Hotel resource recommendation method and device, program product and medium

Abstract

The invention provides a hotel resource recommendation method and device, a program product and a medium, belongs to the technical field of business travel resource management, and can solve the problem that employees cannot check in due to the fact that reservation of a hotel by using a fixed bad mark fails, thereby improving the success rate and reliability of hotel reservation. The method comprises the steps of obtaining a first hotel data set of an area where a destination is located, inputting the first hotel data set into a trained isolated forest model to remove outlier hotels, screening out a group hotel data set, then adaptively determining a first difference mark according to hotel prices in the group hotel data set, and determining a second difference mark according to the first difference mark; and recommending hotels for the business travel according to the first difference standard.

Description

Technical Field

[0001] This application relates to the technical field of business travel resource management, and particularly to a hotel resource recommendation method, device, program product, and medium. Background Art

[0002] Currently, business travel often uses a relatively large geographical area (such as yy city) where the destination (such as xx building) is located as the differential standard control area. This differential standard control area often corresponds to a fixed business travel standard (hereinafter referred to as the differential standard). The price of the reserved hotel shall not exceed this differential standard to control business travel costs.

[0003] However, the hotel prices in the smaller area where the destination is located (such as the block where xx building is located) may generally be higher than the differential standard. For example, the hotel prices at the destination may increase as a whole due to factors such as tourism and conferences, and the current hotel prices at the destination are generally higher than the differential standard determined in previous years. This may result in no hotels meeting the differential standard available for selection around the destination, leading to hotel reservation failures and employees being unable to check in, that is, the existing hotel reservation method has poor reliability. Summary of the Invention

[0004] Embodiments of this application provide a hotel resource recommendation method, device, program product, and medium, which can solve the problem that hotel reservations using a fixed differential standard fail, resulting in employees being unable to check in, thereby improving the success rate and reliability of hotel reservations.

[0005] To achieve the above object, the embodiments of this application provide the following technical solutions: In a first aspect, a hotel resource recommendation method is provided. This method is applicable to a server and includes: Receiving a hotel reservation request from a terminal, where the hotel reservation request carries the destination of this business travel; Obtaining a first hotel data set, where the first hotel data set includes one or more of the following features of hotels in the area where the destination is located: location, price, travel distance, travel duration, or type; Inputting the first hotel data set into an isolation forest model for data screening to obtain a set of gregarious hotel data. The isolation forest model is trained based on a hotel sample data set, and the hotel sample data set and the first hotel data set are data sets of the same type; If the number of hotels in the set of gregarious hotel data is greater than or equal to a quantity threshold, determining a first differential standard according to the prices of the hotels in the set of gregarious hotel data; Determining the hotels in the set of gregarious hotel data with prices less than or equal to the first differential standard as recommended hotels, and the recommended hotels are used to reserve hotels for this business travel; Sending a hotel resource recommendation message to the terminal, where the hotel resource recommendation message carries a list of recommended hotels.

[0006] In a possible design solution, the first hotel dataset is input into an isolation forest model for data screening to obtain a gregarious hotel dataset, including: The first hotel dataset is input into an isolation forest model for data screening to obtain a second hotel dataset; If the number of hotels in the second hotel dataset is greater than or equal to the quantity threshold, the second hotel dataset is determined as the gregarious hotel dataset.

[0007] Optionally, inputting the first hotel dataset into an isolation forest model for data screening to obtain a second hotel dataset, including: The first hotel dataset is input into the isolation forest model, and each binary tree in the isolation forest model is traversed to determine the average height of each hotel data in the first hotel dataset in the isolation forest model; Hotel data with an average height greater than or equal to the first height threshold is screened out from the first hotel dataset to construct the second hotel dataset.

[0008] Furthermore, inputting the first hotel dataset into an isolation forest model for data screening to obtain a second hotel dataset, further including: If the number of hotel data with an average height greater than or equal to the first height threshold in the first hotel dataset is less than the quantity threshold, hotel data with an average height greater than or equal to the second height threshold is screened out from the first hotel dataset to construct the second hotel dataset, and the second height threshold is less than the first height threshold.

[0009] Optionally, inputting the first hotel dataset into an isolation forest model for data screening to obtain a second hotel dataset, including: The first hotel dataset is input into the isolation forest model, and each binary tree in the isolation forest model is traversed to determine the average height of each hotel data in the first hotel dataset in the isolation forest model; Hotel data with a quantity greater than or equal to the quantity threshold is screened out from the first hotel dataset in descending order of average height to construct the second hotel data.

[0010] In a possible design solution, determining a first difference standard according to the prices of hotels in the gregarious hotel dataset, including: Determining a second difference standard according to the prices of hotels in the gregarious hotel dataset, where the second difference standard is the average value or median value of the lowest prices of each hotel in the gregarious hotel dataset; Determining the first difference standard according to the second difference standard and the difference standard threshold, and the difference standard threshold corresponds to the destination.

[0011] Optionally, determining the first difference standard according to the second difference standard and the difference standard threshold, including: If the second difference label is less than or equal to the difference label threshold, the second difference label is determined as the first difference label.

[0012] Optionally, determining the first difference label according to the second difference label and the difference label threshold includes: If the second difference label is greater than the difference label threshold and there is a hotel in the group hotel set whose price is less than or equal to the difference label threshold, the difference label threshold is determined as the first difference label.

[0013] Optionally, determining the first difference label according to the second difference label and the difference label threshold includes: If the price of each hotel in the group hotel set is greater than the difference label threshold, the second difference label is determined as the first difference label.

[0014] Further, determining the second difference label as the first difference label includes: If the deviation between the second difference label and the difference label threshold is less than or equal to the difference label deviation threshold, the second difference label is determined as the first difference label.

[0015] In a possible design, obtaining the first hotel data set includes: Filtering the hotel data in the area where the destination is located according to the first filtering rule to generate the first hotel data set, and the first filtering rule includes one or more of the following: information on the first geographical area where the destination is located, the first hotel price range, the first distance or the first travel duration between the hotel and the destination, the first hotel type.

[0016] Optionally, the method further includes: If the number of hotels in the group hotel data set is less than the number threshold, and / or the prices of the hotels in the group hotel data set are all greater than the difference label threshold, then filter the hotel data in the area where the destination is located according to the second filtering rule to generate the first hotel data set, and the second filtering rule includes one or more of the following: information on the second geographical area where the destination is located, the second hotel price range, the second distance or the second travel duration between the hotel and the destination, the second hotel type; wherein, the second geographical area includes the first geographical area and is larger than the first geographical area; The second hotel price range includes the first hotel price range and is larger than the first hotel price range; The second distance is greater than the first distance; The second travel duration is greater than the first travel duration; The number of types of the second hotel type is more than the number of types of the first hotel type.

[0017] Optionally, the hotel resource recommendation message also carries difference label calculation information, and the difference label calculation information is used to record the calculation method and result of the first difference label.

