E-commerce data processing method, device, medium and equipment
By screening target stores and dividing user groups in the e-commerce platform, and product recommendations are carried out based on user loyalty and feedback data, the problem of insufficient precision for deep user needs in the existing technology is solved, and the targetedness and order rate of recommendations are improved.
Patent Information
- Application Number
- CN202410568482.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-09
- Publication Date
- 2025-04-01
- Estimated Expiration
- 2044-05-09
AI Technical Summary
The existing e-commerce product recommendation methods are difficult to distinguish the needs of deep users and shallow users, resulting in insufficient recommendations for deep users, wasting shopping time and increasing after-sales risk.
By filtering stores in the target field, establishing historical user groups, dividing groups based on user loyalty, and adding users to the group with the highest adaptability, and recommending products based on feedback data within the group.
It improves the targeted product recommendations, saves users' shopping time, and increases the probability of ordering in the target store, reducing returns and after-sales risks.
Smart Images
Figure CN118691361B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of e-commerce, and in particular to an e-commerce data processing method, device, medium and equipment. Background Art
[0002] With the rapid development of science and logistics technology, e-commerce is used more and more frequently in our daily lives. There are some areas in e-commerce where customer characteristics tend to be two-level, such as Hanfu, Lolita, JK and other clothing categories. There are two customer groups with independent group characteristics. One customer group pays attention to cost performance and does not care whether it is a copy. They belong to the shallow users of this category. The other customer group attaches great importance to design and originality. Not only are they sticky to the store, but they are also relatively insensitive to price factors. They belong to the deep users of this category. For these two groups, these categories of goods (or stores) can also be divided into two areas, including the mass production area for the former, which usually has the characteristics of high cost performance and large shipments, and the original area for the latter, which has the characteristics of strong originality, high customer return rate and high price.
[0003] Although many of the product recommendation methods in the prior art are based on the needs of buyers, it is difficult to distinguish between the above two types of user needs. When the prior art is used to recommend the former, the requirements for the recommended products are not high. Even if the recommended store or product is in the original field, there is a possibility of closing the order, and there will be no dissatisfaction. When recommending the latter, including recommending to new users with deep user characteristics, if the recommended products are in the mass production field, especially imitation products, not only will the latter waste a lot of shopping time, but also the probability of closing the order is low, which is easy to cause after-sales problems. Summary of the invention
[0004] The present invention provides an e-commerce data processing method, device, medium and equipment, which solve the above-mentioned technical problems.
[0005] A first aspect of an embodiment of the present invention provides an e-commerce data processing method, comprising the following steps:
[0006] Step 1: select at least one target store from all the stores based on the preset key features of the target field, and create a target store list;
[0007] Step 2, obtaining historical user data of each target store in the target store list, and establishing at least one historical user group according to the loyalty of each historical user in the historical user data relative to the target field;
[0008] Step 3, obtaining user information and / or first search information of the user to be purchased, generating a degree of compatibility between the user to be purchased and each historical user group, and adding the user to be purchased to the target historical user group with the highest degree of compatibility;
[0009] Step 4: Acquire and publish the second search information of the user to be purchased, and generate corresponding recommended stores and / or recommended products according to the feedback data of the target historical user group for the second search information.
[0010] A second aspect of an embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the above e-commerce data processing method is implemented.
[0011] A third aspect of an embodiment of the present invention provides an e-commerce data processing device, including a computer-readable storage medium and a processor, wherein the processor implements the steps of the above e-commerce data processing method when executing a computer program on the computer-readable storage medium.
[0012] A fourth aspect of an embodiment of the present invention provides an e-commerce data processing device, including a selection module, a construction module, a grouping module and a recommendation module.
[0013] The selection module is used to select at least one target store from all the stores based on preset key features of the target field, and to establish a target store list;
[0014] The building module is used to obtain historical user data of each target store in the target store list, and to establish at least one historical user group according to the historical user data and the loyalty of each historical user in the historical user data relative to the target field;
[0015] The grouping module is used to obtain the user information and / or the first search information of the user to be purchased, and generate the degree of compatibility between the user to be purchased and each historical user group, and add the user to be purchased into the target historical user group with the highest degree of compatibility;
[0016] The recommendation module is used to obtain and publish the second search information of the user to be purchased, and generate corresponding recommended stores and / or recommended products according to the feedback data of the target historical user group for the second search information.
