Method and system for recommending goods in business operation, computer program product

Abstract

The application provides a commodity recommendation method and system in business operation, and a computer program product, which provides a recommendation process of goods in stock and selected goods for each shop in business operation, estimates exposure conversion of the available goods through the shop image, coarsely sorts the available goods to obtain candidate goods for the shop, estimates the conversion value of the candidate goods through the shop image, and then finely sorts to obtain the goods for the shop and the delivery value of the goods for the shop, finally generates a goods processing strategy in the shop operation for the two types of goods for the shop, that is, the goods in stock and the selected goods, to realize dynamic selection of goods for all users passing through the shop, accurately control the delivery of the goods in stock, no longer rely on the subjective cognition of the shop owner, realize high reliability and high accuracy of commodity recommendation in business operation, and obtain high customer flow conversion for the shop.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and specifically to a commodity recommendation method and system in commercial operations, and a computer program product. Background Art

[0002] In business operations, the selection and shelving of products in stores and the display of purchased goods all rely on the merchants' subjective consumption data analysis and subjective observations of their own customer groups, lacking highly reliable and accurate product selection and shelving processing.

[0003] In addition, the consumption data generated by merchants will also be affected by the merchants' product display and selection in the store.

[0004] If a merchant has put on the shelves a product that a customer group is more likely to buy, but the product is displayed in a location in the store that is not easily found, then the product's placement value may be low. The consumption data of the product will definitely tell the merchant that the product's placement value is low, and the product should be returned or exchanged.

[0005] As for products that are not on the shelves but can be sold in the store, merchants are unable to accurately select products suitable for their customer groups because they do not have the corresponding consumption data to support analysis.

[0006] In summary, the selection and listing of goods in existing subway commercial operations rely on and are limited by the subjective cognition of merchants. There is an urgent need to provide a highly reliable and accurate product recommendation implementation in subway commercial operations. Summary of the Invention

[0007] One purpose of this application is to abandon the product selection and listing process in commercial operations that relies on and is limited by the subjective cognition of merchants, and to provide a highly reliable and accurate product recommendation implementation in commercial operations.

[0008] According to one aspect of an embodiment of the present application, a method for recommending products in a commercial operation is disclosed, the method comprising:

[0009] Obtain a shop profile of the shop by determining all users who pass through the shop during business, wherein the shop profile includes a user profile of each user;

[0010] Using the store portrait, the exposure conversion of the available products in the store is estimated, and the available products are roughly ranked to obtain candidate products for listing;

[0011] The estimated conversion values ​​of the candidate listed products are sorted by the shop portrait to obtain the listed products of the shop and the placement value of the listed products in the shop;

[0012] A shelf merchandise processing strategy for the store operation is generated by adapting to the two types of shelf merchandise, namely, purchased merchandise and selected merchandise.

[0013] According to one aspect of an embodiment of the present application, obtaining a shop portrait of a shop by determining all users passing through the shop during business, includes:

[0014] For a shop in a commercial area, obtain all corresponding users according to the exit corresponding to the shop at the site;

[0015] The user portraits of all users corresponding to the exit are assigned to the shop to form a shop portrait of the shop.

[0016] According to one aspect of an embodiment of the present application, estimating the exposure conversion of available products in the store by using the store portrait, roughly ranking the available products, and obtaining candidate products for listing includes:

[0017] For products that can be put on the shelves, the conversion value of the products exposed on the shelves in the stores is estimated by using the store portrait;

[0018] Based on the estimated conversion value, products with high conversion value are selected from the available products as candidate products for listing.

[0019] According to one aspect of an embodiment of the present application, estimating the conversion value of a product that can be put on the shelf by using a store portrait includes:

[0020] Estimated click-through rate of available products for each user among all users who pass by the store;

[0021] The click-through rates are accumulated to obtain the conversion value of the shelf-available products when they are exposed in the store.

[0022] According to one aspect of an embodiment of the present application, the estimated click rate of all users passing through the store on the available products includes:

[0023] For all users who pass by the shop, the user-product pairs of the shop are constructed based on the user portraits and the product features corresponding to the available products;

[0024] By predicting the product click-through rate of the user-product pair, the click-through rate of each user for the available products among all users corresponding to the store is obtained.

[0025] According to one aspect of an embodiment of the present application, the step of finely ranking the estimated conversion values ​​of the candidate listed products using the shop portrait to obtain the shop's listed products and the placement value of the listed products in the shop includes:

[0026] Secondarily estimating the click-through rate of the candidate listed products by all users corresponding to the store to obtain a secondary estimated value of the click-through rate;

[0027] Adapting the high click-through rate secondary estimated value to finely sort the candidate listing products and filter out the listing products of the store;

[0028] The placement value of the listed products in the shop is calculated based on the corresponding secondary estimated click rate, click value and the number of exposures of the listed products in the shop.

[0029] According to one aspect of an embodiment of the present application, the listed products include purchased products, and the generating of a listed product processing strategy in the store operation for the two types of purchased products and selected products includes:

[0030] The purchased goods of the store are enumerated, and a shelf-product processing strategy is generated for purchased goods with high investment value, in which the purchased goods are displayed in a conspicuous position in the store; and a shelf-product processing strategy is generated for purchased goods with low investment value, in which the purchased goods are not to be purchased or are returned or exchanged.

[0031] According to one aspect of an embodiment of the present application, the listing of goods includes selecting goods, and the generating of a listing processing strategy for the shop operation based on the two types of listing of goods, namely, purchased goods and selected goods, includes:

[0032] The product selections of the store are enumerated, and a product listing processing strategy for the store's replenishment needs is generated for the product selections with high investment value.

[0033] According to one aspect of an embodiment of the present application, a product recommendation system for commercial operations is disclosed. The system includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the method described above.

[0034] According to one aspect of an embodiment of the present application, a computer program product is disclosed, including a computer program, wherein the computer program is executed by a processor to execute the steps of the above-mentioned method.

[0035] The embodiment of the present application can provide each shop in the business operation with recommended processing of purchased goods and selected products, so as to realize dynamic product selection for all users passing through the shop, and accurately control the release of purchased goods, so as to obtain high customer flow conversion for the shop.

[0036] Thus, the embodiment of the present application firstly determines all users passing through the store in the business, and obtains a store image of the store through the user image of all users, and then performs exposure conversion estimation of the mountable goods through the store image, firstly coarsely sorts the mountable goods to obtain candidate mountable goods of the store, and then estimates the conversion value of the candidate mountable goods through the store image, and further finely sorts to obtain mountable goods of the store and the delivery value of the mountable goods in the store, and finally generates a mountable goods processing strategy in the store operation of the store, which no longer depends on the subjective cognition of the store owner, realizes high-reliability and high-accuracy goods recommendation in the business operation, realizes dynamic selection of goods for the store, and accurately controls the delivery of the goods in stock through the generation of the mountable goods processing strategy for the goods in stock, and realizes high customer flow conversion for the sale of goods of the store.

