Grey dynamic tourism safety early warning method and system based on multi-source data fusion

Abstract

The invention provides a gray dynamic tourism safety early warning method and system based on multi-source data fusion, and belongs to the technical field of tourism safety risk early warning, and the method comprises the steps: collecting data related to tourism safety from a plurality of channels, and carrying out the preprocessing of the data to guarantee the quality and consistency of the data; based on the preprocessed data and the determined evaluation index, weight and risk early warning threshold, calculating a comprehensive evaluation result of the tourism safety risk through a grey system theory; and based on the comprehensive evaluation result of the tourism safety risk, determining a risk level, and generating a corresponding early warning signal. The invention aims to provide timely and accurate safety risk early warning information for tourists through the multi-level grey risk evaluation model and the early warning signal generation system, and the safety guarantee capability of the smart tourism service system is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of tourism safety risk warning, and particularly to a grey dynamic tourism safety warning method and system based on multi-source data fusion. Background Art

[0002] In the tourism business, accurate data monitoring and timely warning capabilities are crucial for effective management and decision-making. The lack of a tourism data monitoring and warning research and judgment system means that it is difficult to understand the changes and trends in the tourism market in real time, which will affect the tourism service system's ability to provide accurate predictions and decision-making support. It is also difficult to pre-detect potential risks and problems and unable to make timely adjustments and response measures.

[0003] Smart tourism enhances the tourism experience and service efficiency through information technology. However, in plateau mountain scenic areas such as Tibet, there are obvious deficiencies in the existing technology for tourism safety risk management. Due to the diverse landscapes, complex landforms, and variable climates in these areas, it is difficult to accurately predict tourism safety risks relying solely on traditional weather forecasts. Existing tourism risk warning systems mostly use static threshold division (such as fixed passenger flow thresholds) or single-index warnings (such as meteorological data). Using the traditional Analytic Hierarchy Process (AHP) relies on expert scoring to construct a judgment matrix, without considering the fuzziness of subjective judgments, which is prone to weight deviation; and it is unable to dynamically adjust the risk level according to real-time data, resulting in a high warning delay. The lack of a systematic and multi-level risk assessment and warning mechanism leads to the inability to effectively collect, analyze, and process data related to tourism safety, making it difficult to issue warning signals in a timely manner and increasing the safety risks of tourists. Summary of the Invention

[0005] The present invention provides a grey dynamic tourism safety warning method and system based on multi-source data fusion, aiming to provide timely and accurate safety risk warning information for tourists through a multi-level grey risk evaluation model and a warning signal generation system, and enhancing the safety guarantee ability of the smart tourism service system.

[0006] To achieve the above object, the present invention adopts the following technical solutions: This specification discloses a grey dynamic tourism safety warning method based on multi-source data fusion, including: Collect data related to tourism safety from multiple channels and preprocess the data to ensure data quality and consistency; Based on the preprocessed data, as well as the determined evaluation indicators, weights, and risk warning thresholds, calculate the comprehensive evaluation result of tourism safety risk through grey system theory; Based on the comprehensive evaluation result of tourism safety risk, determine the risk level and generate corresponding warning signals; Among them, the process of determining the evaluation indicators, weights, and thresholds is as follows: Select key indicators reflecting the risk level according to the tourism safety requirements to obtain the determined evaluation indicators; Use the analytic hierarchy process to determine the weights of each evaluation indicator; Set the risk warning thresholds for each evaluation indicator based on the weights.

[0007] In this specification, data is collected from channels such as tourism-related software, weather-related software, and navigation map-related software, and the collected data is cleaned, de-duplicated, and standardized to ensure the accuracy and consistency of the data.

[0008] In this specification, the warning signals are fed back to tourists.

[0009] In this specification, according to the feedback and requirements of users, the generation method, evaluation indicators, weights, or thresholds of the warning signals are adjusted and optimized.

[0010] In this specification, data related to tourism risks in the area to be warned is collected and preprocessed; According to the characteristics of tourism risks in the area to be warned, construct a hierarchical structure model; Based on the hierarchical structure model, use the analytic hierarchy process to determine the weights of each factor at each level; Based on the hierarchical structure model, construct a grey prediction model for each factor in the criterion layer and the scheme layer; Based on the grey prediction model, predict the tourism risks in the area to be warned to obtain the prediction results; Conduct a comprehensive evaluation based on the prediction results and weights to obtain the comprehensive risk score; Classify and evaluate the tourism risks in the area to be warned according to the comprehensive risk score.