[0017] The present invention provides an e-commerce data processing method, device, medium and equipment, which can take deep users with high loyalty to the target field and new users with corresponding characteristics as target users, and convert the recommendation mode, that is, convert "user demand analysis and recommendation based on big data" into "recommendation based on feedback data of specific users in the target group". For the target users, the recommendation results are more targeted and shopping time is saved. For the target merchants in this field, not only the target users matching the positioning are increased, but also the shopping stickiness of the users can be increased through the guidance of the group to the target users, the order probability of the target store is improved, and the subsequent return, after-sales and other risks are reduced.
[0018] In order to make the above-mentioned objects, features and advantages of the invention more obvious and easy to understand, the preferred embodiments of the present invention are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0020] Figure 1 is a flow chart of the e-commerce data processing method provided in Example 1;
[0021] Figure 2 is a flow chart of step 2 in the e-commerce data processing method provided in Example 1;
[0022] Figure 3 is a schematic diagram of the structure of an e-commerce data processing device provided in Example 2;
[0023] Figure 4 It is a structural diagram of the e-commerce data processing device provided in Example 3. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0025] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, all within the scope of protection of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device or the flow chart. Furthermore, the words "first", "second", "third", etc. used in the present invention do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.
[0026] Figure 1 1 is a flow chart of an e-commerce data processing method provided in Example 1. Figure 1 As shown, the following steps are included:
[0027] Step 1: select at least one target store from all the stores based on the preset key features of the target field, and create a target store list;
[0028] Step 2, obtaining historical user data of each target store in the target store list, and establishing at least one historical user group according to the loyalty of each historical user in the historical user data relative to the target field;
[0029] Step 3, obtaining user information and / or first search information of the user to be purchased, generating a degree of compatibility between the user to be purchased and each historical user group, and adding the user to be purchased to the target historical user group with the highest degree of compatibility;
[0030] Step 4: Acquire and publish the second search information of the user to be purchased, and generate corresponding recommended stores and / or recommended products according to the feedback data of the target historical user group for the second search information.
[0031] The above embodiments provide an e-commerce data processing method, which can divide historical users in a target field into multiple historical user groups with increasing loyalty, and then add new and old users with corresponding user characteristics as target users into the corresponding historical user groups, thereby converting the recommendation mode, that is, converting "user demand analysis and recommendation based on big data" into "recommendation based on feedback data of specific users in the target group". For the target users, the recommendation results are more targeted and save shopping time. For the target merchants in this field, not only the target users matching the positioning are increased, but also the shopping stickiness of the users can be increased through the guidance of the groups to the target users, thereby improving the probability of ordering in the target stores and reducing the risks of subsequent returns and after-sales services.
[0032] Each of the above steps is described in detail below through specific embodiments.
[0033] The target domain in the embodiment of the present application is aimed at the deep user group, that is, the group described in the background technology that "attaches great importance to design sense and originality, not only has high store stickiness, but is relatively insensitive to price factors". For this user group, the key features of the target domain can be pre-set, including: specific keywords included in store promotion or product promotion, such as "original" and similar words; product names include specific product style words, such as "Princess Changle" and "Cream Sweet Cheese"; the average price of the product is in a higher range, such as 25%-70% higher than the similar store with the highest number of views (or shipments), etc. Then, at least one target store can be screened out from all the stores through the preset key features, and a target store list can be established, and these target stores can be used as recommended stores for target new and old users.
[0034] Then proceed to step 2. Figure 2 In a specific embodiment, step 2 includes S201-S204.
[0035] Step 201, first obtain the historical user data of each target store in the target store list. The historical users here are defined as users who have placed valid orders (i.e., orders that have been completed and have no return records) in each target store, and the historical user data includes the browsing time, collection time, purchase quantity, number of pre-sales consultations and / or number of after-sales consultations of each historical user in each target store.
[0036] Specifically, the browsing time refers to the browsing time of each historical user in the corresponding target store before forming an order; the collection time refers to the collection time of the corresponding purchased goods in the shopping cart of each historical user; the purchase quantity refers to the total amount of goods purchased by each historical user in each target store; the number of pre-sales consultations refers to the number of consultations for the purchased goods by each historical user in the corresponding target store before forming an order; the number of after-sales consultations refers to the number of return and exchange consultations for the purchased goods by each historical user in the corresponding target store after forming an order. Preferably, if the historical user has multiple purchased goods in the corresponding target store, the browsing time, collection time, number of pre-sales consultations and / or number of after-sales consultations in the above historical user data are the average values of the corresponding data of all purchased goods.