[0018] Further, the method further includes: Receive a hotel reservation confirmation message from a terminal. The hotel reservation confirmation message carries reservation information for booking a target hotel from the recommended hotels, and the target hotel is used to provide services for this business trip. Send a hotel reservation completion message to the terminal. The hotel reservation completion message carries the reservation success information of the target hotel.

[0019] Optionally, the business trip allowance calculation information and the reservation success information are used for the reimbursement of this business trip.

[0020] In a second aspect, a hotel resource recommendation device is provided. The device can be a server or other device that can execute the hotel resource recommendation method described in the first aspect. The device includes: a processing module and a transceiver module; wherein, The transceiver module is configured to receive a hotel reservation request from a terminal. The hotel reservation request carries the destination of this business trip. The processing module is configured to obtain a first hotel data set. The first hotel data set includes one or more of the following features of the hotels in the destination area: location, price, travel distance, travel duration, or type. The processing module is further configured to input the first hotel data set into an isolation forest model for data screening to obtain a set of conforming hotel data. The isolation forest model is trained based on a hotel sample data set, and the hotel sample data set is of the same type as the first hotel data set. The processing module is further configured to, if the number of hotels in the set of conforming hotel data is greater than or equal to a quantity threshold, determine a first business trip allowance based on the prices of the hotels in the set of conforming hotel data. The processing module is further configured to determine the hotels in the set of conforming hotel data with prices less than or equal to the first business trip allowance as recommended hotels, and the recommended hotels are used to book hotels for this business trip. The transceiver module is further configured to send a hotel resource recommendation message to the terminal. The hotel resource recommendation message carries a list of recommended hotels.

[0021] In a possible design, the processing module is further configured to: Input the first hotel data set into an isolation forest model for data screening to obtain a second hotel data set. If the number of hotels in the second hotel data set is greater than or equal to the quantity threshold, determine the second hotel data set as the set of conforming hotel data.

[0022] Optionally, the processing module is further configured to: Input the first hotel data set into the isolation forest model, traverse each binary tree in the isolation forest model, and determine the average height of each hotel data in the first hotel data set in the isolation forest model. Filter the hotel data with an average height greater than or equal to the first height threshold from the first hotel dataset to construct a second hotel dataset.

[0023] Furthermore, the processing module is also used to, if the number of hotel data with an average height greater than or equal to the first height threshold in the first hotel dataset is less than the quantity threshold, filter the hotel data with an average height greater than or equal to the second height threshold from the first hotel dataset to construct a second hotel dataset, where the second height threshold is less than the first height threshold.

[0024] Optionally, the processing module is also used to: Input the first hotel dataset into the isolation forest model, traverse each binary tree in the isolation forest model, and determine the average height of each hotel data in the first hotel dataset in the isolation forest model; Filter the hotel data with a quantity greater than or equal to the quantity threshold from the first hotel dataset in descending order of average height to construct the second hotel data.

[0025] In a possible design, the processing module is also used to: Determine the second price difference standard according to the prices of the hotels in the gregarious hotel dataset, where the second price difference standard is the average value or median value of the lowest prices of each hotel in the gregarious hotel dataset; Determine the first price difference standard according to the second price difference standard and the price difference threshold, where the price difference threshold corresponds to the destination.

[0026] Optionally, the processing module is also used to, if the second price difference standard is less than or equal to the price difference threshold, determine the second price difference standard as the first price difference standard.

[0027] Optionally, the processing module is also used to, if the second price difference standard is greater than the price difference threshold and there is a hotel with a price less than or equal to the price difference threshold in the gregarious hotel set, determine the price difference threshold as the first price difference standard.

[0028] Optionally, the processing module is also used to, if the price of each hotel in the gregarious hotel set is greater than the price difference threshold, determine the second price difference standard as the first price difference standard.

[0029] Furthermore, the processing module is also used to, if the deviation between the first price difference standard and the price difference threshold is less than or equal to the price difference deviation threshold, determine the second price difference standard as the first price difference standard.

[0030] In a possible design, the processing module is also used to filter the hotel data in the area where the destination is located according to the first filtering rule to generate the first hotel dataset, and the first filtering rule includes one or more of the following: information on the first geographical area where the destination is located, the first hotel price range, the first distance or the first travel duration between the hotel and the destination, the first hotel type.

[0031] Optionally, the processing module is further configured to, if the number of hotels in the grouped hotel dataset is less than the number threshold, and / or if the hotel prices in the grouped hotel dataset are all greater than the differential standard threshold, filter the hotel data in the destination area according to the second filtering rule to generate a first hotel dataset. The second filtering rule includes one or more of the following: information on the second geographical area where the destination is located, the second hotel price range, the second distance or the second travel duration between the hotel and the destination, and the second hotel type; Wherein, the second geographical area includes the first geographical area and is larger than the first geographical area; The second hotel price range includes the first hotel price range and is larger than the first hotel price range; The second distance is greater than the first distance; The second travel duration is greater than the first travel duration; The number of types of the second hotel type is more than the number of types of the first hotel type.

[0032] Optionally, the hotel resource recommendation message further carries differential standard calculation information, which is used to record the calculation method and result of the first differential standard.

[0033] Furthermore, the transceiver module is further configured to: Receive a hotel reservation confirmation message from the terminal. The hotel reservation confirmation message carries reservation information for booking a target hotel from the recommended hotels. The target hotel is used to provide services for this business trip; Send a hotel reservation completion message to the terminal. The hotel reservation completion message carries the reservation success information of the target hotel.

[0034] Optionally, the differential standard calculation information and the reservation success information are used for the reimbursement of this business trip.

[0035] In a third aspect, an electronic device is provided, including: a processor, and the processor is coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the device executes the method described in any implementation manner of the first aspect.

[0036] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a program or instructions. When the program or instructions are run on a computer, the computer is caused to execute the method described in any implementation manner of the first aspect.

[0037] In a fifth aspect, a computer program product is provided. The computer program product includes: computer program code. When the computer program code is run on a computer, the computer is caused to execute the method described in any implementation manner of the first aspect.

[0038] Based on the technical solution provided by the embodiments of the present application, the server can obtain the first hotel dataset of the destination area, input the first hotel dataset into the trained isolation forest model to eliminate outlier hotels, and screen out the inlier hotel dataset. Then, the server can adaptively determine the first difference standard according to the hotel prices in the inlier hotel dataset, and recommend hotels for this business trip according to the first difference standard, which can solve the problem that hotel reservations fail and employees cannot check in because the hotel prices at the destination are generally higher than the fixed difference standard, thereby improving the success rate and reliability of hotel reservations.

[0039] Specifically, the first hotel dataset can be input into the isolation forest model to traverse all binary trees, and the average height of each hotel data in the first hotel dataset can be obtained. Then, the hotel data with an average height greater than or equal to the first height threshold or the second height threshold are grouped into a second hotel dataset. Then, the second hotel dataset with the number of included hotel data greater than or equal to the quantity threshold is used as the inlier hotel dataset to eliminate outlier hotel data, ensuring that the inlier hotel dataset has sufficient hotel data that meets the requirements for selection, and further improving the success rate and reliability of hotel reservations.

