Hotel product recommendation method and device, equipment and storage medium

Abstract

The invention discloses a hotel product recommendation method and device, equipment and a storage medium, and relates to the technical field of data processing, and the hotel product recommendation method comprises the steps: obtaining a user portrait of a target user and a target reservation position; the user portrait and the target reservation position are input into a hotel product scoring model, product scores of all hotel products output by the hotel product scoring model are obtained, and the hotel product scoring model is obtained through iterative training based on user reservation attribute features; and recommending each hotel product based on each product score. According to the method, the user portrait and the target reservation position are obtained, and then product recommendation is carried out through the product score output by the model after iterative training is carried out through the user reservation attribute features, so that the real demands of the user are described and restored more accurately and truly, the reservation transaction rate is improved, and the revenue is increased.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a hotel product recommendation method, device, equipment and storage medium. Background Art

[0002] In the field of hotel product recommendation, although there are many systems dedicated to meeting users' needs to find suitable products, they are insufficient in processing user behavior data. Most methods mainly rely on user characteristics, product characteristics and statistical characteristics of user behavior, such as login days, login time, page click frequency and browsing time, but ignore the decision-making depth behavior patterns shown by users when comparing different products.

[0003] Therefore, although existing hotel product recommendation systems can provide personalized recommendations to a certain extent, they still need to be improved in terms of precision and prediction accuracy, and cannot more truly reflect the actual purchasing behavior of users when browsing products. Summary of the invention

[0004] The main purpose of this application is to provide a hotel product recommendation method, device, equipment and storage medium, aiming to provide personalized recommendations with higher precision and predictive accuracy, thereby improving the booking transaction rate and increasing revenue.

[0005] To achieve the above objectives, the present application proposes a hotel product recommendation method, the method comprising:

[0006] Obtain the user profile of the target user and the target booking location;

[0007] Inputting the user portrait and the target booking location into a hotel product rating model to obtain a product rating of each hotel product output by the hotel product rating model, wherein the hotel product rating model is obtained by iterative training based on user booking attribute features;

[0008] Based on the ratings of the products, recommendations are made for the hotel products.

[0009] In one embodiment, the training process of the hotel product recommendation scoring model includes:

[0010] Obtain several groups of related user booking behavior information, user portraits, and hotel information;

[0011] Based on the associated user booking behavior information, user portraits and hotel information, several groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features are obtained;

[0012] Iterative training is performed on each of the associated customer attribute features, hotel attribute features, behavior statistics attribute features, and user reservation attribute features to obtain the hotel product recommendation scoring model.

[0013] In one embodiment, based on the associated user booking behavior information, user portrait and hotel information, several groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features are obtained, including:

[0014] For any associated user booking behavior information, user portrait, and hotel information: extract features from the user portrait and hotel information to obtain customer attribute features and hotel attribute features;

[0015] Performing data processing on the user booking behavior information to obtain behavior statistical attribute characteristics and user booking attribute characteristics;

[0016] The customer attribute features, the hotel attribute features, the behavior statistics attribute features and the user reservation attribute features are associated and combined.

[0017] In one embodiment, the user booking behavior information includes page access information, user click information, and user browsing information;

[0018] The data processing of the user booking behavior information to obtain the behavior statistical attribute characteristics and the user booking attribute characteristics includes:

[0019] Calculate the page access information, the user click information, and the user browsing information to obtain product click rate, booking conversion rate, and comparison hotel information;

[0020] Associating and combining the product click rate, booking conversion rate and comparative hotel information to generate behavioral statistical attribute features;

[0021] Based on the page access information, the user click information and the user browsing information, a user subscription attribute feature is determined.

[0022] In one embodiment, determining the user subscription attribute characteristics based on the page access information, the user click information, and the user browsing information includes:

[0023] Obtaining a page time decay value, and determining a predetermined in-degree feature based on a page access sequence in the page access information;

[0024] Determining a booking depth feature based on the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information;

[0025] The page time decay value, the booking in-degree feature, and the booking depth feature are calculated to obtain a user booking attribute feature.

[0026] In one embodiment, the recommending each of the hotel products based on the ratings of each of the products includes:

[0027] Sorting the ratings of the products to obtain a ranking list;

[0028] Based on the score ranking list, the product information corresponding to each of the hotel products is associated and combined to generate a product recommendation list;

[0029] The product recommendation list is pushed to target users.

[0030] In one embodiment, after recommending each of the hotel products based on the ratings of each of the products, the method further includes:

[0031] Collect user purchasing behavior;

[0032] Conducting data analysis on the user's purchasing behavior;

[0033] Generate recommended optimization plans based on user purchasing behavior after data analysis.

