Offline commodity recommendation method and related device

Abstract

The application discloses a method and related equipment for recommending offline commodities, and the method comprises the following steps: obtaining portrait data of a user and merchant information corresponding to offline payment of the user after the user completes offline payment through a payment application end; generating a matched commodity recommendation list based on the portrait data and the merchant information, and generating interactive page data based on the commodity recommendation list; and pushing the interactive page data to the payment application end of the user to display on an interactive interface of the payment application end. The technical scheme provided by the application can improve user experience in an offline payment scene.

Description

Technical Field

[0001] This application belongs to the field of product recommendation technology, and in particular relates to an offline product recommendation method and related equipment. Background Technology

[0002] With the rapid development of mobile payment technology, offline QR code payment has become the mainstream payment method in physical consumption scenarios. The offline payment function of payment applications has also simplified the payment process and improved settlement efficiency, bringing consumers a convenient basic payment experience and promoting the digital development of offline physical businesses. However, most existing offline payment scenario technical solutions only focus on the completion of payment transactions and fund settlement. The payment process has a low degree of correlation with offline consumption scenarios, and there is a lack of personalized service extensions for consumers after payment. This makes the service forms of offline payment scenarios relatively simple, making it difficult to fully explore the value of offline consumption scenarios and further enhance the consumer experience throughout the entire payment process.

[0003] Therefore, improving the user experience in offline payment scenarios has become an urgent technical problem to be solved. Summary of the Invention

[0004] Embodiments of this application provide an offline product recommendation method, apparatus, computer program product, computer-readable storage medium, and electronic device, which can at least to some extent improve the user experience in offline payment scenarios.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to a first aspect of the embodiments of this application, an offline product recommendation method is provided. The method is executed on a platform service and includes: after a user completes an offline payment at an offline merchant through a payment application, obtaining the user's profile data and the merchant information corresponding to the user's offline payment; generating a matching product recommendation list based on the profile data and the merchant information, and generating interactive page data based on the product recommendation list; and pushing the interactive page data to the user's payment application for display on the interactive interface of the payment application.

[0007] In some embodiments of this application, based on the foregoing scheme, the merchant information includes the merchant identifier corresponding to the user's current payment; generating a matching product recommendation list based on the profile data and the merchant information includes: obtaining product data associated with the merchant identifier to form a candidate product set; determining products that match the profile data from the candidate product set to form a product recommendation list.

[0008] In some embodiments of this application, based on the foregoing scheme, obtaining the product data associated with the merchant identifier includes: obtaining the geographical location of the offline merchant according to the merchant identifier; filtering the first product data entered by other merchants in the platform service within a preset radius centered on the geographical location; and merging the first product data and the second product data entered by the offline merchant in the platform service into product data associated with the merchant identifier.

[0009] In some embodiments of this application, based on the foregoing scheme, the method further includes: obtaining the business district type of the area where the offline merchant is located, the time period type corresponding to the current time, and the user's historical daily travel activity radius; and dynamically adjusting the value of the preset radius based on the business district type, time period type, and historical daily travel activity radius.

[0010] In some embodiments of this application, based on the foregoing scheme, before determining products that match the profile data from the candidate product set and forming a product recommendation list, the method further includes: performing compliance verification on the product data in the candidate product set, filtering out product data that does not comply with preset regulatory rules, regional sales restrictions, or user age matching requirements; filtering out duplicate product data that has been purchased in the user's historical purchase records, as well as product data with zero inventory, and updating the candidate product set.

[0011] In some embodiments of this application, based on the foregoing scheme, the profile data includes a first list of goods paid by the user in the current payment and / or a second list of goods paid in the past; determining the goods that match the profile data from the candidate goods set includes: obtaining a first feature tag for each goods in the first and / or second list of goods; obtaining a second feature tag for each goods in the candidate goods set; predicting the target matching degree of each goods in the candidate goods set based on the first and second feature tags using a preset matching algorithm, wherein the target matching degree is used to characterize the user's demand for the goods; sorting the goods in the candidate goods set in descending order of target matching degree, selecting a preset number of the top-ranked goods, and generating a corresponding product recommendation list.

[0012] In some embodiments of this application, based on the aforementioned scheme, the step of predicting the target matching degree of each product in the candidate product set using a preset matching algorithm based on the first feature label and the second feature label includes: for each product in the candidate product set, calculating the overlap degree between the first feature label of each product in the first product list and the second feature label of each product, and assigning a first weight to the maximum overlap degree to obtain the first matching degree of each product; calculating the overlap degree between the first feature label of each product in the second product list and the second feature label of each product, and assigning a second weight to the maximum overlap degree to obtain the second matching degree of each product, wherein the second weight is less than the first weight; and determining the maximum value of the first matching degree and the second matching degree as the target matching degree of each product.

[0013] In some embodiments of this application, based on the foregoing scheme, the method further includes: in response to the user clicking on any product in the interactive interface, obtaining the product information of the product and the geographical location of the merchant to which the product belongs; and pushing the product information of the product and the geographical location of the merchant to which the product belongs to the user's payment application.