[0040] Optionally, instead of using height thresholds, sufficient hotel data can be directly selected from the first hotel dataset in descending order of average height to construct the second hotel data and the inlier hotel data, which can further improve the success rate and reliability of hotel reservations.

[0041] Specifically, the average value or median of the hotel prices in the inlier hotel dataset can be used as the dynamic difference standard (the second difference standard). Then, according to the comparison result between the dynamic difference standard and the fixed difference standard (the difference standard threshold), the first difference standard applicable to this business trip is adaptively determined, and hotels are recommended or reserved according to the first difference standard, so as to improve the success rate and reliability of hotel reservations and take into account the business trip cost as much as possible.

[0042] Optionally, when the second difference standard (dynamic difference standard) is less than or equal to the difference standard threshold (fixed difference standard), it indicates that the consumption level at the destination is lower than or equivalent to the fixed difference standard, which can ensure that a hotel can be reserved. In this scenario, the dynamic difference standard (the second difference standard) not higher than the fixed difference standard can also be used to reserve hotels to save the business trip cost as much as possible.

[0043] Optionally, when the second difference standard is greater than the difference standard threshold and there are hotels with prices less than or equal to the difference standard threshold in the inlier hotel set, it indicates that although the consumption level at the destination is higher than or equivalent to the fixed difference standard, there are still hotels with prices lower than the fixed difference standard, which can ensure that a hotel can be reserved. In this scenario, the fixed difference standard (the difference standard threshold) can be used to reserve hotels to save the business trip cost as much as possible.

[0044] Optionally, when the price of each hotel in the group hotel set is greater than the differential standard threshold, it indicates that the consumption level of the destination is generally higher than the fixed differential standard, and it is impossible to book a hotel using the fixed differential standard. In this scenario, a dynamic differential standard (the second differential standard) can be considered to book the hotel, that is, give priority to considering the consumption level of the destination to book the hotel to ensure the success rate and reliability of hotel booking. Description of the Drawings

[0045] Figure 1 Schematic diagram of the architecture of the travel management system provided by the embodiment of the present application; Figure 2 Schematic flow chart of a hotel resource recommendation method provided by the embodiment of the present application; Figure 3 Schematic flow chart of a method for screening data of the first hotel dataset based on the isolation forest model provided by the embodiment of the present application; Figure 4 Schematic flow chart of another method for screening data of the first hotel dataset based on the isolation forest model provided by the embodiment of the present application; Figure 5 Schematic flow chart of yet another method for screening data of the first hotel dataset based on the isolation forest model provided by the embodiment of the present application; Figure 6 Schematic flow chart of yet another method for screening data of the first hotel dataset based on the isolation forest model provided by the embodiment of the present application; Figure 7 Schematic flow chart of a method for determining the first differential standard according to the prices of hotels in the group hotel dataset provided by the embodiment of the present application; Figure 8 Schematic flow chart of another method for determining the first differential standard according to the prices of hotels in the group hotel dataset provided by the embodiment of the present application; Figure 9 Schematic flow chart of yet another method for determining the first differential standard according to the prices of hotels in the group hotel dataset provided by the embodiment of the present application; Figure 10 Schematic flow chart of yet another method for determining the first differential standard according to the prices of hotels in the group hotel dataset provided by the embodiment of the present application; Figure 11 Schematic flow chart of yet another method for determining the first differential standard according to the prices of hotels in the group hotel dataset provided by the embodiment of the present application; Figure 12 Schematic diagram of the structure of a hotel resource recommendation device provided by the embodiment of the present application; Figure 13 Schematic diagram of the structure of an electronic device provided by the embodiment of the present application. Detailed Embodiments

[0046] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in this application will be described below with reference to the accompanying drawings.

[0047] Exemplarily, Figure 1 is a schematic architecture diagram of the business trip management system provided by the embodiments of this application. As Figure 1 shown, the system includes a terminal and a server.

[0048] Among them, the above-mentioned server is located on the network side of the business trip management system, and the terminal device communicates with the server wirelessly or wiredly. The server can also be called a cloud device or a network device, and can be a mainframe computer, a computing device, or other devices with the ability to process business trip services, which are not limited in the embodiments of this application.

[0049] The terminal can also be called a terminal device, a user equipment (UE), a mobile station, a mobile terminal, a client, etc. The terminal device can be a mobile phone, a tablet computer, a Pad, a personal computer, etc. The embodiments of this application do not limit the specific technologies and specific device forms adopted by the terminal device. It should be noted that the hotel resource recommendation method provided by the embodiments of this application can be used for Figure 1 between the terminal and the server as shown.

[0050] After receiving a hotel reservation request containing the destination sent by the terminal, the server can obtain a first hotel data set in the area where the destination is located, input the first hotel data set into a trained isolation forest model to eliminate outlier hotels, screen out a set of inlier hotels, and then adaptively determine a first expense standard according to the hotel prices in the set of inlier hotels, and recommend hotels for this business trip according to the first expense standard, which can solve the problem that hotel reservations fail and employees cannot check in because the hotel prices at the destination are generally higher than the fixed expense standard, thereby improving the success rate and reliability of hotel reservations.

[0051] Those skilled in the art can understand that Figure 1 is only a simplified schematic diagram for easy understanding, and the shown architecture does not constitute any limitation on the business trip management system. The actual business trip management system may include more or fewer devices than shown in the figure. For example, it may also include relay devices, such as base stations, that establish communication connections between the terminal and the server, and / or other terminals, Figure 1 which are not drawn in the figure.

[0052] Next, the hotel resource recommendation method provided by the embodiments of this application will be specifically described in conjunction with Figures 2 - 11 Exemplarily,

[0053] Exemplarily, Figure 2The flowchart shows a method for recommending hotel resources provided by an embodiment of this application. This method is applicable to the server shown in Figure 1 As shown in Figure 2 , this method includes: S1. The server receives a hotel reservation request from a terminal.

[0054] Among them, the hotel reservation request carries the destination of this business trip. The destination can be the address of the customer where the employee travels on business, the conference address, etc. For example, it can be the customer's office location, xx building hosting the conference, etc. That is, the destination referred to in the embodiments of this application is usually a specific location, and its geographical scope is usually much smaller than the destination referred to in the business trip standard, such as yy city.

[0055] Optionally, the hotel reservation request can also carry other information, such as the name and gender of each business trip employee, the start and end dates of this business trip, the location, price, room type (single room, double room, suite, etc.) of the hotel expected to check in, the acceptable distance and travel duration between the hotel and the destination, and personalized requirements such as whether the hotel needs to provide services such as Internet access and breakfast. The embodiments of this application do not limit this.

[0056] S2. The server obtains a first hotel data set.