[0037] Other features and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0038] It should be understood that the foregoing general description and the following detailed description are only examples and are not restrictive of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0039] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0040] Figure 1 A flowchart of a goods recommendation method in a business operation according to an embodiment of the present application is shown.

[0041] Figure 2 According to Figure 1 A method flowchart for describing the step of obtaining a store image of a store by determining all users passing through the store in the business is shown according to the corresponding embodiment.

[0042] Figure 3 According to Figure 1 A method flowchart for describing the steps of exposure conversion estimation of mountable goods in a store through a store image, coarse sorting of mountable goods, and obtaining candidate mountable goods is shown according to the corresponding embodiment.

[0043] Figure 4 According to Figure 3 A method flowchart for describing the step of estimating the conversion value of mountable goods in a store through a store image is shown according to the corresponding embodiment.

[0044] Figure 5 According to Figure 4A flowchart of a method for describing the steps of estimating the click-through rates of all users passing through a store on available products is shown in the corresponding embodiment.

[0045] Figure 6 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of obtaining the store's listed products and the placement value of the listed products in the store by accurately sorting the estimated conversion values ​​of candidate listed products through store portraits. DETAILED DESCRIPTION

[0046] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this application will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The accompanying drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. Identical reference numerals in the figures indicate identical or similar parts, and thus repeated descriptions thereof will be omitted.

[0047] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present application. However, those skilled in the art will appreciate that the technical solutions of the present application may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring the main content and making various aspects of the present application vague.

[0048] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0049] A city is dotted with numerous routes, each with numerous stops. Each stop houses numerous shops based on their business operations. Each shop has its own unique product selection and display characteristics. For example, the selection of available products is often based on the merchant's own subjective understanding, while the display location of purchased goods is also often determined by the merchant's own subjective understanding.

[0050] In commercial operations, each shop is limited by subjective experience and relies heavily on subjective experience to determine what products to put in the shop and how to display the products in the shop. There is no objective, accurate and reliable merchant product selection and shelving process, which leads to poor product placement effects in various shops in commercial operations.

[0051] Based on this, the embodiment of the present application provides a method for recommending goods in commercial operations, thereby serving commercial operations with high reliability and high accuracy, enabling shops in the business to achieve good performance.

[0052] See Figure 1 , Figure 1 A flowchart of a method for recommending products in a commercial operation according to an embodiment of the present application is shown. The method for recommending products in a commercial operation provided by the embodiment of the present application includes:

[0053] Step S110, obtaining a shop profile of the shop by determining all users who pass through the shop during business, the shop profile including the user profile of each user;

[0054] Step S120: Estimating the exposure and conversion of products available for sale in the store through the store portrait, roughly ranking the products available for sale, and obtaining candidate products for sale;

[0055] Step S130: Rank the candidate products for sale based on their estimated conversion values ​​using the store profile to obtain the store's products and their placement values ​​in the store.

[0056] Step S140 , generating a product listing processing strategy for store operations based on two types of products: purchased products and selected products.

[0057] These steps are described in detail below.

[0058] Through the execution of step S110, all users corresponding to the shop are first obtained. All users corresponding to the shop are all users who pass through the shop during the business. For each shop in the business, recommendations for available products and shelf displays of purchased products will be implemented based on all its corresponding users. This will build a recommendation system for merchants to select and display products based on the customer flow of the business. On the one hand, this will enable dynamic product selection for shops and improve customer flow conversion. On the other hand, it will enable shops in the business to obtain good business, thereby assisting and even improving the owners' shop rental business.

[0059] Shops can be located within the station or radiate outward from the station's exits. For example, shops can be located in the station lobby, shops along the way from the gate to each exit, and shops at the station's exits.

[0060] Therefore, for many shops inside and outside the site, product recommendations for each shop can be implemented based on the embodiments of this application, and the implemented product recommendations include but are not limited to product selection recommendations for optional products, and recommendations for display and shelving of purchased products.

[0061] In each store's product recommendations, suitable products are recommended based on all users corresponding to the location and these users' estimated value conversion of the products exposed in the store, or the best products are selected for the store to be put on the shelves.

[0062] Identifying all users who pass through a shop during a business trip is the process of obtaining all users corresponding to the shop's location. The obtained users are traveling and their travel trajectories are related to the shop, that is, the user travel profile of the user is related to the shop.

[0063] Specifically, the user travel portrait may include outbound travel trajectory, user itinerary, etc.; correspondingly, the user travel portrait is related to shops, which means that the outbound travel trajectory and user itinerary described in the user travel portrait can correspond to the location of the shop.

[0064] See also Figure 2 , Figure 2 is based on Figure 1 The corresponding embodiment shows a flowchart of a method for obtaining a shop portrait by determining all users who pass through the shop during a business trip. The step S110 of obtaining a shop portrait by determining all users who pass through the shop during a business trip provided in the embodiment of the present application includes:

[0065] Step S111: For a shop in the commercial area, obtain all corresponding users according to the exit corresponding to the shop at the station;

[0066] Step S112: assign the user portraits of all users corresponding to the exit to the shop to form a shop portrait of the shop.

[0067] The following describes these two steps in detail.

[0068] Based on the exit corresponding to the store at the station, the user's exit travel trajectory and / or user itinerary corresponding to the exit are obtained to obtain all users corresponding to the store. For example, all users whose user itinerary and / or exit travel trajectory correspond to the store's location are obtained to be used for product recommendations for the store.

[0069] For example, the locations corresponding to a user's itinerary and / or exit trajectory are the locations covered by the user's exit behavior. For example, all locations the user passes through when walking from the track area via the exit elevator to the exit gate, as well as the exit direction the user intends to take when exiting the gate, and even the locations on the exit passage of the corresponding exit, and all the shops located therein are all shops corresponding to the user.

[0070] Obtain all users whose user itineraries and / or outbound travel trajectories correspond to the location of the store, which is obtained by aggregating the locations corresponding to the user itineraries and / or outbound travel trajectories.

[0071] Mapping a user's itinerary and / or travel trajectory to a location can be achieved by positioning the user. In addition, it can also be achieved by determining the user's preferred exit direction based on the distribution of the number of times the user exits each gate group at the site, especially the exit gate to which each user belongs.

[0072] At this point, it should be further explained that the execution process of the above-mentioned step S111 includes: first, determining the user's outbound travel trajectory through the distribution of the number of times the user exits the station at each gate group at the site; then aggregating users for the shops covered by the outbound travel trajectory to obtain all users corresponding to the shops, and the aggregated users correspond to the outbound travel trajectory covering the shop.