[0011] In this specification, the data related to tourism risks in the area to be warned includes natural environment data, tourism facility data, social and economic data, tourist feedback data, and epidemic data.

[0012] In this specification, the hierarchical structure model includes an objective layer, a criterion layer, and a scheme layer. The objective layer is the comprehensive evaluation of tourism risks in the area to be warned. The criterion layer includes natural environment risks, tourism facility risks, social and economic risks, and tourist feedback risks. The scheme layer is a specific breakdown of each factor in the criterion layer.

[0013] In this specification, the differential equation form of the grey prediction model is: ; Among them, is the first-order cumulative generating sequence of the original data, and are the parameters to be estimated; Solve the parameters by the least squares method and , a prediction model is obtained.

[0014] In this specification, the parameters and are solved as follows: Let the original data sequence be , and the first-order accumulated generating sequence be ; Construct the data matrix and the constant term vector : ; Use the least squares method to solve the parameter vector : ; After obtaining the parameters and , the prediction model can be constructed: .

[0015] This specification also discloses a grey dynamic tourism safety early warning system based on multi-source data fusion, which is used to implement the grey dynamic tourism safety early warning method described in any one of the above, and the grey dynamic tourism safety early warning system based on multi-source data fusion includes: A data collection and preprocessing module, which is used to collect data related to tourism safety from multiple channels and preprocess the data to ensure data quality and consistency; A multi-level grey risk assessment model, which is used to calculate the comprehensive evaluation result of tourism safety risk through grey system theory based on the preprocessed data, as well as the determined evaluation indicators, weights, and risk early warning thresholds; An early warning signal generation module, which is used to determine the risk level based on the comprehensive evaluation result of tourism safety risk and generate corresponding early warning signals.

[0016] In summary, the present invention has at least the following beneficial effects: Hierarchical evaluation improves accuracy: Through the multi-level grey risk assessment model, various factors affecting tourism safety are comprehensively considered, improving the comprehensiveness and accuracy of risk assessment.

[0017] Real-time response enhances guarantee: The system has real-time data collection and processing functions, can quickly respond to changes in tourism safety conditions, and timely issue early warning signals to provide safety guarantees for tourists. Description of the Drawings

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0019] Figure 1 It is a schematic diagram of the tourism safety risk warning involved in the present invention.

[0020] Figure 2 It is a schematic diagram of the risk assessment process involved in the present invention.

[0021] Figure 3 It is a schematic diagram of the core architecture involved in the present invention. Detailed implementation manners

[0022] In the following, only some exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the embodiments of the present invention. Therefore, the accompanying drawings and the description are considered to be exemplary in nature rather than restrictive.

[0023] The following disclosure provides many different implementation manners or examples for implementing different structures of the embodiments of the present invention. To simplify the disclosure of the embodiments of the present invention, the components and settings of specific examples are described below. Of course, they are only examples and are not intended to limit the embodiments of the present invention. In addition, the embodiments of the present invention may repeat reference numerals and / or reference letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various implementation manners and / or settings discussed.

[0024] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0025] As Figure 1 shown, this embodiment discloses a grey dynamic tourism safety warning method based on multi-source data fusion, including: Collect data related to tourism safety from multiple channels and preprocess the data to ensure data quality and consistency; Based on the preprocessed data, as well as the determined evaluation indicators, weights, and risk warning thresholds, calculate the comprehensive evaluation result of the tourism safety risk through the grey system theory; Based on the comprehensive evaluation result of the tourism safety risk, determine the risk level and generate corresponding warning signals; Among them, the process of determining the evaluation indicators, weights, and thresholds is as follows: Select key indicators reflecting the risk level according to the tourism safety requirements to obtain the determined evaluation indicators; Use the analytic hierarchy process or the expert scoring method to determine the weights of each evaluation indicator; Set the risk warning threshold for each evaluation indicator based on the weights.

[0026] In some embodiments, collect data from channels such as tourism-related software, weather-related software, and navigation map-related software, and perform cleaning, deduplication, and standardization processing on the collected data to ensure the accuracy and consistency of the data.

