Industrial heritage digital display system

Abstract

The invention discloses a digital display system for industrial heritage. The digital display system comprises a front-end display layer, a rear-end data management layer and a technical support layer, the front-end display layer comprises a VR / AR experience module, an interactive touch screen display module, a mobile application function module, a deep culture interpretation module and a diversified expression form module; the rear-end data management layer comprises a digital asset management platform module, an intelligent recommendation system module and a customized experience module, the digital asset management platform module receives and stores a 3D model generated by the 3D scanning and modeling technology module, and the intelligent recommendation system module is responsible for identifying interests and preferences of users by utilizing association rule mining and clustering analysis; the intelligent recommendation system module generates personalized recommendation content by analyzing user data and transmits the personalized recommendation content to the interactive touch screen display module through a data interface, and the customized experience module is responsible for customizing a visiting route according to user interests and providing differentiated experience.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial heritage display, and in particular, to a digital display system for industrial heritage. Background Art

[0002] Industrial heritage is an important carrier of industrial civilization and witnesses the history of the human industrialization process. These heritages not only have historical and cultural values, but also contain rich social, economic and technical information. However, with the rapid development of industrialization and urbanization, many industrial heritages are at risk of being demolished or abandoned, and their values and significances are often ignored or forgotten. In recent years, digital technologies have developed rapidly, and a new generation of digital technologies, including big data, cloud computing, artificial intelligence, virtual reality (VR), augmented reality (AR), etc., have emerged continuously, providing strong technical support for the digital display of industrial heritage. These technologies can achieve high-precision acquisition, processing, display and interaction of industrial heritage, enabling audiences to feel the charm and value of industrial heritage immersive.

[0003] In the prior art, the information volume of the existing carriers carrying the cultural content of industrial heritage is limited, the cultural characteristics and cultural connotations are difficult to highlight, the cultural functions and cultural value attributes of the productized carriers are not distinct, the interpretation and depth of the specific characteristic industrial cultural content are insufficient, the expression form of the cultural content is monotonous, which is not conducive to the display and dissemination of industrial heritage. Therefore, a digital display system for industrial heritage is proposed. Summary of the Invention

[0004] The purpose of the present invention is to solve the deficiencies existing in the prior art, such as the insufficient interpretation and depth of the specific characteristic industrial cultural content, the limited information volume of the carriers carrying the cultural content of industrial heritage, and the disadvantages that are not conducive to the display and dissemination of industrial heritage, and to propose a digital display system for industrial heritage.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0006] A digital display system for industrial heritage, comprising a front-end display layer, a back-end data management layer and a technical support layer;

[0007] The front-end display layer includes a VR / AR experience module, an interactive touch screen display module, a mobile application function module, a deep cultural interpretation module, and a diversified presentation form module. The VR / AR experience module is responsible for creating an immersive industrial heritage environment, realizing the construction of a virtual environment and user interaction. When users explore the industrial heritage environment through VR / AR devices, the VR / AR experience module calls the data stored in the digital asset management platform. The interactive touch screen display module is responsible for displaying industrial heritage through a large touch screen, and users can obtain detailed information through touch operations. The mobile application function module is responsible for developing a dedicated APP to provide functions such as online guided tours, interactive Q&A, and virtual exhibitions. The mobile application function collects users' feedback and behavior data, and the users' feedback and behavior data are transmitted to the data analysis and feedback module through the mobile application function module. The deep cultural interpretation module is responsible for telling the historical stories and biographies of figures behind industrial heritage through forms such as animations and microfilms to increase cultural depth, inviting industry experts to record videos or audio interpretations to provide in-depth analysis from a professional perspective. The diversified presentation form module is responsible for designing games based on industrial heritage knowledge and using holographic technology to display key scenes or products of industrial heritage;

[0008] The back-end data management layer includes a digital asset management platform module, an intelligent recommendation system module, and a customized experience module. The digital asset management platform module is responsible for centrally storing and managing all digital content, including high-definition pictures, 3D models, video materials, audio commentaries, text introductions, etc. The digital asset management platform receives and stores the 3D models generated by the 3D scanning and modeling technology module. The intelligent recommendation system module is responsible for identifying users' interests and preferences using association rule mining and clustering analysis, and intelligently recommending relevant industrial heritage content. The intelligent recommendation system module generates personalized recommendation content by analyzing user data and transmits it to the interactive touch screen display module through a data interface. The customized experience module is responsible for customizing the visit route according to users' interests and providing a differentiated experience;

[0009] The technical support layer includes a 3D scanning and modeling technology module, a big data and cloud computing module, and an artificial intelligence and machine learning module. The 3D scanning and modeling technology module is responsible for scanning industrial heritage to generate 3D models. The big data and cloud computing module is responsible for adopting a big data processing framework and a cloud computing platform to realize distributed storage, parallel processing, and efficient access of data. The big data and cloud computing module provides data processing and storage capabilities for the intelligent recommendation system module. The artificial intelligence and machine learning module is used for content classification, intelligent Q&A, and sentiment analysis, and there is data interaction between the artificial intelligence and machine learning module and the data analysis and feedback module.