[0073] A user's entry and exit behavior at a gate generates a corresponding user itinerary, which is stored in itinerary data. In one exemplary embodiment, the itinerary data exists in the form of a user itinerary table. Each user's itinerary generated when a user exits a gate is stored in the constructed user itinerary table.

[0074] The user's itinerary describes the user's exit gate. In terms of data, the exit gate described in the user's itinerary exists in the form of an exit gate code, and the location of the gate can be obtained from the corresponding gate information.

[0075] The distribution of the number of times each user exits the station at the station gate group is obtained to determine the user's preferred exit direction or even the exit, and then obtain the exit trajectory mapped to the preferred exit direction or even the exit.

[0076] A station has several gate groups for entering and / or exiting the station, and for the gate groups available for exiting the station, the gate group includes a left half group of gates and a right half group of gates. It should be understood that users exiting the station from the left half group of gates tend to one exit direction, and users exiting the station from the right half group of gates tend to the other exit direction.

[0077] Based on the distribution of the number of times the user exits the station at each gate group, it can be determined whether the user prefers the left half of the gate group or the right half of the gate group, and then the preferred exit direction is determined. The exit port to which the user belongs is determined by the preferred exit direction. Since this exit port is based on the distribution of the number of times the user exits the station at each gate group, this exit port is the user's commonly used exit port.

[0078] At this point, the user's exit trajectory is matched to the exit gate determined by the exit direction, and the exit trajectory including the user's passage from the gate to the exit gate is obtained.

[0079] To further illustrate, the distribution of the number of times a user exits each gate in a site gate group describes the number of times a single user exits gate 1 in the gate group, the number of times a single user exits gate 2 in the gate group, and so on, and the number of gates n_zj in the gate group (n_zj is the number of gates in the entire gate group).

[0080] The user's preferred exit direction and exit port can be determined by counting and comparing the number of exits corresponding to the left half of the gate group and the right half of the gate group based on the distribution of the number of exits by the user at each gate group at the site, so as to determine the user's preferred exit direction and exit port.

[0081] In an exemplary embodiment, if the number of times a user exits a station gate group is not less than a set threshold, the user's preferred exit direction can be determined by counting and comparing the number of exits corresponding to the left half group of gates and the right half group of gates as described above, and then the exit in that exit direction can be determined as the user's frequently used exit.

[0082] In a gate group, if users exit the station more frequently, they will mostly exit the station through the same side or even the same gate in this gate group. Therefore, the gate on this side, such as the left half of the gate group, or the right half of the gate group, or the gate on the side where the same gate with frequent exits is located, the corresponding exit direction is the user's preferred direction.

[0083] Therefore, for such users, the preferred exit direction and exit port can be determined directly by counting and comparing the distribution of their exit times at each gate group at the site, thereby reducing the computational complexity and improving execution efficiency.

[0084] The number of times a user exits a station gate group is used to determine whether they frequently exit the station through the current station gate group. The number of times a user exits a station gate group can be obtained based on the distribution statistics of the number of times the user exits the station through each gate group at the station gate group. In addition, it can also be obtained based on the user's travel history and gate information. Further, it can be obtained by constructing user gate group exit data from travel data composed of user travel history and gate information, which is not limited here.

[0085] In another example embodiment, if the number of times the user exits the station gate group is less than the set threshold, the user's preferred exit direction is determined by a binary classification model based on the distribution of the number of times the user exits each gate of the station gate group and the user portrait, and then the exit gate to which the user belongs is determined in the exit direction.

[0086] For example, the set threshold can be 5, that is, if the number of times the user exits a gate group in a station is not less than 5 within a set time range, it means that the exit direction corresponding to the gate group and the exit gate in the exit direction are consistent with the user's exit pass, so the exit gate can be determined as the user's frequently used exit gate.

[0087] If the number of times the user exits the station gate group is less than the set threshold, it means that neither the station nor the gate group is frequently used by the user, so features need to be constructed based on more abundant data, i.e., the distribution of the number of times the user exits each gate of the station gate group and the user portrait, and then the prediction is implemented by the pre-constructed model.

[0088] Further, the step of determining the user's exit travel trajectory based on the distribution of the number of times the user exits each gate of the station gate group is as follows:

[0089] (1) Determine the exit gate to which each user belongs based on the distribution of the number of times the user exits the station gate group and the user portrait.

[0090] (2) Correspond the user's travel trajectory to the exit gate to obtain the exit trajectory of the user passing through the exit gate.

[0091] For this execution process, first of all, it should be noted that a binary classification model for predicting the user's preferred exit direction is pre-constructed, and then the distribution of the number of times the user exits the station gate group and the user portrait can be used as features to predict whether the user passes left or right after exiting the gate group based on the binary classification model, so as to determine the exit gate to which the user belongs based on the exit gate in the pass direction.

[0092] For each user, the exit gate to which the user belongs is determined based on the distribution of the number of times the user exits the station gate group and the user portrait.

[0093] The exit gate to which the user belongs indicates the user's travel trajectory after exiting the gate. That is, by corresponding the existing travel trajectory to the determined exit gate, the exit trajectory of the user passing through the exit gate can be obtained.

[0094] Based on this, each user will determine the exit they frequently use during their travels. Therefore, for product recommendations on shops, shops whose locations correspond to the users' exit trajectories will expose their products to these users. Therefore, the placement of products on shops will be targeted at these users. Product recommendations based on exit trajectories will help improve the accuracy of product placement in shops.

[0095] After determining the user's outbound travel trajectory, users can be aggregated for the shops covered by the outbound travel trajectory, and then all users corresponding to the shops can be obtained.

[0096] In other words, as the product recommendations in the shops proceed, users at the location of each shop will be aggregated to determine the target group of the shop.

[0097] The outbound travel trajectory covers at least one store. In other words, several stores are located on the user's outbound travel trajectory. Therefore, the user's user itinerary can be mapped to the stores on his outbound travel trajectory.

[0098] For each shop, users of the shop are aggregated according to their outbound travel trajectories, that is, users whose outbound travel trajectories cover this shop are aggregated together. In other words, the aggregated users correspond to one shop.

[0099] It should be understood that for users, their inbound and outbound trips generate corresponding user itineraries, which serve as descriptive data for their travels. Therefore, based on their outbound travel trajectories, the users whose user itineraries correspond to each shop are aggregated. The users whose user itineraries correspond to each shop are thus all users associated with that shop.

[0100] Through the execution of step S112, after all users corresponding to the shops in the business are obtained, since each user has his or her own user portrait, the user portraits of all users are assigned to the shops, and the user portraits of all users can be used as the shop portraits of the shop.

