Non-perpetual culture information interaction method and system

Abstract

The invention relates to the technical field of information interaction, in particular to a non-abandoned culture information interaction method and system, which is characterized in that based on multi-dimensional features of non-abandoned culture information, hierarchical division is performed on the multi-dimensional features, multi-level semantic nodes are constructed according to hierarchical division results, and a semantic index tree of the non-abandoned culture information is obtained. According to the method, systematic hierarchical analysis and semantic node construction are carried out on the multi-dimensional features of the non-perpetual and cultural information, so that the organization and retrieval efficiency of the information is optimized. By defining the hierarchical relationship and the node association path, the complex non-perpetual culture data is structured and hierarchical, and a basis is provided for subsequent semantic matching and retrieval. In a user query link, the scheme significantly improves the retrieval accuracy through semantic information analysis and a multi-level semantic node matching mechanism, and solves the redundancy problem caused by information fuzzy matching in a traditional method.

Description

Technical Field

[0001] The present invention relates to the field of information interaction technology, and in particular to a method and system for interacting with intangible cultural heritage information. Background Art

[0002] The field of information interaction technology includes technologies and methods related to data transmission, processing, display and user interaction. The core content of this technical field mainly involves human-computer interaction interface design, data collection and integration, information transmission protocol design and data display method optimization, with the aim of achieving efficient communication and collaboration between users and information systems.

[0003] Among them, the intangible cultural heritage information interaction method refers to the method of optimizing the collection, organization, transmission and display of intangible cultural heritage information through specific technical means. The main topics include the classification and coding of intangible cultural heritage data, the establishment of semantic associations, the construction of interaction models, and the design of multimedia display methods.

[0004] When processing intangible cultural heritage information, the existing technology is difficult to systematically divide and analyze the multi-dimensional features. The organization of information is mostly presented as a single-layer planar structure, and it is impossible to establish an effective hierarchical association relationship. For example, in the processing of regional and temporal features, it is impossible to associate with specific semantic contexts, resulting in poor logic between data. In the process of information retrieval, the existing technology can usually only perform shallow matching based on keywords. For complex query requirements, such as queries involving time, region and skills at the same time, it is difficult to complete accurate retrieval of multi-level nodes, resulting in users having to screen repeatedly to find the target content. In the analysis of hot spot features, the existing technology is difficult to integrate the multi-dimensional features of time, region and content keywords. Usually, only single feature statistics can be performed, and there is a lack of analysis of the correlation and dynamic change trends of hot spot features. For example, the change pattern and diffusion range of hot spot distribution over time are often unable to be accurately identified. In terms of interactive display, the existing technology is mainly based on static display methods and lacks the ability to display real-time dynamic changes in hot spots. For example, the diffusion path and trend analysis of hot spots can only be presented in tables or static charts, which cannot meet the user's intuitive perception needs for dynamic changes, resulting in poor information visualization and limited application scenarios. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the embodiment of the present invention provides a method and system for interacting with intangible cultural heritage information. The technical solution is as follows:

[0006] A method for interacting with intangible cultural heritage information comprises the following steps:

[0007] S1: Based on the multidimensional features of intangible cultural heritage information, the multidimensional features are hierarchically divided, and multi-level semantic nodes are constructed according to the hierarchical division results to obtain the semantic index tree of intangible cultural heritage information;

[0008] S2: parsing the query content input by the user, extracting the semantic information in the query content, matching the semantic information with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and generating a matching retrieval node path set;

[0009] S3: Obtain key features of semantic nodes in the matched search node path set, count the cumulative number of occurrences of the key features in the matched search node path set, mark the key features corresponding to the highest number of occurrences, and generate a set of intangible cultural hotspot features;

[0010] S4: Construct a multi-level response node network diagram with reference to the intangible cultural heritage hotspot feature set, use the marked key features as the core nodes in the node network diagram, extract the time series data of the core nodes, predict the future change trend of the core nodes and the diffusion range of the hotspot region with reference to the time series data, and generate a hotspot propagation dynamic prediction result;

[0011] S5: Based on the dynamic prediction results of hot spot propagation, the distribution and dynamic change range of core nodes in the node network diagram are mapped to the interactive interface and multi-layer screening and regional aggregation are performed to generate an interactive display list of intangible cultural heritage information.

[0012] The present invention has been improved in that the semantic index tree of the intangible cultural heritage information includes multi-level semantic nodes, hierarchical relationships, associated paths and information identifiers; the matched retrieval node path set includes qualified semantic nodes, retrieval paths corresponding to the semantic nodes and semantic information matching results; the intangible cultural heritage hot spot feature set includes time tags, regional identifiers and content keywords; the hot spot propagation dynamic prediction results include future change trends of core nodes, dynamic diffusion ranges of hot spot regions and time series data; the intangible cultural heritage information interactive display list includes core node distribution, dynamic change ranges and multi-dimensional display content.

[0013] The present invention is improved in that, based on the multidimensional features of intangible cultural heritage information, the multidimensional features are hierarchically divided, and multi-level semantic nodes are constructed according to the hierarchical division results to obtain the semantic index tree of the intangible cultural heritage information. The specific steps are as follows:

[0014] S101: Based on the multi-dimensional features of intangible cultural heritage information, including theme, region, time and skills, the multi-dimensional features are analyzed in layers, and the layers are divided according to the characteristics of each dimension and the upper and lower relationships between the layers are determined to generate the multi-dimensional feature hierarchical division results;

[0015] S102: Based on the multi-dimensional feature hierarchical division result, construct semantic nodes corresponding to each level, extract associated attributes of the semantic nodes, bind the associated attributes with the nodes in a corresponding relationship, and generate a multi-level semantic node set;

[0016] S103: Based on the multi-level semantic node set, extract the hierarchical relationship, associated path and information identifier of the corresponding features in the semantic nodes, map the hierarchical relationship and path to the corresponding semantic structure, and establish a semantic index tree of intangible cultural heritage information.

[0017] The improvement of the present invention is that the specific steps of parsing the query content input by the user, extracting the semantic information in the query content, matching the semantic information with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and generating a matching retrieval node path set are as follows:

[0018] S201: Based on the query content input by the user, the semantic information in the query content is parsed, the semantic information and its context-related attributes are extracted, the semantic information is combined with the context, and a user query semantic set is generated;

[0019] S202: Based on the user query semantic set, the query semantics are matched one by one with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and according to the matching results, whether the semantic nodes meet the user's query conditions is determined, and the semantic nodes that meet the conditions are screened to generate a semantic node set that meets the conditions;

[0020] S203: Based on the semantic node set that meets the conditions, extract the association path of the semantic node, correspond the association path with the matching query semantics according to the priority of the association path, output the retrieval path of the query semantics, and generate a matching retrieval node path set.

