Public culture data processing method and system

Abstract

The invention discloses a public culture data processing method and system, and belongs to the technical field of travel propaganda, and the method comprises the following steps: collecting all available public culture resources in a region through big data search, comprising basic data of cultural relics and historic sites, museums, non-abandoned projects, local literatures, historical stories, characteristic blocks, old sizes and natural landscapes, and a structured cultural asset map is formed; the public culture data processing method and system are invented by automatically capturing hot topics of social media in a local area, Gao-like comments and user-generated contents everyday and identifying potential travel hot spots through data cleaning and aggregation, and through combination of multi-dimensional data acquisition, intelligent analysis and hierarchical planning, manual dependence can be eliminated, travel demands can be accurately captured, and the user experience is improved. The propaganda dimension is widened, high efficiency, precision and continuity of text travel propaganda are achieved, and the exposure and attraction of local text travel resources are improved.

Description

Technical Field

[0001] This invention relates to the field of cultural and tourism promotion technology, and more specifically, to a method and system for processing public cultural data. Background Technology

[0002] In current cultural and tourism promotion, traditional promotional models have many pain points. In the selection and identification of promotional entities, traditional methods rely heavily on manual collection of data from social media platforms, which is not only inefficient but also extremely untimely, often failing to keep up with the short-lived dissemination cycle of cultural and tourism hotspots and easily missing the golden window of promotion. At the same time, the scope of promotion is limited to the local area. When there are no obvious hotspots in the local area, there is a lack of effective alternatives, leading to the stagnation of promotion. Even when trying to expand the scope, it is difficult to accurately connect with the traffic of surrounding areas or national tourism trends, failing to achieve efficient revitalization of cultural and tourism resources and broaden the channels for attracting customers, resulting in a significant problem of promotional gaps. In terms of promotional methods, traditional cultural tourism promotion is rigid and inflexible, often limited to singular and formulaic content output, making it difficult to align with the aesthetics and interests of young audiences. Furthermore, the lack of systematic planning and insufficient or irrelevant promotional entities often result in monotonous and thin content, failing to fully showcase local cultural connotations. This reduces the appeal and dissemination of promotional content and hinders the audience's deep understanding of local culture and tourism, severely limiting the overall effectiveness and market adaptability of cultural tourism promotion. Therefore, there is an urgent need for a public cultural data processing solution that can break through the limitations of traditional models, optimize data collection efficiency, expand promotional dimensions, and innovate promotional forms to meet the actual needs of cultural tourism promotion. No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0003] In response to the problems in related technologies, this invention proposes a public cultural data processing method and system to overcome the technical problems of inefficient and delayed data collection, limited publicity scope, and monotonous content format in existing related technologies. Therefore, the specific technical solution adopted by the present invention is as follows: A method for processing public cultural data, comprising the following steps: S1. Through big data search, collect basic data on all available public cultural resources in the region, including cultural relics, museums, intangible cultural heritage projects, local documents, historical stories, distinctive blocks, time-honored brands, and natural landscapes, to form a structured cultural asset map; S2. Automatically capture trending topics, highly-rated comments, and user-generated content from local social media every day. Identify potential cultural and tourism hotspots through data cleaning and aggregation. Verify feasibility by combining local cultural resources, and select high-quality comments that are in line with the essence of culture and are actionable. For suggestions that are not yet feasible but are inspiring, optimize the design by combining the cultural resource database with the appropriate carriers, list them as publicity targets, and generate publicity plans. S3. When there are no hotspots in the local dynamic data, the monitoring range will be automatically expanded to the surrounding areas with adjacent geographical locations. The correlation between the hotspot entities and the cultural resources of the area will be analyzed to determine the publicity objectives and promote a joint publicity plan that is convenient to access and has a self-consistent cultural logic. S4. When there are no hot spots in the local area and surrounding areas, expand the scope of data analysis, combine the seasonal tourist preferences across the country with the hot cultural and tourism trends on the Internet, match local cultural resources and creatively package them, proactively plan and launch seasonal and localized experience projects as promotional targets, create seasonal promotional topics and develop supporting plans. S5. Monitor textual elements in popular TV shows and variety programs, associate them with local cultural resources, and creatively integrate them to produce promotional content that blends popular IPs with local characteristics. As a preferred implementation, the step of collecting basic data on all available public cultural resources in the region through big data search, including cultural relics, museums, intangible cultural heritage projects, local documents, historical stories, distinctive streets, time-honored brands, and natural landscapes, to form a structured cultural asset map includes the following steps: S11. Extract basic data from structured or semi-structured sources such as business databases of various departments, academic research materials, local chronicles, and published census reports; at the same time, manually organize and extract key information from unstructured carriers such as ancient books, old photos, and special documentaries to complete the initial aggregation. S12. Clean the aggregated raw data, correct errors, standardize the format, and complete key fields; then, by identifying the relationships between people, events, time and space, and themes among resources, establish knowledge links between resources to form a knowledge network. The formation of a knowledge network can be achieved, for example, by associating a historical figure with his or her former residence, related intangible cultural heritage skills, and documentary records. S13. Assign coordinates to all cultural resources with geographical location information, including historical sites, neighborhoods, and landscapes, and mark them on an electronic map; for cultural resources without precise coordinates or abstract ones, including intangible cultural heritage and stories, associate them with their place of origin or region of transmission, and finally form a visualized spatial distribution map of cultural resources. S14. Store the cleaned, correlated, and spatialized structured data into the database to complete the establishment of the cultural resource database and set up standardized data access and update interfaces. Storing the processed data into a database can provide stable and scalable data services for subsequent monitoring, analysis, and publicity applications, laying the data foundation for the entire system. As a preferred implementation, the method involves automatically capturing trending topics, highly-rated comments, and user-generated content from local social media daily, identifying potential cultural and tourism hotspots through data cleaning and aggregation, verifying feasibility by combining local cultural resources, and selecting high-quality comments that are both culturally relevant and actionable. For suggestions that are not yet feasible but are inspiring, the method involves optimizing the design of the cultural resource database and its adaptation to various platforms, listing them as promotional targets, and generating a promotional plan, including the following steps: S21. The system uses a preset application programming interface to perform big data searches on mainstream social media platforms such as Weibo, Douyin, and Xiaohongshu on a daily schedule, automatically capturing user-generated content such as posts, comments, and short videos in a specified area, and aggregating this multi-source heterogeneous raw data into a unified data processing platform. S22. Clean the collected unstructured raw data to remove advertisements, irrelevant information and duplicate content, and extract key information through natural language processing techniques such as text analysis and sentiment analysis; then use clustering algorithms and popularity index models to conduct big data analysis, aggregate information, and initially identify potential cultural and tourism hotspots and high-value user suggestions that are emerging. S23. The hot topics and high-quality suggestions identified by big data analysis are matched and cross-validated with the pre-built structured cultural resource database in the region. An evaluation model is established from multiple dimensions such as cultural fit, implementation cost, and expected benefits to automatically select high-quality suggestions that are both in line with the true nature of the culture and are operable. S24. For user suggestions that are inspiring but not directly implementable, based on the local cultural resource database, use big data analysis technology of association rule mining to search for alternative cultural carriers, forms of expression or experience links that can carry their core ideas, optimize the design, and form a preliminary conceptual solution that can be implemented. S25. Integrate the results of data analysis and automatically generate a structured draft of a publicity plan. This draft typically includes the core publicity points, available cultural resources, suggested narrative angles, content formats, and preliminary dissemination channel strategies. The plan is then submitted to cultural and tourism publicity management personnel for final manual review. As a preferred implementation, the process of cleaning the collected unstructured raw data to remove advertisements, irrelevant information, and duplicate content, and extracting key information using natural language processing techniques such as text analysis and sentiment analysis; then, using clustering algorithms and popularity index models for big data analysis to aggregate information and initially identify emerging potential cultural and tourism hotspots and high-value user suggestions includes the following steps. S221. Clean the collected unstructured raw data to remove advertisements, irrelevant information and duplicate content; S222. Perform deep natural language processing on the cleaned unstructured text, including text segmentation, removal of stop words, and use word embedding models to transform each text into a high-dimensional numerical vector. At the same time, extract key entities including locations, activities, cultural symbols, and emotional polarity including positive, negative, and neutral as additional features to transform text information into computable structured data. S223. Use clustering algorithms to perform unsupervised clustering analysis on vectorized text data, and automatically group texts with similar content themes and similar mentioned entities into several topic clusters, with each cluster representing a potential discussion focus. By using clustering algorithms to analyze and classify data, massive amounts of scattered information can be integrated into a limited set of topics; S224. Calculate a multidimensional popularity index for each topic cluster generated by each cluster, including the volume index, interaction index, dissemination index, and growth index. Then, by weighting and combining these indices, obtain the comprehensive popularity score for each topic cluster and sort them in descending order. S225. Based on the preset popularity threshold, select potential hot topics in cultural and tourism sectors with high popularity. At the same time, within each hot topic cluster, combine the sentiment score of the text, the level of detail of the content, and the specificity of the suggestions to