Product screening display method and platform based on user portrait

Abstract

The invention discloses a product screening display method and platform based on a user portrait, and relates to the technical field of data processing. The method comprises the steps that search information is acquired, and historical product browsing records and historical product purchasing records of a target user are called; analyzing and acquiring browsing quality sensitivity, browsing logistics sensitivity, purchasing quality sensitivity and purchasing logistics sensitivity of the target user according to the historical browsing product record and the historical purchasing product record, and calculating to obtain quality sensitivity and logistics sensitivity; searching to obtain a product set according to the search information, and screening and optimizing products in the product set according to the quality sensitivity and the logistics sensitivity to obtain an optimal display product set; and performing product display to the target user according to the optimal display product set. The technical problem of poor user experience caused by inaccurate product recommendation in the prior art is solved, the products are accurately screened and displayed based on the user portrait, and the technical effect of improving the user satisfaction is achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a product screening and display method and platform based on user portraits. Background Art

[0002] In today's digital age, e-commerce platforms have become one of the main channels for consumers to shop. As user needs become increasingly diversified and personalized, how to effectively display products that meet user interests and needs has become an important challenge facing e-commerce platforms. At present, the product display methods of most e-commerce platforms mainly rely on simple search keyword matching and recommendation algorithms based on group behavior, lacking in-depth analysis of individual user behavior characteristics. This approach often leads to recommendation results that are inconsistent with users' real needs, affecting users' shopping experience. Summary of the invention

[0003] This application provides a product screening and display method and platform based on user portraits, which solves the technical problem in the prior art that product recommendations are not accurate enough, resulting in poor user experience.

[0004] In view of the above problems, the embodiments of the present application provide a product screening and display method and platform based on user portraits.

[0005] In a first aspect of the present application, a method for screening and displaying products based on user portraits is provided, the method comprising: In response to the search needs of the target user, the search information is obtained, and the historical product browsing records and historical product purchase records of the target user are retrieved; based on the historical product browsing records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated; based on the search information, a product set is retrieved and obtained, and based on the quality sensitivity and logistics sensitivity, product screening and optimization are performed within the product set to obtain an optimal display product set; according to the optimal display product set, products are displayed to the target user.

[0006] The second aspect of the present application provides a product screening and display platform based on user portraits, the platform comprising: Information acquisition module: in response to the search needs of the target user, the search information is acquired, and the historical product browsing records and historical product purchase records of the target user are retrieved; User sensitivity analysis module: based on the historical product browsing records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and acquired, and the quality sensitivity and logistics sensitivity are calculated; Product screening and optimization module: based on the search information, a product set is retrieved and acquired, and based on the quality sensitivity and logistics sensitivity, the product screening and optimization is performed within the product set to obtain the optimal display product set; Product display module: products are displayed to the target user according to the optimal display product set.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, in response to the search needs of the target user, the search information is obtained, and the historical browsing product records and historical product purchase records of the target user are retrieved. Next, based on the historical browsing product records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated. Further, based on the search information, the product set is retrieved and obtained, and the products are screened and optimized within the product set based on the quality sensitivity and logistics sensitivity to obtain the optimal display product set. Finally, the products are displayed to the target user according to the optimal display product set. The technical problem of poor user experience caused by inaccurate product recommendations in the prior art is solved, and the products are accurately screened and displayed based on user portraits, achieving the technical effect of improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of the process flow of the product screening and display method based on user portrait provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a product screening and display platform based on user portraits provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: information acquisition module 11, user sensitivity analysis module 12, product screening and optimization module 13, product display module 14. DETAILED DESCRIPTION

[0011] The embodiments of the present application solve the technical problem in the prior art that product recommendations are not accurate enough, resulting in poor user experience, by providing a product screening and display method and platform based on user portraits.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a product screening and display method based on user portraits, wherein the method includes: In response to the search needs of the target user, the search information is obtained, and the historical browsing product records and historical purchasing product records of the target user are retrieved.

[0015] When a user issues a search request, the search request of the target user is received and parsed to obtain the search information; at the same time, the target user's historical browsing product records and historical purchase product records are retrieved. These records contain the user's browsing behavior data on the platform (such as the type of products browsed, browsing time, frequency, etc.) and purchase behavior data (such as the category, quantity, brand, price range, etc. of the products purchased), laying the foundation for subsequent user preference analysis and personalized recommendations.

