Method, device, electronic equipment and medium for dynamic recommendation of appointment sites

Abstract

A method and device for dynamic recommendation of reservation sites, electronic equipment and medium are provided, which can be applied to the fields of big data technology and artificial intelligence technology. The method comprises the following steps: obtaining time information of a customer entering a reservation system; judging, based on the time information, an opening condition of a reservation entrance when the customer enters the reservation system; in the case where the reservation entrance is not open, outputting a first recommended site based on a pre-constructed pre-recommendation model; and in the case where the reservation entrance is open, outputting a second recommended site based on a pre-constructed dynamic adjustment model.

Description

Technical Field

[0001] This invention relates to the fields of big data technology and artificial intelligence technology, and more specifically to a method, apparatus, electronic device and medium for dynamically recommending appointment locations. Background Technology

[0002] The reservation and redemption of commemorative coins are handled by major banks, with both offline and online reservation options. When popular commemorative coins are issued, online reservation quotas are often exhausted within minutes or even tens of seconds by customers using mobile banking or online banking. Furthermore, different issuing institutions and sales channels for commemorative coins establish different reservation outlets, which vary in number, location, and service quality. Because customers need to select a redemption outlet during the reservation process, and each outlet has different quotas, reservation numbers, and popularity, reservations often fail due to insufficient quotas at the chosen outlet. Specifically, the reservation systems of major banks require customers to independently select a redemption outlet during the reservation period. Customers must filter through provinces, cities, districts, counties, and individual outlets to choose one that is conveniently located and still has redemption quotas available. This process is time-consuming, and for popular commemorative coins, quotas at popular outlets can be exhausted within tens of seconds. Customers often spend a lot of time searching for redemption outlets, ultimately resulting in quota exhaustion and reservation failure when they submit their reservation requests.

[0003] To address the aforementioned issues, existing technologies propose recommending commemorative coins to target users based on the probability of successful reservations at various bank branches within their historical search range. However, this method only considers customers' past reservation records and cannot meet new needs beyond their previous choices, resulting in a poor customer experience. Therefore, the key challenge is how to quickly and effectively select the best branch for reservations to ensure a high success rate while satisfying the reservation needs of the majority of customers. Summary of the Invention

[0004] In view of the above problems, according to a first aspect of the present invention, a method for dynamically recommending appointment locations is provided, characterized in that the method includes: obtaining the time information of a customer entering the appointment system; determining the openness of the appointment portal when the customer enters the appointment system based on the time information; outputting a first recommended location based on a pre-constructed pre-recommendation model when the appointment portal is not open; and outputting a second recommended location based on a pre-constructed in-process dynamic adjustment model when the appointment portal is open.

[0005] According to some exemplary embodiments, the step of outputting the first recommended service point based on a pre-built pre-recommendation model specifically includes: acquiring first reservation data for each service point; analyzing the first reservation data based on a pre-trained success rate analysis model to output the first reservation success rate for each service point; acquiring the user's location information to obtain the actual distance data between each service point and the user; obtaining a rating factor for each service point based on the actual distance data; and obtaining a comprehensive score for each service point based on the first reservation success rate and the rating factor, and outputting the first recommended service point based on the comprehensive score.

[0006] According to some exemplary embodiments, the first reservation data includes: reservation quota, number of participants in the reservation, percentage of reservations completed after T seconds, and black market user identification information, where T is a preset value.

[0007] According to some exemplary embodiments, the pre-trained success rate analysis model specifically includes: obtaining a training dataset and a test dataset based on the first reservation data; extracting M sub-training datasets with replacement from the training dataset, where M is a positive integer; obtaining a feature set based on the first reservation data; extracting N sub-feature sets with replacement from the feature set, where N is a positive integer; training L decision trees based on the sub-training datasets and sub-feature sets respectively to construct a random forest model, where L is a pre-set value; and evaluating the model based on the test dataset to obtain the success rate analysis model.

[0008] According to some exemplary embodiments, the analysis of the first reservation data based on the pre-trained success rate analysis model and the output of the first reservation success rate of each branch specifically includes: selecting features based on the first reservation data, extracting feature values, inputting them into multiple decision trees to obtain corresponding decision weights; calculating the total decision weight based on the decision weight of each feature value, and obtaining the first reservation success rate of each branch based on the total decision weight.

[0009] According to some exemplary embodiments, obtaining the rating factor for each network point based on the actual distance data specifically includes: calculating the rating factor through a rating factor function, wherein the rating factor function is the ratio of the rating parameter a to the actual distance data, and the rating parameter a is a preset value.

[0010] According to some exemplary embodiments, the step of outputting the first recommended location based on the comprehensive score specifically includes: storing the top k locations with the comprehensive score in a location recommendation table, and setting the location with the first comprehensive score as the first recommended location, where k is a preset value.