further identify constructive user suggestions and associate them with the corresponding hot topics to form a list of hot topics and high-quality suggestions. As a preferred implementation, the process of associating and cross-validating the hot topics and high-quality suggestions identified by big data analysis with the cultural resource database, and establishing an evaluation model from multiple dimensions such as cultural fit, implementation cost, and expected benefits to automatically select high-quality suggestions that are both culturally authentic and feasible includes the following steps: S231. Perform structured analysis on the identified hot topics and highly praised comments, extract the cultural entities and user demands explicitly mentioned, and match them with data in the cultural resource database to establish preliminary associations; Cultural entities such as specific scenic spots, intangible cultural heritage names, and historical figures, as well as user demands such as the desire to add check-in points or suggestions to hold themed events, can be matched with data in the cultural resource database to accurately capture users' real needs and focus on cultural tourism. At the same time, it can anchor the core carriers of local culture and avoid hot spot mining and suggestion selection from deviating from the local culture. S232. First, the system automatically reviews the suggestions for policy compliance based on the preset rule base, and outputs suggestions marked as pending or initially compliant to the management personnel for review. After manual review and confirmation of compliance, a multi-dimensional evaluation is conducted. S233. Construct a quantitative evaluation model that includes three core dimensions: cultural fit, implementation cost, and expected benefits. Generate a multi-dimensional comprehensive score for each suggestion. The specific formula is as follows: ;in, This is the overall score obtained after calculation; Considering cultural compatibility, implementation costs, and expected benefits, These are the weighting coefficients for cultural compatibility, implementation cost, and expected benefits, respectively. S234. The suggestions are ranked according to the comprehensive score, and those with high scores in cultural fit and expected benefits and implementation costs within the preset range are selected and marked as high-quality suggestions. As a preferred implementation, the process of finding inspiring user suggestions that lack direct implementation capabilities, based on a local cultural resource database and utilizing big data analysis techniques such as association rule mining, to search for alternative cultural carriers, forms of expression, or experiential elements capable of carrying the core ideas, and then optimizing the design to form a preliminary, feasible conceptual solution, includes the following steps: S241. Define the core ideas suggested by users and all entities in the local cultural resource library as transactions. Then, through the association rule mining technology in big data analysis, calculate the co-occurrence frequency and conditional probability between different resources and ideas in historical successful projects or online hotspots to form a knowledge network of association between ideas and resources. S242. Based on user suggestions for optimization, search the related knowledge network for other cultural resources or forms of expression that are highly related to the core idea in terms of theme, emotion or function. For example, when a user suggests an immersive nighttime experience that conflicts with the original suggested historical building, the system will suggest nighttime tours of ancient town waterways or intangible cultural heritage iron flower performances as high-potential alternatives. As a preferred implementation, when there are no obvious hotspots in the local dynamic data, the monitoring range is automatically expanded to the surrounding areas with adjacent geographical locations. The correlation between the hotspot entities and the cultural resources of the area is analyzed to determine the publicity objectives and promote a coordinated publicity plan that is convenient to access and has a self-consistent cultural logic. This includes the following steps: S31. When it is determined that there are no hot spots in local dynamic data, the geographical scope of social media monitoring is automatically expanded to surrounding cities or regions. Through big data analysis, specific entities with high population density and high discussion volume, including popular tourist attractions, markets, and exhibitions, are selected as potential sources of traffic. S32. Based on map service data, construct a list of cultural and tourism resources in the region that can be reached within a certain time threshold from the above-mentioned traffic source locations through major transportation modes, including self-driving and public transportation. Prioritize the selection of destinations with short travel time and convenient routes as candidate destinations for receiving and diverting traffic. Setting the time threshold to 2 hours can accurately define the highly accessible circle centered on the core source areas, effectively filtering out core cultural and tourism resources that can attract tourists to make short-distance, high-frequency consumption. S33. Conduct a cultural theme correlation analysis on the selected traffic sources and receiving points, and design a coherent themed tourism route or complementary experience story based on this. S34. Automatically integrate the above information to generate a specific joint planning draft, including core promotional slogans, recommended connecting tour routes, transportation guidance, comparative or complementary experience highlights, and precise content push strategies for tourists in popular areas. S35. This joint action plan will be submitted to the cultural and tourism publicity management personnel for final review. As a preferred implementation method, when there are no hotspots in the local area and surrounding areas, the scope of data analysis is expanded to combine the seasonal tourist preferences across the country with online cultural and tourism hotspots, match local cultural resources and creatively package them, proactively plan and launch seasonal and localized experience projects as promotional targets, create seasonal promotional topics and formulate supporting plans, including the following steps: S41. Expand the scope of data analysis to tourism websites, search engines and mainstream social platforms at the national level. Use big data analysis to capture the core tourism themes of the current season and emerging online cultural and tourism hotspots. Combine historical data models to analyze the general preferences and behavioral patterns of tourists across the country during the current season. S42. Automated matching and screening of the identified national seasonal themes and hot keywords with entities in the local cultural resource database to find resources with points of connection; For example, a local plum grove matches the spring flower viewing trend, or a cool cave meets the summer heat escaping needs; S43. Conduct in-depth analysis of the successfully matched resources to uncover unique local experience projects in the region, and generate a draft promotional plan. The plan should include the core promotional slogan, target customer profile, main visual elements, suggested content formats, and targeted communication channels. Finally, the plan should be submitted to the cultural and tourism promotion management personnel for manual review. As a preferred implementation, the process of monitoring textual elements in popular TV dramas and variety shows, associating them with local cultural resources, and creatively integrating them to produce promotional content that blends popular IPs with local characteristics includes the following steps: S51. Through natural language processing technology, monitor the synopsis and dialogue text of popular TV dramas and variety shows in real time, and automatically identify and extract key elements such as frequently occurring story background, iconic scenes, core props, classic lines or emotional themes. S52. First, assess whether the current number of promotional entities has reached the preset threshold. When it is determined that the number of promotional entities is insufficient, automatically retrieve and add secondary entities that are strongly related to the main body from the local cultural resource library, build an entity cluster, and then intelligently match the extracted popular culture elements with the identified promotional entities to find content or emotional connection points, and automatically generate a creative framework for promotional content that integrates popular culture elements and local characteristics. S53. Transform the creative framework into a structured promotional plan and submit it to cultural and tourism promotion management personnel for review. A public cultural data processing system, which adopts a public cultural data processing method as described above, including a local cultural resource integration module, a big data hotspot analysis module, a popular IP association and integration module, and a scheme output and manual review module; The regional cultural resource integration module collects data on various public cultural resources in the region, cleans and associates them to establish a structured resource database, and generates a visual cultural asset map. The big data hotspot analysis module first captures data from local social media platforms, identifies potential cultural and tourism hotspots through natural language processing and cluster analysis, and filters high-quality user suggestions to optimize the design. When there are no local hotspots, the monitoring scope is expanded to analyze the correlation between surrounding hotspots and local resources, generating a coordinated promotional plan that is conveniently located and culturally consistent. When there are no local or surrounding hotspots, the module combines national seasonal tourist preferences with online hotspots, matches local resources, and plans seasonal and localized experience projects and promotional plans. The popular IP association and integration module, based on the identified promotional entities, monitors key elements of popular TV shows and variety programs, associates them with local cultural resources, and creatively integrates them to generate a promotional content framework and scheme. The solution output and manual review module integrates the solutions from various modules and submits them to the cultural and tourism publicity management personnel for final review. The beneficial effects of this invention are as follows: 1. Regarding the selection and identification of promotional entities: Traditional cultural and tourism promotion relies on manual data collection from social media platforms, which suffers from low efficiency and poor timeliness, easily missing the golden period for disseminating cultural and tourism hotspots. This invention automatically captures data from mainstream social media platforms and combines natural language processing, cluster analysis, and other technologies to quickly clean and integrate information. It can promptly identify potential cultural and tourism hotspots and high-value user suggestions, and can also use evaluation models to screen feasible suggestions and optimize inspiring suggestions. This approach not only eliminates excessive reliance on manual labor but also accurately grasps users' real needs, quickly transforming trends and suggestions into promotional plans, effectively seizing the time window for cultural and tourism promotion, and improving the targeting and timeliness of promotion. When there are no obvious local hotspots, the system automatically expands its monitoring scope to the surrounding areas. It uses map service data to select local cultural and tourism resources that are easily accessible (within 2 hours) as landing points and designs interconnected routes based on cultural relevance. This approach breaks the limitations of relying solely on local hotspots for promotion. It can proactively take advantage of the traffic dividends from surrounding hotspot areas and attract short-distance tourists through complementary experiences and coherent themed routes. This not only revitalizes local cultural and tourism resources but also broadens customer channels, achieves coordinated development of regional cultural and tourism resources, and enhances the exposure and visitor flow of local cultural and tourism. When there are no hotspots in the local area or surrounding areas, the system further expands its analysis scope, combining national seasonal tourist preferences with online cultural and tourism hotspots to match local resources and plan seasonal and localized experience projects. This approach avoids the dilemma of traditional promotion being directionless without hotspots. By anchoring to national tourism trends, it ensures that local cultural and tourism promotion always meets market demands, highlighting local cultural characteristics while accurately targeting tourist preferences in different seasons. This effectively fills promotional gaps, ensures the continuity and market adaptability of cultural and tourism promotion, and attracts a wider range of cross-regional customers. 