[0034] In addition, to achieve the above purpose, the present application also proposes a hotel product recommendation device, which includes:

[0035] An acquisition module, used to acquire a user profile of a target user and a target booking location;

[0036] A scoring module, used for inputting the user portrait and the target booking location into a hotel product scoring model to obtain a product score of each hotel product output by the hotel product scoring model, wherein the hotel product scoring model is obtained by iterative training based on user booking attribute features;

[0037] The recommendation module is used to recommend each of the hotel products based on the ratings of each of the products.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a hotel product recommendation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the hotel product recommendation method described above.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the hotel product recommendation method described above are implemented.

[0040] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the hotel product recommendation method described above are implemented.

[0041] The present application provides a hotel product recommendation method, device, equipment and storage medium. The hotel product recommendation method obtains a user portrait and a target booking location of a target user, and then inputs the user portrait and the target booking location into a hotel product rating model to obtain a product rating of each hotel product output by the hotel product rating model, wherein the hotel product rating model is obtained by iterative training based on user booking attribute features, thereby recommending each hotel product based on each product rating, and then recommending products based on the product rating output by the model after iterative training based on the user booking attribute features, thereby more accurately and truly describing and restoring the user's real needs, thereby improving the booking transaction rate and increasing revenue. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flowchart of the first embodiment of the hotel product recommendation method of this application is provided;

[0045] Figure 2 A flowchart of the second embodiment of the hotel product recommendation method of this application is provided;

[0046] Figure 3 A frequency graph of user visits to hotels in one embodiment of the hotel product recommendation method provided by the present application;

[0047] Figure 4 A brief flow chart of the hotel product recommendation method provided by this application;

[0048] Figure 5 This is a schematic diagram of the module structure of the hotel product recommendation device according to an embodiment of the present application;

[0049] Figure 6This is a schematic diagram of the device structure of the hardware operating environment involved in the hotel product recommendation method in the embodiment of the present application.

[0050] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a big data service platform, a hotel product recommendation system, etc. The following takes the hotel product recommendation system as an example to illustrate this embodiment and the following embodiments.

[0054] Based on this, the present application embodiment provides a hotel product recommendation method, referring to Figure 1 , Figure 1 A flowchart of the first embodiment of the hotel product recommendation method of this application is provided.

[0055] In this embodiment, the hotel product recommendation method includes steps S11 to S13:

[0056] Step S11, obtaining a user portrait of a target user and a target reservation location;

[0057] It should be noted that the target user refers to the user who is going to book a hotel product, and the user portrait refers to the user portrait generated based on the user's historical booking information, including basic information (user's gender, age, occupation, educational background, etc.); preference settings (user's preferences set on the platform, such as hotel star rating, location, etc.), spending power (user's booking budget range, historical consumption records, etc.), member information (user's membership level, points, coupons, etc.) and booking history (user's past booked hotels, room types, prices), etc. The target booking location refers to the location of the hotel that the target user is going to book.

[0058] Specifically, the user portrait generated by the target user in the system and the configuration information of the target user are read, thereby obtaining the user portrait of the target user and the target reservation location.

[0059] Step S12, inputting the user portrait and the target booking location into a hotel product rating model to obtain a product rating of each hotel product output by the hotel product rating model, wherein the hotel product rating model is obtained by iterative training based on user booking attribute features;

[0060] It should be noted that the hotel product rating model is used to predict the user's rating or evaluation of the hotel product based on the user's behavior and preferences. The product rating refers to the quantitative rating of the hotel product generated by the model output for the user's personalization, thereby improving the booking conversion rate by accurately predicting the user's preference for the hotel product.

[0061] Step S13, recommending each of the hotel products based on the ratings of each of the products.

[0062] Specifically, the scores of each product are sorted to obtain a score sorting list, and then based on the score sorting list, the product information corresponding to each hotel product is associated and combined to generate a product recommendation list, and then the product recommendation list is pushed to the target user.

[0063] This embodiment obtains a user portrait and a target booking location of a target user, and then inputs the user portrait and the target booking location into a hotel product rating model to obtain a product rating of each hotel product output by the hotel product rating model, wherein the hotel product rating model is obtained by iterative training based on user booking attribute features, thereby recommending each hotel product based on each product rating, and then performing product recommendations based on the product rating output by the model after iterative training based on user booking attribute features, thereby more accurately and truly describing and restoring the user's real needs, thereby improving the booking transaction rate and increasing revenue.