[0101] For a shop, after obtaining all the corresponding users through the execution of step S110 and obtaining the corresponding shop portrait through the aggregation of all users, it can then determine candidate products from the available products through the estimated exposure conversion value of all users to the products put on the shop during the execution of steps S120 and S130, and then determine the products to be put on the shelf from the candidate products, and quantify the value of each product put on the shelf in the shop.

[0102] That is to say, under the control of step S120 and step S130, a secondary screening of the products exposed in the store will be implemented, that is, product screening will be implemented under the control of the two execution processes of rough sorting and fine sorting respectively, so as to select products corresponding to the highest conversion value and delivery value to recommend them to the store for exposure.

[0103] In step S120, the user attention of the available products in the store is estimated for all users based on the store portrait. It is understandable that the higher the user attention, the higher the possibility of the available products being exposed and converted in the store.

[0104] For example, user attention can be measured and characterized by estimating the conversion value of all users for available products. The conversion value of a product available in a shop refers to the degree of attention it receives from users passing by after it is put on the shop shelves. The conversion value of a product available in a shop is used to measure the degree to which users passing by the shop would be attracted to the product if the product were put on the shop shelves. It should be understood that the higher the conversion value of a product available in a shop, the more suitable the product is for listing in the shop, and the more likely users passing by the shop will be attracted to the product.

[0105] See also Figure 3 , Figure 3 is based on Figure 1 The corresponding embodiment shows a flow chart of a method for estimating the exposure conversion of shelf-ready products in a shop through shop portraits, roughly sorting the shelf-ready products, and obtaining candidate shelf-ready products.

[0106] The embodiment of the present application provides step S120 of estimating the exposure conversion of products available for sale in a shop by using shop portraits, roughly sorting the products available for sale, and obtaining candidate products for sale, including:

[0107] Step S121 , estimating the conversion value of the available products when they are exposed in the store through the store portrait;

[0108] In step S122 , products with high conversion values ​​are selected from the available products according to the estimated conversion values ​​as candidate products for listing.

[0109] The following describes these two steps in detail.

[0110] For a shop, the conversion value of all users for available products can be represented by the expected click value (CPV) of all users for this available product. The CPV describes the click expectation of all users for the shop's exposed products. By estimating the CPV of all users for the shop's exposed products, the shop can determine which available products have the highest CPV, thereby placing the products with the highest CPV in the shop.

[0111] Furthermore, the expected click value for all users of the store is estimated using a pre-trained click-through rate prediction model. For example, the click-through rate prediction model estimates the expected click value of users for the available products and calculates the click rate of each user for the available products.

[0112] The products that can be put on the shelves are products that are intended to be exposed in the store. For example, the products that can be put on the shelves include selected products and / or purchased products.

[0113] It should be noted that in one exemplary embodiment, conversion value estimation is performed for a shop and a product available for sale, targeting all users associated with that shop. This conversion value estimation, along with the click-through rate estimation between each user and the available product, and the cumulative click-through rate for all users, ultimately yield the expected click value (i.e., conversion value) for the available product in the shop.

[0114] In an exemplary embodiment, a click-through rate prediction model for estimating the click-through rate between users and available products is trained using user click records on exposed products on a travel application.

[0115] Specifically, a training dataset is first constructed for the click-through rate prediction model. Each record in the training dataset includes a user profile of the user and product features constructed for the product. The product is exposed on the travel application and clicked by the user, that is, it corresponds to the user's click record on the exposed product on the travel application.

[0116] Thus, the training data set is constructed

[0117] Among them, the constructed training data set D train A single record in Right now A user portrait is composed of multiple data sources, including but not limited to travel data, application tracking data, etc.

[0118] Specifically,

[0119] corresponds to the user's own travel data, and This corresponds to third-party supplementary data. For example,

[0120]

[0121] Product features include descriptive features, statistical features, and generalized statistical features of the product. For example,

[0122] y ij ∈{0,1}, when the value is 0, it means that no click event occurs after product j is exposed to user i; when the value is 1, it means that a click event occurs after product j is exposed to user i.

[0123] As a result, travel applications have been widely used in the past d For each user i in the day, all n i Product generation records to form the training data set for the click-through rate prediction model.

[0124] Correspondingly, the click-through rate (CTR) between users and available products is estimated using a trained CTR prediction model. This CTR prediction model requires constructing a corresponding prediction dataset. Specifically, for each user associated with a store, a prediction dataset is constructed using the user profile and available product features. Each record in the prediction dataset represents a constructed user-item pair.

[0125] The constructed prediction data set is

[0126] Each record, that is, the user product pair The feature list is the same as the training dataset. To further illustrate, the records in the prediction dataset represent products that can be put on the shelves. Recommend to each user who passes by the store at time T, that is, user The possibility of high conversion value can be obtained by the expected click value obtained thereby.

[0127] Each record in the prediction dataset represents the recommendation of product j to all users corresponding to a store, i.e., users 1, 2, ..., n. userEach record will be used as the input of the click-through rate prediction model to obtain the click-through rate of each user corresponding to the store on the available products. Similarly, the click-through rate of all users corresponding to the store on the available products is obtained. Similarly, the click-through rate of each user corresponding to the store on the available products is obtained, and finally the expected click value of the available products on the store is obtained.

[0128] In an exemplary embodiment, for the click rate prediction model, the loss function constructed is as follows:

[0129]

[0130] in, for The kth element of .

[0131] Iterate along the negative gradient direction of l(w) with respect to w Until the convergence condition is met: Wherein, γ is the learning rate, for example, it can be set to 0.001, ∈ is the preset convergence threshold, for example, it can be set to ∈=10 -5 .

[0132] As the training progresses, the convergence is w * , the optimal model is

[0133] Therefore, through the execution of step S121, after the corresponding conversion value of each shelf-able product in the store is estimated through the shop portrait, several products with high conversion value can be screened out from the shelf-able products in the store as candidate shelf-able products under the action of step S122, thereby realizing the initial screening of shelf-able products, excluding most of the products and obtaining a product set of hundreds of levels. The products in this product set are the candidate shelf-able products.

[0134] It should be understood that the constructed click-through rate prediction model is a rough ranking algorithm model suitable for the initial screening of products that can be put on the shelves, that is, for roughly ranking the products that can be put on the shelves.

[0135] See also Figure 4 , Figure 4 is based on Figure 3 A flowchart of a method for describing the steps of estimating the conversion value of shelf-ready products by using shop portraits to estimate the exposure of shelf-ready products in shops, as shown in the corresponding embodiment.

[0136] The embodiment of the present application provides step S121 of estimating the conversion value of the available products in the shop based on the shop portrait, including:

[0137] Step S301, estimating the click rate of each user on the available products among all users passing through the store;

[0138] Step S302: The conversion value of the product being available for sale in the store is obtained by accumulating the click-through rate.

[0139] The following describes these two steps in detail.