[0014] According to a second aspect of the embodiments of this application, an offline product recommendation device is provided. The device is configured on a platform service and includes: an acquisition unit, configured to acquire user profile data and merchant information corresponding to the user's offline payment after the user completes an offline payment through a payment application; a generation unit, configured to generate a matching product recommendation list based on the profile data and the merchant information, and generate interactive page data based on the product recommendation list; and a push unit, configured to push the interactive page data to the user's payment application for display on the interactive interface of the payment application.

[0015] According to a third aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform an operation as described in any of the first aspects above.

[0016] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by a processor to perform the operation as described in any of the first aspects above.

[0017] According to a fifth aspect of the present application, an electronic device is provided, the electronic device including one or more processors and one or more memories, the one or more memories storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the one or more processors to perform the operation as described in any of the first aspects above.

[0018] Based on the technical solution proposed in this application, by acquiring user profile data and merchant information corresponding to the offline payment after the user completes the transaction, the system can accurately capture the user's current offline consumption scenario and personalized consumption needs. This provides a precise data foundation for subsequent product recommendations, avoiding the problem of recommendations being out of touch with the user's actual needs. By generating a matching product recommendation list based on the profile data and merchant information, and then generating interactive page data based on the product recommendation list, the system can integrate product content matching the user's needs into standardized page data, adapting to the display requirements of different payment applications and ensuring the display effect of the recommended content. By pushing the interactive page data to the user's payment application and displaying it on the payment application's interactive interface, the user can view the matching product recommendations in their most frequently used payment application interface immediately after completing the payment, without having to switch to other applications or platforms. This simplifies the user's process of obtaining relevant product information, achieves deep integration of offline payment scenarios and personalized product recommendation services, fully explores the value of offline consumption scenarios, enriches the service forms of offline payment scenarios, and effectively improves the user's experience throughout the entire payment process. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A flowchart of the offline product recommendation method in an embodiment of this application is shown; Figure 2 A block diagram of an offline product recommendation device according to an embodiment of this application is shown; Figure 3 A schematic diagram of the structure of an electronic device in an embodiment of this application is shown. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0022] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices. It should also be noted that, for the sake of simplicity, certain components in the drawings that do not affect the interpretation of the technical solution of this application have been appropriately omitted.

[0023] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined. Therefore, the actual execution order may change depending on the actual situation.

[0024] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0025] This application proposes an offline product recommendation scheme, aiming to achieve deep integration of offline payment scenarios and personalized product recommendation services, fully explore the scenario value of offline consumption, and thereby improve the user experience of offline payment scenarios.

[0026] Next, this application will elaborate on the proposed offline product recommendation scheme. (Refer to...) Figure 1The flowchart of the offline product recommendation method in this application embodiment is shown. This method can be executed by a device with computing processing capabilities, such as a platform service. Figure 1 As shown, the method includes at least steps 110 to 140, which are described in detail below: In step 110, after a user completes an offline payment at a merchant through a payment application, the user's profile data and the merchant information corresponding to the user's offline payment are obtained.

[0027] In step 120, a matching product recommendation list is generated based on the profile data and the merchant information, and interactive page data is generated based on the product recommendation list.

[0028] In step 130, the interactive page data is pushed to the user's payment application so that it can be displayed on the interactive interface of the payment application.

[0029] In this application, the platform service can refer to a backend service system deployed in a cloud server cluster, used to realize payment transaction integration, user data management, product recommendation algorithm execution, and page data generation and push. The platform service can communicate with payment applications of multiple different payment channels and merchant management systems of offline merchants to achieve full-process data interaction and instruction execution. The payment application can refer to an application installed on the user's mobile terminal with offline QR code payment function, including but not limited to third-party payment applications, official bank applications, and life service applications with payment functions. The user profile data can refer to a structured data set generated by the platform service based on multi-dimensional data such as the user's historical consumption behavior, payment behavior, browsing behavior, and preference settings, through data mining and tagging processing, used to characterize the user's consumption preferences, consumption capacity, and consumption habits. The merchant information can refer to various structured data related to the offline merchant corresponding to this offline payment, including but not limited to the merchant's basic identity information, geographical location information, business category information, scene attribute information, and listed product information. The product recommendation list can refer to an ordered list composed of product information with a high degree of matching with user needs, selected from the product library by the platform service based on preset matching rules. The interactive page data can refer to structured data used to render and generate a visual interactive interface on the payment application side, including page layout data, product display data, interactive trigger control data, etc.

[0030] For example, in one specific implementation, a user completes an offline payment at a sporting goods store within a large shopping mall by scanning the merchant's QR code using a third-party payment application on their mobile phone. The purchased item is a standard size 5 soccer ball. Once the platform service receives a payment success notification from the payment channel, it confirms that the user has completed the offline payment and triggers the relevant product recommendation process. The platform service first retrieves the user's profile data from its user database. This profile data reveals tagged information such as the user's preference for sports and fitness, frequent purchases of ball sports-related products, moderate spending power, and activity concentrated in urban shopping mall areas. Simultaneously, the platform service obtains the merchant information corresponding to this payment, including that the merchant is a sporting goods store, located on the third floor of the mall's sports section, and mainly sells ball equipment, sports protective gear, and training apparel. Based on the acquired user profile data and merchant information, the platform service uses preset matching rules to filter out products with a high degree of matching with the user's sports needs. These products include soccer shin guards, professional soccer socks, and soccer pumps from the sports goods store, as well as sports water bottles, sports backpacks, and fitness class vouchers from other stores in the same mall. The platform generates a corresponding product recommendation list, sorted from highest to lowest matching degree. Subsequently, based on the generated product recommendation list, the platform service generates interactive page data adapted to the user's payment application interface specifications. This interactive page data includes a payment success notification, product recommendation display content, and controls for viewing product details and triggering purchase. Finally, the platform service pushes the interactive page data to the user's payment application, where the payment application renders and displays the recommended content on the payment success screen, allowing the user to directly view and perform further actions.

