Big data-based user behavior analysis method, system, and program product
By collecting and processing big data on user behavior, constructing a behavior matrix and profiles, the problem of not being able to accurately obtain prominent user behavior characteristics in existing technologies has been solved, realizing intelligent analysis and precise services for user behavior.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUANGZHOU HUMMINGBIRD NOTE TECHNOLOGY CO LTD
- Filing Date
- 2026-03-06
- Publication Date
- 2026-05-29
AI Technical Summary
In existing technologies, user analysis is mainly based on basic user attributes and preference information, which cannot accurately obtain users' prominent behavioral characteristics, resulting in the inability to accurately recommend relevant services.
By collecting big data on user behavior, performing quantitative processing and matrix construction, calculating convergence parameters, selecting prominent behavior types, and constructing user behavior profiles.
It enables efficient and accurate analysis of prominent user behavior types, builds highly relevant behavioral profiles, and improves user experience and service accuracy.
Smart Images
Figure CN122114993A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of data analysis technology, specifically relating to user behavior analysis methods, systems, and program products based on big data. Background Technology
[0002] With the development of internet and big data technologies, user behavior data on internet platforms is constantly growing. This data has significant application value for the design and optimization of marketing service systems. Marketing service systems can recommend relevant services based on user behavior data to improve user satisfaction and stickiness. However, current user analysis on various platforms is mostly based on the analysis of basic user attribute information and preferred content information, which cannot accurately reflect the degree of emphasis on various user behaviors or accurately identify prominent user behavioral characteristics. Summary of the Invention
[0003] The purpose of this invention is to provide a user behavior analysis method, system, and program product based on big data to solve the aforementioned problems in the prior art.
[0004] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, it provides user behavior analysis methods based on big data, including: Collect a large dataset of target user behavior over various time periods. The large dataset of behavior includes several behavior types and the corresponding behavior parameters for each behavior type. The behavioral parameters corresponding to each behavioral type in the behavioral big data set are quantified to obtain the corresponding behavioral quantification dataset, which contains several behavioral types and the quantified behavioral parameters corresponding to each behavioral type. A behavioral data matrix for the target user is constructed using various behavioral quantification datasets. Each column of the behavioral data matrix corresponds to a behavior type, and the quantified behavioral parameters of different rows in each column come from different behavioral quantification datasets. The data transformation process is performed on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data. Then, each quantized behavioral parameter in the behavioral data matrix is replaced with the corresponding element data to obtain the standard data matrix. Calculate the convergence parameter of each element in the standard data matrix relative to other elements in the same row, and replace each element in the standard data matrix with the corresponding convergence parameter to obtain the behavior space matrix; The salience index of each behavior type is calculated using the behavior space matrix, and the behavior types with the highest salience index are selected as the salience behavior types of the target user. Construct a behavioral profile of the target user by utilizing the prominent behavioral types of the target user, and output the behavioral profile of the target user.
[0005] In one possible design, the quantification of behavioral parameters corresponding to each behavioral type in the behavioral big data set includes: The behavioral parameters corresponding to each behavioral type in the behavioral big data set are substituted into the parameter quantification table corresponding to each behavioral type for matching, and the quantified behavioral parameters corresponding to each behavioral type are determined. The parameter quantification table contains several behavioral parameter ranges under the corresponding behavioral type, as well as the quantified behavioral parameters associated with each behavioral parameter range.
[0006] In one possible design, constructing the target user's behavioral data matrix using various behavioral quantification datasets includes: Determine the behavior type and behavior quantification dataset corresponding to each quantified behavior parameter; A behavior data matrix C is constructed based on each quantified behavior parameter, the corresponding behavior type, and the behavior quantification dataset. The behavior data matrix is as follows:
[0007] Where m represents the maximum index of the behavior quantization dataset, n represents the maximum index of the behavior type, and c mn This represents the quantized behavior parameter corresponding to behavior type n in the behavior quantization dataset m.