[0140] For all users associated with a store, each user forms a user-product pair with an available product, which is used to estimate the user's click-through rate (CTR) for the available products. The CTR indicates the user's attractiveness to the available products. A higher CTR indicates a more attractive product to the user, while a lower CTR indicates a less attractive product to the user.

[0141] For the user-product pair consisting of a user and a product that can be put on the shelf, the click rate of the user on the product that can be put on the shelf is estimated using the click rate prediction model as described above. Similarly, the click rate of each user corresponding to the store on the product that can be put on the shelf is obtained.

[0142] In other words, all users corresponding to the shop have corresponding click-through rates for the available products, which can numerically describe the degree of attractiveness of the available products to all users passing by the shop, and then use this to evaluate the most suitable candidate products for the shop.

[0143] After obtaining the click rate of each user on the available products, the accumulated click rate is used to obtain the expected click value of the available products on the store, that is, the conversion value as mentioned above.

[0144] The conversion value of the products that can be put on the shelves in the store represents the degree of attraction of the products that can be put on the shelves to the user group passing by the store, and the user group passing by the store is composed of all users corresponding to the store.

[0145] For further information, see Figure 5 , Figure 5 is based on Figure 4 A flowchart of a method for describing the steps of estimating the click-through rates of all users passing through a store on available products is shown in the corresponding embodiment.

[0146] The step S301 of estimating the click rate of all users passing by a store on available products provided by the present application includes:

[0147] Step S3011: For all users who pass by the store, user-product pairs are constructed based on user portraits and product features corresponding to available products.

[0148] Step S3012: By predicting the click-through rate of user-product pairs, the click-through rate of each user for the available products among all users corresponding to the store is obtained.

[0149] First of all, it should be explained that users generate corresponding user itineraries as they initiate entry and exit behaviors. Multiple users and the user itineraries of each user will constitute itinerary data. In other words, users will exist in the form of user itineraries in the data. Therefore, it is possible to construct a user profile describing the user's travel based on this, and thus characterize the user with the user profile for use in building user-product pairs with available products.

[0150] The stores that evaluate the click-through rate of available products belong to a specific site. Therefore, the user journey used to construct the user portrait is related to this specific site, thereby ensuring the accuracy of the features of the constructed user-product pairs and eliminating useless or even interfering data.

[0151] The site-based system provides each user with terminal-based travel applications. This allows each user to enter or exit a station simply by interacting with the travel application on their terminal and the gate. For example, they can enter or exit a station by scanning a QR code provided by the travel application at the gate. The travel application running on the user terminal and the system it connects to will have access to the user's personal travel data, including their itinerary.

[0152] In other words, the user's own travel data will be used to represent the user in the data to build the user's user profile. The user's own travel data is the multi-part data owned by the deployed travel application, such as the user's itinerary data mentioned above.

[0153] In addition, users' own travel data also includes user information on travel applications, embedded data on travel applications, statistical data based on travel data, users' commercial operation data on travel applications, user-related product data, etc., which are not listed here one by one.

[0154] For example, the user's tracking data on the travel application is used to describe the user's clicks on the exposed products; the user information on the travel application includes gender, age, region and occupation; the statistical data based on travel data may specifically include but is not limited to the total number of rides in the past 77 / 14 / 30 / 90 days, the total ride duration in the past 7 / 14 / 30 / 90 days, the average arrival time of the first trip on weekdays in the past 7 / 14 / 30 / 90 days, the average departure time of the last trip on weekdays in the past 7 / 14 / 30 / 90 days, the average commuting distance in the past 7 / 14 / 30 / 90 days, the total number of rides, and the TOP10 high-frequency stations.

[0155] User business operation data on travel apps, including but not limited to: total number of business benefits redeemed, total number of business benefits redeemed, total amount of business benefits redeemed, average customer order value of business benefits redeemed, total number of travel benefits redeemed, number of card vouchers redeemed, and card usage frequency;

[0156] User-related product data may include but is not limited to: the top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, the corresponding number of times the top 10 product categories were viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, and the average price of the top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days).

[0157] It should be understood that the user's own travel data will be adapted to the input of product recommendations made by the travel application to shops to obtain a corresponding user portrait.

[0158] The source of user profiles is not limited to the user's own travel data, but can also come from third-party supplementary data. In short, user profiles correspond to the user's own travel data, as well as a combination of own travel data and third-party supplementary data.

[0159] Third-party supplementary data includes, but is not limited to, whether the individual is pregnant or having children, the degree of gaming interest, whether the individual is budget-conscious, whether the individual is a high-net-worth individual, whether the individual frequently flies, whether the individual is interested in financial management, whether the individual is interested in the anime, whether the individual is budget-conscious, whether the individual is a "phone addict", whether the individual likes to go shopping in supermarkets, whether the individual likes to take the children out for a walk, whether the individual is willing to buy a car, whether the individual has a hospital to buy a house, whether the individual likes to visit museums, whether the individual likes to visit historical and cultural attractions, whether the individual likes to visit natural scenic areas, and other data.

[0160] During the execution of step S3011, for each user corresponding to the store, a user portrait is obtained through the user's own travel data, or a combination of the user's own travel data and third-party supplementary data, and then the user portrait is used as the user feature in the constructed user-product pair.

[0161] In other words, the user portrait digitized by the user's own travel data, or the combination of the user's own travel data and third-party supplementary data, will serve as the user feature and constitute a user-product pair together with the product features of the product to be launched.

[0162] The product features of the products that can be put on the shelves are used to describe the features of the products that can be put on the shelves. For example, the product features of the products that can be put on the shelves include product descriptive features, statistical features, and statistical generalization features of the products that can be put on the shelves.

[0163] Specifically, the product characteristics of the products that can be put on the shelves include the first / second / third-level category to which the products can be put on the shelves, the price of the products that can be put on the shelves, the number of exposures of the products that can be put on the shelves in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the products that can be put on the shelves in the past 1 / 3 / 7 / 14 / 30, the number of purchase conversions of the products that can be put on the shelves in the past 1 / 3 / 7 / 14 / 30, the number of days that the products can be put on the shelves, the number of exposures of the third-level category to which the products can be put on the shelves in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the third-level category to which the products can be put on the shelves in the past 1 / 3 / 7 / 14 / 30, and the number of purchase conversions of the third-level category to which the products can be put on the shelves in the past 1 / 3 / 7 / 14 / 30.

[0164] Through step S3011, a user-product pair is constructed for each user in the store through the user portrait and the product features of the products that can be put on the shelves. Therefore, the click rate of the user on the products that can be put on the shelves can be predicted based on the user-product pair.

[0165] It should be understood that shops are physical resources that actually exist offline. Users are attracted by the exposure of shelf-ready products in shops, which is analogous to clicks on products exposed on the Internet. Therefore, the degree of attraction of shelf-ready products to users through offline exposure of shelf-ready products in shops can be accurately measured by the click-through rate of users on the shelf-ready products.