[0031] Based on the technical solutions in steps 110 to 130 above, by acquiring user profile data and merchant information corresponding to the offline payment after the user completes the offline payment, the current offline consumption scenario and the user's personalized consumption needs can be accurately captured. This provides a precise data foundation for subsequent product recommendations, avoiding the problem of recommended content being out of touch with the user's actual needs. By generating a matching product recommendation list based on the profile data and merchant information, and generating interactive page data based on the product recommendation list, product content matching the user's needs can be integrated into standardized page data, adapting to the display requirements of different payment applications and ensuring the display effect of the recommended content. By pushing the interactive page data to the user's payment application and displaying it on the payment application's interactive interface, users can view the matching product recommendations in their most frequently used payment application interface immediately after completing the payment, without having to jump to other applications or platforms. This simplifies the user's operation process for obtaining relevant product information, realizes the deep integration of offline payment scenarios and personalized product recommendation services, fully explores the value of offline consumption scenarios, enriches the service forms of offline payment scenarios, and thus effectively improves the user's experience throughout the entire payment process.

[0032] Next, this application will be published as follows Figure 1 Based on the proposed scheme, this application further elaborates on the details of the offline product recommendation scheme: In this application, the merchant information may include the merchant identifier corresponding to the user's current payment.

[0033] Furthermore, in step 120 above, the generation of a matching product recommendation list based on the profile data and the merchant information can be performed according to steps 121 to 122 as follows: Step 121: Obtain product data associated with the merchant identifier to form a candidate product set.

[0034] Step 122: Determine the products that match the profile data from the candidate product set to form a product recommendation list.

[0035] In this application, the merchant identifier can refer to a unique identification identifier assigned by the platform service to each registered offline merchant. This identifier is associated with and bound to all relevant data of the merchant. The platform service can quickly retrieve all relevant data corresponding to the merchant through the merchant identifier, including the merchant's basic information, listed product data, operational data, account data, etc. The product data associated with the merchant identifier can refer to all product data in the platform service that is bound to the merchant identifier. This includes both the product data entered and listed by the offline merchant corresponding to this payment in the platform service, and the product data of other merchants in the platform service that are associated with this merchant. The candidate product set can refer to the set of all product data selected by the platform service that can be used for this product recommendation, which is the basic data range for subsequent product matching and filtering.

[0036] For example, in the above embodiment, the merchant information obtained by the platform service includes a unique merchant identifier corresponding to the sporting goods store. Using this merchant identifier, the platform service retrieves all product data associated with that merchant identifier from the product database. This includes product data related to footballs, shoes, protective gear, and training equipment entered by the sporting goods store itself, as well as related product data entered by sportswear stores, fitness equipment stores, and sports experience stores within the same shopping mall. This product data is then aggregated to form a candidate product set for this product recommendation. After forming the candidate product set, the platform service, based on user profile data, filters out products with a high degree of matching with ball sports and fitness needs, and finally sorts them according to matching degree to form the final product recommendation list.

[0037] Based on the technical solutions in steps 121 to 122 above, by limiting merchant information to include the merchant identifier corresponding to the user's current payment, the corresponding product data can be quickly located and retrieved using a unique merchant identifier. This improves the efficiency and accuracy of product data retrieval and avoids the problem of mismatch between product data and corresponding merchants. By obtaining product data associated with the merchant identifier to form a candidate product set, a clear filtering range can be defined for product recommendations. This avoids the problems of excessive computation and low recommendation efficiency caused by filtering from the entire product database, while also ensuring that the recommended products have a strong relevance to the user's current offline consumption scenario. By determining products that match the profile data from the candidate product set to form a product recommendation list, products that meet the user's personalized needs can be further filtered within the product range associated with the current scenario. While ensuring the scenario relevance of the recommended content, the matching degree between the recommended content and user needs is improved, thereby further increasing the user's acceptance of the recommended content and ultimately improving the user experience.

[0038] In step 121 above, obtaining the product data associated with the merchant identifier can be performed according to the following steps 1211 to 1213: Step 1211: Obtain the geographical location of the offline merchant based on the merchant identifier.

[0039] Step 1212: Using the geographical location as the center, filter the first product data entered by other merchants in the platform service within a preset radius.

[0040] Step 1213: Merge the first product data and the second product data entered by the offline merchant in the platform service into product data associated with the merchant identifier.

[0041] In this application, the geographical location of the offline merchant can refer to the address of the merchant's business premises. This data is reported and verified by the merchant when joining the platform service, or collected and confirmed through the platform service's map positioning capabilities, ensuring high accuracy. The preset radius can refer to the radius value of a geofence pre-set by the platform service with the merchant's geographical location as the center. This value can be adjusted according to different scenario requirements. The first product data can refer to all product data entered and listed on the platform service by other merchants within the preset radius, excluding the offline merchant corresponding to this payment. The second product data can refer to all product data entered and listed on the platform service by the offline merchant corresponding to this payment itself.