[0027] In some embodiments, feedback the warning signal to tourists.

[0028] In some embodiments, adjust and optimize the generation method, evaluation indicators, weights, or thresholds of the warning signal according to the feedback and requirements of users.

[0029] In some embodiments, collect data related to tourism risks in the area to be warned and perform preprocessing; Construct a hierarchical structure model according to the characteristics of tourism risks in the area to be warned; Based on the hierarchical structure model, use the analytic hierarchy process to determine the weights of each level of factors; Based on the hierarchical structure model, construct a grey prediction model for each criterion layer and scheme layer factor; Based on the grey prediction model, predict the tourism risks in the area to be warned to obtain the prediction results; Conduct a comprehensive evaluation according to the prediction results and weights to obtain the comprehensive risk score; Classify and evaluate the tourism risks in the area to be warned according to the comprehensive risk score.

[0030] In some embodiments, the data related to tourism risks in the area to be warned includes natural environment data, tourism facility data, social and economic data, tourist feedback data, and epidemic data.

[0031] In some embodiments, the hierarchical structure model includes an objective layer, a criterion layer, and a scheme layer. The objective layer is the comprehensive evaluation of tourism risks in the area to be warned. The criterion layer includes natural environment risks, tourism facility risks, social and economic risks, and tourist feedback risks. The scheme layer is a specific breakdown of each factor in the criterion layer.

[0032] In some embodiments, the differential equation form of the grey prediction model is: ; Wherein, is the first-order accumulated generating sequence of the original data, and are the parameters to be estimated; Solve the parameters by the least squares method and , a prediction model is obtained.

[0033] In some embodiments, the parameters and The solution process is as follows: Let the original data sequence be , and the first-order accumulated generating sequence be ; Construct the data matrix and the constant term vector : ; Use the least squares method to solve the parameter vector : ; After obtaining the parameters and , the prediction model can be constructed: .

[0034] This embodiment discloses a grey dynamic tourism safety early warning system based on multi-source data fusion, which is used to implement the grey dynamic tourism safety early warning method described in any one of the above. The grey dynamic tourism safety early warning system based on multi-source data fusion includes: A data collection and preprocessing module, which is used to collect data related to tourism safety from multiple channels and preprocess the data to ensure data quality and consistency; A multi-level grey risk evaluation model, which is used to calculate the comprehensive evaluation result of tourism safety risk through grey system theory based on the preprocessed data, as well as the determined evaluation indicators, weights, and risk early warning thresholds; An early warning signal generation module, which is used to determine the risk level based on the comprehensive evaluation result of tourism safety risk and generate corresponding early warning signals.

[0035] The technical concept of the technical solution of the present invention is as follows: Taking the Tibet region as an example, a tourism safety risk early warning system and method for the Tibet region are proposed, aiming to provide timely and accurate safety risk early warning information for tourists through a multi-level grey risk evaluation model and an early warning signal generation system, and enhance the safety guarantee ability of the intelligent tourism service system. As Figure 1 shown, it shows the core process of the system, including key links such as data collection and preprocessing, multi-level grey risk evaluation model, risk early warning, service API, etc.

[0036] (1) Multi-level grey tourism risk evaluation model The multi-level grey risk assessment method is a method that comprehensively uses qualitative and quantitative data for risk assessment. This method takes into account uncertain factors, subjective factors, and objective factors, and comprehensively evaluates the degree and impact of tourism risks through multi-level evaluations. The tourism industry involves risks in multiple aspects, such as the social environment (e.g., sociocultural factors), natural environment (e.g., climate and seasons, geology and terrain, weather, etc.), safety, transportation (e.g., congestion), safety management measures (e.g., tourism planning and management, safety facilities and services), tourism accident data, tourist preference factors, etc. And most factors are difficult to quantify, and even the information of some risk factors is extremely difficult to obtain, showing a high degree of grey nature. Therefore, it is proposed to use the multi-level grey evaluation method to construct a tourism risk assessment model.

[0037] This method combines the advantages of the analytic hierarchy process and the evaluation based on grey system theory. Using the multi-level grey risk assessment method, these factors can be taken into account, and risks can be comprehensively evaluated through evaluation indicators at different levels. The risk assessment process is divided into multiple levels, each level contains different evaluation indicators, and analysis is carried out according to different data sources and evaluation methods, fully considering the mutual relationships and mutual influences between different factors to provide a more comprehensive and accurate risk assessment result.