[0021] The present invention is improved in that the query semantics is matched one by one with the semantic nodes in the semantic index tree of the intangible cultural heritage information by using the formula:

[0022]

[0023] Calculate keyword q i and n i The similarity score sim(q i ,n i ), judging the similarity between the query semantics and the semantic nodes according to the similarity score;

[0024] Among them, d(q i ,n i ) indicates the keyword q i and n i The edit distance between i | indicates keyword q i The number of characters, |ni | indicates semantic node keyword n i The number of characters, i is q i and n i The character index in .

[0025] The present invention is improved in that the key features of the semantic nodes in the matched search node path set are obtained, the accumulated number of occurrences of the key features in the matched search node path set is counted, the key features corresponding to the highest number of occurrences are marked, and the specific steps of generating the intangible cultural hot spot feature set are as follows:

[0026] S301: based on the matched search node path set, extracting time tags, region identifiers and content keyword information corresponding to semantic nodes in the matched node path set, aggregating the extracted feature information, and generating a key feature set;

[0027] S302: Based on the key feature set, count the cumulative occurrences of time tags, region identifiers and content keywords in the matching search node path set, record the time tags, region identifiers and content keywords with the highest occurrences, and generate key feature statistics results;

[0028] S303: Based on the statistical results of the key features, mark the time tags, region identifiers and content keywords with the highest cumulative occurrence times, analyze their correlation characteristics and co-occurrence relationships, and integrate the analysis results to generate a set of intangible cultural heritage hot spot features.

[0029] The present invention is improved in that a multi-level response node network diagram is constructed with reference to the intangible cultural heritage hot spot feature set, the marked key features are used as core nodes in the node network diagram, time series data of the core nodes are extracted, and the future change trend of the core nodes and the diffusion range of the hot spot area are predicted with reference to the time series data. The specific steps of generating the hot spot propagation dynamic prediction results are as follows:

[0030] S401: Based on the intangible cultural heritage hot spot feature set, extract the marked key features from it, construct a response network with the key features as core nodes, associate the key features with its upper and lower layer nodes and display them in a visual manner, and generate a multi-level response node network diagram;

[0031] S402: Based on the multi-level response node network diagram, extract the time series data of the core nodes, analyze the change characteristics of the time series data, determine the key activity time period of the hotspot nodes based on the change characteristics, and generate the time series characteristics of the core nodes;

[0032] S403: Based on the time series characteristics of the core nodes and in combination with the regional characteristics of the core nodes, the future change trend of the core nodes and the diffusion range of the hotspot regions are predicted, and the prediction results are integrated into hotspot propagation dynamic analysis data to generate hotspot propagation dynamic prediction results.

[0033] The present invention has the following improvements: for predicting the future change trend of core nodes and the diffusion range of hot spots, the formula is adopted:

[0034] X(t+1)=α·R(t)+β·G(t)+γ·ΔR(t);

[0035] Calculate the change value X(t+1) at the next time step t;

[0036] Among them, R(t) is the activity frequency at the current time step t, G(t) is the geographical coverage index at the current time step t, ΔR(t) is the rate of change of the activity frequency at the current time step t, and α, β, and γ are weight parameters.

[0037] The present invention is improved in that, based on the dynamic prediction results of hot spot propagation, the core node distribution and dynamic change range in the node network diagram are mapped to the interactive interface and multi-layer screening and regional aggregation are performed to generate the intangible cultural heritage information interactive display list in the following specific steps:

[0038] S501: Based on the hotspot propagation dynamic prediction result, the core node distribution and the dynamic change range are mapped to the interactive interface to generate an interactive interface hotspot distribution layer;

[0039] S502: Based on the hotspot distribution layer of the interactive interface, the content of the hotspot area is multi-layered screened according to the time and region dimensions, and the screened results are aggregated by region to generate hotspot area aggregated screening results;

[0040] S503: Based on the aggregated screening results of the hotspot areas, the content of the hotspot areas is displayed in multiple dimensions, including time change trends, geographical distribution ranges and key feature related data, and an interactive display list of intangible cultural heritage information is generated.

[0041] A non-legacy cultural information interaction system, the system comprising:

[0042] The multidimensional feature analysis module divides the multidimensional features into levels based on the multidimensional features of intangible cultural heritage information, constructs multi-level semantic nodes according to the hierarchical division results, extracts the hierarchical relationships, association paths and information identifiers in the multi-level semantic nodes, and establishes a semantic index tree for intangible cultural heritage information;

[0043] The semantic query matching module parses the query content input by the user based on the semantic index tree of the intangible cultural heritage information, extracts the semantic information in the query content, matches the semantic information with the semantic nodes in the semantic index tree, and generates a matching retrieval node path set;

[0044] The key feature extraction module extracts key features in the semantic nodes based on the matched retrieval node path set, counts the cumulative occurrence times of the key features in the matched node path set, marks the key features with the highest occurrence times, and generates a set of intangible cultural hot spot features;

[0045] The node network prediction module constructs a multi-level response node network diagram based on the intangible cultural heritage hot spot feature set, uses the marked key features as the core nodes in the node network diagram, extracts the time series data of the core nodes, and predicts the future change trend of the core nodes and the diffusion range of the hot spot region with reference to the time series data, and generates a hot spot propagation dynamic prediction result;

[0046] Based on the dynamic prediction results of hot spot propagation, the interactive display generation module maps the core node distribution and dynamic change range in the node network diagram to the interactive interface, performs multi-layer screening and regional aggregation of the content, and generates an interactive display list of intangible cultural heritage information.