[0037] Then, the loyalty of each historical user relative to the target domain is generated according to the historical user data, and at least one historical user group is established, which specifically includes the following steps:
[0038] S202: Generate a first loyalty of each historical user relative to a corresponding target store based on the historical user data, and establish a first loyalty set for each target store. Specifically:
[0039] Get the adjacent superordinate domain corresponding to the target domain. The adjacent superordinate domain here refers to the closest (smallest) category to which the target domain belongs. For example, the category of clothing can be divided into four categories: underwear, home furnishings, formal wear, and daily wear. Daily wear can be divided into regular styles and special styles. Special styles are divided into Hanfu, JK, Lolita, etc., and the Hanfu category can be divided into regular domains that serve shallow users and original domains that serve deep users. In a specific embodiment, when the target domain is limited to the original domain corresponding to deep users in the Hanfu category, the adjacent superordinate domain is the Hanfu domain.
[0040] Then calculate the initial loyalty of each historical user to the corresponding target store. The initial loyalty here is mainly determined by the total amount of goods purchased by the historical user in the target store. It can be calculated using the following formula: Initial loyalty Y ’ =A1 / A2, where A1 is the number of purchases by the historical user in the target store, such as the number of Hanfu purchased in the target store, and A2 is the number of purchases by the historical user in the adjacent upper-level field, such as the total number of Hanfu purchased in the shopping record of the historical user.
[0041] Finally, a correction coefficient is generated based on the browsing time, collection time, number of pre-sales consultations and / or number of after-sales consultations, and the correction coefficient is used to adjust the initial loyalty Y ’ Correction is performed to generate the first loyalty Y. Generally speaking, the shorter the browsing time, the collection time and the fewer the number of pre-sales consultations, the more the historical user knows about the purchased target products and the greater the preference, so the first loyalty is higher; and the fewer the number of after-sales consultations, the higher the historical user's satisfaction with the purchased products, so the first loyalty will also be higher. In a specific embodiment, a correction coefficient table can be pre-set, and the correction coefficient table sets corresponding correction coefficients according to different intervals of browsing time, collection time, number of pre-sales consultations and / or number of after-sales consultations. In this way, the actual correction coefficient can be obtained by looking up the table, thereby calculating the corresponding first loyalty.
[0042] When the first loyalty of each historical user relative to the corresponding target store is obtained, the first loyalty set of each target store can be established. For example, the first loyalty set of target store n is recorded as {Y 1n , Y 2n ………Y in}, where Y in Represents the first loyalty of historical user i to target store n.
[0043] Then, S203 is executed to generate a second loyalty of each historical user relative to the target domain according to the first loyalty set corresponding to all target stores in the target store list. In a specific embodiment, the following steps are included:
[0044] Obtain the first loyalty sets corresponding to all target stores in the target store list, including the first loyalty set corresponding to target store 1 {Y 11 , Y 21 ………Y i1}、The first loyalty set corresponding to target store 2 {Y 12 , Y 22 ………Y i2}, and the first loyalty set {Y 1n , Y 2n ………Y in}.
[0045] Traverse all first loyalty sets, and select target historical users whose similarity reaches the first preset threshold, and the target historical users have corresponding first loyalty to multiple target stores. This step analyzes user identities, such as account numbers, addresses, etc., to determine whether there are target historical users with the same / similar account numbers or addresses in multiple target stores. These target historical users have historical shopping records in multiple different target stores, and therefore have higher loyalty to the target area.
[0046] Finally, the second loyalty is calculated for the target historical user and other historical users. For the target historical user, the calculation formula of the second loyalty is:
[0047] M=R1*Y i1 +R2*Y i2 +………R n *Y in ,
[0048] Where R1, R2...R n They represent the weight coefficients corresponding to the first target store, the second target store, and the nth target store respectively. The weight coefficient is usually determined according to the store popularity. The greater the store popularity value calculated by the store opening years, store ranking, and store evaluation data, the higher the weight coefficient. i1 , Y i2 ………Y in They represent the first loyalty of the target historical user i to the first target store, the second target store, and the nth target store. If the target historical user i does not shop at the third target store, the corresponding first loyalty Y i3 The value is 0. Therefore, for the target historical user 1, its second loyalty to the target field can be recorded as R1*Y 11 +R2*Y 12 +………R n *Y 1n .