[0038] The risk assessment process is realized through the following 8 steps: ① Analyze the evaluation object and construct a multi-level evaluation index; ② Establish a method for comparing the importance of evaluation indicators and determine the weights of evaluation indicators; ③ Determine the scoring grade standard of evaluation indicators; ④ Establish an evaluation sample matrix; ⑤ Determine the grey classes of evaluation and the risk grade standard; ⑥ Calculate the grey evaluation coefficient; ⑦ Calculate the grey evaluation weight vector and construct a weight matrix; ⑧ Calculate the comprehensive evaluation value of the evaluation object. The process is as Figure 2 shown.

[0039] Among them, grey relational analysis dynamically and quantitatively measures the degree of association between factors in a grey system according to the similarity of the development trends (correlation degrees) between factors. Using the grey relational degree calculation method to calculate the degree of association between each evaluation indicator, the contribution degree of each indicator to tourism safety risks can be obtained. Based on the grey relational degree calculation results, risk assessment is carried out to obtain the comprehensive evaluation value.

[0040] Model operation steps: Data collection and preprocessing: Collect data related to tourism risks in the Tibet region and conduct preprocessing.

[0041] Construct a hierarchical structure model: According to the characteristics of tourism risks in the Tibet region, construct a hierarchical structure model.

[0042] Determine weights: Use the analytic hierarchy process to determine the weights of factors at each level.

[0043] Build a grey prediction model: Build a GM(1,1) model for each factor in the criterion layer and the scheme layer, and solve the parameters.

[0044] Comprehensive evaluation: Conduct a comprehensive evaluation based on the prediction results and weights to obtain the comprehensive risk score.

[0045] Risk classification and evaluation: Classify and evaluate the tourism risks in the Tibet region according to the comprehensive risk score.

[0046] (2)Construction of a multi-level grey warning model Step S1: Data collection and preprocessing In the classification and evaluation of tourism risks in the Tibet region, the following types of data are to be collected: Natural environment data: Such as real-time meteorological data (temperature, humidity, rainfall, wind speed, etc.), geological data (historical records of natural disasters such as earthquakes, mudslides, landslides, etc.).

[0047] Tourism facility data: Such as the number of hotels, the condition of scenic spot facilities, transportation conditions, etc.

[0048] Socio-economic data: Such as the number of tourists, tourism revenue, local economic development level, etc.

[0049] Tourist feedback data: Such as tourist satisfaction surveys, complaint records, etc.

[0050] Epidemic data: Such as news reports on influenza A infections, etc.

[0051] Preprocess the collected data, including steps such as data cleaning, standardization, and normalization, for subsequent analysis.

[0052] Step S2: Build a hierarchical structure model According to the characteristics of tourism risks in the Tibet region, build a hierarchical structure model. The model usually includes an objective layer, a criterion layer, and a scheme layer.

[0053] Objective layer: Comprehensive evaluation of tourism risks in the Tibet region; Criterion layer: Includes natural environment risks, tourism facility risks, socio-economic risks, tourist feedback risks, etc.; Scheme layer: Is a specific breakdown of each factor in the criterion layer.

[0054] Step S3: Determine the weights Use the analytic hierarchy process to determine the weights of each layer of factors. Through steps such as constructing a judgment matrix, calculating the eigenvector, and consistency test, obtain the weights of each factor.

[0055] Step S4: Grey prediction model construction For each criterion layer and alternative layer factor, a grey prediction model (such as the GM(1,1) model) is constructed. The GM(1,1) model is a first-order single-variable grey prediction model, and its differential equation form is: ; where is the first-order accumulated generating sequence of the original data, and are the parameters to be estimated.

[0056] The parameters and are solved by the least squares method to obtain the prediction model. Then, this model is used to predict future data.

[0057] Step S5: Comprehensive evaluation Based on the prediction results obtained from the grey prediction model and the weights determined by the analytic hierarchy process, a comprehensive evaluation is carried out. The risk scores of each factor are calculated, and the weighted sum is used to obtain the comprehensive risk score. The tourism risks in the Tibet region are classified and evaluated according to the comprehensive risk score.