[0047] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0048] Through systematic hierarchical analysis of the multidimensional features of intangible cultural heritage information and the construction of semantic nodes, the organization and retrieval efficiency of information are optimized. By clarifying the hierarchical relationship and node association path, the complex intangible cultural heritage data is structured and hierarchical, providing a basis for subsequent semantic matching and retrieval. In the user query stage, the solution significantly improves the retrieval accuracy through semantic information analysis and multi-level semantic node matching mechanism, and solves the redundancy problem caused by fuzzy information matching in traditional methods. In the analysis of hot spot features, the solution can accurately identify hot spot features and effectively summarize dynamic change trends through statistical analysis of multidimensional features such as time tags, regional identifiers and content keywords and extraction of co-occurrence relationships. In particular, in terms of dynamic prediction of hot spot propagation, the introduction of time series analysis and regional diffusion range prediction methods makes the changes in hot spot trends visualized and dynamic. Finally, the generation of the interactive interface comprehensively displays the distribution and association characteristics of intangible cultural heritage hot spots through multi-layer screening and regional aggregation, realizing the multi-dimensional and visual presentation of content. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 is a flow chart of the method of the present invention;

[0051] Figure 2 This is a detailed flow chart of step S1 of the present invention;

[0052] Figure 3 This is a detailed flow chart of step S2 of the present invention;

[0053] Figure 4 This is a detailed flow chart of step S3 of the present invention;

[0054] Figure 5 This is a detailed flow chart of step S4 of the present invention;

[0055] Figure 6 This is a detailed flow chart of step S5 of the present invention;

[0056] Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0058] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0059] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0060] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0061] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0062] The embodiment of the present invention provides a method for interacting with intangible cultural heritage information, comprising the following steps:

[0063] S1: Based on the multidimensional features of intangible cultural heritage information, the multidimensional features are hierarchically divided, and multi-level semantic nodes are constructed according to the hierarchical division results to obtain the semantic index tree of intangible cultural heritage information;

[0064] S2: Parse the query content input by the user, extract the semantic information in the query content, match the semantic information with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and generate a set of matching retrieval node paths;

[0065] S3: Obtain key features of semantic nodes in the matched search node path set, count the cumulative number of occurrences of key features in the matched search node path set, mark the key features corresponding to the highest number of occurrences, and generate a set of intangible cultural hotspot features;

[0066] S4: Construct a multi-level response node network diagram with reference to the intangible cultural heritage hotspot feature set, use the marked key features as the core nodes in the node network diagram, extract the time series data of the core nodes, and predict the future change trend of the core nodes and the diffusion range of the hotspot region with reference to the time series data to generate the dynamic prediction results of hotspot propagation;

[0067] S5: Based on the dynamic prediction results of hotspot propagation, the distribution and dynamic change range of core nodes in the node network diagram are mapped to the interactive interface and multi-layer screening and regional aggregation are performed to generate an interactive display list of intangible cultural heritage information;

[0068] The semantic index tree of intangible cultural heritage information includes multi-level semantic nodes, hierarchical relationships, association paths and information identifiers. The matching retrieval node path set includes qualified semantic nodes, retrieval paths corresponding to semantic nodes and semantic information matching results. The intangible cultural heritage hot spot feature set includes time tags, regional identifiers and content keywords. The dynamic prediction results of hot spot propagation include future change trends of core nodes, dynamic diffusion range of hot spot regions and time series data. The interactive display list of intangible cultural heritage information includes core node distribution, dynamic change range and multi-dimensional display content.

[0069] See also Figure 2 Based on the multidimensional features of intangible cultural heritage information, the multidimensional features are hierarchically divided, and multi-level semantic nodes are constructed according to the hierarchical division results. The specific steps to obtain the semantic index tree of intangible cultural heritage information are as follows:

[0070] S101: Based on the multi-dimensional features of intangible cultural heritage information, including theme, region, time and skills, the multi-dimensional features are analyzed in layers, and the layers are divided according to the characteristics of each dimension and the upper and lower relationships between the layers are determined to generate the multi-dimensional feature hierarchical division results;

[0071] The subject features are classified and counted according to categories, for example, the classification includes traditional handicrafts, folk activities, drama arts and other categories. For regional characteristics, they are subdivided into provincial, municipal and county areas according to geographical scope. If the intangible cultural heritage skills involve multiple regions, the largest geographical scope is used as the main classification basis. The time characteristics are subdivided into four levels: annual, quarterly, monthly and daily. Time nodes with distribution density higher than 30% are marked as high-frequency time nodes. The skill characteristics are divided into traditional crafts, improved crafts and modern crafts according to the craft classification level. The data of each feature dimension is called for feature hierarchical analysis. For example, the traditional handicraft category includes subcategories of hand embroidery and wood carving crafts. The hierarchical relationship is established layer by layer, and the hierarchical relationship is mapped to the complete feature dimension structure to form a feature stratification result containing hierarchical relationship. All feature stratification results are stored in a unified management manner to generate a multi-dimensional feature hierarchical division result.

[0072] S102: Based on the hierarchical division result of the multi-dimensional features, construct semantic nodes corresponding to each level, extract associated attributes of the semantic nodes, bind the associated attributes with the nodes in a corresponding relationship, and generate a multi-level semantic node set;

[0073] For the hand embroidery category, the skill attributes it contains are extracted, including the type of craft, the number of practitioners and the representative area. The extracted craft type is identified as embroidery stitches, and the areas with more than 100 practitioners are divided into main representative areas. These attribute values ​​are assigned to the corresponding semantic nodes to construct a semantic node set related to embroidery crafts. In the construction of nodes at the regional level, if a county-level area contains more than 50 kinds of intangible cultural heritage skills, it is preferentially classified as a municipal node and marked as a key regional node to complete the association between node attributes and levels. In terms of time characteristics, folk activities that are held repeatedly every year are marked as high-frequency activities, and their time nodes are bound to the annual nodes. The constructed nodes are associated with each other in the upper and lower levels according to the information of the corresponding levels. The semantic nodes are fully defined through the semantic node set to generate a multi-level semantic node set.

[0074] S103: Based on the multi-level semantic node set, extract the hierarchical relationship, associated path and information identifier of the corresponding features in the semantic node, map the hierarchical relationship and path to the corresponding semantic structure, and establish a semantic index tree of intangible cultural heritage information;

[0075] Extract hierarchical relationships, associated paths, and information identifiers from semantic node sets. For example, extract the hierarchical relationships of embroidery crafts, including the craft distribution paths at the national, provincial, municipal, and county levels. Extract the festival distribution paths marked with folk activity time in the associated paths. Optimize the paths by combining the geographic identifiers of representative areas. Bind the craft categories and regional associated identifiers to the hierarchical relationship paths. Ensure that the path nodes contain complete hierarchical and distribution information. Annotate the integrity and correctness of the information by establishing upper and lower-level relationships. If the content of a node completely contains the content of another node, it is marked as the parent node. A hierarchical connection is established between the two through an associated path, and the identifier of the child node is bound to the identifier of the parent node in the associated path. For example, for the needle method classification in the "hand embroidery" category, if the embroidery needle method node contains flat stitch and lock stitch sub-nodes, then the upper and lower layer relationship between the hand embroidery node and the flat stitch and lock stitch nodes is established. At the same time, the representative area and time stamp of the hand embroidery node are recorded in the path, the information identifier is integrated into the path node, and the craft category and regional path information are mapped to the semantic index tree, finally forming a semantic index tree of intangible cultural heritage information containing complete paths and node relationships.