[0016] Furthermore, in response to the search demand of the target user, the search information is obtained, and the historical browsing product records and historical purchasing product records of the target user are retrieved, including: In response to the search needs of the target user, the search information is obtained, wherein the search information includes the search product category; the browsed products and purchased products browsed by the target user within a preset historical time range are retrieved to obtain the historical browsed product records and the historical purchased product records.

[0017] Specifically, by responding to the search needs of target users, we extract the search information submitted by users, where the search information includes the user's explicit or implicit search product categories, such as the type, brand, price range, functional features, etc. of the target product; then, based on the user's unique identifier (such as account or device ID), we retrieve the target user's browsing and purchase records within a preset historical time range (such as the last month or three months) to obtain historical browsing product records and historical purchase product records, where historical browsing product records include information such as product categories, brands, browsing frequency, and browsing time that users have browsed on the platform, while historical purchase product records include data such as product categories, brands, quantities, price ranges, and purchase times that users have purchased. By obtaining the user's search information and the above historical records, a data foundation is laid for subsequent sensitivity analysis, product screening optimization, and personalized product display.

[0018] According to the historical product browsing records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated.

[0019] By analyzing the historical browsing records of products, combined with factors such as the type, brand, price range, browsing time, and browsing frequency of the products browsed, the quality sensitivity and logistics sensitivity of the target users in the browsing stage are calculated. Among them, the browsing quality sensitivity reflects the user's attention to the product quality-related information (such as brand, evaluation, material, etc.) when browsing; the browsing logistics sensitivity reflects the user's attention to the logistics-related information (such as delivery time, logistics service evaluation, etc.) when browsing. Secondly, by analyzing the historical purchase records of products, combined with the category, brand, price range, purchase frequency of the purchased products, and the logistics service feedback after purchase, the quality sensitivity and logistics sensitivity of the target users in the purchase stage are calculated. Among them, the purchase quality sensitivity reflects the user's attention to the product quality-related attributes in the purchase decision, and the purchase logistics sensitivity reflects the user's attention to the logistics service-related factors in the purchase decision. By comprehensively analyzing the target user's browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity, and purchase logistics sensitivity, a weighted calculation is performed to obtain the user's overall quality sensitivity and logistics sensitivity, which provides key parameters for subsequent product screening optimization.

[0020] Furthermore, according to the historical product browsing records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated, including: Extract the first historically browsed product from the historically browsed product record, and calculate and analyze the quality sensitivity and logistics sensitivity of the first browsed product according to the logistics time of the first historically browsed product and similar products; continue to analyze and obtain multiple quality sensitivities of browsed products and multiple logistics sensitivities of browsed products according to the historically browsed product record, and calculate the average to obtain the browsing quality sensitivity and browsing logistics sensitivity; analyze and calculate multiple quality sensitivities of purchased products and multiple logistics sensitivities of purchased products of multiple historically purchased products in the historically purchased product record, and calculate the average to obtain the purchase quality sensitivity and purchase logistics sensitivity; calculate the average of the browsing quality sensitivity and the purchase quality sensitivity to obtain the quality sensitivity, and calculate the average of the browsing logistics sensitivity and the purchase logistics sensitivity to obtain the logistics sensitivity.

[0021] Extract the first historically browsed product of the target user from the historically browsed product records, and calculate and analyze the first browsed product quality sensitivity and the first browsed product logistics sensitivity by combining the attributes of the first historically browsed product (such as brand, price range, evaluation, etc.) and the logistics time of similar products (such as delivery time, logistics evaluation, etc.); further analyze the historically browsed product records of the target user, calculate the browsed product quality sensitivity and browsed product logistics sensitivity corresponding to multiple historically browsed products one by one, and calculate the mean of these sensitivities by statistical methods to obtain the browsed quality sensitivity and browsed logistics sensitivity of the target user respectively; perform the historical purchase product records of the target user Analysis: Based on the attributes of historically purchased products (such as actual purchased brands, price ranges, user reviews, etc.) and the logistics performance during the purchase process (such as delivery time, logistics service quality, etc.), the purchase product quality sensitivity and purchase product logistics sensitivity of multiple historically purchased products are calculated one by one, and the average of multiple product quality sensitivities and multiple purchase product logistics sensitivities are calculated respectively through statistical methods to obtain the purchase quality sensitivity and purchase logistics sensitivity of the target user; the quality sensitivity of the target user is obtained by calculating the average of the browsing quality sensitivity and the purchasing quality sensitivity; the logistics sensitivity of the target user is obtained by calculating the average of the browsing logistics sensitivity and the purchasing logistics sensitivity.

