Document travel management system based on data analysis

Abstract

The invention relates to the technical field of document travel management, and discloses a document travel management system based on data analysis. By introducing a risk event sample generation technology based on data analysis, a selection rule setting mechanism, a graph structure modeling technology and a dynamic risk assessment method, the travel management system can generate more diversified risk event samples on the basis of limited historical data, and the risk event samples can be evaluated through real-time data processing and dynamic adjustment. And comprehensive monitoring and accurate prediction of historical risk events are realized. Specifically, the system not only can effectively cope with important emergencies with large risks, but also can dynamically adjust risk assessment results according to factors such as real-time weather conditions, traffic conditions and tourist flow, and provides more accurate management and decision support. Besides, the system can provide accurate risk values at different time points by constructing a static risk index and a dynamic risk function, and generates corresponding management suggestions according to the risk values.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural and tourism management, and particularly to a cultural and tourism management system based on data analysis. Background Art

[0002] With the rapid development of information technology, the cultural and tourism industry has accumulated a large amount of data resources, including tourists' behavior data, scenic spot operation data, comments on social media, etc. These data have the characteristics of large volume (Volume), variety (Variety), high velocity (Velocity), and low value density (Value), namely the so-called "4V" characteristics. In order to effectively process and utilize these data, the cultural and tourism management system needs to rely on big data technologies such as distributed computing frameworks like Hadoop and Spark, as well as NoSQL databases to store and manage unstructured data.

[0003] However, in the cultural and tourism industry, due to the diversity and complexity of data, traditional data analysis methods face many challenges. First of all, historical data often lacks important events with relatively high risks, such as unexpected events (such as natural disasters, public health crises) or extreme tourism activities (such as large-scale festivals, temporary exhibitions). Although the occurrence frequency of these events is relatively low, they have a significant impact on scenic spot management and tourist safety. Since these events appear less frequently in historical data, traditional statistical analysis methods are difficult to extract effective patterns and rules from them, resulting in insufficient prediction and response capabilities of the system when facing similar situations.

[0004] Secondly, the dynamic and real-time nature of data requires the system to be able to quickly respond to changing environments. For example, factors such as weather conditions, traffic conditions, and tourist flows change in real time, and these changes may quickly affect the occurrence probability and propagation path of historical risk events. Therefore, how to obtain and process these real-time data in a timely manner has become the key to improving the calculation of risk values. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a cultural and tourism management system based on data analysis, including:

[0006] An original data acquisition module: used to acquire tourists' behavior data, scenic spot operation data, and external environment data, and obtain original data from the tourists' behavior data, scenic spot operation data, and external environment data;

[0007] A risk event sample data acquisition module: connected to the original data acquisition module, used to set selection rules for the conditional generative adversarial network, select input conditions according to the selection rules, and generate risk event sample data according to the input conditions; The risk event sample data acquisition module includes the following sub-modules:

[0008] Selection rule setting sub-module: used to set selection rules for the conditional generative adversarial network;

[0009] The selection rule setting sub-module includes the following units:

[0010] Event condition determination unit: used to obtain historical risk events and determine event conditions based on historical risk events;

[0011] Historical risk event probability calculation unit: used to calculate historical risk event probabilities based on each event condition and historical risk events;

[0012] Historical risk event frequency calculation unit: used to calculate historical risk event frequencies based on each event condition and historical risk events;

[0013] Historical risk event propagation path probability calculation unit: used to calculate historical risk event propagation path probabilities;

[0014] Selection rule formulation unit: used to construct a selection rule function based on historical risk event probabilities, historical risk event frequencies, and historical risk event propagation path probabilities, and formulate selection rules according to the selection rule function;

[0015] Input condition selection sub-module: used to select input conditions according to the selection rules;

[0016] Risk event sample data generation sub-module: used to input input conditions into the conditional generative adversarial network to generate risk event sample data;

[0017] Data integration module: connected to the risk event sample data acquisition module and the original data acquisition module, used to integrate risk event sample data with the original data to obtain extended data;

[0018] Risk value calculation module: connected to the data integration module, used to calculate the static risk index for the extended data; construct a dynamic risk function based on the static risk index; obtain real-time data, and calculate the risk value of the real-time data according to the dynamic risk function;

[0019] Management suggestion generation module: connected to the risk value calculation module, used to generate management suggestions according to the risk value.