2. In terms of promotional methods, this invention monitors popular elements in hit TV shows and variety programs and creatively integrates them with local cultural resources. At the same time, it sets a threshold for the number of promotional entities, and automatically supplements secondary related entities to build a cluster when the threshold is insufficient. Firstly, this method ensures that the promotional content keeps up with the latest trends and is more likely to attract young audiences, breaking the stereotype of traditional cultural tourism promotion. Secondly, the construction of entity clusters avoids the problem of monotonous and thin promotional content, making the promotional dimensions richer and the logic more complete. This not only enhances the attractiveness and dissemination of the promotional content, but also showcases the local cultural connotation from multiple dimensions, deepening the audience's understanding and goodwill towards local cultural tourism. Attached Figure Description To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a flowchart of a public cultural data processing method according to an embodiment of the present invention; Figure 2 This is a block diagram of a public cultural data processing system according to an embodiment of the present invention; Figure 3 This is a flowchart of a public cultural data processing system according to an embodiment of the present invention. Detailed Implementation To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components. According to embodiments of the present invention, a method and system for processing public cultural data are provided. The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, a public cultural data processing method according to an embodiment of the present invention includes the following steps: S1. Through big data search, collect basic data on all available public cultural resources in the region, including cultural relics, museums, intangible cultural heritage projects, local documents, historical stories, distinctive blocks, time-honored brands, and natural landscapes, to form a structured cultural asset map; Furthermore, through big data search, basic data on all available public cultural resources in the region, including cultural relics and historical sites, museums, intangible cultural heritage projects, local documents, historical stories, distinctive blocks, time-honored brands, and natural landscapes, are collected to form a structured cultural asset map, including the following steps: S11. Extract basic data from structured or semi-structured sources such as business databases of various departments, academic research materials, local chronicles, and published census reports; at the same time, manually organize and extract key information from unstructured carriers such as ancient books, old photos, and special documentaries to complete the initial aggregation. S12. Clean the aggregated raw data, correct errors, standardize the format, and complete key fields; then, by identifying the relationships between people, events, time and space, and themes among resources, establish knowledge links between resources to form a knowledge network. S13. Assign coordinates to all cultural resources with geographical location information, including historical sites, neighborhoods, and landscapes, and mark them on an electronic map; for cultural resources without precise coordinates or abstract ones, including intangible cultural heritage and stories, associate them with their place of origin or region of transmission, and finally form a visualized spatial distribution map of cultural resources. S14. Store the cleaned, correlated, and spatialized structured data into the database to complete the establishment of the cultural resource database and set up standardized data access and update interfaces. S2. Automatically capture trending topics, highly-rated comments, and user-generated content from local social media every day. Identify potential cultural and tourism hotspots through data cleaning and aggregation. Verify feasibility by combining local cultural resources, and select high-quality comments that are in line with the essence of culture and are actionable. For suggestions that are not yet feasible but are inspiring, optimize the design by combining the cultural resource database with the appropriate carriers, list them as publicity targets, and generate publicity plans. Furthermore, the system automatically captures trending topics, highly-rated comments, and user-generated content from local social media daily, and identifies potential cultural and tourism hotspots through data cleaning and aggregation. It verifies feasibility by combining local cultural resources, selecting high-quality comments that align with cultural authenticity and are actionable. For suggestions that are not yet feasible but offer valuable insights, the system optimizes the design by adapting the suggestions to the cultural resource database and other suitable platforms, listing them as promotional targets and generating promotional plans including the following steps: S21. The system uses a preset application programming interface to perform big data searches on mainstream social media platforms such as Weibo, Douyin, and Xiaohongshu on a daily schedule, automatically capturing user-generated content such as posts, comments, and short videos in a specified area, and aggregating this multi-source heterogeneous raw data into a unified data processing platform. S22. Clean the collected unstructured raw data to remove advertisements, irrelevant information and duplicate content, and extract key information through natural language processing techniques such as text analysis and sentiment analysis; then use clustering algorithms and popularity index models to conduct big data analysis, aggregate information, and initially identify potential cultural and tourism hotspots and high-value user suggestions that are emerging. Furthermore, the collected unstructured raw data is cleaned to remove advertisements, irrelevant information, and duplicate content. Key information is extracted using natural language processing techniques such as text analysis and sentiment analysis. Then, clustering algorithms and popularity index models are used for big data analysis to aggregate information and preliminarily identify emerging potential cultural and tourism hotspots and high-value user suggestions. The process includes the following steps: S221. Clean the collected unstructured raw data to remove advertisements, irrelevant information and duplicate content; S222. Perform deep natural language processing on the cleaned unstructured text, including text segmentation, removal of stop words, and use word embedding models to transform each text into a high-dimensional numerical vector. At the same time, extract key entities including locations, activities, cultural symbols, and emotional polarity including positive, negative, and neutral as additional features to transform text information into computable structured data. Word embedding models are a technique that maps words in text into low-dimensional, dense, and continuous numerical vector representations through training. This enables computers to capture and compute semantic and syntactic relationships between words. It is trained using unsupervised learning algorithms on a large-scale corpus to automatically learn the vector representation of each word. S223. Use clustering algorithms to perform unsupervised clustering analysis on vectorized text data, and automatically group texts with similar content themes and similar mentioned entities into several topic clusters, with each cluster representing a potential discussion focus. S224. Calculate a multidimensional popularity index for each topic cluster generated by each cluster, including the volume index, interaction index, dissemination index, and growth index. Then, by weighting and combining these indices, obtain the comprehensive popularity score for each topic cluster and sort them in descending order. S225. Based on the preset popularity threshold, select potential hot topics in cultural and tourism sectors with high popularity. At the same time, within each hot topic cluster, combine the sentiment score of the text, the level of detail of the content, and the specificity of the suggestions to further identify constructive user suggestions and associate them with the corresponding hot topics to form a list of hot topics and high-quality suggestions. The preset popularity threshold is first calculated using historical data to determine a baseline value. Then, this baseline value is reviewed and fine-tuned by the staff in conjunction with the publicity goals and resources to form an executable initial threshold. At the same time, this threshold is not fixed, but will be dynamically adjusted periodically based on the publicity effect. In addition, if the overall popularity score of a topic cluster does not exceed the preset popularity threshold, it is determined that there are no hot topics. S23. The hot topics and high-quality suggestions identified by big data analysis are matched and cross-validated with the pre-built structured cultural resource database in the region. An evaluation model is established from multiple dimensions such as cultural fit, implementation cost, and expected benefits to automatically select high-quality suggestions that are both in line with the true nature of the culture and are operable. Furthermore, the hot topics and high-quality suggestions identified by big data analysis are correlated, matched, and cross-validated with the cultural resource database. An evaluation model is established from multiple dimensions, including cultural fit, implementation cost, and expected benefits, to automatically select high-quality suggestions that are both culturally authentic and actionable. This includes the following steps: S231. Perform structured analysis on the identified hot topics and highly praised comments, extract the cultural entities and user demands explicitly mentioned, and match them with data in the cultural resource database to establish preliminary associations; S232. First, the system automatically reviews the suggestions for policy compliance based on the preset rule base, and outputs suggestions marked as pending or initially compliant to the management personnel for review. After manual review and confirmation of compliance, a multi-dimensional evaluation is conducted. S233. Construct a quantitative evaluation model that includes three core dimensions: cultural fit, implementation cost, and expected benefits. Generate a multi-dimensional comprehensive score for each suggestion. The specific formula is as follows: ;in, This is the overall score obtained after calculation; Considering cultural compatibility, implementation costs, and expected benefits, These are the weighting coefficients for cultural compatibility, implementation cost, and expected benefits, respectively. It should be noted that cultural compatibility, implementation cost, and expected benefits have all been normalized and their values ​​range from 0 to 1. These are the weighting coefficients for cultural fit, implementation cost, and expected benefits, respectively. ; Weighting coefficient It is initially obtained by using the Delphi method and the analytic hierarchy process to subjectively evaluate and compare the importance of each dimension based on the core objectives of the current publicity stage. Then, regression analysis or simulation optimization is carried out based on the actual effect data of historical successful projects to verify and fine-tune the initial weights. Finally, a set of weight coefficients that are stable, interpretable and in line with management intentions within a specific period are formed, and the weight coefficients can be periodically adjusted as strategic priorities change. S234. Rank the suggestions based on the comprehensive score, and select those that score highly in cultural fit and expected benefits, and whose implementation costs are within the preset range, and mark them as high-quality suggestions. S24. For user suggestions that are inspiring but not directly implementable, based on the local cultural resource database, use big data analysis technology of association rule mining to search for alternative cultural carriers, forms of expression or experience links that can carry their