[0022] Furthermore, extracting a first historically browsed product from the historically browsed product records, and calculating and analyzing the first historically browsed product quality sensitivity and the first historically browsed product logistics sensitivity based on the logistics time of the first historically browsed product and similar products, including: The first historically browsed product is extracted from the historically browsed product record to obtain the maximum logistics time and the minimum logistics time of the same type of products as the first historically browsed product; the first browsed product logistics time of the first historically browsed product is obtained, and the absolute value of the difference between the first browsed product logistics time and the maximum logistics time is calculated to obtain the first logistics time difference; the difference between the maximum logistics time and the minimum logistics time is calculated to obtain the maximum difference, and the ratio of the first logistics time difference to the maximum difference is calculated to obtain the logistics sensitivity of the first browsed product; 1 is subtracted from the logistics sensitivity of the first browsed product to obtain the quality sensitivity of the first browsed product.

[0023] In the historically browsed product records, firstly, the first historically browsed product is extracted, and the logistics time data of similar products of the first historically browsed product are obtained, and the maximum logistics time and the minimum logistics time therein are extracted, which are recorded as the maximum logistics time and the minimum logistics time respectively; then, the actual logistics time of the first historically browsed product is obtained, and the absolute value of the difference between the actual logistics time and the maximum logistics time is calculated to obtain the first logistics time difference; further, the difference between the maximum logistics time and the minimum logistics time of similar products is calculated to obtain the maximum difference, and the ratio of the first logistics time difference to the maximum difference is calculated to obtain the logistics sensitivity of the first browsed product; finally, the quality sensitivity of the first browsed product is obtained by subtracting the logistics sensitivity of the first browsed product from 1.

[0024] According to the search information, a product set is retrieved and obtained, and according to the quality sensitivity and logistics sensitivity, the products in the product set are screened and optimized to obtain the optimal display product set.

[0025] According to the search information of the target user, the product library of the platform is searched to obtain a product set that matches the user's search needs. This set contains all candidate products that meet the search information; then, the product set is screened and optimized based on the quality sensitivity and logistics sensitivity of the target user. In the screening and optimization process, the quality-related attributes of the product (such as brand, evaluation score, material, etc.) are sorted according to the quality sensitivity, and products that match the user's quality preference are given priority; at the same time, the logistics-related attributes of the product (such as delivery time, logistics service evaluation, etc.) are sorted according to the logistics sensitivity, and products that meet the user's logistics needs are given priority. Through the weight calculation of comprehensive quality sensitivity and logistics sensitivity, the products that best match the user's personalized needs are screened out to generate the optimal display product set.

[0026] Further, according to the search information, a product set is retrieved and obtained, and according to the quality sensitivity and logistics sensitivity, product screening and optimization are performed within the product set to obtain an optimal display product set, including: According to the search information, multiple products that meet the search information are retrieved to construct a product set; multiple first products are randomly selected in the product set to construct a first display product set; according to the quality sensitivity and logistics sensitivity, the first display fitness of the first display product set is analyzed and calculated; the product screening and optimization is continued in the product set until convergence, and the display product set with the largest display fitness is output to obtain the optimal display product set.

[0027] Specifically, according to the search information of the target user, multiple products that meet the search information are retrieved from the platform product library, and the initial product set is constructed based on this; then, multiple first products are randomly selected from the product set to construct the first display product set; then, according to the user's quality sensitivity and logistics sensitivity, the fitness of the first display product set is analyzed and calculated, where the first display fitness reflects the degree of match between the display product set and the user's preference. After calculating the first display fitness, further screening and optimization are performed within the product set, and the display product set is repeatedly optimized by adjusting the combination of product selections, and the display fitness of the new display product set generated in each iteration is calculated. In the optimization process, the screening and sorting are based on the weights of quality sensitivity and logistics sensitivity to ensure that the screened products meet the user's concern for product quality and the user's demand for logistics services. The optimization process will continue until the display fitness reaches the convergence condition, that is, no higher fitness value is generated. Finally, the display product set with the largest display fitness is output as the optimal display product set for personalized product display to the target user.

[0028] Furthermore, analyzing and calculating the first display adaptability of the first display product set according to the quality sensitivity and logistics sensitivity includes: Analyze and calculate multiple first display product quality sensitivities and multiple first display product logistics sensitivities of multiple first display products in the first display product set; calculate and obtain the first display adaptability of the first display product set based on the multiple first display product quality sensitivities and multiple first display product logistics sensitivities, combined with the quality sensitivity and logistics sensitivity.

