Method and System for Enhancing the Answer Accuracy of Large Models Based on Knowledge Graphs

Abstract

The present invention discloses a method and system for enhancing the answer accuracy of a large model based on a knowledge graph, which relates to the technical field of electrical digital data processing. The method for enhancing the answer accuracy of a large model based on a knowledge graph includes the following steps: answer accuracy judgment, graph update adjustment, and graph embedding optimization. The present invention evaluates and judges the answer accuracy of the model to be evaluated after embedding a preset knowledge graph to obtain an answer accuracy detection result, and then judges whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, the optimized update speed of the preset knowledge graph is obtained. Otherwise, the knowledge graph embedding optimization of the preset knowledge graph is carried out in combination with the answer accuracy detection result, achieving the effect of enhancing the answer accuracy of the knowledge graph embedded in the large model for reasoning, and solving the problem of low answer accuracy of the knowledge graph embedded in the large model for reasoning in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a method and system for enhancing the answer accuracy of a large model based on a knowledge graph. Background Art

[0002] A knowledge graph (KG), as a graphical structure representing world knowledge through entities, relationships, and attributes, provides efficient knowledge representation and reasoning capabilities. The combination of a knowledge graph and the text generation ability of a large model can make up for the deficiencies of traditional large models in logical reasoning and knowledge application. As time goes by, the information in the knowledge graph will gradually become outdated, especially in fields involving rapid changes (such as technology, etc.), thus affecting the answer accuracy of the large model. Therefore, how to efficiently integrate a dynamically updated knowledge graph into a trained large model to avoid the "cold start" problem or poor timeliness requires new technical support. Entities and relationships in a knowledge graph usually need to be transformed into vector representations so that they can be processed in a neural network. However, there are still great difficulties in representing these structured knowledge graphs as embedding vectors suitable for deep learning models. Existing graph embedding methods (such as TransE, DistMult, etc.) may not be able to fully capture the details and deep relationships in the graph when dealing with complex relationships and high-dimensional knowledge graphs. The knowledge graph provides important knowledge supplementation and reasoning capabilities for the large model, enabling the large model to be significantly improved in terms of knowledge application and generation accuracy. In the future, the integration of the large model and the knowledge graph will be closer, and more accurate and reliable intelligent services can be provided in a wider range of application scenarios.

[0003] Existing large model answers based on knowledge graphs usually rely on the structured knowledge of the knowledge graph, combine entity recognition, relationship extraction, reasoning techniques, etc., and use knowledge graph embedding to enhance the reasoning ability of the large model. First, the question input by the user is processed, including text cleaning, word segmentation, named entity recognition, entity disambiguation, etc., and entities and relationships related to the question are obtained by querying the knowledge graph. If the question requires specific facts or reasoning, the query module can extract relevant information from the graph. Second, based on the input question and the information obtained from the graph, a reasonable answer is generated. The large model can reason based on the structured information in the graph and generate an answer consistent with the facts. Through techniques such as multimodal data integration, context-aware query, and self-supervised learning, the model can dynamically adjust its reasoning process to provide accurate and in-depth answers. Combining the natural language generation ability of the large model with the structured knowledge of the knowledge graph can significantly improve the accuracy and logical consistency of the large model when answering questions.

[0004] For example, a method and system for enhancing the answer accuracy of a large model based on a knowledge graph disclosed in a patent application with the publication number: CN119271784A, including: obtaining a text data set, preprocessing the text data set, and extracting entities and relationships in the text data set; establishing an entity connection graph based on the entities and relationships in the text data set, performing fusion processing on the entity nodes of the entity connection graph, and creating a knowledge graph according to the entity nodes and relationships after the fusion processing; obtaining a user's query question, and determining a matching node of the user's query question according to the user's query question; identifying the user's question intention according to the user's query question, determining a prompt template according to the user's question intention and the matching node corresponding to the user's query question, inputting the prompt template into the large model, and obtaining a credible answer to the user's query question.

[0005] For example, a question-answering method and system based on a knowledge graph and a large language model disclosed in the invention patent announcement with the announcement number: CN116775847B, including: receiving an intelligence question to be processed, extracting entity features to obtain initial feature entities; performing a vector space search in a vector database to determine extended entities; querying a self-established graph database based on the initial feature entities, constructing query auxiliary information to generate an initial intermediate answer; determining whether a new entity appears in the initial intermediate answer to determine whether to perform the next round of entity feature extraction. Each time a round of entity feature extraction is performed, an intermediate answer is generated until it is determined that no new entity appears in the intermediate answer; performing deduplication and fusion on all intermediate answers obtained through one or more rounds of entity feature extraction to obtain a final answer matching the intelligence question to be processed.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of the present application, it is found that the above technologies have at least the following technical problems:

[0007] When embedding a knowledge graph into a large model, rich semantic information, context relationships, and complex structures of the graph in the knowledge graph may be simplified into relatively abstract low-dimensional vectors, that is, converting entities and relationships in the graph into vector representations. However, the graph structure in the knowledge graph is often very sparse, and the types of nodes and edges are also very diverse. This often causes some details to be lost when converting graph information into vector representations. Especially in complex queries, this lost information may lead to inaccurate or incomplete answers.

[0008] In addition, the update speed of the knowledge graph is relatively slow, and it may contain outdated or inaccurate information, resulting in inaccurate answers from the large model, and there is a problem of low accuracy in reasoning and answering when the knowledge graph is embedded into the large model. Summary of the Invention

[0009] Embodiments of the present application provide a method and system for enhancing the answer accuracy of a large model based on a knowledge graph, which solves the problem of low accuracy in reasoning and answering when the knowledge graph is embedded in the large model in the prior art, and realizes the enhancement of the accuracy in reasoning and answering when the knowledge graph is embedded in the large model.