[0057] Among them, the area where the destination is located usually refers to a small geographical area including the location where the destination is located. For example, it is the geographical area within 2 kilometers around the destination. The hotels in the area where the destination is located are various types of business entities that can provide accommodation services in this geographical area, such as star hotels, budget hotels, guesthouses, farmhouses, couple hotels, etc. The embodiments of this application do not limit this.

[0058] The first hotel data set includes one or more of the following features of the hotels in the area where the destination is located: location, price, travel distance, travel duration, or type. Among them, the location can be longitude and latitude, geodetic coordinates, etc. The price can be the unit price of the hotel providing accommodation services, such as 500 yuan / day, 300 yuan / day, and can have multiple values according to different room types. The travel distance can be the straight-line distance or the travel distance between the hotel and the destination. The travel duration can be the commuting time between the hotel and the destination. Both the travel distance and the travel duration can correspond to the travel mode (such as walking, cycling, driving, bus, subway, etc.). These hotel data can be obtained through means such as network search and stored in the server for later use.

[0059] In a possible design, S2. The server obtains a first hotel data set, including: The server filters the hotel data in the area where the destination is located according to the first filtering rule to generate a first hotel data set.

[0060] Among them, the first filtering rule includes one or more of the following: information on the first geographical area where the destination is located, the first hotel price range, the first distance or the first travel duration between the hotel and the destination, and the first hotel type.

[0061] Among them, the first geographical area may be a relatively small geographical area around the destination, such as the area within 2 kilometers around the destination. The first hotel price range may be the price range of hotels within the first geographical area acceptable for this business trip, such as 400 yuan to 1000 yuan per day for a double room and 300 yuan to 600 yuan per day for a single room. The first distance may be the straight-line distance between the hotel and the destination or the travel distance corresponding to a certain mode of transportation. The first duration may be the commuting duration between the hotel and the destination, such as the commuting time corresponding to a certain mode of transportation. The first hotel type may be the hotel type acceptable for this business trip, such as accepting single rooms and double rooms but not suites.

[0062] Specifically, the server can, according to the first filtering rule, through technical means such as network search, screen out hotel data within a specified range (the first geographical area) around the destination to generate a first hotel data set. A hotel can correspond to generating one hotel data or multiple hotel data, which is not limited in the embodiments of the present application.

[0063] In addition, during the process of obtaining the first hotel data set, data preprocessing can also be performed on the obtained hotel data, such as missing value processing, outlier processing, duplicate removal processing, noise data processing, format conversion, etc., to improve the accuracy and reliability of the data and facilitate subsequent processing and improve efficiency.

[0064] It should be noted that data preprocessing usually can only eliminate some obvious or easily processed abnormal data. To further improve the quality of the first hotel data set and ensure the accuracy of subsequent model training, an isolation forest model can also be used to iteratively clean the first hotel data set to thoroughly clean the miscellaneous abnormal data contained in the first hotel data set, that is, execute the following S3. Among them, the isolation forest model is a fast anomaly detection method with linear time complexity and high accuracy.

[0065] S3, the server inputs the first hotel data set into the isolation forest model for data screening to obtain a set of conforming hotel data.

[0066] Among them, the isolation forest model is trained based on the hotel sample dataset. The hotel sample dataset is of the same type as the first hotel dataset and can usually be constructed according to historical hotel data, which may include, but is not limited to, hotel data in a relatively large geographical area where the destination is located (such as yy city). For example, both the hotel sample data and the first hotel data include the attribute (feature) of hotel price. The destination is in city A, and the historical hotel data is the hotel data of city B. At this time, the historical hotel data of city B can be normalized, such as the price of a hotel in city B / average price of hotels in city B, and the isolation forest model can be trained using the historical hotel data of city B containing the normalized hotel price to improve the generalization ability of the isolation forest model. Correspondingly, the price of each hotel in the area where the destination is located in the first hotel dataset can be converted into a normalized price first (such as the price of the destination hotel / average price of hotels in city A), and then the normalized first hotel dataset is input into the trained isolation forest model for data screening. It is also possible to perform the normalization process when obtaining the first hotel dataset and then convert it back to the real price when determining the recommended hotels in the following S5 for convenient booking.

[0067] In some embodiments, using the isolation forest algorithm to screen the data of the first hotel dataset mainly includes two processes: training the isolation forest model based on the hotel sample dataset and screening the data of the first hotel dataset.

[0068] Specifically, training the hotel sample dataset usually includes the following steps: Construct an initial isolation forest model; Input the obtained historical hotel dataset into the initial isolation forest model for training to generate an isolation forest model (hereinafter simply referred to as isolation forest model 1) to complete the training process of the standard dataset.

[0069] Exemplarily, Ψ sample points can be randomly selected from the hotel sample dataset as a sub-sample set and placed in the root node of the tree. A feature is randomly specified (e.g., randomly selected from features such as hotel price, distance, travel duration, hotel type number, etc.). A cutting point p is randomly generated in the current node data (this cutting point is between the maximum and minimum values of the specified feature in the current node). A hyperplane is generated with this cutting point, and the current node data space is divided into two sub-spaces: the hotel sample data with the value of the specified feature less than the segmentation point p is placed in the left sub-node of the current node, and the hotel sample data greater than or equal to the segmentation point p is placed in the right sub-node of the current node; then, according to the above method, recursion is performed in the left and right sub-nodes respectively, continuously constructing new left and right sub-nodes until there is only one hotel sample data (cannot be cut any further) in all sub-nodes or the sub-nodes have reached the maximum height, then the construction of a binary tree is completed. Repeat the above process until the number of constructed binary trees reaches the specified number, thus completing the training process of the isolation forest model.

[0070] Furthermore, in the embodiments of the present application, before generating the isolation forest model, the parameters of the isolation forest model need to be set. For example, the maximum height of the binary tree can be 50% of the number of samples in the sub-sample set, and the number of binary trees in the isolation forest model can be 2 times the number of features, etc.

[0071] Then, the isolation forest model 1 is used to perform anomaly detection on the first hotel dataset, that is, the first hotel dataset is input into the isolation forest model 1 for data screening, and a part of the abnormal data (outlier hotel data) is eliminated to obtain a conforming hotel dataset.

[0072] The following combines Figures 3 - 11 Specifically illustrate the data screening process.

[0073] Exemplarily, Figure 3 is a schematic flowchart of a method for screening data of the first hotel dataset based on the isolation forest model provided by the embodiments of the present application. As Figure 3 shown, S3, the server inputs the first hotel dataset into the isolation forest model for data screening to obtain a conforming hotel dataset, including S31 - S32: S31, the server inputs the first hotel dataset into the isolation forest model for data screening to obtain a second hotel dataset.

[0074] Specifically, each hotel data in the first hotel dataset is input into the Isolation Forest model, and each binary tree in the Isolation Forest model is traversed. Then, it is calculated which layer of each binary tree in the Isolation Forest model each hotel data in the first hotel dataset finally falls into, and the average height of each hotel data in this Isolation Forest model is obtained. Finally, according to the average height of each hotel data in the first hotel dataset, after removing a part of the hotel data (outlier hotel data), the remaining hotel data forms the second hotel dataset.

