Scenic area adaptive navigation optimization method and system based on artificial intelligence

Abstract

The invention relates to the technical field of navigation optimization, and provides a scenic spot adaptive navigation optimization method and system based on artificial intelligence. The method comprises the steps of obtaining a first data set through a tourist terminal after obtaining tourist authorization; activating Internet of Things equipment, collecting data to establish a second data set, and fusing the two to construct a scenic spot dynamic map; reading and encrypting user data, and synchronously inputting a path planning channel with the dynamic map to generate a path result; planning cooperative constraints are configured, user clustering is carried out, path feedback is generated, and a target path is generated and fed back to a user through a feedback compensation path result. The technical problem that a traditional scenic area navigation system cannot adapt to dynamic positions of tourists, scenic area passing conditions and personalized requirements in real time is solved, multi-objective optimization is performed by combining passing efficiency, scenic spot popularity and user preferences, and the purposes of improving navigation precision, optimizing tourist travel paths and improving tourist experience are achieved. Therefore, the user experience and the path flexibility are enhanced.

Description

Technical Field

[0001] The present application relates to the field of navigation optimization technology, and specifically to a scenic area adaptive navigation optimization method and system based on artificial intelligence. Background Art

[0002] With the booming tourism industry, scenic spots, as important tourist destinations, have attracted a large number of tourists. Traditional scenic spot navigation is usually based on static maps and cannot effectively respond to changes in tourists' dynamic behaviors, real-time traffic conditions, and scenic environment. This leads to poor travel experience for tourists in scenic spots, especially during peak hours, which is prone to congestion, misleading, and inconvenience. In addition, scenic area managers are also faced with the challenge of over-concentration of tourist traffic, which leads to difficulties in resource allocation and scenic area environment management. At the same time, traditional navigation systems often take the shortest path as the main goal, ignoring the personalized needs of tourists. For example, different tourists may have significant differences in their interest preferences for attractions, walking speeds, and acceptance of crowd density during their tours, and existing navigation methods are difficult to provide recommendations that adapt to these needs. Furthermore, the complex geographical environment and dynamically changing tourist behavior patterns in scenic spots further exacerbate the challenges of navigation planning. Summary of the invention

[0003] This application provides an artificial intelligence-based scenic spot adaptive navigation optimization method and system, aiming to solve the technical problem that the traditional scenic spot navigation system cannot adapt to the dynamic location of tourists, traffic conditions in the scenic spot and personalized needs in real time.

[0004] In view of the above problems, the present application provides a scenic spot adaptive navigation optimization method and system based on artificial intelligence.

[0005] The first aspect disclosed in the present application provides an artificial intelligence-based adaptive navigation optimization method for a scenic spot, the method comprising: after obtaining authorization from a tourist, obtaining a first data set of the tourist through a mobile terminal of the tourist, the first data set comprising a real-time location and motion status; activating an Internet of Things device, using the Internet of Things device to collect data from the tourist, establishing a second data set, and after data fusion of the first data set and the second data set, constructing a dynamic map of the scenic spot, wherein the dynamic map of the scenic spot is provided with a time-series evolution prediction result identifier; reading user data of a target user, encrypting the user data, and synchronously inputting the data with the dynamic map of the scenic spot into a path planning optimization channel to generate a path optimization result, the path planning optimization channel comprising a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; configuring planning collaborative constraints, clustering and grouping pre-planned users according to the planning collaborative constraints, generating planning path feedback according to the clustering, using the planning path feedback to compensate the path optimization result, generating a target path, and feeding back the target path to the target user.

[0006] Another aspect disclosed in the present application provides an artificial intelligence-based scenic spot adaptive navigation optimization system, the system comprising: a data acquisition module: after obtaining the authorization of the tourist, obtaining a first data set of the tourist through the tourist mobile terminal, the first data set including the real-time location and motion status; a data fusion module: activating the Internet of Things device, using the Internet of Things device to collect data of the tourist, establishing a second data set, and after data fusion of the first data set and the second data set, constructing a dynamic map of the scenic spot, wherein the dynamic map of the scenic spot is provided with a time-series evolution prediction result identifier; a path optimization module: reading the user data of the target user, encrypting the user data, and synchronously inputting it with the dynamic map of the scenic spot into the path planning optimization channel to generate a path optimization result, the path planning optimization channel including a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; a path feedback module: configuring planning collaborative constraints, clustering and grouping the pre-planned users according to the planning collaborative constraints, generating planning path feedback according to the clustering, using the planning path feedback to compensate the path optimization result, generating a target path, and feeding back the target path to the target user.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The above-mentioned method for adaptive navigation optimization of scenic spots based on artificial intelligence, firstly obtains the first data set of tourists through the tourist mobile terminal after obtaining the authorization of tourists, and the first data set includes real-time location and motion status; then, activates the Internet of Things device, uses the Internet of Things device to collect data of tourists, establishes a second data set, and constructs a dynamic map of the scenic spot after data fusion of the first data set and the second data set, wherein the dynamic map of the scenic spot is provided with a time series evolution prediction result identifier; further, reads the user data of the target user, encrypts the user data, and synchronously inputs the user data with the dynamic map of the scenic spot into the path planning optimization channel to generate a path optimization result, and the path planning optimization channel includes a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; finally, configures planning coordination constraints, performs clustering grouping of pre-planned users according to the planning coordination constraints, generates planning path feedback according to the clustering grouping, uses the planning path feedback to compensate the path optimization result, generates a target path, and feeds the target path back to the target user; so as to achieve the technical effect of improving navigation accuracy and optimizing the travel path of tourists by combining traffic efficiency, scenic spot heat and user preference for multi-objective optimization, thereby enhancing user experience and path flexibility.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.