[0020] Furthermore, the historical risk event propagation path probability calculation unit includes the following sub-units:

[0021] Graph structure modeling sub-unit: used to define scenic spots, transportation stations, and accommodation facilities in the scenic area as nodes using a graph neural network, and determine the walking paths of tourists as edges;

[0022] Propagation probability matrix construction subunit: used to obtain historical normal events, obtain the probability of historical risk events spreading from the current node to other nodes based on historical normal events and historical risk events, and obtain the propagation probability matrix according to the probability of historical risk events spreading from the current node to other nodes;

[0023] External factor comprehensive function construction subunit: used to obtain the weather condition index, traffic congestion index, geographical feature index, and population density index from the current node to other nodes, and construct an external factor comprehensive function based on the weather condition index, traffic congestion index, geographical feature index, and population density index from the current node to other nodes to obtain the external factor comprehensive value;

[0024] Historical risk event propagation path probability calculation subunit: used to calculate the historical risk event propagation path probability based on the probability of historical risk events spreading from the current node to other nodes and the external factor comprehensive value.

[0025] Further, the event condition corresponding to the maximum value of the selection rule function is used as the input condition.

[0026] Further, the event conditions include timestamp, geographical location, population density, traffic conditions, weather conditions, and event type.

[0027] Further, the static risk index is the historical risk event probability of each historical risk event under each event condition.

[0028] Further, obtain the parameter values of the event conditions in the real-time data, determine the parameter reference values of the event conditions according to the historical risk events, and obtain the risk value according to the static risk index, the parameter values of the event conditions in the real-time data, and the parameter reference values of the event conditions.

[0029] Further, the calculation formula for the historical risk event propagation path probability is:

[0030]

[0031] In the formula, P i is the propagation path probability of the i-th historical risk event, I h (K, L) is the external factor comprehensive value of the h-th external factor between the K-th node and the L-th node, H is the set of all external factors, P KL is the probability of the i-th historical risk event spreading from the K-th node to the L-th node, and n represents the total number of nodes between the current node and other nodes.

[0032] Further, the selection rule function is:

[0033]

[0034] Wherein, C is the selection rule function, and P(E i |F j ) is the historical risk probability of the occurrence of the i-th historical risk event under the condition of the j-th event in the historical risk events, is the historical risk event frequency of the occurrence of the i-th historical risk event under the condition of the j-th event in the historical risk events, and P i is the propagation path probability of the i-th historical risk event.

[0035] Furthermore, the calculation formula of the risk value is:

[0036]

[0037] Wherein, G is the risk value, and P(E i |F j ) is the historical risk event probability of the occurrence of the i-th historical risk event under the condition of the j-th event in the historical risk events, x t is the parameter value of the t-th event condition in the real-time data, X0 is the parameter reference value of the event condition, and k is the adjustment coefficient.

[0038] The embodiments of the present invention have the following technical effects:

[0039] By introducing the historical risk event sample generation technology based on data analysis, the selection rule setting mechanism, the graph structure modeling technology and the dynamic risk assessment method, this cultural and tourism management system can generate more diverse historical risk event samples based on limited historical data, and through real-time data processing and dynamic adjustment, achieve comprehensive monitoring and accurate prediction of historical risk events. Specifically, the system can not only effectively cope with important emergencies with relatively high risks, but also dynamically adjust the risk assessment results according to factors such as real-time weather conditions, traffic conditions, and tourist flows, providing more accurate management and decision-making support. In addition, by constructing a static risk index and a dynamic risk function, the system can provide accurate risk values at different time points, and generate corresponding management suggestions according to the risk values, helping scenic area management personnel take timely measures to ensure the safety of tourists and the normal operation of the scenic area. Finally, this comprehensive data processing solution not only improves the intelligent level of the system, but also significantly enhances the risk management ability of the cultural and tourism industry, promoting the sustainable development of the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0041] Figure 1 It is a schematic structural diagram of a cultural and tourism management system based on data analysis provided by an embodiment of the present invention. Detailed implementation manners

[0042] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope protected by the present invention.