[0010] The above technical solution further includes:

[0011] Furthermore, the in-depth cultural interpretation module includes a content planning unit, a multimedia creation unit, an expert resource unit, a data management and storage unit, and a front-end display unit. The content planning unit is responsible for planning and formulating the content framework and themes of in-depth cultural interpretation to ensure the accuracy and depth of the content. The multimedia creation unit creates content in multimedia forms such as animation and micro-films according to the requirements of the content planning unit to ensure the vividness and attractiveness of the content. The expert resource unit is responsible for inviting industry experts to record videos or audios, providing interpretations and analyses from a professional perspective to enhance the authority and credibility of the content. The data management and storage unit is responsible for managing and storing all multimedia content and expert interpretations in the in-depth cultural interpretation module to ensure the integrity and security of the data. The front-end display unit is responsible for presenting the content of the in-depth cultural interpretation module to users through the user interface to achieve interaction between users and the content.

[0012] Furthermore, the digital asset management platform module includes a data storage unit, a content management unit, a data invocation unit, a permission management unit, and a data analysis unit. The data storage unit is responsible for storing and backing up digital content to ensure the reliability and security of the data. The data storage unit is implemented using a database management system or cloud storage technology. The content management unit provides management functions such as content upload, download, editing, and deletion, and is a bridge for interaction between users and digital content. The content management unit includes a user interface and a back-end management interface. The data invocation unit is responsible for the efficient invocation and quick response of digital content to ensure that users can quickly obtain the required resources when needed. The data invocation unit uses distributed storage and caching technologies to optimize performance. The permission management unit provides permission control for users to access digital content to ensure the security and controllability of the data. The permission management unit includes user authentication, role assignment, and permission setting. The data analysis unit statistically analyzes the usage of digital content to provide data support for optimizing content management and enhancing the user experience. When a user needs to access digital content, the data invocation unit sends a request to the data storage unit to obtain the required resources. When a user attempts to access content, the content management unit sends a request to the permission management unit to verify the user's permissions. The data analysis unit statistically analyzes the usage of digital content, generates reports and data visualization charts, and feeds the reports and charts back to the content management unit for optimizing content management and enhancing the user experience.

[0013] Furthermore, the intelligent recommendation system module includes a data collection unit, an interest analysis unit, a content recommendation unit, and an effect evaluation unit. The data collection unit is responsible for comprehensively collecting user behavior data, including system logs, user feedback, etc. This unit needs to ensure the accuracy and integrity of the data, providing a reliable basis for subsequent analysis. The interest analysis unit uses big data analysis and machine learning algorithms to deeply mine and analyze user behavior data to identify users' interests and preferences. The interest analysis unit continuously optimizes the algorithm model to improve the accuracy and efficiency of the analysis. The content recommendation unit intelligently recommends relevant industrial heritage content based on users' interests and preferences. The content recommendation unit ensures the diversity and richness of the recommended content and adjusts the recommendation strategy in real time according to user feedback. The effect evaluation unit conducts real-time evaluation and optimization of the recommendation effect through user feedback, click-through rate, and conversion rate. This unit needs to regularly analyze the evaluation results and put forward improvement suggestions to ensure the continuous optimization and improvement of the recommendation system. The data collection unit transfers the collected user behavior data to the interest analysis unit, and the interest analysis unit transfers the analyzed user interests and preferences to the content recommendation unit.

[0014] Furthermore, the customized experience module includes a route customization unit, an experience provision unit, and a cultural dissemination unit. The route customization unit generates personalized tour routes based on users' interests and preferences, combined with the characteristics and display requirements of industrial heritage. The route customization unit ensures the rationality and feasibility of the routes while meeting users' personalized needs. The experience provision unit provides differentiated experiences for users according to the customized tour routes. The experiences include the display of content, the setting of interactive projects, and the design of game sessions. The experience provision unit ensures the quality and effect of the experiences and enhances users' satisfaction. The cultural dissemination unit, while providing personalized experiences, focuses on the dissemination and popularization of industrial heritage culture, including providing cultural interpretations, historical background introductions, interactive Q&A, etc., to increase users' cultural identity. The interest analysis unit transfers the analyzed user interests and preferences to the route customization unit, and the route customization unit transfers the generated tour routes to the experience provision unit. The experience provision unit, while providing personalized experiences, collaborates with the cultural dissemination unit to focus on the dissemination and popularization of industrial heritage culture.

