Knowledge graph-based heritage tourist route planning auxiliary method and system

Abstract

The invention discloses a heritage tourism route planning auxiliary method and system based on a knowledge graph, and relates to the technical field of tourism route planning, and the method comprises the steps: obtaining to-be-processed heritage type tourism data, carrying out the data classification processing of the to-be-processed heritage type tourism data based on a data analysis terminal, and obtaining the to-be-processed heritage type tourism data. And determining different types of heritage type tourism data sets. According to the method, defect analysis is carried out on the to-be-processed heritage type tourism data, whether data supplementation needs to be carried out on the to-be-processed heritage type tourism data or not is determined, the integrity of the to-be-processed heritage type tourism data is guaranteed, and then feature analysis is carried out on the related data of the user, so that the user experience is improved. The method comprises the following steps: determining a heritage type tourist attraction sorting set of a user, and finally carrying out travel planning on the heritage type tourist attraction sorting set of the user and different types of heritage type tourist data sets to generate a tourist route of the user, thereby ensuring that the generated tourist route of the user is the most favorite route of the user. And the travel experience feeling of the user is improved.

Description

Technical Field

[0001] This invention relates to the field of tourism route planning technology, specifically to a knowledge graph-based auxiliary method and system for heritage tourism route planning. Background Technology

[0002] Heritage tourism is a specific form of tourism activity that uses heritage resources (currently mainly world-class heritage sites) as tourist attractions to visit heritage sites, appreciate heritage landscapes, and experience the cultural atmosphere of heritage sites, thus providing tourists with a cultural experience.

[0003] When heritage tourism data is used to match user data to generate travel routes, if the heritage tourism data is not analyzed for defects, it may result in incomplete heritage tourism data. Consequently, it may be impossible to accurately match the tourist attractions that the user likes, and the generated travel route may not be the user's favorite travel route, thus reducing the user's travel experience. Summary of the Invention

[0004] To address the aforementioned technical issues, this paper provides a knowledge graph-based method and system for assisting in the planning of heritage tourism routes. This solution resolves the problem mentioned in the background section: when matching user data with heritage tourism data to generate user travel routes, if defect analysis of the heritage tourism data is not performed, the heritage tourism data may be incomplete, making it impossible to accurately match the user's favorite tourist attractions. Consequently, the generated travel routes will not be the user's preferred routes, thus reducing the user's travel experience.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A knowledge graph-based method for assisting in the planning of heritage tourism routes includes: Acquire heritage tourism data to be processed, and classify the data based on the data analysis terminal to determine different types of heritage tourism data sets. Acquire relevant user data, perform feature analysis on the user data based on the data analysis terminal, and determine the ranked set of heritage tourist attractions that users aspire to visit; Based on the data analysis terminal, location analysis is performed on the sorted set of heritage tourist attractions that users aspire to visit and the data sets of different types of heritage tourism to determine the users' travel routes.

[0006] Preferably, the acquisition of heritage tourism data to be processed, based on a data analysis terminal, involves data classification processing of the heritage tourism data to be processed to determine different types of heritage tourism data sets, specifically including the following steps: Based on the data analysis terminal, data is read and processed from the database system to obtain all tourism-related data; Based on the data analysis terminal, feature data extraction and processing are performed on all tourism-related data with heritage tourism as the characteristic to obtain heritage tourism data to be processed. Based on the data analysis terminal, the heritage tourism data to be processed is filtered and classified to determine different types of heritage tourism data sets.

[0007] Preferably, the step of performing data filtering and classification on the heritage tourism data to be processed based on the data analysis terminal to determine different types of heritage tourism data sets specifically includes the following steps: Based on the data analysis terminal, the heritage tourism data to be processed is traversed to determine the location of data defects; the location of data defects includes data garbled text locations and data missing locations. Based on the data analysis terminal, semantic matching processing is performed on heritage tourism data to be processed, using the location of data defects as a feature, to determine the importance weight of the defective data. Based on the data analysis terminal, the importance weight of defective data is compared and analyzed to determine whether to supplement the data at the defective location. Based on the data analysis terminal, feature extraction processing is performed on the heritage tourism data to be processed to determine the theme of each heritage tourism data. Based on the data analysis terminal, the heritage tourism data to be processed is classified according to the theme of each heritage tourism data, and different types of heritage tourism data sets are determined.