[0042] For example, in the above embodiment, the platform service retrieves the store's address in the sports section on the third floor of a large shopping mall using the merchant's identifier. Using this address as the center, the platform service filters other merchants within and around the mall according to a preset radius, obtaining relevant product data such as sportswear, fitness equipment, and leisure services entered by these merchants on the platform, as the first product data. Simultaneously, the platform service retrieves all product data from the sporting goods store itself, including soccer balls, shin guards, sneakers, and inflatable equipment, as the second product data. Finally, the two sets of product data are merged and deduplicated to form complete product data associated with the merchant's identifier, used to construct a candidate product set.

[0043] Based on the technical solutions in steps 1211 to 1213 above, by obtaining the geographical location of offline merchants according to the merchant identifier, the specific location of the offline scenario where the user completed the payment can be accurately located, providing a precise location basis for subsequent geofencing filtering. By using the merchant's geographical location as the center and filtering the first product data of other merchants within a preset radius, the scope of recommended products can be expanded from the single merchant of this payment to other merchants around the user's current location, fully exploring the surrounding commercial resources of the user's current offline scenario, making the recommended product content more relevant to the user's current geographical location and offline activity scenario. By merging the first product data and the offline merchant's own second product data into product data associated with the merchant identifier, a product pool covering the merchant of this consumption and surrounding related merchants can be constructed. This ensures the relevance of the recommended content to the user's current consumption scenario and expands the coverage of the recommended content, providing users with more product choices that meet the needs of the current scenario, thereby further enriching the service content of the offline payment scenario and improving the user experience.

[0044] In this application, steps 141 to 142 may also be performed: Step 141: Obtain the business district type of the area where the offline merchant is located, the time period type corresponding to the current time, and the user's historical daily travel activity radius.

[0045] Step 142: Based on the business district type, time period type, and historical daily travel activity radius, dynamically adjust the value of the preset radius.

[0046] In this application, the term "business district type" can refer to the commercial attribute classification corresponding to the area where offline merchants are located, including but not limited to different types such as community business districts, office business districts, commercial complex business districts, cultural and tourism business districts, and transportation hub business districts. Different business district types correspond to different user consumption needs and activity ranges. The term "time period type" can refer to the time period attribute classification corresponding to the current time, including but not limited to morning peak hours, breakfast hours, lunch hours, afternoon tea hours, evening peak hours, nighttime hours, weekday hours, and holiday hours. Different time period types correspond to different user consumption needs and activity ranges. The term "user's historical daily travel activity radius" can refer to the average daily travel activity radius value obtained by the platform service based on the user's historical geographical location data and consumption behavior data. This value can be used to characterize the size of the user's daily activity range.

[0047] For example, in the above embodiment, the platform service identifies that the merchant's location is within a large commercial complex area, the current time is a weekend afternoon, which is a leisure consumption period, and the user's historical daily travel radius is relatively large, making it suitable for extensive activity within the mall. Based on this information, the platform service appropriately expands the preset radius from the basic value to cover the entire mall's sports zone, leisure zone, and experience service zone, thereby filtering a wider range of related products and providing users with richer recommendations for football-related products and services.

[0048] Based on the technical solutions in steps 141 to 142 above, by acquiring the business district type of the area where offline merchants are located, the time period type corresponding to the current time, and the user's historical daily travel radius, multiple key dimensions of factors affecting the user's current activity range and consumption needs can be comprehensively captured, providing comprehensive data support for adjusting the preset radius. By dynamically adjusting the value of the preset radius based on the business district type, time period type, and historical daily travel radius, the geofence range can be adapted to different business district scenarios, different time period needs, and different users' daily activity habits, avoiding the problem of mismatch between the recommended range and the user's actual activity range caused by a fixed radius. When the user is in a community scenario with a small activity range or during breakfast time, the recommended range can be narrowed to ensure the accuracy of the recommended content. When the user is in a commercial complex scenario with a large activity range or during holiday leisure time, the recommended range can be expanded to provide the user with a wider range of choices, thereby making the recommended product content more in line with the user's current actual scenario needs, further improving the matching degree of the recommended content and the user's user experience.

[0049] Before step 122 above, that is, before determining the products that match the profile data from the candidate product set and forming the product recommendation list, the following steps 1214 to 1215 can also be performed: Step 1214: Perform compliance verification on the product data in the candidate product set and filter out product data that does not comply with preset regulatory rules, regional sales restrictions, or user age matching requirements.

[0050] Step 1215: Filter the duplicate product data that has been purchased in the user's historical purchase records, as well as the product data with zero inventory, and update the candidate product set.

[0051] In this application, the compliance verification refers to the platform service verifying the legality and compliance of product data in the candidate product set based on preset regulatory rules and platform management rules, ensuring that the recommended product content complies with relevant national laws and regulations, regulatory requirements, and platform management specifications. The preset regulatory rules can refer to relevant rules regarding product sales and advertising in relevant national laws and regulations and management regulations issued by regulatory authorities, including but not limited to prohibited product categories, sales qualification requirements for special products, and compliance requirements for advertising. The geographical sales restrictions can refer to geographical restrictions on the sale of certain products, including but not limited to restrictions on the delivery range of cold chain food, geographical restrictions on the sale of special medicines, and service range restrictions for local life services. The user age matching requirements can refer to age restrictions for certain special products, including but not limited to requiring users to be 18 years of age or older for tobacco and alcohol products, and requiring users of maternal and infant products to meet the needs of specific age groups.