[0015] Furthermore, the 3D scanning and modeling technology module includes a scanning device unit, a data processing unit, and a modeling software unit. The scanning device unit is responsible for scanning industrial heritage using 3D scanning equipment, capturing its surface details and shape features. The scanning device unit needs to ensure the accuracy and integrity of the scanning to provide a reliable data basis for subsequent modeling. The data processing unit preprocesses and cleans the scanned data, removing noise and redundant information to improve the quality and usability of the data. The data processing unit also needs to convert the processed data into a format recognizable by the modeling software for subsequent modeling operations. The modeling software unit performs three-dimensional reconstruction on the processed data to generate a 3D model. The modeling software unit needs to support a variety of modeling algorithms and tools to meet the modeling requirements of industrial heritage with different shapes and structures.

[0016] Furthermore, the interest analysis unit combines association rule mining and clustering analysis to identify users' interests and preferences. The specific steps are as follows:

[0017] Data preprocessing: Collect users' behavior data, including browsing records, click counts, purchase records, etc. Clean the data to remove redundancy and outliers, and convert the data into a format suitable for association rule mining and clustering analysis.

[0018] Association rule mining: Use Apriori to extract frequent item sets and association rules from users' behavior data. Set the support and confidence thresholds to filter out meaningful association rules. The support represents the frequency of the item set appearing in the dataset, and the formula is Support(A→B) = P(A∪B). The confidence represents the probability that item set B appears under the condition that item set A appears, and the formula is Confidence(A→B) = P(B|A).

[0019] Clustering analysis: Use K-means to group users. Each group of users has similar interests and preferences. According to the results of association rule mining, use the frequent item sets and association rules as features and input them into K-means, and set the number of clusters K.

[0020] Result interpretation and verification: Analyze the clustering results, interpret the interests and preferences of different user groups, use indicators such as cross-validation and accuracy to evaluate the stability and accuracy of the clustering results, and adjust the parameters of association rule mining according to the clustering results to optimize the model performance.

[0021] Furthermore, the content recommendation unit uses a combined recommendation algorithm to calculate which industrial heritage a user is interested in and generates a recommendation list. The specific steps are as follows:

[0022] Data collection: Obtain user portraits and industrial heritage information.

[0023] Data cleaning: Identify and remove data that is irrelevant to the recommendation of industrial heritage, reasonably fill in missing values in the user's browsing history, ratings, or comments, and convert the user's browsing behavior into a unified scale;

[0024] Feature extraction: Extract text features from the titles, abstracts, contents, or user comments of industrial heritage and convert them into numerical features, and construct user feature vectors based on the user's behavior;

[0025] Collaborative filtering:

[0026] Construct a user-industrial heritage matrix: Based on the user's browsing history and rating situation, construct a user-industrial heritage interaction matrix. Assuming there are m users and n industrial heritages, the user-industrial heritage matrix R can be expressed as:

[0027]

[0028] where, r ij represents the rating or browsing times of user i for industrial heritage j. If a user has not browsed a certain industrial heritage, the corresponding element can be set to 0 or left blank;

[0029] Calculate similarity: Calculate the similarity between users with common browsing preferences or the similarity between industrial heritages with similar themes or contents:

[0030]

[0031] where, I uv is the set of industrial heritages that both user u and user v have interacted with, r ui is the rating or a certain metric value of user u for industrial heritage i, and r vi is the rating or metric value of user v for industrial heritage i;

[0032] Generate a recommendation list: Based on the browsing history of similar users and the similarity of industrial heritages, generate a recommendation list for the current user;

[0033] Content-based recommendation:

[0034] Feature matching: Match the feature vector of the user's browsing preference with the feature vector of the industrial heritage and calculate the similarity:

[0035]

[0036] where, is the feature vector of the user's reading preference, is the feature vector of the industrial heritage;

[0037] Rating Prediction: Based on content similarity, predict the potential interest or satisfaction of users towards industrial heritages they have not read.

[0038] Hybrid Recommendation:

[0039] Weight Allocation: According to the actual application scenario and data characteristics, allocate different weights to collaborative filtering and content-based recommendation.

[0040] Comprehensive Rating: Weightedly sum up the rating results of collaborative filtering and content-based recommendation according to the weights to obtain the final recommended rating.

[0041] Generate Recommendations: According to the final rating, select the industrial heritage with the highest rating as the recommended result.

