A semantic mapping control method for material information based on natural language processing

Abstract

The present invention discloses a semantic mapping control method for material information based on natural language processing, specifically related to the field of data analysis, including material information collection, data analysis, semantic multi-fusion potential excitation analysis, semantic resilience shaping and co-evolution evaluation, semantic ecological adaptability expansion analysis, and semantic mapping intelligent regulation decision-making. By comprehensively collecting and analyzing multi-dimensional data of material information, the present invention stimulates the potential of semantic multi-fusion, shapes a resilient semantic structure, evaluates its ecological adaptability in different application scenarios, and realizes the intelligent regulation of semantic mapping with the help of intelligent algorithms to optimize the mapping effect. The present invention improves the accuracy and adaptability of the semantics of material information, providing strong support for the efficient utilization and intelligent processing of material information.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis. More specifically, the present invention relates to a semantic mapping control method for material information based on natural language processing. Background Art

[0002] In the prior art, the processing of material information mainly relies on automated information collection systems and database technologies. The system first automatically collects a large amount of material information from channels such as scientific research literature, experimental reports, and patent databases, and then organizes and classifies this information and stores it in the database. When analyzing a specific material, researchers can quickly extract relevant material information from the database through specific retrieval conditions for subsequent analysis and research.

[0003] However, although the prior art has improved the efficiency of material information processing to a certain extent, there are still some obvious deficiencies. First, the prior art mainly relies on keyword matching for information retrieval and is difficult to accurately capture the internal connections and potential value between material information. Second, when dealing with large-scale, complex and diverse material information, the efficiency and accuracy of the prior art still need to be improved. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a semantic mapping control method for material information based on natural language processing, through the following solutions to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solution: A semantic mapping control method for material information based on natural language processing, including:

[0006] Step 1: Material information collection: Collect semantic depth fusion data, semantic innovation expansion data, semantic stability evaluation data, and semantic application adaptation data of the target material information;

[0007] Step 2: Data analysis: Used to analyze the data collected in Step 1 and calculate the evaluation values of each group of data, including a semantic depth fusion evaluation model, a semantic innovation expansion evaluation model, a semantic stability evaluation model, and a semantic application adaptation evaluation model;

[0008] Step 3: Semantic multi-dimensional fusion potential excitation analysis: Used to establish a semantic fusion innovation potential index calculation model for analyzing the basic ability of material information semantics to generate unique value in the initial stage of multi-dimensional fusion and expansion;

[0009] Step 4: Semantic Resilience Shaping and Co-evolution Evaluation: Used to establish a calculation model for the co-evolution coefficient of semantic fusion innovation-stability, to observe how the fusion innovation potential analyzed in Step 3 interacts with stability when facing challenges related to semantic stability, and to shape a resilient and co-evolving semantic structure;

[0010] Step 5: Semantic Ecological Adaptability Expansion Analysis: Used to establish a calculation model for the semantic ecological adaptability expansion coefficient. Based on Steps 3 and 4, it considers the ecological adaptability of semantics in different application scenarios;

[0011] Step 6: Semantic Mapping Intelligent Regulation Decision-making: According to the analysis results of Step 5, it uses intelligent algorithms to dynamically adjust the semantic mapping strategy for control, aiming to optimize the semantic mapping effect of material information.

[0012] Preferably, the semantic deep fusion data includes cross-modal semantic collaboration coefficient, semantic hierarchical nesting score, semantic knowledge graph fusion degree, and semantic metaphor association strength; the semantic innovation expansion data includes semantic concept birth rate, semantic logic reconstruction index, semantic association expansion width, and semantic context migration adaptability; the semantic stability evaluation data includes semantic fluctuation variance value, semantic ambiguity resolution rate, semantic noise tolerance coefficient, and semantic redundancy elimination ratio; the semantic application adaptation data includes semantic task matching degree, semantic process embedding fit degree, semantic decision support effectiveness, and semantic cross-domain transplantation adaptability.

[0013] Preferably, the acquisition method of the cross-modal semantic collaboration coefficient is as follows: First, use the cross-modal feature extraction method to map the text and other modal data into a common semantic space respectively, then calculate the covariance between the semantic feature vectors of different modalities, and divide it by the product of their respective standard deviations to obtain the cross-modal semantic collaboration coefficient. The acquisition method of the semantic hierarchical nesting score is as follows: Use the syntax tree and semantic role annotation technology to analyze the hierarchical structure of semantic components in the material information text, assign scores to reasonably nested semantic levels. A completely matching ideal nesting pattern gets 1 point, and a partial match gets 0.5 points. After summing up the scores of all level pairs and taking the average, the semantic hierarchical nesting score is obtained. The acquisition method of the semantic knowledge graph fusion degree is as follows: Construct a knowledge graph in the material field, extract the semantic elements in the collected text semantic information and fuse and match them with the corresponding nodes and edges in the knowledge graph, and count the proportion of the number of successfully fused semantic elements in the total number of fusible semantic elements in the text, which is used as the semantic knowledge graph fusion degree. The acquisition method of the semantic metaphor association strength is as follows: Through the metaphor recognition algorithm, identify the sentences in the material information text that use metaphor to describe the material, and then analyze the distance between the vehicle and the tenor of the metaphor in the semantic feature space by means of word vectors, and subtract the normalized value of this distance from 1 to obtain the semantic metaphor association strength.

