Method and system for realizing merchant site selection recommendation in commercial operation, medium and product

Abstract

The invention provides a method and a system for realizing merchant site selection recommendation in commercial operation, a computer readable storage medium and a computer program product. The method and the system are oriented to merchants, by means of symbolic dominating commodities of the merchants, merchant portraits are obtained through feature construction and similar commodity retrieval, and the merchant site selection recommendation is realized. The method comprises the following steps: pre-estimating the site selection value of each selectable shop on the basis of a merchant portrait, obtaining the site selection value of the merchant on each selectable shop, determining the maximum site selection value from the site selection value, and finally taking the selectable shop with the maximum site selection value as the final site selection shop, so that the whole process is based on the objectively existing merchant portrait. Value estimation of merchants on offline shops is realized, and accurate, objective and high-timeliness merchant site selection recommendation is achieved.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and specifically to a method and system for implementing merchant site selection recommendations in commercial operations, a computer-readable storage medium, and a computer program product. Background Art

[0002] The process of merchants selecting locations in travel business to determine suitable shop locations is based on the merchants' own subjective experience, for example, surveying the crowds passing by each shop location based on the merchants' subjective experience; on the other hand, they can also obtain the accumulated experience of travel owners, such as subways, buses, airplanes, ships, etc.

[0003] This will lead to disadvantages in the location selection of shops for merchants. For merchants, the accuracy of crowd surveys based on their own subjective experience varies from person to person and takes a long time; for the accumulated experience provided by travel owners, it is also limited by the richness and timeliness of the travel owners' own data, and it is difficult to guarantee accuracy and timeliness.

[0004] In short, merchants rely on manual labor to select store locations in their travel business operations, and are unable to implement merchant location recommendations accurately, objectively, and efficiently. Summary of the invention

[0005] One purpose of this application is to avoid merchants from relying on manual labor in store site selection during commercial operations, and to implement merchant site selection recommendations accurately, objectively and promptly.

[0006] According to one aspect of an embodiment of the present application, a method for implementing merchant site selection recommendation in commercial operations is disclosed, the method comprising:

[0007] Constructing an initial set of commodities for the merchant's iconic flagship commodities, wherein the initial set of commodities includes commodity features constructed for each of the merchant's iconic flagship commodities and corresponding commodity weights;

[0008] The merchant's commodity set is constructed by searching similar commodities in the constructed commodity library through the initial commodity set, and the commodity set is used to characterize the merchant's portrait;

[0009] The merchant portrait is used to estimate the location value of the merchant in each optional store, and the optional store with the maximum location value is selected as the final location store.

[0010] According to one aspect of the embodiment of the present application, the initial set of commodities is constructed for the merchant's iconic flagship commodities, including:

[0011] Constructing a representation vector for each iconic flagship product of the merchant to obtain product features of the iconic flagship product;

[0012] A weight is assigned to each iconic flagship product, and an initial set of products of the merchant is formed based on the product features and weights of the iconic flagship products.

[0013] According to one aspect of the embodiment of the present application, constructing a representation vector for each iconic flagship product of a merchant to obtain product features of the iconic flagship product includes:

[0014] Determine whether there is a pre-built product tag for the iconic flagship product, and if so, extract the product tag corresponding to the iconic flagship product;

[0015] The product features of the iconic flagship product are obtained by using the product label as a representation vector.

[0016] According to one aspect of the embodiment of the present application, constructing a representation vector for each iconic flagship product of a merchant to obtain the product features of the iconic flagship product further includes:

[0017] If there is no pre-constructed product tag for the iconic main product, a characterization vector of the iconic main product is constructed according to the pre-constructed product tag, and the characterization vector is used as the product feature of the iconic main product.

[0018] According to one aspect of an embodiment of the present application, the step of constructing the merchant's product set by searching similar products in the constructed product library through the initial product set includes:

[0019] Searching for similar products in the product library for each iconic main product in the initial set of products, to obtain similar products to the iconic main product;

[0020] Acquire the product tags of the similar products as product features of the similar products, and configure corresponding weights;

[0021] The initial set of commodities is expanded with the commodity features and weights of the similar commodities to obtain the commodity set of the merchant.

[0022] According to one aspect of the embodiment of the present application, estimating the site selection value of the merchant in each optional shop based on the merchant portrait, and obtaining the optional shop with the maximum site selection value as the final site selection shop includes:

[0023] For all users corresponding to the optional shops, the location value of the shop in the optional shops is estimated through the shop portrait;

[0024] The maximum site selection value is determined from the site selection values ​​of the optional shops, and the optional shop with the maximum site selection value is taken as the final site selection shop.

[0025] According to one aspect of an embodiment of the present application, estimating the location value of the merchant in the optional shops for all users corresponding to the optional shops includes:

[0026] By determining all users who pass through the optional shops during business, a shop portrait of the optional shops is obtained, wherein the shop portrait includes a user portrait of each user;

[0027] Through the store portrait, the conversion value of the product set representing the merchant portrait placed in each optional store is estimated to obtain the conversion value of the merchant in the optional store, and the conversion value is used as the location value of the merchant in the optional store.

[0028] A system for implementing merchant site selection recommendations in commercial operations, the system comprising a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the steps of the method described above.

[0029] According to one aspect of an embodiment of the present application, a computer-readable storage medium is disclosed, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0030] 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 implement the steps of the method described above.

[0031] The embodiments of the present application can provide merchants with site recommendations in business, so that the store site selection can avoid subjective human intervention, accurately, objectively and efficiently achieve the store site selection in business, and ensure that the final site selection store has high conversion value for the merchant.

[0032] To further explain, the embodiment of the present application is aimed at merchants. With the help of the merchant's iconic flagship products, a merchant portrait is obtained through feature construction and similar product retrieval. The location value of each optional shop is estimated based on the merchant portrait, and the merchant's location value for each optional shop is obtained. The maximum location value is determined therefrom, and finally the optional shop with the maximum location value is selected as the final location shop. The whole process is based on the objectively existing merchant portrait, which realizes the value estimation of the merchant's offline shops, and further achieves accurate, objective and highly timely merchant site selection recommendations.

[0033] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other objects, features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0036] Figure 1 A flow chart of a method for implementing merchant site recommendation in commercial operations according to an embodiment of the present application is shown.

[0037] Figure 2 is based on Figure 1 A method flow chart describing the steps of constructing an initial set of commodities for a merchant's iconic flagship commodities as shown in the corresponding embodiment.