[0042] User Feedback: Collect users' feedback on the recommended results.

[0043] Model Adjustment: According to users' feedback, dynamically adjust the parameters and weights of the recommendation model to optimize the recommendation effect.

[0044] The present invention has the following beneficial effects:

[0045] In the present invention, the cultural content of industrial heritages is displayed through diverse forms of expression, making the display more vivid and interesting. Association rule mining and clustering analysis are used to identify users' interests and preferences, and relevant industrial heritage content is intelligently recommended. At the same time, the visit route is customized according to users' interests to provide a differentiated experience, enabling users to more deeply understand and experience the cultural characteristics and connotations of specific industrial heritages. Description of the Drawings

[0046] Figure 1 It is a system block diagram of a digital display system for industrial heritages proposed by the present invention. Detailed Embodiments

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Please refer to Figure 1 As shown, the present invention is a digital display system for industrial heritages, including a front-end display layer, a back-end data management layer, and a technical support layer;

[0049] The front - end display layer includes a VR / AR experience module, an interactive touch - screen display module, a mobile application function module, a deep cultural interpretation module, and a diverse presentation form module. The VR / AR experience module is responsible for creating an immersive industrial heritage environment, realizing the construction of a virtual environment and user interaction. When users explore the industrial heritage environment through VR / AR devices, the VR / AR experience module calls the data stored in the digital asset management platform. The interactive touch - screen display module is responsible for displaying industrial heritage through a large touch - screen. Users can obtain detailed information through touch operations. The mobile application function module is responsible for developing an exclusive APP, providing functions such as online guided tours, interactive Q&A, and virtual exhibitions. The mobile application function collects users' feedback and behavior data, and the users' feedback and behavior data are transmitted to the data analysis and feedback module through the mobile application function module. The deep cultural interpretation module is responsible for telling the historical stories and biographies behind industrial heritage through forms such as animations and micro - films, increasing cultural depth, inviting industry experts to record videos or audio interpretations, and providing in - depth analysis from a professional perspective. The diverse presentation form module is responsible for designing games based on industrial heritage knowledge and using holographic technology to display key scenes or products of industrial heritage;

[0050] The back - end data management layer includes a digital asset management platform module, an intelligent recommendation system module, and a customized experience module. The digital asset management platform module is responsible for centrally storing and managing all digital content, including high - definition pictures, 3D models, video materials, audio commentaries, text introductions, etc. The digital asset management platform receives and stores the 3D models generated by the 3D scanning and modeling technology module. The intelligent recommendation system module is responsible for using association rule mining and clustering analysis to identify users' interests and preferences, and intelligently recommend relevant industrial heritage content. The intelligent recommendation system module generates personalized recommendation content by analyzing user data and transmits it to the interactive touch - screen display module through a data interface. The customized experience module is responsible for customizing the visit route according to users' interests and providing a differentiated experience;

[0051] The technical support layer includes a 3D scanning and modeling technology module, a big data and cloud computing module, and an artificial intelligence and machine learning module. The 3D scanning and modeling technology module is responsible for scanning industrial heritage to generate 3D models. The big data and cloud computing module is responsible for adopting a big data processing framework and a cloud computing platform to realize the distributed storage, parallel processing, and efficient access of data. The big data and cloud computing module provides data processing and storage capabilities for the intelligent recommendation system module. The artificial intelligence and machine learning module is used for content classification, intelligent Q&A, and sentiment analysis, and there is data interaction between the artificial intelligence and machine learning module and the data analysis and feedback module.

[0052] In one embodiment, for the above-mentioned in-depth cultural interpretation module, the in-depth cultural interpretation module includes a content planning unit, a multimedia creation unit, an expert resource unit, a data management and storage unit, and a front-end display unit. The content planning unit is responsible for planning and formulating the content framework and theme of in-depth cultural interpretation to ensure the accuracy and depth of the content. The multimedia creation unit creates content in multimedia forms such as animation and micro-films according to the requirements of the content planning unit to ensure the vividness and attractiveness of the content. The expert resource unit is responsible for inviting industry experts to conduct video or audio recordings, providing interpretations and analyses from a professional perspective, and enhancing the authority and credibility of the content. The data management and storage unit is responsible for managing and storing all multimedia content and expert interpretations in the in-depth cultural interpretation module to ensure the integrity and security of the data. The front-end display unit is responsible for presenting the content of the in-depth cultural interpretation module to users through the user interface to achieve interaction between users and the content.