core ideas, optimize the design, and form a preliminary conceptual solution that can be implemented. Furthermore, for user suggestions that are inspiring but lack direct implementation conditions, based on the local cultural resource database, and utilizing big data analysis techniques such as association rule mining, alternative cultural carriers, forms of expression, or experiential elements that can carry their core ideas are searched for, optimized, and designed to form a preliminary, feasible conceptual solution, including the following steps: S241. Define the core ideas suggested by users and all entities in the local cultural resource library as transactions. Then, through the association rule mining technology in big data analysis, calculate the co-occurrence frequency and conditional probability between different resources and ideas in historical successful projects or online hotspots to form a knowledge network of association between ideas and resources. It should be noted that some user suggestions, though insightful, may not be directly feasible. For example, planning large-scale hiking events in the core area of ​​a nature reserve would clearly violate policies and regulations; suggesting large-scale live-action performances at the original site of a historical site might lead to insufficient carrying capacity of the site, highlighting resource and carrier bottlenecks; suggesting the regular staging of complex technological projects at remote historical sites would rely on immature, extremely costly, or unavailable local technologies and funding; and planning overly entertaining flash mob events in serious settings would contradict the true meaning, core values, or specific customs of cultural heritage. S242. Based on user suggestions for optimization, search the related knowledge network for other cultural resources or forms of expression that are highly related to the core idea in terms of theme, emotion or function. S25. Integrate the results of data analysis and automatically generate a structured draft of a publicity plan. This draft typically includes the core publicity points, available cultural resources, suggested narrative angles, content formats, and preliminary dissemination channel strategies. The plan is then submitted to cultural and tourism publicity management personnel for final manual review. Managers will combine their professional experience, in-depth understanding of local conditions, and broader publicity plans to optimize the draft and make decisions on whether to implement it and how to implement it in detail, ensuring an effective combination of data-driven and humanistic decision-making. S3. When there are no hotspots in the local dynamic data, the monitoring range will be automatically expanded to the surrounding areas with adjacent geographical locations. The correlation between the hotspot entities and the cultural resources of the area will be analyzed to determine the publicity objectives and promote a joint publicity plan that is convenient to access and has a self-consistent cultural logic. Furthermore, when there are no obvious hotspots in the local dynamic data, the monitoring scope is automatically expanded to the surrounding areas with adjacent geographical locations. The correlation between the hotspot entities and the cultural resources of the area is analyzed to determine the publicity objectives. The promotion of a coordinated publicity plan that is convenient to access and has a self-consistent cultural logic includes the following steps: S31. When it is determined that there are no hot spots in local dynamic data, the geographical scope of social media monitoring is automatically expanded to surrounding cities or regions. Through big data analysis, specific entities with high population density and high discussion volume, including popular tourist attractions, markets, and exhibitions, are selected as potential sources of traffic. S32. Based on map service data, construct a list of cultural and tourism resources in the region that can be reached within a certain time threshold from the above-mentioned traffic source locations through major transportation modes, including self-driving and public transportation. Prioritize the selection of destinations with short travel time and convenient routes as candidate destinations for receiving and diverting traffic. S33. Conduct a cultural theme correlation analysis on the selected traffic sources and receiving points, and design a coherent themed tourism route or complementary experience story based on this. S34. Automatically integrate the above information to generate a specific joint planning draft, including core promotional slogans, recommended connecting tour routes, transportation guidance, comparative or complementary experience highlights, and precise content push strategies for tourists in popular areas. S35. This joint plan will be submitted to the cultural and tourism publicity management personnel for final review; S4. When there are no hot spots in the local area and surrounding areas, expand the scope of data analysis, combine the seasonal tourist preferences across the country with the hot cultural and tourism trends on the Internet, match local cultural resources and creatively package them, proactively plan and launch seasonal and localized experience projects as promotional targets, create seasonal promotional topics and develop supporting plans. Furthermore, when there are no hotspots in the local area or surrounding areas, expand the scope of data analysis, combine national seasonal tourist preferences with online cultural and tourism hotspots, match local cultural resources and creatively package them, proactively plan and launch seasonal, localized experiential projects as promotional targets, create seasonal promotional topics and develop supporting plans, including the following steps: S41. Expand the scope of data analysis to tourism websites, search engines and mainstream social platforms at the national level. Use big data analysis to capture the core tourism themes of the current season and emerging online cultural and tourism hotspots. Combine historical data models to analyze the general preferences and behavioral patterns of tourists across the country during the current season. It should be noted that the core tourism themes of the seasons, such as flower viewing in spring, summer retreats, fruit picking in autumn, hot springs in winter, and emerging online cultural and tourism hotspots such as tea gatherings around a fire and city strolls, are analyzed in conjunction with historical data models to understand the general preferences and behavioral patterns of tourists across the country during the current season. S42. Automated matching and screening of the identified national seasonal themes and hot keywords with entities in the local cultural resource database to find resources with points of connection; S43. Conduct in-depth analysis of the successfully matched resources to uncover unique local experiential projects and generate a draft promotional plan. This plan should include a core slogan, target audience profile, key visual elements, suggested content formats, and targeted communication channels. Finally, submit the plan to the cultural tourism promotion management personnel for manual review. S5. Monitor textual elements in popular TV shows and variety programs, associate them with local cultural resources, and creatively integrate them to produce promotional content that blends popular IPs with local characteristics. Furthermore, monitoring textual elements in popular TV dramas and variety shows, linking them to local cultural resources, and creatively integrating them to produce promotional content that blends popular IPs with local characteristics includes the following steps: S51. Through natural language processing technology, monitor the synopsis and dialogue text of popular TV dramas and variety shows in real time, and automatically identify and extract key elements such as frequently occurring story background, iconic scenes, core props, classic lines or emotional themes. S52. First, assess whether the current number of promotional entities has reached the preset threshold. When it is determined that the number of promotional entities is insufficient, automatically retrieve and add secondary entities that are strongly related to the main body from the local cultural resource library, build an entity cluster, and then intelligently match the extracted popular culture elements with the identified promotional entities to find content or emotional connection points, and automatically generate a creative framework for promotional content that integrates popular culture elements and local characteristics. It should be noted that this threshold is set based on historical data, specifically by analyzing the range of entities in past successful promotional projects that meet the dissemination needs and ensure content richness. S53. Transform the creative framework into a structured promotional plan and submit it to cultural and tourism promotion management personnel for review; A public cultural data processing system, which adopts any one of the above public cultural data processing methods, including a local cultural resource integration module, a big data hotspot analysis module, a popular IP association and integration module, and a scheme output and manual review module; The regional cultural resource integration module collects data on various public cultural resources in the region, cleans and correlates them to establish a structured resource database, and generates a visual cultural asset map. The big data hotspot analysis module first captures data from local social media platforms, identifying potential cultural and tourism hotspots through natural language processing and cluster analysis, filtering high-quality user suggestions, and optimizing designs. When no local hotspots are found, the monitoring scope is expanded to analyze the correlation between surrounding hotspots and local resources, generating coordinated promotional plans that are conveniently located and culturally consistent. When no local or surrounding hotspots are found, the module combines national seasonal tourist preferences with online hotspots, matching local resources to plan seasonal, localized experience projects and promotional plans. The popular IP association and integration module, based on the identified promotional entities, monitors key elements of popular movies and TV shows, associates them with local cultural resources, and creatively integrates them to generate promotional content frameworks and solutions. The solution output and manual review module integrates the solutions from various modules and submits them to the cultural and tourism publicity management personnel for final review. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for processing public cultural data, characterized in that, The method includes the following steps: S1. Through big data search, collect basic data on all available public cultural resources in the region, including cultural relics, museums, intangible cultural heritage projects, local documents, historical stories, distinctive blocks, time-honored brands, and natural landscapes, to form a structured cultural asset map; S2. Automatically capture trending topics, highly-rated comments, and user-generated content from local social media every day. Identify potential cultural and tourism hotspots through data cleaning and aggregation. Verify feasibility by combining local cultural resources, and select high-quality comments that are in line with the essence of culture and are actionable. For suggestions that are not yet feasible but are inspiring, optimize the design by combining the cultural resource database with the appropriate carriers, list them as publicity targets, and generate publicity plans. S3. When there are no hotspots in the local dynamic data, the monitoring range will be automatically expanded to the surrounding areas with adjacent geographical locations. The correlation between the hotspot entities and the cultural resources of the area will be analyzed to determine the publicity objectives and promote a joint publicity plan that is convenient to access and has a self-consistent cultural logic. S4. When there are no hot spots in the local area and surrounding areas, expand the scope of data analysis, combine the seasonal tourist preferences across the country with the hot cultural and tourism trends on the Internet, match local cultural resources and creatively package them, proactively plan and launch seasonal and localized experience projects as promotional targets, create seasonal promotional topics and develop supporting plans. S5. Monitor textual elements in popular TV shows and variety programs, associate them with local cultural resources, and creatively integrate them to produce promotional content that blends popular IPs with local characteristics.