[0076] See also Figure 3 , parse the query content input by the user, extract the semantic information in the query content, match the semantic information with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and generate the matching retrieval node path set. The specific steps are as follows:

[0077] S201: Based on the query content input by the user, the semantic information in the query content is parsed, the semantic information and its context-related attributes are extracted, the semantic information is combined with the context, and a user query semantic set is generated;

[0078] The sentences are segmented and tagged with parts of speech through natural language processing tools, and keywords such as "embroidery", "traditional skills", "Spring Festival customs" and so on are extracted. For the contextual information in the input content, such as the time and theme association between "Spring Festival" and "embroidery" activities in "embroidery activities during the Spring Festival", the time attribute is marked as "Spring Festival" and the theme attribute is marked as "embroidery". The time information is converted into comparable time intervals through time series analysis tools (such as "Spring Festival" is parsed as "February 10 to February 17, 2025 in the Gregorian calendar"). For the geographical information in the context, such as the input of "Jingdezhen, Jiangxi", "Jingdezhen" is extracted as the geographical identifier, which is mapped with the administrative division code to generate a geographical feature identifier; the above-extracted keywords, time intervals, and geographical identifiers are integrated to form a hierarchical structure, and the tree-like storage structure is used to record the keywords and context-related attributes, and grouped according to time, region and theme features to finally generate a user query semantic set.

[0079] S202: Based on the user query semantic set, the query semantics are matched one by one with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and according to the matching results, whether the semantic nodes meet the user's query conditions is determined, and the semantic nodes that meet the conditions are screened to generate a semantic node set that meets the conditions;

[0080] To match the query semantics with the semantic nodes in the semantic index tree of intangible cultural heritage information one by one, the formula is used:

[0081]

[0082] Calculate keyword q i and n i The similarity score sim(q i ,n i ), judging the similarity between the query semantics and the semantic nodes according to the similarity score;

[0083] Among them, d(q i ,n i ) indicates the keyword q i and n i The edit distance between q i Convert to n i The minimum number of steps required is obtained by constructing the edit distance matrix through dynamic programming. The matrix D[i][j] represents q i The first i characters and n i The edit distance between the first j characters of , the recursive formula is: The boundary conditions are D[0][j] = j and D[i][0] = i, which represents the conversion operands of the empty string to another string, q i [i],n i [j] represents q i and n i The characters at index i and j. Access the corresponding characters through the string index. min means taking the minimum number of editing steps among the three operations: Delete operation: Change q i The first i characters of i The first j-1 characters of , then delete q i [i]. Corresponds to D[i][j-1]+1 in the recursive formula. Insertion operation: replace q i The first i-1 characters are converted to n i The first j characters of , and then insert n i [j]. Corresponds to D[i-1][j]+1 in the recursive formula. Replacement operation: replace q i The first i-1 characters are converted to n i The first j-1 characters of , and then qi Replace [i] with n i [j]. Corresponding to D[i - 1][j - 1] + 1 in the recurrence formula. |q i | represents the keyword q i The length (number of characters) of is obtained directly by counting the characters of the keyword q i For example, if the keyword q i is "culture", then |q i | = 2, |n i | represents the length (number of characters) of the semantic node keyword n i The length (number of characters) of is obtained directly by counting the characters of the semantic node keyword n i For example, if the semantic node keyword n i is "civilization", then |n i | = 2, max(|q i |, |n i |) represents the maximum value of the lengths of q i and n i and is used to normalize the edit distance. By comparing |q i | and |n i |, it is obtained directly. For example, if |q i | = 2, |n i | = 2, then max(|q i |, |n i |) = 2. i is the character index in q i and n i , and its value range is from 1 to the length of the corresponding string.

[0084] If the keyword q i = "culture" and n i = "literature and art", use the dynamic programming method to calculate the edit distance d(q i , n i ). The construction process of the matrix D is as follows:

[0085] Initialize the matrix. The string q i = "culture" has a length of 2, and the string n i = "literature and art" has a length of 2. Initialize the matrix size to (|q i | + 1) × (|n i | + 1), that is, 3 × 3, and the initial values are as follows: The first row and the first column represent the number of conversion operations between the empty string and another string. Calculate using the recurrence formula. Compare the characters q i [1] = "文" and n i [1] = "文". Since the characters are the same, according to the formula D[1][1] = D[0][0], that is: D[1][1] = 0, update the matrix: Compare character q i [1] = "文" and n i [2] = "艺", the characters are different. According to the formula: D[1][2] = min(D[0][2] + 1, D[1][1] + 1, D[0][1] + 1), substituting the values: D[1][2] = min(3, 1, 2) = 1, update the matrix: Compare character q i [2] = "化" and n i [1] = "文", the characters are different. According to the formula: D[2][1] = min(D[1][1] + 1, D[2][0] + 1, D[1][0] + 1), substituting the values: D[2][1] = min(1, 3, 2) = 1, update the matrix: Compare character q i [2] = "化" and n i [2] = "艺", the characters are different. According to the formula: D[2][2] = min(D[1][2] + 1, D[2][1] + 1, D[1][1] + 1), substituting the values: D[2][2] = min(2, 2, 1) = 1, update the matrix: Edit distance d(q i , n i ) = D[2][2] = 1, similarity calculation |q i | = 2, |n i | = 2, = 0.5.