[0038] Figure 3 is based on Figure 2 A flowchart of a method for constructing a representation vector for each iconic flagship product of a merchant to obtain product features of the iconic flagship product as shown in the corresponding embodiment.

[0039] Figure 4 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of constructing a merchant's product set by searching similar products in a constructed product library through an initial set of products.

[0040] Figure 5 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of estimating the site selection value of the merchant in each optional shop based on the merchant portrait, and obtaining the optional shop with the maximum site selection value as the final site selection shop.

[0041] Figure 6 is based on Figure 5 The corresponding embodiment shows a method flow chart describing the steps of obtaining store portraits of optional stores by determining all users who pass through the optional stores during business.

[0042] Figure 7 is based on Figure 5 The corresponding embodiment shows a method flow chart for estimating the conversion value of the product set representing the merchant portrait placed in each optional shop through the shop portrait, obtaining the conversion value of the merchant in the optional shop, and describing the steps of using the conversion value as the location value of the merchant in the optional shop.

[0043] Figure 8 is based on Figure 7 The corresponding embodiment shows a method flow chart describing the steps of estimating the click rate of each user on the products in the product set among all users passing through the optional stores, and obtaining the click rate of each user on each product in the optional stores. DETAILED DESCRIPTION

[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present application will be more comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0045] 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 solution 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 present application and making the various aspects of the present application obscure.

[0046] 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 can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0047] There are many travel routes in a city, and there are many stations on each route, such as subway, bus, bicycle stations, or stations for airplanes, ships and other modes of transportation. There are many shops inside and outside each station, and merchants will choose a shop to sell their goods.

[0048] When merchants are making decisions about choosing a shop, they often need to survey the people passing by each available shop. Their own judgment of the people passing by will serve as a reference for choosing the location of the shop.

[0049] On the other hand, owners who operate commercial businesses and provide rental shops will also provide consulting services to merchants based on their accumulated experience or research data.

[0050] However, whether it is for owners or merchants, if they only rely on experience, they will be limited by their own subjective cognition and there will be inaccuracies; if they use survey data, there will often be problems with the survey data being insufficient and time-sensitive, which will lead to inaccurate store location selection.

[0051] It should be understood that the survey data obtained, whether it is obtained from merchants or owners, requires a certain amount of financial and human resources. Therefore, it is difficult to ensure stable and high-frequency updates, which is often out of time for merchants' site selection, resulting in the lack of timeliness and accuracy in the site selection of shops made by merchants based on survey data.

[0052] Based on this, the embodiment of the present application provides a method for implementing merchant site selection recommendations in commercial operations, thereby enabling accurate, objective and highly timely site selection recommendations to merchants.

[0053] See also Figure 1 , Figure 1 A flowchart of a method for implementing merchant site selection recommendation in commercial operation according to an embodiment of the present application is shown. A method for implementing merchant site selection recommendation in commercial operation provided by an embodiment of the present application includes:

[0054] Step S110, constructing an initial set of products for the merchant's iconic main products, the initial set of products including product features constructed for each of the merchant's iconic main products, and corresponding product weights;

[0055] Step S120, constructing a merchant's commodity set by searching similar commodities in the constructed commodity library through the initial commodity set, and the commodity set is used to characterize the merchant's portrait;

[0056] Step S130, estimating the merchant's location value in each optional store based on the merchant portrait, and obtaining the optional store with the maximum location value as the final location store.

[0057] These steps are described in detail below.

[0058] First of all, it should be noted that the commercial shops can be distributed inside and outside the station, for example, between the exit gate and the exit, and around the exit. In other words, the commercial shops are optional shops for merchants to choose and then use to sell goods.

[0059] In order to enable merchants to accurately select shops that are suitable for their own portraits, suitable shops will be recommended to merchants based on the execution process of the embodiments of the present application.

[0060] In step S110, an initial set of products is first selected based on the merchant's iconic flagship products. The initial set of products is used to describe the merchant from the dimension of the products sold, to achieve initial portrait construction for the merchant who is currently selecting a store site, and further provide a basis for the site selection recommendation performed in this application.

[0061] The merchant's iconic flagship product is a representative product that the merchant will sell in the selected store. For example, the iconic flagship product is a relatively important product of the merchant, for example, a product that contributes relatively more to the merchant's sales. It can be adjusted according to actual conditions or customized by the merchant, and is not limited here.

[0062] For the iconic flagship products determined by the merchant, corresponding product features are constructed, and corresponding product weights are assigned to each product feature. The product features and corresponding product weights form the merchant's initial product set.

[0063] The construction of product features is the execution process of digitizing the product labels of iconic flagship products to obtain product label vectors. Product labels include product category, quantity, weight, brand, number of purchases in the last 1 / 3 / 7 / 14 / 30 days, unit price, cumulative consumption amount, whether it is a sports brand, whether it is a beverage, etc., which are not listed here one by one. The vector representation of product labels, that is, the product label vector is constructed as product features.

[0064] The commodity weight corresponding to the commodity feature is used to measure the importance of the corresponding commodity to the merchant. For example, the commodity weight can be a set value, or a value that changes dynamically to adapt to the merchant's operating conditions, or can be determined based on the conversion value of the corresponding commodity in the merchant. For example, the commodity weight can be the product of the click value of the commodity and the sales contribution of the commodity.

[0065] For each iconic flagship product of the merchant, product features are constructed one by one, and product weights are assigned. Then, the product features and product weights of each iconic flagship product are combined into a record to form an initial set of products corresponding to all iconic flagship products of the merchant.

[0066] Therefore, for merchants who are currently selecting locations, the merchant’s location recommendations will be initiated based on the merchant’s objectively existing iconic flagship products, and the merchant’s portrait will be built based on the merchant’s iconic flagship products, providing an objective basis for the location recommendation.

[0067] For example, the merchant planning to select a site provides a set of multiple iconic flagship products and their weights, namely, the initial set of products:

[0068]

[0069] Among them, pre means just the initial set of products, and weight is the weight of the corresponding product.

[0070] See also Figure 2 , Figure 2 is based on Figure 1A method flow chart describing the steps of constructing an initial set of commodities for a merchant's iconic flagship commodities as shown in the corresponding embodiment.

[0071] The step S110 of constructing an initial merchant set for the merchant's iconic flagship products provided in the embodiment of the present application includes:

[0072] Step S111, constructing a representation vector for each iconic flagship product of the merchant to obtain product features of the iconic flagship product;

[0073] Step S112, assigning a weight to each iconic flagship product, and forming an initial set of products of the merchant based on the product features and weights of the iconic flagship products.