[0008] In one possible design, the process of performing data transformation on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data, and replacing each quantized behavioral parameter in the behavioral data matrix with the corresponding element data to obtain a standard data matrix, includes: Calculate the average value Q of the quantized behavioral parameters in each column of the behavioral data matrix. j Q j =(c 1j +c 2j +…+c mj ) / m, 1≤j≤n; The average value Q of the behavioral parameters quantified in each column of the behavioral data matrix. j Calculate the mean absolute deviation S of the quantified behavioral parameters in each column of the behavioral data matrix. j S j =(|c 1j -Q j |+|c 2j -Q j |+…+|c mj -Q j |) / m,1≤j≤n; The average value Q of the behavioral parameters is quantified using each column of the behavioral data matrix. j and mean absolute deviation S jThe data is converted into parameters in the data matrix to obtain the corresponding element data x. ij x ij =(c ij -Q j ) / S j , 1≤i≤m, 1≤j≤n; Replace each quantized behavioral parameter in the behavioral data matrix with its corresponding element data x. ij The standard data matrix C' is obtained, and the standard data matrix is as follows: .
[0009] In one possible design, the convergence parameter of each element in the computed standard data matrix relative to other elements in the same row includes: Take a certain element x from the standard data matrix ij Substituting the data of the element and other elements in the same row into a preset convergence parameter formula, we obtain the element data x. ij The convergence parameter, relative to the convergence parameter of other elements in the same row, is calculated as follows:
[0010] Where, d ij Represents element data x ij The convergence parameter relative to other elements in the same row is 1≤i≤m, 1≤j≤n.
[0011] In one possible design, the space matrix is: .
[0012] In one possible design, the calculation of the salience index for each behavior type using the behavior space matrix includes: Calculate the sum of convergence parameters for each behavior type column in the behavior space matrix, and use the sum of convergence parameters for each behavior type column as the prominence index of the corresponding behavior type.
[0013] Secondly, it provides a user behavior analysis system based on big data, including a data acquisition unit, a quantification processing unit, a matrix construction unit, a transformation processing unit, a parameter calculation unit, a behavior filtering unit, and a profile generation unit, wherein: The data acquisition unit is used to collect a large dataset of target user behavior over various time periods. The large dataset of behavior includes several behavior types and the behavior parameters corresponding to each behavior type. The quantization processing unit is used to quantify the behavioral parameters corresponding to each behavioral type in the behavioral big data set to obtain the corresponding behavioral quantization dataset. The behavioral quantization dataset contains several behavioral types and the quantized behavioral parameters corresponding to each behavioral type. The matrix construction unit is used to construct a behavioral data matrix of the target user using various behavioral quantification datasets. Each column of the behavioral data matrix corresponds to a behavioral type, and the quantified behavioral parameters of different rows in each column come from different behavioral quantification datasets. The conversion processing unit is used to perform data conversion processing on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data, and replace each quantized behavioral parameter in the behavioral data matrix with the corresponding element data to obtain a standard data matrix. The parameter calculation unit is used to calculate the convergence parameter of each element in the standard data matrix relative to other elements in the same row, and replace each element in the standard data matrix with the corresponding convergence parameter to obtain the behavior space matrix. The behavior filtering unit is used to calculate the prominence index of each behavior type using the behavior space matrix, and select the behavior types with the highest prominence index as the prominence behavior types of the target user. The profile generation unit is used to construct a behavioral profile of the target user by utilizing the prominent behavioral types of the target user, and output the behavioral profile of the target user.
[0014] Thirdly, it provides a user behavior analysis system based on big data, including: Memory, used to store instructions; The processor is configured to read instructions stored in the memory and execute any one of the big data-based user behavior analysis methods described in the first aspect above, according to the instructions.
[0015] Fourthly, a computer-readable storage medium is provided, on which instructions are stored, which, when executed on a computer, cause the computer to perform any one of the big data-based user behavior analysis methods described in the first aspect. Simultaneously, a computer program product is also provided, which, when executed on a computer, performs any one of the big data-based user behavior analysis methods described in the first aspect.
