Hotel user behavior prediction method and related equipment
By preprocessing and inputting the hotel user requested behavior data into the deep learning behavior analysis model, the problem of inaccurate user behavior prediction in the existing system is solved, and more accurate and real-time user behavior analysis is achieved.
Patent Information
- Application Number
- CN202411675049.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-04-22
AI Technical Summary
It is difficult for existing systems to realize real-time monitoring and analysis of hotel user behavior, resulting in inaccurate user behavior prediction results.
By obtaining the hotel's user request behavior data, standardized processing and data preprocessing, input data into the preset deep learning behavior analysis model, and obtain user behavior prediction results. Through training and optimization, this model has strong intelligence to improve prediction accuracy.
It realizes more accurate predictions of hotel user behavior and improves the real-time and accuracy of user behavior analysis.
Smart Images
Figure CN119862980A_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to the field of intelligent prediction technology, and in particular to a hotel user behavior prediction method and related equipment. [Background technology]
[0002] User behavior data from different hotel channels are scattered and difficult to collect and manage in a unified manner, resulting in incomplete data. Existing systems are difficult to monitor and analyze user behavior in real time, resulting in inaccurate prediction results of user behavior. [Summary of the invention]
[0003] In view of this, the present invention provides a method for predicting hotel user behavior and related equipment.
[0004] The specific technical solution of the first embodiment of the present invention is: a method for predicting hotel user behavior, the method comprising: obtaining first user request behavior data to be analyzed for the hotel to be analyzed; inputting the first user request behavior data to be analyzed into a preset behavior analysis model to obtain a first user behavior prediction result for the hotel to be analyzed; the user behavior prediction result is the user request behavior prediction data of the hotel to be analyzed after a first preset time.
[0005] Preferably, the user request behavior data includes access frequency, click behavior, stay time and check-in conditions.
[0006] Preferably, after obtaining the first user request behavior data to be analyzed of the hotel to be analyzed, it also includes: standardizing the data type and format of the first user request behavior data to be analyzed to obtain the second user request behavior data to be analyzed; then inputting the first user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed includes: inputting the second user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed.
[0007] Preferably, after obtaining the first user request behavior data to be analyzed of the hotel to be analyzed, it also includes: performing a first data preprocessing on the first user request behavior data to be analyzed to obtain a third user request behavior data to be analyzed; the first data preprocessing includes data cleaning, data deduplication, and error and invalid data cleaning; then inputting the first user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed includes: inputting the third user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed.
[0008] Preferably, the preset behavior analysis model is obtained by the following method: obtaining sample data; the sample data includes user request behavior data of different hotels; performing a second data preprocessing on the sample data to obtain optimized sample data; the second data preprocessing also includes data normalization and denoising; performing data segmentation on the optimized sample data to obtain a training set, a validation set and a test set; using the training set, the validation set and the test set to train a preset deep learning model to obtain the prediction accuracy of the deep learning model; determining whether the prediction accuracy is greater than a preset threshold; if the prediction accuracy is not greater than the preset threshold, optimizing the deep learning model until the accuracy of the deep learning model is greater than the preset threshold, completing the training of the deep learning model, and obtaining the preset behavior analysis model.
[0009] Preferably, the optimizing the deep learning model comprises: using cross-validation technology to perform hyper-parameter tuning on the deep learning model.
[0010] Preferably, after obtaining the first user behavior prediction result of the hotel to be analyzed, it also includes: obtaining actual user request behavior data of the hotel to be analyzed within the time period corresponding to the first user behavior prediction result; optimizing the preset behavior analysis model based on the difference between the first user behavior prediction result and the actual user request behavior data; using the optimized preset behavior analysis model to obtain the second user behavior prediction result of the hotel to be analyzed; the time corresponding to the second user behavior prediction result is after the first preset time.
[0011] The specific technical solution of the second embodiment of the present invention is: a hotel user behavior prediction system, the system comprising: a data acquisition module and a behavior prediction module; the data acquisition module is used to obtain the first user request behavior data to be analyzed for the hotel to be analyzed; the behavior prediction module is used to input the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed; the user behavior prediction result is the user request behavior prediction data of the hotel to be analyzed after the first preset time.
[0012] The specific technical solution of the third embodiment of the present invention is: a hotel user behavior prediction device, including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of the first embodiments of the present application.
[0013] The specific technical solution of the fourth embodiment of the present invention is: a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the method described in any one of the first embodiments of the present application.