[0074] As mentioned above, the merchant's initial set of products is a product sequence formed by the product features and weights of all iconic flagship products. That is, in the initial set of products, each iconic flagship product will be described by product features and corresponding weights to form an iconic flagship product sequence.

[0075] For merchants, by using the initial set of products, the merchants can be described by iconic flagship products represented by vectors, thereby providing merchants with timely and accurate site recommendation operations.

[0076] For further explanation, see Figure 3 , Figure 3 is based on Figure 2 A flowchart of a method for constructing a representation vector for each iconic flagship product of a merchant to obtain product features of the iconic flagship product as shown in the corresponding embodiment.

[0077] The step S111 of constructing a representation vector for each iconic flagship product of a merchant to obtain the iconic flagship product constructing vector to obtain the product features of the iconic flagship product provided in the embodiment of the present application includes:

[0078] Step S1111, determine whether there is a pre-built product label for the iconic flagship product, if yes, execute step S1112, if not, execute step S1113.

[0079] Step S1112, extracting the product label corresponding to the iconic flagship product;

[0080] Step S1113, constructing a characterization vector of the iconic main product according to the pre-constructed product label, and taking the characterization vector as the product feature of the iconic main product.

[0081] These steps are described below.

[0082] It should be understood that for a merchant's iconic flagship product, if there is a pre-constructed product label, the corresponding vectors of all labels of the product can be directly used to construct the product features.

[0083] The constructed product tag may exist in a pre-constructed product tag table, so that the product tag can be obtained by searching the product tag table, thereby quickly constructing the product.

[0084] If there is no pre-built product tag for a signature flagship product, it is necessary to refer to the pre-built product tags of other products to obtain the product features of the signature flagship product.

[0085] Therefore, for merchants planning to select a site, no matter what kind of iconic flagship product, they can construct corresponding product features for it, so as to realize the numerical description of the merchant, and then provide a highly reliable and accurate basis for site selection.

[0086] For merchants planning to select a location, the initial set of commodities is used as an initial basis, and the initial set of commodities is expanded in step S120 to obtain a richer set of commodities, thereby providing a richer description for the merchant.

[0087] In step S120, a commodity library is pre-constructed, and the commodity library contains commodity features and weights corresponding to a number of commodities. In other words, the commodity library contains a number of commodities, and each commodity is characterized by a corresponding commodity feature and weight.

[0088] For example, a product library can be constructed for all products with exposure and click data in the own data. The constructed product library can be composed of corresponding product identifiers, and each product is marked, and each product has a corresponding product label, and then a corresponding product feature is constructed.

[0089] The product features and weights of each product in the product library are used to expand the description of the merchant currently planning to select a location, so as to avoid the limited amount of data in the merchant's initial product collection, which fails to provide sufficient data support for subsequent recommendation operations, and ensure the reliability of the location recommendation.

[0090] For each product in the product library described by product features and weights, a similarity calculation is performed between the product and the merchant's iconic flagship product under the influence of the product features and weights to determine similar products in the product library to the merchant's iconic flagship product.

[0091] By searching for similar products in the product library based on the initial set of products, the obtained similar products will be used as an expansion of the iconic flagship products and form a product set with the initial set of products, thereby representing the merchant portrait with the product set.

[0092] See also Figure 4 , Figure 4 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of constructing a merchant's product set by searching similar products in a constructed product library through an initial set of products.

[0093] The step S120 of constructing a merchant's product set by searching similar products in the constructed product library through the initial product set provided in the embodiment of the present application includes:

[0094] Step S121, searching similar products in the product library for each iconic main product in the initial product set, to obtain similar products to the iconic main product;

[0095] Step S122, obtaining product tags of similar products as product features of similar products, and configuring corresponding weights;

[0096] Step S123, expanding the initial set of commodities with commodity features and weights of similar commodities to obtain the merchant's commodity set.

[0097] These steps are described in detail below.

[0098] In the execution of step S121, each iconic flagship product in the initial set of products is expanded, and the similar products obtained by the expansion are used to construct a product set based on the initial set of products.

[0099] As each iconic main product searches for similar products for each product in the product library, a number of similar products are obtained for each iconic main product.

[0100] For the similar products obtained, their product labels are used to construct product features. The initial set of products is expanded through the constructed product features and the assigned weights to obtain a product set. This product set will be used as a merchant portrait to describe the merchant from the dimension of the goods sold, and then recommend suitable shops.

[0101] Merchant portraits are obtained through the initial set of goods and the expanded set of goods, which can then provide a basis for site selection recommendations for the goods being planned for site selection quickly, objectively and accurately. This can enable quick recommendations for merchant site selection and ensure the effectiveness and reliability of the recommendations.

[0102] After obtaining the product set used to characterize the merchant portrait through the execution of step S120, the merchant's site selection value among various optional shops can be estimated for the merchant based on the merchant portrait in step S130, and then the shop with high site selection value is selected as the final site selection shop.

[0103] The location value between the merchant and each optional store is predicted to obtain the merchant's location value in each optional store. The merchant's location value in each optional store represents the estimated conversion value of the merchant choosing the store. Therefore, the greater the location value, the greater the sales volume and value of the goods sold by the merchant in the corresponding store.

[0104] Therefore, estimating the store location value based on the merchant portrait and then determining the final store location based on the size of the location value will enable merchants to obtain the most suitable store for selling iconic flagship products and other similar products.

[0105] For example, for the similar product retrieval algorithm, according to the number of products, a hyperparameter K∈N is given + , and randomly assign The K product representation vectors in the above example are used as the initial centers.

[0106] For each t cycles: Each vector in Mark this round as belonging to the category

[0107] Update the representation vectors of K centers:

[0108] Termination condition: The number of iterations reaches the preset threshold T or (Preset convergence threshold).

[0109] Finally, the optimal center set is obtained And each center The corresponding product representation vector

[0110] At this time, based on the similar product retrieval algorithm, the product feature x q ,calculate Get the product feature x q The most similar product, that is, similar product, and assign corresponding weight to this similar product.

[0111] In step S130, the estimation of the site value of the optional shops is performed for all users corresponding to the optional shops. For all users corresponding to the optional shops, the site value of the merchant in the optional shops is estimated through the merchant portrait.

[0112] All users corresponding to the optional goods refer to all users who pass by the optional shop. All users who pass by the optional shop are the consumers of the optional shop, and whether the goods placed by the merchant in the optional shop match all users determines the value that the merchant can convert from the placed goods in the optional shop. This value is the conversion value of the merchant in the optional shop, and this conversion value represents the location value of the optional shop for the merchant.