[0075] In a possible design solution, combined with Figure 3 , such as Figure 4 shown, in S31, the server inputs the first hotel dataset into the Isolation Forest model for data screening to obtain the second hotel dataset, including S311 - S312: S311, the server inputs the first hotel dataset into the Isolation Forest model, traverses each binary tree in the Isolation Forest model, and determines the average height of each hotel data in the first hotel dataset in the Isolation Forest model.

[0076] S312, the server screens out the hotel data with an average height greater than or equal to the first height threshold from the first hotel dataset to construct the second hotel dataset.

[0077] Specifically, from the first hotel dataset, after removing the hotel data (outlier hotel data) with an average height less than the first height threshold, the remaining hotel data is used to generate the second hotel dataset.

[0078] Among them, the first height threshold can be 30%, 20%, etc. of the maximum value of the average height of all hotel data in the first hotel dataset, or can be the average value or median value of the average height of all hotel data in the first hotel dataset, or can also be a preset value, which is not limited in the embodiments of the present application.

[0079] Further, combined with Figure 4 , such as Figure 5 shown, in S312, the server screens out the hotel data with an average height greater than or equal to the first height threshold from the first hotel dataset to construct the second hotel dataset, including S3121: S3121, if the number of hotel data with an average height greater than or equal to the first height threshold in the first hotel dataset is less than the quantity threshold, the server screens out the hotel data with an average height greater than or equal to the second height threshold from the first hotel dataset to construct the second hotel dataset.

[0080] Among them, the second height threshold is less than the first height threshold to relax the requirements and screen out more hotel data for selection and reservation, so as to further improve the reliability of hotel reservation.

[0081] In another possible design solution, in combination with Figure 3 , as Figure 6 shown, in S31, the server inputs the first hotel dataset into the Isolation Forest model for data screening to obtain the second hotel dataset, including S311 and S314: S311, the server inputs the first hotel dataset into the Isolation Forest model, traverses each binary tree in the Isolation Forest model, and determines the average height of each hotel data in the first hotel dataset in the Isolation Forest model.

[0082] S314, the server screens out hotel data with a quantity greater than or equal to the quantity threshold from the first hotel dataset in descending order of the average height to construct the second hotel dataset.

[0083] Compared with the screening solutions in S312 - S313, in S314, as long as the quantity of hotel data in the first hotel dataset is more than the quantity threshold, it can ensure that a sufficient quantity of hotel data is screened out to construct the second hotel dataset, which can further improve the reliability of hotel reservations.

[0084] It should be noted that the screening solutions in S312 - S313 and the screening solution in S314 can also be implemented in combination. For example, the quantity of hotel data should meet the requirements of the quantity threshold, and the average height of the screened hotel data should also meet the requirements of the first height threshold or the second height threshold. The embodiments of the present application do not limit this.

[0085] S32, if the quantity of hotels in the second hotel dataset is greater than or equal to the quantity threshold, the server determines the second hotel dataset as the gregarious hotel dataset.

[0086] Furthermore, in order to ensure the cleanliness of the obtained gregarious hotel dataset, a training - screening iterative operation can also be performed on the first hotel dataset. For example, the gregarious hotel dataset output after screening the first hotel dataset using the Isolation Forest model 1 can be re - input into the Isolation Forest model 1 for iterative training to obtain another Isolation Forest model (Isolation Forest model 2), and the first hotel dataset can be screened again using the Isolation Forest model 2 to obtain another gregarious hotel dataset. This training - screening process can be iterated once or multiple times until the quantity of the output gregarious hotel dataset meets the set requirements. For example, the set requirements can be that the quantity of hotels in the gregarious hotel dataset needs to be greater than or equal to the hotel quantity threshold. In practical applications, the number of training - screening iterations depends on the trade - off between data cleanliness and information loss. The more iterations, the relatively cleaner the hotel data in the gregarious hotel dataset, but more useful information may also be lost.

[0087] It should be noted that in order to reduce the number of divisions, converge quickly, and improve the training and screening efficiency, parameters such as the number of binary trees and the maximum height in the isolation forest model can be adjusted. For example, the maximum height of the binary trees in the isolation forest model can be a part of the number of hotel data in the historical hotel sample dataset or the first hotel dataset, such as 50%, 25%, etc.

[0088] S4. If the number of hotels in the grouped hotel dataset is greater than or equal to the quantity threshold, the server determines the first price difference standard according to the prices of the hotels in the grouped hotel dataset.

[0089] In a possible design solution, combined with Figure 2 , such as Figure 7 shown, in S4, the server determines the first price difference standard according to the prices of the hotels in the grouped hotel dataset, including: S41. The server determines the second price difference standard according to the prices of the hotels in the grouped hotel dataset. The second price difference standard is the average or median value of the lowest prices of each hotel in the grouped hotel dataset. S42. The server determines the first price difference standard according to the second price difference standard and the price difference threshold. The price difference threshold corresponds to the destination.

[0090] Among them, the second price difference standard is a price difference standard dynamically determined according to the hotel prices at the destination, which can truly reflect the consumption level at the destination. The first price difference standard determined by comprehensively considering the second price difference standard and the fixed price difference (price difference threshold) can not only truly reflect the consumption level at the destination but also take into account the need for business travel cost control. Therefore, it has stronger flexibility in the hotel reservation process.

[0091] Specifically, for the following 3 scenarios, different methods can be used to determine the first price difference standard: Scenario 1. Combined with Figure 7 , such as Figure 8 shown, in S42, the server determines the first price difference standard according to the second price difference standard and the price difference threshold, including: S421. If the second price difference standard is less than or equal to the price difference threshold, the server determines the second price difference standard as the first price difference standard.

[0092] Among them, the second price difference standard (dynamic price difference standard) being less than or equal to the price difference threshold (fixed price difference standard) indicates that the consumption level at the destination is lower than or equivalent to the fixed price difference standard, which can ensure that a hotel can be reserved. In this scenario, a dynamic price difference standard (second price difference standard) not higher than the fixed price difference standard can also be used to reserve a hotel to save business travel costs as much as possible.

[0093] Scenario 2. Combined with Figure 7 , such as Figure 9 shown, in S42, the server determines the first price difference standard according to the second price difference standard and the price difference threshold, including: S422. If the second differential standard is greater than the differential standard threshold and there is a hotel in the group of eligible hotels with a price less than or equal to the differential standard threshold, the server determines the differential standard threshold as the first differential standard.

[0094] Among them, although the second differential standard (dynamic differential standard) is greater than the differential standard threshold (fixed differential standard), there is a hotel in the group of eligible hotels with a price less than or equal to the differential standard threshold, indicating that although the consumption level of the destination is higher than or equivalent to the fixed differential standard, there are still hotels with prices lower than the fixed differential standard, ensuring that a hotel can be booked. In this scenario, the fixed differential standard (differential standard threshold) can be used to book a hotel to save travel costs as much as possible.