[0029] Specifically, multiple first display products in the first display product set are analyzed, and the corresponding first display product quality sensitivity and first display product logistics sensitivity are calculated for each first display product one by one; the first display product quality sensitivity and the first display product logistics sensitivity respectively reflect the degree of matching of each product with users in terms of quality attributes (such as brand, evaluation, material, etc.) and logistics attributes (such as delivery time, service quality, etc.); according to the overall quality sensitivity and logistics sensitivity of the target users, the user preferences are matched and analyzed with the multiple first display product quality sensitivities and multiple first display product logistics sensitivities in the first display product set, and the first display fitness of the first display product set is obtained by calculation. The first display fitness reflects the degree of matching of the entire first display product set with user preferences. The first display fitness value is used to evaluate the recommendation effect of the first display product set, provide data basis for subsequent screening and optimization, and ensure that the final displayed product set can meet user needs to a higher degree.

[0030] Furthermore, according to the multiple first display product quality sensitivities and the multiple first display product logistics sensitivities, the first display fitness of the first display product set is calculated and obtained by combining the quality sensitivity and logistics sensitivity, as shown in the following formula: ; Wherein, ZSF is the display fitness, M is the number of multiple first display products in the first display product set, and M is an integer greater than 1. is the first display product quality sensitivity of the i-th first display product, is the quality sensitivity of the target users, is the first display product logistics sensitivity of the i-th first display product, Logistics sensitivity of target users.

[0031] By formula , calculate the first display fitness of the first display product set, where ZSF is the display fitness, M is the number of multiple first display products in the first display product set, and M is an integer greater than 1, is the first display product quality sensitivity of the i-th first display product, is the quality sensitivity of the target users, is the first display product logistics sensitivity of the i-th first display product, Logistics sensitivity of target users.

[0032] The first part of the formula quantifies the deviation of the displayed products in terms of quality matching by comparing the quality sensitivity of each first displayed product with the quality sensitivity of the target user; the second part quantifies the deviation of the displayed products in terms of logistics matching by comparing the logistics sensitivity of each first displayed product with the logistics sensitivity of the target user. The smaller the deviation, the higher the display fitness value, reflecting that the displayed product set is more in line with the preferences of the target user.

[0033] Products are displayed to the target users according to the optimal display product set.

[0034] According to the optimized optimal display product set, personalized product display is provided to the target users to ensure that the recommendation results are highly matched with user needs. Specifically, by analyzing the target user's device type (such as mobile phone, tablet or computer), display interface layout and user behavior preferences (such as waterfall flow arrangement or classification and grouping display), the optimal display product set is presented in a way that best suits user habits; the display content includes key information of the product, such as name, picture, price, brand, evaluation, logistics service information, etc. At the same time, it can prioritize the features related to user concerns (such as high-quality products or fast delivery options) based on user sensitivity.

[0035] In summary, the embodiments of the present application have at least the following technical effects: First, in response to the search needs of the target user, the search information is obtained, and the historical browsing product records and historical product purchase records of the target user are retrieved. Next, based on the historical browsing product records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated. Further, based on the search information, the product set is retrieved and obtained, and the products are screened and optimized within the product set based on the quality sensitivity and logistics sensitivity to obtain the optimal display product set. Finally, the products are displayed to the target user according to the optimal display product set. The technical problem of poor user experience caused by inaccurate product recommendations in the prior art is solved, and the products are accurately screened and displayed based on user portraits, achieving the technical effect of improving user satisfaction.

[0036] Embodiment 2 is based on the same inventive concept as the product screening and display method based on user portraits in the above embodiment. Figure 2 As shown, this application provides a product screening and display platform based on user portraits. The platform includes: Information acquisition module 11: in response to the search needs of the target user, the search information is obtained, and the historical browsing product records and historical product purchase records of the target user are retrieved; User sensitivity analysis module 12: based on the historical browsing product records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated; Product screening and optimization module 13: based on the search information, a product set is retrieved and obtained, and based on the quality sensitivity and logistics sensitivity, the product screening and optimization is performed within the product set to obtain the optimal display product set; Product display module 14: products are displayed to the target user according to the optimal display product set.