[0058] Formula derivation: Taking the GM(1,1) model as an example, the process of solving its parameters is as follows: Let the original data sequence be , and the first-order accumulated generating sequence be ; Construct the data matrix and the constant term vector : ; Use the least squares method to solve the parameter vector : ; After obtaining the parameters and , the prediction model can be constructed: .

[0059] Tibet tourism safety risk early warning model: 1) Determine the risk level classification criteria; The specific classification of tourism risk levels may vary according to different requirements and evaluation systems. The tourism risk levels are classified into the following levels: Low risk: It indicates that the risk of tourism activities is relatively low, and it has little impact on the safety and comfort of tourists. At the low-risk level, all aspects of the tourist destination or tourism activities meet the basic safety standards, and tourists can carry out tourism activities normally without special attention to risk issues.

[0060] Medium risk: indicates that tourism activities have certain risks and may have a certain degree of impact on the safety and comfort of tourists. At the medium risk level, there may be some risk factors in certain aspects of the tourist destination or tourism activities. Tourists need to pay attention to safety tips and take corresponding precautions to reduce risks.

[0061] High risk: indicates that the tourist activity has a higher risk level and may have a greater impact on the safety and comfort of tourists. At the high risk level, there are more potential risk factors in certain aspects of the tourist destination or tourist activities. Tourists need to carefully assess the risks and take adequate safety measures, or consider canceling or changing their travel plans if necessary.

[0062] Very high risk: The very high risk level indicates that there is a very high risk level in tourist activities, which may have a serious impact on the safety and comfort of tourists. At the very high risk level, there are serious safety hazards in many aspects of the tourist destination or tourist activities, and tourists may face serious risks to life and property. In this case, tourists need to strictly follow local warnings and instructions, prioritize personal safety, and try to avoid tourist activities.

[0063] 2) Establish a mapping relationship between evaluation value and risk level; Based on the multi-level grey tourism risk assessment model, the comprehensive risk assessment value (0-100) can be obtained, and the assessment value interval of each risk level can be determined according to the range of the assessment value and the corresponding risk level. For example: set the low risk interval to 0-25, the medium risk interval to 26-50, the high risk interval to 51-75, and the extremely high risk interval to 76-100. The comprehensive risk assessment value obtained by the model is compared and mapped with the pre-set risk level range to determine its corresponding risk level (for example: if the assessment value is 32, it falls into the medium risk interval, so the corresponding risk level is medium risk), which helps decision makers and relevant departments to quickly understand the current tourism risk level and take corresponding measures and early warning actions.

[0064] The grey dynamic tourism safety early warning system based on multi-source data fusion includes the following key modules: 1. Data acquisition and preprocessing module This module is responsible for collecting tourism safety-related data from channels such as weather, transportation, Ctrip, and Amap, and preprocessing it to ensure the quality and consistency of the data. The preprocessing process includes steps such as data cleaning, format conversion, and missing value processing.

[0065] 2. Warning signal generation module This module establishes the mapping relationship between the evaluation value and the risk level according to the risk level classification criteria, and generates corresponding warning signals. First, determine the risk level classification criteria, such as low risk, medium risk, high risk, etc.; then, establish the mapping relationship between the evaluation value and these risk levels; finally, generate corresponding warning signals according to the real-time evaluation results, such as green, yellow, red, etc.

[0066] 3. Multi-level Grey Risk Evaluation Model This module uses the multi-level grey risk evaluation model to evaluate tourism safety. First, determine the evaluation indicators, such as weather conditions, traffic conditions, scenic spot safety, etc.; then, determine the weights according to the importance of each indicator; next, determine the thresholds of each indicator to distinguish different risk levels; finally, calculate the evaluation results according to the collected data and the determined weights and thresholds to obtain the tourism safety risk level.

[0067] Among them, the warning signals are fed back to users through the intelligent tourism service system to remind users of the safety risk situation of the current tourism destination.

[0068] The data collection and preprocessing module includes: The data collection unit is used to collect data from channels such as Ctrip, weather information, and Amap. The data preprocessing unit is used to clean, de-duplicate, standardize, etc. the data to ensure the accuracy and consistency of the data.

