Scenic spot passenger flow volume prediction method, system and device and storage medium

Abstract

The invention discloses a scenic spot passenger flow volume prediction method, system and device and a storage medium. The method comprises the following steps: acquiring initial data related to passenger flow from a plurality of channels; cleaning and integrating the initial data to obtain feature data, and inputting the feature data into a passenger flow prediction model to obtain a prediction result; according to a preset correction parameter, correcting the prediction result to obtain a target result of scenic spot passenger flow prediction; the preset correction parameter is related to historical prediction accuracy and expert experience. The embodiment of the invention is beneficial to improving the prediction accuracy of the model. The method can be widely applied to the technical field of computers.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, system, device and storage medium for predicting visitor flow at a tourist attraction. Background Art

[0002] With the booming tourism industry and the growing demand of tourists, tourism planning has become an important part of improving management level and tourist experience. In tourism planning, the prediction of tourist flow at scenic spots is one of the core tasks. Accurate passenger flow prediction not only helps scenic area managers to formulate reasonable operation strategies, such as resource allocation, facility layout, safety assurance, etc., but also helps tourists better plan their itineraries and improve their travel experience.

[0003] In related technologies, machine learning or data mining techniques are usually used to process and analyze historical tourist data to predict future passenger flow. These systems have improved the accuracy and efficiency of predictions to a certain extent, but there are still some problems. Specifically, the prediction model is not flexible enough and cannot be dynamically adjusted and optimized according to actual conditions, resulting in low prediction accuracy of the prediction model. Summary of the invention

[0004] The purpose of this application is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, the purpose of this application is to provide a highly accurate tourist flow prediction method, system, device and storage medium.

[0006] In order to achieve the above technical objectives, one aspect of an embodiment of the present application provides a method for predicting the passenger flow of a tourist attraction, comprising the following steps: obtaining initial data related to the passenger flow from several channels; cleaning and integrating the initial data to obtain feature data, and inputting the feature data into a passenger flow prediction model to obtain a prediction result; correcting the prediction result according to preset correction parameters to obtain a target result for predicting the passenger flow of the tourist attraction; the preset correction parameters are related to historical prediction accuracy and expert experience. The embodiment of the present application obtains initial data related to the passenger flow through multiple channels and pre-processes the data, which improves the prediction accuracy of the model to a certain extent. At the same time, the embodiment of the present application corrects the prediction results of the model by pre-setting correction parameters, which can flexibly adjust the prediction results of the model and further improve the prediction accuracy of the model.

[0007] In some embodiments, in one embodiment of the present application, the cleaning and integration of the initial data to obtain the characteristic data includes:

[0008] Determine a first weight of the data from each of the channels, perform weighted processing on the initial data according to the first weight, and integrate the weighted data to obtain feature data;

[0009] Alternatively, the initial data is cleaned to remove abnormal values, and the cleaned data is integrated to obtain characteristic data related to passenger flow;

[0010] Alternatively, the initial data is subjected to uniform standardization processing, and the data after the uniform standardization processing is integrated to obtain feature data.

[0011] In some embodiments, in one embodiment of the present application, the passenger flow prediction model is an LSTM model, and the LSTM model is trained by the following steps:

[0012] Get initial sample data;

[0013] The initial sample data is cleaned and integrated to obtain feature sample data, and the feature sample data is input into the LSTM model to obtain a sample prediction result;

[0014] A loss function is established according to the sample prediction result and the sample actual result, and the parameters of the LSTM model are updated according to the loss function to obtain the updated LSTM model;

[0015] The updated LSTM model is dynamically adjusted through other sample data.

[0016] In some embodiments, in one embodiment of the present application, the preset correction parameter includes a first correction parameter, and the first correction parameter is determined by the following steps:

[0017] Obtaining historical collected data, estimated data and actual data; the estimated data is the prediction result of the historical collected data by the passenger flow prediction model, and the actual data is the actual passenger flow data corresponding to the historical collected data;

[0018] A first correction parameter is determined according to the estimated data and the actual data.