[0010] Figure 1 The figure is a flow chart of a scenic area adaptive navigation optimization method based on artificial intelligence in one embodiment.

[0011] Figure 2 The present invention is an architecture diagram of a scenic area adaptive navigation optimization system based on artificial intelligence in one embodiment.

[0012] Description of reference numerals: data acquisition module 11 , data fusion module 12 , path optimization module 13 , path feedback module 14 . DETAILED DESCRIPTION

[0013] The embodiments of the present application provide a scenic spot adaptive navigation optimization method and system based on artificial intelligence to solve the technical problem that the traditional scenic spot navigation system cannot adapt to the dynamic location of tourists, traffic conditions in the scenic spot and personalized needs in real time.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a scenic area adaptive navigation optimization method based on artificial intelligence, the method comprising: After obtaining the authorization of the visitor, a first data set of the visitor is obtained through the visitor's mobile terminal, wherein the first data set includes a real-time location and a motion status.

[0017] In an embodiment of the present application, after obtaining authorization from the tourist, the system terminal collects real-time data through the tourist's mobile terminal (such as a smart phone). These data include the tourist's real-time location and motion status. The real-time location can help the system terminal accurately locate the tourist's location in the scenic area, while the motion status reflects the tourist's activity, for example, whether he is stationary, walking, or moving quickly. This information provides basic data support for subsequent navigation and path optimization.

[0018] Activate the Internet of Things device, use the Internet of Things device to collect data from tourists, establish a second data set, fuse the first data set and the second data set, and then construct a dynamic map of the scenic spot, wherein the dynamic map of the scenic spot is provided with a time series evolution prediction result identifier.

[0019] In one embodiment, when some tourists are not authorized to provide location and motion data, the system terminal collects other tourist or environmental data by activating Internet of Things devices (such as sensors, cameras, wireless networks, etc. in the scenic area) to construct a second data set. This second data set includes information such as tourist flow, road traffic status, and congestion conditions at scenic spots. The system terminal weightedly fuses the first data set (location information and motion status of authorized tourists) with the second data set (additional data from Internet of Things devices), and after integrating these data, constructs a comprehensive dynamic map of the scenic area. This dynamic map of the scenic area not only reflects the current status of the scenic area in real time, but also combines the time series evolution prediction result identifier to predict future changes in the scenic area, and further optimize tourist navigation paths and scenic area resource management.

[0020] Furthermore, the present application provides the method of constructing a dynamic map of a scenic spot after fusing the first data set and the second data set, including: Establish a geographic coordinate system, and configure basic layer data based on the geographic coordinate system, wherein the basic layer data includes road data, scenic spot data, and facility layout data; after aligning the positions of the first data set and the second data set through the geographic coordinate system, perform weighted fusion of the data to establish a weighted fusion result; use the weighted fusion result as dynamic layer data and update it to the basic layer data to construct a dynamic map of the scenic area.

[0021] Preferably, after obtaining the first data set and the second data set, the system terminal establishes a geographic coordinate system, which is used to provide a unified reference framework for all geographical locations in the scenic area. On the basis of this geographic coordinate system, specific information such as location, length, width, etc. of all main roads, trails, entrances and exits in the scenic area is obtained, and this information is composed of road data. Then, the location, name, type and other information of major scenic spots in the scenic area are obtained, and this information is composed of scenic spot data. Then, the layout of other infrastructure in the scenic area, such as parking lots, toilets, dining areas, first aid stations, etc., is obtained, and this information is composed of facility layout data. After collecting these data, the system terminal converts them into corresponding coordinates in the geographic coordinate system. For example, the longitude and latitude information of roads and scenic spots will be converted into coordinate points in the specified coordinate system, and the data of all infrastructure will also be standardized into the same coordinate format to ensure that they can all be accurately mapped to the geographic coordinate system. Subsequently, the converted road data, scenic spot data, facility layout data, etc. are integrated together to form the basic layer data of the scenic area. This layer of data provides static information of the scenic area, including the spatial position relationship of each component of the scenic area, and provides a basic reference for subsequent dynamic data fusion and path planning. Afterwards, the first data set (location information and movement status from authorized tourists) and the second data set (data from IoT devices, such as tourist flow, road traffic status, etc.) may be different in data type and source, so position alignment is required. The system terminal converts the location information in the two data sets into a unified coordinate system through the geographic coordinate system to ensure that the spatial information in the two data sets can match, which is convenient for subsequent processing; after position alignment, the two data sets are weighted fused. Weighted fusion means giving different weights to data from different sources according to their importance or credibility. For example, the real-time location and movement status of tourists may be more important than other environmental data, so these data can be given higher weights in the fusion process. The purpose of weighted fusion is to obtain a comprehensive and more accurate dynamic state of the scenic spot, reflecting information such as tourist flow, traffic status, and congestion of scenic spots in the scenic spot; after completing weighted fusion, the system terminal generates a weighted fusion result, which is a scenic spot status data that integrates multiple data sources, which can more accurately reflect the real-time dynamics in the scenic spot. These real-time dynamics are usually changing all the time. It reflects the current status of the scenic spot in real time, so it needs to be continuously updated according to actual conditions;Then, the weighted fusion result is used as the dynamic layer data, and it is merged and updated with the previously configured basic layer data (roads, scenic spots, etc.), that is, the dynamic layer data will cover or supplement the part of the basic layer data related to the real-time status. For example, the original scenic road network will be supplemented with the current traffic status through the dynamic layer data, and the location and basic information of the scenic spots will be supplemented with the congestion of tourists through the dynamic layer data, thus forming a complete scenic dynamic map containing real-time dynamic information. In this way, the dynamic map not only shows the static information of the scenic spot (such as the location of roads and scenic spots), but also contains dynamic information (such as tourist distribution, congestion, traffic conditions, etc.), providing tourists with accurate real-time navigation and helping scenic area managers optimize resource scheduling. ;