[0064] In a feasible implementation manner, the training process of the hotel product recommendation scoring model includes:

[0065] Step S21, obtaining several groups of related user booking behavior information, user portraits and hotel information;

[0066] It should be noted that the user booking behavior information refers to the behavior information generated by the user when booking a hotel, including page visit information, user click information, and user browsing information, etc., which are not limited here.

[0067] It should be further explained that the hotel information refers to information related to the hotel, including basic information (hotel name, address, contact information, star rating, brand, etc.), facilities and services (facilities provided by the hotel, such as gym, swimming pool, free Wi-Fi, etc.), room information (room type, price, bed type, room facilities, etc.), geographical location (specific location of the hotel, surrounding attractions, transportation convenience, etc.) and user reviews.

[0068] Specifically, the customer's operation behavior on the hotel product, such as browsing, clicking, and staying, can be recorded through log points, and the user's booking behavior information can be obtained according to the business process steps such as the home page, list page, search page, hotel details page, room type page, order filling page, order submission page, hotel review page, etc. At the same time, the user portrait is generated through historical customer information, such as customer age, bank card level, customer membership level, number of children, age, etc., customer portrait tags, etc. In addition, the hotel information can be obtained through the hotel backend system. There is no restriction on the method of obtaining user booking behavior information, user portrait and hotel information, which can be set according to actual conditions.

[0069] Step S22, based on the associated user booking behavior information, user portraits and hotel information, obtaining several groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features;

[0070] It should be noted that the customer attribute characteristics include demographic characteristics (such as age, gender, occupation, income level, etc.), behavioral habits (booking frequency, preferred hotel type, travel destination, etc.), preference characteristics (preferred room type, price sensitivity, facility preference, etc.) and value characteristics (user value assessment of the hotel, such as cost-effectiveness, service quality, etc.) corresponding to different user portraits.

[0071] It should be further explained that the hotel attribute characteristics include hotel star rating, price range, geographical location characteristics, facility service characteristics, user evaluation characteristics, etc. The behavioral statistical attribute characteristics include visit frequency (the number of times users visit the hotel page), click-through rate (the frequency of users clicking on hotel advertisements or links), search frequency (the frequency of users searching for hotels), booking conversion rate (the conversion ratio of users from search to actual booking), etc.

[0072] Furthermore, the user booking attribute features are used to reflect the actual browsing, clicking and booking behaviors of the user in the hotel booking process, including booking in-degree features, booking depth features and time decay values.

[0073] Specifically, for any associated user booking behavior information, user portrait and hotel information: feature extraction is performed on the user portrait and hotel information to obtain customer attribute features and hotel attribute features, and then data processing is performed on the user booking behavior information to obtain behavior statistical attribute features and user booking attribute features, so as to associate and combine the customer attribute features, the hotel attribute features, the behavior statistical attribute features and the user booking attribute features.

[0074] Step S23, iteratively training each of the associated customer attribute features, hotel attribute features, behavior statistics attribute features, and user reservation attribute features to obtain the hotel product recommendation scoring model.

[0075] Specifically, data preprocessing is performed on each of the associated customer attribute features, hotel attribute features, behavior statistical attribute features, and user booking attribute features, such as data cleaning, normalization, etc., so that each of the associated customer attribute features, hotel attribute features, behavior statistical attribute features, and user booking attribute features are input into the initial hotel product recommendation scoring model to obtain the predicted value output by the initial hotel product recommendation scoring model, and then based on the predicted value and the sample label, the model loss value is calculated using the loss function. In this embodiment, the loss function can be set according to actual needs and is not specifically limited here. After the model loss value is calculated, the training process ends, and the error back propagation algorithm is used to update the model parameters in the initial hotel product recommendation scoring model, and then the next training is performed. In the training process, it is determined whether the updated initial hotel product recommendation scoring model meets the preset training end condition. If it meets, the updated initial hotel product recommendation scoring model is used as the hotel product recommendation scoring model. If it does not meet, the model training continues, wherein the preset training end condition includes loss convergence and reaching the maximum number of iterations threshold.

[0076] This embodiment obtains several groups of related user booking behavior information, user portraits and hotel information, and then obtains several groups of related customer attribute characteristics, hotel attribute characteristics, behavior statistical attribute characteristics and user booking attribute characteristics based on each of the related user booking behavior information, user portraits and hotel information, thereby iteratively training each of the related customer attribute characteristics, hotel attribute characteristics, behavior statistical attribute characteristics and user booking attribute characteristics to obtain the hotel product recommendation scoring model, thereby more accurately predicting user preferences for different hotel products, enhancing personalized experience, and increasing the possibility of user clicks and bookings, thereby increasing booking conversion rates, enhancing market competitiveness, and improving user stickiness.