[0019] In some embodiments, in one embodiment of the present application, the preset correction parameter includes a second correction parameter, and the second correction parameter is determined by the following steps:

[0020] Obtain a first change in the current acquisition channel, and determine the second correction parameter through expert evaluation based on the impact of the first change on passenger flow; the first change is a behavioral change made by the current acquisition channel that is related to the current predicted sales volume of the scenic spot.

[0021] In some embodiments, in one embodiment of the present application, the method further comprises:

[0022] Obtaining side data related to customer traffic from several channels; wherein the side data includes comment data and visit data;

[0023] Inputting the side data into an influence model to obtain a first coefficient that affects the prediction result; the influence model is used to characterize the correlation between the side data and the prediction result;

[0024] The first coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

[0025] In some embodiments, in one embodiment of the present application, the method further comprises:

[0026] Get the current traffic changes of each channel;

[0027] Determine a second coefficient of the flow change affecting the prediction result;

[0028] The second coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

[0029] On the other hand, the embodiment of the present application proposes a tourist flow prediction system for a scenic spot, including:

[0030] The first module is used to obtain initial data related to customer traffic from several channels;

[0031] The second module is used to clean and integrate the initial data to obtain feature data, and input the feature data into the passenger flow prediction model to obtain the prediction result;

[0032] The third module is used to correct the prediction result according to the preset correction parameters to obtain the target result of the tourist flow prediction of the scenic spot; the preset correction parameters are related to the historical prediction accuracy and expert experience.

[0033] On the other hand, an embodiment of the present application provides a device for predicting tourist flow at a scenic spot, comprising:

[0034] at least one processor;

[0035] at least one memory for storing at least one program;

[0036] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for predicting the tourist flow of attractions.

[0037] On the other hand, an embodiment of the present application provides a storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for predicting the visitor flow of a tourist attraction.

[0038] The embodiments of the present application include at least the following beneficial effects: The method provided by the embodiments of the present application includes: obtaining initial data related to passenger flow from several channels; cleaning and integrating the initial data to obtain characteristic data, and inputting the characteristic data into a passenger flow prediction model to obtain a prediction result; correcting the prediction result according to preset correction parameters to obtain a target result for the passenger flow prediction of the scenic spot; the preset correction parameters are related to the historical prediction accuracy and expert experience. The embodiments of the present application obtain initial data related to passenger flow through multiple channels and pre-process the data, which improves the prediction accuracy of the model to a certain extent. At the same time, the embodiments of the present application correct the prediction results of the model by pre-setting correction parameters, which can flexibly adjust the prediction results of the model and further improve the prediction accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present application. For technical personnel in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A flow chart of an embodiment of a method for predicting tourist flow at a scenic spot provided by the present application;

[0041] Figure 2 A flow chart of another embodiment of a method for predicting tourist flow at a scenic spot provided by the present application;

[0042] Figure 3 A schematic diagram of the structure of an embodiment of a tourist attraction passenger flow prediction system provided by the present application;

[0043] Figure 4 A schematic diagram of the structure of an embodiment of a device for predicting tourist flow at a tourist attraction provided in the present application. DETAILED DESCRIPTION

[0044] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limitations on the present application. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0045] With the booming tourism industry and the growing demand of tourists, tourism planning has become a crucial link. In tourism planning, the prediction of tourist flow at scenic spots is one of the core tasks. Accurate passenger flow prediction not only helps scenic area managers to formulate reasonable operation strategies, such as resource allocation, facility layout, safety assurance, etc., but also helps tourists better plan their itineraries and improve their travel experience.

[0046] However, there are still some deficiencies in the current methods and technologies for predicting the flow of tourists to scenic spots. Although traditional prediction methods, such as the "four-stage" model, can reflect the characteristics of regular travel flow to a certain extent, they are based on fixed travel patterns and cannot fully consider the particularity of tourist travel, such as tourism seasonality, holiday impact, distribution of scenic spots in scenic spots, and tourist behavior. As a result, the prediction results often deviate greatly from the actual passenger flow.

[0047] In addition, existing passenger flow forecasting systems often lack flexibility and scalability and cannot adapt to the rapid changes in the tourism market. For example, when new attractions are added or tour routes are adjusted in a scenic area, the system often needs to re-collect and process a lot of data, which not only increases the workload and cost, but also may lead to inaccurate forecast results.