[0095] Optionally, in combination with Figure 7 , such as Figure 10 shown, in S42, the server determines the first differential standard according to the second differential standard and the differential standard threshold, including: S423. If the price of each hotel in the group of eligible hotels is greater than the differential standard threshold, the server determines the second differential standard as the first differential standard.

[0096] Among them, the price of each hotel in the group of eligible hotels is greater than the differential standard threshold (it is easy to understand that the second differential standard will also be greater than the differential standard threshold at this time), indicating that the consumption level of the destination is generally higher than the fixed differential standard, and it is impossible to book a hotel using the fixed differential standard. In this scenario, the dynamic differential standard (second differential standard) can be considered to book a hotel, that is, give priority to considering the consumption level of the destination to book a hotel to ensure the success rate and reliability of hotel booking.

[0097] Furthermore, in combination with Figure 10 , such as Figure 11 shown, in S423, if the price of each hotel in the group of eligible hotels is greater than the differential standard threshold, the server determines the second differential standard as the first differential standard, including: S4231. If the price of each hotel in the group of eligible hotels is greater than the differential standard threshold and the deviation between the second differential standard and the differential standard threshold is less than or equal to the differential standard deviation threshold, the server determines the second differential standard as the first differential standard.

[0098] Among them, the differential standard deviation threshold can be a specific value, such as the increase in hotel price not exceeding 100 yuan per day, or a percentage, such as the increase in hotel price not exceeding 20% * fixed differential standard.

[0099] To avoid the second differential standard being much larger than the fixed differential standard, resulting in excessive costs, it is also possible to control the increase range of travel costs. On the one hand, if the increase range of the second differential standard compared to the differential standard threshold is within an acceptable range (such as less than or equal to the differential standard deviation threshold), the remaining process of hotel reservation can be automatically executed, thereby improving the efficiency of hotel reservation. On the other hand, if the increase range of the second differential standard compared to the differential standard threshold exceeds the acceptable range (such as greater than the differential standard deviation threshold), the remaining process of hotel reservation is stopped, and an alarm message is output. This alarm message is used to remind travel standard decision-makers, such as management personnel like the company's general manager, to determine a new fixed differential standard.

[0100] S5, the server determines the hotels in the grouped hotel dataset with hotel prices less than or equal to the first differential standard as recommended hotels, and the recommended hotels are used to reserve hotels for this business trip; S6, the server sends a hotel resource recommendation message to the terminal, and the hotel resource recommendation message carries a list of recommended hotels.

[0101] Specifically, the list of recommended hotels can be sent to the terminal and displayed on the display screen of the terminal. Employees can determine the reserved hotel according to the list of recommended hotels on the hotel reservation interface provided by the terminal.

[0102] Optionally, the method further includes: If the number of hotels in the grouped hotel dataset is less than the number threshold, and / or the hotel prices in the grouped hotel dataset are all greater than the differential standard threshold, then filter the hotel data in the destination area according to the second filtering rule to generate a first hotel dataset. The second filtering rule includes one or more of the following: information on the second geographical area where the destination is located, the second hotel price range, the second distance or second travel duration between the hotel and the destination, and the second hotel type; Among them, the second geographical area includes the first geographical area and is larger than the first geographical area; The second hotel price range includes the first hotel price range and is larger than the first hotel price range; The second distance is greater than the first distance; The second travel duration is greater than the first travel duration; The number of types of the second hotel type is more than the number of types of the first hotel type.

[0103] It can be seen that the second filtering rule is more relaxed than the first filtering rule, and more hotel data can be filtered out from the hotel data in the destination area to construct the first hotel data, so that the server can filter out more hotel data from the first hotel data to construct the grouped hotel data, thereby improving the success rate and reliability of hotel reservation.

[0104] Optionally, the hotel resource recommendation message also carries differential standard calculation information, which is used to record the calculation method and result of the first differential standard.

[0105] Further, please continue to refer to Figure 2 , the method further includes: S7, the server receives a hotel reservation confirmation message from the terminal. The hotel reservation confirmation message carries reservation information for booking a target hotel from the recommended hotels. The target hotel is used to provide services for this business trip.

[0106] S8, the server sends a hotel reservation completion message to the terminal. The hotel reservation completion message carries the reservation success information of the target hotel.

[0107] It should be noted that the interaction process of S1 - S8 can be a complete process for a user (such as a business trip employee) from submitting a hotel reservation request to completing a hotel reservation, so as to provide a full - process closed - loop service for the hotel reservation process, thereby improving the user experience.

[0108] Optionally, the differential standard calculation information and the reservation success information are used for this business trip reimbursement to improve the transparency of business trip information, so as to facilitate business trip cost control and financial accounting.

[0109] It should be noted that the hotel resource recommendation method provided in the embodiments of the present application is not only applicable to the scenario of providing hotel reservation services for employees in the business trip scenario, but also applicable to other scenarios that require hotel reservation such as tourism. The embodiments of the present application do not limit this. For example, in the tourism scenario, the destination can be a tourist attraction. The fixed differential standard (differential standard threshold) can be understood as the hotel accommodation budget in the area where the tourist attraction is located. The first filtering rule and the second filtering rule can be determined according to the personal preferences and economic conditions of the tourist. The second differential standard can be the current hotel price calculated in real - time based on the prices of each hotel in the area where the tourist attraction is located (such as within a radius of 2 kilometers), and then compare the current hotel price with the tourism budget to determine the hotel price acceptable to the tourist (the first differential standard), and recommend hotels to the tourist according to the acceptable price. The tourist can book and check into a hotel from the list of recommended hotels.

[0110] Based on the hotel resource recommendation method provided in the embodiments of the present application, the server can obtain the first hotel data set in the destination area, input the first hotel data set into the trained isolation forest model to eliminate outlier hotels, filter out the inlier hotel data set, then adaptively determine the first differential standard according to the hotel prices in the inlier hotel data set, and recommend hotels for this business trip according to the first differential standard, which can solve the problem that the hotel reservation fails and the employee cannot check in because the hotel prices in the destination are generally higher than the fixed differential standard, thereby improving the success rate and reliability of hotel reservation.

[0111] The above is combined withFigures 2 - 11 The method for recommending hotel resources provided by the embodiments of the present application is described in detail. The following combines Figure 12 and Figure 13 to detail the hotel resource recommendation device and electronic device provided by the embodiments of the present application.

[0112] Exemplarily, Figure 12 is a schematic structural diagram of a hotel resource recommendation device provided by an embodiment of the present application. The device can be a server or other device that can execute the functions of the server in the hotel resource recommendation method described in the above method embodiments, or a component or module that can be set in a server or other devices.