[0052] For example, in the above embodiment, after constructing the candidate product set, the platform service can first perform compliance verification on the product data, filtering out sports equipment products that do not meet sales standards, then filtering out external service vouchers that cannot be used in this mall based on geographical restrictions, and simultaneously filtering out mismatched product types based on user age information. Subsequently, the platform service filters out products such as the same football and duplicate sports equipment that the user has purchased multiple times in the past, and filters out products such as football shoes and limited edition protective gear that currently have zero inventory, ultimately obtaining a valid and usable candidate product set for subsequent matching calculations.

[0053] Based on the technical solutions in steps 1214 and 1215 above, by performing compliance verification on the product data in the candidate product set before product matching, filtering out product data that does not comply with preset regulatory rules, regional sales restrictions, and user age suitability requirements, it can be ensured that the final recommended product content fully complies with relevant national laws, regulations, and regulatory requirements, avoiding the risk of illegal recommendations. It can also filter out product content that users cannot purchase or that does not match their own situation, improving the effectiveness of the recommended content. By filtering duplicate product data already purchased in the user's historical purchase records, as well as product data with zero inventory, it can avoid recommending duplicate products that have already been purchased to the user, and also avoid recommending out-of-stock products, preventing situations where users find they cannot purchase recommended products after clicking on them, thus improving the usability of the recommended content and the user experience. Updating the candidate product set through the above filtering operations provides a compliant, effective, and accurate range of products for subsequent product matching and filtering, reducing the amount of invalid data in subsequent matching operations, improving the efficiency of matching operations, and further improving the quality of the final generated product recommendation list, thereby increasing user acceptance of the recommended content and the overall user experience.

[0054] In this application, the profile data may include a first list of goods paid by the user in this payment, and / or a second list of goods paid in the past.

[0055] Furthermore, in step 122 above, the step of determining the product that matches the profile data from the candidate product set can be performed according to the following steps 1221 to 1224: Step 1221: Obtain the first feature tag of each product in the first product list and / or the second product list.

[0056] Step 1222: Obtain the second feature label of each product in the candidate product set.

[0057] Step 1223: Based on the first feature label and the second feature label, predict the target matching degree of each product in the candidate product set using a preset matching algorithm. The target matching degree is used to characterize the user's demand for the product.

[0058] Step 1224: Sort the products in the candidate product set according to the target matching degree from high to low, select a preset number of products at the top of the sorting, and generate the corresponding product recommendation list.

[0059] In this application, the first product list can refer to a list of all products purchased by the user in this offline payment, including the name, category, specifications, price, and other relevant data of all purchased products. The second product list can refer to a list of all products purchased by the user in historical offline payments and online consumption, recording all historical consumption data of the user, which can be used to characterize the user's long-term consumption preferences. The first feature tag can refer to a structured tag generated by the platform service for each product in the first and second product lists through tagging processing, used to characterize the product's category, attributes, specifications, applicable scenarios, price range, and other characteristics. The second feature tag can refer to the corresponding feature tag generated by the platform service for each product in the candidate product set, whose tag system is completely consistent with the tag system of the first feature tag, ensuring the accuracy of tag matching. The preset matching algorithm can refer to an algorithm model pre-set by the platform service for calculating the user's demand for a product based on the product's feature tags. The target matching degree can refer to a quantitative value calculated by the preset matching algorithm, used to characterize the user's demand for a certain product; the higher the value, the higher the user's demand for the product, and the better the matching degree.

[0060] For example, in the above embodiment, the product purchased by the user in this payment is a size 5 soccer ball, corresponding to the first product list. The platform service generates a first feature tag for the soccer ball, including ball sports, soccer ball, standard size, outdoor use, fitness related, etc. Simultaneously, the platform service retrieves previously purchased items such as sports knee braces, sports backpacks, and fitness courses to form a second product list and generate corresponding feature tags. Subsequently, the platform service generates second feature tags for items such as soccer shin guards, soccer socks, sports water bottles, and gym vouchers in the candidate product set. A preset matching algorithm is used to calculate the tag overlap between each product and the user's previously purchased items to obtain the target matching degree. For example, shin guards and soccer socks have a high tag overlap with soccer balls and thus a higher matching degree, while irrelevant products have a lower matching degree. The platform service sorts the products by matching degree and selects the top-ranked products to generate the final recommendation list.

[0061] Based on the technical solutions in steps 1221 to 1224 above, by limiting the profile data to include a first list of goods paid for by the user in this transaction and / or a second list of goods paid for in the past, it is possible to simultaneously capture the user's immediate consumption needs and long-term consumption preferences, providing a more comprehensive and accurate user demand data foundation for product matching. By obtaining the first feature tags of each product in the first and / or second product lists, and the second feature tags of each product in the candidate product set, unstructured product information can be transformed into standardized structured tags, providing a unified data standard for subsequent matching degree calculation and ensuring the accuracy and consistency of the matching calculation. By predicting the target matching degree of each product in the candidate product set based on the first and second feature tags and using a preset matching algorithm, the user's demand for products can be quantified, achieving an accurate assessment of the product matching degree and avoiding the subjectivity and inaccuracy caused by manual screening. By sorting products according to their target matching degree from high to low, and selecting a preset number of products from the top of the sorted list to generate a product recommendation list, it can be ensured that the products ultimately recommended to users are those that best match the user's immediate needs and long-term preferences. This significantly improves the accuracy of the recommendation content, allowing users to quickly find the products they need, thereby effectively enhancing the user experience.