[0016] Beneficial Effects: This invention utilizes big data technology to collect and process user behavior data across different time periods. It constructs a behavior data matrix using quantified behavior parameters, then transforms this matrix to obtain a standard data matrix. Based on this standard matrix, it performs convergence calculations and behavior space matrix construction analysis to determine the prominence index of each behavior type. Finally, it selects the behavior types with the highest prominence indices as prominent behavior types to construct user behavior profiles, enabling intelligent analysis of user behavior. This invention can efficiently and accurately analyze users' prominent behavior types based on their behavior data across different time periods, thereby constructing highly relevant behavior profiles for users. This facilitates subsequent precise user classification and targeted services, improving user experience. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the method in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the system configuration in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the system configuration in Embodiment 3 of the present invention. Detailed Implementation
[0019] It should be noted that the descriptions of these embodiments are intended to aid in understanding the invention and do not constitute a limitation thereof. The specific structural and functional details disclosed herein are merely for describing exemplary embodiments of the invention. However, the invention may be embodied in many alternative forms and should not be construed as being limited to the embodiments described herein.
[0020] It should be understood that, unless otherwise explicitly specified and limited, the corresponding terms should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments according to the specific circumstances.
[0021] Specific details are provided in the following description to provide a complete understanding of the exemplary embodiments. However, those skilled in the art will understand that the exemplary embodiments can be implemented without these specific details. For example, apparatus may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other embodiments, well-known processes, structures, and techniques may be omitted with non-essential details to avoid obscuring the embodiments.
[0022] Example 1: This embodiment provides a user behavior analysis method based on big data, which can be applied to corresponding data servers, such as... Figure 1 As shown, the method includes the following steps: S1. Collect a large dataset of target user behavior over various time periods. The large dataset of behavior includes several behavior types and corresponding behavior parameters for each behavior type.
[0023] In practice, the data server can collect a large dataset of target user behavior over various time periods using big data technology (such as web scraping or database collection). The large dataset of behavior includes several behavior types and corresponding behavior parameters for each behavior type. Behavior types may include clicking, viewing, collecting, forwarding, commenting, etc. The behavior parameter corresponding to the click behavior type can be set to the number of clicks, the behavior parameter corresponding to the viewing behavior type can be set to the viewing duration, and so on.
[0024] S2. Quantify the behavioral parameters corresponding to each behavioral type in the behavioral big data set to obtain the corresponding behavioral quantification dataset, which contains several behavioral types and the quantified behavioral parameters corresponding to each behavioral type.
[0025] In practice, the data server can preprocess the large datasets of each behavior (such as data cleaning), and then substitute the behavioral parameters corresponding to each behavior type in the large datasets of behavior into the parameter quantization table corresponding to each behavior type for matching, thereby determining the quantified behavioral parameters corresponding to each behavior type. The parameter quantization table contains several behavioral parameter ranges under the corresponding behavior type, as well as the quantified behavioral parameters associated with each behavioral parameter range. This results in the behavioral quantization dataset corresponding to each large dataset of behavior, which contains several behavior types and the quantified behavioral parameters corresponding to each behavior type.
[0026] S3. Construct a behavior data matrix for the target user using various behavior quantification datasets. Each column of the behavior data matrix corresponds to a behavior type, and the quantified behavior parameters of different rows in each column come from different behavior quantification datasets.
[0027] In practice, the data server first determines the behavior type and behavior quantization dataset corresponding to each quantized behavior parameter; then, it constructs a behavior data matrix C based on each quantized behavior parameter, its corresponding behavior type, and the behavior quantization dataset. Each column of the behavior data matrix corresponds to a behavior type, and the quantized behavior parameters in different rows of each column come from different behavior quantization datasets. The behavior data matrix can be represented as:
[0028] Where m represents the maximum index of the behavior quantization dataset, n represents the maximum index of the behavior type, and c mn This represents the quantized behavior parameter corresponding to behavior type n in the behavior quantization dataset m.
