Business hall recommendation method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a business hall recommendation method and device, electronic equipment and storage medium, the method comprises: in response to a service request, obtaining the current user location corresponding to the user account, user account information, a plurality of candidate business halls corresponding to the current user location and the business hall information of the candidate business hall, if the travel mode information is contained in the service request, the candidate business halls are sorted according to the travel mode information, the calculation sequence corresponding to each candidate business hall is obtained, the business hall information of each candidate business hall and the user account information are input into the preset hall store recommendation model according to the calculation sequence of each candidate business hall, the recommended priority, the target recommendation score and the navigation route of each candidate business hall are obtained, the candidate business hall with the highest recommended priority is taken as the recommended business hall corresponding to the hall store recommendation request, and the target recommendation score and the navigation route of the recommended business hall are displayed.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a recommendation method for a business hall, a recommendation device for a business hall, an electronic device, and a computer-readable storage medium. Background Technology

[0002] With the continuous development of internet technology, before going to a physical business hall to handle business, users usually search for business halls near their location in map applications and select the closest business hall based on the distance information provided by the map application.

[0003] While the method of selecting a service center based solely on distance is simple and quick, it fails to consider whether the service the user needs matches the nearest service center. This can easily lead to a mismatch between the selected service center and the user's needs, resulting in low service success rates and a poor user experience. Summary of the Invention

[0004] The present invention provides a method, apparatus, electronic device, and computer-readable storage medium for recommending business halls, in order to solve the problem in the prior art that the business hall selected by the user does not match the user's needs, resulting in a low success rate of business processing and a poor user experience.

[0005] This invention discloses a recommendation method for business halls, including:

[0006] In response to a service processing request, the system obtains the current user location corresponding to the user account, user account information, several candidate service halls corresponding to the current user location, and service hall information of the candidate service halls.

[0007] If the service request includes travel mode information for the candidate service hall, then the candidate service halls are sorted according to the travel mode information to obtain the calculation order corresponding to each candidate service hall;

[0008] According to the calculation order of each candidate business hall, the business hall information of each candidate business hall and the user account information are input into the preset store recommendation model to obtain the recommendation information of each candidate business hall. The recommendation information includes at least the recommendation priority, the target recommendation score and the navigation route.

[0009] The candidate business hall with the highest recommendation priority is selected as the recommended business hall corresponding to the business hall recommendation request, and the target recommendation score and navigation route corresponding to the recommended business hall are displayed.

[0010] Optionally, the recommendation information comprises a recommended service hall name, and the method further comprises:

[0011] obtaining a service handling result of the user account;

[0012] if the service handling result is that the user account has a service handling record corresponding to the service handling request, obtaining a handling service hall corresponding to the service handling result and a handling service hall name of the handling service hall;

[0013] if the handling service hall name is consistent with the recommended service hall name, maintaining a recommendation priority of the recommended service hall;

[0014] if the handling service hall name is not consistent with the recommended service hall name, obtaining historical recommendation information of the recommended service hall, and increasing the recommendation priority of the handling service hall.

[0015] Optionally, the historical recommendation information comprises a user selection frequency and a model recommendation frequency, and the method further comprises:

[0016] if the service handling result is that the user account does not have a service handling record corresponding to the service handling request, obtaining historical recommendation information of the recommended service hall;

[0017] taking a ratio between the user selection frequency and the model recommendation frequency as a historical recommendation score of the recommended service hall;

[0018] if the historical recommendation score is greater than or equal to a preset recommendation score, maintaining the recommendation priority of the recommended service hall;

[0019] if the historical recommendation score is less than the preset recommendation score, decreasing the recommendation priority of the recommended service hall.

[0020] Optionally, in response to the service handling request, the current user location corresponding to the user account, the user account information, a plurality of candidate service halls corresponding to the current user location, and the service hall information of the candidate service halls are obtained, comprising:

[0021] in response to a service handling operation on a service push page or a service handling page, the current user location corresponding to the user account and the user account information are obtained;

[0022] taking the current user location as a midpoint, a plurality of candidate service halls within a preset range and the service hall information of the candidate service halls are obtained.

[0023] Optionally, the candidate service halls are sorted according to the travel mode information to obtain a calculation sequence corresponding to each candidate service hall, comprising:

[0024] According to the travel mode information, a navigation route from the current user location to each of the candidate service halls and a store arrival time corresponding to the navigation route are determined;

[0025] The candidate service halls are sorted according to the store arrival time to obtain a calculation sequence corresponding to each of the candidate service halls;

[0026] The travel mode information includes one of self-driving, subway, bus, cycling and walking.

[0027] Optionally, the service hall information and the user account information of each of the candidate service halls are input into a preset hall-store recommendation model according to the calculation sequence of each of the candidate service halls to obtain recommendation information of each of the candidate service halls, including:

[0028] The service hall information and the user account information are respectively data cleaned and feature fused to obtain business feature information and hall-store location corresponding to the candidate service hall, and user feature information and user trajectory information corresponding to the user account;

[0029] The business feature information, the hall-store location, the user feature information and the user trajectory information are input into the preset hall-store recommendation model according to the calculation sequence to obtain the recommendation information of each of the candidate service halls.

[0030] Optionally, the service hall information includes hall-store location, and the method further includes:

[0031] If the travel mode information for the candidate service hall is not included in the service handling request, a distance value between the hall-store location of each of the candidate service halls and the current user location is calculated, each of the candidate service halls is sorted according to the distance value to obtain a calculation sequence corresponding to each of the candidate service halls;

[0032] The service hall information and the user account information of each of the candidate service halls are input into a preset hall-store recommendation model according to the calculation sequence of each of the candidate service halls to obtain recommendation information of each of the candidate service halls, the recommendation information at least including a recommendation priority, a target recommendation score and a navigation route;

[0033] The candidate service hall with the highest recommendation priority is taken as a recommended service hall corresponding to the hall-store recommendation request, and the target recommendation score and the navigation route corresponding to the recommended service hall are displayed.