[0062] In step 1223 above, the step of predicting the target matching degree of each product in the candidate product set based on the first feature label and the second feature label using a preset matching algorithm can be performed according to the following steps 12231 to 12233: In the next step 12231, for each product in the candidate product set, calculate the overlap between the first feature tag of each product in the first product list and the second feature tag of each product, and assign a first weight to the maximum overlap to obtain the first matching degree of each product.

[0063] In the next step 12232, calculate the overlap between the first feature tag of each product in the second product list and the second feature tag of each product, and assign a second weight to the maximum overlap to obtain the second matching degree of each product, wherein the second weight is less than the first weight.

[0064] In the next step 12233, the maximum value of the first matching degree and the second matching degree is determined as the target matching degree of each product.

[0065] In this application, the overlap between feature tags can refer to the proportion of identical tags in the feature tag sets of two products to the total number of tags. This proportion characterizes the similarity of the features of the two products. A higher overlap indicates greater similarity in the features of the two products and a higher user demand for that product. The first weight can refer to the weight coefficient assigned to the overlap calculated based on the first product list of the current payment, characterizing the impact of the current consumption behavior on product matching. The second weight can refer to the weight coefficient assigned to the overlap calculated based on the second product list of historical payments, characterizing the impact of historical consumption behavior on product matching. A lower second weight indicates that the current consumption behavior has a greater impact on the user's current needs than historical consumption behavior. The first matching degree can refer to the quantified value of the matching degree between the candidate product and the user's current consumption needs, calculated based on the first product list of the current payment. The second matching degree can refer to the quantified value of the matching degree between the candidate product and the user's long-term consumption preferences, calculated based on the second product list of historical payments.

[0066] For example, in the above embodiment, the platform service generates a second feature tag for the soccer shin guards in the candidate product set. The second feature tag for the soccer shin guards is: soccer, sports protection, leg protection, suitable for adults, and for matching use. Then, the platform service can use a preset matching algorithm to calculate the overlap between the first feature tags of the size 5 soccer ball and soccer socks in the first product list and the second feature tag of the soccer shin guards. For example, the overlap for the size 5 soccer ball is 75, and the overlap for the soccer socks is 80. The maximum overlap of 80 is then multiplied by a first weight (e.g., a first weight of 1) to obtain a first matching degree of 80 for the soccer shin guards in the candidate product set. Next, the platform service can calculate the overlap between the first feature tags of the sports water bottle and gym vouchers in the second product list and the second feature tag of the soccer shin guards. For example, the overlap for the sports water bottle is 70, and the overlap for the gym voucher is 60. The maximum overlap of 70 is then multiplied by a second weight less than the first weight (e.g., a second weight of 0.8) to obtain a second matching degree of 56 for the soccer shin guards in the candidate product set. Finally, 80 from the first matching degree 80 and the second matching degree 56 of the candidate product set for football shin guards is determined as the target matching degree of the football shin guards.

[0067] Based on the technical solutions in steps 12231 to 12233 above, by calculating the overlap between the first feature tag of each product in the first product list and the second feature tag of that product for each product in the candidate product set, and assigning a first weight to the maximum overlap to obtain the first matching degree, the immediate consumption needs of users based on their current consumption behavior can be accurately captured. By assigning the first weight, the impact of the current consumption behavior on product matching is amplified, making the recommended content more in line with the user's current immediate needs. By calculating the overlap between the first feature tag of each product in the second product list and the second feature tag of that product, and assigning a second weight to the maximum overlap to obtain the second matching degree, and setting the second weight to be less than the first weight, while considering the user's long-term consumption preferences, priority can be given to ensuring that the recommended content is in line with the user's current immediate needs, avoiding excessive influence of historical consumption behavior on the current recommendations. By setting the maximum value of the first and second matching degrees as the target matching degree for each product, it can be ensured that both products that meet the user's immediate needs and products that conform to the user's long-term preferences receive corresponding matching degree evaluations. This prevents products that meet the user's needs from being missed, while also ensuring the rationality and accuracy of the matching degree calculation. The final product recommendation list is designed to meet both the user's current immediate consumption needs and their long-term consumption preferences, thereby further improving the accuracy of the recommended content and the user experience.

[0068] In this application, steps 152 to 152 may also be performed: Step 151: In response to the user clicking on any product in the interactive interface, obtain the product information of the product and the geographical location of the merchant to which the product belongs.

[0069] Step 152: Push the product information of any product and the geographical location of the merchant to which the product belongs to the user's payment application.

[0070] In this application, clicking on any product can refer to a user clicking on any product control in the product display area of ​​the interactive interface displayed on the payment application, triggering a request to view the corresponding product details. This request is sent to the platform service in real time. The product information can refer to the detailed information of the clicked product, including but not limited to the product's name, specifications, price, description, usage rules, expiration date, and inventory quantity. The geographical location of the merchant to which the product belongs can refer to the coordinates of the offline merchant's business location, as well as the corresponding detailed address information and navigation route information.