[0010] Embodiments of the present application provide a method for enhancing the answer accuracy of a large model based on a knowledge graph, including the following steps: Step 1, evaluate and judge the answer accuracy of the model to be evaluated after embedding the preset knowledge graph, and obtain the answer accuracy detection result; Step 2, combine the answer accuracy detection result to judge whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, then based on the answer accuracy detection result and the initial update speed of the preset knowledge graph, obtain the optimized update speed of the preset knowledge graph. The initial update speed adjustment means optimizing the initial update speed of the preset knowledge graph based on the answer accuracy detection result to improve the answer accuracy of the model to be evaluated; Step 3, if the initial update speed of the preset knowledge graph is not adjusted, then combine the answer accuracy detection result to perform knowledge graph embedding optimization on the preset knowledge graph. The knowledge graph embedding optimization is used to improve the embedding quality of the preset knowledge graph embedded in the model to be evaluated to enhance the answer accuracy of the model to be evaluated.

[0011] Further, the specific steps for evaluating and judging the answer accuracy of the model to be evaluated after embedding the preset knowledge graph are as follows: Obtain the quantization data of the embedding quality after the preset knowledge graph is embedded in the model to be evaluated. The embedding quality quantization data includes embedding vector similarity, embedding global clustering coefficient, embedding space density, and embedding reconstruction error; Perform parameter interaction processing on the embedding global clustering coefficient difference degree and the embedding vector similarity, and the embedding space density difference degree and the embedding reconstruction error respectively. After weighting the corresponding parameter interaction processing results through the embedding quality influence weight, couple them to obtain the embedding quality influence factor; The embedding quality influence weight includes an embedding tightness influence weight and an embedding accuracy influence weight; The embedding quality influence factor is used to describe the influence degree of the embedding quality of the preset knowledge graph embedded in the model to be evaluated on the answer accuracy determination value; The embedding quality influence factor represents the quantization data of the combined influence degree of the embedding quality quantization data on the embedding quality of the preset knowledge graph embedded in the model to be evaluated on the answer accuracy determination value; Obtain the answer accuracy rate of the model to be evaluated, and perform embedding quality correlation operation on the answer accuracy rate according to the obtained embedding quality influence factor to obtain the answer accuracy determination value. The answer accuracy determination value is used to quantitatively evaluate the corresponding answer accuracy degree after the preset knowledge graph is embedded in the model to be evaluated; The answer accuracy determination value represents the quantization data of the embedding quality influence factor and the answer accuracy rate on the corresponding answer accuracy after the preset knowledge graph is embedded in the model to be evaluated.

[0012] Further, the specific steps for obtaining the detection result of the answer accuracy are as follows: Combine the obtained answer accuracy determination value with the minimum answer accuracy threshold obtained from the preset database for comparison and judgment; if the answer accuracy determination value is greater than the minimum answer accuracy threshold, record the answer accuracy detection result as the answer accuracy determination value being qualified and the answer accuracy of the model to be evaluated being to be monitored; if the answer accuracy is not greater than the minimum answer accuracy threshold, record the answer accuracy detection result as the answer accuracy determination value being unqualified and the answer accuracy of the model to be evaluated being to be enhanced.

[0013] Further, the specific process for determining whether to adjust the initial update speed of the preset knowledge graph by combining the answer accuracy detection result is as follows: If the answer accuracy detection result is that the answer accuracy determination value is qualified and the answer accuracy of the model to be evaluated is to be monitored, then adjust the initial update speed of the preset knowledge graph; otherwise, do not adjust the initial update speed of the preset knowledge graph.

[0014] Further, the specific steps for adjusting the initial update speed of the preset knowledge graph are as follows: Map from the preset accurate deviation mapping set in the preset database according to the deviation degree between the answer accuracy determination value in the answer accuracy detection result and the maximum answer accuracy threshold to obtain a graph speed update coefficient, where the preset accurate deviation mapping set represents the mapping relationship between the answer accuracy determination value and the maximum answer accuracy threshold; Obtain the initial update speed of the preset knowledge graph and the graph speed update coefficient, and use the graph speed update coefficient to adjust the initial update speed to obtain an optimized update speed.

[0015] Further, the specific process for optimizing the knowledge graph embedding of the preset knowledge graph by combining the answer accuracy detection result is as follows: S31, when the answer accuracy in the answer accuracy detection result is not greater than the minimum answer accuracy threshold, perform graph community detection and division on the preset knowledge graph to obtain the community density of the graph community; S32, optimize the knowledge graph compression embedding of the preset knowledge graph by combining the community density of the graph community, where the knowledge graph compression embedding optimization refers to obtaining a graph compression rate through the graph compression strength to perform knowledge graph compression; S33, after performing the knowledge graph compression embedding optimization, perform hierarchical embedding optimization on the knowledge graph, where the hierarchical embedding optimization refers to performing hierarchical embedding of the knowledge graph based on the obtained hierarchical embedding priority score, and the hierarchical embedding priority score is used to judge the hierarchical embedding priority during the process of performing hierarchical embedding of the knowledge graph.

[0016] Further, the method for obtaining the graph compression rate based on the graph compression strength to perform knowledge graph compression is as follows: Based on the deviation degree between the community density of the graph community and the maximum community density threshold, map it in the preset strength allocation mapping set in the preset database to obtain the graph compression strength of the graph community. The preset strength allocation mapping set represents the mapping relationship between the community density and the maximum community density threshold; Map the deviation degree between the obtained graph compression strength of the graph community and the compression strength reference value in the preset compression strength mapping set in the preset database to obtain the graph compression rate of the graph community. The preset compression strength mapping set represents the mapping relationship between the graph compression strength and the compression strength reference value; Perform knowledge graph compression on the graph community according to the obtained graph compression rate.