[0034] Optionally, the hall-store recommendation model is generated by the following way:

[0035] construct an initial hall-store recommendation model corresponding to the candidate business hall;

[0036] obtain historical user trajectory information of at least one of the user accounts, the historical user trajectory information including historical store-arrival information and user non-arrival information;

[0037] use the historical store-arrival information as positive samples and the user non-arrival information as negative samples, and use the positive samples and the negative samples as model training data for training the hall-store recommendation model;

[0038] divide the model training data into a training set, a test set, and a validation set according to a preset training ratio;

[0039] train the initial hall-store recommendation model using the training set, the test set, and the validation set, and perform parameter setting on the initial hall-store recommendation model using a preset shrinkage weight coefficient, a preset maximum tree depth, and a preset number of rounds to generate the preset hall-store recommendation model.

[0040] The embodiment of the application further discloses a business hall recommendation device, which comprises:

[0041] a candidate business hall obtaining module configured to obtain, in response to a service handling request, current user location corresponding to a user account, user account information, a plurality of candidate business halls corresponding to the current user location, and business hall information of the candidate business halls;

[0042] a calculation sequence determining module configured to, if the service handling request contains travel mode information for the candidate business halls, sort the candidate business halls according to the travel mode information to obtain calculation sequences of the candidate business halls;

[0043] a recommendation information obtaining module configured to input the business hall information of the candidate business halls and the user account information into a preset hall-store recommendation model according to the calculation sequences of the candidate business halls to obtain recommendation information of the candidate business halls, the recommendation information at least including a recommendation priority, a target recommendation score, and a navigation route;

[0044] a recommended business hall determining module configured to determine the candidate business hall with the highest recommendation priority as a recommended business hall corresponding to the hall-store recommendation request, and display the target recommendation score and the navigation route of the recommended business hall.

[0045] Optionally, the recommendation information includes a recommended business hall name, and the device is specifically configured to:

[0046] obtain a service handling result of the user account;

[0047] If the service handling result is that the user account has a service handling record corresponding to the service handling request, a handling business hall corresponding to the service handling result and a handling business hall name of the handling business hall are obtained;

[0048] If the handling business hall name is consistent with the recommended business hall name, a recommended priority of the recommended business hall is maintained;

[0049] If the handling business hall name is not consistent with the recommended business hall name, historical recommendation information of the recommended business hall is obtained, and the recommended priority of the handling business hall is increased.

[0050] Optionally, the historical recommendation information includes a user selection frequency and a model recommendation frequency, and the device is specifically configured to:

[0051] If the service handling result is that the user account does not have a service handling record corresponding to the service handling request, historical recommendation information of the recommended business hall is obtained;

[0052] A ratio between the user selection frequency and the model recommendation frequency is taken as a historical recommendation score of the recommended business hall;

[0053] If the historical recommendation score is greater than or equal to a preset recommendation score, a recommended priority of the recommended business hall is maintained;

[0054] If the historical recommendation score is less than the preset recommendation score, the recommended priority of the recommended business hall is decreased.

[0055] Optionally, the candidate business hall obtaining module is specifically configured to:

[0056] In response to a service handling operation on a service push page or a service handling page, the current user location corresponding to the user account and the user account information are obtained;

[0057] A plurality of candidate business halls within a preset range and business hall information of the candidate business halls are obtained with the current user location as a midpoint.

[0058] Optionally, the calculation sequence determining module is specifically configured to:

[0059] According to the travel mode information, a navigation route from the current user location to each of the candidate business halls and a store arrival time corresponding to the navigation route are determined;

[0060] The candidate business halls are sorted according to the size of the store arrival time, and a calculation sequence corresponding to each of the candidate business halls is obtained;

[0061] The travel mode information includes one of self-driving, subway, bus, cycling, and walking.

[0062] Optionally, the recommendation information obtaining module is specifically configured to:

[0063] perform data cleaning and feature fusion on the business hall information and the user account information respectively, to obtain service feature information and hall-store location corresponding to the candidate business hall, and user feature information and user trajectory information corresponding to the user account;

[0064] input the service feature information, the hall-store location, the user feature information, and the user trajectory information into the preset hall-store recommendation model according to the calculation sequence one by one, to obtain the recommendation information of each candidate business hall.

[0065] Optionally, the business hall information includes hall-store location, and the device is specifically configured to:

[0066] If the travel mode information for the candidate business hall is not included in the service handling request, calculate the distance value between the hall-store location of each candidate business hall and the current user location, sort each candidate business hall according to the distance value, to obtain the calculation sequence of each candidate business hall;

[0067] input the business hall information of each candidate business hall and the user account information into the preset hall-store recommendation model according to the calculation sequence of each candidate business hall, to obtain the recommendation information of each candidate business hall, the recommendation information at least including recommendation priority, target recommendation score, and navigation route;

[0068] take the candidate business hall with the highest recommendation priority as the recommended business hall corresponding to the hall-store recommendation request, and display the target recommendation score and navigation route corresponding to the recommended business hall.

[0069] Optionally, the hall-store recommendation model is generated by the following method:

[0070] construct an initial hall-store recommendation model corresponding to the candidate business hall;

[0071] obtain historical user trajectory information of at least one user account, the historical user trajectory information including historical store visit information and user non-visit information;

[0072] take the historical store visit information as positive samples, and the user non-visit information as negative samples, and take the positive samples and the negative samples as model training data for training the hall-store recommendation model;

[0073] The model training data is divided into a training set, a test set and a verification set according to a preset training ratio;

[0074] The initial hall store recommendation model is trained by using the training set, the test set and the verification set, and is parameterized by using a preset shrinkage weight coefficient, a preset tree maximum depth and a preset round number, to generate the preset hall store recommendation model.

[0075] The application further discloses an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus.

[0076] The memory is used for storing a computer program.

[0077] The processor is used for executing the program stored on the memory, and realizes the method as described in the embodiments of the application.

[0078] The application further discloses a computer readable storage medium, which stores instructions, and when executed by one or more processors, causes the processor to execute the method as described in the embodiments of the application.

