E-commerce user analysis method and system based on big data mining
Through big data mining technology, the value and quality of e-commerce users are analyzed, and marketing strategies for different levels are formulated, which solves the problems of poor management effect of existing e-commerce platforms and the inability to respond to user changes in time, and improves user management and marketing strategies. Accuracy and practicality.
Patent Information
- Application Number
- CN202411463759.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing e-commerce platforms cannot effectively analyze and classify value levels based on users' e-commerce information, resulting in poor management results, and they cannot timely understand user dynamic changes and formulate appropriate marketing strategies.
Through the method based on big data mining, users' e-commerce information is collected, e-commerce platform tendency index, purchasing power index and purchasing frequency index are generated, data analysis models are established, user value evaluation coefficients and comprehensive quality evaluation coefficients are generated, and user value and quality are carried out. and formulate corresponding marketing strategies according to different levels.
It realizes accurate classification management of users and real-time monitoring of dynamic changes, improves the timeliness of management effects and marketing strategies, and enhances the overall practicality of the e-commerce platform.
Smart Images

Figure CN118982378A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of user analysis, and in particular to an e-commerce user analysis method and system based on big data mining. Background Art
[0002] Electronic Commerce (E-commerce for short) refers to the use of electronic communication technology and network technology to carry out business activities and realize the electronicization of various links such as production, circulation, sales, and services. It can cover various business activities, including online shopping, electronic payment, online banking, electronic auctions, online advertising, etc. E-commerce mainly includes three models: B2B (business to business), B2C (business to consumer), and C2C (consumer to consumer). The B2B model is e-commerce between businesses, that is, businesses conduct commercial activities such as procurement, sales, and logistics through the Internet; the B2C model is e-commerce between businesses, that is, businesses sell goods and services to consumers through the Internet; the C2C model is e-commerce between consumers, that is, transactions of second-hand goods are conducted through the Internet platform.
[0003] The existing technology has the following deficiencies: most of the e-commerce platforms in the existing technology manage users in a centralized and comprehensive manner. Since it is impossible to analyze the user's value level based on the user's e-commerce information, it is inconvenient to classify and manage different users, and the management effect is poor; secondly, the e-commerce platforms in the existing technology cannot accurately analyze users, cannot understand the dynamic changes of users, and cannot formulate different marketing strategies in time according to the dynamic changes of users, so the overall practicality is poor.
[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0005] The purpose of the present invention is to provide an e-commerce user analysis method and system based on big data mining to solve the problems in the above-mentioned background technology.
[0006] In order to achieve the above object, the present invention provides the following technical solution: an e-commerce user analysis method based on big data mining, comprising the following steps: Collecting users' e-commerce information based on the e-commerce big data platform, including users' historical e-commerce time information, users' purchasing power information, and users' purchase frequency information, and generating e-commerce platform tendency index, purchasing power index, and purchase frequency index based on users' consumption time information, users' purchasing power information, and users' purchase frequency information; Establish a data analysis model through the e-commerce platform preference index, purchasing power index, and purchase frequency index to generate a user value assessment coefficient; Divide the user's value according to the user value evaluation coefficient; After obtaining the user's value information, the user's quality is analyzed according to the user's value information, and a user comprehensive quality evaluation coefficient is generated. The user's comprehensive quality is divided and marked according to the user's comprehensive quality evaluation coefficient; Receive user information that has been divided and labeled based on its comprehensive quality, and formulate different marketing strategies based on the user information that has been divided and labeled based on its comprehensive quality.
[0007] Preferably, after obtaining the e-commerce platform tendency index, purchasing power index, and purchase frequency index, the e-commerce platform tendency index, purchasing power index, and purchase frequency index are calibrated as QXzi, GMzi, and PLzi, respectively.