[0029] S4. Perform data transformation processing on each quantized behavior parameter in the behavior data matrix to obtain the corresponding element data, and replace each quantized behavior parameter in the behavior data matrix with the corresponding element data to obtain the standard data matrix.
[0030] In practice, the data server can first calculate the average value Q of the quantized behavioral parameters in each column of the behavioral data matrix. j Q j =(c 1j +c 2j +…+c mj ) / m, 1≤j≤n; then quantify the average value Q of the behavioral parameters in each column of the behavioral data matrix. j Calculate the mean absolute deviation S of the quantified behavioral parameters in each column of the behavioral data matrix. j S j =(|c 1j -Q j |+|c 2j -Q j |+…+|c mj -Q j |) / m,1≤j≤n; then use the average value Q of the behavioral parameters in each column of the behavioral data matrix to quantize the behavior parameters. j and mean absolute deviation S j The data is converted into parameters in the data matrix to obtain the corresponding element data x. ij x ij =(c ij -Q j ) / S j 1≤i≤m, 1≤j≤n; finally, replace each quantized behavioral parameter in the behavioral data matrix with the corresponding element data x. ij The standard data matrix C' is obtained, which can be represented as: .
[0031] S5. Calculate the convergence parameter of each element in the standard data matrix relative to other elements in the same row, and replace each element in the standard data matrix with the corresponding convergence parameter to obtain the behavior space matrix.
[0032] In practice, the data server can use a specific element x from the standard data matrix. ij Substituting the data of the element and other elements in the same row into a preset convergence parameter formula, we obtain the element data x. ij The convergence parameter, relative to the convergence parameter of other elements in the same row, is calculated as follows:
[0033] Where, d ij Represents element data x ij The convergence parameter relative to other elements in the same row is 1≤i≤m, 1≤j≤n.
[0034] Then, each element in the standard data matrix is replaced with the corresponding convergence parameter to obtain the behavior space matrix, which is: .
[0035] S6. Calculate the prominence index of each behavior type using the behavior space matrix, and select the behavior types with the highest prominence index as the prominence behavior types of the target user.
[0036] In practice, the data server can first calculate the sum of convergence parameters for each behavior type column in the behavior space matrix, and use the sum of convergence parameters for each behavior type column as the prominence index of the corresponding behavior type. Then, select the behavior types with the highest prominence indices as the prominence behavior types of the target user.
[0037] S7. Construct a behavioral profile of the target user by utilizing the prominent behavioral types of the target user, and output the behavioral profile of the target user.
[0038] In practice, the data server can construct a behavioral profile of the target user by using various prominent behavioral types of the target user, and then archive and output the behavioral profile of the target user so that users can be accurately classified and provided with targeted services based on the behavioral profile of the target user in the future, thereby improving the user experience.
[0039] This method can efficiently and accurately analyze users' prominent behavior types based on their behavioral data at different time periods, thereby building a highly relevant behavioral profile for users. This allows for precise user classification and targeted services to improve user experience.
[0040] Example 2: This embodiment provides a user behavior analysis system based on big data, such as Figure 2 As shown, it includes a data acquisition unit, a quantization processing unit, a matrix construction unit, a transformation processing unit, a parameter calculation unit, a behavior filtering unit, and a profile generation unit, wherein: The data acquisition unit is used to collect a large dataset of target user behavior over various time periods. The large dataset of behavior includes several behavior types and the behavior parameters corresponding to each behavior type. The quantization processing unit is used to quantify the behavioral parameters corresponding to each behavioral type in the behavioral big data set to obtain the corresponding behavioral quantization dataset. The behavioral quantization dataset contains several behavioral types and the quantized behavioral parameters corresponding to each behavioral type. The matrix construction unit is used to construct a behavioral data matrix of the target user using various behavioral quantification datasets. Each column of the behavioral data matrix corresponds to a behavioral type, and the quantified behavioral parameters of different rows in each column come from different behavioral quantification datasets. The conversion processing unit is used to perform data conversion processing on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data, and replace each quantized behavioral parameter in the behavioral data matrix with the corresponding element data to obtain a standard data matrix. The parameter calculation unit is used to calculate the convergence parameter of each element in the standard data matrix relative to other elements in the same row, and replace each element in the standard data matrix with the corresponding convergence parameter to obtain the behavior space matrix. The behavior filtering unit is used to calculate the prominence index of each behavior type using the behavior space matrix, and select the behavior types with the highest prominence index as the prominence behavior types of the target user. The profile generation unit is used to construct a behavioral profile of the target user by utilizing the prominent behavioral types of the target user, and output the behavioral profile of the target user.