[0079] The embodiments of the application have the following advantages:

[0080] In the embodiments of the application, in response to a service handling request, a current user location corresponding to a user account, user account information, a plurality of candidate business halls corresponding to the current user location and business hall information of the candidate business halls are obtained, if the service handling request contains travel mode information for the candidate business halls, each candidate business hall is sorted according to the travel mode information, a calculation sequence corresponding to each candidate business hall is obtained, then the business hall information of each candidate business hall and the user account information are input into a preset hall store recommendation model according to the calculation sequence of each candidate business hall, a recommended priority, a target recommendation score and a navigation route of each candidate business hall are obtained, the candidate business hall with the highest recommended priority is taken as a recommended business hall corresponding to the hall store recommendation request, the target recommendation score and the navigation route corresponding to the recommended business hall are displayed, each candidate business hall is sorted by combining the travel mode information, the screening and recommendation according to the actual travel demand of the user are realized, the business hall information for the candidate business hall and the user account information for the user are input into the preset hall store recommendation model, the recommended business hall with high matching with the user account characteristics is obtained, the recommendation accuracy of the business hall is improved, and the target recommendation score and the navigation route of the recommended business hall are displayed to intuitively guide the user to reach the recommended business hall, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0081] Figure 1 is a step flow chart of a business hall recommendation method provided in an embodiment of the present application;

[0082] Figure 2 is a step flow chart of a business push page schematic diagram provided in an embodiment of the present application;

[0083] Figure 3 is a step flow chart of a business handling page schematic diagram provided in an embodiment of the present application;

[0084] Figure 4 is a step flow chart of a business hall recommendation model outputting a recommended business hall provided in an embodiment of the present application;

[0085] Figure 5 is a structural block diagram of a business hall recommendation device provided in an embodiment of the present application;

[0086] Figure 6 is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] In order to make the above objectives, characteristics and advantages of the present application more apparent, comprehensible and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0088] Referring to Figure 1 , a step flow chart of a business hall recommendation method provided in an embodiment of the present application is shown, which can specifically include the following steps:

[0089] Step 101, in response to a business handling request, obtaining a current user location corresponding to a user account, user account information, a plurality of candidate business halls corresponding to the current user location, and business hall information of the candidate business halls;

[0090] In an embodiment of the present application, after responding to the business handling request, the related business hall recommendation application can obtain the current user location corresponding to the user account, the user account information, the plurality of candidate business halls corresponding to the current user location, and the business hall information of each candidate business hall.

[0091] Optionally, the business handling request can be a request generated by user operation of the user on a business push page or a business handling page of a user terminal to which the user account belongs, for example, referring to Figure 2 A business push page schematic diagram provided in an embodiment of the present application is shown, the business push page can be a notification page, and a business handling recommendation message is displayed on the business push page, when it is detected that the user clicks the business handling recommendation message on the notification page to enter the business handling page, a corresponding business handling request can be generated, referring to Figure 3The business handling page provided in the embodiment of the application is shown, which can be a package handling page in a business application. The user initiates opening of the related application to enter the package handling page. When it is detected that the user selects a certain business in the package handling page, a corresponding business handling request can be generated.

[0092] The user account can be an account logged in the business hall recommendation application, such as a mobile phone number or a user-defined account number. The current user location can be the LBS (Location Based Services) geographic location data of the user terminal to which the user account belongs. The LBS location service refers to a service developed around geographic location data. It obtains the geographic location coordinate information of the user based on a spatial database using a wireless communication network or a satellite positioning system, and provides a value-added service related to the location by combining mobile communication technology and positioning technology. The user obtains the geographic location of the user by using the positioning technology of the mobile device, and provides various services related to the location for the user according to the location information and query information of the user account and through the network. The user account information can be attribute information of the user account, such as user business handling demand information, historical package information, and account information. The business hall information can be attribute information of the business hall, such as business handling volume, transaction amount, number of employees, and hall store rating of the business hall.

[0093] In a specific implementation, a current user location can be taken as a midpoint to obtain a plurality of candidate business halls within a preset range and business hall information of the candidate business halls. The preset range can be a distance range from the current user location, for example, the preset range can be 【0 meters, 1000 meters】, 【0 meters, 2000 meters】, and the like.

[0094] As an example, it is assumed that there is a business hall recommendation application, the user logs in a user account A in the application, the preset range is 【0 meters, 1500 meters】, and it is detected that the user selects a business handling push message “5G package limited-time 8-fold discount” in the business push page of the user terminal to which the application belongs. In response to the business handling request sent by the user terminal, the current LBS location of the user terminal is obtained, and then candidate business hall a, candidate business hall b, candidate business hall c, candidate business hall d within 【0 meters, 1500 meters】 centered on the LBS location and business hall information such as business handling volume, transaction amount, number of employees, and hall store rating of each candidate business hall are obtained.

[0095] In step 102, if the travel mode information for the candidate business hall is included in the business handling request, each candidate business hall is sorted according to the travel mode information to obtain the calculation order corresponding to each candidate business hall.

[0096] In the embodiment of the present application, if the travel mode information for the candidate service hall is carried in the service handling request, the candidate service halls can be sorted according to the travel mode information, and then the calculation sequence corresponding to each candidate service hall is obtained.

[0097] Optionally, the travel mode information can be the mode set by the user to move from the current user location to each candidate service hall, which can include one of self-driving, subway, bus, cycling, and walking, and the calculation sequence can be the sequence determined according to the size of the store time and the store distance, which is used to display the arrangement sequence and the calculation order of each candidate service hall, for example, candidate service hall a, candidate service hall b, candidate service hall c, and candidate service hall d, and the calculation sequence of each candidate service hall is: candidate service hall a--candidate service hall c--candidate service hall b--candidate service hall d.

[0098] In a specific implementation, the navigation route from the current user location to each candidate service hall and the store time corresponding to the navigation route can be determined according to the travel mode information, the candidate service halls are sorted according to the size of the store time, and the calculation sequence corresponding to each candidate service hall is obtained.

[0099] As an example, the travel mode information corresponding to the user account A is walking, the preset range is 【0 meters, 1500 meters】, candidate service hall a, candidate service hall b, and candidate service hall c corresponding to the current user location in the preset range are obtained, and the navigation route corresponding to candidate service hall a, candidate service hall b, and candidate service hall c is obtained. In combination with the walking mode and the navigation route of each candidate service hall, it is determined that the store time of candidate service hall a is 10 minutes, the store time of candidate service hall b is 15 minutes, and the store time of candidate service hall c is 12 minutes. According to the size of the store time of each service hall, candidate service hall a, candidate service hall b, and candidate service hall c are sorted, and the calculation sequence corresponding to each candidate service hall is obtained: candidate service hall a--candidate service hall c--candidate service hall b.