[0022] Furthermore, the present application also provides: The dynamic layer data is subjected to time series back-tracing extraction to establish historical time series back-tracing data; real-time data is extracted from the dynamic layer data to establish real-time distribution data; the real-time distribution data and the historical time series back-tracing data are input into a time series model, distribution development prediction is performed, a time series evolution prediction result is established, and the dynamic map of the scenic spot is marked with the time series evolution prediction result.

[0023] Optionally, the system terminal uses the timestamp in the dynamic layer data as an identifier to perform time series backtracking, that is, extracting data of historical time periods from the historical dynamic layer logs. These data may include information such as the distribution of tourists (such as the number of tourists), congestion of scenic spots (such as accessibility coefficient, congestion coefficient), road traffic status (such as traffic speed), and scenic spot conditions (such as popularity, attractiveness, maximum number of people, service quality) in the past period of time. The purpose of time series backtracking extraction is to collect past dynamic data to understand the status and change trend of the scenic spot in different time periods. The system terminal organizes and stores the extracted historical data to form historical time series backtracking data. This historical time series backtracking data shows the dynamic evolution process of the scenic spot in the past and reflects The system terminal collects the changes of tourist flow, scenic spot congestion, traffic conditions, etc. over time, and then extracts the real-time information of the current moment from the dynamic layer data. The real-time data includes the current tourist location, road traffic conditions in the scenic area, real-time congestion of scenic spots, tourist flow, etc. The system terminal organizes the real-time extracted data into real-time distribution data, which reflects the current dynamic situation of the scenic area. The real-time distribution data can instantly display the status of the scenic area and provide tourists with accurate path planning and dynamic adjustment; then, the historical time series backtracking data is divided into training set and test set. The system terminal trains the constructed initial time series model through the training set. After the training, the test set is used for verification to evaluate the performance of the model. Specifically, the system terminal is based on long-term and short-term The memory network (LSTM) builds the initial time series model, including the input layer, LSTM layer, fully connected layer and output layer. The input layer receives the time series data, the LSTM layer is responsible for capturing the long-term dependencies in the data, the fully connected layer is used to map the output of the LSTM, and the output layer generates prediction results according to the task requirements; the system terminal uses the sliding window method to divide the training set, and each time uses the data of the first N time steps to predict the data of the next M time steps. The system terminal inputs these time step data into the initial time series model for forward propagation, and passes through the LSTM layer, the fully connected layer and the output layer layer by layer to calculate the data prediction results for the next period of time; then, the mean square error (MSE) is used to calculate the prediction results of the next period of time. ) The loss function calculates the loss value between the data prediction result and the actual data, and calculates the gradient of the loss to the weight of each layer layer by layer through back propagation, and then uses the Adam optimizer to optimize the model parameters, adjusts the weights to minimize the value of the loss function, and repeats the above process until the maximum number of iterations is reached or the loss value converges; after the training is completed, the test set is used to evaluate the model performance and analyze the accuracy of the model in the next data prediction task. If the model performance meets the expected requirements, the trained initial time series model is used as the final time series model. If the model performance does not meet the expectations, it is optimized by adjusting the hyperparameters (such as the number of LSTM units, learning rate, batch size, etc.) and the model is retrained;After obtaining the time series model, the system terminal uses the real-time distribution data as input and inputs it into the time series model. The time series model is used to analyze the time series characteristics in the data and reveal the correlation between the past and current states. With the auxiliary analysis of the time series model, the system terminal can predict the dynamic changes of the scenic spot in the future and generate the time series evolution prediction results. The results show the dynamic change trend of the scenic spot in the future. For example, a certain scenic spot may have too many tourists in the next few hours, or the traffic efficiency of a certain road may decrease during peak hours. The time series evolution prediction results provide data support for the dynamic decision-making of the scenic spot. It can provide scenic spot managers with decision-making basis such as flow control and path optimization, and also provide tourists with more accurate future navigation suggestions; then, based on the time series evolution prediction results, the system terminal feeds the prediction information as the scenic spot dynamic map mark to the scenic spot dynamic map. In this way, the scenic spot dynamic map can not only show the current real-time state, but also predict future changes. For example, some scenic spots or roads may be highly congested in the future. The map will display relevant prompts or marks to help tourists make travel decisions in advance, thereby reducing congestion, improving tourist experience, and better managing scenic spot resources. ;

[0024] Furthermore, the present application provides weighted fusion of the execution data, including: A calibration grid unit is established based on the geographic coordinate system; after the positions of the first data set and the second data set are aligned, timestamp alignment is performed; a matching analysis of the calibration grid unit is performed on the first data set and the second data set after the positions and timestamps are aligned, and weighted fusion is completed according to the matching analysis results.