[0113] As Figure 12 shown, the hotel resource recommendation device 1200 includes: a processing module 1201 and a transceiver module 1202; wherein, The transceiver module 1202 is configured to receive a hotel reservation request from a terminal, and the hotel reservation request carries the destination of the current business trip; The processing module 1201 is configured to obtain a first hotel data set, and the first hotel data set includes one or more of the following features of hotels in the area where the destination is located: location, price, travel distance, travel duration, or type; The processing module 1201 is further configured to input the first hotel data set into an isolation forest model for data screening to obtain a set of conforming hotel data. The isolation forest model is trained based on a hotel sample data set, and the hotel sample data set is of the same type as the first hotel data set; The processing module 1201 is further configured to, if the number of hotels in the set of conforming hotel data is greater than or equal to a quantity threshold, determine a first difference standard according to the prices of the hotels in the set of conforming hotel data; The processing module 1201 is further configured to determine the hotels in the set of conforming hotel data whose prices are less than or equal to the first difference standard as recommended hotels, and the recommended hotels are used to reserve hotels for the current business trip; The transceiver module 1202 is further configured to send a hotel resource recommendation message to the terminal, and the hotel resource recommendation message carries a list of recommended hotels.

[0114] In a possible design, the processing module 1201 is further configured to: Input the first hotel data set into an isolation forest model for data screening to obtain a second hotel data set; If the number of hotels in the second hotel data set is greater than or equal to the quantity threshold, determine the second hotel data set as the set of conforming hotel data.

[0115] Optionally, the processing module 1201 is further configured to: Input the first hotel dataset into the isolation forest model, traverse each binary tree in the isolation forest model, and determine the average height of each hotel data in the first hotel dataset in the isolation forest model; Filter out the hotel data with an average height greater than or equal to the first height threshold from the first hotel dataset to construct a second hotel dataset.

[0116] Furthermore, the processing module 1201 is also used to, if the number of hotel data with an average height greater than or equal to the first height threshold in the first hotel dataset is less than the quantity threshold, filter out the hotel data with an average height greater than or equal to the second height threshold from the first hotel dataset to construct a second hotel dataset, where the second height threshold is less than the first height threshold.

[0117] Optionally, the processing module 1201 is also used to: Input the first hotel dataset into the isolation forest model, traverse each binary tree in the isolation forest model, and determine the average height of each hotel data in the first hotel dataset in the isolation forest model; Filter out the hotel data with a quantity greater than or equal to the quantity threshold from the first hotel dataset in descending order of average height to construct the second hotel data.

[0118] In a possible design solution, the processing module 1201 is also used to: Determine the second price difference standard based on the prices of the hotels in the gregarious hotel dataset, where the second price difference standard is the average value or median value of the lowest prices of each hotel in the gregarious hotel dataset; Determine the first price difference standard based on the second price difference standard and the price difference threshold, where the price difference threshold corresponds to the destination.

[0119] Optionally, the processing module 1201 is also used to, if the second price difference standard is less than or equal to the price difference threshold, determine the second price difference standard as the first price difference standard.

[0120] Optionally, the processing module 1201 is also used to, if the second price difference standard is greater than the price difference threshold and there are hotels in the gregarious hotel set with prices less than or equal to the price difference threshold, determine the price difference threshold as the first price difference standard.

[0121] Optionally, the processing module 1201 is also used to, if the price of each hotel in the gregarious hotel set is greater than the price difference threshold, determine the second price difference standard as the first price difference standard.

[0122] Furthermore, the processing module 1201 is also used to, if the deviation between the first price difference standard and the price difference threshold is less than or equal to the price difference deviation threshold, determine the second price difference standard as the first price difference standard.

[0123] In a possible design solution, the processing module 1201 is further configured to screen hotel data in the area where the destination is located according to a first filtering rule to generate a first hotel data set. The first filtering rule includes one or more of the following: information on the first geographical area where the destination is located, the first hotel price range, the first distance or the first travel duration between the hotel and the destination, and the first hotel type.

[0124] Optionally, the processing module 1201 is further configured to, if the number of hotels in the grouped hotel data set is less than the quantity threshold, and / or if the hotel prices in the grouped hotel data set are all greater than the difference standard threshold, screen the hotel data in the area where the destination is located according to a second filtering rule to generate a first hotel data set. The second filtering rule includes one or more of the following: information on the second geographical area where the destination is located, the second hotel price range, the second distance or the second travel duration between the hotel and the destination, and the second hotel type; wherein, the second geographical area includes the first geographical area and is larger than the first geographical area; the second hotel price range includes the first hotel price range and is larger than the first hotel price range; the second distance is greater than the first distance; the second travel duration is greater than the first travel duration; the number of types of the second hotel type is more than the number of types of the first hotel type.

[0125] Optionally, the hotel resource recommendation message further carries difference standard calculation information, and the difference standard calculation information is used to record the calculation method and result of the first difference standard.

[0126] Furthermore, the transceiver module 1202 is further configured to: receive a hotel reservation confirmation message from the terminal. The hotel reservation confirmation message carries reservation information for booking a target hotel from the recommended hotels, and the target hotel is used to provide services for this business trip; send a hotel reservation completion message to the terminal. The hotel reservation completion message carries the reservation success information of the target hotel.

[0127] Optionally, the difference standard calculation information and the reservation success information are used for the reimbursement of this business trip.

[0128] Exemplarily, Figure 13 FIG. is a schematic structural diagram of an electronic device applicable to the hotel resource recommendation method provided in the embodiment of the present application. The electronic device can be a server, or a chip or other component or assembly applied in the server, or other devices that can execute the functions of the server in the above method embodiment.

[0129] As Figure 13As shown, the electronic device 1300 may include at least one processor 1301, a memory 1302, and a transceiver 1303. Among them, there are signal connections between the at least one processor 1301, the memory 1302, and the transceiver 1303. For example, they can be connected through a bus.

[0130] The following specifically introduces each component of the electronic device 1300 in conjunction with Figure 13 : The processor 1301 is the control center of the electronic device 1300 and can be a single processor or a collective term for multiple processing elements. For example, the processor 1301 is one or more central processing units (CPUs), or can be an application specific integrated circuit (ASIC), or an integrated circuit configured to implement the embodiments of the present application. For example: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0131] Among them, the processor 1301 can execute various functions of the electronic device 1300 by running or executing software programs stored in the memory 1302 and calling data stored in the memory 1302.

[0132] In a specific implementation, as an embodiment, the processor 1301 may include one or more CPUs, such as Figure 13 the CPU0 and CPU1 shown in

[0133] In a specific implementation, as an embodiment, the electronic device 1300 may also include multiple processors, such as Figure 13 the processor 1301 and the processor 1304 shown in

[0134] The memory 1302 can be a read-only memory (ROM) or other types of static storage communication devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage communication devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage communication devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1302 can exist independently or be integrated with the processor 1301.

[0135] Among them, the memory 1302 is used to store the software program for executing the technical solution provided in this application and is controlled by the processor 1301 for execution. The above specific implementation manners can refer to the following method embodiments and will not be elaborated here.

