Scenic spot information acquisition system

Abstract

The invention relates to the field of intelligent scenic spot management, in particular to a scenic spot information acquisition system, which comprises a data acquisition module used for acquiring tourist flow, facility state and environment data in a scenic spot; the cloud platform is used for storing the data acquired by the data acquisition module; the data processing module is used for cleaning and duplicating the collected data; the data analysis module is used for analyzing the data by using a machine learning algorithm and outputting a result; and the recommendation engine module is used for receiving a result of the data analysis module and pushing personalized services. Data collected by the data collection module is integrated in a unified database through the cloud platform, the problem of data islands is solved, the data processing module removes data redundancy and ensures that the collected data has high accuracy and timeliness, and the data analysis module predicts the interior of a scenic spot in real time by using an algorithm, so that the real-time performance of the scenic spot is improved. And decisions are quickly made in response to internal and external changes of the scenic spot in a short time, so that personalized recommendation services are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent scenic area management, and particularly to a scenic area information collection system. Background Art

[0002] With the rapid development of the modern tourism industry, the demands of tourists for scenic areas are gradually shifting from traditional sightseeing tours to more personalized and intelligent experiences. Based on this, higher requirements are put forward for the intelligent management of scenic areas. Currently, although many scenic areas have started to use information technology for management and services, there are still great deficiencies in the collection and management of scenic area information in the existing technologies. For example, various types of data (such as tourist behavior data, scenic area facility data, weather data, tourist satisfaction, etc.) often exist in different systems, and each system forms a data island, making it difficult to integrate and effectively utilize; duplicate or invalid data is frequently collected, resulting in data redundancy, and it is difficult for decision-makers to quickly obtain valuable information from the vast amount of data; the personalization of tourist needs is insufficient, that is, most traditional systems are one-way information releases and do not provide personalized recommendations and services based on the behavior and interests of tourists. Summary of the Invention

[0003] The present invention provides a scenic area information collection system, aiming to solve the problems of data islands, poor real-time performance, and data redundancy existing in traditional scenic area management systems.

[0004] The present invention is realized through the following technical solutions: A scenic area information collection system includes:

[0005] A cloud platform, connected to the data collection module, for storing the data collected by the data collection module;

[0006] A data processing module, connected to the cloud platform, for cleaning and de-duplicating the collected data;

[0007] A data analysis module, connected to the data processing module, for analyzing the data using machine learning algorithms and outputting results;

[0008] A recommendation engine module, connected to the data analysis module, for receiving the analysis results of the data analysis module and pushing personalized services.

[0009] Further, the data collection module includes one or a combination of a temperature and humidity sensor, an infrared sensor, a pressure sensing flowmeter, and a video monitor.

[0010] Further, the de-duplication methods of the data processing module include time window de-duplication, same value de-duplication, threshold de-duplication, and time series de-duplication; the calculation method of the time window de-duplication is: set a time window, if the data collected within this time window is the same, then keep one data: D unique=filter(D, T), where D is all the collected data, D unique The filter function is used to filter out unique data items in the time window T from the dataset D.

[0011] The calculation method for removing duplicates with the same value is: for each element in the data set, if the data items are the same, remove the redundant items: D unique ={d|d∈D,d∈ / D duplicates}, where D is the original data set, D unique is the dataset after deduplication, D duplicates Indicates all repeated items;

[0012] The calculation method of the threshold deduplication is: set a tolerance threshold ε, if the difference between two data items is less than ε, they are considered to be duplicates: where di and d j is the data item, ε is the threshold;

[0013] The calculation method for deduplication of time series is as follows: set the change threshold Δ, for adjacent data points x in the time series t and x t+1 , if |x t -x t+1 |<Δ, it is considered redundant.

[0014] Furthermore, the data analysis module uses a time series data prediction algorithm and / or a cluster analysis algorithm to perform real-time predictions on tourist flow, facility status, and environmental data within the scenic area.