[0086] The calculation result sim(q i , n i ) = 0.5 indicates that the similarity between the query keyword q i and the semantic node keyword n i is 50%. This shows that the character structures of q i and n i only have a 50% degree of consistency. Specifically, a similarity value close to 1 indicates that the two keywords are more similar, while a value close to 0 indicates a greater difference between the keywords. Similarity range definition: High similarity: sim(q i , n i ) ≥ 0.7, indicating a high degree of keyword matching, and the two keywords can be considered to have a strong semantic correlation. Medium similarity: 0.4 ≤ sim(q i , n i ) < 0.7, indicating that there is a certain correlation between the keywords, but it is necessary to further analyze whether the semantic matching requirements are met. Low similarity: sim(q i , n i)<0.4, indicating that the keyword matching degree is low, and it is usually considered that the matching condition is not met. If the similarity benchmark value of high-correlation keywords in historical data is usually above 0.7. The current similarity is 0.5, which is in the medium similarity range. The current keywords "culture" and "art" have a certain correlation, but do not meet the high similarity matching standard.

[0087] S203: extracting association paths of semantic nodes based on the semantic node set that meets the conditions, matching the association paths with matching query semantics according to the priorities of the association paths, outputting retrieval paths of the query semantics, and generating a matching retrieval node path set;

[0088] Based on the semantic node set that meets the conditions, the semantic nodes that meet the conditions are screened through the matching results of similarity. The similarity score of each semantic node is directly used as the priority indicator to extract the associated path corresponding to the semantic node, and the priority of the path is determined according to the size of the similarity score. The path with the highest priority is matched with the matching query semantics, and the retrieval path of the query semantics is output. In the process of path extraction, the semantic node set that meets the conditions is traversed one by one, and the associated path corresponding to each node is directly associated with its similarity score by recording the similarity score. The node paths with higher similarity are preferentially retained, and the node paths with lower similarity are eliminated to ensure that the paths with higher priority can accurately match the query semantics. For example, if the semantic node set contains nodes A, B and C, and their similarity scores are 0.5, 0.7 and 0.8 respectively, the path corresponding to the node C with the highest similarity has the highest priority. The path of node C is directly selected as the final retrieval path and matched with the query semantics. Finally, through the above screening and path priority judgment, a matching retrieval node path set is generated, and each path in the set corresponds to the optimal association result of the query semantics.

[0089] See also Figure 4 , obtain the key features of the semantic nodes in the matching retrieval node path set, count the cumulative number of occurrences of the key features in the matching retrieval node path set, mark the key features corresponding to the highest number of occurrences, and generate the intangible cultural heritage hot spot feature set in the following specific steps:

[0090] S301: based on the matched search node path set, extract the time stamp, region identifier and content keyword information corresponding to the semantic node in the matched node path set, summarize the extracted feature information, and generate a key feature set;

[0091] The process of extracting the time stamp, regional identifier and content keyword information corresponding to the semantic node is as follows: for example, a certain search node path set contains semantic nodes A, B and C, the time stamp of node A is 2020, the regional identifier is East China, and the content keyword is "paper cutting", the time stamp of node B is 2019, the regional identifier is South China, and the content keyword is "embroidery", and the time stamp of node C is 2020, the regional identifier is East China, and the content keyword is "shadow play". After traversing the paths one by one and extracting these feature information, the time stamps are grouped according to the year, for example, the 2020 tag includes the path information of nodes A and C, the regional identifier is stored according to the geographical region, for example, the East China tag includes the information of nodes A and C, and the content keywords are classified and sorted according to the theme or skill characteristics, for example, the paper cutting keyword corresponds to the information of node A, the embroidery corresponds to the information of node B, and the shadow play corresponds to the information of node C. Finally, all feature information is summarized to generate a key feature set.

[0092] S302: Based on the key feature set, count the cumulative occurrences of the time stamp, region identifier and content keyword in the matching search node path set, record the time stamp, region identifier and content keyword with the highest occurrence, and generate key feature statistical results;

[0093] The process of counting the cumulative number of occurrences of time tags, regional identifiers, and content keywords in the set of matched search node paths is as follows: for example, the key feature set includes the time tags of 2020 and 2019, the regional identifiers of East China and South China, and the content keywords of paper-cutting, embroidery, and shadow puppetry. Through statistics, it is found that the time tag 2020 appeared twice in all paths, 2019 appeared once, the regional identifier East China appeared twice, South China appeared once, the content keyword paper-cutting appeared once, embroidery appeared once, and shadow puppetry appeared once. The statistical results are sorted by the cumulative number of times. For example, the cumulative number of the time tag in 2020 is the highest, the cumulative number of the regional identifier East China is the highest, and the cumulative number of paper-cutting, embroidery, and shadow puppetry in the content keywords is the same, which is 1 time each. These feature information are recorded according to the cumulative number of times to generate key feature statistical results.

[0094] S303: Based on the key feature statistics, mark the time tags, region identifiers and content keywords with the highest cumulative occurrence times, analyze their correlation characteristics and co-occurrence relationships, and integrate the analysis results to generate a set of intangible cultural heritage hot spot features;

[0095] The process of marking the time tags, regional identifiers, and content keywords with the highest cumulative occurrence times is as follows, for example, the time tag 2020, the regional identifier East China, and the content keywords paper-cutting, embroidery, and shadow puppetry. Analyze their association characteristics and co-occurrence relationships. For example, through the co-occurrence of the time tag and the regional identifier, it is found that 2020 and East China appear simultaneously in two semantic nodes. The association between the regional identifier and the content keyword shows that the keywords associated with East China are paper-cutting and shadow puppetry, and the keywords associated with South China are embroidery. Combine the co-occurrence frequency and association strength to generate a co-occurrence matrix. For example, the matrix records that the co-occurrence value of 2020 with East China is 2, and the co-occurrence value with other regions is 0. The content keyword paper-cutting has an association value of 1 with East China, and an association value of 0 with other regions. Finally, these analysis results are integrated to generate a set of intangible cultural heritage hotspot feature sets, which are marked as the intangible cultural heritage projects related to East China in 2020 mainly include paper-cutting and shadow puppetry, and the intangible cultural heritage projects related to South China in 2019 mainly include embroidery.