[0011] According to some exemplary embodiments, the step of outputting the second recommended outlet based on the pre-built real-time dynamic adjustment model specifically includes: obtaining the second reservation data of each outlet in the outlet recommendation table; generating a real-time dynamic adjustment function based on the second reservation data; calculating the second reservation success rate of each outlet in the order of each outlet in the outlet recommendation table based on the real-time dynamic adjustment function, wherein the second reservation success rate is 0 or 1; and outputting the second recommended outlet based on the second reservation success rate.

[0012] According to some exemplary embodiments, the step of recommending the second recommended outlet to the customer based on the output of the real-time dynamic adjustment model further includes: if the second appointment success rate is 1, then outputting the corresponding outlet as the second recommended outlet; if the second appointment success rate is 0, calculating the second appointment success rate of the next outlet in the outlet recommendation table; if the second appointment success rate of each outlet is 0, then outputting an empty second recommended outlet and suggesting that the customer select one manually.

[0013] According to some exemplary embodiments, the second reservation data includes: the reservation system's opening time, remaining quota, and the number of reservation requests to be submitted on the current page.

[0014] According to a second aspect of the present invention, an apparatus for dynamically recommending reservation locations is provided. The apparatus includes: a time information acquisition module, configured to: acquire time information of a customer entering the reservation system; a reservation entrance opening judgment module, configured to: determine the opening status of the reservation entrance when the customer enters the reservation system based on the time information; a first recommendation module, configured to: output a first recommended location based on a pre-built pre-recommendation model when the reservation entrance is not open; and a second recommendation module, configured to: output a second recommended location based on a pre-built real-time dynamic adjustment model when the reservation entrance is open.

[0015] According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method as described above.

[0016] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method described above.

[0017] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described above.

[0018] The above-described one or more embodiments have the following advantages or beneficial effects: Based on the time information of customers entering the reservation system, suitable recommended locations can be intelligently recommended to customers with different reservation location selection needs, thereby helping customers to select reservation locations more efficiently. Therefore, preferred locations can be recommended for customer groups who enter the reservation system when it is not open or who enter when it is open, enabling the recommendation of locations with high historical success rates or real-time success rates, thereby further improving user experience and enhancing customer loyalty. Attached Figure Description

[0019] The above-described features, other objects, and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0020] Figure 1 The illustration schematically depicts an application scenario of the method, apparatus, equipment, and medium for dynamically recommending appointment locations according to embodiments of the present invention.

[0021] Figure 2 A flowchart illustrating a method for dynamically recommending appointment locations according to an embodiment of the present invention is shown.

[0022] Figure 3 The flowchart illustrates a method for recommending a first recommended outlet to a customer based on the output of a pre-recommendation model according to an embodiment of the present invention.

[0023] Figure 4 A flowchart illustrating a method for pre-training a success rate analysis model according to an embodiment of the present invention is shown.

[0024] Figure 5 The flowchart illustrates a method for recommending second recommended outlets to customers based on the output of a real-time dynamic adjustment model according to an embodiment of the present invention.

[0025] Figure 6 The diagram illustrates the structure of a device for dynamically recommending appointment locations according to an embodiment of the present invention.

[0026] Figure 7 A block diagram of an electronic device suitable for implementing a dynamic recommendation method for reservation outlets according to an embodiment of the present invention is shown schematically. Detailed Implementation

[0027] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0030] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0031] In the technical solution of this invention, the acquisition, storage and application of user personal information all comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good morals.

[0032] First, the technical terms used in this article are explained and clarified as follows.

[0033] Machine learning: Machine learning refers to the process by which machines learn from large amounts of historical data using statistical algorithms, and then use the generated experience models to guide business operations. It is a multidisciplinary field that specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance.

[0034] Random Forest: Random forest is a method that uses multiple decision trees to train, classify, and predict sample data. While classifying data, it can also give importance scores for each variable and evaluate the role of each variable in the classification.

[0035] Bank branches: Bank branches refer to the places where banks operate to the public. They are generally divided into branches, sub-branches, branch offices, savings offices, and 24-hour self-service banks.

[0036] Major banks' online reservation systems allocate a certain quota for each redemption branch. Currently, these systems require customers to manually select a redemption branch during the reservation period. Customers must filter through provinces, cities, districts, counties, and individual branches to choose a branch that is reasonably far away and still has available quota. This process is time-consuming, and popular branches for commemorative coins often run out of quota within seconds. Customers often spend a lot of time searching for redemption branches, ultimately resulting in quota exhaustion and reservation failure when they submit their reservation requests. Manually selecting branches not only prolongs the submission time and reduces the success rate of reservations, but also leads to poor customer satisfaction.