[0008] Preferably, the user's historical e-commerce time information includes session time, average stay time, page browsing time, and search time. After collection, the session time is marked as X1, the average stay time is marked as X2, the page browsing time is marked as X3, and the search time is marked as X4; After obtaining the session duration X1, average stay duration X2, page browsing duration X3, and search duration X4, the e-commerce platform preference index is calculated according to the formula. The calculation expression is: .
[0009] Preferably, the user purchasing power information includes the purchase quantity added by the user in history, the purchase amount added by the user in history, the quantity actually purchased by the user, and the amount actually purchased by the user. After collection, the purchase quantity added by the user in history, the purchase amount added by the user in history, the quantity actually purchased by the user, and the amount actually purchased by the user are marked as Y1, Y2, M1, and M2 respectively, and the purchasing power index is calculated according to the formula. The calculation expression is: ; The purchase frequency index is directly generated through user purchase frequency information.
[0010] Preferably, after obtaining the e-commerce platform preference index QXzi, the purchasing power index GMzi, and the purchase frequency index PLzi, a data analysis model is established to generate a user value evaluation coefficient PGxi, based on the formula: ; In the formula, , , are the preset proportional coefficients of the e-commerce platform preference index, purchasing power index, and purchase frequency index, respectively, and , , Both are greater than 0.
[0011] Preferably, the user value evaluation coefficient PGxi is compared with thresholds YZ1 and YZ2, where YZ1 is less than YZ2. If the evaluation coefficient PGix is less than or equal to YZ1, the user is classified as a low-level value user. If the user value evaluation coefficient PGxi is greater than YZ1 and less than or equal to YZ2, the user is classified as a medium-level value user. If the user value evaluation coefficient PGxi is greater than YZ2, the user is classified as a high-level value user.
[0012] Preferably, the number of low-level value users, the number of medium-level value users, and the number of high-level value users in the e-commerce platform are obtained, and the number of low-level value users, the number of medium-level value users, and the number of high-level value users are marked as DDx, ZDx, and GDx, respectively. The number of low-level value users DDx, the number of medium-level value users ZDx, the number of high-level value users GDx, and the total number of users GD are used to establish a data analysis model to generate a user comprehensive quality evaluation coefficient ZPGx, based on the formula: ; In the formula, are the preset ratio coefficients of the number of low-level value users, the number of medium-level value users, the number of high-level value users, and the total number of users, respectively, and are greater than 0, is the error correction factor, and its value is 0.7695.
[0013] Preferably, the user comprehensive quality assessment coefficient ZPGx is compared with the threshold SS. If the user comprehensive quality assessment coefficient ZPGx is greater than or equal to the threshold SS, the user is classified as a high comprehensive quality user and a high comprehensive quality user mark is generated. If the user comprehensive quality assessment coefficient ZPGx is less than the threshold SS, the user is classified as a low comprehensive quality user and a low comprehensive quality user mark is generated.
[0014] Preferably, different marketing strategies customized according to user value information are as follows: When receiving high comprehensive quality user tags, no marketing strategy is formulated; When receiving a low overall quality user flag, the marketing strategy developed is as follows: Customize new customer acquisition strategies for low-level value users to attract more customers to try the product, and improve customer loyalty and purchase intention by providing a good customer experience; Customize promotional strategies for mid-level value users to increase customer purchase frequency and loyalty; For high-level value users, we customize strategies that focus on maintaining customer relationships, providing high-quality products and services, and adopt reward mechanisms to further improve customer loyalty and purchase frequency.