[0049] For other users, that is, users who have shopping records in only one target store in the list, the unique first loyalty will be used as the second loyalty relative to the target area.
[0050] Finally, S204 is executed. First, multiple historical user groups are preset, and the multiple historical user groups correspond to different second loyalty intervals. Then, each historical user is divided into a corresponding preset historical user group according to the target interval of the second loyalty of each historical user. In this way, different user groups are constructed. Users in the group can recommend each other, and the recommendation range is naturally limited to the range of the target store in the list. At the same time, new users can be attracted to increase customer stickiness.
[0051] When new and old users, that is, users waiting to purchase, conduct shopping searches, the users waiting to purchase are first added to the corresponding group, and then stores or products that better meet the user's needs can be recommended through internal group recommendations.
[0052] In a specific embodiment, the step 3 specifically includes the following steps:
[0053] Obtain the user information and / or first search information of the user to be purchased. Specifically, the user information includes the identity information (such as gender, age, occupation, address, etc.) of the user to be purchased and / or historical shopping information in the target field. The first search information includes product category, product style, store name, product image and / or product image source information. Product images are usually seen and saved by users on specific platforms, such as Weibo, Xiaohongshu, WeChat groups, QQ groups, etc., and watermarks are automatically generated when saving images on these platforms. Therefore, watermark recognition and analysis of the image can immediately obtain specific product image source information.
[0054] Then, it is determined whether the user to be purchased has joined any historical user group according to the user information, such as account number, address, etc. If so, the historical user group that has been joined is used as the target historical user group.
[0055] If not, it means that the user to be purchased is a new user in the target field, and the following judgment process is continued: judge whether the user information and / or the first search information meets any preset conditions, such as whether the store name is in the target store list, whether the source of the product image matches the preset source (such as QQ group, WeChat group), and whether the product style matches the styles on sale in any target store. If any condition is met, it means that the new user has a certain understanding of the target field and the selected search keywords are also targeted, or it means that the new user is in the relevant QQ group or WeChat group in the target field, and is recommended to search for products, so the user can be marked as a potential user and added to the second lowest loyalty target historical user group.
[0056] If any of the preset conditions is not met, the predicted loyalty is generated based on the identity information of the user to be purchased. For example, when the user to be purchased is a designer or has a strong purchasing power, the generated predicted loyalty is relatively large. In this way, when the predicted loyalty is greater than the preset value, the user to be purchased is added as a potential user to the second target historical user group with the lowest loyalty.
[0057] Finally, step 4 is executed, that is, searching and recommending within the group. In a specific embodiment, step 4 is specifically as follows:
[0058] The second search information of the user to be purchased is obtained, and the second search information is published to the corresponding target historical user group, wherein the second search information includes product category, product style and / or product image. The second search information can be new search information or simplified information of the first search information.
[0059] Then, feedback data for the second search information in the target historical user group is obtained, the feedback data including recommended shops and / or recommended products in the target store list whose similarity with the product category, the product style and / or the product image is higher than a second preset threshold;
[0060] Finally, the corresponding recommended store link and / or recommended product link is displayed to make the recommendation results more targeted, which not only saves the shopping time of the target users, but also increases the target users who match the positioning for the target merchants in this field. At the same time, by guiding the target users by groups, the shopping stickiness of the users is increased, the probability of orders in the target stores is improved, and the risks of subsequent returns, after-sales and other risks are reduced.
[0061] In a preferred embodiment, an updating step is further included, specifically: Step 1-Step 2 is repeatedly executed at preset intervals to update the target store list and the data of the historical user group, thereby further improving the accuracy of the recommendation results.
[0062] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.
[0063] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the above-mentioned e-commerce data processing method is implemented.
[0064] Figure 3 is a schematic diagram of the structure of the e-commerce data processing device provided in Example 2. Figure 3 As shown, it includes a selection module 100, a construction module 200, a grouping module 300 and a recommendation module 400.