[0166] In step S3012, the pre-built click-through rate prediction model is used to predict the click-through rate of user-product pairs to obtain the click-through rate of users on available products. It should be understood that the click-through rate of users on available products is the probability that the user is attracted to the available products.

[0167] For a shop, each of its corresponding users will construct a user-product pair, and also use the constructed user-product pairs to predict the click-through rate of the corresponding products. By analogy, the click-through rate of each user pair of products that can be put on the shelves among all users corresponding to the shop can be obtained.

[0168] After the execution of step S302, the click rate of each user on the available products is estimated among all users corresponding to the available products in the shop, step S302 can be executed to accumulate the click rates corresponding to all users to obtain the expected click value of the available products in the shop.

[0169] The click-through rate refers to a single user, while the expected click value of a product on a store corresponds to a user group, which includes all users corresponding to the store.

[0170] The expected click value of a product available on a store for a user group is used to indicate the appeal of that user group to that product. In other words, the expected click value of a product available on a store for a user group also reflects the level of interest in the product among the user group passing through the store.

[0171] All users corresponding to the shop obtained through the aforementioned step S110 constitute a user group that can be regarded as the user group owned by the shop. The product recommendation for the shop based on the user group should consider the degree of fit between the available products and the user group. The click-through rate estimation between users and available products and the cumulative calculation based on this will accurately quantify the degree of fit between the available products and the user group, and then determine what kind of products each shop should candidate for listing, which greatly ensures the accuracy of product recommendations in the shop and the effectiveness of product listing.

[0172] For product recommendations of a store, the execution of step S120 realizes a rough sorting of products that can be put on the shelves, so as to obtain candidate products for putting on the shelves, i.e., products that may be attracted by passing users, thereby further narrowing the selection range of products for the store's product recommendations.

[0173] In step S130, a refined ranking is performed based on the candidate listing products to obtain the store's listing products and accurately quantify the placement value of the listing products in the store. It should be understood that the quantified placement value is relative to all users corresponding to the store.

[0174] Exemplarily, a refined ranking binary classification model is pre-built and trained to perform click-through rate estimation for each candidate product for all users corresponding to the store, and obtain a secondary estimated value of the click-through rate of each user for the candidate product.

[0175] It should be understood that for a candidate product, each user corresponding to the store will obtain the secondary estimated value of the user's click-through rate for this candidate product through the precise ranking binary classification model. Similarly, the secondary estimated values ​​of the click-through rate of all users for this candidate product can be obtained and accumulated to obtain the secondary estimated value of the click-through rate of all users corresponding to the store for this candidate product.

[0176] Several candidate listing products corresponding to the secondary estimated values ​​of high click rates are used as the store's listing products to achieve precise ranking of the candidate listing products.

[0177] After identifying the products on the shelves of the store, the placement value of each product on the shelves can be calculated based on its corresponding secondary estimated click-through rate, click value and the number of exposures of the product on the shelves in the store.

[0178] Specifically, see Figure 6 , Figure 6 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of obtaining the store's listed products and the placement value of the listed products in the store by accurately sorting the estimated conversion values ​​of candidate listed products through store portraits.

[0179] The step S130 of accurately ranking the estimated conversion values ​​of candidate listings based on the store portrait to obtain the store's listings and the placement values ​​of the listings in the store provided in the embodiment of the present application includes:

[0180] Step S131, secondary estimating the click-through rate of all users corresponding to the shop for the candidate listed products to obtain a secondary estimated value of the click-through rate;

[0181] Step S132: Adapting the high click-through rate secondary estimated value to finely sort the candidate listing products and filter out the store's listing products;

[0182] Step S133 , calculating the placement value of the products on the shelves in the store according to the corresponding secondary estimated click rate, click value, and the number of exposures of the products on the shelves in the store.

[0183] These steps are described in detail below.

[0184] First of all, it should be explained that under the action of the fine ranking binary classification model that implements the secondary estimation of the click rate of the candidate listing products, the fine ranking candidate product set, namely the aforementioned candidate listing products Invest in the fine sorting two-classification model select Predictions are made to obtain a secondary estimate of the click-through rate of the candidate products for all users of a specific store, and the products are then screened out.

[0185] For the products listed in the precise ranking, the secondary estimated click rate, click value and exposure times of the products in the store are calculated. Perform weighted summation to obtain the estimated value of the product being put on the shelf in the store, that is, Among them, n user is the number of users of this shop, ctv j is the click value of the listed product, is the number of exposures of user i in time T.

[0186] To further illustrate, the problem loss function for the t-th iteration of the refined binary classification model is constructed as follows:

[0187]

[0188] in, is the predicted value of the ijth record in round t, f t is the t-th tree, f t (x) = w q (x), q represents the tree f t The structure of w is a tree f t The weight of the leaf is w i To represent the weight of the i-th leaf, Ω(f t ) is about the tree f t The complexity of the regular term, then L (t) At the point The second-order approximation is:

[0189]

[0190] in,

[0191] So far, the optimal solution to the problem is:

[0192]

[0193] Where q is a tree with a fixed structure, γ and λ are the first-order and second-order regularization coefficients, respectively.

[0194] The optimal solution of each round based on the training data set can be iteratively converged to obtain the refined binary classification model model select .

[0195] After obtaining the store's listed products and their placement value in the store through step S130, in step S140, a store's listed product processing strategy is generated for the selected products and / or purchased products in the listed products.

[0196] During the execution of step S140 , all purchased commodities and unselected but available commodities of the store are enumerated, ie, the commodities are selected, and corresponding commodity putting-on-shelf processing strategies are generated respectively.

[0197] Exemplarily, step S140 includes: enumerating the purchased goods of the store, generating a shelf product processing strategy for displaying the purchased goods in a conspicuous position in the store for the purchased goods with high investment value, and generating a shelf product processing strategy for no longer purchasing or returning or exchanging the purchased goods with low investment value.

[0198] Exemplarily, step S140 includes: enumerating the product selections of the store, and generating a product listing processing strategy for the store's replenishment needs for the product selections with high investment value.

[0199] Based on this, the display position of the purchased goods can be adjusted. For example, the goods with high estimated marketing value can be displayed in a more prominent position in the store. For the purchased goods with low estimated marketing value, the customer can choose not to purchase them or even return or exchange them.

[0200] You can also use this as a basis to generate replenishment demand and choose to replenish products with high investment value.

[0201] At this point, we will build an intelligent product recommendation system for merchants based on the merchant traffic generated by users, so that merchants can dynamically select products and achieve high customer traffic conversion.

[0202] And for the owners, the implementation of this application can also help merchants achieve good performance, which in turn helps to stabilize or even improve the owners' shop rental business.