[0069] The multi-level grey risk evaluation model includes: The evaluation index determination unit is used to select key indicators reflecting the risk level according to the tourism safety requirements. The weight determination unit is used to determine the weights of each evaluation index by using the analytic hierarchy process or the expert scoring method. The threshold determination unit is used to set the risk warning thresholds of each evaluation index. The evaluation result calculation unit is used to calculate the comprehensive evaluation result of the tourism safety risk through the grey system theory.

[0070] The warning signal generation module includes: The risk level determination unit is used to determine the risk level according to the output result of the multi-level grey risk evaluation model. The warning signal generation unit is used to generate corresponding warning signals according to the determined risk level. The warning signal feedback unit is used to feed back the generated warning signals to users through the intelligent tourism service system.

[0071] The grey dynamic tourism safety early warning system based on multi-source data fusion further includes a user feedback mechanism, which is used to adjust and optimize the generation method, evaluation indicators, weights or thresholds of early warning signals according to users' feedback and requirements.

[0072] Technical effects: 1. Improved accuracy through multi-level assessment: By using a multi-level grey risk assessment model, various factors affecting tourism safety are comprehensively considered, improving the comprehensiveness and accuracy of risk assessment.

[0073] 2. Enhanced guarantee with real-time response: The system has real-time data collection and processing functions, can quickly respond to changes in tourism safety conditions, and issue early warning signals in a timely manner to provide safety guarantees for tourists.

[0074] 3. Seamless connection to the smart tourism system: The system of the present invention can be seamlessly connected to the smart tourism service system, and provides safety risk early warning information to users through a unified interface, enhancing the overall function and user experience of smart tourism services.

[0075] As Figure 3 shown, based on large language model (LLM) technology, the grey dynamic tourism safety early warning system based on multi-source data fusion is applied. The core architecture consists of a front-end display layer, an application system layer, a data service layer, a network transmission layer, and a local tourism knowledge base. The front-end display layer covers mobile terminals, WEB browsers, and large-screen visualizations, providing an intuitive operation interface. The application system layer integrates functions such as monitoring and early warning, emergency handling, intelligent search, and intention recognition, and uses Prompt engineering to optimize LLM intelligent generation to achieve precise services. The data service layer relies on Wi-Fi, 5G, and Internet technologies to ensure high-speed data transmission and real-time processing. The network transmission layer guarantees stable data transmission and stable operation of the system. The local tourism knowledge base integrates multi-dimensional information such as weather, traffic, and scenic spots, providing comprehensive support for the system.

[0076] Innovatively applying large language model (LLM) technology to smart tourism, realizing intelligent recommendation of tourism information and intelligentization of early warning and emergency response, significantly enhancing tourism experience and safety. By integrating diverse data and advanced network technologies, this system is at the forefront of the industry, demonstrating outstanding innovation and practical value, and setting a technical benchmark for the field of smart tourism.

[0077] The above-described embodiments are used to illustrate the present invention, not to limit the present invention. Therefore, changes in the exemplified numerical values or replacement of equivalent elements still belong to the scope of the present invention.

[0078] From the above detailed description, those of ordinary skill in the art can clearly understand that the present invention can indeed achieve the aforementioned objectives and has met the requirements of the patent law.

[0079] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included within the protection scope of the present invention.

[0080] It should be noted that the above description of the process is only for illustration and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various corrections and changes can be made to the process under the guidance of this specification. However, these corrections and changes are still within the scope of this specification.

[0081] The basic concept has been described above. Obviously, for those of ordinary skill in the art after reading this application, the above invention disclosure is only an example and does not constitute a limitation to this application. Although not explicitly stated here, those of ordinary skill in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are proposed in this application, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this application.

[0082] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned two or more times in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0083] In addition, those of ordinary skill in the art can understand that various aspects of this application can be described and illustrated by several patentable types or situations, including any new and useful process, machine, product, or combination of substances, or any new and useful improvement thereof. Therefore, various aspects of this application can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software can be referred to as "unit", "module", or "system". In addition, various aspects of this application can take the form of a computer program product embodied in one or more computer-readable media, in which computer-readable program code is included.