[0065] The selection module 100 is used to select at least one target store from all the stores based on the preset key features of the target field, and to establish a target store list;
[0066] The construction module 200 is used to obtain the historical user data of each target store in the target store list, and to establish at least one historical user group according to the loyalty of each historical user in the historical user data relative to the target field;
[0067] The grouping module 300 is used to obtain the user information and / or the first search information of the user to be purchased, and generate the degree of compatibility between the user to be purchased and each historical user group, and add the user to be purchased into the target historical user group with the highest degree of compatibility;
[0068] The recommendation module 400 is used to obtain and publish the second search information of the user to be purchased, and generate corresponding recommended stores and / or recommended products according to the feedback data of the target historical user group for the second search information.
[0069] The above embodiment provides an e-commerce data processing device, which can divide the historical users of the target field into multiple historical user groups with increasing loyalty, and then add new and old users with corresponding user characteristics as target users into the corresponding historical user groups, so as to convert the recommendation mode, that is, convert "user demand analysis and recommendation based on big data" into "recommendation based on feedback data of specific users in the target group". For the target users, the recommendation results are more targeted and save shopping time. For the target merchants in this field, not only the target users matching the positioning are increased, but also the shopping stickiness of the users can be increased through the guidance of the groups to the target users, the order probability of the target store can be improved, and the subsequent returns, after-sales and other risks can be reduced.
[0070] In a preferred embodiment, the construction module 200 specifically includes:
[0071] A first acquisition unit is used to acquire historical user data of each target store in the target store list, wherein the historical user data includes browsing time, collection time, purchase quantity, number of pre-sales consultations and / or number of after-sales consultations corresponding to each historical user;
[0072] A first loyalty calculation unit, configured to generate a first loyalty of each historical user relative to a corresponding target store according to the historical user data, and establish a first loyalty set for each target store;
[0073] A second loyalty calculation unit, configured to generate a second loyalty of each historical user relative to a target domain according to a first loyalty set corresponding to all target stores in the target store list;
[0074] The user classification unit is configured to classify each historical user into a corresponding preset historical user group according to the target interval where the second loyalty lies.
[0075] In a preferred embodiment, the first loyalty calculation unit specifically includes:
[0076] A second acquisition unit is used to acquire an adjacent superordinate domain corresponding to the target domain;
[0077] The first calculation unit is used to calculate the initial loyalty of each historical user relative to the corresponding target store, where the initial loyalty Y ’ =A1 / A2, where A1 is the number of purchases made by the historical user in the target store, and A2 is the number of purchases made by the historical user in the adjacent upper domain;
[0078] A correction unit is used to generate a correction coefficient according to the browsing time, the collection time, the number of pre-sales consultations and / or the number of after-sales consultations, and use the correction coefficient to correct the initial loyalty to generate the first loyalty Y.
[0079] In a preferred embodiment, the second loyalty calculation unit specifically includes:
[0080] A third acquisition unit is used to acquire a first loyalty set corresponding to all target stores in the target store list;
[0081] A user selection unit, configured to traverse all first loyalty sets and screen out target historical users whose similarity reaches a first preset threshold, wherein the target historical users have corresponding first loyalty to the plurality of target stores respectively;
[0082] The second calculation unit is used to generate, for the target historical user, a second loyalty of the target historical user relative to the target field according to the corresponding multiple first loyalty; for other historical users, use the only corresponding first loyalty as their second loyalty relative to the target field.
[0083] In a preferred embodiment, the second loyalty M=R1*Y i1 +R2*Y i2 +………R n *Y in , where R1, R2………R n They represent the weight coefficients corresponding to the first target store, the second target store, and the nth target store, respectively. i1 , Y i2 ………Y in They respectively represent the first loyalty of target historical user i to the first target store, the second target store, and so on to the nth target store.
[0084] In a preferred embodiment, the grouping module 300 specifically includes:
[0085] A fourth acquisition unit, used to acquire the user information of the user to be purchased and / or the first search information;
[0086] A first judgment unit is used to judge whether the user to be purchased has joined any historical user group according to the user information, and if so, the historical user group that has been joined is used as the target historical user group, and if not, the next step is executed;
[0087] The second judgment unit is used to judge whether the user information and / or the first search information meets any preset condition. If so, the user to be purchased is added to the second target historical user group with the lowest loyalty; if not, the predicted loyalty is generated according to the identity information. When the predicted loyalty is greater than a preset value, the user to be purchased is added to the second target historical user group with the lowest loyalty.