2. The public cultural data processing method according to claim 1, characterized in that, The process of collecting basic data on all available public cultural resources in the region through big data search, including cultural relics, museums, intangible cultural heritage projects, local documents, historical stories, distinctive streets, time-honored brands, and natural landscapes, to form a structured cultural asset map, includes the following steps: S11. Extract basic data from structured or semi-structured sources such as business databases of various departments, academic research materials, local chronicles, and published census reports; at the same time, manually organize and extract key information from unstructured carriers such as ancient books, old photos, and special documentaries to complete the initial aggregation. S12. Clean the aggregated raw data, correct errors, standardize the format, and complete key fields; then, by identifying the relationships between people, events, time and space, and themes among resources, establish knowledge links between resources to form a knowledge network. S13. Assign coordinates to all cultural resources with geographical location information, including historical sites, neighborhoods, and landscapes, and mark them on an electronic map; for cultural resources without precise coordinates or abstract ones, including intangible cultural heritage and stories, associate them with their place of origin or region of transmission, and finally form a visualized spatial distribution map of cultural resources. S14. Store the cleaned, correlated, and spatialized structured data into the database to complete the establishment of the cultural resource database and set up standardized data access and update interfaces.

3. The public cultural data processing method according to claim 1, characterized in that, The system automatically captures trending topics, highly-rated comments, and user-generated content from local social media daily. Through data cleaning and aggregation, it identifies potential cultural and tourism hotspots. Feasibility is verified using local cultural resources, and high-quality comments that align with cultural authenticity and are actionable are selected. For suggestions that are not yet feasible but offer valuable insights, the system optimizes the design by adapting the suggestions to the cultural resource database and other suitable platforms, designating them as promotional targets and generating a promotional plan that includes the following steps: S21. The system uses a preset application programming interface to perform big data searches on mainstream social media platforms such as Weibo, Douyin, and Xiaohongshu on a daily schedule, automatically capturing user-generated content such as posts, comments, and short videos in a specified area, and aggregating this multi-source heterogeneous raw data into a unified data processing platform. S22. Clean the collected unstructured raw data to remove advertisements, irrelevant information and duplicate content, and extract key information through natural language processing techniques such as text analysis and sentiment analysis; then use clustering algorithms and popularity index models to conduct big data analysis, aggregate information, and initially identify potential cultural and tourism hotspots and high-value user suggestions that are emerging. S23. The hot topics and high-quality suggestions identified by big data analysis are matched and cross-validated with the pre-built structured cultural resource database in the region. An evaluation model is established from multiple dimensions such as cultural fit, implementation cost, and expected benefits to automatically select high-quality suggestions that are both in line with the true nature of the culture and are operable. S24. For user suggestions that are inspiring but not directly implementable, based on the local cultural resource database, use big data analysis technology of association rule mining to search for alternative cultural carriers, forms of expression or experience links that can carry their core ideas, optimize the design, and form a preliminary conceptual solution that can be implemented. S25. Integrate the results of data analysis and automatically generate a structured draft of a publicity plan. This draft typically includes the core publicity points, available cultural resources, suggested narrative angles, content formats, and preliminary dissemination channel strategies. The plan is then submitted to cultural and tourism publicity management personnel for final manual review.