[0048] At present, some tourist attraction visitor number prediction systems have been developed. They usually use machine learning or data mining techniques to process and analyze historical visitor data to predict future passenger flow. These systems have improved the accuracy and efficiency of prediction to a certain extent, but there are still the following problems:

[0049] 1. Data processing is not sophisticated enough: Existing systems often only consider the total number of tourists or simple time series data, while ignoring the impact of factors such as tourists' behavioral characteristics, tour routes, and scenic spot distribution on passenger flow.

[0050] 2. The prediction model is not flexible enough: Existing systems usually use fixed prediction models and cannot be dynamically adjusted and optimized according to the actual situation of the scenic area.

[0051] 3. Insufficient system scalability: When changes occur in the scenic area, the existing system often needs to re-collect and process a large amount of data, which lacks flexibility and scalability.

[0052] In response to the above problems, this application proposes a tourist flow prediction solution for tourism planning assistance. The core of this application is to establish a more accurate, flexible and scalable passenger flow prediction model by comprehensively considering factors such as tourists' behavioral characteristics, tour routes, and scenic spot distribution, combined with machine learning technology. Specifically, this application needs to solve the following technical problems:

[0053] 1. Refined data processing: Through in-depth analysis and processing of tourist behavior data, tour route data, scenic spot distribution data, etc., the key factors affecting passenger flow are extracted and used as input features of the prediction model.

[0054] 2. Flexibility of prediction model: Using advanced machine learning algorithms, such as deep learning and ensemble learning, we can establish a prediction model that can adapt to the actual situation of the scenic spot. The model can dynamically adjust and optimize the prediction results based on the historical data and real-time data of the scenic spot.

[0055] 3. System scalability: Design a modular system architecture so that when changes occur in the scenic area, only the corresponding modules need to be updated and adjusted without redeveloping the entire system. At the same time, the system should also support the access and processing of multiple data sources to meet the actual needs of different scenic spots.

[0056] The following describes in detail the method and system for predicting the tourist flow of a tourist attraction proposed according to an embodiment of the present application with reference to the accompanying drawings. First, the method for predicting the tourist flow of a tourist attraction proposed according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0057] Reference Figure 1 In an embodiment of the present application, a method for predicting the flow of tourists to a tourist attraction is provided. The method for predicting the flow of tourists to a tourist attraction in the embodiment of the present application can be applied to a terminal, or to a server, or can be software running in a terminal or a server, etc. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The method for predicting the flow of tourists to a tourist attraction in the embodiment of the present application mainly includes the following steps:

[0058] S100: Acquire initial data related to passenger flow from a number of channels;

[0059] S200: Cleaning and integrating the initial data to obtain feature data, and inputting the feature data into a passenger flow prediction model to obtain a prediction result;

[0060] S300: Correcting the prediction result according to preset correction parameters to obtain a target result of the tourist flow prediction of the scenic spot; the preset correction parameters are related to the historical prediction accuracy and expert experience.

[0061] In some possible implementations, the channel in the embodiment of the present application can be website data or relevant data of offline attractions. Correspondingly, the initial data can be website sales data, offline sales data, historical visitor data of the corresponding attractions, etc. The present application does not limit the specific data source channels and data types. The embodiment of the present application corrects / adjusts the prediction results of the model by correcting the data so that the model can adapt to external changes related to passenger flow. For example, if there are some uncontrollable factors around the corresponding scenic spot that affect the traffic to the scenic spot; or abnormal weather / extreme weather, etc., will affect the accuracy of the prediction results. The present application sets correction parameters to alleviate the above problems and improve the prediction accuracy of the model.

[0062] Optionally, in an embodiment of the present application, the cleaning and integration of the initial data to obtain the characteristic data includes:

[0063] Determine a first weight of the data from each of the channels, perform weighted processing on the initial data according to the first weight, and integrate the weighted data to obtain feature data;

[0064] Alternatively, the initial data is cleaned to remove abnormal values, and the cleaned data is integrated to obtain characteristic data related to passenger flow;

[0065] Alternatively, the initial data is subjected to uniform standardization processing, and the data after the uniform standardization processing is integrated to obtain feature data.