[0096] See also Figure 5 , refer to the intangible cultural heritage hot spot feature set to build a multi-level response node network diagram, use the marked key features as the core nodes in the node network diagram, extract the time series data of the core nodes, and refer to the time series data to predict the future change trend of the core nodes and the diffusion range of the hot spot area. The specific steps to generate the hot spot propagation dynamic prediction results are as follows:

[0097] S401: Based on the intangible cultural heritage hot spot feature set, extract the marked key features from it, build a response network with the key features as the core nodes, associate the key features with its upper and lower layer nodes and display them in a visual way, and generate a multi-level response node network diagram;

[0098] The process of extracting the key features of the tags is, for example, the time tag "2020", the regional identifier "East China", and the content keyword "paper-cutting", setting these key features as core nodes, and constructing a response network by analyzing the associated upper and lower feature nodes. For example, the time tag "2020" is associated with the semantic node of the East China region, and further connected to other related nodes in the upper and lower layers through the content keyword "paper-cutting", such as the skill feature "traditional craft" or the activity identifier "cultural festival". The feature association path is calculated based on the relationship between the upper and lower nodes, the nodes are grouped through hierarchical classification, and the association direction between the core nodes and the upper and lower nodes is marked, which is displayed in a visual way of the relationship strength to finally generate a multi-level response node network diagram.

[0099] S402: Based on the multi-level response node network diagram, extract the time series data of the core nodes, analyze the change characteristics of the time series data, determine the key activity time period of the hot node based on the change characteristics, and generate the time series characteristics of the core nodes;

[0100] The process of extracting the time series data of the core nodes is, for example, for the core node with the time mark "2020", by analyzing the time distribution records of the nodes associated with it, the activity frequency from January to December is counted, for example, the activity frequency is 10 times per month from January to March, 15 times per month from April to June, and 5 times per month from July to December. Combined with the changing characteristics of the time series data, the rising, stable and falling trends of the activity frequency are analyzed. For example, the activity frequency gradually increases from January to March, reaches a peak from April to June, and gradually decreases from July to December. The changing characteristics are matched with the time period of the time series, and the key activity time period is determined to be from April to June. The core node time series features are generated by recording the activity frequency and change trends of these time periods.

[0101] S403: Based on the core node time series characteristics and the regional characteristics of the core nodes, the future change trend of the core nodes and the diffusion range of the hotspot regions are predicted, and the prediction results are integrated into the hotspot propagation dynamic analysis data to generate the hotspot propagation dynamic prediction results;

[0102] To predict the future change trend of core nodes and the diffusion range of hot spots, the formula is used:

[0103] X(t+1)=α·R(t)+β·G(t)+γ·ΔR(t);

[0104] Calculate the change value X(t+1) at the next time step t;

[0105] Among them, R(t) is the activity frequency at the current time step t, which is obtained by counting the total number of activities recorded in a certain time step in the time series data. For example, by extracting event logs or intangible cultural heritage activity records, the total number of activities in a certain time step (such as one month) is counted. G(t) is the regional coverage index of the current time step t, which indicates the total number of regions involved in the core node in a specific time step. For example, the number of regions involved in intangible cultural heritage activities (such as "East China" and "South China") can be directly extracted through the location attribute field of the activity. ΔR(t) is the rate of change of the activity frequency at the current time step t, which indicates the relative change of the activity frequency between the current time step and the previous time step. The calculation formula is: R(t-1) is the activity frequency of the previous time step, which is consistent with the activity frequency acquisition method of the current time step. α, β, and γ are weight parameters used to balance the contribution of activity frequency, regional coverage index, and change rate to the comprehensive change value. The weight parameters can be determined by analyzing the correlation of historical data or experimental results. For example, correlation analysis is used to determine that the weight of the impact of activity frequency on the change trend is greater than the regional coverage index. The setting process of weight parameters can be combined with the actual scenario of intangible cultural heritage activities. For example, the weight α of the impact of activity frequency on the comprehensive change value can be determined by analyzing the correlation between frequency changes in historical data and future trends. For example, if the increase in activity frequency has a greater impact on the next If the influence of the hotspot diffusion trend in a time step is relatively high, α>0.5 is set; the influence weight β of the regional coverage index on the comprehensive change value can be determined by statistically analyzing the correlation between the activity coverage range and the hotspot diffusion range in different regions. For example, if the diffusion range is mainly determined by the regional correlation, the weight of β can be set lower than α and higher than the change rate weight; the influence weight γ of the change rate on the comprehensive change value is set according to the fine-tuning effect of activity frequency fluctuations on future trends. For example, when the fluctuations are small in certain time steps, γ<0.2 is set. Finally, the rationality of each parameter on the prediction results is verified through experimental data, and the weight ratio is dynamically adjusted according to the activity scenario.

[0106] For example, if the activity frequency of the current time step is R(t)=80, the activity frequency of the previous time step is R(t-1)=60; the regional coverage index of the current time step is G(t)=5; the weight parameters are α=0.6, β=0.3, and γ=0.1 respectively.

[0107] Calculate the rate of change of activity frequency ΔR(t):

[0108]

[0109] Substitute the formula to calculate the comprehensive change value X(t+1):

[0110] X(t+1)=α·R(t)+β·G(t)+γ·ΔR(t)

[0111] =0.6·80+0.3·5+0.1·0.333=49.5333;

[0112] Comprehensive change value analysis: According to the comprehensive change value X(t+1)=49.53, combined with the change trend of historical data, the threshold range is set. For example: if X(t+1)>50, it means that the frequency of activities will increase significantly in the future, and the geographical diffusion range may expand rapidly; if X(t+1)∈[30,50], it means that the frequency of activities and the geographical diffusion range are showing a steady growth trend; if X(t+1)<30, it means that the frequency of activities and the geographical diffusion range may decrease or stagnate. The result X(t+1)=49.53 shows that the comprehensive change value is close to the upper limit of steady growth, and it is predicted that the diffusion range of hot spots in the future may remain at the current level or expand slightly.

[0113] See also Figure 6 , based on the dynamic prediction results of hot spot propagation, the core node distribution and dynamic change range in the node network diagram are mapped to the interactive interface and multi-layer screening and regional aggregation are performed to generate the interactive display list of intangible cultural heritage information. The specific steps are as follows:

[0114] S501: Based on the hotspot propagation dynamic prediction result, the core node distribution and the dynamic change range are mapped to the interactive interface to generate the hotspot distribution layer of the interactive interface;

[0115] The dynamic range of core nodes is extracted from the prediction results, and the geographical location and range of core nodes are converted into spatial coordinate data. The data is visualized through GIS (Geographic Information System) software such as ArcGIS, and the hotspot distribution layer is mapped. In the specific process, ArcGIS is used to spatially project the coordinates of the core nodes, map the range of hotspot changes to the map, and highlight the density of hotspot areas through heat map tools. At the same time, combined with layered vector data such as terrain and administrative boundaries, layer overlay processing is performed. The final hotspot distribution layer is presented in the interactive interface in a real-time updated manner through WebGIS technology.