[0014] Implementing the embodiments of the present invention will have the following beneficial effects:
[0015] The present invention obtains the first user request behavior data to be analyzed of the hotel to be analyzed; inputs the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed. The preset behavior analysis model has strong intelligence, and a more accurate prediction result can be obtained by using the preset behavior analysis model to predict the user request behavior data.
Brief Description of the Drawings
[0016] 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, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 A flowchart of the steps of the method for predicting hotel user behavior;
[0018] Figure 2 This is a schematic diagram of the structure of the prediction system for hotel user behavior;
[0019] Figure 3 This is a diagram of the internal structure of a computer device. [Specific implementation method]
[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0021] The terms "first", "second", etc. in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other steps or modules that are inherent to these processes, methods, products or devices.
[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0023] See also Figure 1 , is a flowchart of a method for predicting hotel user behavior in the first embodiment of the present application, the method comprising:
[0024] Step 101, obtaining the first user request behavior data to be analyzed of the hotel to be analyzed;
[0025] Step 102: input the first user request behavior data to be analyzed into a preset behavior analysis model to obtain a first user behavior prediction result of the hotel to be analyzed; the user behavior prediction result is the user request behavior prediction data of the hotel to be analyzed after a first preset time.
[0026] Specifically, through technical selection, confirm the time series database (InfluxDB) used to store channel tracking data to ensure that it has efficient writing and query capabilities for high concurrency and large-scale data analysis scenarios. Confirm the data type and format that need to be tracked, formulate a unified tracking standard, cover the data collection needs of multiple channels, and ensure the consistency and integrity of the data. A time series database is a database system specifically used to store and manage time series data. Time series data is data arranged in chronological order, describing the measurement values of a measured subject at each time point within a time range. Time series databases have significant beneficial effects in processing such data. The time series database is optimized for the characteristics of time series data and uses efficient data structures and algorithms to store and query data. This enables the time series database to quickly insert, update, and query large amounts of data, improving the storage efficiency and query efficiency of the data. The time series database in this application includes the first user request behavior data to be analyzed.
[0027] The method in this embodiment obtains the first user request behavior data to be analyzed of the hotel to be analyzed; inputs the first user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed. The preset behavior analysis model has strong intelligence, and using the preset behavior analysis model to predict the user request behavior data can obtain a more accurate prediction result.
[0028] In a specific embodiment, the user request behavior data includes access frequency, click behavior, stay time and check-in conditions.
[0029] Specifically, the hotel's user request behavior data covers various behaviors and preferences of users in hotel-related scenarios. These data are extremely valuable to hotels and can help them better understand user needs, optimize services, and improve customer satisfaction. Among them, user behavior data can also include reservation and check-in data, user feedback data, consumption preference data, social media data, user profile data, etc.
[0030] Booking and stay data includes:
[0031] 1. Booking channel: The platform or channel through which the user made the booking, such as the hotel’s official website, online travel agency (OTA) platform, third-party application, etc.
[0032] 2. Booking time: The specific time when the user books a room can reflect the user's booking habits and seasonal changes in market demand.
[0033] 3. Length of stay: The number of days the user plans to stay at the hotel, which helps the hotel understand the user's accommodation needs.
[0034] 4. Room type: The room type selected by the user, such as single room, double room, suite, etc., can reflect the user's accommodation preferences.
[0035] User feedback data includes:
[0036] 1. Online reviews: User reviews of hotels on OTA platforms, social media or other channels, including text, ratings and pictures.
[0037] 2. Complaints and Suggestions: Complaints or suggestions made directly by users to the hotel are usually submitted through the customer service hotline, email or online form.
[0038] 3. Satisfaction survey: The user satisfaction data collected by the hotel through questionnaire surveys and other means can reflect the user's evaluation of the hotel's overall services.
[0039] Consumption preference data includes:
[0040] 1. Consumption habits: Users’ consumption habits in the hotel, such as dining consumption, entertainment consumption, etc., can reflect the users’ consumption level and preferences.
[0041] 2. Demand for value-added services: The degree to which users demand the value-added services provided by the hotel, such as SPA, gym, laundry services, etc.
[0042] Social media data includes:
[0043] 1. Social media interaction: user interaction with the hotel on social media, such as likes, comments, and reposts.
[0044] 2. User-generated content (UGC): hotel-related content posted by users on social media, such as photos, videos, travel notes, etc.
[0045] User profile data includes:
[0046] 1. Personal information: user’s name, age, gender, occupation and other basic information.
[0047] 2. Historical check-in records: The user’s previous check-in records at the hotel, including check-in time, room type, consumption amount, etc.