[0008] Preferably, the step of comparing and analyzing the importance weights of defective data based on the data analysis terminal, and selecting whether to supplement the data at the defective location, specifically includes the following steps: Based on the data analysis terminal, the importance weight of defect data and the set importance weight threshold are judged and processed; If the importance weight of the defective data is greater than or equal to the set importance weight threshold, the data at the defective data location affects the correlation of the heritage tourism data corresponding to the defective data location. Based on the data analysis terminal, data supplementation processing is performed on the defective data location. If the importance weight of the defective data is less than the set importance weight threshold, the data at the defective data location will not affect the correlation of the heritage tourism data corresponding to the defective data location, and there is no need to supplement the data at the defective data location.

[0009] Preferably, the data supplementation process for data defect locations based on the data analysis terminal specifically includes the following steps: Based on the data analysis terminal, feature extraction processing is performed on the heritage tourism data corresponding to the data defect locations to obtain the themes of the heritage tourism data corresponding to the data defect locations. Based on the data analysis terminal, data retrieval and processing are performed using the theme of heritage-type tourism data corresponding to the data defect location as a feature to obtain relevant tourism data corresponding to the data defect location. Based on the data analysis terminal, semantic analysis processing is performed on the relevant tourism data corresponding to the data defect locations to obtain the semantic features of several sets of search data. Based on the data analysis terminal, semantic analysis processing is performed on the heritage tourism data corresponding to the data defect locations to obtain the semantic features of the heritage tourism data corresponding to the data defect locations. Based on the data analysis terminal, feature matching processing was performed on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations to determine supplementary data. Based on the data analysis terminal, supplementary data is used to address the locations of data defects.

[0010] Preferably, the step of performing feature matching processing on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations based on the data analysis terminal to determine supplementary data specifically includes the following steps: Based on the data analysis terminal, the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations are processed to obtain the overlap of several sets of semantic features. Based on the maximum value function, several groups of semantic feature overlap are sorted to determine the maximum value of semantic feature overlap. Based on the data analysis terminal, the tourism data corresponding to the maximum semantic feature overlap is set as supplementary data.

[0011] Preferably, the step of obtaining relevant user data, and based on a data analysis terminal, performing feature analysis on the relevant user data to determine the user's preferred heritage tourist attractions ranking set specifically includes the following steps: Based on the data analysis terminal, data retrieval and processing are performed using the user's ID as a feature to obtain relevant user data; Based on the data analysis terminal, and taking the characteristics of heritage tourism data as a reference, relevant user data is extracted and processed to obtain heritage tourism data about the user. Based on the data analysis terminal, data extraction and processing are performed on heritage tourism data of users, with heritage-type tourist attractions as the feature, to determine the heritage-type tourist attractions that users aspire to visit. Based on the data analysis terminal, the heritage tourism data of users is sorted according to the characteristics of the heritage tourist attractions they aspire to, and a sorted set of heritage tourist attractions is obtained.

[0012] Preferably, the step of sorting the user's heritage tourism data based on the user's desired heritage tourist attractions using the data analysis terminal as a feature, and obtaining the sorted set of the user's desired heritage tourist attractions, specifically includes the following steps: Based on the data analysis terminal, the data on heritage tourism of users is classified and processed according to the characteristics of the heritage tourism attractions that users aspire to, and the data set of each heritage tourism attraction that user aspires to is determined. Based on the data analysis terminal, the data set of each desired heritage tourist attraction of the user is processed to determine the browsing time of each desired heritage tourist attraction. Based on the data analysis terminal, each desired heritage tourist attraction is sorted according to the browsing time of the user, and a sorted set of desired heritage tourist attractions is obtained.

[0013] Preferably, the step of performing location analysis processing on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets based on the data analysis terminal to determine the user's travel route specifically includes the following steps: Based on the data analysis terminal, data extraction and processing are performed on different types of heritage tourism datasets using the ranking set of heritage tourist attractions desired by users as a feature, to obtain the location of heritage tourist attractions desired by users. Based on the data analysis terminal, the location of the heritage tourist attractions desired by the user is sorted according to the sorted set of heritage tourist attractions desired by the user, and the sorted set of the location of the heritage tourist attractions desired by the user is obtained. Based on the data analysis terminal, the user's travel route is generated according to the data arrangement order in the set of locations of the heritage tourist attractions the user desires.