[0066] In some possible implementations, data from different channels may be incomplete or inaccurate. The embodiment of the present application sets weights for each channel to obtain complete data and improve the prediction accuracy of the model. Of course, the first weight can be set according to actual conditions. During implementation, the first weight can also be adjusted as the data changes or external conditions change. The present application does not limit the setting method and specific value of the first weight.

[0067] Optionally, in one embodiment of the present application, the passenger flow prediction model is an LSTM model, and the LSTM model is trained by the following steps:

[0068] Get initial sample data;

[0069] The initial sample data is cleaned and integrated to obtain feature sample data, and the feature sample data is input into the LSTM model to obtain a sample prediction result;

[0070] A loss function is established according to the sample prediction result and the sample actual result, and the parameters of the LSTM model are updated according to the loss function to obtain the updated LSTM model;

[0071] The updated LSTM model is dynamically adjusted through other sample data.

[0072] In some possible implementations, the LSTM model is trained using existing sample data and the actual results of each sample contained in the sample data to obtain a trained LSTM model. Of course, it is understandable that the passenger flow prediction model in this application can also be other artificial intelligence models, and this application does not specifically limit this.

[0073] Optionally, in one embodiment of the present application, the preset correction parameter includes a first correction parameter, and the first correction parameter is determined by the following steps:

[0074] Obtaining historical collected data, estimated data and actual data; the estimated data is the prediction result of the historical collected data by the passenger flow prediction model, and the actual data is the actual passenger flow data corresponding to the historical collected data;

[0075] A first correction parameter is determined according to the estimated data and the actual data.

[0076] In some possible implementations, after the passenger flow prediction model is determined, as the model is used, if other factors related to passenger flow appear, the accuracy of the prediction results will be affected. The present application uses the historical collected data in the process, and the corresponding estimated data and actual data to correct the prediction results of the model, so that the prediction results are infinitely close to the real results. The relationship between the difference between the estimated data and the actual data and the first correction parameter can be represented by a functional relationship, or by a chart, a curve, etc., and can also be associated through an artificial intelligence model. The present application does not limit the specific determination method of the first correction coefficient.

[0077] Optionally, in one embodiment of the present application, the preset correction parameter includes a second correction parameter, and the second correction parameter is determined by the following steps:

[0078] Obtain a first change in the current acquisition channel, and determine the second correction parameter through expert evaluation based on the impact of the first change on passenger flow; the first change is a behavioral change made by the current acquisition channel that is related to the current predicted sales volume of the scenic spot.

[0079] In some possible implementations, the collection channel will update the recommendation strength of each scenic spot from time to time, thereby affecting the sales data of the scenic spot and affecting the passenger flow of the scenic spot. The present application determines the second correction parameter through expert judgment for the first change of the collection channel to improve the prediction accuracy.

[0080] Optionally, in one embodiment of the present application, the method further includes:

[0081] Obtaining side data related to customer traffic from several channels; wherein the side data includes comment data and visit data;

[0082] Inputting the side data into an influence model to obtain a first coefficient that affects the prediction result; the influence model is used to characterize the correlation between the side data and the prediction result;

[0083] The first coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

[0084] In some possible implementations, the side data may be website visit data, comment data, recommendation data, etc. Of course, the side data may also be other side data that affects customer flow. The embodiment of the present application may determine the first coefficient related to the side data and affecting the prediction result through an existing model; or may determine the first coefficient by setting a calculation formula for the side data and the first coefficient based on experience.

[0085] Optionally, in one embodiment of the present application, the method further includes:

[0086] Get the current traffic changes of each channel;

[0087] Determine a second coefficient of the flow change affecting the prediction result;

[0088] The second coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

[0089] In some possible implementations, the prediction process involved in the embodiments of the present application can be regarded as the following modules:

[0090] The data collection and processing module collects and processes various data related to the prediction of tourist flow at scenic spots. These data include but are not limited to historical passenger flow data, tourist behavior data (such as visit time, stay time, tour route, etc.), scenic spot distribution data, weather data, holiday data, etc. By cleaning, integrating and extracting features from these data, a data set for training the prediction model is obtained.