[0100] In another example of the present application, if the travel mode information for the candidate service hall is not included in the service handling request, the distance values between the locations of the candidate service halls and the current user location can be calculated, the candidate service halls can be ranked according to the distance values, the calculation order of each candidate service hall can be obtained, the service hall information and the user account information of each candidate service hall can be input into a preset hall-store recommendation model according to the calculation order of each candidate service hall, the recommendation information of each candidate service hall can be obtained, and the recommendation information at least includes the recommendation priority, the target recommendation score, and the navigation route. The candidate service hall with the highest recommendation priority is taken as the recommended service hall corresponding to the hall-store recommendation request, and the target recommendation score and the navigation route corresponding to the recommended service hall are displayed.

[0101] In step 103, the service hall information and the user account information of each candidate service hall are input into a preset hall-store recommendation model according to the calculation order of each candidate service hall, the recommendation information of each candidate service hall is obtained, and the recommendation information at least includes the recommendation priority, the target recommendation score, and the navigation route.

[0102] In the embodiment of the present application, after the calculation order of each candidate service hall is obtained according to the current user location, the service hall information and the user account information of each candidate service hall can be input into a preset hall-store recommendation model, and the recommendation priority, the target recommendation score, and the navigation route of each candidate service hall can be output by the hall-store recommendation model.

[0103] The hall store recommendation model can be a model for predicting user preference for a business hall. The recommendation priority can be a parameter agreed or defined by relevant technical personnel for the priority level of the hall store recommendation model when processing and outputting multiple candidate business halls. The higher the recommendation priority, the more matched the candidate business hall is to the user demand. For example, the recommendation priority of each candidate business hall can be: candidate business hall a > candidate business hall c > candidate business hall b. The recommendation score is a score obtained by the hall store recommendation model according to user account information and business hall information, and is used to represent the recommendation score of the candidate business hall. The target recommendation score is the recommendation score of the candidate business hall that meets the preset range. The historical recommendation score is the recommendation score of the recommended business hall output by the hall store recommendation model before the business handling request. The higher the recommendation score, the more matched the candidate business hall is to the user demand. For example, if the total score of the recommendation score is 5 points, the target recommendation score of candidate business hall a can be 4.9 points, the target recommendation score of candidate business hall b can be 4.2 points, and the target recommendation score of candidate business hall c can be 4.5 points. If the total score of the recommendation score is 100 points, the target recommendation score of candidate business hall a can be 90 points, the target recommendation score of candidate business hall b can be 80 points, and the target recommendation score of candidate business hall c can be 70 points. The navigation route is a route determined based on the current user location and the hall store location, combined with the user's travel mode and the current traffic situation.

[0104] Specifically, the hall store recommendation model is generated by the following method:

[0105] S11, an initial hall store recommendation model corresponding to the candidate business hall is constructed.

[0106] S12, historical user trajectory information of at least one user account is obtained, the historical user trajectory information including historical store visit information and user non-visit information.

[0107] S13, the historical store visit information is taken as a positive sample, and the user non-visit information is taken as a negative sample. The positive sample and the negative sample are taken as model training data for training the hall store recommendation model.

[0108] S14, the model training data is divided into a training set, a test set and a validation set according to a preset training ratio.

[0109] S15, the initial hall store recommendation model is trained by using the training set, the test set and the validation set, and the initial hall store recommendation model is parameterized by using a preset shrinkage weight coefficient, a preset tree maximum depth and a preset number of rounds to generate the preset hall store recommendation model.

[0110] Optionally, the preset hall store recommendation model can be trained by XGBoost in the Python sklearn library. The XGBoost algorithm (eXtreme Gradient Boosting) is an algorithm toolkit based on the Boosting framework, which is superior in parallel computing efficiency, missing value processing, and prediction performance. The historical store information can be the information of each user going to the candidate operating hall, the user non-store information can be the information of each user not going to the candidate operating hall, the preset training ratio can be the ratio of dividing the sample data into training set, test set and validation set, for example, the preset training ratio can be 7:2:1, the preset shrinkage weight can be the learning rate eta (learning rate), which is specified by the relevant technical personnel to control the iteration rate and update step shrinkage to prevent overfitting, the shrinkage weight in each step makes the model more robust, the preset tree maximum depth max_depth, which defines the maximum depth of a tree, can also be used to control overfitting, and the preset number of rounds num_boost_round can be the number of iterations (the number of trees). The parameters of the model can be optimized based on the grid search method to obtain the optimal model index and the corresponding model parameters. The preset shrinkage weight coefficient, the preset tree maximum depth and the preset number of rounds have the value range shown in Table 1:

[0111]

[0112] Table 1

[0113] In a specific implementation, before predicting the recommended operating hall of the user, the operating hall information and the user account information can be respectively data cleaned and feature fused to obtain the business feature information and the hall store location corresponding to the candidate operating hall, and the user feature information and the user trajectory information corresponding to the user account. Then, according to the calculation order, the business feature information, the hall store location of each candidate operating hall, and the user feature information, the user trajectory information of the user account are input into the preset hall store recommendation model one by one to obtain the recommendation information of each candidate operating hall, thereby realizing the personalized recommendation operating hall function for the user.

[0114] Optionally, data cleaning refers to the last procedure of discovering and correcting identifiable errors in data files by computers, including checking data consistency, processing invalid values and missing values, etc., feature fusion refers to the optimization combination of different feature vectors extracted from the same mode, on the one hand, from the order of fusion and prediction, feature fusion can be divided into early fusion and late fusion, early fusion: refers to the fusion on the feature, the connection of different features is carried out, and the training is carried out in a model (firstly, the features of multiple layers are fused, then the predictor is trained on the fused features, and only after complete fusion, detection is carried out), late fusion: refers to the fusion on the prediction score, multiple models are trained, each model will have a prediction score, and the results of all models are fused to obtain the final prediction result (the detection performance is improved by combining the detection results of different layers, before the final fusion is completed, the detection is started on the partially fused layer, there will be multiple layers of detection, and finally the multiple detection results are fused), on the other hand, from the perspective of model structure, feature fusion can be divided into serial strategy and parallel strategy, serial strategy: the whole model has only one branch, parallel strategy: the model has multiple branches, and each branch processes different features.

[0115] In the application, the business hall information and the user account information are data cleaned to delete the repeated data in the business hall information and the user account information, and then the business hall information and the user account information after data cleaning are feature fused, so that different characteristics of features are better utilized, and these different features are jointly modeled, and the performance of the hall store recommendation model is improved.