[0014] Preferably, the method for collecting the semantic concept emergence rate is specifically as follows: Using text mining technology to analyze a large number of latest material information texts, combining with a professional field dictionary and the boundary entropy method based on a statistical language model, identifying concepts that have newly emerged completely and do not exist in the previous material semantic system, and counting the proportion of their quantity to the total number of concepts as the semantic concept emergence rate. The method for collecting the semantic logic reconstruction index is specifically as follows: With the help of a rule-based logic analyzer combined with a deep learning semantic parsing model, analyzing the logical expressions of material causal relationships, function and structure associations in the material information text, comparing with the traditional and established material semantic logic structure, and counting the proportion of the number of sentences that have reconstructed the original logical relationship in the text to the total number of logically relevant sentences to obtain the semantic logic reconstruction index. The method for collecting the semantic association expansion width is specifically as follows: Starting from the core concept of the material, calculating the semantic similarity of word vectors and finding paths from the core concept to other related concepts in the semantic network based on graph algorithms, counting the number of concepts in different fields and of different natures that can be associated within a certain text corpus range, comparing it with the benchmark value of the number of traditional associated concepts, and calculating the expanded proportion as the semantic association expansion width index. The method for collecting the semantic context transfer adaptability is specifically as follows: Placing the material information text in different simulated contexts, and evaluating whether the text semantics can still be reasonably expressed, understood and remain coherent in these new contexts through a pre-trained language model, and counting the proportion of effective adaptation of the semantics in different new contexts, that is, the semantic context transfer adaptability.

[0015] Preferably, the method for collecting the semantic fluctuation variance value is specifically as follows: At different time points, quantitatively representing the same key semantic dimension and calculating the variance of these numerical sequences. The method for collecting the semantic ambiguity resolution rate is specifically as follows: Collecting material information texts from different backgrounds, and for the material property index words with multiple interpretations among them, using a Bayesian model combined with semantic role analysis to count the proportion of the number of successfully resolved ambiguity cases to the total number of ambiguity cases to obtain the semantic ambiguity resolution rate. The method for collecting the semantic noise tolerance coefficient is specifically as follows: Artificially adding different degrees of noise to the material information text, and then judging the proportion of the text that can still accurately convey the original semantics after adding the noise through a deep learning-based semantic understanding model to obtain the semantic noise tolerance coefficient. The method for collecting the semantic redundancy elimination ratio is specifically as follows: Analyzing the semantic redundancy situation in the material information text, judging the importance through a text compression algorithm according to the contribution of the semantics to the expression of the core information of the material, and calculating the proportion of the reduction in the semantic information volume of the text after removing the redundancy, that is, the semantic redundancy elimination ratio.

[0016] Preferably, the method for collecting the semantic task matching degree is specifically as follows: for different actual application tasks related to materials, the text semantics of the material information is matched and compared with the key semantic elements required for each task, and the proportion of the semantic intersection in the total semantic set is measured by an algorithm related to set theory in combination with semantic similarity to obtain the semantic task matching degree. The method for collecting the semantic process embedding fitness is specifically as follows: according to the established process of material processing and application, by constructing a process semantic model, the degree of fit between the text semantics and the process semantics is calculated. The method for collecting the semantic decision support effectiveness is specifically as follows: in a decision-making scenario involving materials, the text semantics containing material information is used as input, and by combining an expert system and a machine learning decision algorithm, the degree of conformity between the decision made based on this semantics and the actual optimal decision is observed, and the proportion of the number of conforming times in the total number of decision-making times is used to measure the semantic decision support effectiveness. The method for collecting the semantic cross-domain transplantation adaptability is specifically as follows: attempt to transplant the text semantics of the material information to other fields, and through the representative texts in the target field combined with semantic similarity and logical coherence quantification analysis methods, the proportion of the semantics that can be applied after cross-domain transplantation is statistically obtained to obtain the semantic cross-domain transplantation adaptability.

[0017] Preferably, the semantic deep fusion evaluation model is used to evaluate the semantic deep fusion data, and is specifically expressed as: , where SD represents the semantic deep fusion evaluation value, C represents the cross-modal semantic collaboration coefficient, L represents the semantic hierarchical nesting score, G represents the semantic knowledge graph fusion degree, and I represents the semantic metaphor association strength.

[0018] Preferably, the semantic innovation and expansion evaluation model is used to evaluate the semantic innovation and expansion data, and is specifically expressed as: , where SI represents the semantic innovation and expansion evaluation value, R represents the semantic concept birth rate, E represents the semantic logic reconstruction index, W represents the semantic association and expansion width, and M represents the semantic context migration adaptability.