[0015] E-commerce user analysis system based on big data mining, including user information collection module, analysis model building module, user value level classification module, user comprehensive quality analysis module, and marketing strategy formulation module; A user information collection module collects the user's e-commerce information based on the e-commerce big data platform. The e-commerce information includes the user's historical e-commerce time information, the user's purchasing power information, and the user's purchase frequency information. The e-commerce platform tendency index, the purchasing power index, and the purchase frequency index are generated according to the user's consumption time information, the user's purchasing power information, and the user's purchase frequency information, and the e-commerce platform tendency index, the purchasing power index, and the purchase frequency index are transmitted to the analysis model establishment module; The analysis model building module builds a data analysis model through the e-commerce platform tendency index, purchasing power index, and purchase frequency index, generates a user value evaluation coefficient, and transmits the user value evaluation coefficient to the user value level classification module; The user value level classification module classifies the user's value according to the user value evaluation coefficient and transmits the classified information to the user comprehensive quality analysis module; The user comprehensive quality analysis module obtains the user's value information, analyzes the user's quality according to the user's value information, generates a user comprehensive quality evaluation coefficient, divides and marks the user's comprehensive quality according to the user comprehensive quality evaluation coefficient, and transmits the divided and marked information to the marketing strategy formulation module; The marketing strategy formulation module receives the information divided and marked by the comprehensive quality of users, and formulates different marketing strategies based on the information divided and marked by the comprehensive quality of users.
[0016] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention collects the e-commerce information of users, generates the e-commerce platform tendency index, the purchasing power index, and the purchasing frequency index through the user's historical e-commerce time information, the user's purchasing power information, and the user's purchasing frequency information, establishes a data analysis model for the e-commerce platform tendency index, the purchasing power index, and the purchasing frequency index, generates a user value evaluation coefficient, divides the users into low-level value users, medium-level value users, and high-level value users through the user value evaluation coefficient, classifies and manages users of different value levels, formulates different marketing strategies according to users of different value levels, and improves management effects; The present invention establishes a data analysis model for the number of medium-value users, the number of medium-value users, the number of high-value users, and the total number of users on the e-commerce platform, so as to evaluate the comprehensive quality of users in the e-commerce platform and monitor it in real time. When a low-comprehensive-quality user mark is received, different marketing strategies are formulated in time according to the dynamic changes of users and the value levels of users, and the marketing methods are adjusted in time, so as to timely and accurately analyze the trends of users, and then conduct real-time dynamic monitoring of the distribution of the e-commerce platform according to the changes of users. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0018] Figure 1 The present invention is a method flow chart of an e-commerce user analysis system based on big data mining.
[0019] Figure 2 This is a module diagram of the e-commerce user analysis system based on big data mining of the present invention. DETAILED DESCRIPTION
[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.
[0021] Embodiment 1 The present invention provides Figure 2 The e-commerce user analysis system based on big data mining shown includes a user information collection module, an analysis model establishment module, a user value level classification module, a user comprehensive quality analysis module, and a marketing strategy formulation module; A user information collection module collects the user's e-commerce information based on the e-commerce big data platform. The e-commerce information includes the user's historical e-commerce time information, the user's purchasing power information, and the user's purchase frequency information. The e-commerce platform tendency index, the purchasing power index, and the purchase frequency index are generated according to the user's consumption time information, the user's purchasing power information, and the user's purchase frequency information, and the e-commerce platform tendency index, the purchasing power index, and the purchase frequency index are transmitted to the analysis model establishment module; After obtaining the e-commerce platform tendency index, purchasing power index, and purchase frequency index, the user information collection module marks the e-commerce platform tendency index, purchasing power index, and purchase frequency index as QXzi, GMzi, and PLzi, respectively; The user's historical e-commerce duration information includes session duration, average stay time, page browsing time, and search time. Session duration refers to the historical duration from the user's login to the exit of the e-commerce platform. After collection, the session duration is calibrated as X1. The longer the session duration, the higher the user's trust in the e-commerce platform. Conversely, the lower the user's trust in the e-commerce platform. The average stay time refers to the historical average stay time of the user on the e-commerce