[0116] Specifically, after the business hall information and the user account information are data cleaned, mobile DPI data (Deep Packet Inspection), CRM data (Customer Relationship Management), billing system data, basic information data of the hall store, and terminal platform data are extracted, and then the mobile DPI data, the CRM data, the billing system data, the basic information data of the hall store, and the terminal platform data are feature fused to obtain business feature information corresponding to the candidate business hall and hall store location, user feature information corresponding to the user account, and user trajectory information. The business feature information can be basic information of the business hall, such as business hall business handling volume, business hall transaction amount, business hall employee data, business hall score, and the like. The hall store location can be latitude and longitude location information of the business hall. The user feature information can be user characteristics and preference information, such as user age, user account package price, family composition, terminal price, consumption trend, monthly average outgoing amount, monthly average recharging amount, and the like. The user trajectory information can be information about the user's historical visit to the business hall to handle business, such as the user's round trip time to the business hall to handle business, business hall name, business hall location, and stay time.

[0117] In step 104, the candidate business hall with the highest recommendation priority is taken as a recommended business hall corresponding to the hall store recommendation request, and the target recommendation score and the navigation route corresponding to the recommended business hall are displayed.

[0118] In the embodiment of the present application, the recommendation priority of each candidate business hall can be calculated by the preset hall store recommendation model, and the candidate business hall with the highest recommendation priority is taken as the recommended business hall corresponding to the hall store recommendation request, and the target recommendation score and the navigation route corresponding to the recommended business hall are displayed. For example, the recommendation priority of each candidate business hall can be: candidate business hall a > candidate business hall c > candidate business hall b. The preset hall store recommendation model can output the candidate business hall a to the corresponding business hall recommendation page, and display the target recommendation score and the navigation route of the candidate business hall a in the business hall recommendation page.

[0119] In an example, after the corresponding recommended business hall is recommended to the user, the preset hall store recommendation model can be further dynamically optimized by obtaining the service handling result of the user account. If the service handling result is that the user account has a service handling record corresponding to the service handling request, the handling business hall corresponding to the service handling result is obtained, and the handling business hall name and hall store location of the handling business hall are compared with the recommended business hall name and hall store location of the recommended business hall. If the handling business hall name and hall store location of the handling business hall are consistent with the recommended business hall name and hall store location of the recommended business hall, the recommended priority of the recommended business hall is maintained.

[0120] The service handling record can be a historical user behavior of handling a service corresponding to the service handling request recorded in the user account, which indicates that the user went to the business hall to handle the service. For example, the service handling request is "handle 5G package", and if the user account has a behavior corresponding to "order 5G package" that "the account orders 60 yuan 5G package", it indicates that the user successfully handled the corresponding service. If the user account does not record the historical user behavior corresponding to the 5G package, it indicates that the user did not handle the corresponding service.

[0121] In another example, if the handling business hall name is not consistent with the recommended business hall name, the historical recommendation information of the recommended business hall is obtained, and the recommended priority of the handling business hall is improved. For example, the service handling request is "handle 5G package", the preset hall store recommendation model outputs the recommended business hall a, the business hall name of the recommended business hall a is "China Telecom Yangji Business Hall", and the hall store location is "Guangdong Province, Guangzhou City, Yuexiu District, Zhongshan First Road, Yangji Street". The service handling result of the user account A is that the user account A has a record of handling 5G package, but the business hall name of the handling business hall that the user account A goes to is "China Telecom Zhongshan First Road Business Hall", and the hall store location is "Guangdong Province, Guangzhou City, Yuexiu District, Jinyang Second Street". After comparing the information between the business halls, it is determined that the handling business hall of the user account A handling the service is not the same as the recommended business hall output by the preset hall store recommendation model. The historical recommendation information of the recommended business hall a is obtained, and then the recommended priority of the recommended business hall is adjusted according to the historical recommendation information.

[0122] In another example, if the service handling result is that the user account does not have a service handling record corresponding to the service handling request, the historical recommendation information of the recommended business hall is obtained. For example, the service handling request is "handle 5G package", the preset hall store recommendation model outputs the recommended business hall a, but the user account does not have a historical user behavior of handling 5G service. The historical recommendation information of the recommended business hall a is obtained, and then the recommended priority of the recommended business hall is adjusted according to the historical recommendation information.

[0123] In a specific implementation, the historical recommendation information includes the user selection times and the model recommendation times, a ratio between the user selection times and the model recommendation times is taken as a historical recommendation score of the recommended business hall, if the historical recommendation score is greater than or equal to a preset recommendation score, the recommendation priority of the recommended business hall is maintained, and if the historical recommendation score is less than the preset recommendation score, the recommendation priority of the recommended business hall is reduced.

[0124] Optionally, the user selection times can be the times of selecting the business hall for handling the business by each user in the related application program, the model recommendation times can be the times of recommendation or output by the preset hall store recommendation model in response to the business handling request, and the historical recommendation score is a ratio between the user selection times and the model recommendation times. For example, the total recommendation score is 100 points, the user selection times are 30 times, and the model recommendation times are 50 times, and then the historical recommendation score can be 60 points. The preset recommendation score is a recommendation threshold set by the related technical personnel according to the actual demand, for example, 60 points, 70 points, 80 points, etc. The preset hall store recommendation model is optimized according to the actual business handling result of the user, so that the recommended business hall is more accurate and has a higher matching degree with the user demand.

[0125] As an example, refer to Figure 4The step flow chart of outputting the recommended business hall by using the hall store recommendation model provided by the embodiment of the application is shown. It is assumed that there is a user account A, the user clicks the push message of "5G package preferential handling" on the notification page, and the travel mode information corresponding to the user account A is riding. The preset range is 【0 meters, 3000 meters】. The candidate business hall a, the candidate business hall b and the candidate business hall c corresponding to the current user position of the user account A within 【0 meters, 3000 meters】 are obtained respectively. According to the travel mode of "riding", it is determined that the store time of the candidate business hall a is 10 minutes, the store time of the candidate business hall b is 15 minutes, and the store time of the candidate business hall c is 12 minutes. Then, the candidate business hall a, the candidate business hall b and the candidate business hall c are sorted according to the size of the store time of each business hall, and the calculation order corresponding to each candidate business hall is obtained as: candidate business hall a--candidate business hall c--candidate business hall b. The business hall information and the user account information of each candidate business hall are input into the preset hall store recommendation model one by one according to the calculation order, and the recommendation priority of each candidate business hall is obtained as: candidate business hall a > candidate business hall c > candidate business hall b. The target recommendation score of the candidate business hall a is 90 points, the target recommendation score of the candidate business hall c is 85 points, and the target recommendation score of the candidate business hall b is 80 points. Then, the candidate business hall a can be taken as the recommended business hall, and the riding navigation route and the target recommendation score of the candidate business hall a are displayed. If the name of the handling business hall to be visited by the user is inconsistent with the name of the recommended business hall, the ratio between the number of user selections and the number of model recommendations is taken as the historical recommendation score of the recommended business hall. The recommendation priority of the recommended business hall is adjusted according to the historical recommendation score, and the preset hall store recommendation model is optimized.