[0116] S502: Based on the hotspot distribution layer of the interactive interface, the content of the hotspot area is multi-layered screened according to the time and region dimensions, and the screened results are aggregated by region to generate hotspot area aggregated screening results;

[0117] First, use Excel or Tableau to filter the time dimension content of the hotspot area, divide the time axis into time intervals such as hours, days, weeks, and months, and use the filter function to extract the hotspot change information at different time levels. Next, use ArcGIS or QGIS to map the regional identifier to the hotspot distribution layer, and divide the content by regional range based on the screening results. For example, select the hotspot area of ​​a province or city through the filtering function, and aggregate the hotspot information in the selected range. After aggregation, the results can be used to generate a bar chart or pie chart of the hotspot distribution through Tableau, showing the hotspot distribution ratio in different regions, and finally generate the hotspot area aggregation screening results.

[0118] S503: Based on the aggregated screening results of the hotspot areas, the content of the hotspot areas is displayed in multiple dimensions, including time change trends, geographical distribution ranges, and key feature related data, and an interactive display list of intangible cultural heritage information is generated;

[0119] Use PowerBI or Tableau to display the content of hot spots in multiple dimensions. In terms of time dimension, the time-varying trend of hot spots can be dynamically displayed by setting the playback axis function of time changes. In terms of geographical dimension, the distribution range boundary of hot spots can be highlighted by using the heat map function. In terms of key features, extract the intangible cultural heritage themes, skills or historical heritage data related to the hot spots, and display them through a combination of text and charts. For example, the geographical scope of the hot spots is presented through the map visualization component in Tableau, and the key features are embedded in the interactive interface in the form of line charts and keyword clouds. The integrated display of all data is achieved through the dashboard function of Tableau, and finally an interactive display list of intangible cultural heritage information is generated.

[0120] See also Figure 7 , a non-legacy cultural information interaction system, the system comprising:

[0121] The multidimensional feature analysis module divides the multidimensional features into levels based on the multidimensional features of intangible cultural heritage information, constructs multi-level semantic nodes according to the hierarchical division results, extracts the hierarchical relationships, association paths and information identifiers in the multi-level semantic nodes, and establishes a semantic index tree for intangible cultural heritage information;

[0122] The semantic query matching module parses the query content input by the user based on the semantic index tree of intangible cultural heritage information, extracts the semantic information in the query content, matches the semantic information with the semantic nodes in the semantic index tree, and generates a set of matching retrieval node paths;

[0123] The key feature extraction module extracts key features from semantic nodes based on the matched retrieval node path set, counts the cumulative number of occurrences of key features in the matched node path set, marks the key features with the highest number of occurrences, and generates a set of intangible cultural hotspot features;

[0124] The node network prediction module constructs a multi-level response node network diagram based on the feature set of intangible cultural heritage hotspots, takes the marked key features as the core nodes in the node network diagram, extracts the time series data of the core nodes, and predicts the future change trend of the core nodes and the diffusion range of the hotspot regions with reference to the time series data, generating the dynamic prediction results of hotspot propagation;

[0125] The interactive display generation module maps the distribution and dynamic change range of core nodes in the node network diagram to the interactive interface based on the dynamic prediction results of hot spot propagation, performs multi-layer screening and regional aggregation of content, and generates an interactive display list of intangible cultural heritage information.

[0126] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0127] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0128] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0129] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0135] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for interacting with intangible cultural heritage information, characterized in that: The following steps are involved: S1: Based on the multidimensional features of intangible cultural heritage information, the multidimensional features are hierarchically divided, and multi-level semantic nodes are constructed according to the hierarchical division results to obtain the semantic index tree of intangible cultural heritage information; S2: parsing the query content input by the user, extracting the semantic information in the query content, matching the semantic information with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and generating a matching retrieval node path set; S3: Obtain key features of semantic nodes in the matched search node path set, count the cumulative number of occurrences of the key features in the matched search node path set, mark the key features corresponding to the highest number of occurrences, and generate a set of intangible cultural hotspot features; S4: Construct a multi-level response node network diagram with reference to the intangible cultural heritage hotspot feature set, use the marked key features as the core nodes in the node network diagram, extract the time series data of the core nodes, predict the future change trend of the core nodes and the diffusion range of the hotspot region with reference to the time series data, and generate a hotspot propagation dynamic prediction result; S5: Based on the dynamic prediction results of hot spot propagation, the core node distribution and dynamic change range in the node network diagram are mapped to the interactive interface and multi-layer screening and regional aggregation are performed to generate an interactive display list of intangible cultural heritage information.

2. The intangible cultural heritage information interaction method according to claim 1, characterized in that: The semantic index tree of the intangible cultural heritage information includes multi-level semantic nodes, hierarchical relationships, associated paths and information identifiers; the matched retrieval node path set includes qualified semantic nodes, retrieval paths corresponding to the semantic nodes and semantic information matching results; the intangible cultural heritage hot spot feature set includes time tags, regional identifiers and content keywords; the hot spot propagation dynamic prediction results include future change trends of core nodes, dynamic diffusion ranges of hot spot regions and time series data; the intangible cultural heritage information interactive display list includes core node distribution, dynamic change ranges and multi-dimensional display content.

3. The intangible cultural heritage information interaction method according to claim 1, characterized in that: Based on the multidimensional features of intangible cultural heritage information, the multidimensional features are hierarchically divided, and multi-level semantic nodes are constructed according to the hierarchical division results. The specific steps to obtain the semantic index tree of intangible cultural heritage information are as follows: S101: Based on the multi-dimensional features of intangible cultural heritage information, including theme, region, time and skills, the multi-dimensional features are analyzed in layers, and the layers are divided according to the characteristics of each dimension and the upper and lower relationships between the layers are determined to generate the multi-dimensional feature hierarchical division results; S102: Based on the multi-dimensional feature hierarchical division result, construct semantic nodes corresponding to each level, extract associated attributes of the semantic nodes, bind the associated attributes with the nodes in a corresponding relationship, and generate a multi-level semantic node set; S103: Based on the multi-level semantic node set, extract the hierarchical relationship, associated path and information identifier of the corresponding features in the semantic nodes, map the hierarchical relationship and path to the corresponding semantic structure, and establish a semantic index tree of intangible cultural heritage information.