[0113] Based on this, during the execution of step S130, for each optional shop, the merchant's location value among the optional shops is estimated through the merchant portrait for all corresponding users, and then the maximum location value is determined, and the optional shop corresponding to the maximum location value is used as the merchant's final location shop.

[0114] That is Figure 5 As shown, Figure 5 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of estimating the site selection value of the merchant in each optional shop based on the merchant portrait, and obtaining the optional shop with the maximum site selection value as the final site selection shop.

[0115] The step S130 of estimating the site selection value of the merchant in each optional shop based on the merchant portrait provided in the embodiment of the present application and obtaining the optional shop with the maximum site selection value as the final site selection shop includes:

[0116] Step S131, by determining all users who pass through the optional shops during business, obtain the shop portraits of the optional shops, the shop portraits including the user portraits of each user.

[0117] Step S132, using the store portrait, estimate the conversion value of the product set representing the merchant portrait placed in each optional store, obtain the merchant's conversion value in the optional store, and use the conversion value as the merchant's location value in the optional store.

[0118] These two steps are described in detail below.

[0119] Through the execution of step S131, firstly, all users corresponding to each optional store are obtained, and all users corresponding to the optional store are all users passing through the optional store in the business. For each optional store in the business, the merchant's location recommendation will be implemented based on all users corresponding to it.

[0120] The user corresponding to the optional shop is traveling and his / her outbound travel trajectory is related to the corresponding optional shop, that is, the user travel profile of the user is related to the optional shop.

[0121] Specifically, the user travel portrait may include outbound travel trajectory, user itinerary, etc.; correspondingly, the user travel portrait is related to optional shops, which means that the outbound travel trajectory and user itinerary described in the user travel portrait can correspond to the locations of the optional shops.

[0122] For a selectable shop, after obtaining all the corresponding users, its user portrait can be obtained as the shop portrait.

[0123] See also Figure 6 , Figure 6 is based on Figure 5 The corresponding embodiment shows a method flow chart describing the steps of obtaining store portraits of optional stores by determining all users who pass through the optional stores during business.

[0124] The step S131 of obtaining a shop portrait of an optional shop by determining all users passing through the optional shop during business provided in the embodiment of the present application includes:

[0125] Step S1311, for the optional shops in the business, all corresponding users are obtained according to the exits corresponding to the optional shops at the station;

[0126] Step S1312, assigning user portraits of all users corresponding to the exit to the shop to form a shop portrait of the shop.

[0127] These two steps are described below.

[0128] According to the exit corresponding to the store at the station, the exit travel trajectory and / or the user itinerary corresponding to the exit are obtained to obtain all users corresponding to the store. Exemplarily, all users whose user itinerary and / or exit travel trajectory correspond to the location of the store are obtained for location recommendation of the store.

[0129] Exemplarily, the locations corresponding to the user's itinerary and / or exit trajectory are the locations that can be covered by the user's exit behavior. For example, all the locations that the user passes through when walking from the track area to the exit elevator to the exit gate, as well as the location of the user in the exit direction of the exit gate, and even the location on the exit channel of the exit to which the user belongs, and all the shops distributed on it are the shops corresponding to the user.

[0130] Obtain all users whose user itineraries and / or outbound travel trajectories correspond to the locations of shops, which are obtained by aggregating the locations corresponding to the user itineraries and / or outbound travel trajectories.

[0131] Mapping the 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.

[0132] At this point, the user's exit travel trajectory is first determined by the distribution of the number of times the user exits each gate in the station gate group; then the users are aggregated for the shops covered by the exit trajectory to obtain all the users corresponding to the shops. The aggregated users correspond to the exit travel trajectory covering the shop.

[0133] The user's entry and exit behaviors at the gate will generate corresponding user trips, which are stored in the trip data. In an exemplary embodiment, the trip data exists in the form of a user trip table. Each user trip generated when the user exits the gate is stored in the constructed user trip table.

[0134] 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.

[0135] The distribution of the number of exits at the station gate group is obtained for each user, so as to determine the exit direction or even the exit port that the user prefers, and then obtain the exit trajectory mapped by the preferred exit direction or even the exit port.

[0136] 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 from the left half group of gates tend to exit in one direction, while users exiting from the right half group of gates tend to exit in another direction.

[0137] According to 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 user's exit gate is then determined by the preferred exit direction. This exit gate is based on the distribution of the number of times the user exits the station at each gate group. Therefore, this exit gate is the user's commonly used exit gate.

[0138] 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.

[0139] 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, at gate n_zj in the gate group (n_zj is the number of gates in the entire gate group).

[0140] 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 user's exit times at each gate group at the site, so as to determine the user's preferred exit direction and exit port.

[0141] In an exemplary embodiment, if the number of exits and exits of a user at 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.

[0142] In a gate group, if users exit from this gate group more frequently, they will mostly exit from 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 frequent exits are located, the corresponding exit direction is the one preferred by the users.

[0143] 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 calculation complexity and improving execution efficiency.

[0144] The number of times a user exits a station gate group is used to determine whether the user exits the station frequently 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 each gate of the station gate group. In addition, it can also be obtained based on the user's user itinerary and gate information. Further, it can be obtained from the user gate group exit data constructed by the itinerary data constituted by the user's itinerary and the gate information, which is not limited here.

[0145] In another exemplary embodiment, if the number of exits of a user at a site gate group is less than a 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 site gate group and the user's portrait through a binary classification model, and then determine the exit gate to which the user belongs in this exit direction.

[0146] Exemplarily, the set threshold may be 5, that is, if the number of exits and exits of a gate group at a station is not less than 5 times within the set time range, it means that an exit direction corresponding to the gate group and the exit gate in the exit direction are both consistent with the user's exit passage, thereby determining that the exit gate is the user's frequently used exit gate.

[0147] If the number of times a user exits a site gate group is less than the set threshold, it means that neither the site nor the gate group is frequently visited by users. Therefore, it is necessary to construct features based on richer data, that is, the distribution of the number of times a user exits each gate in the site gate group and the user portrait as mentioned above, and then implement predictions through a pre-built model.

[0148] To further illustrate, the step of determining the user's exit travel trajectory by the distribution of the number of exits of the user at each gate of the station gate group is specifically performed as follows, namely:

[0149] (1) Determine the exit gate to which each user belongs based on the distribution of the number of times the user exits the station at the station gate group and the user profile;

[0150] (2) The user's travel trajectory is mapped to the exit, and the exit trajectory of the user passing through the exit is obtained.