[0053] In one embodiment, for the above-mentioned digital asset management platform module, the digital asset management platform module includes a data storage unit, a content management unit, a data invocation unit, a permission management unit, and a data analysis unit. The data storage unit is responsible for storing and backing up digital content to ensure the reliability and security of the data. The data storage unit is implemented using a database management system or cloud storage technology. The content management unit provides management functions such as content upload, download, editing, and deletion, and is a bridge for interaction between users and digital content. The content management unit includes a user interface and a background management interface. The data invocation unit is responsible for the efficient invocation and quick response of digital content to ensure that users can quickly obtain the required resources when needed. The data invocation unit uses distributed storage and caching technologies to optimize performance. The permission management unit provides permission control for users to access digital content to ensure the security and controllability of the data. The permission management unit includes user authentication, role assignment, and permission setting. The data analysis unit statistically analyzes the usage of digital content to provide data support for optimizing content management and enhancing the user experience. When a user needs to access digital content, the data invocation unit sends a request to the data storage unit to obtain the required resources. When a user attempts to access content, the content management unit sends a request to the permission management unit to verify the user's permissions. The data analysis unit statistically analyzes the usage of digital content, generates reports and data visualization charts, and feeds the reports and charts back to the content management unit for optimizing content management and enhancing the user experience.

[0054] In one embodiment, for the above-mentioned intelligent recommendation system module, the intelligent recommendation system module includes a data collection unit, an interest analysis unit, a content recommendation unit, and an effect evaluation unit. The data collection unit is responsible for comprehensively collecting user behavior data, including system logs, user feedback, etc. This unit needs to ensure the accuracy and integrity of the data to provide a reliable basis for subsequent analysis. The interest analysis unit uses big data analysis and machine learning algorithms to deeply mine and analyze user behavior data to identify users' interests and preferences. The interest analysis unit continuously optimizes the algorithm model to improve the accuracy and efficiency of the analysis. The content recommendation unit intelligently recommends relevant industrial heritage content based on users' interests and preferences. The content recommendation unit ensures the diversity and richness of the recommended content and adjusts the recommendation strategy in real time according to user feedback. The effect evaluation unit conducts real-time evaluation and optimization of the recommendation effect through user feedback, click-through rate, and conversion rate. This unit needs to regularly analyze the evaluation results and put forward improvement suggestions to ensure the continuous optimization and improvement of the recommendation system. The data collection unit transfers the collected user behavior data to the interest analysis unit, and the interest analysis unit transfers the analyzed user interests and preferences to the content recommendation unit.

[0055] In one embodiment, for the above-mentioned customized experience module, the customized experience module includes a route customization unit, an experience provision unit, and a cultural dissemination unit. The route customization unit generates a personalized tour route based on users' interests and preferences, combined with the characteristics and display requirements of industrial heritage. The route customization unit ensures the rationality and feasibility of the route while meeting users' personalized needs. The experience provision unit provides a differentiated experience for users according to the customized tour route. The experience includes the display of content, the setting of interactive projects, and the design of game sessions. The experience provision unit ensures the quality and effect of the experience and improves users' satisfaction. The cultural dissemination unit pays attention to the dissemination and popularization of industrial heritage culture while providing a personalized experience, including providing cultural interpretations, historical background introductions, interactive Q&A sessions, etc., to increase users' cultural identity. The interest analysis unit transfers the analyzed user interests and preferences to the route customization unit, and the route customization unit transfers the generated tour route to the experience provision unit. The experience provision unit collaborates with the cultural dissemination unit to pay attention to the dissemination and popularization of industrial heritage culture while providing a personalized experience.

[0056] In one embodiment, for the above-mentioned 3D scanning and modeling technology module, the 3D scanning and modeling technology module includes a scanning device unit, a data processing unit, and a modeling software unit. The scanning device unit is responsible for scanning industrial heritage using a 3D scanning device to capture its surface details and shape features. The scanning device unit needs to ensure the accuracy and integrity of the scanning to provide a reliable data basis for subsequent modeling. The data processing unit preprocesses and cleans the scanned data to remove noise and redundant information, improving the quality and usability of the data. The data processing unit also needs to convert the processed data into a format recognizable by the modeling software for subsequent modeling operations. The modeling software unit performs three-dimensional reconstruction on the processed data to generate a 3D model. The modeling software unit needs to support a variety of modeling algorithms and tools to meet the modeling requirements of industrial heritage with different shapes and structures.

[0057] In one embodiment, for the above-mentioned interest analysis unit, the interest analysis unit combines association rule mining and clustering analysis to identify users' interests and preferences. The specific steps are as follows:

[0058] Data preprocessing: Collect user behavior data, including browsing records, click counts, purchase records, etc. Clean the data to remove redundancy and outliers, and convert the data into a format suitable for association rule mining and clustering analysis.