4. The intangible cultural heritage information interaction method according to claim 1, characterized in that: The specific steps of parsing the query content input by the user, extracting the semantic information in the query content, matching the semantic information with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and generating a matching retrieval node path set are as follows: S201: Based on the query content input by the user, the semantic information in the query content is parsed, the semantic information and its context-related attributes are extracted, the semantic information is combined with the context, and a user query semantic set is generated; S202: Based on the user query semantic set, the query semantics are matched one by one with the semantic nodes in the semantic index tree of the intangible cultural heritage information, and according to the matching results, whether the semantic nodes meet the user's query conditions is determined, and the semantic nodes that meet the conditions are screened to generate a semantic node set that meets the conditions; S203: Based on the semantic node set that meets the conditions, extract the association path of the semantic node, correspond the association path with the matching query semantics according to the priority of the association path, output the retrieval path of the query semantics, and generate a matching retrieval node path set.

5. The intangible cultural heritage information interaction method according to claim 4, characterized in that: To match the query semantics with the semantic nodes in the semantic index tree of intangible cultural heritage information one by one, the formula is used: Calculate keyword q i and n i The similarity score sim(q i ,n i ), judging the similarity between the query semantics and the semantic nodes according to the similarity score; Among them, d(q i ,n i ) indicates the keyword q i and n i The edit distance between i | indicates keyword q i The number of characters, |n i | indicates semantic node keyword n i The number of characters, i is q i and n i The character index in .

6. The intangible cultural heritage information interaction method according to claim 1, characterized in that: The specific steps of obtaining the key features of the semantic nodes in the matched search node path set, counting the cumulative occurrence times of the key features in the matched search node path set, marking the key features corresponding to the highest occurrence times, and generating the intangible cultural hot spot feature set are as follows: S301: based on the matched search node path set, extracting time tags, region identifiers and content keyword information corresponding to semantic nodes in the matched node path set, aggregating the extracted feature information, and generating a key feature set; S302: Based on the key feature set, count the cumulative occurrences of time tags, region identifiers and content keywords in the matching search node path set, record the time tags, region identifiers and content keywords with the highest occurrences, and generate key feature statistics results; S303: Based on the statistical results of the key features, mark the time tags, region identifiers and content keywords with the highest cumulative occurrence times, analyze their correlation characteristics and co-occurrence relationships, and integrate the analysis results to generate a set of intangible cultural heritage hot spot features.

7. The intangible cultural heritage information interaction method according to claim 1, characterized in that: A multi-level response node network diagram is constructed by referring to the intangible cultural heritage hotspot feature set, and the marked key features are used as the core nodes in the node network diagram. The time series data of the core nodes are extracted, and the future change trend of the core nodes and the diffusion range of the hotspot regions are predicted by referring to the time series data. The specific steps for generating the hotspot propagation dynamic prediction results are as follows: S401: Based on the intangible cultural heritage hot spot feature set, extract the marked key features from it, construct a response network with the key features as core nodes, associate the key features with its upper and lower layer nodes and display them in a visual manner, and generate a multi-level response node network diagram; S402: Based on the multi-level response node network diagram, extract the time series data of the core nodes, analyze the change characteristics of the time series data, determine the key activity time period of the hotspot nodes based on the change characteristics, and generate the time series characteristics of the core nodes; S403: Based on the time series characteristics of the core nodes and in combination with the regional characteristics of the core nodes, the future change trend of the core nodes and the diffusion range of the hotspot regions are predicted, and the prediction results are integrated into hotspot propagation dynamic analysis data to generate hotspot propagation dynamic prediction results.

8. The intangible cultural heritage information interaction method according to claim 7, characterized in that: To predict the future change trend of core nodes and the diffusion range of hot spots, the formula is used: X(t+1)=α·R(t)+β·G(t)+γ·ΔR(t); Calculate the change value X(t+1) at the next time step t; Among them, R(t) is the activity frequency at the current time step t, G(t) is the geographical coverage index at the current time step t, ΔR(t) is the rate of change of the activity frequency at the current time step t, and α, β, and γ are weight parameters.

9. The intangible cultural heritage information interaction method according to claim 1, characterized in that: Based on the dynamic prediction results of hot spot propagation, the distribution and dynamic change range of core nodes in the node network diagram are mapped to the interactive interface and multi-layer screening and regional aggregation are performed to generate the interactive display list of intangible cultural heritage information. The specific steps are as follows: S501: Based on the hotspot propagation dynamic prediction result, the core node distribution and the dynamic change range are mapped to the interactive interface to generate an interactive interface hotspot distribution layer; S502: Based on the hotspot distribution layer of the interactive interface, the content of the hotspot area is multi-layered screened according to the time and region dimensions, and the screened results are aggregated by region to generate hotspot area aggregated screening results; S503: Based on the aggregated screening results of the hotspot areas, the content of the hotspot areas is displayed in multiple dimensions, including time change trends, geographical distribution ranges and key feature related data, and an interactive display list of intangible cultural heritage information is generated.

10. A non-legacy cultural information interaction system, characterized in that: According to any one of claims 1 to 9, the intangible cultural heritage information interaction method is implemented, and the system comprises: The multidimensional feature analysis module divides the multidimensional features into levels based on the multidimensional features of intangible cultural heritage information, constructs multi-level semantic nodes according to the hierarchical division results, extracts the hierarchical relationships, association paths and information identifiers in the multi-level semantic nodes, and establishes a semantic index tree for intangible cultural heritage information; The semantic query matching module parses the query content input by the user based on the semantic index tree of the intangible cultural heritage information, extracts the semantic information in the query content, matches the semantic information with the semantic nodes in the semantic index tree, and generates a matching retrieval node path set; The key feature extraction module extracts key features in the semantic nodes based on the matched retrieval node path set, counts the cumulative occurrence times of the key features in the matched node path set, marks the key features with the highest occurrence times, and generates a set of intangible cultural hot spot features; The node network prediction module constructs a multi-level response node network diagram based on the intangible cultural heritage hot spot feature set, uses the marked key features as the core nodes in the node network diagram, extracts the time series data of the core nodes, and predicts the future change trend of the core nodes and the diffusion range of the hot spot region with reference to the time series data, and generates a hot spot propagation dynamic prediction result; Based on the dynamic prediction results of hot spot propagation, the interactive display generation module maps the core node distribution and dynamic change range in the node network diagram to the interactive interface, performs multi-layer screening and regional aggregation of the content, and generates an interactive display list of intangible cultural heritage information.

Images