[0041] Example 3: This embodiment provides a user behavior analysis system based on big data, such as Figure 3 As shown, at the hardware level, it includes: The data interface is used to establish data communication between the processor and external data terminals; Memory, used to store instructions; The processor is used to read instructions stored in the memory and execute the user behavior analysis method in Embodiment 1 according to the instructions.
[0042] Optionally, the system also includes an internal bus, through which the processor, memory, and data interface can be interconnected. This internal bus can be a PCIe (Peripheral Component Interconnect Eexpress) bus, which can be divided into an address bus, a data bus, a control bus, etc. The memory can include, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Flash Memory, First Input First Output (FIFO), and / or First In Last Out (FILO). The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0043] Example 4: This embodiment provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the user behavior analysis method described in Embodiment 1. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
[0044] This embodiment also provides a computer program product that, when run on a computer, executes the user behavior analysis method described in Embodiment 1. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
[0045] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A user behavior analysis method based on big data, characterized in that, include: Collect a large dataset of target user behavior over various time periods. The large dataset of behavior includes several behavior types and the corresponding behavior parameters for each behavior type. The behavioral parameters corresponding to each behavioral type in the behavioral big data set are quantified to obtain the corresponding behavioral quantification dataset, which contains several behavioral types and the quantified behavioral parameters corresponding to each behavioral type. A behavioral data matrix for the target user is constructed using various behavioral quantification datasets. Each column of the behavioral data matrix corresponds to a behavior type, and the quantified behavioral parameters of different rows in each column come from different behavioral quantification datasets. The data transformation process is performed on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data. Then, each quantized behavioral parameter in the behavioral data matrix is replaced with the corresponding element data to obtain the standard data matrix. Calculate the convergence parameter of each element in the standard data matrix relative to other elements in the same row, and replace each element in the standard data matrix with the corresponding convergence parameter to obtain the behavior space matrix; The salience index of each behavior type is calculated using the behavior space matrix, and the behavior types with the highest salience index are selected as the salience behavior types of the target user. Construct a behavioral profile of the target user by utilizing the prominent behavioral types of the target user, and output the behavioral profile of the target user.
2. The user behavior analysis method based on big data according to claim 1, characterized in that, The quantitative processing of behavioral parameters corresponding to each behavioral type in the behavioral big data set includes: The behavioral parameters corresponding to each behavioral type in the behavioral big data set are substituted into the parameter quantification table corresponding to each behavioral type for matching, and the quantified behavioral parameters corresponding to each behavioral type are determined. The parameter quantification table contains several behavioral parameter ranges under the corresponding behavioral type, as well as the quantified behavioral parameters associated with each behavioral parameter range.
3. The user behavior analysis method based on big data according to claim 1, characterized in that, The construction of the target user's behavioral data matrix using various behavioral quantification datasets includes: Determine the behavior type and behavior quantification dataset corresponding to each quantified behavior parameter; A behavior data matrix C is constructed based on each quantified behavior parameter, the corresponding behavior type, and the behavior quantification dataset. The behavior data matrix is as follows: Where m represents the maximum index of the behavior quantization dataset, n represents the maximum index of the behavior type, and c mn This represents the quantized behavior parameter corresponding to behavior type n in the behavior quantization dataset m.