[0015] Furthermore, the push personalized service is that the recommendation engine module pushes one or more combinations of scenic spot recommendations, restaurant recommendations, and activity recommendations based on the analysis results.

[0016] Furthermore, the data collection module also includes a scenic spot APP and an electronic tag, which are used to collect data on tourists' activity paths and stay time in the scenic spot;

[0017] Furthermore, the time series data prediction algorithm adopts the ARIMA model; the cluster analysis algorithm includes the following steps:

[0018] S1, select the cluster number K value;

[0019] S2, randomly select K points as the initial center;

[0020] S3, calculate the distance between each sample point and K centers, assign each sample point to the nearest center, and form K clusters;

[0021] S4, calculate the mean of all points in each cluster and update the center points of all clusters;

[0022] S5. Repeat steps S3 and S4 until the position of the center point no longer changes significantly, and the clustering process ends.

[0023] Among them, the calculation distance formula in step S3 is:

[0024] Among them, and respectively represent the coordinates of the sample point ci and the center point ck in the j-th dimension, and d is the number of dimensions.

[0025] In the present invention, the data collected by the data collection module is integrated into a unified database through a cloud platform to solve the problem of data islands, thereby realizing the comprehensive integration and efficient management of data. The data processing module uses time window deduplication, same value deduplication, threshold deduplication, and time series deduplication for the collected data to remove data redundancy, ensuring that the collected data has high accuracy and timeliness, thereby reducing the interference of invalid data and enabling decision-makers to quickly obtain valuable information. The data analysis module uses time series data prediction algorithms and clustering analysis algorithms to perform real-time prediction on the tourist flow, facility status, and environmental data in the scenic area, and can respond to changes inside and outside the scenic area in a short time, make decisions quickly. The recommendation engine module can implement personalized recommendation services according to the results of the data analysis module. This service can not only provide scenic spot recommendations, but also recommend the optimal play route, dining location, etc. according to the characteristics of tourists such as interests and stay time, improving the overall experience of tourists. For example, when a tourist arrives at a certain scenic spot, the system can push recommendation information through the App to remind tourists of relevant preferential activities or popular scenic spots nearby. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic block diagram of the module mechanism of the scenic area information collection system of the present invention;

[0027] Figure 2 is a schematic block diagram of the steps of the clustering analysis algorithm of the scenic area information collection system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] In order to make the purpose and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0029] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0030] It should be noted that in the description of the present invention, the terms indicating the direction or positional relationship such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0031] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0032] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this article represents any one of multiple types or any combination of at least two of multiple types. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0033] The following further describes the present invention in detail with reference to the drawings.

[0034] As Figure 1 shown, a scenic area information collection system includes: a data collection module for collecting the tourist flow, facility status, environmental data, scenic area APP, and electronic tags in the scenic area. Generally, a temperature and humidity sensor is used for the data collection module, and the temperature and humidity sensor is set in the scenic area to collect weather conditions; an infrared sensor that monitors the passenger flow in each area of the scenic area in real time. When the passenger flow exceeds the preset safety threshold, the infrared sensor can issue a warning; a pressure induction flowmeter is set at the entrance and exit of the scenic area to collect the number of people entering and leaving in real time; a video monitor. In order to reduce the visual blind area, it monitors the safety of tourists in real time. The scenic area APP and the electronic tag are used to collect the activity path and stay time data of tourists in the scenic area.

[0035] A cloud platform for storing the collected data, integrating the data in a unified database, and solving the problem of data islands.