[0025] Optionally, based on the established geographic coordinate system, the system terminal divides the geographic area of ​​the scenic spot into multiple grid units, the boundary of each grid unit can be determined based on the geographic coordinates, and the grid size can be set according to demand. For example, using a grid of a certain size (such as each grid covers an area of ​​1 square kilometer), the system terminal maps all scenic spot related data (such as roads, scenic spot locations, facility layouts, etc.) to these grid units, and each grid unit will correspond to one or more scenic spot data points. In this way, each location in the scenic spot will have a clear grid unit label to ensure that the spatial information of the data is clearly organized and calibrated; then, for the obtained first data set and the second data set, the system terminal maps each data point in the first data set and the second data set to the corresponding grid unit through the coordinate information in the geographic coordinate system, so that each data point can correspond to the correct geographic location. Since the data may come from different devices or sensors, the timestamps may be different, so the time data also needs to be aligned. The specific approach is to ensure that each data point in the first data set and the second data set can be matched by the timestamp, that is, the data at the same time from different sources are aligned. Alignment ensures the temporal consistency of each data source during analysis. If the timestamps between the data sets are not completely aligned, for example, some data points may be lost or have large intervals, an interpolation method (such as the mean of multiple adjacent data) can be used to fill the data to maintain the continuity and consistency of the data. After completing the alignment of the position and timestamp, the system terminal matches the data points in the first data set and the second data set according to the grid unit. Each data point is mapped to the corresponding grid unit through its geographic location and timestamp to ensure that the data in the same grid unit can be correctly associated. For the data matched to the same grid unit, weighted fusion is performed. The weighted fusion process is to perform weighted summation of the first data and the second data in the same grid unit according to the preset weights for the first data and the second data, so as to obtain a comprehensive data value, reflecting the comprehensive state of the grid unit at that moment. The weighted fusion result obtained after weighted fusion will be used as the dynamic layer data to provide the real-time state of the scenic spot, covering information such as tourist behavior, traffic conditions and environmental changes. These weighted fusion data will be used as an important part of the dynamic map of the scenic spot to provide support for subsequent path planning and management decisions.

[0026] The user data of the target user is read, the user data is encrypted, and then synchronously input into the path planning optimization channel with the dynamic map of the scenic spot to generate a path optimization result. The path planning optimization channel includes a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function.

[0027] In one embodiment, the system terminal obtains user-related data from the mobile terminal of the target user. The user data includes the user's preferred attractions, activity types, travel destinations, travel history, etc. These data provide personalized needs for subsequent route planning; in order to protect user privacy and security, the target user's sensitive data (such as personal information, interest tags, etc.) needs to be encrypted during transmission and processing. Common encryption methods include AES (Advanced Encryption Standard) or RSA encryption algorithm. The system terminal encrypts the target user data to generate an encrypted data string. The encrypted data cannot be interpreted by unauthorized third parties, thereby ensuring data confidentiality. For data security, the encrypted data can be stored in the cloud or transmitted to other system nodes for path planning calculation. The decryption operation is usually performed by authorized users or systems when needed. After the encryption is completed, the system terminal synchronizes the encrypted user data with the dynamic map of the scenic spot. The dynamic map of the scenic spot contains real-time scenic spot data, such as tourist flow, popularity of scenic spots, traffic conditions, etc., which can reflect the current status of the scenic spot. The system terminal combines the user data with the dynamic map of the scenic spot to generate a comprehensive input data. This data, as the basis for path planning, will be input into the path planning optimization channel. The path planning optimization channel is used to calculate the optimal path. It is based on the input user data. According to the dynamic map of the scenic spot, multiple functions are used to optimize the path, including the traffic efficiency function, the attraction popularity function, and the user preference adaptation function. The traffic efficiency function is used to evaluate the traffic efficiency of different paths, taking into account factors such as the number of path segments, the length of the path, the predicted travel speed, etc., smoother roads will get higher traffic efficiency scores, while roads with traffic congestion will get lower scores. The attraction popularity function is used to measure the popularity or popularity of each attraction in the scenic area. This can be calculated based on the total number of attractions, the popularity of the attractions at a certain moment, the number of tourists and other data. Popular attractions may cause the path optimization to avoid these attractions, especially during peak hours. The user preference adaptation function adjusts the path planning according to the user's interests and preferences (such as the priority of certain attractions, service quality, etc.); the path optimization channel randomly generates a path through the navigation system, and comprehensively calculates multiple factors such as the travel efficiency, attraction popularity and user preferences of this path to generate a comprehensive score for the path. If the comprehensive score of the path meets the scoring threshold, the path will be output as the path optimization result. Otherwise, the path will be re-planned based on the navigation system until the scoring threshold is met to ensure that the target users can travel efficiently and comfortably in the scenic area, improve the tourists' experience, and help scenic area managers optimize traffic control.

