Service management method and system for smart scenic spot

Abstract

The invention discloses a service management method and system for a smart scenic spot, and the method comprises the steps: collecting historical tourist behavior data, carrying out the preprocessing of the historical tourist behavior data, and obtaining the preprocessed data; historical weather data and historical holiday and festival data are collected, a behavior prediction model is constructed based on the preprocessed data, the weather data and the holiday and festival data, and a tourist behavior mode prediction result is obtained through the behavior prediction model; historical operation state data and historical fault records of the scenic spot equipment are collected, an equipment fault prediction model is constructed based on the historical operation state data, the historical fault records, the weather data and the holiday and festival data, and an equipment fault prediction result is obtained through the equipment fault prediction model; and generating a tourist guiding strategy based on the tourist behavior mode prediction result, and generating an equipment maintenance strategy based on the equipment fault prediction result. Through a data mining technology, a tourist guiding strategy and an equipment maintenance strategy are formulated, and the intelligent level and the service quality of scenic spot management are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of service management and artificial intelligence intersection, and specifically relates to a service management method and system for a smart scenic spot. Background Art

[0002] In practical applications, the smart scenic area service management system faces the technical difficulties of collecting and analyzing tourist behavior data. Massive tourist behavior data comes from heterogeneous data sources such as various sensors, video surveillance, and ticketing systems. The data format is not unified, and the timeliness varies greatly, making it difficult to effectively integrate and analyze in real time. At the same time, tourist behavior patterns are complex and changeable, and are affected by factors such as weather and holidays. How to timely discover abnormal tourist behavior from massive data, predict tourist flow trends, and optimize the allocation of scenic area service resources is a technical challenge that needs to be solved urgently. In addition, scenic area facilities and equipment are of various types and widely distributed, with a harsh operating environment, making fault diagnosis and maintenance difficult. Traditional equipment fault diagnosis relies on manual experience, which is inefficient and not accurate. How to use technologies such as the Internet of Things and big data to achieve real-time monitoring of equipment operating status, build an equipment fault knowledge base, realize intelligent and automated fault diagnosis and predictive maintenance, improve equipment reliability and availability, and reduce operation and maintenance costs is another key technical issue facing the smart scenic area service management system. Summary of the invention

[0003] The present invention aims to solve the deficiencies of the prior art and provides the following solutions:

[0004] A service management method for a smart scenic spot comprises the following steps:

[0005] Collecting historical tourist behavior data, and preprocessing the historical tourist behavior data to obtain preprocessed data;

[0006] Collecting historical weather data and historical holiday data, building a behavior prediction model based on the pre-processed data, the weather data and the holiday data, and using the behavior prediction model to obtain a prediction result of a tourist behavior pattern;

[0007] Collecting historical operating status data and historical fault records of scenic area equipment, building an equipment fault prediction model based on the historical operating status data, the historical fault records, the weather data and the holiday data, and using the equipment fault prediction model to obtain equipment fault prediction results;

[0008] A tourist guidance strategy is generated based on the tourist behavior pattern prediction result, and an equipment maintenance strategy is generated based on the equipment failure prediction result.

[0009] Preferably, the pretreatment method comprises:

[0010] Cleaning the historical tourist behavior data, removing outliers and supplementing missing values, to obtain cleaned data;

[0011] The cleaned data is standardized and normalized to obtain the preprocessed data.

[0012] Preferably, the method for constructing a behavior prediction model includes:

[0013] Standardizing the historical weather data and the historical holiday data to obtain a structured weather data set and a structured holiday data set;

[0014] Analyze the historical tourist behavior data using a time series analysis algorithm to obtain tourist behavior characteristics, and use an association rule mining algorithm to analyze the correlation between the tourist behavior characteristics and the structured weather data set and the structured holiday data set to obtain behavior pattern influencing factors;

[0015] The behavior prediction model is constructed based on the historical weather data, the historical holiday data and the behavior pattern influencing factors.