[0019] Preferably, the semantic stability evaluation model is used to evaluate the semantic stability evaluation data, and is specifically expressed as: , where SS represents the semantic stability evaluation value, T represents the time stability, D represents the semantic ambiguity resolution rate, V represents the semantic fluctuation variance value, N represents the semantic noise tolerance coefficient, and R represents the semantic redundancy elimination ratio.

[0020] Preferably, the semantic application adaptation evaluation model is used to evaluate the semantic application adaptation data, and is specifically expressed as: , where SA represents the semantic application adaptation evaluation value, S represents the semantic task matching degree, F represents the semantic process embedding fitness, A represents the semantic decision support effectiveness, and P represents the semantic cross-domain transplantation adaptability.

[0021] Preferably, the calculation model of the semantic fusion innovation potential index is specifically expressed as: , where P1 represents the semantic fusion innovation potential index, α represents the semantic deep fusion adjustment index, β represents the semantic innovation expansion adjustment index, and ε = 0.001.

[0022] Preferably, the calculation model of the semantic fusion innovation-stability co-evolution coefficient is specifically expressed as: , where P2 represents the semantic fusion innovation-stability co-evolution coefficient, and γ represents the semantic stability adjustment coefficient.

[0023] Preferably, the calculation model of the semantic ecological adaptability expansion coefficient is specifically expressed as: , where P3 represents the semantic ecological adaptability expansion coefficient, and δ represents the semantic application adaptation adjustment parameter.

[0024] Preferably, in step 6, P3 is input into the intelligent decision-making model based on reinforcement learning. Specifically, a deep Q-network model is adopted. Using P3 and historical data as state inputs, different semantic mapping control actions are used as optional behaviors. The model undergoes simulation training, and the training data is constructed based on past material information semantic mapping cases and corresponding control feedback results, learning the optimal control actions under different P3 value ranges.

[0025] Preferably, when the decision indication output by the model is P3 ≥ 0.7, the "aggressive expansion" strategy is adopted, which means actively exploring new fusion modes, innovative concepts, and application scenarios on the basis of maintaining the existing semantic mapping state, achieved by increasing the types of modalities for multimodal fusion and encouraging cross-domain semantic associations. When 0.3 < P3 < 0.7, the "steady optimization" strategy is executed, optimizing the relatively weak links in steps 4 and 5, specifically determined by tracing back the data and calculation processes of each stage. When P3 ≤ 0.3, the "reconstruction and reshaping" strategy is implemented, which requires a comprehensive re-examination of the construction, fusion, and application adaptation links of the material information semantics, involving replacing the semantic analysis model, re-planning the semantic knowledge graph structure, and redefining semantic elements based on actual application pain points.

[0026] The technical effects and advantages of the present invention:

[0027] The present invention comprehensively collects multi-dimensional data of material information, including semantically deeply fused data, semantically innovatively expanded data, semantically stability-evaluated data, and semantically application-adapted data. Through specific data collection methods, the accuracy and reliability of the data are ensured; the data collected in step 1 is deeply analyzed. By constructing different evaluation models, the evaluation values of each group of data are calculated. These evaluation models comprehensively consider multiple factors and can comprehensively reflect the performance of material information in different dimensions, providing strong data support for subsequent steps such as the analysis of stimulating the potential of semantic multi-dimensional fusion, the shaping of semantic resilience, and the co-evolution evaluation, and providing a rich and high-quality information basis for subsequent data analysis and semantic mapping control; a semantic fusion innovation potential index calculation model is established to analyze the basic ability of the semantics of material information to generate unique value at the initial stage of multi-dimensional fusion and expansion. Through this model, the potential of semantics in multi-dimensional fusion can be quantitatively evaluated, providing a clear direction for subsequent development and optimization, helping to discover new fusion patterns and innovative concepts, and promoting the further development of the semantics of material information; a semantic fusion innovation-stability co-evolution coefficient calculation model is established to observe how the fusion innovation potential interacts with stability when facing challenges related to semantic stability. This model can evaluate the performance of the semantic structure in co-evolution and the impact of stability on the overall semantic structure, helping to shape a resilient and co-evolving semantic structure and improve the adaptability and vitality of the semantics of material information; a semantic ecological adaptability expansion coefficient calculation model is established. Based on the fusion innovation and stability shaping, it considers the ecological adaptability of semantics in different application scenarios. Through this model, the adaptability expansion of semantics in the application ecosystem can be quantitatively evaluated, providing strong support for subsequent application development and optimization, helping to improve the adaptability and expansion effect of semantics in actual applications, and promoting the wide application of the semantics of material information; according to the analysis results of step 5, the semantic mapping strategy is dynamically adjusted and controlled by means of intelligent algorithms to optimize the semantic mapping effect of material information. Through an intelligent decision-making model based on reinforcement learning, the optimal control actions under different conditions can be learned to achieve the intelligent regulation of semantic mapping, helping to improve the accuracy and efficiency of semantic mapping and promoting the further development of the semantic mapping technology of material information. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying 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.

[0030] Reference Figure 1 A semantic mapping control method for material information based on natural language processing is shown as follows. The specific steps include:

[0031] Step 1: Material information collection: Collect the semantic depth fusion data, semantic innovation expansion data, semantic stability evaluation data, and semantic application adaptation data of the target material information.