[0028] Furthermore, the present application provides the path planning optimization channel, including: The path planning optimization channel is as follows: .

[0029] Preferably, the path planning optimization channel can be weighted by calculating the results of the traffic efficiency function, the scenic spot heat function, and the user preference adaptation function to obtain a comprehensive score that quantifies the current path. The path planning optimization channel is specifically as follows: ;in, Represents the total score value, reflecting the overall quality of the path. , , They are the weight factors of the traffic efficiency function, the scenic spot popularity function, and the user preference adaptation function, which control the influence of each function in the final score. is the traffic efficiency function, which is used to evaluate the traffic capacity of the path. ; is the number of path segments, To represent any path, For the The length of the segment path. The longer the length, the lower the traffic efficiency. Characterization Segment path at time The predicted speed reflects the traffic flow and road conditions. The higher the speed, the better the traffic efficiency. Characterization Segment path at time The accessibility prediction coefficient reflects whether the path is easy to reach or unobstructed. Characterization Segment path at time The congestion coefficient reflects the degree of congestion on a path at a specific time. The higher the value, the more congested the road is, which affects traffic efficiency. Characterization Segment path at time The risk coefficient reflects the safety risk of the path. The higher the risk, the lower the traffic efficiency may be. is the attraction heat function, which evaluates the popularity of the attractions passed by the path. ; Represents the total number of attractions, Represent any scenic spot, Characterization Attractions at the time The higher the popularity, the more attractive the attraction is to tourists at a certain moment. Characterization Attractions at the time Number of tourists, Characterization The maximum number of people that can be carried by each attraction helps measure the load of the attraction. Characterization Attractions at the time The attraction index reflects the charm of the scenic spot itself. Characterization The probability of passing through a scenic spot. The higher the probability of passing through, the more likely the path is to pass through the scenic spot. Characterization The dynamic weight of each scenic spot affects the priority of the scenic spot in route planning. It is a user preference adaptation function used to adjust the path planning according to the user's personalized needs. ; is the user interest label vector, which reflects the user's interest preference for different types of attractions (such as natural attractions, historical sites, etc.) and affects the choice of attractions. For the The attribute label vector of each scenic spot describes the specific characteristics of the scenic spot (such as whether it is a cultural heritage). Characterization Attractions at the time The service quality index reflects tourists’ satisfaction. Characterization Attractions at the time Comfort, Characterization Attractions at the time The higher the priority, the more users want to visit the attraction. Through the above formula, path planning takes into account factors such as traffic efficiency, popularity of attractions, and user preferences. Based on the weighted summation method, the comprehensive score of each path is evaluated. By adjusting the weight factors of different functions, path planning can be optimized according to different needs (such as tourists' traffic efficiency, crowdedness of attractions, personalized needs, etc.), so that tourists can choose the most suitable walking route.

[0030] Configure planning coordination constraints, perform clustering of pre-planned users according to the planning coordination constraints, generate planning path feedback according to the clustering, use the planning path feedback to compensate the path optimization result, generate a target path, and feed back the target path to the target user.

[0031] In one embodiment, in multi-user path planning, scenic area resources (such as roads, scenic spot capacity, etc.) are limited, so it is necessary to configure planning coordination constraints to ensure that when multiple users perform path planning at the same time, there will be no path conflict or resource competition. The purpose of planning coordination constraints is to optimize the overall path planning to ensure that the needs of each user are met while avoiding excessive congestion or conflict of resources. The content of planning coordination constraints includes road resources and scenic spot capacity. Road resources refer to the roads that need to be used. The paths of different users may pass through the same road, causing traffic congestion. Therefore, by configuring the road resource constraints of planning coordination constraints, the paths of different users can be ensured. There will be no conflict and excessive use of road resources will be avoided. The scenic spot capacity refers to the maximum number of people that each scenic spot can carry. If multiple users choose the same scenic spot as their destination, the maximum capacity of the scenic spot may be exceeded. The scenic spot capacity constraint of the planning coordination constraint limits the number of visits to the scenic spot to ensure that each scenic spot is within the user flow control range to avoid overcrowding. In multi-user path planning, the system terminal clusters and groups users according to their needs and locations. The basis for user clustering is time period, that is, users in the same time period are classified into one category according to the time of user travel to avoid path conflicts in the same time period. In each cluster grouping, the system terminal will perform Evaluation, counting the number of users on the same road section and the number of users at the same scenic spot to see whether they meet the road resource constraints and scenic spot capacity constraints in the planning coordination constraints. If a cluster group does not meet the constraints, the cluster group will be marked with a path conflict (including conflicting road sections and scenic spots). After the judgment is completed, the system terminal will summarize all cluster groups with path conflict marks and generate a planned path feedback. After obtaining the planned path feedback, the system terminal will compensate for the path optimization result based on the planned path feedback. Specifically, the system terminal will compare the path optimization result with the planned path feedback to determine whether the path optimization result exists in the planned path feedback. In the feedback, if it does not exist, the system terminal will directly use the path optimization result as the target path. If it exists, the system terminal will re-plan the path according to the navigation system, combined with the path conflict mark and the path optimization result, to stagger the conflicting sections and attractions in the path conflict mark. The compensation process is dynamic. With the real-time adjustment of the path planning results, the system terminal can generate a new optimized path to maximize resource utilization efficiency while reducing conflicts and congestion. After the path planning and coordination constraint adjustment are completed, the final generated target path will be returned to the target user, and the target user will receive the new path planning results through the mobile terminal to ensure a smooth tour experience.