[0037] Based on this, embodiments of the present invention provide a method for dynamically recommending reservation locations. The method includes: acquiring the time information of a customer entering the reservation system; determining, based on the time information, whether the reservation portal is open when the customer enters the reservation system; if the reservation portal is not open, outputting a first recommended location based on a pre-built pre-recommendation model; and if the reservation portal is open, outputting a second recommended location based on a pre-built real-time dynamic adjustment model. In the method according to embodiments of the present invention, based on the time information of a customer entering the reservation system, suitable recommended locations can be intelligently recommended to customers with different reservation needs, thereby helping customers select reservation locations more efficiently. Specifically, if the reservation portal is not open when a customer enters the reservation system, a first recommended location is recommended to the customer, i.e., a location with a high historical reservation success rate and a suitable distance, to ensure that the optimal reservation location is recommended to this customer group; if the reservation portal is open when a customer enters the reservation system, a second recommended location is recommended to the customer, i.e., a location where reservations can currently be successfully made, to help this customer group improve their reservation success rate, thereby avoiding customers spending a lot of time manually selecting locations, improving customer experience, and enhancing customer loyalty.

[0038] It should be noted that the method, apparatus, equipment, and medium for dynamic recommendation of appointment outlets as defined in this invention can be used in the fields of big data technology and artificial intelligence technology, as well as in the financial field, and can also be used in various other fields besides big data technology, artificial intelligence technology, and the financial field. The application fields of the method, apparatus, equipment, and medium for dynamic recommendation of appointment outlets provided in the embodiments of this invention are not limited.

[0039] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information all comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good morals.

[0040] In the technical solution of the present invention, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0041] Figure 1 The illustration schematically depicts an application scenario of the method, apparatus, equipment, and medium for dynamically recommending appointment locations according to embodiments of the present invention.

[0042] like Figure 1 As shown, application scenario 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as a medium for providing a communication link between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0043] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0044] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0045] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0046] It should be noted that the method for dynamically recommending reservation locations provided in this embodiment of the invention can generally be executed by server 105. Correspondingly, the device for dynamically recommending reservation locations provided in this embodiment of the invention can generally be located in server 105. The method for dynamically recommending reservation locations provided in this embodiment of the invention can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the device for dynamically recommending reservation locations provided in this embodiment of the invention can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0047] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0048] Figure 2 A flowchart illustrating a method for dynamically recommending appointment locations according to an embodiment of the present invention is shown.

[0049] like Figure 2 As shown, the method 200 for dynamically recommending appointment locations in this embodiment may include operations S210 to S240.

[0050] In operation S210, obtain the time information of the customer entering the appointment system.

[0051] In operation S220, the openness of the reservation portal when a customer enters the reservation system is determined based on the time information.

[0052] Existing online commemorative coin reservation systems typically include the following structure: a user interface, providing users with a platform for making reservations, usually a webpage or mobile application; a back-end management system, used to manage reservation information, branch information, and inventory information; and a notification system, used to send notifications to users regarding reservation success, failure, or reminders. Correspondingly, it can include the following functions: users can check the currently available quantity of commemorative coins and branch locations; the system can send notifications to users regarding reservation success, failure, or reminders via SMS, email, mobile application push notifications, etc.

[0053] Therefore, the general process for reserving commemorative coins can be as follows: register or log in to an account; check the commemorative coin inventory and issuing outlets in the system, select the desired type of commemorative coin and outlet location; enter the quantity to be reserved and personal information, confirm the reservation information and submit the reservation request; if the reservation is successful, the system will send a notification to the user, including the time of successful reservation, reservation code and the time and place to collect the commemorative coins.

[0054] In embodiments of the present invention, different customers enter the reservation system at different times, resulting in situations where the reservation portal is either open or closed. This leads to two groups of customers: those who have already entered the system before the reservation portal opens and those who have already entered the system during the reservation process. Based on the different needs of these two customer groups, different reservation outlet recommendation models can be provided. Furthermore, the time information of a customer entering the reservation system reflects the type of customer group. Specifically, if a customer enters the system before the reservation portal opens, they belong to the pre-entry customer group; if a customer enters the system after the reservation portal opens, they belong to the in-process customer group.

[0055] When operating S230, if the reservation portal is not open, the first recommended branch is output based on the pre-built pre-recommendation model.

[0056] Figure 3 The flowchart illustrates a method for outputting a first recommended site based on a pre-recommendation model according to an embodiment of the present invention.

[0057] like Figure 3 As shown, the method for outputting the first recommended site based on the pre-recommendation model in this embodiment may include operations S310 to S350.

[0058] Using S310, the first reservation data of each branch is obtained.