[0017] Further, the method for performing hierarchical embedding of the knowledge graph based on the obtained hierarchical embedding priority score is as follows: Quantify the information retention degree of the graph community for knowledge graph compression by the graph compression data after knowledge graph compression based on the graph community to obtain a graph compression determination value; Map the deviation degree between the obtained graph compression determination value and the graph compression reference value in the preset database to obtain a compression quality scoring weight; Weight the graph compression determination value by the obtained compression quality scoring weight, and couple it with the compression rate scoring weight obtained from the preset database to weight the graph compression rate to obtain a hierarchical embedding priority score; Combine the hierarchical embedding priority scores of the graph communities and sort them in descending order to obtain a hierarchical embedding priority level, and perform hierarchical embedding of the knowledge graph according to the hierarchical embedding priority level.

[0018] Further, the method for quantifying the information retention degree of the graph community for knowledge graph compression by the graph compression data after knowledge graph compression based on the graph community to obtain a graph compression determination value is as follows: Obtain the graph compression data after knowledge graph compression of the graph community. The graph compression data includes graph density, node retention degree, edge retention degree, and information loss degree; Perform parameter interaction processing on the coupling result of the node retention degree and the edge retention degree through the result of the graph density difference degree, and couple it with the zeroing operation result of the information loss degree weighted by the compression evaluation weight to obtain a graph compression determination value; The compression evaluation weight includes a compression retention evaluation weight and a compression loss evaluation weight; The graph compression determination value represents the quantization data for jointly evaluating the information retention degree of the graph community for knowledge graph compression by the graph compression data.

[0019] The embodiment of the present application provides a system for enhancing the answer accuracy of a large model based on a knowledge graph, including: an answer accuracy judgment module, a graph update adjustment module, and a graph embedding optimization module; the answer accuracy judgment module is used to evaluate and judge the answer accuracy of the model to be evaluated after being embedded in a preset knowledge graph, and obtain an answer accuracy detection result; the graph update adjustment module is used to judge whether to adjust the initial update speed of the preset knowledge graph in combination with the answer accuracy detection result. If the initial update speed of the preset knowledge graph is adjusted, the optimized update speed of the preset knowledge graph is obtained based on the answer accuracy detection result and the initial update speed of the preset knowledge graph. The initial update speed adjustment means optimizing the initial update speed of the preset knowledge graph based on the answer accuracy detection result to improve the answer accuracy of the model to be evaluated; the graph embedding optimization module is used to, if the initial update speed of the preset knowledge graph is not adjusted, perform knowledge graph embedding optimization on the preset knowledge graph in combination with the answer accuracy detection result. The knowledge graph embedding optimization is used to improve the embedding quality of the preset knowledge graph embedded in the model to be evaluated to enhance the answer accuracy of the model to be evaluated.

[0020] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0021] 1. By evaluating and judging the answer accuracy of the model to be evaluated after being embedded in a preset knowledge graph to obtain an answer accuracy detection result, then judging whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, the optimized update speed of the preset knowledge graph is obtained. Otherwise, the knowledge graph embedding optimization is performed on the preset knowledge graph in combination with the answer accuracy detection result, thereby realizing the improvement of the embedding quality of the knowledge graph embedded in the large model, and further realizing the enhancement of the inference answer accuracy of the knowledge graph embedded in the large model, effectively solving the problem of low inference answer accuracy of the knowledge graph embedded in the large model in the prior art.

[0022] 2. By mapping the deviation degree between the answer accuracy determination value in the answer accuracy detection result and the maximum answer accuracy threshold from the preset accurate deviation mapping set in the preset database, a graph speed update coefficient is obtained, and then the initial update speed is adjusted with the graph speed update coefficient to obtain the optimized update speed, thereby realizing the optimization of the initial update speed of the preset knowledge graph based on the answer accuracy detection result, and further realizing the enhancement of the inference answer accuracy of the large model through the knowledge graph update optimization.

[0023] 3. By mapping the deviation degree between the obtained graph compression determination value and the graph compression reference value from a preset database to obtain the compression quality scoring weight, then weighting the graph compression determination value based on the obtained compression quality scoring weight, coupling with the compression ratio scoring weight obtained from the preset database to weight the graph compression ratio to obtain a hierarchical embedding priority score, and finally performing hierarchical embedding of the knowledge graph according to the hierarchical embedding priority, the reliability of the hierarchical embedding of the knowledge graph into the large model is improved, and furthermore, the accuracy of the inference answer of the large model is enhanced through the optimization of the knowledge graph embedding. Description of the Drawings

[0024] Figure 1 It is a flowchart of the method for enhancing the answer accuracy of the large model based on the knowledge graph provided by the embodiment of the present application;

[0025] Figure 2 It is a schematic structural diagram of the system for enhancing the answer accuracy of the large model based on the knowledge graph provided by the embodiment of the present application. Detailed Embodiments

[0026] The embodiment of the present application provides a method and system for enhancing the answer accuracy of a large model based on a knowledge graph, which solves the problem in the prior art that the accuracy of the inference answer when the knowledge graph is embedded in the large model is not high. By evaluating and judging the answer accuracy of the model to be evaluated after embedding the preset knowledge graph to obtain the answer accuracy detection result, then combining the answer accuracy detection result to judge whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, then the optimized update speed of the preset knowledge graph is obtained based on the answer accuracy detection result and the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is not adjusted, then the knowledge graph embedding optimization of the preset knowledge graph is performed in combination with the answer accuracy detection result, realizing the enhancement of the inference answer accuracy when the knowledge graph is embedded in the large model.

[0027] The technical solution in the embodiment of the present application for solving the problem of low accuracy of the inference answer when the knowledge graph is embedded in the large model is as follows:

[0028] By obtaining the answer accuracy detection result to judge whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, then the optimized update speed of the preset knowledge graph is obtained. Otherwise, the knowledge graph embedding optimization of the preset knowledge graph is performed, achieving the effect of enhancing the inference answer accuracy when the knowledge graph is embedded in the large model.

[0029] To better understand the above technical solution, the above technical solution will be described in detail below in combination with the accompanying drawings of the specification and specific embodiments.