[0077] In a feasible implementation manner, based on the associated user booking behavior information, user portraits and hotel information, a plurality of groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features are obtained, including:

[0078] Step S31, for any associated user booking behavior information, user portrait and hotel information: extract features from the user portrait and hotel information to obtain customer attribute features and hotel attribute features;

[0079] Specifically, for any associated user booking behavior information, user portrait and hotel information: perform feature extraction on the user portrait and hotel information to obtain customer attribute features and hotel attribute features, such as calculating the number of bookings and page visits made by the user within a certain period of time, calculating the average stay time of the user on the page, the periodicity of bookings, etc., and analyzing the frequency of user visits or searches, etc., so as to obtain customer attribute features and hotel attribute features.

[0080] Step S32, performing data processing on the user booking behavior information to obtain behavior statistical attribute characteristics and user booking attribute characteristics;

[0081] Specifically, the page access information, the user click information and the user browsing information are calculated to obtain the product click rate, booking conversion rate and comparative hotel information, and then the product click rate, booking conversion rate and comparative hotel information are associated and combined to generate behavioral statistical attribute characteristics, so as to determine the user booking attribute characteristics based on the page access information, the user click information and the user browsing information.

[0082] Step S33, associating and combining the customer attribute features, the hotel attribute features, the behavior statistics attribute features and the user reservation attribute features.

[0083] Specifically, the extracted customer attribute features, hotel attribute features, behavioral statistical attribute features, and user booking attribute features are integrated to form a complete user-hotel interaction feature set for model training.

[0084] This embodiment performs feature extraction on any associated user booking behavior information, user portrait and hotel information to obtain customer attribute features and hotel attribute features, and then performs data processing on the user booking behavior information to obtain behavior statistical attribute features and user booking attribute features, thereby associating and combining the customer attribute features, the hotel attribute features, the behavior statistical attribute features and the user booking attribute features, and then integrating multiple data sources to construct more comprehensive user and hotel features, thereby improving the performance and accuracy of the recommendation system, enhancing the personalized experience, generating more personalized recommendation information, and meeting the unique needs and preferences of users.

[0085] In a feasible implementation manner, the user booking behavior information includes page access information, user click information, and user browsing information; the data processing of the user booking behavior information to obtain behavior statistical attribute characteristics and user booking attribute characteristics includes:

[0086] Step S41, calculating the page access information, the user click information and the user browsing information to obtain product click rate, booking conversion rate and comparison hotel information;

[0087] It should be noted that the product click-through rate refers to the ratio of the number of times users click on a recommended product to the number of times the product is displayed (or recommended); the booking conversion rate refers to the ratio of the number of times users actually make reservations (such as hotel reservations) after clicking on a recommended product to the number of clicks; the comparative hotel information refers to the information of other hotels that users have considered during the booking process, including but not limited to price, facilities, location, user reviews, etc., so as to understand the information of other hotels that users have considered during the booking process, which in turn helps to analyze the user's decision-making process and preferences, thereby optimizing the recommendation algorithm and providing recommendations that better meet user needs.

[0088] Specifically, according to a preset indicator algorithm, the page access information, the user click information and the user browsing information are calculated to obtain information related to the behavior statistical attribute characteristics such as product click rate, booking conversion rate and comparative hotel information.

[0089] Step S42, associating and combining the product click rate, booking conversion rate and comparison hotel information to generate a behavior statistical attribute feature;

[0090] Specifically, the information calculated such as the product click rate, booking conversion rate, and comparative hotel information is associated and combined to generate behavioral statistical attribute features.

[0091] Step S43: determining user subscription attribute characteristics based on the page access information, the user click information and the user browsing information.

[0092] Specifically, a page time decay value is obtained, and based on the page access sequence in the page access information, a booking in-degree feature is determined, and then based on the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information, a booking depth feature is determined, thereby calculating the page time decay value, the booking in-degree feature, and the booking depth feature to obtain the user booking attribute feature.

[0093] This embodiment calculates the page access information, the user click information and the user browsing information to obtain the product click rate, the booking conversion rate and the comparative hotel information, and then associates and combines the product click rate, the booking conversion rate and the comparative hotel information to generate behavioral statistical attribute characteristics, thereby determining the user booking attribute characteristics based on the page access information, the user click information and the user browsing information, and then making more full use of the collected user data and hotel data to reflect a more realistic user booking process, thereby further improving the recommendation accuracy and the booking conversion rate.

