different first groups to obtain an aggregation index corresponding to each first group.

[0083] Specifically, based on the dynamic behavioral age of each target user, each target user is divided into multiple first groups, each first group corresponds to a different dynamic behavioral age segment, and the target users in each first group are aggregated and analyzed to obtain an aggregation indicator corresponding to each first group. The aggregation indicator is used to describe the characteristics or attributes of the current group, and the aggregation indicator category is associated with the application scenario.

[0084] For example, taking the online education scenario as an example, the target users of the online education platform are divided into multiple groups of different behavioral age groups, and the target users in each behavioral age group are aggregated and analyzed to obtain aggregate indicators such as the proportion of users in each behavioral age group who have completed courses and the average learning time.

[0085] Through this embodiment, based on the dynamic behavioral age of each target user, each target user is divided into multiple first groups, and the target users in different first groups are aggregated and analyzed to obtain aggregation indicators corresponding to each first group. In this way, effective analysis is performed on users at different stages, and the statistical characteristics and behavioral patterns of users in each group are obtained, which meets the behavioral analysis needs in complex business scenarios and helps to achieve efficient and accurate decision-making.

[0086] In some embodiments, the step S231 of dividing each target user into a plurality of first groups based on the dynamic behavior age of each target user includes the following steps:

[0087] Based on a second preset condition, dividing each target user into a plurality of second groups;

[0088] Based on the dynamic behavior age of each target user, each target user in each second group is divided into a plurality of first groups.

[0089] Specifically, after obtaining the dynamic behavioral age of each target user, each target user is divided into multiple second groups based on a second preset condition. The second preset condition is used to limit the target users to specific regions, genders, etc., which are not limited here. Subsequently, based on the dynamic behavioral age of each target user, each target user is divided into multiple first groups, each first group corresponding to a different dynamic behavioral age range.

[0090] For example, for multiple target users on an online education platform, each target user is divided into multiple second groups according to their geographical location, each second group corresponds to a different geographical location, and the users in each second group are divided into multiple first groups according to different dynamic behavioral age groups, so that the learning trends of users in each dynamic behavioral age group in different regions can be analyzed.

[0091] Through this embodiment, based on the second preset condition, each target user is divided into multiple second groups, and based on the dynamic behavioral age of each target user, each target user in each second group is divided into multiple first groups. In this way, the second preset condition and the dynamic behavioral age are combined to perform fine group division, realize multi-dimensional group analysis, and contribute to the subsequent efficient use of system resources.

[0092] In some embodiments, the dynamic age-based group analysis method further includes the following steps:

[0093] Preprocessing the behavior trajectory information; preprocessing includes dictionary compression and difference coding;

[0094] The preprocessed behavior trajectory information is stored in column format.

[0095] Specifically, we use optimization strategies such as dictionary compression algorithm and difference coding technology to preprocess the behavior trajectory information of each user, and store the preprocessed behavior trajectory information in column format to reduce the storage overhead of large-scale user behavior data.

[0096] In addition, a primary key index is established for the activity data table, with user ID, behavior time, behavior category, etc. as index fields. This allows the database to quickly filter and locate data that meets the conditions when performing multi-condition queries, thereby improving query speed.

[0097] Through this embodiment, the behavior trajectory information is preprocessed, and the preprocessing includes dictionary compression and difference encoding. The preprocessed behavior trajectory information is stored in column format, thereby reducing storage space and optimizing query efficiency.

[0098] Figure 5 is a flow chart of the dynamic age-based group analysis method of this preferred embodiment, as shown in FIG. Figure 5 As shown, the dynamic age-based group analysis method includes the following steps:

[0099] Step S510: Based on the acquired activity data table, a plurality of target users meeting a first preset condition are screened out; the first preset condition is used to indicate the time when the user first meets a preset behavior event; and corresponding user groups are generated based on the plurality of target users meeting the first preset condition.

[0100] Step S520: Analyze the behavior trajectory information of each target user in the user group using a dynamic age calculation model based on the preset constraint chain rules to obtain the dynamic behavior age of each target user. The dynamic age calculation model is used to determine the dynamic behavior age of the target user based on the number of times the target user meets the behavior conditions specified by the constraint chain rules.

[0101] Step S530 : dividing each target user into a plurality of first groups based on the dynamic behavior age of each target user; performing aggregation analysis on the target users in different first groups to obtain an aggregation index corresponding to each first group.