[0048] By analyzing these data, hotels can better understand user needs, optimize service processes, and improve customer satisfaction and loyalty. At the same time, these data can also provide strong support for the hotel's marketing strategy formulation and help the hotel achieve precision marketing and personalized services.
[0049] In a specific embodiment, after obtaining the first user request behavior data to be analyzed of the hotel to be analyzed, it also includes: standardizing the data type and format of the first user request behavior data to be analyzed to obtain the second user request behavior data to be analyzed; then inputting the first user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed includes: inputting the second user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed.
[0050] Specifically, the standardization of data types requires clarifying all data types involved in the data, such as numeric, character, date, etc. This helps to perform targeted conversion and normalization of data types later. Standardization of formats can be applied to a variety of data types and scenarios, such as text, numbers, dates, etc., such as selecting integer, decimal, percentage or currency formats as needed. For example, in a table, you can use the "Number Format" option to set decimal places, thousands separators, etc.
[0051] In a specific embodiment, after obtaining the first user request behavior data to be analyzed of the hotel to be analyzed, it also includes: performing a first data preprocessing on the first user request behavior data to be analyzed to obtain the third user request behavior data to be analyzed; the first data preprocessing includes data cleaning, data deduplication, and error and invalid data cleaning; then the first user request behavior data to be analyzed is input into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed, including: inputting the third user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed. Specifically, the collected user request behavior data to be analyzed is cleaned to remove duplicate, error and invalid data, improve data quality, and lay the foundation for subsequent accurate analysis.
[0052] Specifically, the preset behavior analysis model is obtained by the following method: obtaining sample data; the sample data includes user request behavior data of different hotels; performing a second data preprocessing on the sample data to obtain optimized sample data; the second data preprocessing also includes data normalization and denoising; performing data segmentation on the optimized sample data to obtain a training set, a validation set and a test set; using the training set, the validation set and the test set to train a preset deep learning model to obtain the prediction accuracy of the deep learning model; judging whether the prediction accuracy is greater than a preset threshold; if the prediction accuracy is not greater than the preset threshold, optimizing the deep learning model until the accuracy of the deep learning model is greater than the preset threshold, completing the training of the deep learning model, and obtaining the preset behavior analysis model.
[0053] Specifically, select a dataset related to the task (the first user request to be analyzed) and ensure its quality, completeness and representativeness. The dataset should contain enough samples to cover various possible scenarios and situations. Clean the data to remove duplicate, missing or invalid data. Perform data enhancement, such as random cropping, flipping, rotation, etc., to increase data diversity. Normalize or standardize the data to ensure that different features are on the same scale. Divide the dataset into training set, validation set and test set, such as dividing the data into training set (70%), validation set (20%) and test set (10%) to ensure that the data is evenly distributed and prevent overfitting. The training set is used for model training, the validation set is used to adjust model parameters and select the best model, and the test set is used to evaluate model performance. Select a suitable model architecture according to the task type and dataset characteristics, such as the deep learning LSTM model for embedded point time series data analysis. Determine the model's hyperparameters, such as learning rate, batch size, number of iterations, etc., based on experience or experiments. Select a suitable loss function according to the task type, such as cross entropy loss for classification tasks, mean square error loss for regression tasks, etc. Choose a suitable optimizer, such as Adam, SGD, etc., to speed up model training and reduce overfitting. Use the training set to train the model and update the model parameters through the back-propagation algorithm. During the training process, use the validation set regularly to evaluate the model performance and adjust the hyperparameters or model architecture as needed. Use the test set to evaluate the performance of the model, such as accuracy, recall, F1 score and other indicators. Visually analyze the output of the model to understand the decision-making process and error types of the model. Optimize the model based on the evaluation results, such as adjusting hyperparameters, modifying the model architecture, adding data enhancement, etc. Use ensemble learning methods (such as Bagging, Boosting, etc.) to further improve model performance. After the training is completed, save the model parameters and architecture to a file for subsequent use. When needed, load the model parameters and architecture from the file to make predictions or continue training.
[0054] In a specific embodiment, the optimization of the deep learning model includes: using cross-validation technology to tune the hyperparameters of the deep learning model. Specifically, the basic idea of cross-validation is to divide the original data set into two parts: one part is used as a training set for training the model; the other part is used as a test set for evaluating the performance of the model. However, simple division may lead to instability in the evaluation results because the division of the training set and the test set may not be optimal. To solve this problem, cross-validation provides a more stable and reliable model evaluation by dividing the data set multiple times and repeating the training and testing process.