[0088] In a preferred embodiment, the recommendation module 400 specifically includes:
[0089] An information publishing unit, used for acquiring second search information of the user to be purchased, and publishing the second search information to a corresponding target historical user group, wherein the second search information includes commodity category, commodity style and / or commodity picture;
[0090] A recommendation unit, configured to obtain feedback data for the second search information in the target historical user group, the feedback data including recommended shops and / or recommended products in the target shop list whose similarity with the product category, the product style and / or the product image is higher than a second preset threshold;
[0091] The display unit is used to display corresponding recommended store links and / or recommended product links.
[0092] An embodiment of the present invention further provides an e-commerce data processing device, comprising a computer-readable storage medium and a processor, wherein the processor implements the steps of the above-mentioned e-commerce data processing method when executing a computer program on the computer-readable storage medium.
[0093] Figure 4 is a schematic diagram of the structure of an e-commerce data processing device provided by Embodiment 3 of the present invention. Figure 4 As shown, the e-commerce data processing device 8 of this embodiment includes: a processor 80, a readable storage medium 81, and a computer program 82 stored in the readable storage medium 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned method embodiments are implemented, for example Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of each module in the above-mentioned device embodiments are realized, for example Figure 3 The functions of modules 100 to 400 are shown.
[0094] Exemplarily, the computer program 82 may be divided into one or more modules, which are stored in the readable storage medium 81 and executed by the processor 80 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 82 in the e-commerce data processing device 8.
[0095] The e-commerce data processing device 8 may include, but is not limited to, a processor 80 and a readable storage medium 81. Those skilled in the art will appreciate that Figure 4 It is only an example of the e-commerce data processing device 8 and does not constitute a limitation of the e-commerce data processing device 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the e-commerce data processing device may also include a power management module, an operation processing module, input and output devices, a network access device, a bus, etc.
[0096] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0097] The readable storage medium 81 may be an internal storage unit of the e-commerce data processing device 8, such as a hard disk or memory of the e-commerce data processing device 8. The readable storage medium 81 may also be an external storage device of the e-commerce data processing device 8, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the e-commerce data processing device 8. Further, the readable storage medium 81 may also include both an internal storage unit and an external storage device of the e-commerce data processing device 8. The readable storage medium 81 is used to store the computer program and other programs and data required by the e-commerce data processing device. The readable storage medium 81 may also be used to temporarily store data that has been output or is to be output.
[0098] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0099] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0100] Those of ordinary skill in the art will appreciate that the units and method 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 the present invention.
[0101] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0102] 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.
[0103] In addition, each functional unit in each embodiment of the present invention 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0104] The present invention is not limited to what is described in the specification and implementation modes, and therefore additional advantages and modifications can be easily realized by those skilled in the art. Therefore, without departing from the spirit and scope of the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details, representative devices, and illustrative examples shown and described herein.
Claims
1. An e-commerce data processing method, characterized in that: The following steps are involved: Step 1: select at least one target store from all the stores based on preset key features of the target field, and create a target store list, wherein the preset key features include specific keywords in store promotion or product promotion, specific product style words in product names, and average prices of products in a relatively high range; Step 2, obtaining historical user data of each target store in the target store list, and establishing at least one historical user group according to the loyalty of each historical user in the historical user data relative to the target field; Step 3, obtaining the user information and the first search information of the user to be purchased, generating the degree of compatibility between the user to be purchased and each historical user group, and adding the user to be purchased into the target historical user group with the highest degree of compatibility; Step 4, obtain and publish the second search information of the user to be purchased, and generate corresponding recommended stores and / or recommended products based on the feedback data of the second search information in the target historical user group, wherein the second search information is new search information or information obtained by simplifying the first search information, and the feedback data includes recommended stores and / or recommended products in the target store list whose similarity with the product category, product style and / or product image is higher than a second preset threshold.
2. The electronic commerce data processing method according to claim 1, characterized in that: The step of obtaining the historical user data of each target store in the target store list and establishing at least one historical user group according to the loyalty of each historical user in the historical user data relative to the target field specifically includes the following steps: S201, obtaining historical user data of each target store in the target store list, wherein the historical user data includes browsing time, collection time, purchase quantity, number of pre-sales consultations and / or number of after-sales consultations corresponding to each historical user; S202, generating a first loyalty of each historical user relative to a corresponding target store according to the historical user data, and establishing a first loyalty set for each target store; S203, generating a second loyalty of each historical user relative to the target domain according to the first loyalty set corresponding to all target stores in the target store list; S204: Classify each historical user into a corresponding preset historical user group according to the target interval of the second loyalty.