[0043] Figure 1 It is a schematic structural diagram of a cultural and tourism management system based on data analysis provided by an embodiment of the present invention. Refer to Figure 1 , specifically including:

[0044] Original data acquisition module: used to acquire tourist behavior data, scenic spot operation data and external environment data, and obtain original data from the tourist behavior data, scenic spot operation data and external environment data.

[0045] Risk event sample data acquisition module: connected to the original data acquisition module, used to set selection rules for the conditional generative adversarial network, select input conditions according to the selection rules, and generate risk event sample data according to the input conditions.

[0046] The risk event sample data acquisition module includes the following sub-modules:

[0047] Selection rule setting sub-module: used to set selection rules for the conditional generative adversarial network.

[0048] The selection rule setting sub-module includes the following units:

[0049] Event condition determination unit: used to obtain historical risk events and determine event conditions according to the historical risk events.

[0050] The historical risk events include but are not limited to: natural disasters, infectious diseases, food safety, fires, crowd stampedes, traffic accidents, public security incidents, terrorist attacks, equipment failures, etc.

[0051] The event conditions include timestamp, geographical location, population density, traffic conditions, weather conditions, event type.

[0052] Historical risk event probability calculation unit: used to calculate historical risk event probabilities according to each event condition and historical risk events.

[0053] The historical risk event propagation path probability calculation unit includes the following sub-units:

[0054] Graph structure modeling subunit: It is used to define scenic spots, transportation stations, and accommodation facilities in the scenic area as nodes by using a graph neural network, determine the walking paths of tourists as edges, and model the graph structure according to the nodes and edges.

[0055] Propagation probability matrix construction subunit: It is used to obtain historical normal events, obtain the probability that a historical risk event spreads from the current node to other nodes according to the historical normal events and historical risk events, and obtain the propagation probability matrix according to the probability that a historical risk event spreads from the current node to other nodes.

[0056] External factor comprehensive function construction subunit: It is used to obtain the weather condition index, traffic congestion index, geographical feature index, and population density index from the current node to other nodes, and construct an external factor comprehensive function according to the weather condition index, traffic congestion index, geographical feature index, and population density index from the current node to other nodes to obtain the external factor comprehensive value.

[0057] In this embodiment, the weather conditions are preferably rainfall, wind speed, and temperature, and the weather condition index is obtained based on the rainfall index, wind speed index, and temperature index:

[0058] Rainfall index: Obtain the maximum rainfall from historical risk events, obtain the average rainfall from the Kth node to the Lth node, and divide it by the maximum rainfall to obtain the rainfall index.

[0059] Wind speed index: Obtain the wind speed threshold that causes the event to spread rapidly from historical risk events, obtain the average wind speed from the Kth node to the Lth node, and obtain the wind speed index wind(K, L) according to the average wind speed and the wind speed threshold:

[0060]

[0061] Temperature index: Define the temperature within the normal range as the reference temperature, obtain the temperature threshold that causes the event to spread rapidly from historical risk events, obtain the average temperature from the Kth node to the Lth node, and calculate the temperature index T(K, L) according to the average temperature, the reference temperature, and the temperature threshold:

[0062]

[0063] Add the above temperature index, wind speed index, and rainfall index to obtain the external factor comprehensive function and the external factor comprehensive value.

[0064] Historical risk event frequency calculation subunit: It is used to calculate the historical risk event frequency according to each event condition and historical risk events.

[0065] Historical risk event propagation path probability calculation unit: used to calculate the historical risk event propagation path probability based on the probability of the historical risk event propagating from the current node to other nodes and the comprehensive value of external factors.

[0066]

[0067] In the formula, P i is the propagation path probability of the i-th historical risk event, I h (K, L) is the comprehensive value of the h-th external factor between the K-th node and the L-th node, H is the set of all external factors, P KL is the probability of the i-th historical risk event propagating from the K-th node to the L-th node, and n represents the total number of nodes between the current node and other nodes.