[0055] Hyperparameters are parameters that need to be set before model training, rather than parameters that are automatically learned from training data. The goal of hyperparameter tuning is to find an optimal set of hyperparameters so that the model performs best on new data. Cross-validation is a technique for evaluating model performance. It verifies the generalization ability of a model by dividing a dataset into multiple subsets. Common cross-validation methods include K-fold cross-validation and leave-one-out cross-validation. Specific validation methods include K-fold cross-validation and leave-one-out cross-validation. K-fold cross-validation randomly divides the original dataset into K subsets, leaving out one subset each time as a validation set, and the remaining K-1 subsets are used to train the model. This is repeated K times, with a different subset used as a validation set each time, and the average of the K results is used as the final evaluation indicator. K-fold cross-validation can make more effective use of data, reduce the variance of the evaluation results, and make the evaluation more reliable. Leave-one-out cross-validation leaves out only one sample each time as a validation set, which is suitable for small datasets.
[0056] There are many methods for hyperparameter tuning, the most common ones are grid search and random search.
[0057] Grid search: Within a predefined parameter range, all possible parameter combinations are exhausted, and then the performance of each combination is evaluated through cross-validation to select the best combination. Grid search can ensure that the best hyperparameter settings are not missed, but the computational cost is high, especially when the parameter space is large, the training time will increase significantly.
[0058] Random search: Randomly sample a certain number of combinations in the parameter space for evaluation. Random search can more efficiently explore the possible best parameter combinations and has high computational efficiency, but it may miss the optimal parameter combination, but usually finds a good enough parameter combination.
[0059] When using grid search or random search for hyperparameter tuning, you need to combine cross-validation to evaluate the performance of each parameter combination. The specific steps are as follows: For each parameter combination in grid search or random search, use K-fold cross-validation to evaluate its performance. Calculate the average performance index of K-fold cross-validation as the final performance of the parameter combination. Select the best performing parameter combination as the final hyperparameter setting. After finding the best hyperparameter setting, you need to use the entire training set (including the part of the validation set previously used for cross-validation) to retrain the model. Then, use the test set to evaluate the performance of the final model to ensure that the model has good generalization ability.
[0060] In a specific embodiment, after obtaining the first user behavior prediction result of the hotel to be analyzed, it also includes: obtaining the actual user request behavior data of the hotel to be analyzed within the time period corresponding to the first user behavior prediction result; optimizing the preset behavior analysis model based on the difference between the first user behavior prediction result and the actual user request behavior data; using the optimized preset behavior analysis model to obtain the second user behavior prediction result of the hotel to be analyzed; the time corresponding to the second user behavior prediction result is after the first preset time. Specifically, by comparing the system effects before and after the deployment of the preset behavior analysis model, use indicators such as anomaly detection rate, trend prediction accuracy, etc. for evaluation.
[0061] In the specific embodiments, see Figure 2 , is a structural diagram of a hotel user behavior prediction system in the second embodiment of the present application, the system includes: a data acquisition module 201 and a behavior prediction module 202; the data acquisition module 201 is used to obtain the first user request behavior data to be analyzed for the hotel to be analyzed; the behavior prediction module 202 is used to input the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed; the user behavior prediction result is the user request behavior prediction data of the hotel to be analyzed after the first preset time. The system in this embodiment obtains the first user request behavior data to be analyzed for the hotel to be analyzed; inputs the first user request behavior data to be analyzed into the preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed. The preset behavior analysis model has strong intelligence, and using the preset behavior analysis model to predict the user request behavior data can obtain more accurate prediction results.
[0062] Specifically, the preset behavior analysis model is integrated into the real-time monitoring system to ensure that it can analyze the buried data of user request behavior in real time. The model is used to predict changes in user behavior in real time, detect abnormal behavior and trends, and generate alarms and reports. New data is collected regularly, and the model is retrained and optimized to cope with changing user behavior. Using actual monitoring results and user feedback, the model is continuously iterated and improved to enhance the intelligence level of the system. The system can intelligently analyze the buried data of user request behavior in the hotel channel, detect abnormal behavior in real time, predict trends and generate reports, thereby improving the hotel's operational efficiency and user satisfaction. In addition, through continuous model updates and optimizations, the system can flexibly adapt to changes in user behavior to ensure that efficient monitoring and analysis capabilities are always maintained.