[0036] The data processing module is used to clean and deduplicate the collected data. Since a large amount of duplicate and invalid data will appear in the data collected by the scenic area, resulting in data redundancy, it is difficult for decision-makers to quickly obtain valuable information from the vast amount of data. To efficiently manage this data, the system processes it through data cleaning algorithms. This data processing module generally uses several methods such as time window deduplication, value-based deduplication, threshold deduplication, and time series deduplication. The calculation method of time window deduplication is as follows: Set a time window. If the data collected within this time window is the same, then retain one piece of data: D unique = filter(D, T), where D is all the collected data, D unique is the deduplicated data, and the filter function represents selecting the unique data items from the data set D within the time window T;

[0037] The calculation method of value-based deduplication is as follows: For each element in the data set, if the data items are the same, then remove the redundant items: D unique = {d|d ∈ D, d ∉ D duplicates}, where D is the original data set, D unique is the deduplicated data set, and D duplicates represents all the duplicate items;

[0038] The calculation method of threshold deduplication is as follows: Set a tolerance threshold ε. If the difference between two data items is less than ε, then they are considered duplicates: where di and d j are data items, and ε is the threshold;

[0039] The calculation method of time series deduplication is as follows: Set a change threshold Δ. For adjacent data points x t and x t+1 in the time series, if |x t - x t+1 | < Δ, then it is regarded as redundant.

[0040] The data analysis module uses time series data prediction algorithms or / and clustering analysis algorithms to perform real-time prediction on the tourist flow, facility status, and environmental data in the scenic area;

[0041] The time series data prediction algorithm uses the ARIMA model. The specific steps are as follows:

[0042] S1. Data preprocessing:

[0043] Collect time series data to ensure that there are no missing values.

[0044] Visualize the data to understand the characteristics such as trends, seasonality, and periodicity of the data.

[0045] Check the stationarity of the data by methods such as plotting data charts and ADF tests.

[0046] S2. Stationarize the data:

[0047] If the data is not stationary, stationary the data through differencing operations.

[0048] Determine the differencing order, usually by observing the ACF and PACF plots.

[0049] S3. Model selection (determine p, d, q):

[0050] p (autoregressive order): Determine by looking at the PACF plot.

[0051] d (differencing order): Has been determined during the data stationarization process.

[0052] q (moving average order): Determine by looking at the ACF plot.

[0053] S4. Fit the ARIMA model:

[0054] Based on the determined p, d, q values, construct an ARIMA model.

[0055] Use historical data to fit the ARIMA model, usually using the maximum likelihood estimation method.

[0056] S5. Model diagnosis:

[0057] Perform residual analysis to check if the residuals are white noise.

[0058] Use methods such as ACF / PACF plots and Ljung-Box tests to check the autocorrelation and partial autocorrelation of the residuals.

[0059] S6. Model prediction:

[0060] Use the fitted model to predict future values.

[0061] Use different evaluation metrics (such as MSE, RMSE, etc.) to evaluate the prediction accuracy of the model.

[0062] S7. Model optimization:

[0063] According to the diagnosis results or prediction effects, adjust p, d, q and refit the model.

[0064] Cluster analysis is used to group similar data points into the same category to help understand the behavior patterns of scenic area visitors, facility usage patterns, etc.

[0065] Specifically: data collection and preprocessing, collecting information about tourists, facility status, weather, etc. The data may include the age, gender, playing time, activity type of tourists, etc.;

[0066] Data cleaning: Remove duplicate values, handle missing values, and perform data normalization or standardization to ensure that the impacts of different features on the clustering results are relatively balanced; Feature selection: Select features that can reflect tourist behavior or facility status, such as the duration of stay in the scenic area, visited attractions, weather conditions, etc.

[0067] Feature scaling: Since clustering algorithms are sensitive to the scale of features, it is necessary to standardize or normalize the data to avoid certain features dominating.

[0068] Select a clustering algorithm:

[0069] As Figure 2 shown, the steps of clustering analysis:

[0070] S1. Select the number of clusters K value;

[0071] S2. Randomly select K points as the initial centers;

[0072] S3. Calculate the distances between each sample point and the K centers, and assign each sample point to the nearest center to form K clusters;

[0073] S4. Calculate the mean of all points within each cluster and update the center points of all clusters;

[0074] S5. Repeat steps S3 and S4 until the positions of the center points no longer change significantly and the clustering process ends.

[0075] Among them, the distance calculation formula in step S3 is:

[0076] Among them, and respectively represent the coordinates of the sample point ci and the center point ck in the jth dimension, and d is the number of dimensions.