[0203] The following describes a specific example of a product recommendation implementation in commercial operations provided by this application.

[0204] First, for a shop, a shop portrait is obtained based on all its corresponding users, which is used to form user-product pairs on the shop with the constructed product features, and then the estimated click-through rate is obtained.

[0205] Specifically, the user's itinerary table and gate information table are used to obtain the distribution of the number of times a user exits a station at a gate group. If a user exits a station by scanning a QR code using a travel app, the distribution of the number of times the user scans the code at each gate group describes the number of times the user scans the code at each gate, thus obtaining the user's gate group scan table.

[0206] That is to say, the user's travel table is associated with the gate information table through the gate code to obtain the user's gate group code table.

[0207] Based on the user gate group code swiping table, the distribution of the user's code swiping at this group of gates can be known, and the distribution of the user's code swiping at this group of gates will indicate the user's exit direction.

[0208] Combined with the gate group entrance and exit distance relationship described in the gate group entrance and exit distance relationship table, the exits to which the gate group points in different directions can be known, and the user's frequently used exits can be determined, and the user's recently frequently used exit table can be obtained.

[0209] For each exit, the shop mapped to the exit is recorded to build and maintain a shop exit relationship table.

[0210] By mapping the exits to the shops, we can know the shops that users will pass by when they leave the station from a certain exit. In other words, all users who pass by a shop are all users corresponding to that shop.

[0211] Assign the user portraits of all users corresponding to the shop to the shop, further enrich its labels, and obtain the shop portrait table.

[0212] At this point, the most suitable products for the store can be found, thereby realizing dynamic product selection and shelf recommendations for the store.

[0213] It should be further explained that all users corresponding to the shop can determine the commonly used exit gates through the statistics of the user's preferred exit direction in the user gate group code scanning table, and then use this to determine all the users corresponding to the shop.

[0214] In addition, if the user has fewer trips in the user itinerary, for example, the number of times the user exits the station gate group is less than the set threshold, it will be necessary to determine the user's preferred exit direction through the distribution of the user's exit times at each gate of the station gate group and the user portrait through a binary classification model, and then determine the user's exit gate in this exit direction.

[0215] A pre-trained binary classification model is used to determine the probability of the user belonging to each exit, and the probability is then used to determine the user's exit. For example, the pre-trained binary classification model can be characterized by the distribution of the number of times a user exits each gate at the station and the user's profile. This feature is annotated with a corresponding direction value based on the direction the user travels after exiting the station. Each direction value uniquely corresponds to an exit accessible from the gate.

[0216] For example, if the user in the feature mapping passes to the left after exiting the gate group, the marked direction value is 0; correspondingly, if the user in the feature mapping passes to the right after exiting the gate group, the marked direction value is 1.

[0217] Based on this, construct the training data set

[0218] Among them, each training data set D train In a single record It is the feature of this record, which is used to describe the user status of the corresponding user.

[0219] Specific It includes the distribution of the number of times a user exits each gate in a site gate group at a certain time and the user portrait, and the user portrait can be represented by multiple user tags. is the characteristic of user i in gate group j, R m is the m-dimensional feature of user i.

[0220] For example, x ij ∈R m=[date (YYYYMM), user tag 1 of user i, user tag 2 of user i, ..., user tag n of user i label , the number of times user i exits the station at gate 1 of gate group j, the number of times user i exits the station at gate 2 of gate group j, ..., the number of times user i exits the station at gate n of gate group j zj Number of outbound trips], date (YYYYMM) represents the month, such as 202312, which represents December 2023. The date feature indicates the time range corresponding to other features. label Refers to the nth label User tags, that is, n r Represents the number of users, n i represents the number of gate groups that user i faces when exiting the station during travel, n label Represents the number of user tags, y ij ∈{0,1} is the direction value of the feature annotation in a single record of the corresponding training dataset. ij ∈{0,1} represents the final exit direction of user i under the corresponding features (especially the actual number of exits).

[0221] That is, y in a single record of the training dataset ij is the marked direction value. For example, if user i turns left after exiting gate group j, then y ij =0, if going right, then y ij =1.

[0222] By training the model with the constructed training data set, a model is obtained that can accurately predict the user's exit, providing users with accurate judgment of their exit affiliation. There is no need to obtain location, that is, it is no longer restricted by GPS positioning and the acquisition of location permissions.

[0223] Furthermore, the training for exit prediction is performed on gate groups corresponding to a single exit. A training dataset is constructed for each gate group, and features are constructed based on all records related to that gate group. These features are annotated with direction values ​​based on the gate group's unique orientation.

[0224] Specifically, the number of times the user exits each gate of the gate group in the site is obtained through the travel data and gate information, that is, the user gate group exit data of user-site-gate group-gate-exit times is obtained, which can be in a tabular form, that is, a table maintained according to fields such as user, site, gate group, gate, and exit times, and the user gate group exit data corresponding only to the unique exit is obtained therefrom, and the number of times the user exits each gate of the gate group at the site is obtained from the user gate group exit data corresponding only to the unique exit, and the feature is constructed based on this.

[0225] In addition, the corresponding user portraits will be extracted for feature construction, and the constructed features will be labeled with direction values ​​to finally form a training data set.

[0226] The constructed training dataset shields the influence of other exits and only considers the prediction of the user's exit in the feature dimension, so that subsequent predictions will not be affected by other factors, which will greatly improve the accuracy and reliability of the prediction.

[0227] Exemplarily, a gate group entrance and exit distance relationship will also be constructed. The gate group entrance and exit distance relationship is used to indicate the distance of each gate of the gate group in a site relative to the exits in each direction. Therefore, after predicting the most likely direction for the user to exit the gate, it can be directly mapped to the closest exit based on the gate group entrance and exit distance relationship. This exit is the exit to which the predicted user belongs.

[0228] As previously mentioned, the model trained using the constructed training dataset can be a binary classification model. This binary classification model is then used to predict a user's assigned exit gate. Specifically, the binary classification model predicts the user's most likely exit direction from each gate group based on the user's exit count at each gate group and the user's profile. The exit gate mapped to this direction is then used as the user's assigned exit gate.

[0229] Further explanation: the number of times users exit each gate at the site gate group and the user profile are used to construct a prediction data set. Among them, unlike the training dataset, the prediction dataset is not limited to the gate group corresponding to a unique exit; in other words, it will not distinguish whether the gate group corresponds to a unique exit. All user data will be used to construct the prediction dataset, and then the features of the constructed prediction dataset will be used to predict the exit to which the user belongs.

[0230] Prediction dataset D predict In each record Represents the characteristics of user i in gate group j whose exit gate has not yet been determined. As mentioned above, this characteristic describes the number of exits of user i at each gate in gate group j and the user tag. The characteristic list included is the same as similar.