[0014] Furthermore, a knowledge graph-based heritage tourism route planning assistance system is proposed to implement the aforementioned knowledge graph-based heritage tourism route planning assistance method, including: The data analysis terminal is used to control the various modules to perform data combination analysis and processing on heritage tourism data and relevant user data to determine the user's travel route. The data analysis terminal is also used to control the data transmission and information interaction between the various modules. A database system for storing all tourism-related data; The data query module is used to perform data traversal processing on the heritage tourism data to be processed and to determine the location of data defects. The missing data weight analysis module is used to perform semantic matching and comparative analysis on the heritage tourism data to be processed, and to select whether to supplement the data at the missing data locations. The data supplementation module is used to perform feature matching processing on the location of data defects to determine supplementary data; The attraction sorting module is used to extract and sort relevant user data to determine the user's desired set of heritage tourist attractions. The route generation module is used to perform location analysis on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets to determine the user's travel route.

[0015] Compared with existing technologies, this invention provides a knowledge graph-based method and system for assisting in the planning of heritage tourism routes, which has the following beneficial effects: This invention analyzes the defects in heritage tourism data to determine whether supplementation is needed, ensuring the integrity of the data. Then, it analyzes the characteristics of user-related data to determine a ranking set of desired heritage tourist attractions. Finally, it generates travel routes for users by combining this ranking set with different types of heritage tourism data. This approach ensures that the generated travel routes are the users' favorite routes, enhancing their travel experience. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating steps S100-S300 in a knowledge graph-based heritage tourism route planning auxiliary method proposed in this invention. Figure 2 This is a structural block diagram of a heritage tourism route planning auxiliary system based on knowledge graphs proposed in this invention. Detailed Implementation

[0017] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0018] Reference Figure 1 As shown, a knowledge graph-based method for assisting in the planning of heritage tourism routes includes: S100. Obtain heritage tourism data to be processed. Based on the data analysis terminal, classify and process the heritage tourism data to be processed to determine the sets of different types of heritage tourism data. S200: Obtain relevant user data, perform feature analysis on the relevant user data based on the data analysis terminal, and determine the ranked set of heritage tourist attractions that the user desires; S300: Based on the data analysis terminal, perform location analysis on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets to determine the user's travel route; Those skilled in the art will understand that each user has their own favorite tourist attractions. However, when traveling, users certainly want to learn more about their favorite attractions. Therefore, it is necessary to ensure the integrity of the data on the tourist attractions that users want to visit. If the data is incomplete, users cannot fully understand the tourist attractions. In addition, when the data on tourist attractions is severely missing, it may be impossible to determine the user's favorite tourist attractions when matching them with the user's data, and thus it may be impossible to generate the user's favorite travel route. For example, the user's favorite is the Longmen Grottoes, but the tourism data for the Longmen Grottoes is missing data on the core attractions. Therefore, when the user goes to the Longmen Grottoes, the generated route will not include the core attractions, which will prevent the user from appreciating the charm of the core attractions of the Longmen Grottoes and reduce the user's travel experience. Therefore, it is necessary to conduct data integrity analysis on the heritage tourism data to be processed to determine whether data supplementation is needed to ensure that the subsequently generated user travel route is the user's favorite travel route.