[0032] Further, the present application provides the step of feeding back the target path to the target user, comprising: A navigation adaptation analysis is performed according to the user data to establish a navigation adaptation analysis result, wherein the navigation adaptation analysis includes a voice adaptation analysis and a text adaptation analysis; the target path feedback is optimized using the navigation adaptation analysis result and then fed back to the target user.

[0033] Preferably, after obtaining the target path, the system terminal will perform a navigation adaptation analysis based on the user data. Specifically, the system terminal extracts the user's navigation preference data from the user data. The navigation preference data includes the user's preferred language type (such as Chinese, English, etc.), whether voice prompts are preferred, and the user's preference for voice broadcast style (such as formal, friendly, concise, etc.). Based on these data, the system terminal can extract adaptive voice and adaptive text that meet user needs from the voice package and text package of the navigation system, and establish a navigation adaptation analysis result based on the extracted adaptive voice and adaptive text; then, the system terminal uses the navigation adaptation analysis result to perform feedback optimization on the target path, that is, the adaptive voice and adaptive text in the navigation adaptation analysis result are used to convert the target path, obtain corresponding voice prompts and text prompts, and use the converted voice prompts and text prompts as feedback information, which is transmitted to the user in real time. When the user performs path navigation, the system terminal continuously provides corresponding voice and text feedback according to the progress of the target path to ensure a smooth and personalized navigation experience.

[0034] Furthermore, the present application provides that after feeding back the target path to the target user, the method includes: Acquire the real-time interaction of the target user, wherein the real-time interaction includes the real-time feeling interaction and planning interaction of the target user; generate incremental data according to the real-time interaction, make incremental decisions based on the incremental data and the target path, and generate optimized decisions; and feed back the optimized decisions to the target user.

[0035] Preferably, the system terminal obtains real-time interaction data of the target user, which includes the real-time feeling interaction and planning interaction of the target user. The real-time feeling interaction refers to the target user's feedback on the current path during the path navigation process, such as the target user expressing satisfaction with the path through gestures, voice or clicks, or proposing a part that he wants to change, such as the congestion of the path. The planning interaction refers to the needs actively proposed by the target user during the navigation process, such as the desire to adjust the order of attractions, avoid certain areas, or request path modification due to emergencies (such as traffic changes or weather changes); after collecting these real-time interaction data, the system terminal will generate incremental data based on the target user's feedback. The incremental data reflects the changes in the target user's needs during the navigation process, for example, the target user hopes to change certain attractions, avoid congested areas, or proposes adjustments to certain path segments to adapt to the dynamic changes in the target user's needs; then, the system terminal will make incremental decisions based on these incremental data. Unlike recalculating the entire path, the incremental decision focuses on local adjustments to the existing path. In order to respond to the changing needs of the target users, the system terminal analyzes the feedback from the target users, identifies the path parts that need to be adjusted, and adjusts and optimizes the corresponding path in combination with the navigation system. If the target user is not interested in a certain attraction, the system terminal will adjust the path based on these feedbacks and perform the same verification as above to ensure that the new path is more in line with the expectations of the target users. The core of the optimization process is flexibility and real-time performance, ensuring that the needs of the target users are responded to in a timely manner; after that, the system terminal will generate an optimization decision, which combines the real-time needs of the target users and the rationality of the path planning, and gives an optimized path. The optimization decision will ensure that the path adjustment not only meets the needs of the target users, but also takes into account the carrying capacity of the attractions and other factors that may affect the path selection; finally, the system terminal will feed back the optimization decision to the target users in real time to ensure that the target users can smoothly follow the new path for navigation. If the path changes significantly, the system terminal will prompt the target users in time through voice or text to ensure that they can make correct decisions based on the new navigation information. Through the combination of real-time interaction, incremental data and incremental decisions, the system terminal can provide more accurate and personalized navigation services under the changing user needs, thereby improving the user experience.

[0036] In summary, the embodiments of the present application have at least the following technical effects: The embodiment of the present application first obtains the first data set of the tourist through the tourist's mobile terminal after obtaining the tourist's authorization, and the first data set includes the real-time location and movement status; then, the Internet of Things device is activated, and the Internet of Things device is used to collect the tourist's data to establish a second data set. After data fusion of the first data set and the second data set, a dynamic map of the scenic spot is constructed, wherein the dynamic map of the scenic spot is provided with a time-series evolution prediction result identifier; further, the user data of the target user is read, and after the user data is encrypted, it is synchronously input into the path planning optimization channel with the dynamic map of the scenic spot to generate a path optimization result, and the path planning optimization channel includes a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; finally, planning collaborative constraints are configured, and clustering and grouping of pre-planned users is performed according to the planning collaborative constraints, and planning path feedback is generated according to the clustering grouping, and the planning path feedback is used to compensate the path optimization result to generate a target path, and the target path is fed back to the target user. These technical effects jointly solve the technical problem that traditional scenic spot navigation systems are unable to adapt to tourists' dynamic locations, scenic spot traffic conditions and personalized needs in real time. By combining traffic efficiency, attraction popularity and user preferences for multi-objective optimization, the technical effect of improving navigation accuracy and optimizing tourists' travel routes is achieved, thereby enhancing user experience and route flexibility.