[0068] Calculating the historical risk event propagation path probability through this formula can more accurately evaluate and predict the propagation possibility of historical risk events between different nodes. Specifically, this formula comprehensively considers the propagation probability of historical risk events from the current node to other nodes, the comprehensive influence of external factors, and the frequency of historical risk events. This multi-factor comprehensive evaluation method can effectively improve the accuracy of prediction, help decision-makers better identify high-risk areas and key propagation paths, so as to take targeted preventive measures and reduce potential risk losses.

[0069] Selection rule formulation unit: used to construct a selection rule function based on the historical risk event probability, historical risk event frequency, and historical risk event propagation path probability, and formulate selection rules according to the selection rule function.

[0070] The main function of the selection rule is to determine which event conditions are most likely to trigger historical risk events and provide a basis for the subsequent generation of historical risk event samples. By constructing a selection rule function, the system can quantify the risk levels under different event conditions and select the most representative event conditions as input conditions based on these quantification results. This helps to ensure that the generated historical risk event samples are more in line with the actual situation, improve the prediction accuracy and response ability of the system. In practical applications, there are various types of historical risk events faced by scenic spots, and the occurrence conditions of each event are also different. Without selection rules, the system may generate a large number of historical risk event samples that do not conform to the actual situation, resulting in poor model training effects and even overfitting phenomena. By introducing selection rules, the system can screen out the scenarios most likely to trigger historical risk events according to historical data and current environmental conditions, so as to generate more representative and practical sample data.

[0071]

[0072] where C is the selection rule function, P(E i |F j ) is the historical risk event probability of the i-th historical risk event occurring under the condition of the j-th event in historical risk events, is the historical risk event frequency of the i-th historical risk event occurring under the condition of the j-th event in historical risk events, P i is the propagation path probability of the i-th historical risk event.

[0073] Input conditions refer to the specific parameters used to generate historical risk event samples. Different event conditions have a significant impact on the occurrence probability and influence range of historical risk events. For example, the occurrence probability of flood events is higher under rainy weather, while the risk of stampede events is greater in cases of high population density. By selecting the input conditions most likely to trigger historical risk events, the system can generate more diverse and realistic historical risk event samples.

[0074] Input condition selection sub-module: used to select input conditions according to the selection rule.

[0075] Take the event condition corresponding to the maximum value of the selection rule function as the input condition.

[0076] The input condition is:

[0077] where is to take the event condition when the selection rule function reaches the maximum value as the input condition, and Z is the event set.

[0078] Through the collaborative work of the selection rule formulation unit and the input condition selection sub-module, the system can construct a selection rule function based on the probability, frequency of historical risk events, and event propagation path probability, and select the input conditions most likely to trigger historical risk events. This not only helps generate more diverse and realistic historical risk event samples, but also improves the prediction accuracy and response ability of the system, helps scenic area managers better identify high-risk areas and key propagation paths, and take effective preventive measures to ensure the safety of tourists and the normal operation of the scenic area.

[0079] Risk event sample data generation sub-module: used to input the input conditions into the conditional generative adversarial network to generate risk event sample data.

[0080] The conditional generative adversarial network consists of a generator and a discriminator. The task of the generator is to generate realistic risk event sample data based on input conditions. It receives a random noise vector and a set of input conditions, and outputs a historical risk event sample similar to the real data distribution. The task of the discriminator is to distinguish between the generated samples and the real historical risk event samples. It receives a sample and the corresponding conditions, and outputs a probability value indicating the probability that the sample is real data. The generator generates a batch of fake samples based on the input conditions and the random noise vector. The discriminator receives the generated fake samples and the real samples, and outputs the probability that each sample is real data. According to the output of the discriminator, the parameters of the generator and the discriminator are updated so that the generator can generate more realistic samples, while the discriminator can more accurately identify true and false samples. After multiple rounds of adversarial training, the generator gradually learns to generate realistic historical risk event samples. At this time, the trained generator can be used to generate new risk event sample data according to the input conditions. The event condition corresponding to the maximum value of the selection rule function is used as the input condition and input into the generator to generate risk event sample data that meets this condition.

[0081] Data integration module: Connected to the risk event sample data acquisition module and the original data acquisition module, it is used to integrate the risk event sample data with the original data to obtain extended data.

[0082] Risk value calculation module: Connected to the data integration module, it is used to calculate the static risk index for the extended data; construct a dynamic risk function based on the static risk index; obtain real-time data, and calculate the risk value of the real-time data according to the dynamic risk function.