[0032] The semantic depth fusion data includes cross-modal semantic collaboration coefficient, semantic hierarchical nesting score, semantic knowledge graph fusion degree, and semantic metaphor association strength. The semantic innovation expansion data includes semantic concept birth rate, semantic logic reconstruction index, semantic association expansion width, and semantic context migration adaptability. The semantic stability evaluation data includes semantic fluctuation variance value, semantic ambiguity resolution rate, semantic noise tolerance coefficient, and semantic redundancy elimination ratio. The semantic application adaptation data includes semantic task matching degree, semantic process embedding fit degree, semantic decision support effectiveness, and semantic cross-domain transplantation adaptability.

[0033] The specific method for collecting the cross-modal semantic collaboration coefficient is as follows: First, map the text and other modal data to a common semantic space through cross-modal feature extraction methods, then calculate the covariance between the semantic feature vectors of different modalities, and then divide it by the product of their respective standard deviations to obtain the cross-modal semantic collaboration coefficient. The specific method for collecting the semantic hierarchical nesting score is as follows: Use the syntax tree and semantic role annotation technology to analyze the hierarchical structure of the semantic components in the material information text, assign scores to the reasonably nested semantic levels, get 1 point for a perfect match with the set ideal nesting pattern, and 0.5 points for a partial match. After summing up the scores of all levels and averaging, the semantic hierarchical nesting score is obtained. The specific method for collecting the semantic knowledge graph fusion degree is as follows: Construct a knowledge graph in the material field, extract the semantic elements in the collected text semantic information and fuse and match them with the corresponding nodes and edges in the knowledge graph, and count the proportion of the number of successfully fused semantic elements in the total number of fusible semantic elements in the text as the semantic knowledge graph fusion degree. The specific method for collecting the semantic metaphor association strength is as follows: Through the metaphor recognition algorithm, identify the sentences in the material information text that use metaphor to describe the material, and then analyze the distance between the vehicle and the ontology of the metaphor in the semantic feature space by the word vector method, and use 1 minus the normalized value of this distance to obtain the semantic metaphor association strength.

[0034] The specific method for collecting the semantic concept birth rate is as follows: Using text mining techniques to analyze a large number of latest material information texts, combining with a professional field dictionary and the boundary entropy method based on a statistical language model, identifying concepts that have newly emerged completely and do not exist in the previous material semantic system, and counting the proportion of their quantity in the total number of concepts as the semantic concept birth rate. The method for collecting the semantic logic reconstruction index is as follows: With the help of a rule-based logic analyzer combined with a deep learning semantic parsing model, analyzing the causal relationship of materials, the logical expressions of the functional and structural associations in the material information text, comparing with the traditional and established material semantic logic structure, and counting the proportion of the number of sentences that have reconstructed the original logical relationship in the total number of logically relevant sentences to obtain the semantic logic reconstruction index. The method for collecting the semantic association expansion width is as follows: Starting from the core concept of the material, calculating the semantic similarity of word vectors and finding the paths from the core concept to other related concepts in the semantic network based on graph algorithms, counting the number of concepts in different fields and of different natures that can be associated within a certain text corpus range, comparing it with the benchmark value of the number of traditional associated concepts, and calculating the expansion ratio as the semantic association expansion width index. The method for collecting the semantic context transfer adaptability is as follows: Placing the material information text in different simulated contexts, and evaluating whether the text semantics can still be reasonably expressed, understood, and remain coherent in these new contexts through a pre-trained language model, and counting the proportion of effective adaptation of the semantics in different new contexts, that is, the semantic context transfer adaptability.

[0035] The specific method for collecting the semantic fluctuation variance value is as follows: At different time points, quantitatively representing the same key semantic dimension and calculating the variance of these numerical sequences. The method for collecting the semantic ambiguity resolution rate is as follows: Collecting material information texts from different backgrounds, for the material property index words with multiple interpretations among them, using a Bayesian model combined with semantic role analysis, and counting the proportion of the number of successfully resolved ambiguity cases in the total number of ambiguity cases to obtain the semantic ambiguity resolution rate. The method for collecting the semantic noise tolerance coefficient is as follows: Artificially adding different degrees of noise to the material information text, and then judging the proportion of the text that can still accurately convey the original semantics after adding the noise through a deep learning-based semantic understanding model to obtain the semantic noise tolerance coefficient. The method for collecting the semantic redundancy elimination ratio is as follows: Analyzing the semantic redundancy situation in the material information text, judging the importance through a text compression algorithm according to the contribution of the semantic to the expression of the core information of the material, and calculating the proportion of the reduction in the semantic information volume of the text after removing the redundancy, that is, the semantic redundancy elimination ratio.