[0059] Association rule mining: Use Apriori to extract frequent item sets and association rules from user behavior data. Set support and confidence thresholds to filter out meaningful association rules. Support represents the frequency of an item set appearing in the dataset, and the formula is Support(A→B) = P(A∪B). Confidence represents the probability that item set B appears under the condition that item set A appears, and the formula is Confidence(A→B) = P(B|A).

[0060] Clustering analysis: Use K-means to group users. Each group of users has similar interests and preferences. According to the results of association rule mining, use the frequent item sets and association rules as features and input them into K-means, and set the number of clusters K.

[0061] Result interpretation and verification: Analyze the clustering results, interpret the interests and preferences of different user groups, and use indicators such as cross-validation and accuracy to evaluate the stability and accuracy of the clustering results. Adjust the parameters of association rule mining according to the clustering results to optimize the model performance.

[0062] Data preprocessing: Convert user behavior data into a format suitable for association rule mining and clustering analysis, such as a user-item matrix.

[0063] Association rule mining: Use the Apriori algorithm to extract frequent item sets and association rules. For example, discover the association rule that "80% of the users who buy milk also buy bread", with a support of 0.2 and a confidence of 0.8.

[0064] Cluster analysis: Use the K-means algorithm to group users. Based on the results of association rule mining, use the frequent item sets and association rules as features and input them into the K-means algorithm. Set the number of clusters K to 3, and obtain three user groups: Group 1 likes to buy milk and bread, Group 2 likes to buy electronic products and books, and Group 3 likes to buy clothing and cosmetics.

[0065] Result interpretation and verification: Analyze the clustering results and find that the users in Group 1 may be interested in food and daily necessities, the users in Group 2 may be interested in technology and culture, and the users in Group 3 may be interested in fashion and beauty. Use cross-validation to evaluate the stability and accuracy of the clustering results and find that the accuracy of the clustering results is relatively high. Adjust the parameters of association rule mining according to the clustering results, such as increasing the support threshold to filter out uncommon association rules, and further optimize the model performance.

[0066] In one embodiment, for the above content recommendation unit, the content recommendation unit uses a combined recommendation algorithm to calculate which industrial heritages a user is interested in and generates a recommendation list. The specific steps are as follows:

[0067] Data collection: Obtain user portraits and industrial heritage information;

[0068] Data cleaning: Identify and remove data irrelevant to industrial heritage recommendations, reasonably fill in missing values in the user's browsing history, ratings, or comments, and convert the user's browsing behavior into a unified scale;

[0069] Feature extraction: Extract text features from the titles, abstracts, contents, or user comments of industrial heritages and convert them into numerical features, and construct a user feature vector based on the user's behavior;

[0070] Collaborative filtering:

[0071] Construct a user-industrial heritage matrix: According to the user's browsing history and rating situation, construct a user-industrial heritage interaction matrix. Assuming there are m users and n industrial heritages, the user-industrial heritage matrix R can be represented as:

[0072]

[0073] where r ij represents the rating or browsing times of user i for industrial heritage j. If a user has not browsed a certain industrial heritage, the corresponding element can be set to 0 or left blank;

[0074] Calculate similarity: Calculate the similarity between users with common browsing preferences or the similarity between industrial heritages with similar themes and contents:

[0075]

[0076] where I uv is the set of industrial heritages that both user u and user v have interacted with, r ui is the rating or some metric value of user u for industrial heritage i, r vi is the rating or metric value of user v for industrial heritage i;

[0077] Generate a recommendation list: Generate a recommendation list for the current user based on the browsing history of similar users and the similarity of industrial heritages;

[0078] Content-based recommendation:

[0079] Feature matching: Match the feature vector of the user's browsing preference with the feature vector of the industrial heritage and calculate the similarity:

[0080]

[0081] where is the feature vector of the user's reading preference, is the feature vector of the industrial heritage;

[0082] Rating prediction: Predict the potential interest or satisfaction of the user in industrial heritages not yet read based on content similarity;

[0083] Hybrid recommendation:

[0084] Weight assignment: Assign different weights to collaborative filtering and content-based recommendation according to the actual application scenario and data characteristics;

[0085] Comprehensive rating: Perform a weighted sum of the rating results of collaborative filtering and content-based recommendation according to the weights to obtain the final recommendation rating;

[0086] Generate a recommendation: Select the industrial heritage with the highest rating as the recommendation result according to the final rating;

[0087] User feedback: Collect the feedback of users on the recommendation results;

[0088] Model adjustment: Dynamically adjust the parameters and weights of the recommendation model according to user feedback to optimize the recommendation effect.