[0091] The prediction model building module builds a prediction model that can adapt to the actual situation of the scenic spot based on machine learning technology. The model uses deep learning algorithms (such as recurrent neural networks RNN, long short-term memory networks LSTM, etc.) or integrated learning algorithms (such as random forests, gradient boosting trees, etc.) to process time series data and extracted features as input and output future passenger flow forecasts. During the model training process, cross-validation and other technical means are used to ensure the generalization ability and prediction accuracy of the model.

[0092] The prediction result optimization module further optimizes the output of the prediction model. By introducing real-time data (such as real-time weather, real-time traffic conditions, etc.) and expert experience, the prediction results are dynamically adjusted. At the same time, this module also has a model self-update function, which can regularly update and optimize the prediction model based on new historical data and real-time data to maintain the prediction accuracy and timeliness of the model.

[0093] The user interface module provides users with a friendly interactive interface, which is convenient for users to view prediction results, set prediction parameters, manage data, etc. The interface design is concise and easy to operate. Users can use this interface to select parameters such as the scenic spots to be predicted, time period, and prediction accuracy, and view the prediction results and charts in real time.

[0094] The system extension module supports flexible expansion and customization of the system. When changes occur in the scenic area (such as adding new attractions, adjusting tour routes, etc.), users can incorporate new data and information into the prediction model through simple configuration and update without redeveloping the entire system. At the same time, this module also supports the access and processing of multiple data sources to meet the actual needs of different scenic areas.

[0095] Reference Figure 2 As shown, the method for predicting the tourist flow of scenic spots provided by the present application is described in detail with a specific embodiment as follows, specifically:

[0096] Regarding the implementation environment, this embodiment assumes that the application is implemented in a large tourist attraction, which includes multiple attractions, and the number of tourists is affected by various factors such as seasons, holidays, and weather. In order to accurately predict the passenger flow of each attraction, the scenic area management department decides to adopt the attraction passenger flow prediction solution described in this application.

[0097] S21. Data collection and processing.

[0098] 1. Data sources include but are not limited to the following:

[0099] Historical tourist flow data of scenic spots: including daily, weekly, monthly and annual tourist flow data.

[0100] Tourist behavior data: collected through surveillance cameras and tourist positioning systems in scenic areas, including tourists’ visit time, length of stay, tour routes, etc.

[0101] Scenic spot distribution data: including the location, type, characteristics and other information of each scenic spot in the scenic area.

[0102] External data: such as weather data, holiday schedules, etc.

[0103] 2. Data preprocessing:

[0104] Clean the historical passenger flow data to remove outliers and missing values.

[0105] Integrate tourist behavior data and extract features related to passenger flow prediction, such as average length of stay of tourists, tour route preferences, etc.

[0106] Standardize the scenic spot distribution data, weather data, holiday data, etc. so that they can be combined with the passenger flow data.

[0107] 3. Feature extraction:

[0108] Based on the tourist behavior data and scenic spot distribution data, feature vectors related to passenger flow are extracted, such as peak tourist flow periods, popular attractions, weather conditions, etc.

[0109] S22. Prediction model construction.

[0110] 1. Model selection:

[0111] Long short-term memory network is selected as the prediction model because it can effectively process time series data and capture long-term dependencies in the data.

[0112] 2. Model training:

[0113] The preprocessed dataset is divided into training set and test set.

[0114] The LSTM model is trained using the training set and the model parameters are adjusted to optimize the prediction performance.

[0115] Use the test set to validate the trained model and evaluate the prediction accuracy and generalization ability of the model.

[0116] 3. Model optimization:

[0117] Fine-tune the model based on the verification results, such as adjusting the network structure, optimizing the algorithm, etc.

[0118] Introduce real-time data to dynamically adjust the model to improve prediction accuracy.

[0119] S23. Optimizing prediction results.

[0120] 1. Real-time data fusion:

[0121] Integrate real-time data such as weather data and traffic conditions into the prediction model to dynamically adjust the prediction results.