[0036] The specific method for collecting the semantic task matching degree is as follows: for different actual application tasks related to materials, the text semantics of the material information is matched and compared with the key semantic elements required for each task. Through set theory-related algorithms and semantic similarity, the proportion of the semantic intersection in the total semantic set is measured to obtain the semantic task matching degree. The specific method for collecting the semantic process embedding fitness is as follows: according to the established process of material processing and application, by constructing a process semantic model, the degree of fit between the text semantics and the process semantics is calculated. The specific method for collecting the semantic decision support effectiveness is as follows: in the decision-making scenario involving materials, the text semantics containing material information is used as input. By combining an expert system and a machine learning decision algorithm, the degree of conformity between the decision made based on this semantics and the actual optimal decision is observed, and the proportion of the number of conforming times in the total number of decision-making times is used to measure the semantic decision support effectiveness. The specific method for collecting the semantic cross-domain transplantation adaptability is as follows: attempt to transplant the text semantics of the material information to other domains. Through the representative text of the target domain and semantic similarity and logical coherence quantification analysis methods, the proportion of the semantics that can be applied after cross-domain transplantation is statistically obtained to get the semantic cross-domain transplantation adaptability.

[0037] Step 2: Data analysis: used to analyze the data collected in Step 1 and calculate the evaluation value of each group of data, including the semantic deep fusion evaluation model, the semantic innovation and expansion evaluation model, the semantic stability evaluation model, and the semantic application adaptation evaluation model.

[0038] The semantic deep fusion evaluation model is used to evaluate the semantic deep fusion data, specifically expressed as: , where SD represents the semantic deep fusion evaluation value, C represents the cross-modal semantic collaboration coefficient, L represents the semantic hierarchical nesting score, G represents the semantic knowledge graph fusion degree, and I represents the semantic metaphor association strength.

[0039] In the semantic deep fusion evaluation model, ln(C + 1) reflects the marginal diminishing effect of cross-modal collaboration, arctan(L / π) maps the hierarchical nesting score to a finite interval, tanh(G) is used to normalize the influence of the knowledge graph fusion degree, √(I^3 + 1) emphasizes the non-linear growth of metaphorical association, and the denominator e^((C + L) / (G + I)) is used as a regulatory factor to balance the influence of each parameter.

[0040] The semantic innovation and expansion evaluation model is used to evaluate the semantic innovation and expansion data, specifically expressed as: , where SI represents the semantic innovation and expansion evaluation value, R represents the semantic concept birth rate, E represents the semantic logical reconstruction index, W represents the semantic association and expansion width, and M represents the semantic context migration adaptability.

[0041] In the semantic innovation and expansion evaluation model, (R × ln(E + 1))^2 represents the synergy effect of concept generation and logical reconstruction, sinh(W / 10) reflects the exponential growth characteristic of associative expansion, |cos(M × π)| introduces periodic fluctuation correction, and √(R × E × W × M) serves as the basic guarantee value.

[0042] The semantic stability evaluation model is used to evaluate semantic stability evaluation data, specifically expressed as: , where SS represents the semantic stability evaluation value, T represents the time stability, D represents the semantic ambiguity resolution rate, V represents the semantic fluctuation variance value, N represents the semantic noise tolerance coefficient, and R represents the semantic redundancy elimination ratio.

[0043] In the semantic stability evaluation model, (T^2 + D^2)^(1 / 3) calculates the comprehensive effect of stability and ambiguity resolution, exp(-V / N) reflects the negative impact of fluctuations on stability, sin(πR / 180) introduces the periodic effect of redundancy elimination, and log(V × N + 1) serves as the normalization factor.

[0044] The semantic application adaptation evaluation model is used to evaluate semantic application adaptation data, specifically expressed as: , where SA represents the semantic application adaptation evaluation value, S represents the semantic task matching degree, F represents the semantic process embedding fit degree, A represents the semantic decision support effectiveness, and P represents the semantic cross - domain transplantation adaptability.

[0045] In the semantic application adaptation evaluation model, the cubic mean of (S^3 + F^3)^(1 / 3) reflects the basic adaptation ability, exp(-(A - P)^2 / 10) evaluates the matching degree of decision support and transplantation adaptability, sinh((A + P) / 4) emphasizes the synergy effect of decision - making and transplantation, and log(S × F + 2) serves as a constraint term to ensure that the evaluation value is within a reasonable range.

[0046] Step 3: Analysis of stimulating the potential of semantic multi - dimensional integration: It is used to establish a calculation model for the semantic integration innovation potential index, and is used to analyze the basic ability of the semantic information of materials to generate unique value in the initial stage of multi - dimensional integration and expansion.

[0047] The calculation model for the semantic integration innovation potential index is specifically expressed as: , where P1 represents the semantic integration innovation potential index, α represents the semantic deep integration adjustment index, β represents the semantic innovation and expansion adjustment index, and ε = 0.001.

[0048] The ε is used to avoid the denominator being zero and is a very small positive number.

[0049] The semantic fusion innovation potential index calculation model measures the initial potential of semantic multi - element fusion by performing power operations on SD and SI and combining the difference processing of the denominator. It not only considers the individual intensities of the two, but also pays attention to the relative balance relationship between them. The higher the P1 value, the stronger the potential for semantic mining from the perspective of fusion and innovation, providing a good start for subsequent development.