platform. After collection, the average stay time is calibrated as X2. The average stay time is used to measure the user experience of the e-commerce platform. The shorter the average stay time, the less trust the user has in the content of the e-commerce platform. The lower the interest, the higher the interest of the user in the content of the e-commerce platform. The page browsing time refers to the historical length of time that the user browses the page on the e-commerce platform. After collection, the page browsing time is calibrated as X3. The longer the page browsing time, the higher the user's trust in the e-commerce platform. On the contrary, it indicates that the user's interest in the content of the e-commerce platform is lower. The search time refers to the historical length of time that the user searches on the e-commerce platform. After collection, the search time is calibrated as X4. The longer the user's search time, the higher the user's trust in the e-commerce platform. On the contrary, it indicates that the user's interest in the content of the e-commerce platform is lower. After obtaining the session duration X1, average stay duration X2, page browsing duration X3, and search duration X4, the e-commerce platform preference index is calculated according to the formula. The calculation expression is: ; From the formula, we can see that the longer the session duration, the longer the average stay time, the longer the page browsing time, and the longer the search time, that is, the greater the e-commerce platform preference index, the higher the user's preference for the e-commerce platform, and the higher the user's trust in the e-commerce platform. Conversely, the lower the user's trust in the e-commerce platform. User purchasing power information includes the purchase quantity added by the user in history, the purchase amount added by the user in history, the quantity actually purchased by the user, and the actual purchase amount of the user. After collection, the purchase quantity added by the user in history, the purchase amount added by the user in history, the quantity actually purchased by the user, and the actual purchase amount of the user are marked as Y1, Y2, M1, and M2 respectively. The purchasing power index is calculated according to the formula. The calculation expression is: ; From the formula, we can see that the greater the ratio of the purchase quantity added by the user to the actual purchase quantity, the greater the purchase amount added by the user to the actual purchase amount, that is, , The larger the value, that is, the larger the purchasing power index, indicates that the user's purchasing power on the e-commerce platform is higher, indicating that the user's trust in the e-commerce platform is higher, and vice versa, it indicates that the user's trust in the e-commerce platform is lower; User purchase frequency information refers to the number of times a user purchases a certain product or service on the platform within a certain period of time. The purchase frequency is used to measure consumers' loyalty and purchase activity to a certain product or service. The purchase frequency index is directly generated through user purchase frequency information. The higher the purchase frequency, the higher the user's loyalty and purchase activity to a certain product or service, and the higher the user's trust in the e-commerce platform. Conversely, the lower the user's trust in the e-commerce platform. The analysis model building module builds a data analysis model through the e-commerce platform tendency index, purchasing power index, and purchase frequency index, generates a user value evaluation coefficient, and transmits the user value evaluation coefficient to the user value level classification module; After obtaining the e-commerce platform preference index QXzi, purchasing power index GMzi, and purchase frequency index PLzi, a data analysis model is established to generate the user value evaluation coefficient PGxi based on the formula: ; In the formula, , , are the preset proportional coefficients of the e-commerce platform preference index, purchasing power index, and purchase frequency index, respectively, and , , All are greater than 0; The user value evaluation coefficient PGxi is used to evaluate the user's value. The higher the user's e-commerce platform preference index, the higher the purchasing power index, and the higher the purchase frequency index, that is, the higher the user value evaluation coefficient PGxi, the higher the user's value level, and vice versa; The user value level classification module classifies the user's value according to the user value evaluation coefficient and transmits the classified information to the user comprehensive quality analysis module; Compare the user value evaluation coefficient PGxi with the thresholds YZ1 and YZ2, where YZ1 is less than YZ2. If the evaluation coefficient PGix is less than or equal to YZ1, it indicates that the user value level is low, and the user is classified as a low-level value user. If the user value evaluation coefficient PGxi is greater than YZ1 and less than or equal to YZ2, it indicates that the user value level is medium, and the user is classified as a medium-level value user. If the user value evaluation coefficient PGxi is greater than YZ2, it indicates that the user value level is high, and the user is classified as a high-level value user. The user comprehensive quality analysis module obtains the user's value information, analyzes the user's quality according to the user's value information, generates a user comprehensive quality evaluation coefficient, divides and marks the user's comprehensive quality according to the user comprehensive quality evaluation coefficient, and transmits the divided and marked information to the marketing strategy formulation module; Obtain the number of low-level value users, medium-level value users, and high-level value users in the e-commerce platform, and mark the number of low-level value users, medium-level value users, and high-level value users as