[0030] As Figure 1 shown, the following is a flowchart of a method for enhancing the answer accuracy of a large model based on a knowledge graph provided by an embodiment of the present application. The method includes the following steps: Step 1, evaluate and judge the answer accuracy of the model to be evaluated after embedding a preset knowledge graph, and obtain an answer accuracy detection result; Step 2, combine the answer accuracy detection result to judge whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, then obtain an optimized update speed of the preset knowledge graph based on the answer accuracy detection result and the initial update speed of the preset knowledge graph. The initial update speed adjustment means optimizing the initial update speed of the preset knowledge graph based on the answer accuracy detection result to improve the answer accuracy of the model to be evaluated; Step 3, if the initial update speed of the preset knowledge graph is not adjusted, then perform knowledge graph embedding optimization on the preset knowledge graph in combination with the answer accuracy detection result. The knowledge graph embedding optimization is used to improve the embedding quality of the preset knowledge graph embedded in the model to be evaluated to enhance the answer accuracy of the model to be evaluated.

[0031] In this embodiment, the large model to be evaluated is specifically, for example, the GPT series (such as GPT-4) can be used for tasks such as text generation, translation, and question answering; a knowledge graph is a way of representing entities (such as people, places, things, etc.) and their relationships as a graphical structure, constructing a knowledge network through nodes (representing entities) and edges (representing relationships between entities), enabling the large model to be evaluated (such as GPT-4) to understand and process the connections between information; the knowledge graph can provide structured and explicit knowledge about the world. Over time, the information in the knowledge graph may become outdated or inaccurate, especially in rapidly developing fields. Therefore, the update of the knowledge graph is very important. At the same time, the large model to be evaluated has advantages in language generation and reasoning capabilities. The combination of the two can make up for their respective shortcomings and improve reasoning capabilities and answer accuracy. By converting the knowledge graph into a format that can be input into the large model to be evaluated, for example, using graph embedding methods (such as TransE, DistMult, etc.) to map the entities and relationships in the knowledge graph to a low-dimensional space, the information in the knowledge graph can be introduced as background knowledge into the reasoning process of the large model to be evaluated, thereby helping the model make more reasonable judgments when facing some reasoning problems without direct text support.

[0032] Although embedding knowledge graphs into the large model to be evaluated to enhance reasoning ability has become a popular direction, it still faces the problem of low quality of knowledge graphs, which directly affects the accuracy of the reasoning answers of the large model to be evaluated. During the reasoning process, the large model to be evaluated often needs to extract information from the knowledge graph and combine it with natural language text information. When the embedding quality of the knowledge graph is low, the smoothness of information flow may be hindered. The large model to be evaluated often requires multi-step reasoning to generate answers. If the embedded information in the graph is missing or inaccurate, the reasoning chain will break, resulting in inaccurate final answers. The algorithm of this application optimizes the knowledge graph embedding and the knowledge graph update speed to further improve the embedding quality of the knowledge graph into the large model to be evaluated (taking GPT-4 as an example), so that the large model to be evaluated can more accurately understand and utilize structured knowledge, improve the coherence and correctness of reasoning, and then provide more accurate and reliable answers.

[0033] Further, evaluate and judge the answer accuracy of the model to be evaluated after embedding the preset knowledge graph. The specific steps are as follows: Obtain the quantitative data of the embedding quality after embedding the preset knowledge graph into the model to be evaluated; perform parameter interaction processing on the global clustering coefficient difference degree of the embedding, the embedding vector similarity, the embedding space density difference degree, and the embedding reconstruction error respectively, and couple the results of the parameter interaction processing weighted by the embedding quality influence weights to obtain the embedding quality influence factor.

[0034] The method for obtaining the embedding quality influence factor is as follows:

[0035] ;

[0036] In the formula, represents the embedding quality influence factor, represents the embedding tightness influence weight, represents the embedding accuracy influence weight, represents the global clustering coefficient of the embedding, represents the reference minimum clustering coefficient, represents the embedding vector similarity, represents the embedding space density, represents the reference embedding space density, represents the embedding reconstruction error.

[0037] It should be added that the parameter interaction processing is used to describe the interaction relationship between the two parameters involved; among them, the embedded quality quantification data includes the embedded vector similarity, the embedded global clustering coefficient, the embedded space density, and the embedded reconstruction error; specifically, the embedded vector similarity is obtained through the sklearn library in Python; the embedded global clustering coefficient is obtained through NetworkX in Python; the embedded space density is obtained through the scikit-learn library in Python; the embedded reconstruction error is obtained through TensorFlow.

[0038] The minimum value of the collected historical embedded global clustering coefficient represents the reference minimum clustering coefficient, and the result of summing and averaging the collected historical embedded space density represents the reference embedded space density.

[0039] The embedded quality influence weights include the embedded tightness influence weight and the embedded accuracy influence weight; the embedded tightness influence weight and the embedded accuracy influence weight respectively correspond to describing the influence degree of the embedded tightness situation (that is, the result of parameter interaction processing of the difference degree of the embedded global clustering coefficient and the embedded vector similarity) and the embedded accuracy situation (that is, the result of parameter interaction processing of the difference degree of the embedded space density and the embedded reconstruction error) on the embedded quality influence factor, and the value ranges are both [0, 1] and their sum is 1. For example, the real-time embedded tightness situation and the embedded accuracy situation are input into the mapping set of the preset embedded tightness situation, embedded accuracy situation and their corresponding weight factors in the database to obtain the corresponding weights.

[0040] Obtain the answer accuracy rate of the model to be evaluated, and perform an embedded quality correlation operation on the answer accuracy rate according to the obtained embedded quality influence factor to obtain the answer accuracy determination value. Among them, the answer accuracy rate is the ratio of the number of times the model to be evaluated answers correctly to the total number of answers, and the answer accuracy rate is obtained through manual annotation.