[0151] Regarding this execution process, it should be explained first that a binary classification model is pre-built to predict the user's preferred exit direction. Then, based on the distribution of the number of times the user exits the station gate group and the user portrait, the binary classification model can predict whether the user will go left or right after exiting the gate group, thereby determining the user's preferred exit based on the exit in the direction of travel.

[0152] For each user, the exit gate to which the user belongs will be determined based on the distribution of the number of exits at the station gate group and the user portrait.

[0153] The exit gate to which the user belongs indicates the travel trajectory of the user after exiting the station from the gate. In other words, by mapping the existing travel trajectory to the determined exit gate, the exit trajectory of the user passing through the exit gate can be obtained.

[0154] Based on this, each user will determine the exit they frequently use during their travels. Therefore, for product recommendations in shops, shops whose locations correspond to the users' exit trajectories will expose their products to these users. Therefore, the placement of products in shops will be targeted at these users. Product recommendations based on exit trajectories will help improve the accuracy of product placement in shops.

[0155] After the user's outbound travel trajectory is determined, the users can be aggregated for the shops covered by the outbound travel trajectory, thereby obtaining all users corresponding to the shops.

[0156] In other words, as the product recommendations in the shops are made, the users at the location of each shop will be aggregated to determine the target group of the shop.

[0157] The outbound travel track covers at least one store. In other words, several stores are located on the outbound travel track of the user, so the user's user trip can be mapped to the store on the outbound travel track.

[0158] For each shop, the shop's users are aggregated according to their outbound travel trajectories, that is, the users whose outbound travel trajectories cover this shop are aggregated together, that is, the aggregated users correspond to one shop.

[0159] It should be understood that for users, along with their inbound and outbound behaviors, corresponding user trips will be generated, and the user trips are descriptive data of the user trips. Therefore, according to the outbound travel trajectory, the users whose user trips correspond to the shop are aggregated for each shop, and the users whose user trips correspond to the shop are all the users corresponding to the shop.

[0160] Through the execution of step S131, all users corresponding to the optional shop are determined and the corresponding user portraits are assigned to the optional shop, thereby obtaining the shop portrait of the optional shop. As a result, in the execution of the subsequent step S132, the conversion value of the merchant in each optional shop can be obtained by estimating the conversion value of the goods placed by the merchant in the optional shop by all users.

[0161] For an optional store, the conversion value of a merchant in the optional store is essentially the conversion value of the product set representing the merchant's profile placed in the optional store. For example, the conversion value can be calculated by the click rate of all users on each product in the optional store and the weight of the product.

[0162] The click rate of all users for each product in the optional stores is used to describe the click expectations of all users corresponding to the optional stores for the products placed by the merchants, so as to estimate in which optional store the merchants can obtain the highest click expectations for placing products.

[0163] Furthermore, the click rate prediction is achieved by using a pre-trained click rate prediction model. Exemplarily, the click rate of the user on the products placed by the optional store is predicted by using the click rate prediction model. The placed products are the products described in the product set.

[0164] It should be noted that in an exemplary embodiment, the conversion value estimation is performed for a merchant and an optional store for all users corresponding to the store. The conversion value estimation is the click rate estimation between each user and the product, and the execution process of the click rate accumulation for all users.

[0165] See also Figure 7 , Figure 7 is based on Figure 5The corresponding embodiment shows a method flow chart for estimating the conversion value of the product set representing the merchant portrait placed in each optional shop through the shop portrait, obtaining the conversion value of the merchant in the optional shop, and describing the steps of using the conversion value as the location value of the merchant in the optional shop.

[0166] The embodiment of the present application provides a method of estimating the conversion value of a set of products representing a merchant portrait placed in each optional shop through a shop portrait, obtaining the conversion value of the merchant in the optional shop, and using the conversion value as the location value of the merchant in the optional shop, step S132, including:

[0167] Step S1321, estimating the click rate of each user on the products in the product set among all users passing through the optional shops, and obtaining the click rate of all users on each product in the optional shops;

[0168] Step S1322, the conversion value of the merchant's products in the optional product shops is calculated based on the click rate of the products in the optional product shops according to the weights corresponding to the adapted products.

[0169] These two steps are described in detail below.

[0170] In an exemplary embodiment, a click rate prediction model for estimating the click rate between users and products is trained through the click records of users on the exposed products on the travel application.

[0171] Specifically, a training data set is first constructed for the click-through rate prediction model. Each record of the training data set includes a user portrait of the user and a product feature constructed for a 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.

[0172] Thus, the training data set is constructed

[0173] Among them, the constructed training data set D train A single record in Right now The user portrait is composed of multiple parts of data, and the data sources include but are not limited to travel data, application tracking data, etc.

[0174] Specifically,

[0175] corresponds to the user's own travel data, and This corresponds to third-party supplementary data.

[0176] The product features include descriptive features, statistical features, and generalized statistical features of the product. For example,

[0177] 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.

[0178] As a result, travel applications have been d For each user i in the day, all n i Product generation records to form the training data set for the click rate prediction model.

[0179] Correspondingly, the click rate between users and products is estimated, and the click rate of the corresponding users of the store on the products placed in the store will be obtained through the trained click rate prediction model.

[0180] The click-through rate prediction performed by the click-through rate prediction model requires the construction of a corresponding prediction data set, that is, for each user corresponding to the store, a prediction data set is constructed through the user portrait and the product features of the products placed by the merchant in the store. Each record of the prediction data set is the constructed user-product pair.

[0181] The constructed prediction data set is:

[0182] Each record, that is, the user product pair The feature list of the prediction dataset is the same as that of the training dataset. To further illustrate, the records in the prediction dataset represent the products Relative to each user passing by the store at time T in the store portrait, that is, user The possibility of purchase, and thus the resulting click-through rate, can lead to store locations with high conversion value.

[0183] Each record in the prediction data set represents the product j placed in the optional store, corresponding to all users corresponding to the store, that is, users 1, 2, ..., n user The possibility of being purchased will be used as the input of the click-through rate prediction model for each record to obtain the click-through rate of each user for the product corresponding to the store, and so on, to obtain the click-through rate of all users for the products corresponding to the store.

[0184] In an exemplary embodiment, for the click rate prediction model, the loss function constructed at the t-th iteration is as follows:

[0185]

[0186] in, is the predicted value of the ijth record in round t, f t is the tth 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, w i represents 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:

[0187]

[0188] in,

[0189] The optimal solution to the problem is:

[0190]

[0191] Among them, γ and λ are the first-order regularization term coefficient and the second-order regularization term coefficient, respectively.