[0094] Based on this, the present application embodiment provides a hotel product recommendation method, referring to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the hotel product recommendation method of this application.

[0095] In a feasible implementation manner, determining the user reservation attribute characteristics based on the page access information, the user click information, and the user browsing information includes:

[0096] Step S51, obtaining a page time decay value, and determining a predetermined in-degree feature based on a page access sequence in the page access information;

[0097] It should be noted that the page time decay value refers to the measure of the user's reduced interest in a page or a hotel over time. It is usually used to reflect the speed of user interest changes over time. The page access sequence refers to the order in which users visit each page during browsing. The booking in-degree feature refers to the number of times a user "enters" a page, that is, the frequency of users entering the page through click operations. Therefore, the booking in-degree feature reflects the user's interest in a specific hotel, which helps predict the user's booking intention.

[0098] Specifically, a page time decay value is obtained, wherein the page time decay value can be obtained by counting the number of ordering users / current customer users in each time window and then normalizing it, and is used for weighted processing of time decay.

[0099] Further, based on the page access sequence in the page access information, the booking in-degree feature is determined. For example, the booking in-degree feature is determined by the user's hotel access frequency graph. Figure 3 , Figure 3 The Pi (i is an integer such as 1, 2, or 3) in is a hotel object, which indicates the hotel products visited by the customer in a certain time window. The arrows between the hotels Pi indicate the order in which the customer compares the quality of different hotel products, and express the order of precedence and comparison between different hotels. The number of arrows for comparison back and forth indicates the degree of attention paid by the user to this product list. Then, the arrow in-degree calculation value of the user's hotel visit frequency graph is used as the number of hotel product comparisons, that is, the booking in-degree feature. Figure 3 Take the user hotel visit frequency graph in as an example, where the hotel product and booking in-degree features can be determined by the data in Table 1.

[0100] Table 1

[0101] Product ID Number of comparisons P1 1 P2 3 P3 1 P4 2 P5 1

[0102] As can be seen from Table 1, the booking in-degree feature of product P1 is 1, the booking in-degree feature of product P2 is 3, and so on.

[0103] Step S52, determining a reservation depth feature based on the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information;

[0104] It should be noted that the page click count refers to the total number of click operations performed by users on a certain page, thereby reflecting the user's participation and interest in the page content. The browsing time refers to the length of time a user stays on a certain page. The booking depth feature refers to the business depth according to the business process steps, that is, the hierarchical depth from product display to order conversion.

[0105] Specifically, the reservation depth feature is determined according to the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information. Please refer to Table 2, which records the hotel reservation system operation steps, and describes the depth of hotel reservation conversion from left to right.

[0106] Table 2

[0107]

[0108]

[0109] Step S53, calculating the page time decay value, the booking in-degree feature, and the booking depth feature to obtain a user booking attribute feature.

[0110] Specifically, according to a preset feature calculation function, the page time decay value, the booking in-degree feature and the booking depth feature are calculated to obtain a user booking attribute feature, wherein the preset feature calculation function can be designed by an expert so as to dynamically and truly reflect the actual meaning of the data, thereby more accurately reflecting the user booking behavior.

[0111] This embodiment obtains a page time decay value, and determines a booking in-degree feature based on the page access sequence in the page access information, and then determines a booking depth feature based on the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information, thereby calculating the page time decay value, the booking in-degree feature, and the booking depth feature to obtain a user booking attribute feature. Considering the time decay of page access can help the recommendation system capture the latest changes in user interests and provide personalized recommendations that better meet the user's current needs, thereby improving data-driven decision-making capabilities, making full use of user behavior data, improving the value of data, and then improving data utilization, so that the model can more accurately predict products that meet user preferences.

[0112] In a feasible implementation manner, the recommending each of the hotel products based on the ratings of each of the products includes:

[0113] Step S61, sorting the ratings of the products to obtain a rating sorting list;

[0114] It should be noted that the score ranking list refers to a list that sorts products according to their scores, including product names, score values, product categories, and product rankings.

[0115] Specifically, the ratings of the products are sorted in descending order to obtain a rating sorting list.

[0116] Step S62, based on the score ranking list, associating and combining the product information corresponding to each of the hotel products to generate a product recommendation list;

[0117] It should be noted that the product recommendation list refers to a product recommendation table generated based on a rating sorted list, which represents product recommendations generated based on the user's actual browsing behavior and product preferences, including product details (detailed introduction of the product, including description, specifications, price, etc.), user ratings and comments, product pictures or videos, links to purchase or learn more, inventory status, promotional information, and hotel information, etc.