3. The electronic commerce data processing method according to claim 2, characterized in that: The generating of the first loyalty of each historical user relative to the corresponding target store according to the historical user data is specifically: Obtaining the adjacent superordinate domain corresponding to the target domain; Calculate the initial loyalty of each historical user to the corresponding target store, the initial loyalty Y ’ =A1 / A2, where A1 is the number of purchases made by the historical user in the target store, and A2 is the number of purchases made by the historical user in the adjacent upper domain; A correction coefficient is generated according to the browsing time, the collection time, the number of pre-sales consultations and / or the number of after-sales consultations, and the initial loyalty is corrected using the correction coefficient to generate the first loyalty Y.
4. The electronic commerce data processing method according to claim 2, characterized in that: The generating of the second loyalty of each historical user relative to the target domain according to the first loyalty set corresponding to all target stores in the target store list is specifically: Obtaining a first loyalty set corresponding to all target stores in the target store list; Traversing all first loyalty sets, screening out target historical users whose similarity reaches a first preset threshold, wherein the target historical users have corresponding first loyalty to multiple target stores respectively; For the target historical user, generating a second loyalty of the target historical user relative to the target domain according to the corresponding plurality of first loyaltys; For other historical users, the unique corresponding first loyalty is used as their second loyalty relative to the target domain.
5. The electronic commerce data processing method according to claim 4, characterized in that: The generating of the second loyalty of the target historical user relative to the target domain according to the corresponding plurality of first loyaltys is specifically: The second loyalty M=R1*Y i1 +R2*Y i2 +………R n *Y in , where R1, R2………R n They represent the weight coefficients corresponding to the first target store, the second target store, and the nth target store, respectively. i1 , Y i2 ………Y in They respectively represent the first loyalty of target historical user i to the first target store, the second target store, and so on to the nth target store.
6. The electronic commerce data processing method according to any one of claims 2 to 5, characterized in that: The step of adding the user to be purchased into the target historical user group with the highest adaptability is specifically as follows: Acquiring user information and / or first search information of the user to be purchased; Determine whether the user to be purchased has joined any historical user group according to the user information, if so, use the historical user group that has been joined as the target historical user group, if not, execute the next step; Determine whether the user information and / or the first search information meets any preset condition. If so, add the user to be purchased into the second target historical user group with the lowest loyalty; if not, generate a predicted loyalty based on the user information. When the predicted loyalty is greater than a preset value, add the user to be purchased into the second target historical user group with the lowest loyalty.
7. The electronic commerce data processing method according to claim 6, characterized in that: The generating corresponding recommended stores and / or recommended products according to the feedback data of the target historical user group for the second search information is specifically: Acquire the second search information of the user to be purchased, and publish the second search information to the corresponding target historical user group, wherein the second search information includes product category, product style and / or product picture; Acquire feedback data for the second search information in the target historical user group, the feedback data including recommended shops and / or recommended products in the target store list whose similarity with the product category, the product style and / or the product image is higher than a second preset threshold; Display the corresponding recommended store links and / or recommended product links.
8. An e-commerce data processing device, based on the e-commerce data processing method according to any one of claims 1 to 7, characterized in that: It includes selection module, construction module, grouping module and recommendation module. The selection module is used to select at least one target store from all the stores based on preset key features of the target field, and to establish a target store list; The building module is used to obtain the historical user data of each target store in the target store list, and to establish at least one historical user group according to the loyalty of each historical user in the historical user data relative to the target field; The grouping module is used to obtain the user information and / or the first search information of the user to be purchased, and generate the degree of compatibility between the user to be purchased and each historical user group, and add the user to be purchased into the target historical user group with the highest degree of compatibility; The recommendation module is used to obtain and publish the second search information of the user to be purchased, and generate corresponding recommended stores and / or recommended products according to the feedback data of the target historical user group for the second search information.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the e-commerce data processing method described in any one of claims 1 to 7 is implemented.
10. An electronic commerce data processing device, characterized in that: The method comprises a computer-readable storage medium and a processor, wherein the processor implements the steps of the e-commerce data processing method according to any one of claims 1 to 7 when executing the computer program on the computer-readable storage medium.