[0083] The static risk index is the historical risk event probability of each historical risk event under each event condition.

[0084] Obtain the parameter values of the event conditions in the real-time data, determine the parameter reference values of the event conditions according to the historical risk events, and obtain the risk value according to the static risk index, the parameter values of the event conditions in the real-time data, and the parameter reference values of the event conditions.

[0085] The parameter reference value is determined according to the average value or typical value under the same event condition in the historical data. For example: Population density: The reference value can be the average population density of this area in the historical data. Traffic conditions: The reference value can be the average traffic flow of this area in the historical data. Weather conditions: The reference value can be the average rainfall or temperature of this area in the historical data.

[0086]

[0087] Where G is the risk value, P(E i |F j) is the historical risk event probability of the i-th historical risk event occurring under the j-th event condition in the historical risk event, x t is the parameter value of the tth event condition in the real-time data, X0 is the parameter reference value of the event condition, and k is the adjustment coefficient.

[0088] Management suggestion generation module: connected with the risk value calculation module, used to generate management suggestions based on the risk value.

[0089] The main task of the management suggestion generation module is to generate specific management suggestions based on the risk value output by the risk value calculation module, combined with the actual situation and historical experience of the scenic area. These management suggestions are intended to help scenic area managers take effective preventive measures and emergency responses to reduce the probability of historical risk events or mitigate their impact. The generation process of management suggestions can be divided into the following steps:

[0090] According to the size of the risk value, the risk level of the current situation is evaluated. According to different risk levels, corresponding management suggestions are generated, including preventive measures, emergency response measures and long-term improvement measures. The generated management suggestions are pushed to relevant departments or personnel, and the implementation status is tracked.

[0091] Specifically, in order to better manage and deal with risks of different levels, this embodiment divides risks into different levels according to the size of the risk value. Common risk levels are divided as follows:

[0092] Low risk (0 <G≤1.0):风险较低,发生概率较小,影响范围有限。

[0093] Medium risk (1.0 <G≤2.0):风险适中,可能发生,影响范围较大,但可控。

[0094] High risk (2.0 <G≤3.0):风险较高,发生概率较大,影响范围广泛,需立即采取措施。

[0095] Extremely high risk (G>3.0): The risk is extremely high, the probability of occurrence is very high, and it may cause serious consequences, requiring emergency response.

[0096] Furthermore, low risk (0 <G≤1.0)

[0097] When the risk value is in the low risk range, the system recommends taking the following preventive measures to further reduce the possibility of risk:

[0098] Strengthen monitoring: Increase the monitoring frequency of relevant areas to detect abnormal situations in a timely manner.

[0099] Remind tourists: Through broadcasting, announcements, etc., remind tourists to pay attention to safety and avoid entering high-risk areas.

[0100] Prepare emergency supplies: Ensure that emergency supplies (such as life jackets, first aid kits, etc.) are sufficient for use when necessary.

[0101] Medium risk (1.0 < G ≤ 2.0)

[0102] When the risk value is in the medium - risk range, the system recommends taking more specific preventive and emergency response measures to ensure the safety of tourists:

[0103] Limit the flow of people: According to the carrying capacity of the scenic area, appropriately limit the number of tourists entering high - risk areas to avoid over - crowding.

[0104] Strengthen guidance: Arrange staff to conduct guidance in key areas to ensure the orderly flow of tourists and prevent stampedes.

[0105] Activate the emergency plan: According to the type of risk (such as floods, fires, etc.), activate the corresponding emergency plan and make preparations in advance.

[0106] Release early warning information: Through channels such as the scenic area's official website, social media, etc., release early warning information to inform tourists of the current risk situation and provide safety tips.

[0107] Prepare evacuation routes: Plan and mark clear evacuation routes to ensure that tourists can evacuate quickly in case of emergencies.

[0108] High risk (2.0 < G ≤ 3.0)

[0109] When the risk value is in the high - risk range, the system recommends immediately taking emergency measures to ensure the safety of tourists and staff:

[0110] Suspend opening: Temporarily close high - risk areas and prohibit tourists from entering to avoid danger.