[0118] Specifically, according to the score ranking list, the product information corresponding to each of the hotel products is associated and combined, that is, the product information corresponding to each of the hotel products is sorted according to the score of the score ranking list to generate a product recommendation list, wherein the specific list generation template can be set according to actual conditions, such as adding highlights, adding slogans to high-scoring products to attract users, etc., which are not limited here.

[0119] Step S63: Push the product recommendation list to the target user.

[0120] Specifically, the product recommendation list is pushed to the target user, wherein the product recommendation list can be pushed in real time to the mobile device (such as a mobile phone, tablet, computer, etc.) that the target user is using, including push methods such as APP, mini-programs, website links, and text messages. There is no limitation here and it can be set according to actual conditions.

[0121] In this embodiment, the ratings of the products are sorted to obtain a rating sorting list, and then based on the rating sorting list, the product information corresponding to the hotel products is associated and combined to generate a product recommendation list, so as to push the product recommendation list to the target user, thereby increasing the browsing conversion rate by recommending high-rated products, and realizing recommendations based on the user's rating preferences to provide personalized recommendation services. In addition, the rating sorting list can be dynamically updated to reflect the latest user preference feedback.

[0122] In a feasible implementation manner, after recommending each of the hotel products based on the product scores, the method further includes:

[0123] Step S71, collecting user purchasing behavior;

[0124] It should be noted that the user purchasing behavior refers to the actual click behavior of the user after the product recommendation, such as click, purchase, browsing time, jump and other behavioral data.

[0125] Specifically, data on the interaction between target users and hotel products, such as clicks, purchases, browsing time, jumps and other behavioral data, are collected in real time. System logs, including recommendation requests, recommendation results, user feedback, etc., can also be collected to further reflect actual user purchasing behavior. There is no restriction here.

[0126] Step S72, performing data analysis on the user's purchasing behavior to generate product recommendation results;

[0127] It should be noted that the product recommendation effect refers to the performance of product recommendations in actual applications and user feedback, including user click-through rate (CTR), conversion rate (the proportion of users who complete purchases or reservations after clicking on recommended products), user satisfaction, user retention rate coverage (the types and quantity of recommended products), novelty (the ability of the recommendation system to recommend products that are unknown to users but may be of interest to them), real-time (the speed at which the recommendation system responds to changes in user behavior and preferences) and accuracy (the degree to which the recommendation results match the actual needs of users).

[0128] Specifically, data preprocessing is performed on the user purchasing behavior, such as cleaning data, removing outliers and noise, and formatting data, etc., to ensure data consistency and readability, and then key indicators that can reflect product recommendation performance, such as CTR, conversion rate, user satisfaction, etc., are calculated based on the user purchasing behavior after data preprocessing, so as to analyze the performance of current product recommendations through each of the key indicators. Statistical analysis methods, such as clustering, classification, regression, etc., can be used to understand the relationship between user behavior and product recommendation effect. The user purchasing behavior can also be input into a machine learning model to obtain the product recommendation effect output by the model, thereby analyzing potential problems of the recommendation system.

[0129] Step S73: Generate a recommendation optimization plan based on the product recommendation effect.

[0130] It should be noted that the recommendation optimization scheme refers to a series of measures and strategies taken to improve the recommendation effect, such as algorithm optimization, feature engineering (adding or optimizing features used in the recommendation model to better capture user preferences), data cleaning methods, diversity enhancement (introducing diversity mechanisms to avoid recommendation results being too single) and context awareness (adjusting recommendations based on the user's current context), etc. There are no restrictions here and it can be set according to actual conditions.

[0131] Specifically, based on the product recommendation effects, identify the reasons for poor recommendation effects, such as overly single recommendations, lack of personalization, insufficient real-time performance, etc., and then, based on the reasons for poor recommendation effects and data analysis results, design recommendation optimization plans, including algorithm improvements, feature engineering, user experience improvements, etc., and adjust or replace the recommendation algorithm to improve recommendation accuracy.

[0132] Furthermore, after implementing the recommendation optimization plan, continuously monitor the recommendation effects to ensure that the optimization measures are effective. Real-time monitoring tools can be used to track changes in key indicators, and then based on monitoring results and user feedback, continuously adjust and optimize the recommendation strategy, such as conducting regular A / B testing to verify the effectiveness of new strategies.