[0059] In an embodiment of the present invention, the first reservation data is historical reservation data from various outlets during several historical issuances, and this data includes the following categories:

[0060] (1) Reservation quota: that is, the total reservation quota reserved by the outlet in a certain issuance, calculated per set;

[0061] (2) Number of participants in the reservation: that is, the total number of people who made reservation requests in a certain issuance at this outlet, including successful and failed records;

[0062] (3) Percentage of reservations after 30 seconds: The percentage of the reservation quota of this branch that has been reserved 30 seconds after the reservation portal has been opened; Percentage of reservations after 60 seconds: The percentage of the reservation quota of this branch that has been reserved 60 seconds after the reservation portal has been opened; Percentage of reservations after T seconds: The percentage of the reservation quota of this branch that has been reserved T seconds after the reservation portal has been opened.

[0063] (4) Black Market User Information: Black market user information refers to the black market users in the successful reservation orders of this branch. The black market users are identified as users whose ID numbers and names do not match in the successful reservations. If black market users exist, the number of black market users is counted as the black market user information of this branch.

[0064] The various types of first appointment data mentioned above can provide comprehensive information and references, which can improve the accuracy of prediction success rates.

[0065] During operation S320, the first appointment data is analyzed based on the pre-trained success rate analysis model, and the first appointment success rate of each branch is output.

[0066] In an embodiment of the present invention, a success rate analysis model is obtained by training a random forest model, and is used to output the first appointment success rate of the first appointment data.

[0067] Figure 4 A flowchart illustrating a method for pre-training a success rate analysis model according to an embodiment of the present invention is shown.

[0068] like Figure 4 As shown, the method for pre-training the success rate analysis model in this embodiment may include operations S410 to S440.

[0069] In operation S410, based on the first reservation data, a training dataset and a test dataset are obtained, and M sub-training datasets are extracted from the training dataset with replacement, where M is a positive integer.

[0070] It should be noted that before obtaining the training and test datasets, the first reservation data needs to be preprocessed, including data cleaning and handling of missing values, for subsequent operations.

[0071] In operation S420, based on the first reservation data, a feature set is obtained, and N sub-feature sets are extracted from the feature set with replacement, where N is a positive integer.

[0072] In operation S430, L decision trees are trained based on the sub-training dataset and the sub-feature set respectively to construct a random forest model, where L is a pre-set value.

[0073] In operation S440, an evaluation is performed based on the test dataset to obtain the success rate analysis model.

[0074] In an embodiment of the present invention, the training process of the random forest model includes the following steps: random sampling, randomly selecting a portion of samples from the training dataset for sampling with replacement, forming M sub-training datasets; in each sub-training dataset, randomly sampling with replacement based on the feature set obtained from the first reservation data to obtain N sub-feature sets; for each sub-training dataset, constructing a decision tree model, and dividing the model based on the features of the sub-feature sets during the construction of the decision tree to reduce model complexity and the risk of overfitting; repeating the above steps to construct L decision tree models, combining these decision tree models into a random forest model, and making predictions according to the majority voting principle.

[0075] It should be noted that one of the core principles of random forest is random sampling. Therefore, before building a random forest, it is necessary to perform random sampling with replacement from the training dataset to obtain multiple different sub-training datasets. The feature set is obtained based on the first set of data. Before building the random forest model, it is necessary to perform operations such as feature selection, feature preprocessing, and feature engineering to finally obtain the feature set used to train the model.

[0076] It's important to note that in the Random Forest model, the majority voting principle is an ensemble learning technique used to synthesize and decide on the predictions from multiple decision trees within the random forest. This effectively reduces the variance of the random forest model and improves its stability and generalization ability. In the random forest model, each decision tree makes a prediction for a sample and outputs its prediction. The majority voting principle statistically analyzes the predictions from all decision trees and selects the prediction that appears most frequently as the final prediction.

[0077] By using the random forest model, high-dimensional data can be processed, and because it randomly selects a subset for training, no feature selection or data dimensionality reduction is required. Random forests are less prone to overfitting because they use the average of the decision trees, and each tree only uses a portion of the training data and features. Furthermore, random forests can detect the interactions between features, thereby improving the accuracy of the first appointment success rate at each site.

[0078] In an embodiment of the present invention, the analysis of the first reservation data based on the pre-trained success rate analysis model and the output of the first reservation success rate of each branch specifically includes: selecting features based on the first reservation data, extracting feature values, inputting them into multiple decision trees to obtain corresponding decision weights; calculating the total decision weight based on the decision weight of each feature value, and obtaining the first reservation success rate of each branch based on the total decision weight.

[0079] In operation S330, the user's location information is obtained to acquire the actual distance data between each network point and the user.

[0080] In an embodiment of the present invention, the actual distance data between each outlet and the user can be obtained based on the GPS positioning information obtained by the system when the customer group logs into the reservation system.