[0037] Embodiment 2 is based on the same inventive concept as the artificial intelligence-based scenic area adaptive navigation optimization method in the aforementioned embodiment. Figure 2 As shown, the present application provides an artificial intelligence-based scenic spot adaptive navigation optimization system, the system comprising: a data acquisition module 11: after obtaining the authorization of the tourist, a first data set of the tourist is obtained through the tourist mobile terminal, the first data set including the real-time location and motion status; a data fusion module 12: activating the Internet of Things device, using the Internet of Things device to collect data of the tourist, establishing a second data set, and after data fusion of the first data set and the second data set, constructing a dynamic map of the scenic spot, wherein the dynamic map of the scenic spot is provided with a time-series evolution prediction result identifier; a path optimization module 13: reading the user data of the target user, encrypting the user data, and synchronously inputting it with the dynamic map of the scenic spot into the path planning optimization channel to generate a path optimization result, the path planning optimization channel including a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; a path feedback module 14: configuring planning collaborative constraints, clustering and grouping the pre-planned users according to the planning collaborative constraints, generating planning path feedback according to the clustering grouping, using the planning path feedback to compensate the path optimization result, generating a target path, and feeding back the target path to the target user.

[0038] Furthermore, the data fusion module 12 is also used to execute the following method: Establish a geographic coordinate system, and configure basic layer data based on the geographic coordinate system, wherein the basic layer data includes road data, scenic spot data, and facility layout data; after aligning the positions of the first data set and the second data set through the geographic coordinate system, perform weighted fusion of the data to establish a weighted fusion result; use the weighted fusion result as dynamic layer data and update it to the basic layer data to construct a dynamic map of the scenic area.

[0039] Furthermore, the data fusion module 12 is also used to execute the following method: The dynamic layer data is subjected to time series back-tracing extraction to establish historical time series back-tracing data; real-time data is extracted from the dynamic layer data to establish real-time distribution data; the real-time distribution data and the historical time series back-tracing data are input into a time series model, distribution development prediction is performed, a time series evolution prediction result is established, and the dynamic map of the scenic spot is marked with the time series evolution prediction result.

[0040] Furthermore, the data fusion module 12 is also used to execute the following method: A calibration grid unit is established based on the geographic coordinate system; after the positions of the first data set and the second data set are aligned, timestamp alignment is performed; a matching analysis of the calibration grid unit is performed on the first data set and the second data set after the positions and timestamps are aligned, and weighted fusion is completed according to the matching analysis results.

[0041] Furthermore, the path optimization module 13 is also used to execute the following method: The path planning optimization channel is as follows: ;in, Represents the total score value, is the traffic efficiency function, ; is the number of path segments, To represent any path, For the The length of the segment path, Characterization Segment path at time The predicted speed of travel, Characterization Segment path at time The accessibility prediction coefficient of Characterization Segment path at time The congestion coefficient, Characterization Segment path at time The risk factor, is the attraction heat function, ; Represents the total number of attractions, Represent any scenic spot, Characterization Attractions at the time The heat, Characterization Attractions at the time Number of tourists, Characterization The maximum number of people that can be accommodated at each attraction. Characterization Attractions at the time The attractiveness index, Characterization The probability of passing a scenic spot, Characterization The dynamic weight of each attraction, Adapt the function to user preferences, ; is the user interest label vector, For the The attribute label vector of each scenic spot, Characterization Attractions at the time The service quality index, Characterization Attractions at the time Comfort, Characterization Attractions at the time The priority of , , They are the weight factors of traffic efficiency function, scenic spot popularity function, and user preference adaptation function respectively.

[0042] Furthermore, the path feedback module 14 is also used to execute the following method: A navigation adaptation analysis is performed according to the user data to establish a navigation adaptation analysis result, wherein the navigation adaptation analysis includes a voice adaptation analysis and a text adaptation analysis; the target path feedback is optimized using the navigation adaptation analysis result and then fed back to the target user.

[0043] Furthermore, the path feedback module 14 is also used to execute the following method: Acquire the real-time interaction of the target user, wherein the real-time interaction includes the real-time feeling interaction and planning interaction of the target user; generate incremental data according to the real-time interaction, make incremental decisions based on the incremental data and the target path, and generate optimized decisions; and feed back the optimized decisions to the target user.