[0050] Step 4: Semantic resilience shaping and co - evolution evaluation: It is used to establish a semantic fusion innovation - stability co - evolution coefficient calculation model, which is used to observe how the fusion innovation potential analyzed in Step 3 interacts with stability when facing challenges related to semantic stability, and shape a resilient and co - evolving semantic structure.

[0051] The semantic fusion innovation - stability co - evolution coefficient calculation model is specifically expressed as: , where P2 represents the semantic fusion innovation - stability co - evolution coefficient, and γ represents the semantic stability adjustment coefficient.

[0052] The semantic fusion innovation - stability co - evolution coefficient calculation model multiplies P1 in Step 3 by a function of SS. In this function, power operations are performed on SS and combined with a special structure of the denominator. By subtracting SS from 1 and adding a very small positive number ε, the positive impact of good stability is highlighted. At the same time, an exponential operation is performed with the logarithm of the sum of SD and SI as the base, associating stability with the fusion innovation potential and considering the impact of stability on the overall semantic structure in terms of co - evolution. The larger the P2 value, the better the semantic can shape resilient and co - evolving characteristics with the help of stability on the basis of fusion innovation.

[0053] Step 5: Semantic ecological adaptability expansion analysis: It is used to establish a semantic ecological adaptability expansion coefficient calculation model. On the basis of Step 3 and Step 4, it considers the ecological adaptability of semantics in different application scenarios.

[0054] The semantic ecological adaptability expansion coefficient calculation model is specifically expressed as: , where P3 represents the semantic ecological adaptability expansion coefficient, and δ represents the semantic application adaptation adjustment parameter.

[0055] After performing power operations on SA, the semantic ecological adaptability expansion coefficient calculation model multiplies an expression combining a trigonometric function and an exponential function. The trigonometric function makes SA show non - linear, increasing first and then decreasing characteristics when changing in the range of 0 to 1, which can better depict the influence of application adaptation degree at different stages. The exponential function part further adjusts the curve shape, overall measuring the adaptability expansion of semantics in the application ecosystem. The higher the P3 value, the stronger the adaptability of semantics in the actual application ecosystem and the better the expansion effect after experiencing fusion innovation and stability shaping.

[0056] Step 6: Semantic mapping intelligent regulation decision-making: According to the analysis results of Step 5, with the help of intelligent algorithms, dynamically adjust the semantic mapping strategy for control to optimize the semantic mapping effect of material information.

[0057] In Step 6, P3 is input into the intelligent decision-making model based on reinforcement learning. Specifically, a deep Q-network model is adopted. Using P3 and historical data as state inputs, different semantic mapping control actions as optional behaviors, the model undergoes simulation training. The training data is constructed based on past material information semantic mapping cases and corresponding control feedback results, and the optimal control actions under different P3 value ranges are learned.

[0058] When the decision indication output by the model in Step 6 is P3≥0.7, the "aggressive expansion" strategy is adopted, which means actively exploring new fusion modes, innovative concepts, and application scenarios on the basis of maintaining the existing semantic mapping state, achieved by increasing the types of modalities for multimodal fusion and encouraging cross-domain semantic associations. When 0.3<P3<0.7, the "steady optimization" strategy is executed to optimize the relatively weak links in Steps 4 and 5, specifically determined by tracing back the data and calculation processes at each stage. When P3≤0.3, the "reconstruction and reshaping" strategy is implemented, which requires a comprehensive re-examination of the construction, fusion, and application adaptation links of material information semantics, involving replacing the semantic analysis model, re-planning the structure of the semantic knowledge graph, and redefining semantic elements based on the actual application pain points.

[0059] The present invention comprehensively collects multi-dimensional data of material information, including semantically deeply fused data, semantically innovatively expanded data, semantically stability-evaluated data, and semantically application-adapted data. Through specific data collection methods, the accuracy and reliability of the data are ensured; the data collected in step 1 is deeply analyzed. By constructing different evaluation models, the evaluation values of each group of data are calculated. These evaluation models comprehensively consider multiple factors and can comprehensively reflect the performance of material information in different dimensions, providing strong data support for subsequent steps such as the analysis of stimulating the potential of semantic multi-dimensional fusion, the shaping of semantic resilience, and the co-evolution evaluation, and providing a rich and high-quality information basis for subsequent data analysis and semantic mapping control; a calculation model for the semantic fusion innovation potential index is established to analyze the basic ability of the semantics of material information to generate unique value in the initial stage of multi-dimensional fusion and expansion. Through this model, the potential of semantics in multi-dimensional fusion can be quantitatively evaluated, providing a clear direction for subsequent development and optimization, helping to discover new fusion patterns and innovative concepts, and promoting the further development of the semantics of material information; a calculation model for the co-evolution coefficient of semantic fusion innovation-stability is established to observe how the fusion innovation potential interacts with stability when facing challenges related to semantic stability. This model can evaluate the performance of the semantic structure in co-evolution and the impact of stability on the overall semantic structure, helping to shape a resilient and co-evolving semantic structure and improving the adaptability and vitality of the semantics of material information; a calculation model for the semantic ecological adaptability expansion coefficient is established. Based on the fusion innovation and stability shaping, the ecological adaptability of semantics in different application scenarios is considered. Through this model, the adaptability expansion of semantics in the application ecosystem can be quantitatively evaluated, providing strong support for subsequent application development and optimization, helping to improve the adaptability and expansion effect of semantics in actual applications, and promoting the wide application of the semantics of material information; according to the analysis results of step 5, the semantic mapping strategy is dynamically adjusted and controlled by means of intelligent algorithms to optimize the semantic mapping effect of material information. Through an intelligent decision-making model based on reinforcement learning, the optimal control actions under different conditions can be learned, realizing the intelligent regulation of semantic mapping, helping to improve the accuracy and efficiency of semantic mapping, and promoting the further development of the semantic mapping technology of material information.