[0136] The transceiver 1303 is used for communication with other electronic devices, such as second-hand item trading cabinets. The transceiver 1303 can include a receiving unit to implement the receiving function and a sending unit to implement the sending function.

[0137] It should be noted that Figure 13 the structure of the electronic device 1300 shown in does not constitute a limitation on the electronic device. The actual electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, which are not limited in the embodiments of this application.

[0138] The embodiments of this application provide a computer-readable storage medium. The computer-readable storage medium stores programs or instructions. When the programs or instructions run on a computer, the computer is enabled to execute the method described in any implementation manner in the first aspect.

[0139] The embodiments of this application provide a computer program product. The computer program product includes: computer program code. When the computer program code runs on a computer, the computer is enabled to execute the method described in any implementation manner in the first aspect.

[0140] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. A hotel resource recommendation method, characterized in that: Applicable to a server, the method comprises: Receiving a hotel reservation request from a terminal, wherein the hotel reservation request carries a destination of the current business trip; Obtaining a first hotel dataset, wherein the first hotel dataset includes one or more of the following features of hotels in the area where the destination is located: location, price, travel distance, travel duration, or type; Inputting the first hotel data set into an isolation forest model for data screening to obtain a sociable hotel data set, wherein the isolation forest model is trained based on a hotel sample data set, and the hotel sample data set and the first hotel data set are of the same type; If the number of hotels in the group hotel data set is greater than or equal to the number threshold, determining a first difference standard according to the price of each hotel in the group hotel data set; Determine the hotels in the group hotel data set whose hotel prices are less than or equal to the first difference standard as recommended hotels, and the recommended hotels are used to book hotels for this business trip; A hotel resource recommendation message is sent to the terminal, wherein the hotel resource recommendation message carries a list of recommended hotels.

2. The method according to claim 1, characterized in that: The first hotel dataset is input into the isolation forest model for data screening to obtain a gregarious hotel dataset, including: Inputting the first hotel data set into the isolation forest model for data screening to obtain a second hotel data set; If the number of hotels in the second hotel data set is greater than or equal to the number threshold, the second hotel data set is determined as the group hotel data set.

3. The method according to claim 2, characterized in that The inputting the first hotel data set into the isolation forest model for data screening to obtain a second hotel data set includes: Inputting the first hotel data set into the isolation forest model, traversing each binary tree in the isolation forest model, and determining the average height of each hotel data in the first hotel data set in the isolation forest model; The hotel data whose average height is greater than or equal to the first height threshold is screened out from the first hotel data set to construct the second hotel data set.

4. The method according to claim 3, characterized in that The step of inputting the first hotel data set into the isolation forest model for data screening to obtain a second hotel data set further includes: If the number of hotel data in the first hotel data set whose average height is greater than or equal to the first height threshold is less than the number threshold, hotel data with an average height greater than or equal to a second height threshold is filtered out from the first hotel data set to construct the second hotel data set, and the second height threshold is less than the first height threshold.

5. The method according to claim 2, characterized in that: The inputting the first hotel data set into the isolation forest model for data screening to obtain a second hotel data set includes: Inputting the first hotel data set into the isolation forest model, traversing each binary tree in the isolation forest model, and determining the average height of each hotel data in the first hotel data set in the isolation forest model; According to the order of the average height from high to low, the hotel data whose quantity is greater than or equal to the quantity threshold are screened out from the first hotel data set to construct the second hotel data.

6. The method according to claim 1, characterized in that Determining the first difference mark according to the price of each hotel in the group hotel data set includes: Determine a second difference mark according to the price of each hotel in the group hotel data set, where the second difference mark is the average or median of the lowest price of each hotel in the group hotel data set; The first difference mark is determined according to the second difference mark and a difference mark threshold, and the difference mark threshold corresponds to the destination.

7. The method according to claim 6, characterized in that The determining the first difference mark according to the second difference mark and a difference mark threshold comprises: If the second difference mark is less than or equal to the difference mark threshold, the second difference mark is determined as the first difference mark.

8. The method according to claim 6, characterized in that The determining the first difference mark according to the second difference mark and a difference mark threshold comprises: If the second difference is greater than the difference threshold, and there is a hotel in the group hotel set whose price is less than or equal to the difference threshold, the difference threshold is determined as the first difference.

9. The method according to claim 6, characterized in that The determining the first difference mark according to the second difference mark and a difference mark threshold comprises: If the price of each hotel in the group hotel set is greater than the difference threshold, the second difference is determined as the first difference.

10. The method according to claim 9, characterized in that The step of determining the second difference standard as the first difference standard comprises: If the deviation between the second difference standard and the difference standard threshold is less than or equal to the difference standard deviation threshold, the second difference standard is determined as the first difference standard.

11. The method according to claim 1, characterized in that: The obtaining of the first hotel data set includes: The hotel data of the area where the destination is located is filtered according to a first filtering rule to generate the first hotel data set, wherein the first filtering rule includes one or more of the following: information about a first geographical area where the destination is located, a first hotel price range, a first distance or a first travel time between the hotel and the destination, and a first hotel type.

12. The method according to claim 11, characterized in that Also includes: If the number of hotels in the group hotel data set is less than the number threshold, and / or the hotel prices in the group hotel data set are all greater than the difference threshold, then the hotel data in the area where the destination is located is filtered according to a second filtering rule to generate the first hotel data set, wherein the second filtering rule includes one or more of the following: information about a second geographical area where the destination is located, a second hotel price range, a second distance or a second travel time between the hotel and the destination, and a second hotel type; wherein the second geographical area includes the first geographical area and is larger than the first geographical area; The second hotel price range includes the first hotel price range and is larger than the first hotel price range; The second distance is greater than the first distance; The second passage time is longer than the first passage time; The number of types of the second hotel type is greater than the number of types of the first hotel type.

13. The method according to any one of claims 1 to 12, characterized in that The hotel resource recommendation message also carries difference calculation information, and the difference calculation information is used to record the calculation method and result of the first difference.

14. The method according to claim 13, characterized in that Also includes: receiving a hotel reservation confirmation message from the terminal, the hotel reservation confirmation message carrying reservation information for booking a target hotel from the recommended hotels, the target hotel being used to provide services for this business trip; A hotel reservation completion message is sent to the terminal, wherein the hotel reservation completion message carries reservation success information of the target hotel.

15. The method according to claim 14, characterized in that The difference calculation information and the booking success information are used for this travel reimbursement.

16. An electronic device, characterized in that: include: a processor coupled to the memory; The processor is configured to execute a computer program stored in the memory so that the electronic device executes the method according to any one of claims 1 to 15.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or an instruction, and when the program or the instruction is executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 15.

18. A computer program product, characterized in that The computer program product comprises: a computer program code, and when the computer program code is run on a computer, the computer is caused to perform the method according to any one of claims 1 to 15.

Images