[0192] Based on the iterative convergence of the optimal solution of each round on the training data set, a click-through rate prediction model is obtained.

[0193] For the conversion value calculation of a merchant in an optional store, after estimating the click rate of each user of all users of the optional store on a product in the product set through the click rate estimation model, all click rates of the product are accumulated to obtain the click rate of the product by all users in the optional store.

[0194] As mentioned above, each product has its weight. In the recommendation calculation of an optional store, the click rate estimation and click rate accumulation performed by the click rate estimation model are used to calculate the click rate of each product in the product set for the optional store by all users corresponding to the store.

[0195] The click rate of all users for each product in the optional store is obtained, and the weight assigned to each product by the merchant is weighted to obtain the merchant's conversion value in the optional store. It should be understood that the merchant's conversion value in the optional store, that is, the location value of the store in the optional store as mentioned above, for the current location recommendation, is actually the recommendation value of the optional store to the merchant, which can be recorded as "merchant-store recommendation value", and the calculation formula is as follows:

[0196]

[0197] Among them, n user is the number of users of the store portrait, that is, the number of all users corresponding to the store; n_item is the number of products corresponding to the product set that represents the merchant portrait; weight_j is the weight assigned by the merchant to the jth product in the product set.

[0198] Exemplarily, the weight may be the importance of the corresponding product to the merchant, which may be calculated by click value*product sales contribution.

[0199] Therefore, in step S1322, the weights corresponding to the commodities can be adapted to realize the optional store conversion value calculation which can measure the optional store location value for the merchants, thereby providing a quantitative and accurate basis for the merchants' store location selection.

[0200] It can be understood that the site value estimation performed in step 130 is based on the merchant portrait and the store portraits of each optional store, and estimates the conversion value of the merchant in each optional store, and then uses the obtained conversion value as the site value of the merchant in the optional store.

[0201] At this point, it should be explained that the shop portrait is a description of the shop's portrait information by users passing by the shop, so that the shop portrait can be consistent with the merchant portrait, and then the merchant's conversion value in the shop can be accurately estimated, so that the site selection recommendation can be realized objectively, accurately and reliably based on this.

[0202] Further explanation, in an exemplary embodiment, all users passing through the optional store estimate the click rate of each product in the product set in the optional store, see also Figure 8 , Figure 8 is based on Figure 7 The corresponding embodiment shows a method flow chart describing the steps of estimating the click rate of each user on the products in the product set among all users passing through the optional stores, and obtaining the click rate of each user on each product in the optional stores.

[0203] The step S1321 of estimating the click rate of each user on a product in a product set among all users passing through an optional store provided in the embodiment of the present application, and obtaining the click rate of each product in the optional store by all users, includes:

[0204] Step S301, for each product in the product set, estimate the click rate of each user on the product among all users corresponding to the store;

[0205] Step S302: The cumulative click rate is used to obtain the click rate of all users on the product in the optional stores.

[0206] These two steps are described in detail below.

[0207] For an optional store and each product in the product set, each user corresponding to the optional store forms a user-product pair with the product, so as to estimate the click rate of the user on the product.

[0208] For the user-product pair consisting of the user and the product, the click rate of the user for the product is estimated by the click rate estimation model as described above, and so on, the click rate of the user corresponding to the store for this product is obtained.

[0209] That is to say, all users corresponding to the optional store have corresponding click-through rates for this product, which can numerically describe the attraction of the product placed in the optional store to the users passing by, and then evaluate whether the optional store is suitable for the merchant who places this product.

[0210] After obtaining the click rate of each user on this product, the cumulative click rate is used to obtain the click rate of all users on this product in this optional store.

[0211] The click rate of this product by all users in this optional store represents the degree of attraction of the products placed by the merchant in this optional store to the user group passing through the store, and the user group passing through the store is composed of all users corresponding to the store.

[0212] Furthermore, for each product in the product set, the execution process of estimating the click rate of each user on the product among all users corresponding to the store S301 includes:

[0213] For all users who pass by the optional shops, we build user-product pairs of the optional shops based on the user portraits and the corresponding product features;

[0214] By predicting the click-through rate of user-item pairs, the click-through rate of each user on the product among all users corresponding to the optional stores is obtained.

[0215] First of all, as the application explains, users will generate corresponding user itineraries as they initiate entry and exit behaviors. Many users and the user itineraries of each user will constitute itinerary data. In other words, the user 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 then characterize the user with the user profile, which can be used to construct user-product pairs with the products in the product set.

[0216] The optional shops belong to a specific station and the exit of the specific station. Therefore, the user itinerary used to build the user portrait is related to this specific station, thereby ensuring the accuracy of the features of the constructed user-product pairs and eliminating useless or even interfering data.

[0217] The system built for sites provides each user with travel application deployment based on user terminals. Therefore, each user only needs to interact with the travel application in the user terminal and the gate to initiate his / her own entry or exit behavior, such as entering and exiting the site by scanning the QR code provided by the travel application on the gate. The travel application running on the user terminal and the system connected to the travel application will obtain the user's own travel data such as the user's itinerary.

[0218] That is to say, the user's own travel data will be used to characterize the user in data to build the user's user profile. The user's own travel data is multiple parts of data owned by the deployed travel application, such as the user's itinerary and other travel data mentioned above.

[0219] In addition, the user's own travel data also includes user information on the travel application, tracking data on the travel application, statistical data based on travel data, user's commercial operation data on the travel application, user-related product data, etc., which are not listed here one by one.

[0220] Exemplarily, the user's tracking data on the travel application is used to describe the user's clicks on the exposed products; user information on the travel application includes gender, age, region and occupation; statistical data based on travel data may specifically include but are 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 entry time of the first trip on weekdays in the past 7 / 14 / 30 / 90 days, the average exit time of the last trip on weekdays in the past 7 / 14 / 30 / 90 days, the average commuting distance per time in the past 7 / 14 / 30 / 90 days, the total number of rides, and the TOP10 high-frequency stations.

[0221] The business operation data of users on travel applications, including but not limited to: the total number of times commercial benefits are received, the total number of times commercial benefits are written off, the total amount of commercial benefits written off, the average price per customer of commercial benefits written off, the total number of times travel benefits are received, the number of times each card voucher is used, and the frequency of card use;

[0222] User-related product data may include but is not limited to: top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, corresponding number of times the top 10 product categories were viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, average price of the top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days).