[0133] This embodiment collects user purchasing behaviors and then performs data analysis on the user purchasing behaviors to generate product recommendation effects, and then generates recommendation optimization solutions based on the product recommendation effects, thereby optimizing the product recommendation system, thereby more accurately meeting customer needs and preferences, and effectively improving customer satisfaction, increasing bookings, and improving the conversion rate from browsing to actual bookings.

[0134] For example, to help understand the implementation process of the hotel product recommendation method, please refer to Figure 4 , Figure 4 A brief flowchart example diagram is provided for the hotel product recommendation method for this application.

[0135] It should be noted that the examples in the figure are only used to understand the present application and do not constitute a limitation on the hotel product recommendation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0136] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0137] This application also provides a hotel product recommendation device, please refer to Figure 5 , the hotel product recommendation device comprises:

[0138] An acquisition module 51 is used to acquire a user portrait of a target user and a target reservation location;

[0139] A scoring module 52 is used to input the user portrait and the target booking location into a hotel product scoring model to obtain a product score of each hotel product output by the hotel product scoring model, wherein the hotel product scoring model is obtained by iterative training based on user booking attribute features;

[0140] The recommendation module 53 is used to recommend each of the hotel products based on the ratings of each of the products.

[0141] The hotel product recommendation device is also used for:

[0142] Obtain several groups of related user booking behavior information, user portraits, and hotel information;

[0143] Based on the associated user booking behavior information, user portraits and hotel information, several groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features are obtained;

[0144] Iterative training is performed on each of the associated customer attribute features, hotel attribute features, behavior statistics attribute features, and user reservation attribute features to obtain the hotel product recommendation scoring model.

[0145] The hotel product recommendation device is also used for:

[0146] For any associated user booking behavior information, user portrait, and hotel information: extract features from the user portrait and hotel information to obtain customer attribute features and hotel attribute features;

[0147] Performing data processing on the user booking behavior information to obtain behavior statistical attribute characteristics and user booking attribute characteristics;

[0148] The customer attribute features, the hotel attribute features, the behavior statistics attribute features and the user reservation attribute features are associated and combined.

[0149] The hotel product recommendation device is also used for:

[0150] Calculate the page access information, the user click information, and the user browsing information to obtain product click rate, booking conversion rate, and comparison hotel information;

[0151] Associating and combining the product click rate, booking conversion rate and comparative hotel information to generate behavioral statistical attribute features;

[0152] Based on the page access information, the user click information and the user browsing information, a user subscription attribute feature is determined.

[0153] The hotel product recommendation device is also used for:

[0154] Obtaining a page time decay value, and determining a predetermined in-degree feature based on a page access sequence in the page access information;

[0155] Determining a booking depth feature based on the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information;

[0156] The page time decay value, the booking in-degree feature, and the booking depth feature are calculated to obtain a user booking attribute feature.

[0157] The hotel product recommendation device is also used for:

[0158] Sorting the ratings of the products to obtain a ranking list;

[0159] Based on the score ranking list, the product information corresponding to each of the hotel products is associated and combined to generate a product recommendation list;

[0160] The product recommendation list is pushed to target users.

[0161] The hotel product recommendation device is also used for:

[0162] Collect user purchasing behavior;

[0163] Performing data analysis on the user's purchasing behavior to generate product recommendation results;

[0164] Based on the product recommendation effect, a recommendation optimization plan is generated.

[0165] The hotel product recommendation device provided by the present application adopts the hotel product recommendation method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the hotel product recommendation device provided by the present application are the same as the beneficial effects of the hotel product recommendation method provided by the above embodiment, and other technical features in the hotel product recommendation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0166] The present application provides a hotel product recommendation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the hotel product recommendation method in the above-mentioned embodiment one.

[0167] Reference below Figure 6 , which shows a schematic diagram of the structure of a hotel product recommendation device suitable for implementing an embodiment of the present application. The hotel product recommendation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The hotel product recommendation device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0168] like Figure 6As shown, the hotel product recommendation device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the hotel product recommendation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. Communication device 1009 can allow hotel product recommendation equipment to carry out wireless or wired communication with other equipment to exchange data. Although the hotel product recommendation equipment with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or less systems can be implemented or possessed alternatively.

[0169] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0170] The hotel product recommendation device provided by the present application adopts the hotel product recommendation method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the hotel product recommendation device provided by the present application are the same as the beneficial effects of the hotel product recommendation method provided by the above embodiment, and other technical features in the hotel product recommendation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0171] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0172] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0173] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the hotel product recommendation method in the above-mentioned embodiment.