[0081] It should be noted that the above selection of methods for obtaining the user's actual distance data is merely exemplary and is not intended to limit the methods for obtaining location information in the embodiments of the present invention. That is, other methods can also be selected for obtaining location information in the embodiments of the present invention. For example, using an address database, the user's location can be determined based on the address information provided by the user to obtain the actual distance data.

[0082] In operation S340, the rating factor for each network point is obtained based on the actual distance data.

[0083] In embodiments of the present invention, the rating factor is calculated using a rating factor function, which is the ratio of the rating parameter 'a' to the actual distance data, where the rating parameter 'a' is preset. The rating factor represents the impact of the actual distance data on the branch rating. Specifically, the rating factor is inversely proportional to the actual distance data, indicating that the larger the actual distance data, i.e., the farther the branch is from the customer, the lower the rating factor. By calculating this rating factor, the balance between rating and distance can be controlled, making the rating results more valuable.

[0084] In operation S350, based on the first appointment success rate and the rating factor, a comprehensive score for each outlet is obtained, and the first recommended outlet is output according to the comprehensive score.

[0085] According to embodiments of the present invention, the process may include calculating the product of a first appointment success rate and a rating factor, storing the k-th ranked locations in the comprehensive rating in a location recommendation table, and setting the location with the highest comprehensive rating as the first recommended location, where k is a preset value. For example, locations with the top 5 or top 10 comprehensive ratings may be stored in the location recommendation table, with the highest-rated location recommended by default, and automatically selected as the default location when a customer enters the appointment system.

[0086] According to an embodiment of the present invention, by combining the first appointment success rate and actual distance data of a certain outlet, multiple optional outlets can be recommended to customers, which can more practically help customers choose outlets and thus save customers' selection time.

[0087] When operating S240, if the reservation portal is already open, the system outputs a second recommended branch based on a pre-built real-time dynamic adjustment model.

[0088] In embodiments of the present invention, the real-time dynamic adjustment model is used for customers whose appointment portal is already open when they enter the appointment system. Since the real-time appointment situation varies across different branches, the pre-approval model is no longer applicable; therefore, the real-time dynamic adjustment model is used for re-evaluation.

[0089] Figure 5 The flowchart illustrates a method for outputting a second recommended site based on a real-time dynamic adjustment model according to an embodiment of the present invention.

[0090] like Figure 5 As shown, the method for outputting the second recommended network point based on the real-time dynamic adjustment model in this embodiment may include operations S510 to S540.

[0091] In operation S510, the second reservation data of each outlet in the outlet recommendation table is obtained.

[0092] In embodiments of the present invention, the real-time dynamic adjustment model needs to collect real-time data on various aspects of customer groups at each branch during the reservation process, i.e., the second reservation data, including: the reservation system's open time, the branch's remaining quota, and the number of people waiting to submit reservation requests on the current page. Table 1 below is an example of the second reservation data for a certain branch:

[0093] Table 1. Second Reservation Data for a Certain Branch

[0094] The reservation system has been open since [date / time]. Remaining amount The current page has a number of reservation requests pending submission. 1 100％ 1000 2 97％ 970 3 95％ 950 4 93％ 930 5 90％ 900 … … …

[0095] In operation S520, a real-time dynamic adjustment function is generated based on the second reservation data.

[0096] In embodiments of the present invention, the dynamic adjustment function generated based on the second reservation data can be implemented through linear fitting or nonlinear fitting. Specifically, it can be implemented through the following process: Based on the reservation system's open time, the remaining quota at the branch, and the number of reservation requests to be submitted on the current page, an appropriate fitting function is selected for fitting. If the data exhibits a linear relationship, a linear fitting function can be selected, for example, y = ax + b; if the data exhibits a nonlinear relationship, a nonlinear fitting function can be selected, such as an exponential function, a logarithmic function, or a polynomial function; the data is substituted into the fitting function, and the parameters of the fitting function are calculated using the least squares method or other mathematical methods to obtain the final fitting function. If a nonlinear fitting function is used, it can be solved using numerical calculation methods.

[0097] It should be noted that the above selection of methods for generating in-process dynamic adjustment functions is merely exemplary and is not intended to limit the methods for generating in-process dynamic adjustment functions in the embodiments of the present invention. That is, other methods can also be selected for generating in-process dynamic adjustment functions in the embodiments of the present invention.

[0098] In operation S530, based on the real-time dynamic adjustment function, the second appointment success rate of each network point is calculated according to the order of each network point in the network point recommendation table, wherein the second appointment success rate is 0 or 1.

[0099] In operation S540, based on the second appointment success rate, the second recommended outlet is output.