[0041] The method for obtaining the answer accuracy determination value is as follows:

[0042] ;

[0043] In the formula, represents the answer accuracy determination value, represents the embedded quality influence factor, represents the answer accuracy rate.

[0044] It should be understood that the answer accuracy determination value is used to quantitatively evaluate the accuracy degree of the corresponding answer after the preset knowledge graph is embedded in the model to be evaluated; among them, as the answer accuracy rate increases, the answer accuracy determination value increases accordingly. In addition, the answer accuracy determination value includes parameters in multiple aspects, representing the quantitative data of the embedding quality impact factor and the answer accuracy rate jointly on the answer accuracy after the preset knowledge graph is embedded in the model to be evaluated.

[0045] It also should be understood that the embedding quality impact factor represents the quantitative data of the joint impact of the embedding quality quantitative data on the embedding quality of the preset knowledge graph embedded in the model to be evaluated on the answer accuracy determination value, and is used to describe the impact degree of the embedding quality of the preset knowledge graph embedded in the model to be evaluated on the answer accuracy determination value; the embedding quality impact factor includes parameters in multiple aspects, and there are connections between the parameters and they do not exist independently. For example, as the global clustering coefficient of the embedding increases, it usually means that the entity and relationship of the knowledge graph are more closely organized in the embedding space, with better clustering, making the embedding vectors of similar entities or relationships in the knowledge graph closer, improving the similarity of the vectors, that is, the embedding vector similarity increases accordingly; if the embedding vector can well capture the relationship between similar entities, the model to be evaluated will better retain the global clustering characteristics of the knowledge graph; at the same time, as the density of the embedding space increases, it indicates that the high-density embedding space can provide more information, thereby reducing the reconstruction error, that is, the embedding reconstruction error decreases accordingly.

[0046] Through the numerical evaluation of the accuracy degree of the corresponding answer after the preset knowledge graph is embedded in the model to be evaluated, a more accurate evaluation of the answer accuracy degree of the model to be evaluated is realized, and further, the reliability of the evaluation of the accuracy degree of the corresponding answer after the preset knowledge graph is embedded in the model to be evaluated is improved.

[0047] Furthermore, the specific steps to obtain the answer accuracy detection result are as follows: Combine the obtained answer accuracy determination value with the minimum answer accuracy threshold obtained from the preset database for comparison and judgment; if the answer accuracy determination value is greater than the minimum answer accuracy threshold, record the answer accuracy detection result as the answer accuracy determination value being qualified and the answer accuracy of the model to be evaluated being to be monitored; if the answer accuracy is not greater than the minimum answer accuracy threshold, record the answer accuracy detection result as the answer accuracy determination value being unqualified and the answer accuracy of the model to be evaluated being to be enhanced.

[0048] In this embodiment, the minimum answer accuracy threshold is set by professionals according to the standards in the field. For example, the minimum answer accuracy threshold is set to 0.5; by combining the minimum answer accuracy threshold with the obtained answer accuracy determination value for comparison and judgment to obtain the answer accuracy detection result, a more accurate judgment of the accuracy degree of the corresponding answer after the preset knowledge graph is embedded in the model to be evaluated is realized.

[0049] Further, it is determined whether to adjust the initial update speed of the preset knowledge graph in combination with the answer accuracy detection result. The specific process is as follows: If the answer accuracy detection result is that the answer accuracy determination value is qualified and the answer accuracy of the model to be evaluated is to be monitored, the initial update speed of the preset knowledge graph is adjusted; otherwise, the initial update speed of the preset knowledge graph is not adjusted.

[0050] It should be added that the specific steps for adjusting the initial update speed of the preset knowledge graph are as follows: Map from the preset accurate deviation mapping set in the preset database according to the deviation degree between the answer accuracy determination value in the answer accuracy detection result and the maximum answer accuracy threshold to obtain the graph speed update coefficient. The preset accurate deviation mapping set represents the mapping relationship between the answer accuracy determination value and the maximum answer accuracy threshold; Obtain the initial update speed of the preset knowledge graph and the graph speed update coefficient, and adjust the initial update speed with the graph speed update coefficient to obtain the optimized update speed.

[0051] In this embodiment, the maximum answer accuracy threshold is set by professionals according to the standards in the field. For example, the maximum answer accuracy threshold is set to 1; A preset accurate deviation mapping set between the answer accuracy determination value and the maximum answer accuracy threshold is constructed, and the real-time answer accuracy determination value is input into the preset accurate deviation mapping set to obtain the corresponding graph speed update coefficient; By adjusting the initial update speed of the preset knowledge graph, the enhancement of the inference answer accuracy of the knowledge graph update embedded in the model to be evaluated is realized.

[0052] Further, the specific process of optimizing the knowledge graph embedding of the preset knowledge graph in combination with the answer accuracy detection result is as follows: S31, when the answer accuracy in the answer accuracy detection result is not greater than the minimum answer accuracy threshold, perform graph community detection and division on the preset knowledge graph to obtain the community density of the graph community; S32, optimize the knowledge graph compression embedding of the preset knowledge graph in combination with the community density of the graph community. The knowledge graph compression embedding optimization refers to obtaining the graph compression rate through the graph compression strength to perform knowledge graph compression; S33, after performing the knowledge graph compression embedding optimization, perform hierarchical embedding optimization on the knowledge graph. The hierarchical embedding optimization refers to performing hierarchical embedding of the knowledge graph based on the obtained hierarchical embedding priority score, and the hierarchical embedding priority score is used to judge the hierarchical embedding priority during the hierarchical embedding process of the knowledge graph.

[0053] In this embodiment, the preset knowledge graph is partitioned by a community detection algorithm (such as the Louvain algorithm) to detect graph communities, and the community density of the graph community is obtained through Density provided by Gephi. By combining the answer accuracy detection results, the knowledge graph embedding is optimized for the preset knowledge graph, so as to enhance the inference answer accuracy of the large model to be evaluated when the answer accuracy detection result is unqualified for the answer accuracy determination value and the answer accuracy of the model to be evaluated needs to be enhanced.