[0126] It should be noted that the embodiments of the application include but are not limited to the above examples. It can be understood that under the guidance of the idea of the embodiments of the application, those skilled in the art can set it according to the actual situation, and the application does not limit this.

[0127] In the embodiment of the present application, in response to a service handling request, the current user location corresponding to the user account, the user account information, a plurality of candidate service halls corresponding to the current user location and the service hall information of the candidate service halls are obtained. If the travel mode information for the candidate service halls is included in the service handling request, the candidate service halls are sorted according to the travel mode information, the calculation order corresponding to each candidate service hall is obtained, and then the service hall information of each candidate service hall and the user account information are input into the preset hall-store recommendation model to obtain the recommendation priority, the target recommendation score and the navigation route of each candidate service hall. The candidate service hall with the highest recommendation priority is taken as the recommended service hall corresponding to the hall-store recommendation request, and the target recommendation score and the navigation route corresponding to the recommended service hall are displayed. By sorting each candidate service hall in combination with the travel mode information, the user's actual travel demand is screened and recommended, and by inputting the service hall information of the candidate service hall and the user account information of the user into the preset hall-store recommendation model, the recommended service hall with high matching with the user account characteristics is obtained, the recommendation accuracy of the service hall is improved, and the target recommendation score and the navigation route of the recommended service hall are displayed to intuitively guide the user to the recommended service hall, thereby improving the user experience.

[0128] It should be noted that for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present application are not limited by the order of the described actions, because according to the embodiments of the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0129] Referring to Figure 5 , a structural block diagram of a service hall recommendation device provided in the embodiment of the present application is shown, which can specifically include the following modules:

[0130] The candidate service hall acquisition module 501 is configured to, in response to a service handling request, acquire the current user location corresponding to the user account, the user account information, a plurality of candidate service halls corresponding to the current user location and the service hall information of the candidate service halls.

[0131] The calculation order determination module 502 is configured to, if the travel mode information for the candidate service halls is included in the service handling request, sort each candidate service hall according to the travel mode information, and obtain the calculation order corresponding to each candidate service hall.

[0132] The recommendation information obtaining module 503 is configured to input the store information of each candidate store and the user account information into a preset store recommendation model according to the calculation sequence of each candidate store, and obtain recommendation information of each candidate store, wherein the recommendation information at least includes a recommendation priority, a target recommendation score and a navigation route.

[0133] The recommended store determining module 504 is configured to determine the candidate store with the highest recommendation priority as a recommended store corresponding to the store recommendation request, and display the target recommendation score and the navigation route corresponding to the recommended store.

[0134] In an optional embodiment of the present application, the recommendation information includes a recommended store name, and the device is specifically configured to:

[0135] Obtain a service handling result of the user account;

[0136] If the service handling result is that the user account has a service handling record corresponding to the service handling request, obtain a handling store corresponding to the service handling result and a handling store name of the handling store;

[0137] If the handling store name is consistent with the recommended store name, maintain the recommendation priority of the recommended store;

[0138] If the handling store name is not consistent with the recommended store name, obtain historical recommendation information of the recommended store, and improve the recommendation priority of the handling store.

[0139] In an optional embodiment of the present application, the historical recommendation information includes a user selection frequency and a model recommendation frequency, and the device is specifically configured to:

[0140] If the service handling result is that the user account does not have a service handling record corresponding to the service handling request, obtain historical recommendation information of the recommended store;

[0141] Take a ratio between the user selection frequency and the model recommendation frequency as a historical recommendation score of the recommended store;

[0142] If the historical recommendation score is greater than or equal to a preset recommendation score, maintain the recommendation priority of the recommended store;

[0143] If the historical recommendation score is less than the preset recommendation score, reduce the recommendation priority of the recommended store.

[0144] In an optional embodiment of the present application, the candidate store obtaining module 501 is specifically configured to:

[0145] In response to the service operation for the service push page or the service handling page, the current user location corresponding to the user account and the user account information are acquired;

[0146] The current user location is taken as a midpoint, and a plurality of candidate service halls in a preset range and service hall information of the candidate service halls are acquired.

[0147] In an optional embodiment of the embodiment of the application, the calculation sequence determination module 502 is specifically configured to:

[0148] According to the travel mode information, a navigation route from the current user location to each of the candidate service halls and a store arrival time corresponding to the navigation route are determined;

[0149] The candidate service halls are sorted according to the size of the store arrival time, and a calculation sequence corresponding to each of the candidate service halls is obtained.

[0150] The travel mode information includes one of self-driving, subway, bus, cycling and walking.

[0151] In an optional embodiment of the embodiment of the application, the recommendation information acquisition module 503 is specifically configured to:

[0152] The service hall information and the user account information are respectively subjected to data cleaning and feature fusion, and service feature information and hall store location corresponding to the candidate service halls, and user feature information and user trajectory information corresponding to the user account are obtained.

[0153] The service feature information, the hall store location, the user feature information and the user trajectory information are sequentially input into the preset hall store recommendation model according to the calculation sequence, and recommendation information of each of the candidate service halls is acquired.

[0154] In an optional embodiment of the embodiment of the application, the service hall information includes hall store location, and the device is specifically configured to:

[0155] If the travel mode information for the candidate service halls is not included in the service handling request, distance values between the hall store locations of each of the candidate service halls and the current user location are calculated, each of the candidate service halls is sorted according to the size of the distance value, and a calculation sequence corresponding to each of the candidate service halls is obtained.

[0156] The store information of each of the candidate stores and the user account information are input into a preset store recommendation model according to the calculation sequence of each of the candidate stores, to obtain recommendation information of each of the candidate stores, the recommendation information at least including a recommendation priority, a target recommendation score and a navigation route;

[0157] The candidate store with the highest recommendation priority is taken as a recommended store corresponding to the store recommendation request, and the target recommendation score and the navigation route corresponding to the recommended store are displayed.