[0100] In an embodiment of the present invention, a second appointment success rate of 0 or 1 indicates that there are only two outputs: success or failure, that is, whether a certain recommended outlet in the outlet recommendation table can be successfully booked at the current time.

[0101] In an embodiment of the present invention, if the second appointment success rate is 1, the corresponding outlet is output as the second recommended outlet; if the second appointment success rate is 0, the second appointment success rate of the next outlet in the outlet recommendation table is calculated; if the second appointment success rate of each outlet is 0, the second recommended outlet is output as empty, and the customer is advised to select manually. Specifically, the above process includes: calculating the second appointment success rate of the first-ranked outlet in the outlet recommendation table; if the second appointment success rate is 1, then the first-ranked outlet is output as the second recommended outlet; if the second appointment success rate is 0, then the second appointment success rate of the second-ranked outlet is calculated; calculating the second appointment success rate of the second-ranked outlet; if the second appointment success rate is 1, then the second-ranked outlet is output as the second recommended outlet; if the second appointment success rate is 0, then the second appointment success rate of the third-ranked outlet is calculated... calculating the second appointment success rate of the k-th ranked outlet in the outlet recommendation table; if the second appointment success rate is 1, then the k-th ranked outlet is output as the second recommended outlet; if the second appointment success rate is 0, that is, the second appointment success rate of all outlets in the outlet recommendation table is 0, indicating that no outlet meets the recommendation model at the current time, then the second recommended outlet is output as empty, and the customer is advised to select manually.

[0102] In embodiments of the present invention, by setting a real-time dynamic adjustment model, it is possible to recommend outlets with high real-time success rates, avoiding the failure of recommended outlets for customers who have entered the reservation system after the reservation portal has opened, thereby further improving customer experience and enhancing user stickiness.

[0103] According to embodiments of the present invention, locations with suitable distance and success rate can be selected as preferred reservation and redemption locations for customers, replacing the old process where customers had to manually select locations from province, city, county, district, and other levels. This solves the problems of long search times and cumbersome procedures for customers manually searching for locations, and can quickly and effectively recommend the best locations for reservations, avoiding reservation failures and poor customer experience caused by long selection times. At the same time, combined with a real-time dynamic adjustment model, it can make more comprehensive recommendations for customers based on different times they enter the system, preventing recommended locations from becoming invalid for customers who have entered the reservation system after the reservation portal's opening time, thereby further improving customer experience and enhancing user stickiness.

[0104] Figure 6 The diagram illustrates the structure of a device for dynamically recommending appointment locations according to an embodiment of the present invention.

[0105] like Figure 6As shown, the device 600 for dynamically recommending reservation outlets according to this embodiment includes a time information acquisition module 610, a reservation entry opening judgment module 620, a first recommendation module 630, and a second recommendation module 640.

[0106] The time information acquisition module 610 can be used to acquire the time information of the customer entering the reservation system. In one embodiment, the time information acquisition module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0107] The reservation entry opening determination module 620 can be used to determine the opening status of the reservation entry when a customer enters the reservation system based on the time information. In one embodiment, the reservation entry opening determination module 620 can be used to execute the operation S220 described above, which will not be repeated here.

[0108] The first recommendation module 630 can be used to output a first recommended location based on a pre-built pre-recommendation model when the reservation portal is not open. In one embodiment, the first recommendation module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0109] The second recommendation module 640 can be used to output a second recommended service point based on a pre-built real-time dynamic adjustment model when the reservation portal is open. In one embodiment, the second recommendation module 640 can be used to perform the operation S240 described above, which will not be repeated here.

[0110] According to an embodiment of the present invention, the first recommendation module 630 includes: a first reservation data acquisition unit, a first reservation success rate analysis module, an actual distance data acquisition unit, a rating factor acquisition unit, and a first recommended outlet acquisition unit.

[0111] The first reservation data acquisition unit can be used to acquire the first reservation data of each branch. In one embodiment, the first reservation data acquisition unit can be used to perform the operation S310 described above, which will not be repeated here.

[0112] The first appointment success rate analysis module can be used to analyze the first appointment data based on a pre-trained success rate analysis model and output the first appointment success rate for each branch. In one embodiment, the first appointment success rate analysis module can be used to perform the operation S320 described above, which will not be repeated here.

[0113] The actual distance data acquisition unit can be used to acquire the user's location information to obtain the actual distance data between each network point and the user. In one embodiment, the actual distance data acquisition unit can be used to perform the operation S330 described above, which will not be repeated here.

[0114] The rating factor acquisition unit can be used to obtain the rating factor for each network point based on the actual distance data. In one embodiment, the rating factor acquisition unit can be used to perform the operation S340 described above, which will not be repeated here.