4. The public cultural data processing method according to claim 3, characterized in that, The process of cleaning the collected unstructured raw data to remove advertisements, irrelevant information, and duplicate content, and extracting key information using natural language processing techniques such as text analysis and sentiment analysis; then, using clustering algorithms and popularity index models for big data analysis to aggregate information and initially identify emerging potential cultural and tourism hotspots and high-value user suggestions includes the following steps. S221. Clean the collected unstructured raw data to remove advertisements, irrelevant information and duplicate content; S222. Perform deep natural language processing on the cleaned unstructured text, including text segmentation, removal of stop words, and use word embedding models to transform each text into a high-dimensional numerical vector. At the same time, extract key entities including locations, activities, cultural symbols, and emotional polarity including positive, negative, and neutral as additional features to transform text information into computable structured data. S223. Use clustering algorithms to perform unsupervised clustering analysis on vectorized text data, and automatically group texts with similar content themes and similar mentioned entities into several topic clusters, with each cluster representing a potential discussion focus. S224. Calculate a multidimensional popularity index for each topic cluster generated by each cluster, including the volume index, interaction index, dissemination index, and growth index. Then, by weighting and combining these indices, obtain the comprehensive popularity score for each topic cluster and sort them in descending order. S225. Based on the preset popularity threshold, select potential hot topics in cultural and tourism sectors with high popularity. At the same time, within each hot topic cluster, combine the sentiment score of the text, the level of detail of the content, and the specificity of the suggestions to further identify constructive user suggestions and associate them with the corresponding hot topics to form a list of hot topics and high-quality suggestions.