[0223] It should be understood that the user's own travel data will be adapted to the travel application as input for merchant location recommendations to obtain a corresponding user portrait.

[0224] The source of user portrait is not limited to the user's own travel data, but can also come from third-party supplementary data. In short, the user portrait corresponds to the user's own travel data, as well as the combination of the user's own travel data and third-party supplementary data.

[0225] The third-party supplementary data includes, but is not limited to, whether the person is a pregnant woman, the degree of his or her interest in games, whether the person is a budget-conscious person, whether the person is a high net worth person, whether the person often flies, whether the person is interested in financial management, whether the person is interested in the two-dimensional world, whether the person is a budget-conscious person, whether the person is a phone addict, whether the person likes to go shopping in supermarkets, whether the person likes to take the kids out for a walk, whether the person is willing to buy a car, whether the person wants to buy a house or a hospital, whether the person likes to go to museums, whether the person likes to go to historical and cultural sites, whether the person likes to go to natural scenic areas, etc.

[0226] For each user corresponding to the store, the user's 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.

[0227] 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.

[0228] The commodity features of the commodities in the commodity set are used to describe the characteristics of the commodities. For example, the commodity features include commodity descriptive features, statistical features, and statistical generalized features of the commodities.

[0229] Specifically, the product characteristics include the first / second / third-level category to which the product belongs, the price of the product, the number of exposures of the product in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the product in the past 1 / 3 / 7 / 14 / 30, the number of purchase conversions of the product in the past 1 / 3 / 7 / 14 / 30, the number of days the product has been on the shelves, the number of exposures of the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30, and the number of purchase conversions of the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30.

[0230] For each user, the store builds a user-product pair based on the user portrait and the product features, thereby predicting the user's click rate on the product based on the user-product pair.

[0231] The optional shops used for location recommendation to shops are actual physical resources that exist offline. The goods placed in the shops are attracted by the users passing by. This can be compared to the clicks on the goods exposed on the Internet. Therefore, the degree of attractiveness of the merchants' goods placed in the optional shops to users can be accurately measured by the users' clicks on the goods.

[0232] The pre-built click rate prediction model is used to predict the click rate of user-to-product pairs to obtain the click rate of the user-to-product pair. It should be understood that the click rate of the user-to-product pair is the probability that the user is attracted by the products placed in the optional stores.

[0233] For a shop, each of its corresponding users will construct a user-item pair, and predict the click-through rate of the corresponding products through the constructed user-item pairs. By analogy, the click-through rate of the products of each user among all the users corresponding to the shop can be obtained.

[0234] The following is a specific example to illustrate the store location recommendation implemented by the present application.

[0235] First, for each optional store, a store portrait is obtained based on all corresponding users, which is used to form user-product pairs on the store with the constructed product features, and then the estimated click-through rate is obtained.

[0236] Specifically, the distribution of the number of times a user exits a station at a gate group is obtained through the user itinerary table and the gate information table. When a user exits a station by scanning a QR code of a travel application, the distribution of the number of times a user exits a station at a gate group describes the number of times the user scans the code at each gate, that is, the user gate group scan code table is obtained.

[0237] That is to say, the user travel table is associated with the gate information table through the gate code to obtain the user gate group code swiping table.

[0238] Based on the user gate group code scanning table, the distribution of user code scanning in this group of gates can be known, and the distribution of user code scanning in this group of gates will indicate the user's exit direction.

[0239] Combined with the gate group entrance and exit distance relationship described in the gate group entrance and exit distance relationship table, the exits pointing to different directions of the gate group are known, and the user's frequently used exits can be determined, and the user's recently frequently used exit table can be obtained.

[0240] For each exit, the shop mapped to the exit is recorded to build and maintain a shop exit relationship table.

[0241] Through the mapping of the exit to the shop, it is possible to know the shop that the user will pass by when leaving the station from an exit. In other words, all users passing by the shop are all users corresponding to the shop.

[0242] Assign user portraits of all users corresponding to the shop to the shop, further enrich its labels, and obtain a shop portrait table.

[0243] At this point, the store portrait table can be adapted to merchants to recommend the most suitable stores, thereby realizing site selection recommendations in business.

[0244] It should be further explained that for all users corresponding to a shop, the commonly used exit gates can be determined by counting the users' preferred exit directions in the code scanning table of the user gate group, and then all users corresponding to the shop can be determined based on this.

[0245] In addition, if the user has fewer trips in the user itinerary, for example, the number of exits of the user at the site 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 site gate group and the user portrait through a binary classification model, and then determine the exit gate to which the user belongs in this exit direction.

[0246] The probability that the user belongs to each exit is obtained through a pre-trained binary classification model, and then the exit to which the user belongs is finally determined by the probability. Exemplarily, the pre-trained model can be a binary classification model, which is characterized by the distribution of the number of times the user exits each gate group at the station and the user portrait. Under this feature, the direction value corresponding to the feature is marked according to the direction of the user after exiting the station, and each direction value uniquely corresponds to an exit that can be passed from the gate group.

[0247] 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.

[0248] Based on this, construct a training data set

[0249] Among them, each training data set D train In a single record in It is the feature of this record, which is used to describe the user status of the corresponding user.

[0250] Specifically, It includes the distribution of the number of times users exit 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.

[0251] 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 exits of user i at gate 1 of gate group j, the number of exits of user i at gate 2 of gate group j, ..., the number of exits of user i at gate n of gate group j zj The date (YYYYMM) represents the month, such as 202312, which means 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 characteristics (especially the actual number of exits).

[0252] That is, y in a single record of the training data set 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.

[0253] By training the model with the constructed training data set, a model is obtained that can accurately predict the exit to which the user belongs, providing the user with accurate judgment of the exit affiliation. There is no need to obtain the location, that is, it is no longer restricted by GPS positioning and the acquisition of location permissions.

[0254] Furthermore, the training for exit prediction will be conducted for gate groups corresponding to only one exit. A training data set is constructed for the gate group corresponding to the only exit, and features are constructed based on all records related to the gate group, and direction values ​​are annotated for the constructed features based on the unique direction of the gate group.

[0255] Specifically, the number of times the user exits each gate of the gate group in the site is obtained through the travel data and the gate information, that is, the user gate group exit data of user-site-gate group-gate-exit number 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 number, and the user gate group exit data corresponding only to the only 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 only exit, and the feature is constructed based on this.

[0256] In addition, the corresponding user portraits will be extracted for feature construction, and the constructed features will be labeled with directional values ​​to finally form a training data set.