[0071] For example, in the above embodiment, when a user sees the recommended soccer shin guards on the payment success screen and clicks to view them, the platform service immediately obtains detailed information about the shin guards, including material, size, price, and applicable scenarios. Simultaneously, it obtains the specific location of the store where the product is located, i.e., another sporting goods store on the fourth floor of the same shopping mall. The platform service pushes this information to the user's payment application, allowing the user to directly view the details and go to the corresponding store to purchase, or to place an order online.

[0072] Based on the technical solutions in steps 151 to 152 above, by responding to a user's click on any product in the interactive interface, the system obtains the product information and the geographical location of the merchant. This allows for rapid response to user requests, accurately retrieving detailed information about products of interest to the user, and accurately providing subsequent services. By pushing product information and the merchant's geographical location to the user's payment application, users can directly view detailed information about products of interest within the payment application without being redirected to other applications or platforms. Simultaneously, the system obtains the merchant's geographical location and navigation information, facilitating offline consumption. This simplifies the user's workflow, creating a closed-loop service from product recommendation to viewing product details and offline consumption guidance. This further enriches the service content of offline payment scenarios, effectively improving the user's overall experience.

[0073] Overall, the offline product recommendation method provided in this application generates a precise product recommendation list by combining user profile data with the merchant information corresponding to the payment after the user completes offline payment. It then generates an adapted interactive page and pushes it to the user's payment application, achieving a deep integration of offline payment scenarios and personalized product recommendation services. This breaks through the limitations of existing technologies where offline payment only focuses on transaction settlement, fully exploring the value of offline consumption scenarios. Through a series of technical means such as geofencing, dynamic radius adjustment, compliance pre-verification, and multi-dimensional tag matching algorithms, it achieves precise matching between recommended content and the user's current scenario, immediate needs, and long-term preferences, significantly improving the effectiveness and accuracy of recommended content. Simultaneously, through a closed-loop service process, it simplifies the user's operation process, enriches the service forms of offline payment scenarios, and ultimately achieves a comprehensive improvement in the user experience of offline payment scenarios.

[0074] The following describes an embodiment of the apparatus described in this application, which can be used to execute the offline product recommendation method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the offline product recommendation method described above.

[0075] See Figure 2 The diagram shows a block diagram of an offline product recommendation device in an embodiment of this application.

[0076] like Figure 2 As shown, the offline product recommendation device 200 according to the embodiments of this application can be set in the platform service, and may include: an acquisition unit 201, a generation unit 202 and a push unit 203.

[0077] The acquisition unit 201 is used to acquire the user's profile data and the merchant information corresponding to the user's offline payment after the user completes offline payment through the payment application terminal; the generation unit 202 is used to generate a matching product recommendation list based on the profile data and the merchant information, and generate interactive page data based on the product recommendation list; the push unit 203 is used to push the interactive page data to the user's payment application terminal for display on the interactive interface of the payment application terminal.

[0078] In some embodiments of this application, based on the aforementioned scheme, the merchant information includes the merchant identifier corresponding to the user's current payment; the generation unit 202 is configured to: acquire product data associated with the merchant identifier to form a candidate product set; determine products that match the profile data from the candidate product set to form a product recommendation list.

[0079] In some embodiments of this application, based on the foregoing scheme, the generation unit 202 is configured to: obtain the geographical location of the offline merchant according to the merchant identifier; filter the first product data entered by other merchants in the platform service within a preset radius with the geographical location as the center; and merge the first product data and the second product data entered by the offline merchant in the platform service into product data associated with the merchant identifier.

[0080] In some embodiments of this application, based on the foregoing solution, the device further includes: an adjustment unit, configured to obtain the business district type of the area where the offline merchant is located, the time period type corresponding to the current time, and the user's historical daily travel activity radius; and dynamically adjust the value of the preset radius based on the business district type, time period type, and historical daily travel activity radius.

[0081] In some embodiments of this application, based on the foregoing scheme, the device further includes: a verification unit, configured to perform compliance verification on the product data in the candidate product set before determining the product that matches the profile data from the candidate product set and forming a product recommendation list, filtering out product data that does not comply with preset regulatory rules, regional sales restrictions, or user age matching requirements; filtering out duplicate product data that has been purchased in the user's historical purchase records, as well as product data with zero inventory, and updating the candidate product set.

[0082] In some embodiments of this application, based on the foregoing scheme, the profile data includes a first list of goods paid by the user in this payment and / or a second list of goods paid in the past; the generation unit 202 is configured to: obtain a first feature tag for each item in the first list and / or the second list of goods; obtain a second feature tag for each item in the candidate item set; based on the first feature tag and the second feature tag, predict the target matching degree of each item in the candidate item set using a preset matching algorithm, wherein the target matching degree is used to characterize the user's demand for the item; sort the items in the candidate item set according to the target matching degree from high to low, select a preset number of items at the top of the sort, and generate a corresponding item recommendation list.