[0019] Example 1 Step S100: Obtain the heritage tourism data to be processed. Based on the data analysis terminal, classify the heritage tourism data to be processed and determine the different types of heritage tourism data sets. This specifically includes the following steps: S101. Based on the data analysis terminal, perform data reading and processing on the database system to obtain all tourism-related data; Understandably, all tourism-related data includes both heritage tourism data and data on artificially created tourist attractions, so it is necessary to filter all tourism-related data. S102. Based on the data analysis terminal, feature data extraction and processing are performed on all tourism-related data with heritage tourism as the feature, to obtain heritage tourism data to be processed. S103. Based on the data analysis terminal, perform data screening and classification on the heritage tourism data to be processed, and determine the sets of different types of heritage tourism data. Understandably, heritage tourism data comes in many types. To make subsequent route planning more convenient and faster, heritage tourism routes are categorized. Specifically, step S103, based on the data analysis terminal, involves data filtering and classification of the heritage tourism data to be processed, and determining the different types of heritage tourism data sets, including the following steps: S1031. Based on the data analysis terminal, perform data traversal processing on the heritage tourism data to be processed to determine the data defect locations; the data defect locations include data garbled locations and data missing locations. It is understandable that garbled data and spaces are used as features to traverse the data. When garbled data or spaces are found, the position is marked, thereby determining the location of the data defect. S1032. Based on the data analysis terminal, semantic matching processing is performed on the heritage tourism data to be processed, using the location of data defects as a feature, to determine the importance weight of the defective data. Understandably, natural language processing algorithms can be used to determine the specific meaning of missing data. Then, the specific meaning of the missing data can be embedded into the location of the data defect. The text can be converted into numerical features using the TF-IDF algorithm to measure the importance of each word in all documents, and then decide whether data supplementation is needed. S1033. Based on the data analysis terminal, compare and analyze the importance weight of the defective data, and select whether to supplement the data at the defective data location. S1034. Based on the data analysis terminal, perform feature extraction processing on the heritage tourism data to be processed, and determine the theme of each heritage tourism data. Understandably, the TF-IDF algorithm can also be used to convert the text of heritage tourism data into numerical features, and the word with the largest value is the theme of each heritage tourism data point. S1035. Based on the data analysis terminal, the heritage tourism data to be processed is classified according to the theme of each heritage tourism data, and different types of heritage tourism data sets are determined. Specifically, step S1033, based on the data analysis terminal, involves comparing and analyzing the importance weights of the defective data, and selecting whether to supplement the data at the defective locations. This includes the following steps: S10331. Based on the data analysis terminal, the importance weight of defect data and the set importance weight threshold are judged and processed. S10332. If the importance weight of the defective data is greater than or equal to the set importance weight threshold, the data at the defective data location affects the correlation of the heritage tourism data corresponding to the defective data location. Based on the data analysis terminal, data supplementation processing is performed on the defective data location. S10333. If the importance weight of the defective data is less than the set importance weight threshold, the data at the defective data location will not affect the correlation of the heritage tourism data corresponding to the defective data location, and there is no need to supplement the data at the defective data location. Understandably, not every missing piece of data is of equal importance. For example, detailed descriptions of attractions are very important because they reveal the specific features of the attraction and can be compared with data from subsequent users to generate more detailed travel routes. Specifically, step S10332, which involves supplementing data at the location of data defects based on the data analysis terminal, includes the following steps: S103321. Based on the data analysis terminal, perform feature extraction processing on the heritage tourism data corresponding to the data defect location to obtain the theme of the heritage tourism data corresponding to the data defect location. S103322. Based on the data analysis terminal, data retrieval and processing are performed using the theme of heritage-type tourism data corresponding to the data defect location as a feature, to obtain relevant tourism data corresponding to the data defect location. S103323. Based on the data analysis terminal, perform semantic analysis on the relevant tourism data corresponding to the data defect location to obtain the semantic features of several sets of search data. S103324. Based on the data analysis terminal, perform semantic analysis processing on the heritage tourism data corresponding to the data defect location to obtain the semantic features of the heritage tourism data corresponding to the data defect location. S103325. Based on the data analysis terminal, perform feature matching processing on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations to determine supplementary data. S103326. Based on the data analysis terminal, perform data supplementation processing on the data defect location according to the supplementary data; Understandably, to select the most suitable supplementary data for the missing data locations, semantic analysis of the retrieved data is required to determine its semantic features. Semantic analysis of the heritage tourism data corresponding to the missing data locations is also necessary. The search file with the closest semantics between the two is the most suitable supplementary file. However, the supplementary file may be too large. Therefore, a link to the supplementary data is embedded at the missing data locations. Later, when you want to learn more about the supplementary data, you only need to click the link.