[0102] Through this embodiment, based on the obtained activity data table, multiple target users that meet the first preset condition are screened out; the first preset condition is used to indicate the time when the user first meets the preset behavior event; based on the multiple target users that meet the first preset condition, corresponding user groups are generated.

[0103] Furthermore, according to the preset constraint chain rules, the behavior trajectory information of each target user in the user group is analyzed through a dynamic age calculation model to obtain the dynamic behavior age of each target user; wherein, the dynamic age calculation model is used to determine the dynamic behavior age of the target user based on the number of times the target user meets the behavioral conditions specified by the constraint chain rules. Based on the dynamic behavior age of each target user, each target user is divided into multiple first groups; the target users in different first groups are aggregated and analyzed to obtain aggregate indicators corresponding to each first group. This solves the problem of inaccurate reflection of the stage characteristics of user behavior, lack of support for multi-dimensional group analysis, and lack of flexibility in the analysis method, which leads to distorted analysis results. It realizes the accurate reflection of the stage characteristics of user behavior through dynamic age calculation, while supporting multi-dimensional group analysis and improving the accuracy of the analysis results.

[0104] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0105] This embodiment also provides a dynamic age-based group analysis device for implementing the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. The terms "module," "unit," "subunit," etc. used below may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0106] Figure 6 This is a structural block diagram of the dynamic age-based group analysis device of this embodiment. Figure 6 As shown, the device includes:

[0107] A generating module 10 is configured to generate a user group that meets a first preset condition based on the acquired activity data table; the behavior trajectory information of each target user in the user group matches the first preset condition;

[0108] The analysis module 20 is used to analyze the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of multiple behavior conditions used to define key nodes in the user behavior trajectory;

[0109] The aggregation module 30 is used to perform aggregation analysis on each target user based on the dynamic behavior age of each target user to obtain a corresponding aggregation index.

[0110] Through the device provided by this embodiment, based on the acquired activity data table, a user group that meets the first preset condition is generated; the behavioral trajectory information of each target user in the user group matches the first preset condition; according to the preset constraint chain rule, the behavioral trajectory information of each target user in the user group is analyzed to obtain the dynamic behavioral age of each target user; the constraint chain rule is composed of multiple behavioral conditions for defining key nodes in the user behavior trajectory; based on the dynamic behavioral age of each target user, an aggregation analysis is performed on each target user to obtain a corresponding aggregation index, which solves the problem of not being able to accurately reflect the stage characteristics of user behavior, not supporting multi-dimensional group analysis, and lacking flexibility in the analysis method, resulting in distorted analysis results. It realizes the accurate reflection of the stage characteristics of user behavior through dynamic age calculation, while supporting multi-dimensional group analysis and improving the accuracy of the analysis results.

[0111] In some embodiments, the generation module 10 is further used to screen out multiple target users that meet a first preset condition based on the acquired activity data table; the first preset condition is used to indicate the time when the user first meets a preset behavioral event; and based on the multiple target users that meet the first preset condition, generate a corresponding user group.

[0112] In some of these embodiments, Figure 6 On the basis of this, the device also includes a preprocessing module for generating behavior trajectory information of each user based on a plurality of predefined user behavior categories; the behavior trajectory information includes at least user identification, behavior category, behavior time, and dimensional data and measurement data associated with the user behavior.

[0113] In some embodiments, the analysis module 20 is further configured to analyze the behavioral trajectory information of each target user in the user group according to a preset constraint chain rule using a dynamic age calculation model to obtain the dynamic behavioral age of each target user; wherein the dynamic age calculation model is configured to determine the dynamic behavioral age of the target user based on the number of times the target user meets the behavioral conditions specified by the constraint chain rule.

[0114] In some embodiments, the aggregation module 30 is further configured to divide each target user into multiple first groups based on the dynamic behavior age of each target user; perform aggregation analysis on the target users in different first groups to obtain aggregation indicators corresponding to each first group.

[0115] In some embodiments, the aggregation module 30 is further configured to divide each target user into a plurality of second groups based on a second preset condition; and divide each target user in each second group into a plurality of first groups based on the dynamic behavior age of each target user.

[0116] In some of these embodiments, Figure 6 On the basis of, the device also includes a storage module for preprocessing the behavior trajectory information; the preprocessing includes dictionary compression and difference coding; and the preprocessed behavior trajectory information is stored in column format.