[0089] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An industrial heritage digital display system, characterized in that, It includes a front-end display layer, a back-end data management layer, and a technical support layer; The front-end display layer includes a VR / AR experience module, an interactive touch screen display module, a mobile application function module, a deep cultural interpretation module, and a diverse presentation form module. The VR / AR experience module is responsible for creating an immersive industrial heritage environment, realizing the construction of a virtual environment and user interaction. When a user explores the industrial heritage environment through VR / AR devices, the VR / AR experience module calls the data stored in the digital asset management platform. The interactive touch screen display module is responsible for displaying industrial heritage through a large touch screen. The mobile application function module is responsible for developing a dedicated APP. The mobile application function collects the feedback and behavior data of users. The feedback and behavior data of users are transmitted to the intelligent recommendation system module through the mobile application function module. The deep cultural interpretation module is responsible for telling the historical stories and biographies of figures behind industrial heritage. The diverse presentation form module is responsible for designing games based on industrial heritage knowledge and using holographic technology to display key scenes or products of industrial heritage; The back-end data management layer includes a digital asset management platform module, an intelligent recommendation system module, and a customized experience module. The digital asset management platform module is responsible for centrally storing and managing all digital content. The digital asset management platform receives and stores the 3D models generated by the 3D scanning and modeling technology module. The intelligent recommendation system module is responsible for identifying users' interests and preferences using association rule mining and clustering analysis, and intelligently recommending relevant industrial heritage content. The intelligent recommendation system module generates personalized recommendation content by analyzing user data and transmits it to the interactive touch screen display module through a data interface. The customized experience module is responsible for customizing a visit route according to users' interests and providing a differentiated experience; The technical support layer includes a 3D scanning and modeling technology module, a big data and cloud computing module, and an artificial intelligence and machine learning module. The 3D scanning and modeling technology module is responsible for scanning industrial heritage to generate 3D models. The big data and cloud computing module is responsible for adopting a big data processing framework and a cloud computing platform. The big data and cloud computing module provides data processing and storage capabilities for the intelligent recommendation system module. The artificial intelligence and machine learning module is used for content classification, intelligent question answering, and sentiment analysis. There is data interaction between the artificial intelligence and machine learning module and the data analysis and feedback module.

2. The digital display system for industrial heritage according to claim 1, characterized in that The deep cultural interpretation module includes a content planning unit, a multimedia creation unit, an expert resource unit, a data management and storage unit, and a front-end display unit. The content planning unit is responsible for planning and formulating the content framework and theme of deep cultural interpretation. The multimedia creation unit creates content in multimedia form according to the requirements of the content planning unit. The expert resource unit is responsible for inviting industry experts to record videos or audios and provide interpretations and analyses from a professional perspective. The data management and storage unit is responsible for managing and storing all multimedia content and expert interpretations in the deep cultural interpretation module. The front-end display unit is responsible for presenting the content of the deep cultural interpretation module to users through the user interface and realizing the interaction between users and the content.

3. An industrial heritage digital display system according to claim 1, characterized in that, The digital asset management platform module includes a data storage unit, a content management unit, a data invocation unit, a permission management unit, and a data analysis unit. The data storage unit is responsible for storing and backing up digital content. The content management unit provides content management functions, and the content management unit includes a user interface and a background management interface. The data invocation unit is responsible for invoking and responding to digital content, and the data invocation unit adopts distributed storage and caching technologies. The permission management unit provides permission control for users to access digital content, and the permission management unit includes user authentication, role assignment, and permission settings. The data analysis unit statistically analyzes the usage of digital content. When a user needs to access digital content, the data invocation unit sends a request to the data storage unit to obtain the required resources. When a user attempts to access content, the content management unit sends a request to the permission management unit to verify the user's permissions. The data analysis unit statistically analyzes the usage of digital content, generates reports and data visualization charts, and feeds the reports and charts back to the content management unit for optimizing content management and enhancing the user experience.

4. An industrial heritage digital display system according to claim 1, characterized in that, The intelligent recommendation system module includes a data collection unit, an interest analysis unit, a content recommendation unit, and an effect evaluation unit. The data collection unit is responsible for collecting users' behavioral data. The interest analysis unit uses big data analysis and machine learning algorithms to deeply mine and analyze users' behavioral data and identify users' interests and preferences. The content recommendation unit intelligently recommends relevant industrial heritage content based on users' interests and preferences. The effect evaluation unit real-time evaluates and optimizes the recommendation effect through user feedback, click-through rate, and conversion rate. The data collection unit transmits the collected users' behavioral data to the interest analysis unit, and the interest analysis unit transmits the analyzed users' interests and preferences to the content recommendation unit.