[0111] Evacuate tourists: Activate the emergency evacuation procedure, organize tourists to evacuate orderly according to the pre - determined evacuation routes, and ensure that all personnel leave the dangerous area safely.

[0112] Dispatch rescue forces: Contact the local emergency management departments (such as fire, medical, etc.) and request support to ensure a rapid response in case of emergencies.

[0113] Strengthen patrols: Increase the number of patrol personnel and equipment, closely monitor the situation in high - risk areas, and handle emergencies in a timely manner.

[0114] Issue emergency notices: Through various channels (such as text messages, broadcasts, social media, etc.), issue emergency notices to tourists and staff, informing them of the current dangerous situation and response measures.

[0115] Extremely high risk (G > 3.0)

[0116] When the risk value is in the extremely high-risk range, the system recommends taking the strictest emergency response measures to ensure the safety of all personnel in the scenic area:

[0117] Full closure: Immediately close the entire scenic area, prohibit any personnel from entering, and ensure that all tourists and staff in the scenic area are evacuated.

[0118] Activate the emergency plan: Fully activate the emergency plan, mobilize all available resources, and ensure a rapid response in case of emergencies.

[0119] Coordinate multiple parties: Coordinate with local governments, emergency management departments, medical institutions, etc. to ensure that rescue forces can arrive in a timely manner.

[0120] Continuous monitoring: Continuously evaluate the risk situation through monitoring data from meteorological, geological and other departments, and adjust response strategies in a timely manner.

[0121] Information release: Continuously release the latest information through official channels, inform the public of the current dangerous situation and response measures, and prevent the spread of panic.

[0122] After the management suggestions are generated, the system can push the suggestions to relevant departments or personnel in various ways:

[0123] SMS notification: Send SMS to scenic area managers, staff and tourists to inform them of the current risk situation and response measures.

[0124] Broadcast system: Through the broadcast system in the scenic area, release real-time warning information and safety tips to tourists.

[0125] Social media: Through the official website, WeChat official account, Weibo and other social media platforms of the scenic area, release the latest management suggestions and response measures.

[0126] APP push: Through the official APP of the scenic area, push real-time risk information and management suggestions to users to ensure that tourists can obtain relevant information in a timely manner.

[0127] To ensure the effective implementation of management suggestions, the system can set up an implementation tracking mechanism:

[0128] Task assignment: Decompose management suggestions into specific tasks, and assign them to relevant departments or personnel, clarifying responsibilities and time nodes.

[0129] Progress tracking: Automatically record the implementation progress of each task through the system to ensure that each measure can be completed on time.

[0130] Feedback mechanism: Establish a feedback mechanism, require relevant departments or personnel to timely feedback the implementation situation after the task is completed, and the system evaluates and adjusts according to the feedback.

[0131] Emergency drills: Regularly organize emergency drills to test the feasibility and effectiveness of management suggestions, and improve problems in a timely manner when they are found.

[0132] It should be noted that the terms used in the present invention are only for describing specific embodiments and do not limit the scope of the present application. As shown in the specification of the present invention, unless the context clearly indicates otherwise, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of additional identical elements in the process, method or device including the said element.

[0133] It should also be noted that the orientation or positional relationship indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise clearly specified and defined, terms such as "installed", "connected", "connected" 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 of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0134] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention and do not limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A cultural and tourism management system based on data analysis, characterized in that It includes the following modules: Original data acquisition module: It is used to acquire tourist behavior data, scenic spot operation data, and external environment data, and obtain original data from the tourist behavior data, scenic spot operation data, and external environment data; Risk event sample data acquisition module: It is connected to the original data acquisition module and is used to set selection rules for the conditional generative adversarial network, select input conditions according to the selection rules, and generate risk event sample data according to the input conditions; Risk event sample data acquisition module, including the following sub-modules: Selection rule setting sub-module: It is used to set selection rules for the conditional generative adversarial network; Selection rule setting sub-module, including the following units: Event condition determination unit: It is used to acquire historical risk events and determine event conditions according to the historical risk events; Historical risk event probability calculation unit: It is used to calculate the historical risk event probability according to each event condition and historical risk events; Historical risk event frequency calculation unit: It is used to calculate the historical risk event frequency according to each event condition and historical risk events; Historical risk event propagation path probability calculation unit: It is used to calculate the historical risk event propagation path probability; Selection rule formulation unit: It is used to construct a selection rule function according to the historical risk event probability, historical risk event frequency, and historical risk event propagation path probability, and formulate selection rules according to the selection rule function; Input condition selection sub-module: It is used to select input conditions according to the selection rules; Risk event sample data generation sub-module: It is used to input the input conditions into the conditional generative adversarial network to generate risk event sample data; Data integration module: It is connected to the risk event sample data acquisition module and the original data acquisition module, and is used to integrate the risk event sample data with the original data to obtain extended data; Risk value calculation module: It is connected to the data integration module and is used to calculate the static risk index for the extended data; construct a dynamic risk function based on the static risk index; acquire real-time data, and calculate the risk value of the real-time data according to the dynamic risk function; Management suggestion generation module: It is connected to the risk value calculation module and is used to generate management suggestions according to the risk value.