[0020] Specifically, step S103325, based on the data analysis terminal, involves performing feature matching processing on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations to determine supplementary data. This includes the following steps: S1033251. Based on the data analysis terminal, perform data intersection processing on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations to obtain the overlap of several sets of semantic features. S1033252. Based on the maximum value function, sort several groups of semantic feature overlap degrees and determine the maximum value of semantic feature overlap degree. S1033253. Based on the data analysis terminal, the tourism data corresponding to the maximum semantic feature overlap is set as supplementary data. It is understandable that the file corresponding to the semantic feature with the highest overlap is the most suitable data to fill in the missing data position. Therefore, the file corresponding to the maximum overlap of semantic features is set as the supplementary data.

[0021] Example 2 Step S200: Obtain relevant user data. Based on the data analysis terminal, perform feature analysis on the relevant user data to determine the user's preferred heritage tourist attractions ranking set. This specifically includes the following steps: S201. Based on the data analysis terminal, perform data retrieval processing using the user's ID as a feature to obtain relevant user data; S202. Based on the data analysis terminal, and taking the characteristics of heritage tourism data as a reference, perform data extraction and processing on the user's relevant data to obtain heritage tourism data about the user. S203. Based on the data analysis terminal, extract and process the heritage tourism data of users with heritage-type tourist attractions as the feature, and determine the heritage-type tourist attractions that users aspire to visit. S204. Based on the data analysis terminal, sort the heritage tourism data of users according to the characteristics of the heritage tourist attractions they aspire to, and obtain the sorted set of heritage tourist attractions that users aspire to. Specifically, step S204, based on the data analysis terminal, sorts the user's heritage tourism data according to the user's desired heritage tourist attractions, and obtains the sorted set of the user's desired heritage tourist attractions, includes the following steps: S2041. Based on the data analysis terminal, the data on heritage tourism of users is classified and processed according to the characteristics of the heritage tourism attractions that users aspire to, and the data set of each heritage tourism attraction that the user aspires to is determined. S2042. Based on the data analysis terminal, perform data calculation and processing on the data set of each heritage-type tourist attraction that the user desires, and determine the browsing time of each heritage-type tourist attraction that the user desires; S2043. Based on the data analysis terminal, sort each of the user's desired heritage tourist attractions by the browsing time of each attraction, and obtain a sorted set of the user's desired heritage tourist attractions. Understandably, to quickly determine a user's travel route, it's necessary to prioritize data on the user's heritage tourism. Therefore, relevant user data needs to be filtered. In addition, users also have their most desired tourist attractions when they travel, so it's also necessary to rank these desired heritage tourist attractions. The attractions that users spend the most time browsing are the ones they most want to visit. Therefore, the desired heritage tourist attractions are ranked based on the browsing time of each user.

[0022] Example 3 Step S300: Based on the data analysis terminal, perform location analysis processing on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets to determine the user's travel route. This specifically includes the following steps: S301. Based on the data analysis terminal, the system extracts and processes data from different types of heritage tourism datasets using the user's desired heritage tourism attractions ranking set as a feature, and obtains the location of the user's desired heritage tourism attractions. S302. Based on the data analysis terminal, sort the locations of the heritage tourist attractions desired by the user according to the sorted set of heritage tourist attractions desired by the user, and obtain the sorted set of locations of the heritage tourist attractions desired by the user. S303. Based on the data analysis terminal, generate the user's travel route according to the data arrangement order in the location sorting set of heritage tourist attractions that the user desires; Understandably, once the user's desired heritage tourism destinations are ranked, route planning can be done based on the names of the attractions in the ranking. However, the specific locations and ways in which the attractions appear are all contained in different types of heritage tourism data sets. Therefore, it is necessary to combine different types of heritage tourism data sets to generate the user's travel route.

[0023] Reference Figure 2 As shown, a knowledge graph-based heritage tourism route planning assistance system is used to implement the aforementioned knowledge graph-based heritage tourism route planning assistance method, including: The data analysis terminal is used to control the various modules to perform data combination analysis and processing on heritage tourism data and relevant user data to determine the user's travel route. The data analysis terminal is also used to control the data transmission and information interaction between the various modules. A database system for storing all tourism-related data; The data query module is used to perform data traversal processing on the heritage tourism data to be processed and to determine the location of data defects. The missing data weight analysis module is used to perform semantic matching and comparative analysis on the heritage tourism data to be processed, and to select whether to supplement the data at the missing data locations. The data supplementation module is used to perform feature matching processing on the location of data defects to determine supplementary data; The attraction sorting module is used to extract and sort relevant user data to determine the user's desired set of heritage tourist attractions. The route generation module is used to perform location analysis on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets to determine the user's travel route.