[0083] In some embodiments of this application, based on the foregoing scheme, the generation unit 202 is configured to: for each product in the candidate product set, calculate the overlap between the first feature tag of each product in the first product list and the second feature tag of each product, and assign a first weight to the maximum overlap to obtain the first matching degree of each product; calculate the overlap between the first feature tag of each product in the second product list and the second feature tag of each product, and assign a second weight to the maximum overlap to obtain the second matching degree of each product, wherein the second weight is less than the first weight; and determine the maximum value of the first matching degree and the second matching degree as the target matching degree of each product.

[0084] In some embodiments of this application, based on the foregoing scheme, the push unit 203 is configured to: in response to the user clicking on any product in the interactive interface, obtain the product information of the product and the geographical location of the merchant to which the product belongs; and push the product information of the product and the geographical location of the merchant to which the product belongs to the user's payment application.

[0085] Based on the same inventive concept, embodiments of this application provide a computer program product, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor, so as to cause a computer device having the processor to perform the operations performed by the offline product recommendation method as described above.

[0086] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations performed by the offline product recommendation method as described above.

[0087] Based on the same inventive concept, this application also provides an electronic device, see reference. Figure 3 The diagram shows a schematic of the structure of an electronic device in an embodiment of this application. The electronic device includes one or more memories 304, one or more processors 302, and at least one computer program (computer program instruction) stored in the memory 304 and executable on the processor 302. When the processor 302 executes the computer program, it implements the offline product recommendation method as described above.

[0088] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.

[0089] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0091] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0092] When the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program instructions, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0093] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An offline product recommendation method, characterized in that, The method is executed on a platform service, and the method includes: After a user completes an offline payment at a merchant through a payment application, the user's profile data and the merchant information corresponding to the user's offline payment are obtained. Based on the profile data and the merchant information, a matching product recommendation list is generated, and interactive page data is generated based on the product recommendation list; The interactive page data is pushed to the user's payment application so that it can be displayed on the interactive interface of the payment application.

2. The method according to claim 1, characterized in that, The merchant information includes the merchant identifier corresponding to the user's current payment; The step of generating a matching product recommendation list based on the profile data and the merchant information includes: Obtain product data associated with the merchant identifier to form a candidate product set; Products that match the profile data are selected from the candidate product set to form a product recommendation list.

3. The method according to claim 2, characterized in that, The acquisition of product data associated with the merchant identifier includes: Based on the merchant identifier, obtain the geographical location of the offline merchant; Using the aforementioned geographical location as the center, filter the first product data entered by other merchants in the platform service within a preset radius; The first product data and the second product data entered by the offline merchant in the platform service are merged into product data associated with the merchant identifier.

4. The method according to claim 3, characterized in that, The method further includes: Obtain the business district type of the area where the offline merchant is located, the time period type corresponding to the current time, and the user's historical daily travel activity radius; The value of the preset radius is dynamically adjusted based on the business district type, time period type, and historical daily travel activity radius.

5. The method according to claim 2, characterized in that, Before determining the products that match the profile data from the candidate product set and forming a product recommendation list, the method further includes: The product data in the candidate product set is subjected to compliance verification, and product data that does not comply with preset regulatory rules, regional sales restrictions, or user age matching requirements is filtered out. Filter out duplicate product data that has been purchased in the user's historical purchase records, as well as product data with zero inventory, and update the candidate product set.

6. The method according to claim 2, characterized in that, The profile data includes the user's first list of goods paid for in this transaction, and / or a second list of goods paid for in the past. The step of determining the product that matches the profile data from the candidate product set includes: Obtain the first feature tag of each product in the first product list and / or the second product list; Obtain the second feature label of each product in the candidate product set; Based on the first feature label and the second feature label, the target matching degree of each product in the candidate product set is predicted by a preset matching algorithm. The target matching degree is used to characterize the user's demand for the product. The products in the candidate product set are sorted in descending order of target matching degree, and a preset number of products at the top of the sort are selected to generate a corresponding product recommendation list.

7. The method according to claim 6, characterized in that, The step of predicting the target matching degree of each product in the candidate product set based on the first feature label and the second feature label using a preset matching algorithm includes: For each product in the candidate product set, calculate the overlap between the first feature tag of each product in the first product list and the second feature tag of each product, and assign a first weight to the maximum overlap to obtain the first matching degree of each product; Calculate the overlap between the first feature tag of each product in the second product list and the second feature tag of each product, and assign a second weight to the maximum overlap to obtain the second matching degree of each product, wherein the second weight is less than the first weight; The maximum value of the first matching degree and the second matching degree is determined as the target matching degree for each product.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: In response to the user clicking on any product in the interactive interface, obtain the product information of the product and the geographical location of the merchant to which the product belongs; The product information of any one of the products, as well as the geographical location of the merchant to which the product belongs, will be pushed to the user's payment application.

9. An offline product recommendation device, characterized in that, The device is configured within the platform service, and the device includes: The acquisition unit is used to acquire the user's profile data and the merchant information corresponding to the user's offline payment after the user completes an offline payment through the payment application at an offline merchant. The generation unit is used to generate a matching product recommendation list based on the profile data and the merchant information, and to generate interactive page data based on the product recommendation list; The push unit is used to push the interactive page data to the user's payment application terminal for display on the interactive interface of the payment application terminal.

10. An electronic device, characterized in that, The electronic device includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the method as described in any one of claims 1 to 8.

Images