[0122] 2. Expert experience correction:

[0123] Combined with the expert experience of the scenic area management department, the prediction results are manually corrected to improve the accuracy and reliability of the prediction results. Specifically, regarding real-time data fusion and expert experience correction:

[0124] (1) Quantitatively compare historically collected data, estimated data, and actual data, analyze the differences between estimated data and actual data, calculate data analysis errors, and use the average error as a correction parameter for the prediction results.

[0125] (2) Due to the changes in the data collection channels each year, experts evaluate the influence coefficient of the channel on the predicted results by analyzing the relationship between the channel data and the predicted results, and use the system as a correction parameter for the predicted results.

[0126] S24, user interaction interface.

[0127] 1. Interface design:

[0128] The user interaction interface is designed to be concise and clear, including parameter setting area, prediction result display area and chart display area.

[0129] 2. Function realization:

[0130] Users can select parameters such as the scenic spots to be predicted, time period and prediction accuracy through the parameter setting area.

[0131] The forecast result display area displays the forecast results in real time, including the passenger flow forecast value and trend chart for each time period.

[0132] The chart display area provides a variety of chart formats (such as bar charts, line charts, etc.) to help users intuitively understand changes in passenger flow.

[0133] S25. System expansion.

[0134] 1. Data source expansion:

[0135] When new attractions are added to the scenic area or the tour route is adjusted, it is only necessary to incorporate the new data source into the system and update the corresponding data processing and feature extraction processes.

[0136] For example, the original data source only has ticket sales data, and later on, comment data, OTA visit data, etc. can be included in the data source. The data of each data source can be analyzed through modeling to obtain the coefficient that affects the prediction result as the prediction parameter.

[0137] 2. Model update:

[0138] Regularly collect new historical data and real-time data, and update and optimize the prediction model to maintain the model's prediction accuracy and timeliness.

[0139] Since the traffic in different channels changes every year, the model's prediction results must also be adjusted accordingly. Therefore, it is necessary to continuously adjust the model's predicted result coefficient based on the changes in channel traffic corresponding to each model.

[0140] Through the above embodiments, the scenic spot passenger flow prediction method program design described in this application is first applied in tourist attractions, providing accurate passenger flow prediction results for scenic area management departments, which is helpful to formulate reasonable operation strategies and enhance tourist experience.

[0141] The embodiments of the present application are conducive to improving the prediction accuracy: the present application can more accurately predict the tourist flow of scenic spots by comprehensively considering multiple factors such as tourist behavior data, scenic spot distribution data, weather data, etc. Compared with traditional methods, the present application can better capture the complex factors that affect the passenger flow, thereby providing more accurate prediction results.

[0142] The embodiments of the present application are conducive to enhancing the flexibility of the model: the present application adopts advanced machine learning algorithms (such as LSTM), which have adaptive capabilities and can be dynamically adjusted and optimized according to the actual conditions of different scenic spots. When changes occur in the scenic area (such as adding new attractions and adjusting tour routes), the model can quickly adapt and give accurate prediction results.

[0143] The embodiments of the present application are conducive to improving the scalability of the system: the present application designs a modular system architecture, which enables the system to have good scalability. When a new data source or function needs to be added, only the corresponding module needs to be updated and adjusted without redeveloping the entire system. This greatly reduces the maintenance cost and development cycle of the system.

[0144] The embodiment of the present application can support real-time data fusion: The present application supports the fusion and processing of real-time data, such as real-time weather, real-time traffic conditions, etc. By incorporating these real-time data into the prediction model, the system can dynamically adjust and optimize the prediction results to further improve the accuracy of the prediction.

[0145] The embodiment of the present application provides a friendly user interaction interface: The present application provides a concise and clear user interaction interface, which is convenient for users to view prediction results, set prediction parameters, etc. The interface design is intuitive and easy to understand, easy to operate, and improves the user experience.

[0146] The embodiment of this application proposes an innovative data processing and feature extraction method: This application uses advanced data processing and feature extraction technology to extract key features related to passenger flow prediction from massive amounts of data. These features not only help improve prediction accuracy, but also provide deeper insights and decision support for scenic area management departments.