DDx, ZDx, and GDx, respectively. The number of low-level value users DDx, the number of medium-level value users ZDx, the number of high-level value users GDx, and the total number of users GD are used to establish a data analysis model to generate a user comprehensive quality evaluation coefficient ZPGx, based on the following formula: ; In the formula, are the preset ratio coefficients of the number of low-level value users, the number of medium-level value users, the number of high-level value users, and the total number of users, respectively, and are greater than 0, is the error correction factor, and its value is 0.7695; It should be noted that the user comprehensive quality evaluation coefficient ZPGx is used to evaluate the comprehensive quality of the user. The higher the performance value of the user comprehensive quality evaluation coefficient ZPGx, the higher the comprehensive quality of the user, and vice versa. Compare the user comprehensive quality evaluation coefficient ZPGx with the threshold SS. If the user comprehensive quality evaluation coefficient ZPGx is greater than or equal to the threshold SS, it indicates that the user's comprehensive quality is high. The user is classified as a high comprehensive quality user and a high comprehensive quality user tag is generated. If the user comprehensive quality evaluation coefficient ZPGx is less than the threshold SS, it indicates that the user's comprehensive quality is low. The user is classified as a low comprehensive quality user and a low comprehensive quality user tag is generated. The marketing strategy formulation module receives the information divided and marked by the comprehensive quality of users, and formulates different marketing strategies according to the information divided and marked by the comprehensive quality of users; Different marketing strategies customized according to user value information are as follows: When receiving high comprehensive quality user tags, no marketing strategy is formulated; When receiving a low overall quality user flag, the marketing strategy developed is as follows: Customize some new customer acquisition strategies for low-level value users, such as launching low-priced products and services to attract more customers to try them, and improve customer loyalty and purchase intention by providing a good customer experience; Customize some promotional strategies for medium-value users, such as discounts and gifts, to increase customer purchase frequency and loyalty; For high-level value users, we customize strategies that focus on maintaining customer relationships, providing high-quality products and services, and adopt some reward mechanisms to further improve customer loyalty and purchase frequency.
[0022] The present invention collects the e-commerce information of users, generates the e-commerce platform tendency index, the purchasing power index, and the purchasing frequency index through the user's historical e-commerce time information, the user's purchasing power information, and the user's purchasing frequency information, establishes a data analysis model for the e-commerce platform tendency index, the purchasing power index, and the purchasing frequency index, generates a user value evaluation coefficient, divides the users into low-level value users, medium-level value users, and high-level value users through the user value evaluation coefficient, classifies and manages users of different value levels, formulates different marketing strategies according to users of different value levels, and improves management effects; The present invention establishes a data analysis model for the number of medium-value users, the number of medium-value users, the number of high-value users, and the total number of users on the e-commerce platform, so as to evaluate the comprehensive quality of users in the e-commerce platform and monitor it in real time. When a low-comprehensive-quality user mark is received, different marketing strategies are formulated in time according to the dynamic changes of users and the value levels of users, and the marketing methods are adjusted in time, so as to timely and accurately analyze the trends of users, and then conduct real-time dynamic monitoring of the distribution of the e-commerce platform according to the changes of users.
[0023] Embodiment 2 The present invention provides as Figure 1 The e-commerce user analysis method based on big data mining shown includes the following steps: Collecting users' e-commerce information based on the e-commerce big data platform, including users' historical e-commerce time information, users' purchasing power information, and users' purchase frequency information, and generating e-commerce platform tendency index, purchasing power index, and purchase frequency index based on users' consumption time information, users' purchasing power information, and users' purchase frequency information; Establish a data analysis model through the e-commerce platform preference index, purchasing power index, and purchase frequency index to generate a user value assessment coefficient; Divide the user's value according to the user value evaluation coefficient; After obtaining the user's value information, the user's quality is analyzed according to the user's value information, and a user comprehensive quality evaluation coefficient is generated. The user's comprehensive quality is divided and marked according to the user's comprehensive quality evaluation coefficient; Receive information that is divided and marked by comprehensive quality of users, and formulate different marketing strategies based on the information that is divided and marked by comprehensive quality of users; The e-commerce user analysis method based on big data mining provided in the embodiment of the present invention is implemented by the above-mentioned e-commerce user analysis system based on big data mining. For the specific implementation method, please refer to the embodiment of the e-commerce user analysis system based on big data mining, which will not be repeated here.