[0158] In an optional embodiment of the embodiment of the application, the store recommendation model is generated by the following manner:

[0159] An initial store recommendation model corresponding to the candidate store is constructed;

[0160] The historical user trajectory information of at least one of the user accounts is obtained, the historical user trajectory information including historical store visit information and user non-visit information;

[0161] The historical store visit information is taken as positive samples, and the user non-visit information is taken as negative samples, and the positive samples and the negative samples are taken as model training data for training the store recommendation model;

[0162] The model training data is divided into a training set, a test set and a validation set according to a preset training ratio;

[0163] The initial store recommendation model is trained by using the training set, the test set and the validation set, and the initial store recommendation model is parameterized by using a preset shrinkage weight coefficient, a preset tree maximum depth and a preset number of rounds, to generate the preset store recommendation model.

[0164] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts refer to the part of the method embodiment.

[0165] In addition, the embodiment of the application further provides an electronic device, which comprises a processor, a memory, a computer program stored on the memory and executable on the processor, the computer program being executed by the processor to implement each process of the store recommendation method embodiment and achieve the same technical effects, and thus the description is not repeated here.

[0166] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, the computer program is executed by a processor to realize each process of the business hall recommendation method embodiment and achieve the same technical effects, and details are not repeated here. The computer readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0167] Figure 6 A structural schematic diagram of an electronic device for implementing various embodiments of the present application.

[0168] The electronic device 600 includes, but is not limited to, a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, a processor 610, and a power supply 611, etc. Figure 6 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than shown, or combine certain components, or different component arrangements. In the embodiments of the present application, the electronic device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle terminal, a wearable device, and a pedometer, etc.

[0169] It should be understood that in the embodiments of the present application, the radio frequency unit 601 can be used for receiving and transmitting signals in the process of information or call, specifically, receiving downlink data from a base station and processing it by the processor 610; in addition, transmitting uplink data to the base station. Generally, the radio frequency unit 601 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 601 can also communicate with the network and other devices through a wireless communication system.

[0170] The electronic device provides wireless broadband Internet access for users through the network module 602, such as helping users to send and receive emails, browse web pages, and access streaming media, etc.

[0171] The audio output unit 603 can convert audio data received by the radio frequency unit 601 or the network module 602 or stored in the memory 609 into an audio signal and output as a sound. Moreover, the audio output unit 603 can also provide audio output related to a specific function performed by the electronic device 600 (for example, a call signal receiving sound, a message receiving sound, etc.). The audio output unit 603 includes a speaker, a buzzer, and a receiver, etc.

[0172] The input unit 604 is configured to receive audio or video signals. The input unit 604 can include a graphic processing unit (GPU) 6041 and a microphone 6042. The graphic processing unit 6041 processes image data of a still picture or a video obtained by an image capture apparatus (e.g., a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 606. The image frame processed by the graphic processing unit 6041 can be stored in the memory 609 (or other storage medium) or transmitted via the radio frequency unit 601 or the network module 602. The microphone 6042 can receive sound, and can process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via the radio frequency unit 601 in a telephone call mode.

[0173] The electronic device 600 further includes at least one sensor 605, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 6061 according to the brightness of ambient light, and the proximity sensor can turn off the display panel 6061 and / or the backlight when the electronic device 600 is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when at rest, which can be used to identify the electronic device posture (such as screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, knock), and the like. The sensor 605 can also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which will not be described here.

[0174] The display unit 606 is configured to display information input by a user or information provided to the user. The display unit 606 can include a display panel 6061, which can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0175] The user input unit 607 can be used to receive inputted digital or character information, and to generate key signal input related to user settings of the electronic device and control of functions. Specifically, the user input unit 607 includes a touch panel 6071 and other input devices 6072. The touch panel 6071, also called a touch screen, can collect a user's touch operation (such as a user's operation on or near the touch panel 6071 using a finger, a stylus, or any suitable object or accessory) on or near it. The touch panel 6071 can include two parts, a touch detection device and a touch controller. The touch detection device detects the user's touch position and detects a signal caused by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch coordinates, and sends it to the processor 610, receives commands from the processor 610 and executes them. In addition, the touch panel 6071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 6071, the user input unit 607 can also include other input devices 6072. Specifically, the other input devices 6072 can include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, on / off buttons, etc.), trackballs, mice, joysticks, and the like, which will not be described here.

[0176] Further, the touch panel 6071 can be overlaid on the display panel 6061, and when the touch panel 6071 detects a touch operation on or near it, it transmits to the processor 610 to determine the type of touch event, and then the processor 610 provides corresponding visual output on the display panel 6061 according to the type of touch event. Although in the Figure 6 In some embodiments, the touch panel 6071 and the display panel 6061 can be integrated to realize the input and output functions of the electronic device, which is not limited here.

[0177] The interface unit 608 is an interface for connecting external devices to the electronic device 600. For example, the external devices can include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and the like. The interface unit 608 can be used to receive input (e.g., data information, power, etc.) from external devices and transmit the received input to one or more elements within the electronic device 600, or can be used to transmit data between the electronic device 600 and external devices.

[0178] The memory 609 is used to store software programs and various data. The memory 609 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory 609 can include a high-speed random access memory, and can also include a nonvolatile memory, for example, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0179] The processor 610 is a control center of the electronic device, connects all parts of the electronic device through various interfaces and lines, executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 609 and calling data stored in the memory 609, and thus performs overall monitoring on the electronic device. The processor 610 can include one or more processing units; preferably, the processor 610 can integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 610.

[0180] The electronic device 600 can further include a power supply 611 (such as a battery) for supplying power to various components; preferably, the power supply 611 can be logically connected to the processor 610 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system.

[0181] In addition, the electronic device 600 includes some functional modules which are not shown and will not be described herein.

[0182] It should be noted that, in this document, the term “comprising” or “including” or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without more limitations, the element defined by the statement “including a…” does not exclude the presence of additional identical elements in the process, method, article, or device including the element.

[0183] Those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, air conditioner, or network device) execute the method described in each embodiment of the present application.

[0184] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are only illustrative, not restrictive. Those skilled in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims.

[0185] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the embodiments of the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0186] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0187] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0189] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit.