[0115] The first recommended service point acquisition unit can be used to obtain a comprehensive score for each service point based on the first appointment success rate and the rating factor, and output the first recommended service point according to the comprehensive score. In one embodiment, the first recommended service point acquisition unit can be used to perform the operation S350 described above, which will not be repeated here.

[0116] In an embodiment of the present invention, the first appointment success rate analysis module may include a dataset acquisition unit, a feature set acquisition unit, a model building unit, and an evaluation model unit.

[0117] The dataset acquisition unit can be used to acquire a training dataset and a test dataset based on the first reservation data, and to extract M sub-training datasets with replacement from the training dataset, where M is a positive integer. In one embodiment, the dataset acquisition unit can be used to perform the operation S410 described above, which will not be repeated here.

[0118] The feature set acquisition unit can be used to acquire a feature set based on the first reservation data, and extract N sub-feature sets with replacement from the feature set, where N is a positive integer. In one embodiment, the feature set acquisition unit can be used to perform the operation S420 described above, which will not be repeated here.

[0119] The model building unit can be used to train L decision trees based on the sub-training dataset and the sub-feature set respectively to construct a random forest model, where L is a pre-defined value. In one embodiment, the model building unit can be used to perform the operation S430 described above, which will not be repeated here.

[0120] The evaluation model unit can be used to perform an evaluation based on the test dataset to obtain the success rate analysis model. In one embodiment, the evaluation model unit can be used to perform the operation S440 described above, which will not be repeated here.

[0121] In an embodiment of the present invention, the second recommendation module 640 may include a second appointment data acquisition unit, a real-time dynamic adjustment function generation unit, a second appointment success rate calculation unit, and a second recommendation site output unit.

[0122] The second reservation data acquisition unit can be used to acquire the second reservation data of each outlet in the outlet recommendation table. In one embodiment, the second reservation data acquisition unit can be used to perform the operation S510 described above, which will not be repeated here.

[0123] The in-process dynamic adjustment function generation unit can be used to generate an in-process dynamic adjustment function based on the second reservation data. In one embodiment, the in-process dynamic adjustment function generation unit can be used to execute the operation S520 described above, which will not be repeated here.

[0124] The second appointment success rate calculation unit can be used to calculate the second appointment success rate of each network point according to the order of each network point in the network point recommendation table based on the real-time dynamic adjustment function, wherein the second appointment success rate is 0 or 1. In one embodiment, the second appointment success rate calculation unit can be used to perform the operation S530 described above, which will not be repeated here.

[0125] The second recommended service point output unit can be used to output a second recommended service point based on the second appointment success rate. In one embodiment, the second appointment data acquisition unit can be used to perform the operation S540 described above, which will not be repeated here.

[0126] Figure 7 A block diagram of an electronic device suitable for implementing a dynamic recommendation method for reservation outlets according to an embodiment of the present invention is shown schematically.

[0127] like Figure 7 As shown, an electronic device 700 according to an embodiment of the present invention includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage portion 707 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0128] RAM 703 stores various programs and data required for the operation of electronic device 700. Processor 701, ROM 702, and RAM 703 are interconnected via bus 704. Processor 701 executes various operations of the method flow according to embodiments of the present invention by executing programs in ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also execute various operations of the method flow according to embodiments of the present invention by executing programs stored in said one or more memories.

[0129] According to an embodiment of the present invention, the electronic device 700 may further include an input / output (I / O) interface 707, which is also connected to the bus 704. The electronic device 700 may also include one or more of the following components connected to the I / O interface 707: an input section 707 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 707 including a hard disk, etc.; and a communication section 707 including a network interface card such as a LAN card, modem, etc. The communication section 707 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 707 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 707 as needed.

[0130] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0131] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of the present invention, a computer-readable storage medium may include ROM 702 and / or RAM 703 and / or one or more memories other than ROM 702 and RAM 703 described above.

[0132] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of the present invention.

[0133] When the computer program is executed by the processor 701, it performs the functions defined in the system / apparatus of this invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0134] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 707, and / or installed from a removable medium 711. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0135] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 707, and / or installed from removable medium 711. When the computer program is executed by processor 701, it performs the functions defined in the system of this embodiment of the invention. According to embodiments of the invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0136] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0137] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0138] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A method for dynamically recommending appointment locations, characterized in that, The method includes: Obtain the time information when the customer enters the appointment system; Based on the aforementioned time information, determine whether the reservation portal is open when a customer enters the reservation system; If the reservation portal is not open, the first recommended service point will be output based on a pre-built recommendation model, including: Obtain the initial reservation data from each branch; The first reservation data is analyzed based on a pre-trained success rate analysis model, and the first reservation success rate of each branch is output. Obtain the user's location information to obtain the actual distance data between each network point and the user; Based on the actual distance data, the rating factors for each location are obtained; Based on the first appointment success rate and the scoring factor, a comprehensive score for each outlet is obtained, and the first recommended outlet is output according to the comprehensive score. With the reservation portal open, a second recommended service point is output based on a pre-built real-time dynamic adjustment model, including: Obtain the second reservation data of each outlet in the outlet recommendation table, wherein the outlet recommendation table includes the outlets ranked in the top k by the comprehensive score, where k is a preset value; A real-time dynamic adjustment function is generated based on the second reservation data; Based on the real-time dynamic adjustment function, the second appointment success rate of each network point is calculated according to the order of each network point in the network point recommendation table, wherein the second appointment success rate is 0 or 1; Based on the second appointment success rate, output the second recommended service point.