[0016] Preferably, the method for constructing the equipment failure prediction model includes:

[0017] Cleaning and normalizing the historical operating status data and the historical fault records of the scenic area equipment to obtain processed operating status data and processed fault records;

[0018] Based on the processed operating status data and the processed fault records, a device fault prediction model is constructed using a decision tree algorithm.

[0019] The present invention also provides a service management system for a smart scenic spot, the management system applies any of the management methods described above, including: a data collection module, a tourist behavior prediction module, a scenic spot equipment failure prediction module and a strategy generation module;

[0020] The data collection module is used to collect historical tourist behavior data, pre-process the historical tourist behavior data, and obtain pre-processed data;

[0021] The tourist behavior prediction module is used to collect historical weather data and historical holiday data, build a behavior prediction model based on the pre-processed data, the weather data and the holiday data, and use the behavior prediction model to obtain a tourist behavior pattern prediction result;

[0022] The scenic area equipment failure prediction module is used to collect historical operation status data and historical failure records of scenic area equipment, build an equipment failure prediction model based on the historical operation status data, the historical failure records, the weather data and the holiday data, and use the equipment failure prediction model to obtain equipment failure prediction results;

[0023] The strategy generation module generates a tourist guidance strategy based on the tourist behavior pattern prediction result, and generates an equipment maintenance strategy based on the equipment failure prediction result.

[0024] Preferably, the workflow of the data acquisition module includes:

[0025] Cleaning the historical tourist behavior data, removing outliers and supplementing missing values, to obtain cleaned data;

[0026] The cleaned data is standardized and normalized to obtain the preprocessed data.

[0027] Preferably, in the tourist behavior prediction module, the process of building a behavior prediction model includes:

[0028] Standardizing the historical weather data and the historical holiday data to obtain a structured weather data set and a structured holiday data set;

[0029] Analyze the historical tourist behavior data using a time series analysis algorithm to obtain tourist behavior characteristics, and use an association rule mining algorithm to analyze the correlation between the tourist behavior characteristics and the structured weather data set and the structured holiday data set to obtain behavior pattern influencing factors;

[0030] The behavior prediction model is constructed based on the historical weather data, the historical holiday data and the behavior pattern influencing factors.

[0031] Preferably, in the scenic area equipment failure prediction module, the process of building an equipment failure prediction model includes:

[0032] Cleaning and normalizing the historical operating status data and the historical fault records of the scenic area equipment to obtain processed operating status data and processed fault records;

[0033] Based on the processed operating status data and the processed fault records, a device fault prediction model is constructed using a decision tree algorithm.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention firstly processes and stores the tourist behavior data collected from heterogeneous data sources in a standardized manner, and based on these data, uses time series analysis and association rule mining algorithms to analyze tourist behavior patterns and predict tourist flow trends. At the same time, the present invention also obtains the operating status data of scenic area equipment, builds a fault diagnosis model through a decision tree algorithm, and realizes equipment failure risk warning.

[0036] In addition, the present invention also uses data mining technology to formulate tourist guidance strategies and equipment predictive maintenance strategies. By continuously collecting and analyzing data, it can continuously iterate and upgrade itself, achieve the sustainable development of smart scenic spots, and improve the intelligence level and service quality of scenic spot management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] Embodiment 1

[0042] In this embodiment, if Figure 1 As shown, a service management method for a smart scenic spot includes the following steps:

[0043] S1. Collect historical tourist behavior data, pre-process the historical tourist behavior data, and obtain pre-processed data.

[0044] The preprocessing method includes: cleaning the historical tourist behavior data, removing outliers and supplementing missing values ​​to obtain cleaned data; standardizing and normalizing the cleaned data to obtain preprocessed data.