5. A public cultural data processing method according to claim 3, characterized in that, The process of linking and cross-validating the hot topics and high-quality suggestions identified by big data analysis with the cultural resource database, and establishing an evaluation model from multiple dimensions such as cultural fit, implementation cost, and expected benefits to automatically select high-quality suggestions that are both culturally authentic and actionable, includes the following steps: S231. Perform structured analysis on the identified hot topics and highly praised comments, extract the cultural entities and user demands explicitly mentioned, and match them with data in the cultural resource database to establish preliminary associations; S232. First, the system automatically reviews the suggestions for policy compliance based on the preset rule base, and outputs suggestions marked as pending or initially compliant to the management personnel for review. After manual review and confirmation of compliance, a multi-dimensional evaluation is conducted. S233. Construct a quantitative evaluation model that includes three core dimensions: cultural fit, implementation cost, and expected benefits. Generate a multi-dimensional comprehensive score for each suggestion. The specific formula is as follows: ;in, This is the overall score obtained after calculation; Considering cultural compatibility, implementation costs, and expected benefits, These are the weighting coefficients for cultural compatibility, implementation cost, and expected benefits, respectively. S234. The suggestions are ranked according to the comprehensive score, and those with high scores in cultural fit and expected benefits and implementation costs within the preset range are selected and marked as high-quality suggestions.