[0257] The constructed training data set shields the influence of other exits and only considers the prediction of the user's exit in the feature dimension, so that the subsequent predictions will not be affected by other factors, which will greatly improve the accuracy and reliability of the prediction.

[0258] 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 of the user after exiting 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.

[0259] As mentioned above, the model trained by constructing the obtained training data set can be a binary classification model, and thus, the obtained binary classification model will be used to predict the exit to which the user belongs. Specifically, the binary classification model is used to predict the most likely direction of the user after exiting from the gate group according to the number of exits of the user at each gate on the station gate group and the user portrait, and the exit mapped by the direction is used as the exit to which the user belongs.

[0260] To further illustrate, a prediction data set is constructed based on the number of times a user exits each gate at the site gate group and the user profile. Among them, unlike the training data set, the prediction data set is not limited to the gate group corresponding to the only exit; in other words, it will not distinguish whether the gate group corresponds to the only exit, and all the user's data will be used to construct the prediction data set, and then the exit to which the user belongs will be predicted based on the characteristics of the constructed prediction data set.

[0261] 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, the characteristics describe the number of exits of user i at each gate in gate group j and the user tag. The characteristics list included is similar.

[0262] Based on the obtained binary classification model, the prediction data set D predict Each record of Use the binary classification model to implement predictions one by one, and get the probability that the characteristics of user i in gate group j are biased in one direction, that is, belonging to an exit corresponding to gate group j.

[0263] For example, if the gate group j corresponds to two exits. In other words, after exiting the gate group j, user i has two directions, each direction corresponds to an exit, then the probability of leaning towards the other direction, that is, belonging to the other exit, is

[0264] 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.

[0265] Specifically, each exit in one direction has its flow, which can be sensed by the passenger flow counter set 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.

[0266] 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.

[0267] 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 match these users with the positions at this exit, that is, determine which users correspond to the positions at this exit, and match the user portraits of these users with the positions at this exit, such as media locations, shop locations, etc.

[0268] On the other hand, the exit corresponding to the travel trajectory provides the tracked travel trajectory within the station, breaking out of 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.

[0269] As the user's travel trajectory out of the station and the exit in the user's itinerary can be matched, the user is aggregated at the location at the exit, and the aggregated user is assigned a location at the exit.

[0270] The user aggregation referred to 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.

[0271] 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.

[0272] The location mapped by the exit refers to the location on the exit. For example, in terms of location type, the location includes but is not limited to the media location, the store location, etc.; in terms of geographical location, the location mapped by the exit is any location in the direction of the exit, such as the location inside the station in the direction of the exit, the exit passage in the direction of the exit, and the location outside the station exiting from the exit.

[0273] 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, so that 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 the store location to construct the corresponding store portrait.

[0274] For the obtained store portrait, the location value of the store relative to the merchant will be estimated based on the click-through rate for each user corresponding to the store, so as to determine the final location of the store for the merchant.

[0275] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods 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 implementation methods of the present application.

[0276] 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 enabled to execute the method described in the above method embodiment.

[0277] According to one embodiment of the present application, a program product for implementing the method in the above method embodiment is also provided, which can adopt a portable compact disk read-only memory (CD-ROM) and include 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 to this. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0278] The program product may use 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 device, or any combination of the above. More specific examples (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 of the above.

[0279] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0280] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0281] 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++, etc., and 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 separate 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 through 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., through the Internet using an Internet service provider).

[0282] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0283] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the 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, etc.

[0284] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods 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 implementation methods of the present application.

[0285] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

Claims

1. A method for implementing merchant site selection recommendation in commercial operation, characterized in that: The method comprises: Constructing an initial set of commodities for the merchant's iconic flagship commodities, wherein the initial set of commodities includes commodity features constructed for each of the merchant's iconic flagship commodities and corresponding commodity weights; The merchant's commodity set is constructed by searching similar commodities in the constructed commodity library through the initial commodity set, and the commodity set is used to characterize the merchant's portrait; The merchant portrait is used to estimate the location value of the merchant in each optional store, and the optional store with the maximum location value is selected as the final location store.

2. The method according to claim 1, characterized in that The initial set of products is constructed for the merchant's iconic flagship products, including: Constructing a representation vector for each iconic flagship product of the merchant to obtain product features of the iconic flagship product; A weight is assigned to each iconic flagship product, and an initial set of products of the merchant is formed based on the product features and weights of the iconic flagship products.

3. The method according to claim 2, characterized in that The step of constructing a representation vector for each iconic flagship product of a merchant to obtain product features of the iconic flagship product includes: Determine whether there is a pre-built product tag for the iconic flagship product, and if so, extract the product tag corresponding to the iconic flagship product; The product features of the iconic flagship product are obtained by using the product label as a representation vector.

4. The method according to claim 3, characterized in that The step of constructing a representation vector for each iconic flagship product of a merchant to obtain product features of the iconic flagship product also includes: If there is no pre-constructed product tag for the iconic main product, a characterization vector of the iconic main product is constructed according to the pre-constructed product tag, and the characterization vector is used as the product feature of the iconic main product.

5. The method according to claim 1, wherein the step of constructing the merchant's product set by searching similar products in the constructed product library through the initial product set comprises: Searching for similar products in the product library for each iconic main product in the initial set of products, to obtain similar products to the iconic main product; Acquire the product tags of the similar products as product features of the similar products, and configure corresponding weights; The initial set of commodities is expanded with the commodity features and weights of the similar commodities to obtain the commodity set of the merchant.

6. The method according to claim 1, characterized in that The estimating the site selection value of the merchant in each optional shop based on the merchant portrait, and obtaining the optional shop with the maximum site selection value as the final site selection shop, includes: For all users corresponding to the optional shops, the location value of the shop in the optional shops is estimated through the shop portrait; The maximum site selection value is determined from the site selection values ​​of the optional shops, and the optional shop with the maximum site selection value is taken as the final site selection shop.

7. The method according to claim 6, characterized in that The estimating the location value of the merchant in the optional shops for all users corresponding to the optional shops includes: By determining all users who pass through the optional shops during business, a shop portrait of the optional shops is obtained, wherein the shop portrait includes a user portrait of each user; Through the store portrait, the conversion value of the product set representing the merchant portrait placed in each optional store is estimated to obtain the conversion value of the merchant in the optional store, and the conversion value is used as the location value of the merchant in the optional store.

8. A system for implementing merchant site selection recommendation in commercial operation, characterized in that: The system comprises a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images