[0045] In this embodiment, for the data collection process, a data collection interface based on JDBC is designed for structured data such as tourist ticket purchase records, and the age group and consumption amount of tourists are analyzed based on the ticket purchase records. For unstructured data such as tourist comments, photos, and stay time, a RESTful API data collection interface based on WebService is used. The K-Means algorithm is used to convert the age of tourists into 4 age groups according to the attributes such as the age group, consumption amount, and stay time of tourists, which are under 18 years old, 18-35 years old, 36-60 years old, and over 60 years old, and the tourist rating is converted into 5 levels of 1-5 points. In terms of data cleaning, an outlier detection algorithm such as a box plot is used, and data that exceeds 5 times the distance between the upper and lower quartiles is regarded as an outlier and removed. For missing values, the highest frequency value filling method can be used. HDFS can be used as the underlying storage, and 100GB of new data is stored in HDFS every day, and then the data in HDFS is mapped to a data table through Hive for easy analysis.

[0046] S2. Collect historical weather data and historical holiday data, build a behavior prediction model based on the preprocessed data, weather data and holiday data, and use the behavior prediction model to obtain the prediction results of tourist behavior patterns.

[0047] The method for constructing a behavior prediction model includes: standardizing historical weather data and historical holiday data to obtain structured weather data sets and structured holiday data sets; using a time series analysis algorithm to analyze historical tourist behavior data to obtain tourist behavior characteristics, and using an association rule mining algorithm to analyze the correlation between tourist behavior characteristics and structured weather data sets and structured holiday data sets to obtain behavior pattern influencing factors; constructing a behavior prediction model based on historical weather data, historical holiday data and behavior pattern influencing factors.

[0048] In this embodiment, by designing a RESTful API interface, the data collection specification is defined in JSON format to realize the automatic collection of historical weather data and historical holiday data. The collected data is cleaned, and regular expressions are used to match and filter invalid data, remove records with empty or erroneous tourist IDs, remove abnormal weather data with temperature values ​​beyond a reasonable range, and convert the cleaned data into a unified structured format through data mapping and conversion, such as converting text descriptions in weather data into numerical types (such as "sunny" to 0, "cloudy" to 1). Time series analysis is performed on structured data, and the number of tourists is modeled using the ARIMA model. The model parameters are evaluated through indicators such as AIC and BIC, and the optimal p, d, and q values ​​are selected, such as the ARIMA (1,1,2) model, and external factors such as weather and holidays are added as covariates to improve the prediction accuracy of the model. Using the Apriori algorithm, the minimum support is set to 05 and the minimum confidence is set to 8, and the association rules between tourist behavior and weather and holidays are mined, such as "When it is sunny, tourists stay longer at scenic spot A (support 12, confidence 9)" and other rules to obtain the influencing factors of behavior patterns. Based on historical weather data, historical holiday data and behavioral pattern influencing factors, a tourist behavior prediction model is constructed, and the abnormal threshold is set to 3 times the standard deviation of the number of tourists. The tourist behavior data is monitored in real time. When the actual number of tourists exceeds the abnormal threshold of the predicted value, an early warning message is generated and notified to the scenic area management personnel via SMS or push. In this embodiment, the support vector machine algorithm is adopted, the Gaussian kernel function is selected, the behavior prediction model is trained, and the C and gamma parameters of the model are optimized using the grid search method to improve the prediction accuracy.

[0049] S3. Collect historical operating status data and historical fault records of scenic area equipment, build an equipment failure prediction model based on the historical operating status data, historical fault records, weather data and holiday data, and use the equipment failure prediction model to obtain equipment failure prediction results.

[0050] The method for constructing an equipment failure prediction model includes: cleaning and normalizing the historical operating status data and historical fault records of scenic area equipment to obtain processed operating status data and processed fault records; based on the processed operating status data and processed fault records, using a decision tree algorithm to construct an equipment failure prediction model.