[0054] Furthermore, the graph compression rate is obtained through the graph compression strength to perform knowledge graph compression. The specific steps are as follows: map based on the deviation degree between the community density of the graph community and the maximum community density threshold in the preset strength allocation mapping set in the preset database to obtain the graph compression strength of the graph community. The preset strength allocation mapping set represents the mapping relationship between the community density and the maximum community density threshold; map the deviation degree between the obtained graph compression strength of the graph community and the compression strength reference value from the preset compression strength mapping set in the preset database to obtain the graph compression rate of the graph community. The preset compression strength mapping set represents the mapping relationship between the graph compression strength and the compression strength reference value; perform knowledge graph compression on the graph community according to the obtained graph compression rate.

[0055] In this embodiment, a preset strength allocation mapping set between the community density and the maximum community density threshold is constructed, and the real-time community density is input into the preset strength allocation mapping set to obtain the corresponding graph compression strength; a preset compression strength mapping set between the graph compression strength and the compression strength reference value is constructed, and the real-time graph compression strength is input into the preset compression strength mapping set to obtain the corresponding graph compression rate; knowledge graph compression of the graph community is performed through a knowledge graph compression algorithm (such as GraphSAGE, Graph Sample and Aggregation); the graph compression rate is obtained through the graph compression strength to perform knowledge graph compression, so as to enhance the inference answer accuracy of the large model to be evaluated during the process of embedding the knowledge graph into the large model to be evaluated through knowledge graph compression optimization.

[0056] Furthermore, based on the obtained hierarchical embedding priority score, hierarchical knowledge graph embedding is performed. The specific steps are as follows: Quantify the information retention degree of the graph community for knowledge graph compression after knowledge graph compression based on the graph community to obtain a graph compression determination value.

[0057] Specifically, based on the graph community, the graph compression data after knowledge graph compression is used to quantify the information retention degree of the knowledge graph compression by the graph community, and a graph compression determination value is obtained. The specific steps are as follows: Obtain the graph compression data after the knowledge graph compression by the graph community; perform parameter interaction processing on the coupling result of the node retention degree and the edge retention degree through the result of the graph density difference degree, and couple the result of the zeroing operation of the information loss degree after weighting with the compression evaluation weight to obtain the graph compression determination value.

[0058] The method for obtaining the graph compression determination value is as follows:

[0059] ;

[0060] In the formula, represents the graph compression determination value, represents the compression retention evaluation weight, represents the compression loss evaluation weight, represents the graph density, represents the reference graph density, represents the node retention degree, represents the edge retention degree, represents the information loss degree.

[0061] It should be added that the graph compression data includes graph density, node retention degree, edge retention degree, and information loss degree; the graph density is obtained through NetworkX in Python; the node retention degree and edge retention degree are obtained through Gephi; the information loss degree is obtained through GraphMatching; the reference graph density is represented by the result of summing and averaging the collected historical graph densities.

[0062] The compression evaluation weight includes the compression retention evaluation weight and the compression loss evaluation weight; the compression retention evaluation weight and the compression loss evaluation weight respectively describe the influence degree of the compression retention situation (i.e., the result of parameter interaction processing on the coupling result of the node retention degree and the edge retention degree by the result of the graph density difference degree) and the information loss degree on the graph compression determination value. For example, the real-time compression retention situation and the information loss degree are input into the mapping set of the preset compression retention situation, information loss degree, and their respective weight factors in the database to obtain the corresponding weights.

[0063] It should be understood that the graph compression determination value represents the quantitative data for evaluating the information retention degree of the knowledge graph compression by the graph community by the graph compression data. Among them, the graph compression determination value includes parameters in multiple aspects. Specifically, as the graph density, node retention degree, and edge retention degree increase, the graph compression determination value increases, and as the information loss degree decreases, the graph compression determination value also increases.

[0064] In addition, the various parameters in the graph compression determination value are related and do not exist independently. This algorithm takes into account the correlation and mutual influence among the parameters and conducts comprehensive analysis through a quantitative method. For example, the graph density is used to reflect the overall distribution of nodes and edges in the knowledge graph. If most nodes and edges are retained during the compression process, it means that the structure of the graph is relatively dense, that is, the graph density increases accordingly. Similarly, if a large number of nodes or edges are deleted during the compression process, it may lead to the sparsification of the graph, that is, the graph density decreases accordingly. At the same time, during the compression process, if a large number of nodes are retained, it is usually necessary to retain the edges between the nodes to maintain the structural integrity of the graph. Therefore, there is a certain mutual influence between the edge retention degree and the node retention degree. When compressing the graph, retaining more nodes may also retain more edges, that is, as the node retention degree increases, the edge retention degree also increases. As the node retention degree and the edge retention degree increase, it indicates that more original nodes and edges are retained during the compression process, usually better able to retain the structural information and connectivity of the graph, thereby reducing information loss, that is, the information loss degree decreases accordingly.

[0065] Map the deviation degree between the obtained graph compression determination value and the graph compression reference value to obtain the compression quality scoring weight from the preset database; weight the graph compression determination value through the obtained compression quality scoring weight, and couple it with the compression ratio scoring weight obtained from the preset database to weight the graph compression ratio to obtain the hierarchical embedding priority score.

[0066] The method for obtaining the hierarchical embedding priority score is as follows:

[0067] ;

[0068] In the formula, represents the hierarchical embedding priority score, represents the compression quality scoring weight, represents the compression ratio scoring weight, represents the graph compression determination value, represents the graph compression ratio.

[0069] Sort the hierarchical embedding priority scores of the graph community in descending order to obtain the hierarchical embedding priority level, and perform hierarchical embedding of the knowledge graph according to the hierarchical embedding priority level.