[0147] The embodiments of the present application are conducive to improving the operation efficiency of scenic spots and the tourist experience: through accurate passenger flow prediction, scenic spot management departments can formulate more reasonable operation strategies, such as resource allocation, facility layout, safety assurance, etc. This helps to improve the operation efficiency and service quality of scenic spots and provide tourists with a better travel experience.

[0148] In summary, the solution proposed in this application can significantly improve prediction accuracy, enhance model flexibility, and enhance system scalability, providing strong support for tourism planning and scenic spot management.

[0149] In summary, the method provided by the embodiment of the present application includes: obtaining initial data related to passenger flow from several channels; cleaning and integrating the initial data to obtain feature data, and inputting the feature data into the passenger flow prediction model to obtain a prediction result; correcting the prediction result according to preset correction parameters to obtain a target result for the passenger flow prediction of the scenic spot; the preset correction parameters are related to the historical prediction accuracy and expert experience. The embodiment of the present application obtains initial data related to passenger flow through multiple channels and pre-processes the data, which improves the prediction accuracy of the model to a certain extent. At the same time, the embodiment of the present application corrects the prediction results of the model by preset correction parameters, which can flexibly adjust the prediction results of the model, further improving the prediction accuracy of the model.

[0150] Secondly, refer to the attached Figure 3 A tourist attraction passenger flow prediction system proposed according to an embodiment of the present application is described.

[0151] Figure 3 : is a schematic diagram of the structure of a tourist flow prediction system for a scenic spot according to an embodiment of the present application, and the system specifically includes:

[0152] The first module 310 is used to obtain initial data related to passenger flow from several channels;

[0153] The second module 320 is used to clean and integrate the initial data to obtain feature data, and input the feature data into a passenger flow prediction model to obtain a prediction result;

[0154] The third module 330 is used to correct the prediction result according to preset correction parameters to obtain the target result of the tourist flow prediction of the scenic spot; the preset correction parameters are related to the historical prediction accuracy and expert experience.

[0155] Optionally, in one embodiment of the present application, the system further includes a fourth module, configured to:

[0156] Get initial sample data;

[0157] The initial sample data is cleaned and integrated to obtain feature sample data, and the feature sample data is input into the LSTM model to obtain a sample prediction result;

[0158] A loss function is established according to the sample prediction result and the sample actual result, and the parameters of the LSTM model are updated according to the loss function to obtain the updated LSTM model;

[0159] The updated LSTM model is dynamically adjusted through other sample data.

[0160] Optionally, in one embodiment of the present application, the system further includes a fifth module, configured to:

[0161] Obtaining historical collected data, estimated data and actual data; the estimated data is the prediction result of the historical collected data by the passenger flow prediction model, and the actual data is the actual passenger flow data corresponding to the historical collected data;

[0162] A first correction parameter is determined according to the estimated data and the actual data.

[0163] Optionally, in one embodiment of the present application, the system further includes a sixth module, configured to:

[0164] Obtain a first change in the current acquisition channel, and determine the second correction parameter through expert evaluation based on the impact of the first change on passenger flow; the first change is a behavioral change made by the current acquisition channel that is related to the current predicted sales volume of the scenic spot.

[0165] Optionally, in one embodiment of the present application, the system further includes a seventh module, which is used to:

[0166] Obtaining side data related to customer traffic from several channels; wherein the side data includes comment data and visit data;

[0167] Inputting the side data into an influence model to obtain a first coefficient that affects the prediction result; the influence model is used to characterize the correlation between the side data and the prediction result;

[0168] The first coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

[0169] Optionally, in one embodiment of the present application, the system further includes an eighth module, configured to:

[0170] Get the current traffic changes of each channel;

[0171] Determine a second coefficient of the flow change affecting the prediction result;

[0172] The second coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

[0173] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0174] Reference Figure 4 The present application embodiment provides a device for predicting tourist flow of scenic spots, including:

[0175] at least one processor 410;

[0176] At least one memory 420, used to store at least one program;

[0177] When the at least one program is executed by the at least one processor 410, the at least one processor 410 implements the scenic spot passenger flow prediction method.