[0084] The computer program code required for the operations of various parts of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C programming language, VisualBasic, Fortran2103, Perl, COBOL2102, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages. This program code can run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., through the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0085] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this application are not used to limit the order of the processes and methods of this application. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this application. For example, although the implementation of the above various components can be embodied in a hardware device, it can also be implemented as a pure software solution, for example, installation on an existing server or mobile device.

[0086] Similarly, it should be noted that, in order to simplify the description of this application disclosure and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this application, sometimes multiple features are merged into one embodiment, drawing or description thereof. However, this method of this application should not be construed as reflecting the intention that the claimed subject matter requires more features than those clearly recited in each claim. On the contrary, the subject matter of the invention should have fewer features than the above single embodiment.

Claims

1. A grey dynamic tourism safety early warning method based on multi-source data fusion is characterized by: include: Collect tourism safety-related data from multiple channels and pre-process the data to ensure data quality and consistency; Based on the pre-processed data, as well as the determined evaluation indicators, weights and risk warning thresholds, the comprehensive evaluation results of tourism safety risks are calculated through the grey system theory; Based on the comprehensive evaluation results of tourism safety risks, determine the risk level and generate corresponding early warning signals; The process of determining the evaluation indicators, weights and thresholds is as follows: According to tourism safety needs, key indicators reflecting risk levels are selected to obtain determined evaluation indicators; Using the analytic hierarchy process, determine the weight of each evaluation index; Set the risk warning threshold of each evaluation indicator based on the weight.

2. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 1 is characterized in that: Collect data from channels such as tourism-related software, weather-related software, traffic-related software, geological disaster-related software, and navigation map-related software, and clean, deduplicate, and standardize the collected data to ensure its accuracy and consistency.

3. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 1 is characterized in that: Feedback early warning signals to tourists.

4. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 1 is characterized in that: Based on user feedback and needs, the generation method, evaluation indicators, weights or thresholds of warning signals are adjusted and optimized.

5. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 1 is characterized in that: Collect data related to tourism risks in the areas to be warned and conduct pre-processing; According to the characteristics of tourism risks in the areas to be warned, a hierarchical model is constructed; Based on the hierarchical model, the analytic hierarchy process is used to determine the weights of factors at each level; Based on the hierarchical model, a grey prediction model is constructed for each criterion layer and scheme layer factor; Based on the grey prediction model, the tourism risk in the warning area is predicted and the prediction results are obtained; Perform a comprehensive assessment based on the prediction results and weights to obtain a comprehensive risk score; Tourism risks in the warning areas are classified and assessed based on the comprehensive risk scores.

6. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 5 is characterized in that: The tourism risk-related data in the areas to be warned include natural environment data, tourism facilities data, socio-economic data, tourist feedback data and epidemic data.

7. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 5 is characterized in that: The hierarchical model includes the target layer, the criterion layer and the plan layer. The target layer is a comprehensive assessment of tourism risks in the areas to be warned. The criterion layer includes natural environment risks, tourism facility risks, socio-economic risks and tourist feedback risks. The plan layer is a specific subdivision of the factors in the criterion layer.

8. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 5 is characterized in that: The differential equation form of the grey prediction model is: ； in, Generate a sequence for a one-time accumulation of the original data, and is the parameter to be estimated; Solving for parameters using the least squares method and , and obtain the prediction model.

9. The grey dynamic tourism safety early warning method based on multi-source data fusion according to claim 8 is characterized in that: parameter and The solution process is as follows: Assume the original data sequence is , the cumulative sequence generated once is ; Constructing the data matrix and constant term vector : ； Solve for the parameter vector using the least squares method : ； Get parameters and After that, you can build a prediction model: 。 10. The grey dynamic tourism safety early warning system based on multi-source data fusion is characterized by: Used to implement the gray dynamic tourism safety early warning method based on multi-source data fusion according to any one of claims 1 to 9, the gray dynamic tourism safety early warning system based on multi-source data fusion comprises: Data collection and preprocessing module, which is used to collect tourism safety-related data from multiple channels and preprocess the data to ensure data quality and consistency; A multi-level grey risk assessment model is used to calculate the comprehensive evaluation results of tourism safety risks through grey system theory based on pre-processed data, as well as determined evaluation indicators, weights and risk warning thresholds; The early warning signal generation module is used to determine the risk level based on the comprehensive evaluation results of tourism safety risks and generate corresponding early warning signals.

Images