[0037] Furthermore, the information acquisition module 11 is used to execute the following method: In response to the search needs of the target user, the search information is obtained, wherein the search information includes the search product category; the browsed products and purchased products browsed by the target user within a preset historical time range are retrieved to obtain the historical browsed product records and the historical purchased product records.

[0038] Furthermore, the user sensitivity analysis module 12 is used to perform the following method: Extract the first historically browsed product from the historically browsed product record, and calculate and analyze the quality sensitivity and logistics sensitivity of the first browsed product according to the logistics time of the first historically browsed product and similar products; continue to analyze and obtain multiple quality sensitivities of browsed products and multiple logistics sensitivities of browsed products according to the historically browsed product record, and calculate the average to obtain the browsing quality sensitivity and browsing logistics sensitivity; analyze and calculate multiple quality sensitivities of purchased products and multiple logistics sensitivities of purchased products of multiple historically purchased products in the historically purchased product record, and calculate the average to obtain the purchase quality sensitivity and purchase logistics sensitivity; calculate the average of the browsing quality sensitivity and the purchase quality sensitivity to obtain the quality sensitivity, and calculate the average of the browsing logistics sensitivity and the purchase logistics sensitivity to obtain the logistics sensitivity.

[0039] Furthermore, the user sensitivity analysis module 12 is used to perform the following method: The first historically browsed product is extracted from the historically browsed product record to obtain the maximum logistics time and the minimum logistics time of the same type of products as the first historically browsed product; the first browsed product logistics time of the first historically browsed product is obtained, and the absolute value of the difference between the first browsed product logistics time and the maximum logistics time is calculated to obtain the first logistics time difference; the difference between the maximum logistics time and the minimum logistics time is calculated to obtain the maximum difference, and the ratio of the first logistics time difference to the maximum difference is calculated to obtain the logistics sensitivity of the first browsed product; 1 is subtracted from the logistics sensitivity of the first browsed product to obtain the quality sensitivity of the first browsed product.

[0040] Furthermore, the product screening and optimization module 13 is used to perform the following method: According to the search information, multiple products that meet the search information are retrieved to construct a product set; multiple first products are randomly selected in the product set to construct a first display product set; according to the quality sensitivity and logistics sensitivity, the first display fitness of the first display product set is analyzed and calculated; the product screening and optimization is continued in the product set until convergence, and the display product set with the largest display fitness is output to obtain the optimal display product set.

[0041] Furthermore, the product screening and optimization module 13 is used to perform the following method: Analyze and calculate multiple first display product quality sensitivities and multiple first display product logistics sensitivities of multiple first display products in the first display product set; calculate and obtain the first display adaptability of the first display product set based on the multiple first display product quality sensitivities and multiple first display product logistics sensitivities, combined with the quality sensitivity and logistics sensitivity.

[0042] Furthermore, the product screening and optimization module 13 is used to perform the following method: According to the multiple first display product quality sensitivities and the multiple first display product logistics sensitivities, combined with the quality sensitivity and logistics sensitivity, the first display fitness of the first display product set is calculated and obtained as follows: ; Wherein, ZSF is the display fitness, M is the number of multiple first display products in the first display product set, and M is an integer greater than 1, is the first display product quality sensitivity of the i-th first display product, is the quality sensitivity of the target users, is the first display product logistics sensitivity of the i-th first display product, Logistics sensitivity of target users.

[0043] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0044] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0045] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A product screening and display method based on user portraits, characterized in that: The method comprises: In response to the search needs of the target user, the search information is obtained, and the historical browsing product records and historical purchasing product records of the target user are retrieved; Analyze and obtain the browsing quality sensitivity, browsing logistics sensitivity, purchasing quality sensitivity and purchasing logistics sensitivity of the target user according to the historical product browsing records and historical product purchase records, and calculate and obtain the quality sensitivity and logistics sensitivity; Retrieve and obtain a product set according to the search information, and perform product screening and optimization within the product set according to the quality sensitivity and logistics sensitivity to obtain an optimal display product set; Products are displayed to the target users according to the optimal display product set.

2. The product screening and display method based on user portrait according to claim 1 is characterized in that: In response to the search needs of the target user, the search information is obtained, and the historical browsing product records and historical purchase product records of the target user are retrieved, including: In response to the search demand of the target user, obtaining search information, wherein the search information includes a search product category; The browsed products and purchased products browsed by the target user within a preset historical time range are retrieved to obtain the historical browsed product records and the historical purchased product records.