[0178] Similarly, the contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0179] The embodiment of the present application further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned method for predicting the tourist flow of tourists.

[0180] Similarly, the contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0181] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are expected, wherein the order of various operations is changed and the sub-operation described as a part of a larger operation is performed independently.

[0182] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0183] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several programs to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0184] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution systems, devices or apparatuses.

[0185] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0186] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0187] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0188] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0189] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the described embodiments. Technical personnel familiar with the field may make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for predicting tourist flow at a scenic spot, characterized in that: The following steps are involved: Obtain initial data related to customer traffic from several channels; Cleaning and integrating the initial data to obtain feature data, and inputting the feature data into a passenger flow prediction model to obtain a prediction result; The prediction result is corrected according to preset correction parameters to obtain a target result for the tourist flow prediction of the scenic spot; the preset correction parameters are related to the historical prediction accuracy and expert experience.

2. The method for predicting tourist flow of scenic spots according to claim 1, characterized in that: The cleaning and integration of the initial data to obtain feature data includes: Determine a first weight of the data from each of the channels, perform weighted processing on the initial data according to the first weight, and integrate the weighted data to obtain feature data; Alternatively, the initial data is cleaned to remove abnormal values, and the cleaned data is integrated to obtain characteristic data related to passenger flow; Alternatively, the initial data is subjected to uniform standardization processing, and the data after the uniform standardization processing is integrated to obtain feature data.

3. The method for predicting tourist flow of scenic spots according to claim 2, characterized in that: The passenger flow prediction model is an LSTM model, which is trained by the following steps: Get initial sample data; The initial sample data is cleaned and integrated to obtain feature sample data, and the feature sample data is input into the LSTM model to obtain a sample prediction result; A loss function is established according to the sample prediction result and the sample actual result, and the parameters of the LSTM model are updated according to the loss function to obtain the updated LSTM model; The updated LSTM model is dynamically adjusted through other sample data.

4. The method for predicting tourist flow of scenic spots according to claim 1, characterized in that: The preset correction parameters include a first correction parameter, and the first correction parameter is determined by the following steps: Obtaining historical collected data, estimated data and actual data; the estimated data is the prediction result of the historical collected data by the passenger flow prediction model, and the actual data is the actual passenger flow data corresponding to the historical collected data; A first correction parameter is determined according to the estimated data and the actual data.

5. The method for predicting tourist flow of scenic spots according to claim 1, characterized in that: The preset correction parameter includes a second correction parameter, and the second correction parameter is determined by the following steps: Obtain a first change in the current acquisition channel, and determine the second correction parameter through expert evaluation based on the impact of the first change on passenger flow; the first change is a behavioral change made by the current acquisition channel that is related to the current predicted sales volume of the scenic spot.

6. The method for predicting tourist flow of scenic spots according to claim 1, characterized in that: The method further comprises: Obtaining side data related to customer traffic from several channels; wherein the side data includes comment data and visit data; Inputting the side data into an influence model to obtain a first coefficient that affects the prediction result; the influence model is used to characterize the correlation between the side data and the prediction result; The first coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

7. The method for predicting tourist flow of scenic spots according to claim 1, characterized in that: The method further comprises: Get the current traffic changes of each channel; Determine a second coefficient of the flow change affecting the prediction result; The second coefficient is integrated into the passenger flow prediction model to obtain a new passenger flow prediction model.

8. A tourist flow prediction system for scenic spots, characterized in that: include: The first module is used to obtain initial data related to customer traffic from several channels; The second module is used to clean and integrate the initial data to obtain feature data, and input the feature data into the passenger flow prediction model to obtain the prediction result; The third module is used to correct the prediction result according to the preset correction parameters to obtain the target result of the tourist flow prediction of the scenic spot; The preset correction parameters are related to historical prediction accuracy and expert experience.

9. A device for predicting tourist flow at a scenic spot, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method for predicting tourist flow of attractions according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the scenic spot passenger flow prediction method according to any one of claims 1 to 7 when executed by the processor.

Images