2. The method according to claim 1, characterized in that, The first reservation data includes: reservation quota, number of participants, percentage of reservations completed after T seconds, and identification information of black market users, where T is a preset value.

3. The method according to claim 2, characterized in that, The pre-trained success rate analysis model specifically includes: Based on the first reservation data, a training dataset and a test dataset are obtained, and M sub-training datasets are extracted from the training dataset with replacement, where M is a positive integer; Based on the first reservation data, a feature set is obtained, and N sub-feature sets are extracted from the feature set with replacement, where N is a positive integer; L decision trees are trained based on the sub-training dataset and the sub-feature set respectively to construct a random forest model, where L is a pre-defined value; The success rate analysis model is obtained by evaluating the test dataset.

4. The method according to any one of claims 1-3, characterized in that, The pre-trained success rate analysis model analyzes the first appointment data and outputs the first appointment success rate for each branch, specifically including: Based on the first reservation data, features are selected, feature values ​​are extracted, and input into multiple decision trees to obtain the corresponding decision weights; The total decision weight is calculated based on the decision weight of each feature value, and the first reservation success rate of each branch is obtained based on the total decision weight.

5. The method according to claim 1, characterized in that, The process of obtaining the rating factors for each location based on the actual distance data specifically includes: The rating factor is calculated using a rating factor function, which is the ratio of the rating parameter a to the actual distance data, where the rating parameter a is a preset value.

6. The method according to claim 1, characterized in that, The step of outputting the first recommended location based on the comprehensive score specifically includes: Store the k outlets with the highest overall scores in the outlet recommendation table, and set the outlet with the highest overall score as the first recommended outlet.

7. The method according to claim 1, characterized in that, The process of recommending second recommended outlets to customers based on the output of the real-time dynamic adjustment model also includes: If the second appointment success rate is 1, then output the corresponding branch as the second recommended branch; If the second appointment success rate is 0, calculate the second appointment success rate of the next branch in the branch recommendation table; If the success rate of the second appointment at each branch is 0, then the output of the second recommended branch will be empty, and the customer will be advised to select one manually.

8. The method according to claim 1 or 7, characterized in that, The second reservation data includes: the reservation system's opening time, remaining quota, and the number of people waiting to submit reservation requests on the current page.

9. A device for dynamically recommending appointment locations, characterized in that, The device includes: The time information acquisition module is used to: acquire the time information of customers entering the appointment system; The reservation entry opening determination module is used to: determine the opening status of the reservation entry when a customer enters the reservation system based on the time information; The first recommendation module is used to: output the first recommended service point based on a pre-built pre-recommendation model when the reservation portal is not open; and The second recommendation module is used to: output a second recommended service point based on a pre-built real-time dynamic adjustment model when the reservation portal is open; The first reservation data acquisition unit is used to: acquire the first reservation data of each branch; The first appointment success rate analysis module is used to: analyze the first appointment data based on a pre-trained success rate analysis model and output the first appointment success rate of each branch. The actual distance data acquisition unit is used to: acquire the user's location information to obtain the actual distance data between each network point and the user; The rating factor acquisition unit is used to: obtain the rating factor for each network point based on the actual distance data; The first recommended outlet acquisition unit is used to: obtain a comprehensive score for each outlet based on the first appointment success rate and the rating factor, and output the first recommended outlet according to the comprehensive score; The second reservation data acquisition unit is used to: acquire the second reservation data of each outlet in the outlet recommendation table, wherein the outlet recommendation table includes the outlets ranked in the top k by the comprehensive score, where k is a preset value; The in-process dynamic adjustment function generation unit is used to: generate an in-process dynamic adjustment function based on the second reservation data; The second appointment success rate calculation unit is used to: calculate the second appointment success rate of each network point according to the order of each network point in the network point recommendation table based on the in-process dynamic adjustment function, wherein the second appointment success rate is 0 or 1; The second recommended service point output unit is used to: output a second recommended service point based on the second appointment success rate.

10. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images