[0063] In a specific embodiment, the third embodiment of the present application provides a hotel user behavior prediction device, including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of the first embodiments of the present application. The device in this embodiment obtains the first user request behavior data to be analyzed of the hotel to be analyzed; inputs the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed. The preset behavior analysis model has strong intelligence, and using the preset behavior analysis model to predict the user request behavior data can obtain a more accurate prediction result.
[0064] In a specific embodiment, the fourth embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the method described in any one of the first embodiments of the present application. The storage medium in this embodiment obtains the first user request behavior data to be analyzed of the hotel to be analyzed; inputs the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed. The preset behavior analysis model has strong intelligence. Using the preset behavior analysis model to predict the user request behavior data can obtain a more accurate prediction result.
[0065] like Figure 3 As shown, an embodiment of the present application provides a computer device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.
[0066] Memory 113, used for storing computer programs;
[0067] In one embodiment of the present application, the processor 111 is used to implement the hotel user behavior prediction method provided by any of the aforementioned method embodiments when executing the program stored in the memory 113.
[0068] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
[0069] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A method for predicting hotel user behavior, characterized in that: The method comprises: Obtain the first user request behavior data to be analyzed of the hotel to be analyzed; The first user request behavior data to be analyzed is input into a preset behavior analysis model to obtain a first user behavior prediction result of the hotel to be analyzed; the user behavior prediction result is the user request behavior prediction data of the hotel to be analyzed after a first preset time.
2. The method for predicting hotel user behavior as claimed in claim 1, characterized in that: The user request behavior data includes visit frequency, click behavior, stay time and check-in conditions.
3. The method for predicting hotel user behavior as claimed in claim 1, characterized in that: After obtaining the first user request behavior data to be analyzed of the hotel to be analyzed, the method further includes: Standardizing the data type and format of the first to-be-analyzed user request behavior data to obtain second to-be-analyzed user request behavior data; Then, inputting the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed includes: The second user request behavior data to be analyzed is input into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed.
4. The method for predicting hotel user behavior as claimed in claim 1, characterized in that: After obtaining the first user request behavior data to be analyzed of the hotel to be analyzed, the method further includes: Performing a first data preprocessing on the first to-be-analyzed user request behavior data to obtain a third to-be-analyzed user request behavior data; the first data preprocessing includes data cleaning, data deduplication, and error and invalid data cleaning; Then, inputting the first user request behavior data to be analyzed into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed includes: The third user request behavior data to be analyzed is input into a preset behavior analysis model to obtain the first user behavior prediction result of the hotel to be analyzed.
5. The method for predicting hotel user behavior as claimed in claim 1, characterized in that: The preset behavior analysis model is obtained by the following method: Obtaining sample data; the sample data includes user request behavior data of different hotels; Performing a second data preprocessing on the sample data to obtain optimized sample data; the second data preprocessing also includes data normalization and denoising; Segmenting the optimized sample data to obtain a training set, a validation set, and a test set; Using the training set, the validation set, and the test set to train a preset deep learning model to obtain a prediction accuracy of the deep learning model; Determining whether the prediction accuracy is greater than a preset threshold; If the prediction accuracy is not greater than the preset threshold, the deep learning model is optimized until the accuracy of the deep learning model is greater than the preset threshold, the training of the deep learning model is completed, and the preset behavior analysis model is obtained.
6. The method for predicting hotel user behavior as claimed in claim 5, characterized in that: The optimizing the deep learning model comprises: Use cross-validation techniques to tune hyperparameters of deep learning models.
7. The method for predicting hotel user behavior as claimed in claim 1, characterized in that: After obtaining the first user behavior prediction result of the hotel to be analyzed, the method further includes: Obtaining actual user request behavior data of the hotel to be analyzed within the time period corresponding to the first user behavior prediction result; Optimizing the preset behavior analysis model based on the difference between the first user behavior prediction result and the actual user request behavior data; The optimized preset behavior analysis model is used to obtain a second user behavior prediction result of the hotel to be analyzed; the time corresponding to the second user behavior prediction result is after the first preset time.
8. A hotel user behavior prediction system, characterized in that: The system comprises: a data acquisition module and a behavior prediction module; The data acquisition module is used to acquire first to-be-analyzed user request behavior data of the to-be-analyzed hotel; The behavior prediction module is used to input the first user request behavior data to be analyzed into a preset behavior analysis model to obtain a first user behavior prediction result of the hotel to be analyzed; the user behavior prediction result is the user request behavior prediction data of the hotel to be analyzed after a first preset time.
9. A hotel user behavior prediction device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.