[0231] Based on the obtained two-class model, the prediction dataset D predict Each record of Use the binary classification model to implement predictions one by one, and obtain the probability that the characteristics of user i in gate group j are biased in one direction, that is, the probability that the user i belongs to the exit corresponding to gate group j.

[0232] For example, if the gate group j corresponds to two exits. In other words, after exiting the station through the gate group j, user i has two directions, each direction corresponds to an exit. If the user i leans towards the other direction, the probability of him belonging to the other exit is

[0233] In addition, if there are more than two exits in one direction of gate group j, that is, the exit in this direction is not unique, then when the binary classification model predicts that user i tends to go in a direction with more than two exits after exiting gate group j, the exit that user i is most likely to pass through will be determined based on the traffic flow of each exit, and this exit is the exit to which user i belongs.

[0234] Specifically, each exit in one direction has its own flow rate, which can be detected by the passenger flow counter installed at the exit. The flow rate corresponding to each exit is used to determine the flow ratio of each exit, and then the exit to which user i belongs is determined based on the flow ratio.

[0235] Therefore, after the user's belonging exit is determined, the user's travel trajectory is mapped to the belonging exit according to the user's belonging exit, and the user's itinerary during travel will also be mapped to this exit.

[0236] In other words, for the exit corresponding to the travel trajectory, on the one hand, we can know which users have passed through this exit, and then we can match these users to the positions on this exit, that is, determine which users correspond to the positions on this exit, and match the user portraits of these users to the positions on this exit, such as media positions, shop positions, etc.

[0237] On the other hand, the exit corresponding to the travel trajectory provides the tracked travel trajectory within the station, breaking away from the restricted GPS positioning and the required location permissions, and can also obtain the user's in-station trajectory, enhancing the in-station tracking performance.

[0238] As the user's travel trajectory out of the station and their itinerary can correspond to the exit, the user is aggregated at the location at the exit, and the aggregated user is assigned to the location at the exit.

[0239] The user aggregation referred to here is to determine the corresponding user group for the location at the exit, and to describe and characterize the aggregated user group through the user profiles of the aggregated users.

[0240] The travel trajectory is mapped to the corresponding exit, so that the corresponding user trip can be mapped to the exit, and then the user who generated the user trip is also mapped to the exit, so that the users corresponding to the same exit are aggregated.

[0241] The exit-mapped location refers to the location at the exit. For example, in terms of location type, this location includes but is not limited to media locations and store locations. Geographically, the exit-mapped location refers to any location in the direction of the exit, such as a location within the station in the direction of the exit, an exit passage in the direction of the exit, or a location outside the station that exits the exit.

[0242] In terms of data, users exist in the form of user portraits and their travel trajectories. Therefore, user aggregation is achieved in the form of travel trajectories and user portraits, and the user portraits corresponding to the aggregated users are assigned to the location mapped by the exit, so as to accurately locate and describe the user characteristics of the location through the assigned user portraits. For example, the user portraits of the aggregated users are assigned to shops to construct corresponding shop portraits.

[0243] For the obtained shop portrait, a click-through rate prediction recommendation algorithm will be used for each user corresponding to the shop. That is, the constructed click-through rate prediction model will estimate the click-through rate of the products to be placed on the shop, and then the click-through rate on the shop will be accumulated to obtain the expected click value, that is, the shop product click-through rate estimation table will be obtained.

[0244] The expected click value of the products to be placed in the store is provided through the store product click rate estimation table, and the conversion value of the products in the store is obtained by combining the click value of the products, and the store product conversion value table is obtained, which is finally used to execute product recommendations.

[0245] It should be noted that the click-through rate prediction recommendation algorithm, that is, the click-through rate prediction model, is trained based on online product exposure click data from platforms such as travel applications. The training data set and the product features of the products to be launched are obtained from the constructed product label table, which will not be repeated here.

[0246] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0247] In an exemplary embodiment of the present application, a computer program medium is further provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the method described in the above method embodiment.

[0248] According to one embodiment of the present application, a program product for implementing the method in the above method embodiment is also provided. The program product may be a portable compact disc read-only memory (CD-ROM) and includes program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0249] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0250] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0251] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0252] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0253] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0254] Furthermore, although the steps of the method of the present application are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0255] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0256] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

Claims

1. A method for recommending products in commercial operations, characterized in that: The method comprises: Obtain a shop profile of the shop by determining all users who pass through the shop during business, wherein the shop profile includes a user profile of each user; Estimated click-through rate of available products for each user among all users who pass by the store; The click-through rates are accumulated to obtain the conversion value of the available products being exposed on the shop shelves; Based on the estimated conversion value, select products with high conversion value from the available products as candidate products for listing; Secondarily estimating the click-through rate of the candidate listed products by all users corresponding to the store to obtain a secondary estimated value of the click-through rate; Adapting the high click-through rate secondary estimated value to finely sort the candidate listing products and filter out the listing products of the store; Calculate the placement value of the listed products in the store based on the corresponding secondary estimated click-through rate, click value, and the number of exposures of the listed products in the store; A shelf merchandise processing strategy for the store operation is generated by adapting to the two types of shelf merchandise, namely, purchased merchandise and selected merchandise.

2. The method according to claim 1, characterized in that The step of obtaining a shop profile of a shop by determining all users passing through the shop during business, includes: For a shop in a commercial area, obtain all corresponding users according to the exit corresponding to the shop at the site; The user portraits of all users corresponding to the exit are assigned to the shop to form a shop portrait of the shop.

3. The method according to claim 1, characterized in that The estimated click-through rate of all users passing through the store for available products includes: For all users who pass by the shop, the user-product pairs of the shop are constructed based on the user portraits and the product features corresponding to the available products; By predicting the product click-through rate of the user-product pair, the click-through rate of each user for the available products among all users corresponding to the store is obtained.

4. The method according to claim 1, wherein The listed products include purchased products. The two types of listed products, purchased products and selected products, are adapted to generate a listed product processing strategy in the store operation, including: The purchased goods of the store are enumerated, and a shelf-product processing strategy is generated for purchased goods with high investment value, in which the purchased goods are displayed in a conspicuous position in the store; and a shelf-product processing strategy is generated for purchased goods with low investment value, in which the purchased goods are not to be purchased or are returned or exchanged.

5. The method according to claim 1, wherein The product listing includes product selection, and the product listing processing strategy for the store operation is generated by adapting the two types of purchased products and selected products, including: The product selections of the store are enumerated, and a product listing processing strategy for the store's replenishment needs is generated for the product selections with high investment value.

6. A product recommendation system for commercial operations, the system comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

7. A computer program product comprising a computer program, characterized in that The computer program is used by a processor to execute the steps of the method according to any one of claims 1 to 5.

Images