[0024] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0025] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0026] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.
[0027] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.
[0028] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0029] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0030] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0031] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0032] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0033] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.
[0034] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. An e-commerce user analysis method based on big data mining, characterized in that: The following steps are involved: Collecting users' e-commerce information based on the e-commerce big data platform, including users' historical e-commerce time information, users' purchasing power information, and users' purchase frequency information, and generating e-commerce platform tendency index, purchasing power index, and purchase frequency index based on users' consumption time information, users' purchasing power information, and users' purchase frequency information; Establish a data analysis model through the e-commerce platform preference index, purchasing power index, and purchase frequency index to generate a user value assessment coefficient; Divide the user's value according to the user value evaluation coefficient; After obtaining the user's value information, the user's quality is analyzed according to the user's value information, and a user comprehensive quality evaluation coefficient is generated. The user's comprehensive quality is divided and marked according to the user's comprehensive quality evaluation coefficient; Compare the user value evaluation coefficient PGxi with the thresholds YZ1 and YZ2, where YZ1 is less than YZ2. If the evaluation coefficient PGix is less than or equal to YZ1, the user is classified as a low-level value user. If the user value evaluation coefficient PGxi is greater than YZ1 and less than or equal to YZ2, the user is classified as a medium-level value user. If the user value evaluation coefficient PGxi is greater than YZ2, the user is classified as a high-level value user. Obtain the number of low-level value users, medium-level value users, and high-level value users in the e-commerce platform, and mark the number of low-level value users, medium-level value users, and high-level value users as DDx, ZDx, and GDx, respectively. The number of low-level value users DDx, the number of medium-level value users ZDx, the number of high-level value users GDx, and the total number of users GD are used to establish a data analysis model to generate a user comprehensive quality evaluation coefficient ZPGx, based on the following formula: ; In the formula, are the preset ratio coefficients of the number of low-level value users, the number of medium-level value users, the number of high-level value users, and the total number of users, respectively, and are greater than 0, is the error correction factor, and its value is 0.7695; Receive user information that has been divided and labeled based on its comprehensive quality, and formulate different marketing strategies based on the user information that has been divided and labeled based on its comprehensive quality.
2. The e-commerce user analysis method based on big data mining according to claim 1 is characterized in that: After obtaining the e-commerce platform tendency index, purchasing power index, and purchase frequency index, the e-commerce platform tendency index, purchasing power index, and purchase frequency index are calibrated as QXzi, GMzi, and PLzi, respectively.
3. The e-commerce user analysis method based on big data mining according to claim 2 is characterized in that: The user's historical e-commerce time information includes session time, average stay time, page browsing time, and search time. After collection, the session time is marked as X1, the average stay time is marked as X2, the page browsing time is marked as X3, and the search time is marked as X4; After obtaining the session duration X1, average stay duration X2, page browsing duration X3, and search duration X4, the e-commerce platform preference index is calculated according to the formula. The calculation expression is: .
4. The e-commerce user analysis method based on big data mining according to claim 3 is characterized in that: User purchasing power information includes the purchase quantity added by the user in history, the purchase amount added by the user in history, the quantity actually purchased by the user, and the actual purchase amount of the user. After collection, the purchase quantity added by the user in history, the purchase amount added by the user in history, the quantity actually purchased by the user, and the actual purchase amount of the user are marked as Y1, Y2, M1, and M2 respectively. The purchasing power index is calculated according to the formula. The calculation expression is: ; The purchase frequency index is directly generated through user purchase frequency information.