5. An industrial heritage digital display system according to claim 4, characterized in that, The customized experience module includes a route customization unit, an experience provision unit, and a cultural dissemination unit. The route customization unit generates a personalized tour route based on the user's interests and preferences, combined with the characteristics and display requirements of industrial heritage. The experience provision unit provides a differentiated experience for the user according to the customized tour route. The experience includes the display of content, the setting of interactive projects, and the design of game sessions. The cultural dissemination unit focuses on the dissemination and popularization of industrial heritage culture while providing a personalized experience. The interest analysis unit transmits the analyzed user interests and preferences to the route customization unit. The route customization unit transmits the generated tour route to the experience provision unit. The experience provision unit collaborates with the cultural dissemination unit while providing a personalized experience.

6. The digital display system for industrial heritage according to claim 1, wherein The 3D scanning and modeling technology module includes a scanning device unit, a data processing unit, and a modeling software unit. The scanning device unit is responsible for scanning industrial heritage using 3D scanning devices to capture its surface details and shape features. The data processing unit preprocesses and cleans the scanned data to remove noise and redundant information. The modeling software unit performs three-dimensional reconstruction on the processed data to generate a 3D model.

7. An industrial heritage digital display system according to claim 4, characterized in that, The interest analysis unit combines association rule mining and clustering analysis to identify the user's interests and preferences. The specific steps are as follows: Data preprocessing: Collect user behavior data, clean the data to remove redundancy and outliers, and convert the data into a format suitable for association rule mining and clustering analysis. Association rule mining: Use Apriori to extract frequent item sets and association rules from user behavior data. Set support and confidence thresholds to filter out meaningful association rules. The support represents the frequency of an item set appearing in the dataset, and the formula is Support(A→B) = P(A∪B). The confidence represents the probability of item set B appearing under the condition that item set A appears, and the formula is Confidence(A→B) = P(B|A). Clustering analysis: Use K-means to group users. Each group of users has similar interests and preferences. According to the results of association rule mining, use the frequent item sets and association rules as features and input them into K-means, and set the number of clusters K. Result interpretation and verification: Analyze the clustering results, interpret the interests and preferences of different user groups, evaluate the stability and accuracy of the clustering results, and adjust the parameters of association rule mining according to the clustering results to optimize the model performance.

8. An industrial heritage digital display system according to claim 4, wherein The content recommendation unit uses a combined recommendation algorithm to calculate which industrial heritage the user is interested in and generates a recommendation list. The specific steps are as follows: Data collection: Obtain user portraits and industrial heritage information. Data cleaning: Identify and remove data irrelevant to industrial heritage recommendation, reasonably fill in missing values in the user's browsing records, ratings, or comments, and convert the user's browsing behavior into a unified scale. Feature extraction: Extract text features from the titles, abstracts, content, or user comments of industrial heritage and convert them into numerical features. Construct a user feature vector based on the user's behavior. Collaborative filtering: Construct a user-industrial heritage matrix: Based on the user's browsing history and rating situation, construct a user-industrial heritage interaction matrix. Assuming there are m users and n industrial heritages, the user-industrial heritage matrix R can be expressed as: Among them, r ij represents the score or the number of views of industrial heritage j by user i. If a user has not viewed a certain industrial heritage, the corresponding element can be set to 0 or left blank; Calculate similarity: Calculate the similarity between users with common browsing preferences or the similarity between industrial heritages with similar themes and contents: Among them, I uv is the set of industrial heritages that both user u and user v have interacted with, and r ui is the score or some measure of user u for industrial heritage i, and r vi is the score or measure of user v for industrial heritage i; Generate a recommendation list: Based on the browsing history of similar users and the similarity of industrial heritages, generate a recommendation list for the current user; Content-based recommendation: Feature matching: Match the feature vector of the user's browsing preference with the feature vector of the industrial heritage and calculate the similarity: Among them, is the feature vector of the user's reading preference, is the feature vector of the industrial heritage; Rating prediction: Based on the content similarity, predict the user's potential interest or satisfaction with the industrial heritage that has not been read; Hybrid recommendation: Weight assignment: According to the actual application scenario and data characteristics, assign different weights to collaborative filtering and content-based recommendation; Comprehensive rating: Perform a weighted sum of the rating results of collaborative filtering and content-based recommendation according to the weights to obtain the final recommendation rating; Generate recommendations: According to the final rating, select the industrial heritage with the highest rating as the recommendation result; User feedback: Collect the user's feedback on the recommendation results; Model adjustment: According to the user's feedback, dynamically adjust the parameters and weights of the recommendation model to optimize the recommendation effect.

Images