[0024] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A knowledge graph-based method for assisting in the planning of heritage tourism routes, characterized in that, include: Acquire heritage tourism data to be processed, and classify the data based on the data analysis terminal to determine different types of heritage tourism data sets. Acquire relevant user data, perform feature analysis on the user data based on the data analysis terminal, and determine the ranked set of heritage tourist attractions that users aspire to visit; Based on the data analysis terminal, location analysis is performed on the sorted set of heritage tourist attractions that users aspire to visit and the data sets of different types of heritage tourism to determine the users' travel routes.

2. The knowledge graph-based heritage tourism route planning assistance method according to claim 1, characterized in that, The process of acquiring heritage tourism data to be processed, and classifying the data based on a data analysis terminal to determine different types of heritage tourism data sets, specifically includes the following steps: Based on the data analysis terminal, data is read and processed from the database system to obtain all tourism-related data; Based on the data analysis terminal, feature data extraction and processing are performed on all tourism-related data with heritage tourism as the characteristic to obtain heritage tourism data to be processed. Based on the data analysis terminal, the heritage tourism data to be processed is filtered and classified to determine different types of heritage tourism data sets.

3. The knowledge graph-based heritage tourism route planning assistance method according to claim 2, characterized in that, The process of filtering and classifying heritage tourism data based on a data analysis terminal to determine different types of heritage tourism data sets includes the following steps: Based on the data analysis terminal, the heritage tourism data to be processed is traversed to determine the location of data defects; the location of data defects includes data garbled text locations and data missing locations. Based on the data analysis terminal, semantic matching processing is performed on heritage tourism data to be processed, using the location of data defects as a feature, to determine the importance weight of the defective data. Based on the data analysis terminal, the importance weight of defective data is compared and analyzed to determine whether to supplement the data at the defective location. Based on the data analysis terminal, feature extraction processing is performed on the heritage tourism data to be processed to determine the theme of each heritage tourism data. Based on the data analysis terminal, the heritage tourism data to be processed is classified according to the theme of each heritage tourism data, and different types of heritage tourism data sets are determined.

4. The knowledge graph-based heritage tourism route planning assistance method according to claim 3, characterized in that, The process of comparing and analyzing the importance weights of defective data based on the data analysis terminal, and selecting whether to supplement the data at the defective locations, specifically includes the following steps: Based on the data analysis terminal, the importance weight of defect data and the set importance weight threshold are judged and processed; If the importance weight of the defective data is greater than or equal to the set importance weight threshold, the data at the defective data location affects the correlation of the heritage tourism data corresponding to the defective data location. Based on the data analysis terminal, data supplementation processing is performed on the defective data location. If the importance weight of the defective data is less than the set importance weight threshold, the data at the defective data location will not affect the correlation of the heritage tourism data corresponding to the defective data location, and there is no need to supplement the data at the defective data location.

5. The knowledge graph-based heritage tourism route planning assistance method according to claim 4, characterized in that, The data supplementation process for data defect locations based on the data analysis terminal specifically includes the following steps: Based on the data analysis terminal, feature extraction processing is performed on the heritage tourism data corresponding to the data defect locations to obtain the themes of the heritage tourism data corresponding to the data defect locations. Based on the data analysis terminal, data retrieval and processing are performed using the theme of heritage-type tourism data corresponding to the data defect location as a feature to obtain relevant tourism data corresponding to the data defect location. Based on the data analysis terminal, semantic analysis processing is performed on the relevant tourism data corresponding to the data defect locations to obtain the semantic features of several sets of search data. Based on the data analysis terminal, semantic analysis processing is performed on the heritage tourism data corresponding to the data defect locations to obtain the semantic features of the heritage tourism data corresponding to the data defect locations. Based on the data analysis terminal, feature matching processing was performed on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations to determine supplementary data. Based on the data analysis terminal, supplementary data is used to address the locations of data defects.