2. The cultural and tourism management system based on data analysis according to claim 1, wherein Historical risk event propagation path probability calculation unit, including the following sub-units: Graph structure modeling sub-unit: It is used to define scenic spots, transportation stations, and accommodation facilities in the scenic area as nodes by using a graph neural network, and determine the walking paths of tourists as edges; Propagation probability matrix construction sub-unit: It is used to acquire historical normal events, obtain the probability of historical risk events propagating from the current node to other nodes according to the historical normal events and historical risk events, and obtain the propagation probability matrix according to the probability of historical risk events propagating from the current node to other nodes; External factor comprehensive function construction sub-unit: It is used to acquire the weather condition index, traffic congestion index, geographical feature index, and population density index from the current node to other nodes, construct an external factor comprehensive function according to the weather condition index, traffic congestion index, geographical feature index, and population density index from the current node to other nodes, and obtain the external factor comprehensive value; Historical risk event propagation path probability calculation sub-unit: used to calculate the historical risk event propagation path probability based on the probability of the historical risk event propagating from the current node to other nodes and the comprehensive value of external factors.

3. The cultural and tourism management system based on data analysis according to claim 1, characterized in that, Take the event condition corresponding to the maximum value of the selection rule function as the input condition.

4. A cultural and tourism management system based on data analysis according to claim 1, characterized in that, Event conditions include timestamp, geographical location, population density, traffic conditions, weather conditions, event type.

5. The cultural and tourism management system based on data analysis according to claim 1, characterized in that, The static risk index is the historical risk event probability of each historical risk event under each event condition.

6. The cultural and tourism management system based on data analysis according to claim 1, characterized in that Obtain the parameter values of the event conditions in the real-time data, determine the parameter reference values of the event conditions according to the historical risk events, and obtain the risk value according to the static risk index, the parameter values of the event conditions in the real-time data, and the parameter reference values of the event conditions.

7. The cultural and tourism management system based on data analysis according to claim 2, characterized in that, The calculation formula for the historical risk event propagation path probability is: Where P i is the propagation path probability of the i-th historical risk event, and I h (K, L) is the comprehensive external factor value of the h-th external factor between the K-th node and the L-th node, H is the set of all external factors, and P KL is the probability that the i-th historical risk event propagates from the K-th node to the L-th node, and n represents the total number of nodes between the current node and other nodes.

8. The cultural and tourism management system based on data analysis according to claim 7, characterized in that, The selection rule function is: C = P(E i |F j ) + f Ei (F j ) + P i ; where C is the selection rule function, P(E i |F j ) is the historical risk event probability of the occurrence of the i-th historical risk event under the condition of the j-th event in the historical risk events, is the historical risk event frequency of the occurrence of the i-th historical risk event under the condition of the j-th event in the historical risk events, P i is the propagation path probability of the i-th historical risk event.

9. The cultural and tourism management system based on data analysis according to claim 6, wherein The calculation formula for the risk value is: Where G is the risk value, P(E i |F j ) is the historical risk event probability of the i-th historical risk event occurring under the condition of the j-th event in historical risk events, x t is the parameter value under the condition of the t-th event in real-time data, X0 is the parameter reference value of the event condition, and k is the adjustment coefficient.

Images