[0060] Secondly: In the attached drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present disclosure are involved. For other structures, reference may be made to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0061] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A material information semantic mapping control method based on natural language processing, characterized in that: include: Step 1: Material information collection: Collect semantic deep fusion data, semantic innovation and expansion data, semantic stability assessment data, and semantic application adaptation data of target material information; Step 2: Data analysis: used to analyze the data collected in step 1 and calculate the evaluation value of each set of data, including the semantic deep fusion evaluation model, the semantic innovation and expansion evaluation model, the semantic stability evaluation model, and the semantic application adaptation evaluation model; The semantic deep fusion evaluation model is used to evaluate the semantic deep fusion data, which is specifically expressed as follows: , SD represents the semantic deep fusion evaluation value, C represents the cross-modal semantic synergy coefficient, L represents the semantic hierarchical nesting score, G represents the semantic knowledge graph fusion degree, and I represents the semantic metaphor association strength; The semantic innovation and extension evaluation model is used to evaluate the semantic innovation and extension data, which is specifically expressed as follows: , SI represents the semantic innovation and expansion evaluation value, R represents the semantic concept newness rate, E represents the semantic logic reconstruction index, W represents the semantic association expansion width, and M represents the semantic context transfer adaptability; The semantic stability evaluation model is used to evaluate the semantic stability evaluation data, and is specifically expressed as follows: , SS represents the semantic stability evaluation value, T represents the temporal stability, D represents the semantic ambiguity resolution rate, V represents the semantic fluctuation variance value, N represents the semantic noise tolerance coefficient, and R represents the semantic redundancy elimination ratio; The semantic application adaptation evaluation model is used to evaluate the semantic application adaptation data, which is specifically expressed as follows: , SA represents the semantic application adaptation assessment value, S represents the semantic task matching degree, F represents the semantic process embedding fit, A represents the semantic decision support effectiveness, and P represents the semantic cross-domain transplant adaptability; The method for collecting the cross-modal semantic synergy coefficient is specifically as follows: first, the text and other modal data are respectively mapped to a common semantic space through a cross-modal feature extraction method, and then the covariance between the semantic feature vectors of different modalities is calculated, and then divided by the product of their respective standard deviations to obtain the cross-modal semantic synergy coefficient. The method for collecting the semantic level nesting score is specifically as follows: the syntax tree and semantic role labeling technology are used to analyze the hierarchical structure of the semantic components in the material information text, and scores are assigned to reasonably nested semantic level pairs. A complete match with the set ideal nesting mode is scored as 1 point, and a partial match is scored as 0.5 points. The scores of all level pairs are summarized and averaged to obtain the semantic level nesting score. The specific method for collecting the degree of fusion of semantic knowledge graph is as follows: construct a knowledge graph in the field of materials, extract the semantic elements in the collected text semantic information and fuse them with the corresponding nodes and edges in the knowledge graph, and count the proportion of the number of successfully fused semantic elements to the total number of fused semantic elements in the text, which is used as the degree of fusion of semantic knowledge graph. The specific method for collecting the strength of semantic metaphor association is as follows: through the metaphor recognition algorithm, identify the sentences in the material information text that use metaphors to describe the material, and then analyze the distance between the metaphor and the subject in the semantic feature space through the word vector method, and subtract the normalized value of the distance from 1 to obtain the strength of semantic metaphor association; The method for collecting the semantic concept birth rate is specifically as follows: using text mining technology to analyze a large amount of the latest material information texts, combining professional field dictionaries and the boundary entropy method based on statistical language models, identifying completely new concepts that did not exist in the previous material semantic system, and counting the proportion of their number to the total number of concepts, which is the semantic concept birth rate. The method for collecting the semantic logic reconstruction index is specifically as follows: using a rule-based logic analyzer combined with a deep learning semantic parsing model to analyze the logical expressions of material causal relationships, function and structure associations in the material information text, and comparing them with the traditional and established material semantic logic structure, counting the proportion of the number of sentences in the text that reconstructed the original logical relationship to the total number of logic-related sentences, and obtaining the semantic logic reconstruction index. The specific method for collecting the width of semantic association expansion is as follows: starting from the core concept of the material, calculating the semantic similarity of word vectors and finding the path from the core concept to other related concepts in the semantic network based on graph algorithms, counting the number of concepts of different fields and natures that can be associated within a certain text corpus, comparing it with the benchmark value of the number of traditional associated concepts, and calculating the expansion ratio as an indicator of the width of semantic association expansion. The specific method for collecting the adaptability of semantic context transfer is as follows: placing the material information text in different simulated contexts, and evaluating whether the text semantics can still be reasonably expressed, understood