[0117] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0118] This embodiment further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0119] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0120] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0121] S1, based on the obtained activity data table, generating a user group that meets a first preset condition; the behavior trajectory information of each target user in the user group matches the first preset condition;

[0122] S2, analyzing the behavior trajectory information of each target user in the user group according to the preset constraint chain rules to obtain the dynamic behavior age of each target user; the constraint chain rules are composed of multiple behavior conditions used to define key nodes in the user's behavior trajectory;

[0123] S3, based on the dynamic behavior age of each target user, conduct aggregation analysis on each target user to obtain the corresponding aggregation index.

[0124] It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0125] In addition, in conjunction with the dynamic age-based group analysis method provided in the above embodiments, this embodiment may also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements any of the dynamic age-based group analysis methods in the above embodiments.

[0126] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0127] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

[0128] The term "embodiment" as used in this application refers to specific features, structures, or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily mean that the embodiment is the same, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is understood, either explicitly or implicitly, by those skilled in the art that the embodiments described in this application can be combined with other embodiments when there is no conflict.

[0129] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A group analysis method based on dynamic age, characterized in that: include: generating a user group meeting a first preset condition based on the acquired activity data table; The behavior trajectory information of each target user in the user group matches the first preset condition; Analyzing the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user; The constraint chain rule is composed of multiple behavior conditions for defining key nodes in the user behavior trajectory; Based on the dynamic behavior age of each target user, an aggregate analysis is performed on each target user to obtain a corresponding aggregate index.

2. The dynamic age-based group analysis method according to claim 1, characterized in that: The generating of a user group meeting a first preset condition based on the acquired activity data table includes: Based on the obtained activity data table, a plurality of target users meeting the first preset condition are screened out; the first preset condition is used to indicate the time when the user first meets the preset behavior event; Based on the plurality of target users meeting the first preset condition, the corresponding user group is generated.

3. The dynamic age-based group analysis method according to claim 2, characterized in that: Before screening out the plurality of target users that meet the first preset condition based on the obtained activity data table, the method further includes: Based on a plurality of predefined user behavior categories, the behavior trajectory information of each user is generated; the behavior trajectory information includes at least a user identifier, a behavior category, a behavior time, and dimension data and measurement data associated with the user behavior.

4. The method for group analysis based on dynamic age according to claim 1, characterized in that: The step of analyzing the behavior trajectory information of each target user in the user group according to the preset constraint chain rule to obtain the dynamic behavior age of each target user includes: According to the preset constraint chain rules, the behavior trajectory information of each target user in the user group is analyzed by a dynamic age calculation model to obtain the dynamic behavior age of each target user; The dynamic age calculation model is used to determine the dynamic behavioral age of the target user according to the number of times the target user meets the behavioral condition specified by the constraint chain rule.

5. The method for group analysis based on dynamic age according to claim 1, characterized in that: The aggregation analysis is performed on each target user based on the dynamic behavior age of each target user to obtain corresponding aggregation indicators, including: Based on the dynamic behavior age of each target user, dividing each target user into a plurality of first groups; Aggregate analysis is performed on the target users in different first groups to obtain the aggregation index corresponding to each first group.

6. The method for group analysis based on dynamic age according to claim 5, characterized in that: The dividing the target users into a plurality of first groups based on the dynamic behavior age of each target user includes: Based on a second preset condition, each of the target users is divided into a plurality of second groups; The target users in each of the second groups are divided into a plurality of first groups based on the dynamic behavior age of each of the target users.

7. The method for group analysis based on dynamic age according to any one of claims 1 to 6, characterized in that: The method further comprises: Preprocessing the behavior trajectory information; the preprocessing includes dictionary compression and difference coding; The pre-processed behavior trajectory information is stored in column format.

8. A group analysis device based on dynamic age, characterized in that: include: A generating module, configured to generate a user group meeting a first preset condition based on the acquired activity data table; The behavior trajectory information of each target user in the user group matches the first preset condition; an analysis module, configured to analyze the behavior trajectory information of each target user in the user group according to a preset constraint chain rule to obtain the dynamic behavior age of each target user; the constraint chain rule is composed of a plurality of behavior conditions for defining key nodes in the user behavior trajectory; The aggregation module is used to perform aggregation analysis on each target user based on the dynamic behavior age of each target user to obtain a corresponding aggregation index.

9. A computer device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps of the dynamic age-based group analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the dynamic age-based group analysis method according to any one of claims 1 to 7 are implemented.

Images