[0051] In this embodiment, the historical operating status data and historical fault records of the scenic area equipment are obtained. The historical operating status data can be obtained through sensors and monitoring modules installed on the equipment, such as temperature and humidity sensors, vibration sensors, and current monitoring modules, etc., to collect environmental parameters, performance indicators, and fault records. The collected data is preprocessed, and the abnormal values ​​exceeding the threshold are eliminated by setting reasonable thresholds, temperature range -10 ° C to 50 ° C, humidity range 20% to 90%, vibration amplitude less than 1mm, current change rate less than 10%, etc. For missing values, mean filling or interpolation methods can be used for estimation. Then, the minimum-maximum normalization method is used to scale the data to the [0,1] interval to eliminate the dimensional influence between different indicators. After that, 5 to 10 key features are extracted from the normalized data using principal component analysis (PCA) to construct a feature vector reflecting the operating status of the equipment. The decision tree algorithm is used to train and generate an equipment fault prediction model with the historical operating status data of the equipment and the corresponding historical fault records as the training set. The model selects the optimal partitioning attribute through information gain or Gini index, and recursively builds a tree structure until the samples belong to the same category or reach a predetermined depth. The real-time operation status data of the equipment is obtained, and the data is preprocessed and feature extracted in the same way as the training data, and then input into the trained fault diagnosis model for prediction to obtain the equipment fault prediction result.

[0052] S4. Generate a tourist guidance strategy based on the tourist behavior pattern prediction results, and generate an equipment maintenance strategy based on the equipment failure prediction results.

[0053] In this embodiment, based on the predicted tourist behavior, flow and other data, combined with the scenic area's road network, facility distribution and other information, a genetic algorithm is used to optimize resource allocation, setting the population size to 50, the crossover probability to 8, the mutation probability to 1, and iterating 100 times to obtain the optimal personnel arrangement and facility opening plan, i.e., the tourist guidance strategy. According to the equipment failure prediction results, similar cases are matched, the corresponding maintenance methods are obtained, and the equipment maintenance strategy is generated.

[0054] Embodiment 2

[0055] In this embodiment, a service management system for a smart scenic spot includes: a data collection module, a tourist behavior prediction module, a scenic spot equipment failure prediction module and a strategy generation module.

[0056] The data collection module is used to collect historical tourist behavior data, pre-process the historical tourist behavior data, and obtain pre-processed data.

[0057] The workflow of the data collection module includes: cleaning the historical tourist behavior data, removing outliers and supplementing missing values ​​to obtain cleaned data; standardizing and normalizing the cleaned data to obtain preprocessed data.

[0058] The tourist behavior prediction module is used to collect historical weather data and historical holiday data, build a behavior prediction model based on preprocessed data, weather data and holiday data, and use the behavior prediction model to obtain the prediction results of tourist behavior patterns.

[0059] In the tourist behavior prediction module, the process of building a behavior prediction model includes: standardizing historical weather data and historical holiday data to obtain structured weather data sets and structured holiday data sets; using a time series analysis algorithm to analyze historical tourist behavior data to obtain tourist behavior characteristics, and using an association rule mining algorithm to analyze the correlation between tourist behavior characteristics and structured weather data sets and structured holiday data sets to obtain behavior pattern influencing factors; building a behavior prediction model based on historical weather data, historical holiday data, and behavior pattern influencing factors.

[0060] The scenic area equipment failure prediction module is used to collect the historical operating status data and historical fault records of scenic area equipment, build an equipment failure prediction model based on the historical operating status data, historical fault records, weather data and holiday data, and use the equipment failure prediction model to obtain equipment failure prediction results.

[0061] In the scenic area equipment failure prediction module, the process of building an equipment failure prediction model includes: cleaning and normalizing the historical operating status data and historical fault records of the scenic area equipment to obtain processed operating status data and processed fault records; based on the processed operating status data and processed fault records, using the decision tree algorithm to build an equipment failure prediction model.

[0062] The strategy generation module generates a tourist guidance strategy based on the prediction results of tourist behavior patterns, and generates an equipment maintenance strategy based on the prediction results of equipment failures.