and coherent in these new contexts through the pre-trained language model, and counting the proportion of effective adaptation of semantics in different new contexts, that is, the adaptability of semantic context transfer; The method for collecting the variance value of semantic fluctuation is specifically as follows: at different time points, the same key semantic dimension is quantified and expressed, and the variance of these numerical sequences is calculated. The method for collecting the semantic ambiguity resolution rate is specifically as follows: material information texts from different backgrounds are collected, and for material performance index words with multiple interpretations, the Bayesian model is combined with semantic role analysis to count the proportion of the number of cases where ambiguity is successfully resolved to the total number of ambiguous cases, and the semantic ambiguity resolution rate is obtained. The method for collecting the semantic noise tolerance coefficient is specifically as follows: different degrees of noise are artificially added to the material information text, and then the semantic understanding model based on deep learning is used to determine the proportion of the text that can still accurately convey the original semantics after the noise is added, and the semantic noise tolerance coefficient is obtained. The method for collecting the semantic redundancy elimination ratio is specifically as follows: the semantic redundancy in the material information text is analyzed, and the importance is determined according to the contribution of semantics to the expression of the core information of the material through a text compression algorithm, and the proportion of the reduction in the amount of text semantic information after removing the redundancy is calculated, that is, the semantic redundancy elimination ratio. The method for collecting the semantic task matching degree is specifically as follows: for different practical application tasks related to materials, the semantics of the material information text are matched and compared with the key semantic elements required for each task, and the semantic task matching degree is obtained by measuring the proportion of the semantic intersection in the total semantic set through set theory-related algorithms combined with semantic similarity. The method for collecting the semantic process embedding fit is specifically as follows: according to the established process of material processing and application, the degree of fit between the text semantics and the process semantics is calculated by constructing a process semantic model. The method for collecting the effectiveness of semantic decision support is specifically as follows: in a decision-making scenario involving materials, the text semantics containing material information is used as input, and by combining an expert system and a machine learning decision algorithm, the degree of fit between the decision made based on the semantics and the actual optimal decision is observed, and the effectiveness of semantic decision support is measured by the proportion of the number of fits in the total number of decisions. The method for collecting the adaptability of semantic cross-domain transplantation is specifically as follows: an attempt is made to transplant the semantics of the material information text to other fields, and through representative texts in the target field combined with semantic similarity and logical coherence quantitative analysis methods, the proportion of semantics that can be applied after cross-domain transplantation is statistically analyzed to obtain the adaptability of semantic cross-domain transplantation; Step 3: Semantic multi-dimensional fusion potential stimulation analysis: used to establish a semantic fusion innovation potential index calculation model, used to analyze the basic ability of material information semantics to generate unique value in the initial stage of multi-dimensional fusion and expansion; The semantic fusion innovation potential index calculation model is specifically expressed as: , P1 represents the semantic fusion innovation potential index, α represents the semantic deep fusion regulation index, β represents the semantic innovation expansion regulation index, ε=0.001; Step 4: Semantic resilience shaping and co-evolution assessment: used to establish a semantic fusion innovation-stability co-evolution coefficient calculation model to observe how the fusion innovation potential analyzed in step 3 interacts with stability when facing challenges related to semantic stability, shaping a semantic structure that is resilient and capable of co-evolution; The semantic fusion innovation-stability co-evolution coefficient calculation model is specifically expressed as: , P2 represents the semantic fusion innovation-stability co-evolution coefficient, and γ represents the semantic stability adjustment coefficient; Step 5: Semantic ecological adaptability expansion analysis: used to establish a semantic ecological adaptability expansion coefficient calculation model. Based on steps 3 and 4, the ecological adaptability of semantics in different application scenarios is considered; The semantic ecological adaptability expansion coefficient calculation model is specifically expressed as: , P3 represents the semantic ecological adaptability expansion coefficient, and δ represents the semantic application adaptation adjustment parameter; Step 6: Semantic mapping intelligent control decision: According to the analysis results of step 5, the semantic mapping strategy is dynamically adjusted with the help of intelligent algorithms to optimize the semantic mapping effect of material information.

2. The material information semantic mapping control method based on natural language processing according to claim 1 is characterized by: The semantic deep fusion data include cross-modal semantic synergy coefficient, semantic hierarchical nesting score, semantic knowledge graph fusion degree and semantic metaphor association strength; the semantic innovation and expansion data include semantic concept generation rate, semantic logic reconstruction index, semantic association expansion width and semantic context migration adaptability; the semantic stability assessment data include semantic fluctuation variance value, semantic ambiguity resolution rate, semantic noise tolerance coefficient and semantic redundancy elimination ratio; the semantic application adaptation data include semantic task matching degree, semantic process embedding fit, semantic decision support effectiveness and semantic cross-domain transplantation adaptability.

Images