[0174] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0175] The computer-readable storage medium may be included in the hotel product recommendation device; or may exist independently without being assembled into the hotel product recommendation device.

[0176] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the hotel product recommendation device, the hotel product recommendation device:

[0177] Obtain the user profile of the target user and the target booking location;

[0178] Inputting the user portrait and the target booking location into a hotel product rating model to obtain a product rating of each hotel product output by the hotel product rating model, wherein the hotel product rating model is obtained by iterative training based on user booking attribute features;

[0179] Based on the ratings of the products, recommendations are made for the hotel products.

[0180] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0181] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0182] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0183] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned hotel product recommendation method, and can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the hotel product recommendation method provided by the above-mentioned embodiment, and will not be repeated here.

[0184] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the above-mentioned hotel product recommendation method when executed by a processor.

[0185] The computer program product provided in this application can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the hotel product recommendation method provided in the above embodiment, which will not be repeated here.

[0186] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A hotel product recommendation method, characterized in that: include: Obtain the user profile of the target user and the target booking location; Inputting the user portrait and the target booking location into a hotel product rating model to obtain a product rating of each hotel product output by the hotel product rating model, wherein the hotel product rating model is obtained by iterative training based on user booking attribute features; Based on the ratings of the products, recommendations are made for the hotel products.

2. The hotel product recommendation method according to claim 1, characterized in that: The training process of the hotel product recommendation scoring model includes: Obtain several groups of related user booking behavior information, user portraits, and hotel information; Based on the associated user booking behavior information, user portraits and hotel information, several groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features are obtained; Iterative training is performed on each of the associated customer attribute features, hotel attribute features, behavior statistics attribute features, and user reservation attribute features to obtain the hotel product recommendation scoring model.

3. The hotel product recommendation method according to claim 2, characterized in that: Based on the associated user booking behavior information, user portraits and hotel information, several groups of associated customer attribute features, hotel attribute features, behavior statistical attribute features and user booking attribute features are obtained, including: For any associated user booking behavior information, user portrait, and hotel information: extract features from the user portrait and hotel information to obtain customer attribute features and hotel attribute features; Performing data processing on the user booking behavior information to obtain behavior statistical attribute characteristics and user booking attribute characteristics; The customer attribute features, the hotel attribute features, the behavior statistics attribute features and the user reservation attribute features are associated and combined.

4. The hotel product recommendation method according to claim 3, characterized in that: The user booking behavior information includes page access information, user click information and user browsing information; The data processing of the user booking behavior information to obtain the behavior statistical attribute characteristics and the user booking attribute characteristics includes: Calculate the page access information, the user click information, and the user browsing information to obtain product click rate, booking conversion rate, and comparison hotel information; Associating and combining the product click rate, booking conversion rate and comparative hotel information to generate behavioral statistical attribute features; Based on the page access information, the user click information and the user browsing information, a user subscription attribute feature is determined.

5. The hotel product recommendation method according to claim 4, characterized in that: The determining of user reservation attribute characteristics based on the page access information, the user click information and the user browsing information includes: Obtaining a page time decay value, and determining a predetermined in-degree feature based on a page access sequence in the page access information; Determining a booking depth feature based on the page access sequence, the number of page clicks in the user click information, and the browsing time in the user browsing information; The page time decay value, the booking in-degree feature, and the booking depth feature are calculated to obtain a user booking attribute feature.

6. The hotel product recommendation method according to claim 1, characterized in that: The recommending of each of the hotel products based on the ratings of each of the products includes: Sorting the ratings of the products to obtain a ranking list; Based on the score ranking list, the product information corresponding to each of the hotel products is associated and combined to generate a product recommendation list; The product recommendation list is pushed to target users.

7. The hotel product recommendation method according to claim 1, characterized in that: After recommending each of the hotel products based on the product ratings, the method further includes: Collect user purchasing behavior; Performing data analysis on the user's purchasing behavior to generate product recommendation results; Based on the product recommendation effect, a recommendation optimization plan is generated.

8. A hotel product recommendation device, characterized in that: include: An acquisition module, used to acquire a user profile of a target user and a target booking location; A scoring module, used for inputting the user portrait and the target booking location into a hotel product scoring model to obtain a product score of each hotel product output by the hotel product scoring model, wherein the hotel product scoring model is obtained by iterative training based on user booking attribute features; The recommendation module is used to recommend each of the hotel products based on the ratings of each of the products.

9. A hotel product recommendation device, characterized in that: The hotel product recommendation device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the hotel product recommendation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the hotel product recommendation method according to any one of claims 1 to 7 are implemented.

Images