[0044] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0045] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0046] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A scenic area adaptive navigation optimization method based on artificial intelligence, characterized in that: The method comprises: After obtaining authorization from the visitor, obtaining a first data set of the visitor through the visitor's mobile terminal, the first data set including a real-time location and a motion status; Activate the Internet of Things device, use the Internet of Things device to collect data of tourists, establish a second data set, and after fusing the first data set and the second data set, construct a dynamic map of the scenic spot, wherein the dynamic map of the scenic spot is provided with a time series evolution prediction result identifier; Read the user data of the target user, encrypt the user data, and synchronously input the data with the scenic spot dynamic map into the path planning optimization channel to generate a path optimization result. The path planning optimization channel includes a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; Configure planning coordination constraints, perform clustering of pre-planned users according to the planning coordination constraints, generate planning path feedback according to the clustering, use the planning path feedback to compensate the path optimization result, generate a target path, and feed back the target path to the target user.

2. The scenic area adaptive navigation optimization method based on artificial intelligence as claimed in claim 1, characterized in that: The path planning optimization channel is as follows: ； in, Represents the total score value, is the traffic efficiency function, ; is the number of path segments, To represent any path, For the The length of the segment path, Characterization Segment path at time The predicted speed of travel, Characterization Segment path at time The accessibility prediction coefficient of Characterization Segment path at time The congestion coefficient, Characterization Segment path at time The risk factor, is the attraction heat function, ; Represents the total number of attractions, Represent any scenic spot, Characterization Attractions at the time The heat, Characterization Attractions at the time Number of tourists, Characterization The maximum number of people that can be accommodated at each attraction. Characterization Attractions at the time The attractiveness index, Characterization The probability of passing a scenic spot, Characterization The dynamic weight of each attraction, Adapt the function to user preferences, ; is the user interest label vector, For the The attribute label vector of each scenic spot, Characterization Attractions at the time The service quality index, Characterization Attractions at the time Comfort, Characterization Attractions at the time The priority of , , They are the weight factors of traffic efficiency function, scenic spot popularity function, and user preference adaptation function respectively.

3. The scenic area adaptive navigation optimization method based on artificial intelligence as claimed in claim 1, characterized in that: After fusing the first data set and the second data set, constructing a dynamic map of the scenic spot includes: Establishing a geographic coordinate system, and configuring basic layer data based on the geographic coordinate system, the basic layer data including road data, scenic spot data, and facility layout data; After aligning the positions of the first data set and the second data set through the geographic coordinate system, performing weighted fusion of the data to establish a weighted fusion result; The weighted fusion result is used as dynamic layer data and updated to the basic layer data to construct the dynamic map of the scenic spot.

4. The method for optimizing scenic area adaptive navigation based on artificial intelligence according to claim 3, characterized in that: The method further comprises: Extract the dynamic layer data in time series backtracking to establish historical time series backtracking data; Performing real-time data extraction on the dynamic layer data to establish real-time distribution data; The real-time distribution data and the historical time series backtracking data are input into a time series model, distribution development prediction is performed, a time series evolution prediction result is established, and the scenic spot dynamic map is marked with the time series evolution prediction result.

5. The method for optimizing scenic area adaptive navigation based on artificial intelligence according to claim 3, characterized in that: The weighted fusion of the execution data includes: Establishing a calibration grid cell based on the geographic coordinate system; After position alignment of the first data set and the second data set, timestamp alignment is performed; The first data set and the second data set after the positions and timestamps are aligned are subjected to matching analysis of the calibrated grid units, and weighted fusion is completed according to the matching analysis results.

6. The method for optimizing scenic area adaptive navigation based on artificial intelligence according to claim 1, characterized in that: Feeding back the target path to the target user includes: Performing navigation adaptation analysis according to the user data and establishing navigation adaptation analysis results, wherein the navigation adaptation analysis includes voice adaptation analysis and text adaptation analysis; The target path feedback is optimized using the navigation adaptation analysis result and then fed back to the target user.

7. The method for optimizing scenic area adaptive navigation based on artificial intelligence according to claim 1, characterized in that: After feeding back the target path to the target user, the method further comprises: Acquire the real-time interaction of the target user, wherein the real-time interaction includes the real-time feeling interaction and planning interaction of the target user; Generate incremental data according to the real-time interaction, make incremental decisions based on the incremental data and the target path, and generate an optimization decision; The optimization decision is fed back to the target user.

8. The scenic area adaptive navigation optimization system based on artificial intelligence is characterized by: The steps for implementing the artificial intelligence-based scenic area adaptive navigation optimization method according to any one of claims 1 to 7 include: Data acquisition module: after obtaining the authorization of the tourist, obtain the first data set of the tourist through the tourist mobile terminal, wherein the first data set includes the real-time location and movement status; Data fusion module: activating the Internet of Things device, using the Internet of Things device to collect data of tourists, establishing a second data set, fusing the first data set and the second data set, and constructing a dynamic map of the scenic spot, wherein the dynamic map of the scenic spot is provided with a time series evolution prediction result mark; Path optimization module: reads the user data of the target user, encrypts the user data, and synchronously inputs it into the path planning optimization channel with the scenic spot dynamic map to generate a path optimization result. The path planning optimization channel includes a traffic efficiency function, a scenic spot heat function, and a user preference adaptation function; Path feedback module: configure planning coordination constraints, cluster and group pre-planned users according to the planning coordination constraints, generate planning path feedback according to the clustering, use the planning path feedback to compensate the path optimization result, generate a target path, and feed back the target path to the target user.

Images