5. The e-commerce user analysis method based on big data mining according to claim 4 is characterized in that: After obtaining the e-commerce platform preference index QXzi, purchasing power index GMzi, and purchase frequency index PLzi, a data analysis model is established to generate the user value evaluation coefficient PGxi based on the following formula: ; In the formula, , , are the preset proportional coefficients of the e-commerce platform preference index, purchasing power index, and purchase frequency index, respectively, and , , Both are greater than 0.
6. The e-commerce user analysis method based on big data mining according to claim 1 is characterized in that: The user's comprehensive quality evaluation coefficient ZPGx is compared with the threshold SS. If the user's comprehensive quality evaluation coefficient ZPGx is greater than or equal to the threshold SS, the user is classified as a high comprehensive quality user and a high comprehensive quality user tag is generated. If the user's comprehensive quality evaluation coefficient ZPGx is less than the threshold SS, the user is classified as a low comprehensive quality user and a low comprehensive quality user tag is generated.
7. The e-commerce user analysis method based on big data mining according to claim 6 is characterized in that: Different marketing strategies customized according to user value information are as follows: When receiving high comprehensive quality user tags, no marketing strategy is formulated; When receiving a low overall quality user flag, the marketing strategy developed is as follows: Customize new customer acquisition strategies for low-level value users to attract more customers to try the product, and improve customer loyalty and purchase intention by providing a good customer experience; Customize promotional strategies for mid-level value users to increase customer purchase frequency and loyalty; For high-level value users, we customize strategies that focus on maintaining customer relationships, providing high-quality products and services, and adopt reward mechanisms to further improve customer loyalty and purchase frequency.
8. An e-commerce user analysis system based on big data mining, used to implement the e-commerce user analysis method based on big data mining as described in any one of claims 1 to 7, characterized in that: It includes user information collection module, analysis model building module, user value level classification module, user comprehensive quality analysis module, and marketing strategy formulation module; A user information collection module collects the user's e-commerce information based on the e-commerce big data platform. The e-commerce information includes the user's historical e-commerce time information, the user's purchasing power information, and the user's purchase frequency information. The e-commerce platform tendency index, the purchasing power index, and the purchase frequency index are generated according to the user's consumption time information, the user's purchasing power information, and the user's purchase frequency information, and the e-commerce platform tendency index, the purchasing power index, and the purchase frequency index are transmitted to the analysis model establishment module; The analysis model building module builds a data analysis model through the e-commerce platform tendency index, purchasing power index, and purchase frequency index, generates a user value evaluation coefficient, and transmits the user value evaluation coefficient to the user value level classification module; The user value level classification module classifies the user's value according to the user value evaluation coefficient and transmits the classified information to the user comprehensive quality analysis module; The user comprehensive quality analysis module obtains the user's value information, analyzes the user's quality according to the user's value information, generates a user comprehensive quality evaluation coefficient, divides and marks the user's comprehensive quality according to the user comprehensive quality evaluation coefficient, and transmits the divided and marked information to the marketing strategy formulation module; The marketing strategy formulation module receives the information divided and marked by the comprehensive quality of users, and formulates different marketing strategies based on the information divided and marked by the comprehensive quality of users.
Citation Information
Patent Citations
Method and device for determining consumption contribution value, and storage medium
CN107665448A
Marketing design method and device for life cycle or growth characteristics and storage medium
CN110111158A
Supply chain financial platform transaction method based on block chain
CN116664288A
User product preference analysis method and system based on data security
CN116860820A
Online network sales user potential demand analysis monitoring method and system
CN116894692A
Cited By
User behavior safety early warning analysis system and method based on data feedback
CN119398886A
Digital intelligent marketing method and system applying AI large model
CN120069973A
Incentive differentiation configuration and promotion support system based on user hierarchy
CN121391345A