[0070] Among them, the maximum value of the collected historical graph compression determination values represents the graph compression reference value. Construct a mapping set between the graph compression determination value and the graph compression reference value, and input the real-time graph compression determination value into the mapping set to obtain the corresponding compression quality scoring weight; the compression ratio scoring weight is used to describe the influence degree of the graph compression ratio on the hierarchical embedding priority score. For example, input the real-time graph compression ratio into the mapping set of the preset graph compression ratio and its corresponding weight factor in the database to obtain the corresponding weight.

[0071] Hierarchical embedding prioritization obtained by combining hierarchical embedding prioritization of the graph community is used for hierarchical embedding of the knowledge graph, which improves the reliability of hierarchical embedding in the process of embedding the knowledge graph into the large model to be evaluated, and further enhances the accuracy of reasoning answers of the large model by improving the embedding quality of the knowledge graph.

[0072] As Figure 2 shown, it is a schematic structural diagram of a large model answer accuracy enhancement system based on a knowledge graph provided by an embodiment of the present application. The large model answer accuracy enhancement system based on the knowledge graph provided by the embodiment of the present application includes: an answer accuracy judgment module, a graph update adjustment module, and a graph embedding optimization module; the answer accuracy judgment module is used to evaluate and judge the answer accuracy of the model to be evaluated after embedding the preset knowledge graph, and obtain the answer accuracy detection result; the graph update adjustment module is used to judge whether to adjust the initial update speed of the preset knowledge graph in combination with the answer accuracy detection result. If the initial update speed of the preset knowledge graph is adjusted, the optimized update speed of the preset knowledge graph is obtained based on the answer accuracy detection result and the initial update speed of the preset knowledge graph. The initial update speed adjustment means optimizing the initial update speed of the preset knowledge graph based on the answer accuracy detection result to improve the answer accuracy of the model to be evaluated; the graph embedding optimization module is used to, if the initial update speed of the preset knowledge graph is not adjusted, perform knowledge graph embedding optimization on the preset knowledge graph in combination with the answer accuracy detection result. The knowledge graph embedding optimization is used to improve the embedding quality of the preset knowledge graph embedded into the model to be evaluated to enhance the answer accuracy of the model to be evaluated.

[0073] In summary, the embodiment of the present application evaluates and judges the answer accuracy of the model to be evaluated after embedding the preset knowledge graph to obtain the answer accuracy detection result, and then judges whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, the optimized update speed of the preset knowledge graph is obtained. Otherwise, the knowledge graph embedding optimization is performed on the preset knowledge graph in combination with the answer accuracy detection result, thereby improving the embedding quality of the knowledge graph embedded into the large model, and further enhancing the accuracy of reasoning answers of the knowledge graph embedded into the large model, effectively solving the problem of low accuracy of reasoning answers when the knowledge graph is embedded into the large model in the prior art.

[0074] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0075] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0076] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0078] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0079] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and its equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for enhancing the answer accuracy of large models based on knowledge graphs, characterized in that It includes the following steps: Step 1: Evaluate and judge the answer accuracy of the model to be evaluated after embedding the preset knowledge graph, and obtain the answer accuracy detection result; Obtain the quantitative data of the embedding quality after the preset knowledge graph is embedded into the model to be evaluated. The quantitative data of the embedding quality includes the embedding vector similarity, the embedding global clustering coefficient, the embedding space density, and the embedding reconstruction error; Perform parameter interaction processing on the difference degree of the embedding global clustering coefficient and the embedding vector similarity, and the difference degree of the embedding space density and the embedding reconstruction error respectively. After weighting the corresponding parameter interaction results through the embedding quality influence weight, the embedding quality influence factor is obtained by coupling; The embedding quality influence weight includes the embedding tightness influence weight and the embedding accuracy influence weight; The embedding quality influence factor is used to describe the influence degree of the embedding quality of the preset knowledge graph embedded into the model to be evaluated on the answer accuracy determination value; Obtain the answer accuracy rate of the model to be evaluated, and perform an embedding quality correlation operation on the answer accuracy rate according to the obtained embedding quality influence factor to obtain the answer accuracy determination value. The answer accuracy determination value is used to quantitatively evaluate the corresponding answer accuracy degree after the preset knowledge graph is embedded into the model to be evaluated; Step 2: Combine the answer accuracy detection result to judge whether to adjust the initial update speed of the preset knowledge graph. If the initial update speed of the preset knowledge graph is adjusted, then based on the answer accuracy detection result and the initial update speed of the preset knowledge graph, obtain the optimized update speed of the preset knowledge graph. The initial update speed adjustment means optimizing the initial update speed of the preset knowledge graph based on the answer accuracy detection result to improve the answer accuracy of the model to be evaluated; Step 3: If the initial update speed of the preset knowledge graph is not adjusted, then combine the answer accuracy detection result to optimize the knowledge graph embedding of the preset knowledge graph. The knowledge graph embedding optimization is used to improve the embedding quality of the preset knowledge graph embedded into the model to be evaluated to enhance the answer accuracy of the model to be evaluated.

2. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 1, wherein, The specific steps for evaluating and judging the answer accuracy of the model to be evaluated after embedding the preset knowledge graph are as follows: The embedding quality influence factor represents the quantitative data of the combined influence degree of the quantitative data of the embedding quality on the embedding quality of the preset knowledge graph embedded into the model to be evaluated on the answer accuracy determination value; The answer accuracy determination value represents the quantitative data of the combined influence of the embedding quality influence factor and the answer accuracy rate on the corresponding answer accuracy after the preset knowledge graph is embedded into the model to be evaluated.

3. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 2, wherein, The specific steps for obtaining the answer accuracy detection result are as follows: Compare and judge by combining the obtained answer accuracy determination value with the minimum answer accuracy threshold obtained from the preset database; If the answer accuracy determination value is greater than the minimum answer accuracy threshold, record the answer accuracy detection result as the answer accuracy determination value being qualified and the answer accuracy of the model to be evaluated to be monitored; If the answer accuracy is not greater than the minimum answer accuracy threshold, record the answer accuracy detection result as the answer accuracy determination value being unqualified and the answer accuracy of the model to be evaluated to be enhanced.

4. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 3, wherein Based on the combined answer accuracy detection result, it is determined whether to adjust the initial update speed of the preset knowledge graph. The specific process is as follows: If the answer accuracy detection result shows that the answer accuracy determination value is qualified and the answer accuracy of the model to be evaluated is to be monitored, then the initial update speed of the preset knowledge graph is adjusted; Otherwise, the initial update speed of the preset knowledge graph is not adjusted.

5. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 4, wherein The specific steps for adjusting the initial update speed of the preset knowledge graph are as follows: Based on the deviation degree between the answer accuracy determination value in the answer accuracy detection result and the maximum answer accuracy threshold, a mapping is performed from the preset accurate deviation mapping set in the preset database to obtain a graph speed update coefficient. The preset accurate deviation mapping set represents the mapping relationship between the answer accuracy determination value and the maximum answer accuracy threshold; Obtain the initial update speed of the preset knowledge graph and the graph speed update coefficient, and use the graph speed update coefficient to adjust the initial update speed to obtain an optimized update speed.

6. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 3, characterized in that, The specific process of optimizing the knowledge graph embedding of the preset knowledge graph by combining the answer accuracy detection result is as follows: S31. When the answer accuracy in the answer accuracy detection result is not greater than the minimum answer accuracy threshold, perform graph community detection and division on the preset knowledge graph to obtain the community density of the graph community; S32. Combine the community density of the graph community to perform knowledge graph compression embedding optimization on the preset knowledge graph. The knowledge graph compression embedding optimization refers to obtaining a graph compression rate through the graph compression strength to perform knowledge graph compression; S33. After performing the knowledge graph compression embedding optimization, perform hierarchical embedding optimization on the knowledge graph. The hierarchical embedding optimization refers to performing hierarchical embedding of the knowledge graph based on the obtained hierarchical embedding priority score, and the hierarchical embedding priority score is used to judge the hierarchical embedding priority during the hierarchical embedding process of the knowledge graph.

7. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 6, characterized in that, The specific steps for obtaining a graph compression rate through the graph compression strength to perform knowledge graph compression are as follows: Based on the deviation degree between the community density of the graph community and the maximum community density threshold, a mapping is performed from the preset strength allocation mapping set in the preset database to obtain the graph compression strength of the graph community. The preset strength allocation mapping set represents the mapping relationship between the community density and the maximum community density threshold; Based on the deviation degree between the obtained graph compression strength of the graph community and the compression strength reference value, a mapping is performed from the preset compression strength mapping set in the preset database to obtain the graph compression rate of the graph community. The preset compression strength mapping set represents the mapping relationship between the graph compression strength and the compression strength reference value; Perform knowledge graph compression on the graph community according to the obtained graph compression rate.

8. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 6, wherein, The specific steps for performing hierarchical embedding of the knowledge graph based on the obtained hierarchical embedding priority score are as follows: Quantify the information retention degree of the graph compression of the graph community after the knowledge graph compression based on the graph community to obtain a graph compression determination value; Based on the deviation degree between the obtained graph compression determination value and the graph compression reference value, map from the preset database to obtain a compression quality scoring weight; The graph compression determination value is weighted by the obtained compression quality scoring weight, and is coupled with the compression ratio scoring weight obtained from the preset database to weight the graph compression ratio, and then hierarchically embedded priority scoring is obtained through coupling; Combined with the hierarchical embedding priority scoring of the graph community, a hierarchical embedding priority is obtained through descending sorting, and the knowledge graph is hierarchically embedded according to the hierarchical embedding priority.

9. The method for enhancing the answer accuracy of the large model based on the knowledge graph according to claim 8, wherein, The graph compression data after knowledge graph compression based on the graph community quantifies the information retention degree of the knowledge graph compression by the graph community, and obtains a graph compression determination value. The specific steps are as follows: Obtain the graph compression data after knowledge graph compression by the graph community. The graph compression data includes graph density, node retention degree, edge retention degree, and information loss degree; Perform parameter interaction processing on the coupling result of the node retention degree and the edge retention degree through the result of the graph density difference degree, and couple with the weighted result of the zeroing operation of the information loss degree by combining the compression evaluation weight to obtain the graph compression determination value; The compression evaluation weight includes a compression retention evaluation weight and a compression loss evaluation weight; The graph compression determination value represents the quantitative data for jointly evaluating the information retention degree of the knowledge graph compression by the graph compression data for the graph community.

10. A system for applying the method for enhancing the answer accuracy of a large model based on a knowledge graph according to any one of claims 1-9, characterized in that, Including: An answer accuracy judgment module, a graph update adjustment module, and a graph embedding optimization module; The answer accuracy judgment module is used to evaluate and judge the answer accuracy of the model to be evaluated after being embedded in the preset knowledge graph, and obtain the answer accuracy detection result; The graph update adjustment module is used to judge whether to adjust the initial update speed of the preset knowledge graph in combination with the answer accuracy detection result. If the initial update speed of the preset knowledge graph is adjusted, the optimized update speed of the preset knowledge graph is obtained based on the answer accuracy detection result and the initial update speed of the preset knowledge graph. The initial update speed adjustment means optimizing the initial update speed of the preset knowledge graph based on the answer accuracy detection result to improve the answer accuracy of the model to be evaluated; The graph embedding optimization module is used to perform knowledge graph embedding optimization on the preset knowledge graph in combination with the answer accuracy detection result if the initial update speed of the preset knowledge graph is not adjusted. The knowledge graph embedding optimization is used to improve the embedding quality of the preset knowledge graph embedded in the model to be evaluated to enhance the answer accuracy of the model to be evaluated.

Images