[0077] Model training: After selecting a suitable clustering algorithm, use the training data for clustering.

[0078] Determine the number of clusters (K value): The optimal number of clusters can be determined by methods such as the Elbow Method or SilhouetteScore.

[0079] Analysis of clustering results: According to the clustering results, analyze the characteristics of different categories of tourists. For example, one category of tourists may be family tourists, and another may be young backpackers, and analyze the behavior patterns and needs of each cluster.

[0080] Application and Optimization

[0081] . According to the clustering results, the recommendation engine module receives the results of the data analysis module (such as tourist category, traffic, environmental data, tourist behavior data), and pushes personalized services, such as scenic spot recommendations, dining recommendations, activity recommendations, etc., to optimize the configuration and management of facilities.

[0082] Through such steps, the managers of the scenic area can make more accurate and flexible decisions based on real-time data, send real-time information to tourists through methods such as APP push and SMS, provide personalized suggestions, and optimize tourist guidance and experience to improve the operation efficiency and tourist satisfaction of the scenic area.

[0083] The present invention is not limited to the above specific embodiments. Those of ordinary skill in the art starting from the above concepts and making various transformations without creative labor fall within the protection scope of the present invention.

Claims

1. A scenic spot information collection system, characterized in that: include: Data collection module, used to collect tourist flow, facility status, and environmental data within the scenic area; A cloud platform, connected to the data acquisition module, for storing data collected by the data acquisition module; A data processing module, connected to the cloud platform, for cleaning and deduplicating the collected data; A data analysis module, connected to the data processing module, uses a machine learning algorithm to analyze the data and output the results; The recommendation engine module is connected to the data analysis module, receives the analysis results of the data analysis module, and pushes personalized services.

2. The system according to claim 1, characterized in that The data acquisition module includes one or more combinations of a temperature and humidity sensor, an infrared sensor, a pressure sensing flow meter, and a video monitor.

3. The system according to claim 1, characterized in that The deduplication methods of the data processing module include time window deduplication, same value deduplication, threshold deduplication, and time series deduplication; the calculation method of the time window deduplication is: set a time window T, if the data collected in the time window is the same, then retain one data: D unique =filter(D, T), where D is all the collected data, D unique The filter function is used to filter out unique data items in the time window T from the dataset D. The calculation method for removing duplicates with the same value is: for each element in the data set, if the data items are the same, remove the redundant items: Among them, D is the original data set, D unique is the dataset after deduplication, D duplicates Indicates all repeated items; The calculation method of the threshold deduplication is: set a tolerance threshold ε, if the difference between two data items is less than ε, they are considered to be duplicates: where di and d j is the data item, ε is the threshold; The calculation method for deduplication of time series is as follows: set the change threshold Δ, for adjacent data points x in the time series t and x t+1 , if |X t -X t+1 |<Δ, it is considered redundant.

4. The system according to claim 1, characterized in that The data analysis module uses a time series data prediction algorithm and / or a cluster analysis algorithm to perform real-time predictions on tourist flow, facility status, and environmental data within the scenic area.

5. The system according to claim 1, characterized in that The personalized push service is one or more combinations of push attraction recommendations, restaurant recommendations, and activity recommendations.

6. The system according to claim 1, characterized in that The data collection module also includes a scenic spot APP and electronic tags, which are used to collect tourists' activity paths and stay time data in the scenic spot.

7. The system according to claim 4, characterized in that The time series data prediction algorithm adopts the ARIMA model; the cluster analysis algorithm includes the following steps: S1, select the cluster number K value; S2, randomly select K points as the initial center; S3, calculate the distance between each sample point and K centers, assign each sample point to the nearest center, and form K clusters; S4, calculate the mean of all points in each cluster and update the center points of all clusters; S5. Repeat steps S3 and S4 until the position of the center point no longer changes significantly, and the clustering process ends. The distance calculation formula in step S3 is: in, and They respectively represent the coordinates of the sample point ci and the center point ck in the jth dimension, and d is the number of dimensions.

Images