6. The knowledge graph-based heritage tourism route planning assistance method according to claim 5, characterized in that, The process of using a data analysis terminal to perform feature matching on the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the locations of data defects, in order to determine supplementary data, specifically includes the following steps: Based on the data analysis terminal, the semantic features of several sets of retrieved data and the semantic features of heritage tourism data corresponding to the data defect locations are processed to obtain the overlap of several sets of semantic features. Based on the maximum value function, several groups of semantic feature overlap are sorted to determine the maximum value of semantic feature overlap. Based on the data analysis terminal, the tourism data corresponding to the maximum semantic feature overlap is set as supplementary data.

7. The knowledge graph-based heritage tourism route planning assistance method according to claim 1, characterized in that, The process of acquiring relevant user data, performing feature analysis on the user data based on a data analysis terminal, and determining the user's preferred heritage tourist attractions ranking set specifically includes the following steps: Based on the data analysis terminal, data retrieval and processing are performed using the user's ID as a feature to obtain relevant user data; Based on the data analysis terminal, and taking the characteristics of heritage tourism data as a reference, relevant user data is extracted and processed to obtain heritage tourism data about the user. Based on the data analysis terminal, data extraction and processing are performed on heritage tourism data of users, with heritage-type tourist attractions as the feature, to determine the heritage-type tourist attractions that users aspire to visit. Based on the data analysis terminal, the heritage tourism data of users is sorted according to the characteristics of the heritage tourist attractions they aspire to, and a sorted set of heritage tourist attractions is obtained.

8. The knowledge graph-based heritage tourism route planning assistance method according to claim 7, characterized in that, The process of sorting user-desired heritage tourism data based on the user's preferred heritage tourist attractions using a data analysis terminal to obtain a sorted set of user-desired heritage tourist attractions specifically includes the following steps: Based on the data analysis terminal, the data on heritage tourism of users is classified and processed according to the characteristics of the heritage tourism attractions that users aspire to, and the data set of each heritage tourism attraction that user aspires to is determined. Based on the data analysis terminal, the data set of each desired heritage tourist attraction of the user is processed to determine the browsing time of each desired heritage tourist attraction. Based on the data analysis terminal, each desired heritage tourist attraction is sorted according to the browsing time of the user, and a sorted set of desired heritage tourist attractions is obtained.

9. The knowledge graph-based method for assisting in the planning of heritage tourism routes according to claim 8, characterized in that, The process of determining a user's travel route based on a data analysis terminal, by performing location analysis on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets, specifically includes the following steps: Based on the data analysis terminal, data extraction and processing are performed on different types of heritage tourism datasets using the ranking set of heritage tourist attractions desired by users as a feature, to obtain the location of heritage tourist attractions desired by users. Based on the data analysis terminal, the location of the heritage tourist attractions desired by the user is sorted according to the sorted set of heritage tourist attractions desired by the user, and the sorted set of the location of the heritage tourist attractions desired by the user is obtained. Based on the data analysis terminal, the user's travel route is generated according to the data arrangement order in the set of locations of the heritage tourist attractions the user desires.

10. A knowledge graph-based heritage tourism route planning assistance system, used to implement the knowledge graph-based heritage tourism route planning assistance method as described in any one of claims 1-9, characterized in that, include: The data analysis terminal is used to control the various modules to perform data combination analysis and processing on heritage tourism data and relevant user data to determine the user's travel route. The data analysis terminal is also used to control the data transmission and information interaction between the various modules. A database system for storing all tourism-related data; The data query module is used to perform data traversal processing on the heritage tourism data to be processed and to determine the location of data defects. The missing data weight analysis module is used to perform semantic matching and comparative analysis on the heritage tourism data to be processed, and to select whether to supplement the data at the missing data locations. The data supplementation module is used to perform feature matching processing on the location of data defects to determine supplementary data; The attraction sorting module is used to extract and sort relevant user data to determine the user's desired set of heritage tourist attractions. The route generation module is used to perform location analysis on the user's desired heritage tourist attractions ranking set and different types of heritage tourist data sets to determine the user's travel route.

Images