3. The product screening and display method based on user portrait according to claim 1 is characterized in that: According to the historical product browsing records and historical product purchase records, the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user are analyzed and obtained, and the quality sensitivity and logistics sensitivity are calculated, including: Extracting a first historically browsed product from the historically browsed product records, and calculating and analyzing the first historically browsed product quality sensitivity and the first historically browsed product logistics sensitivity based on the logistics time of the first historically browsed product and similar products; Continue to analyze the historical product browsing records to obtain multiple product browsing quality sensitivities and multiple product browsing logistics sensitivities, and calculate the average to obtain browsing quality sensitivity and browsing logistics sensitivity; Analyze and calculate to obtain multiple product quality sensitivities and multiple product logistics sensitivities of multiple historically purchased products in the historically purchased product records, and calculate the average to obtain the purchase quality sensitivity and the purchase logistics sensitivity; The average of the browsing quality sensitivity and the purchasing quality sensitivity is calculated to obtain the quality sensitivity, and the average of the browsing logistics sensitivity and the purchasing logistics sensitivity is calculated to obtain the logistics sensitivity.

4. The product screening and display method based on user portrait according to claim 3 is characterized in that: Extracting a first historically browsed product from the historically browsed product records, and calculating and analyzing the first historically browsed product quality sensitivity and the first historically browsed product logistics sensitivity based on the logistics time of the first historically browsed product and similar products, including: Extracting a first historically browsed product from the historically browsed product record, and obtaining the maximum logistics time and minimum logistics time of products of the same type as the first historically browsed product; Obtaining the first browsed product logistics time of the first historically browsed product, calculating the absolute value of the difference between the first browsed product logistics time and the maximum logistics time, and obtaining a first logistics time difference; Calculate the difference between the maximum logistics time and the minimum logistics time to obtain the maximum difference, calculate the ratio of the first logistics time difference to the maximum difference, and obtain the logistics sensitivity of the first browsed product; The first browsed product quality sensitivity is obtained by subtracting the first browsed product logistics sensitivity from 1.

5. The product screening and display method based on user portrait according to claim 1 is characterized in that: According to the search information, a product set is retrieved and obtained, and according to the quality sensitivity and logistics sensitivity, product screening and optimization are performed within the product set to obtain an optimal display product set, including: According to the search information, multiple products matching the search information are retrieved and obtained, and a product set is constructed; Randomly selecting a plurality of first products from the product set to construct a first display product set; Analyzing and calculating the first display adaptability of the first display product set according to the quality sensitivity and logistics sensitivity; Continue to screen and optimize products within the product set until convergence, output a display product set with the greatest display fitness, and obtain an optimal display product set.

6. The product screening and display method based on user portrait according to claim 5 is characterized in that: Analyzing and calculating the first display adaptability of the first display product set according to the quality sensitivity and logistics sensitivity, including: Analyze and calculate a plurality of first display product quality sensitivities and a plurality of first display product logistics sensitivities of a plurality of first display products in the first display product set; The first display adaptability of the first display product set is calculated based on the multiple first display product quality sensitivities and the multiple first display product logistics sensitivities in combination with the quality sensitivity and the logistics sensitivity.

7. The product screening and display method based on user portrait according to claim 6 is characterized in that: According to the multiple first display product quality sensitivities and the multiple first display product logistics sensitivities, combined with the quality sensitivity and logistics sensitivity, the first display fitness of the first display product set is calculated and obtained as follows: ； Wherein, ZSF is the display fitness, M is the number of multiple first display products in the first display product set, and M is an integer greater than 1. is the first display product quality sensitivity of the i-th first display product, is the quality sensitivity of the target users, is the first display product logistics sensitivity of the i-th first display product, Logistics sensitivity of target users.

8. Product screening and display platform based on user portraits, characterized by: The platform is used to implement the product screening and display method based on user portraits according to any one of claims 1 to 7, and comprises: Information acquisition module: in response to the search needs of the target user, acquires the search information and retrieves the historical browsing product records and historical purchasing product records of the target user; User sensitivity analysis module: according to the historical product browsing records and historical product purchase records, analyze and obtain the browsing quality sensitivity, browsing logistics sensitivity, purchase quality sensitivity and purchase logistics sensitivity of the target user, and calculate and obtain the quality sensitivity and logistics sensitivity; Product screening and optimization module: retrieves and obtains a product set according to the search information, and screens and optimizes products in the product set according to the quality sensitivity and logistics sensitivity to obtain an optimal display product set; Product display module: display products to the target users according to the optimal display product set.

Images