[0190] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application or the part of the application that contributes to the prior art in essence or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes various storage media that can store program codes, such as a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk.

[0191] The above is only a specific embodiment of the application, but the protection scope of the application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the application, which should be covered within the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A method for recommending services at a business hall, characterized in that, include: In response to a service processing request, the system obtains the current user location corresponding to the user account, user account information, several candidate service halls corresponding to the current user location, and service hall information of the candidate service halls. The user account information is the attribute information of the user account, and the attribute information includes at least user service request information, historical package information, and billing information; If the service request includes travel mode information for the candidate service hall, then the candidate service halls are sorted according to the travel mode information to obtain the calculation order corresponding to each candidate service hall; Data cleaning and feature fusion are performed on the business hall information and the user account information respectively to obtain business feature information and store location corresponding to the candidate business hall, and user feature information and user trajectory information corresponding to the user account; According to the calculation order, the business feature information, the store location, the user feature information, and the user trajectory information are input into the preset store recommendation model one by one to obtain the recommendation information of each candidate store. The recommendation information includes at least the recommendation priority, the target recommendation score, and the navigation route. The user feature information is the characteristics and preference information of the user account. The store recommendation model is used to predict the preferred store of the user account. The candidate business hall with the highest recommendation priority is selected as the recommended business hall corresponding to the business hall recommendation request, and the target recommendation score and navigation route corresponding to the recommended business hall are displayed.

2. The method according to claim 1, characterized in that, The recommended information includes the name of the recommended business hall, and also includes: Obtain the transaction processing result of the user account; If the business processing result is that the user account has a business processing record corresponding to the business processing request, then obtain the processing business hall corresponding to the business processing result and the name of the processing business hall; If the name of the service hall being processed is the same as the name of the recommended service hall, then the recommendation priority of the recommended service hall will be maintained. If the name of the service hall being processed is different from the name of the recommended service hall, then the historical recommendation information of the recommended service hall is obtained, and the recommendation priority of the service hall being processed is increased.

3. The method according to claim 2, characterized in that, The historical recommendation information includes the number of times the user selected the data and the number of times the model recommended the data, and also includes: If the result of the service processing is that the user account does not have a service processing record corresponding to the service processing request, then the historical recommendation information of the recommended business hall is obtained; The ratio between the number of user selections and the number of model recommendations is used as the historical recommendation score for the recommended business hall; If the historical recommendation score is greater than or equal to the preset recommendation score, the recommendation priority of the recommended business hall will be maintained. If the historical recommendation score is less than the preset recommendation score, the recommendation priority of the recommended business hall will be reduced.

4. The method according to claim 1, characterized in that, The step of responding to a service request by obtaining the current user location corresponding to the user account, user account information, several candidate service halls corresponding to the current user location, and service hall information of the candidate service halls includes: In response to a business processing operation on a business push page or a business processing page, obtain the current user location and the user account information corresponding to the user account; Using the current user's location as the midpoint, obtain several candidate service halls within a preset range, along with the service hall information of the candidate service halls.

5. The method according to claim 1, characterized in that, The step of sorting the candidate service halls according to the travel mode information to obtain the calculation order corresponding to each candidate service hall includes: Based on the travel mode information, determine the navigation route from the current user's location to each of the candidate service halls and the corresponding arrival time for the navigation route; The candidate business halls are sorted according to the length of time spent in the store, and the calculation order corresponding to each candidate business hall is obtained. The travel mode information includes one of the following: driving, subway, bus, cycling, or walking.

6. The method according to claim 1, characterized in that, The business hall information includes the location of the store, and the method further includes: If the service request does not contain travel mode information for the candidate service hall, then the distance between the location of each candidate service hall and the current user's location is calculated, and the candidate service halls are sorted according to the size of the distance value to obtain the calculation order corresponding to each candidate service hall. According to the calculation order of each candidate business hall, the business hall information of each candidate business hall and the user account information are input into the preset store recommendation model to obtain the recommendation information of each candidate business hall. The recommendation information includes at least the recommendation priority, the target recommendation score and the navigation route. The candidate business hall with the highest recommendation priority is selected as the recommended business hall corresponding to the business hall recommendation request, and the target recommendation score and navigation route corresponding to the recommended business hall are displayed.

7. The method according to claim 1, characterized in that, The store recommendation model is generated in the following way: Construct an initial store recommendation model corresponding to the candidate stores; Obtain historical user trajectory information for at least one of the user accounts, the historical user trajectory information including historical store visit information and user non-store visit information; The historical store visit information is used as a positive sample, and the user's non-store visit information is used as a negative sample. The positive sample and the negative sample are used as model training data for training the store recommendation model. The model training data is divided into a training set, a test set, and a validation set according to a preset training ratio. The initial restaurant recommendation model is trained using the training set, the test set, and the validation set. The parameters of the initial restaurant recommendation model are set using preset shrinkage weight coefficients, preset maximum tree depth, and preset number of rounds to generate the preset restaurant recommendation model.

8. A recommendation device for a business hall, characterized in that, include: The candidate service hall acquisition module is used to respond to a service processing request by acquiring the current user location corresponding to the user account, the user account information, several candidate service halls corresponding to the current user location, and the service hall information of the candidate service halls. The user account information is the attribute information of the user account, and the attribute information includes at least user service request information, historical package information, and billing information; The calculation order determination module is used to sort each candidate business hall according to the travel mode information if the business processing request contains travel mode information for the candidate business hall, and obtain the calculation order corresponding to each candidate business hall. The recommendation information acquisition module is used to perform data cleaning and feature fusion on the business hall information and the user account information respectively to obtain business feature information and store location corresponding to the candidate business hall, and user feature information and user trajectory information corresponding to the user account; according to the calculation order, the business feature information, the store location, the user feature information, and the user trajectory information are input into a preset business hall recommendation model one by one to obtain recommendation information for each candidate business hall. The recommendation information includes at least recommendation priority, target recommendation score, and navigation route; the user feature information is the characteristics and preference information of the user account, and the business hall recommendation model is used to predict the preferred business hall of the user account; The recommended business hall determination module is used to select the candidate business hall with the highest recommendation priority as the recommended business hall corresponding to the business hall recommendation request, and display the target recommendation score and navigation route corresponding to the recommended business hall.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes a program stored in the memory, it implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method as described in any one of claims 1-7.

Images