4. The user behavior analysis method based on big data according to claim 3, characterized in that, The process of performing data transformation on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data, and then replacing each quantized behavioral parameter in the behavioral data matrix with the corresponding element data to obtain a standard data matrix includes: Calculate the average value Q of the quantized behavioral parameters in each column of the behavioral data matrix. j Q j =(c 1j +c 2j +…+c mj ) / m, 1≤j≤n; The average value Q of the behavioral parameters quantified in each column of the behavioral data matrix. j Calculate the mean absolute deviation S of the quantified behavioral parameters in each column of the behavioral data matrix. j S j =(|c 1j -Q j |+|c 2j -Q j |+…+|c mj -Q j |) / m,1≤j≤n; The average value Q of the behavioral parameters is quantified using each column of the behavioral data matrix. j and mean absolute deviation S j The data is converted into parameters in the data matrix to obtain the corresponding element data x. ij x ij =(c ij -Q j ) / S j , 1≤i≤m, 1≤j≤n; Replace each quantized behavioral parameter in the behavioral data matrix with its corresponding element data x. ij The standard data matrix C' is obtained, and the standard data matrix is as follows: 。 5. The user behavior analysis method based on big data according to claim 4, characterized in that, The convergence parameter of each element in the standard data matrix relative to other elements in the same row includes: Take a certain element x from the standard data matrix ij Substituting the data of the element and other elements in the same row into a preset convergence parameter formula, we obtain the element data x. ij The convergence parameter, relative to the convergence parameter of other elements in the same row, is calculated as follows: Where, d ij Represents element data x ij The convergence parameter relative to other elements in the same row is 1≤i≤m, 1≤j≤n.
6. The user behavior analysis method based on big data according to claim 5, characterized in that, The space matrix is: 。 7. The user behavior analysis method based on big data according to claim 1, characterized in that, The calculation of the prominence index for each behavior type using the behavior space matrix includes: Calculate the sum of convergence parameters for each behavior type column in the behavior space matrix, and use the sum of convergence parameters for each behavior type column as the prominence index of the corresponding behavior type.
8. A user behavior analysis system based on big data, characterized in that: It includes a data acquisition unit, a quantization processing unit, a matrix construction unit, a transformation processing unit, a parameter calculation unit, a behavior filtering unit, and a profile generation unit, among which: The data acquisition unit is used to collect a large dataset of target user behavior over various time periods. The large dataset of behavior includes several behavior types and the behavior parameters corresponding to each behavior type. The quantization processing unit is used to quantify the behavioral parameters corresponding to each behavioral type in the behavioral big data set to obtain the corresponding behavioral quantization dataset. The behavioral quantization dataset contains several behavioral types and the quantized behavioral parameters corresponding to each behavioral type. The matrix construction unit is used to construct a behavioral data matrix of the target user using various behavioral quantification datasets. Each column of the behavioral data matrix corresponds to a behavioral type, and the quantified behavioral parameters of different rows in each column come from different behavioral quantification datasets. The conversion processing unit is used to perform data conversion processing on each quantized behavioral parameter in the behavioral data matrix to obtain the corresponding element data, and replace each quantized behavioral parameter in the behavioral data matrix with the corresponding element data to obtain a standard data matrix. The parameter calculation unit is used to calculate the convergence parameter of each element in the standard data matrix relative to other elements in the same row, and replace each element in the standard data matrix with the corresponding convergence parameter to obtain the behavior space matrix. The behavior filtering unit is used to calculate the prominence index of each behavior type using the behavior space matrix, and select the behavior types with the highest prominence index as the prominence behavior types of the target user. The profile generation unit is used to construct a behavioral profile of the target user by utilizing the prominent behavioral types of the target user, and output the behavioral profile of the target user.
9. A user behavior analysis system based on big data, characterized in that: include: Memory, used to store instructions; A processor is configured to read instructions stored in the memory and execute the user behavior analysis method based on big data as described in any one of claims 1-7 according to the instructions.
10. A computer program product, characterized in that, When the computer program product is run on a computer, it performs the user behavior analysis method based on big data as described in any one of claims 1-7.