[0063] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A service management method for a smart scenic spot, characterized in that: The following steps are involved: Collecting historical tourist behavior data, and preprocessing the historical tourist behavior data to obtain preprocessed data; Collecting historical weather data and historical holiday data, building a behavior prediction model based on the pre-processed data, the weather data and the holiday data, and using the behavior prediction model to obtain a prediction result of a tourist behavior pattern; Collecting historical operating status data and historical fault records of scenic area equipment, building an equipment fault prediction model based on the historical operating status data, the historical fault records, the weather data and the holiday data, and using the equipment fault prediction model to obtain equipment fault prediction results; A tourist guidance strategy is generated based on the tourist behavior pattern prediction result, and an equipment maintenance strategy is generated based on the equipment failure prediction result.

2. A service management method for a smart scenic spot according to claim 1, characterized in that: The pretreatment method comprises: Cleaning the historical tourist behavior data, removing outliers and supplementing missing values, to obtain cleaned data; The cleaned data is standardized and normalized to obtain the preprocessed data.

3. A service management method for a smart scenic spot according to claim 1, characterized in that: Methods for building behavior prediction models include: Standardizing the historical weather data and the historical holiday data to obtain a structured weather data set and a structured holiday data set; Analyze the historical tourist behavior data using a time series analysis algorithm to obtain tourist behavior characteristics, and use an association rule mining algorithm to analyze the correlation between the tourist behavior characteristics and the structured weather data set and the structured holiday data set to obtain behavior pattern influencing factors; The behavior prediction model is constructed based on the historical weather data, the historical holiday data and the behavior pattern influencing factors.

4. A service management method for a smart scenic spot according to claim 3, characterized in that: The method for constructing the equipment failure prediction model includes: Cleaning and normalizing the historical operating status data and the historical fault records of the scenic area equipment to obtain processed operating status data and processed fault records; Based on the processed operating status data and the processed fault records, a device fault prediction model is constructed using a decision tree algorithm.

5. A service management system for a smart scenic spot, the management system applying the management method according to any one of claims 1 to 4, characterized in that: include: Data collection module, tourist behavior prediction module, scenic spot equipment failure prediction module and strategy generation module; The data collection module is used to collect historical tourist behavior data, pre-process the historical tourist behavior data, and obtain pre-processed data; The tourist behavior prediction module is used to collect historical weather data and historical holiday data, build a behavior prediction model based on the pre-processed data, the weather data and the holiday data, and use the behavior prediction model to obtain a tourist behavior pattern prediction result; The scenic area equipment failure prediction module is used to collect historical operation status data and historical failure records of scenic area equipment, build an equipment failure prediction model based on the historical operation status data, the historical failure records, the weather data and the holiday data, and use the equipment failure prediction model to obtain equipment failure prediction results; The strategy generation module generates a tourist guidance strategy based on the tourist behavior pattern prediction result, and generates an equipment maintenance strategy based on the equipment failure prediction result.

6. A service management system for a smart scenic spot according to claim 5, characterized in that: The workflow of the data acquisition module includes: Cleaning the historical tourist behavior data, removing outliers and supplementing missing values ​​to obtain cleaned data; The cleaned data is standardized and normalized to obtain the preprocessed data.

7. According to claim 5, a service management system for a smart scenic spot is characterized in that: In the tourist behavior prediction module, the process of building a behavior prediction model includes: Standardizing the historical weather data and the historical holiday data to obtain a structured weather data set and a structured holiday data set; Analyze the historical tourist behavior data using a time series analysis algorithm to obtain tourist behavior characteristics, and use an association rule mining algorithm to analyze the correlation between the tourist behavior characteristics and the structured weather data set and the structured holiday data set to obtain behavior pattern influencing factors; The behavior prediction model is constructed based on the historical weather data, the historical holiday data and the behavior pattern influencing factors.

8. A service management system for a smart scenic spot according to claim 7, characterized in that: In the scenic area equipment failure prediction module, the process of building an equipment failure prediction model includes: Cleaning and normalizing the historical operating status data and the historical fault records of the scenic area equipment to obtain processed operating status data and processed fault records; Based on the processed operating status data and the processed fault records, a device fault prediction model is constructed using a decision tree algorithm.

Images