6. A public cultural data processing method according to claim 3, characterized in that, The aforementioned user suggestions, which are inspiring but lack direct implementation conditions, are analyzed using big data techniques such as association rule mining based on a local cultural resource database. The process involves searching for alternative cultural carriers, forms of expression, or experiential elements that can carry the core ideas, optimizing the design, and forming a preliminary, feasible conceptual solution. This includes the following steps: S241. Define the core ideas suggested by users and all entities in the local cultural resource library as transactions. Then, through the association rule mining technology in big data analysis, calculate the co-occurrence frequency and conditional probability between different resources and ideas in historical successful projects or online hotspots to form a knowledge network of association between ideas and resources. S242. Based on user suggestions for optimization, search the related knowledge network for other cultural resources or forms of expression that are highly related to the core idea in terms of theme, emotion, or function.

7. A public cultural data processing method according to claim 3, characterized in that, When there are no obvious hotspots in the local dynamic data, the monitoring scope is automatically expanded to the surrounding areas with adjacent geographical locations. The correlation between the hotspot entities and the cultural resources of the area is analyzed to determine the publicity objectives and promote a coordinated publicity plan that is convenient to access and has a self-consistent cultural logic. This includes the following steps: S31. When it is determined that there are no hot spots in local dynamic data, the geographical scope of social media monitoring is automatically expanded to surrounding cities or regions. Through big data analysis, specific entities with high population density and high discussion volume, including popular tourist attractions, markets, and exhibitions, are selected as potential sources of traffic. S32. Based on map service data, construct a list of cultural and tourism resources in the region that can be reached within a certain time threshold from the above-mentioned traffic source locations through major transportation modes, including self-driving and public transportation. Prioritize the selection of destinations with short travel time and convenient routes as candidate destinations for receiving and diverting traffic. S33. Conduct a cultural theme correlation analysis on the selected traffic sources and receiving points, and design a coherent themed tourism route or complementary experience story based on this. S34. Automatically integrate the above information to generate a specific joint planning draft, including core promotional slogans, recommended connecting tour routes, transportation guidance, comparative or complementary experience highlights, and precise content push strategies for tourists in popular areas. S35. This joint action plan will be submitted to the cultural and tourism publicity management personnel for final review.

8. A public cultural data processing method according to claim 1, characterized in that, When there are no hotspots in the local area or surrounding areas, the scope of data analysis is expanded to combine national seasonal tourist preferences with online cultural and tourism hotspots. Local cultural resources are matched and creatively packaged to proactively plan and launch seasonal, localized experiential projects as promotional targets. Seasonal promotional topics and supporting plans are developed, including the following steps: S41. Expand the scope of data analysis to tourism websites, search engines and mainstream social platforms at the national level. Use big data analysis to capture the core tourism themes of the current season and emerging online cultural and tourism hotspots. Combine historical data models to analyze the general preferences and behavioral patterns of tourists across the country during the current season. S42. Automated matching and screening of the identified national seasonal themes and hot keywords with entities in the local cultural resource database to find resources with points of connection; S43. Conduct in-depth analysis of the successfully matched resources to uncover unique local experience projects in the region, and generate a draft promotional plan. The plan should include the core promotional slogan, target customer profile, main visual elements, suggested content formats, and targeted communication channels. Finally, the plan should be submitted to the cultural and tourism promotion management personnel for manual review.

9. A public cultural data processing method according to claim 1, characterized in that, The process of monitoring textual elements in popular TV dramas and variety shows, associating them with local cultural resources, and creatively integrating them to produce promotional content that blends popular IPs with local characteristics includes the following steps: S51. Through natural language processing technology, monitor the synopsis and dialogue text of popular TV dramas and variety shows in real time, and automatically identify and extract key elements such as frequently occurring story background, iconic scenes, core props, classic lines or emotional themes. S52. First, assess whether the current number of promotional entities has reached the preset threshold. When it is determined that the number of promotional entities is insufficient, automatically retrieve and add secondary entities that are strongly related to the main body from the local cultural resource library, build an entity cluster, and then intelligently match the extracted popular culture elements with the identified promotional entities to find content or emotional connection points, and automatically generate a creative framework for promotional content that integrates popular culture elements and local characteristics. S53. Transform the creative framework into a structured promotional plan and submit it to cultural and tourism promotion management personnel for review.

10. A public cultural data processing system, characterized in that, The system employs a public cultural data processing method as described in any one of claims 1-9, including a local cultural resource integration module, a big data hotspot analysis module, a popular IP association and fusion module, and a scheme output and manual review module; The regional cultural resource integration module collects data on various public cultural resources in the region, cleans and associates them to establish a structured resource database, and generates a visual cultural asset map. The big data hotspot analysis module first captures data from local social media platforms, identifies potential cultural and tourism hotspots through natural language processing and cluster analysis, and filters high-quality user suggestions to optimize the design. When there are no local hotspots, the monitoring scope is expanded to analyze the correlation between surrounding hotspots and local resources, generating a coordinated promotional plan that is conveniently located and culturally consistent. When there are no local or surrounding hotspots, the module combines national seasonal tourist preferences with online hotspots, matches local resources, and plans seasonal and localized experience projects and promotional plans. The popular IP association and integration module, based on the identified promotional entities, monitors key elements of popular TV shows and variety programs, associates them with local cultural resources, and creatively integrates them to generate a promotional content framework and scheme. The solution output and manual review module integrates the solutions from various modules and submits them to the cultural and tourism publicity management personnel for final review.

Images