Electrical fire information analysis and statistics method and system based on knowledge graph

Abstract

The invention relates to the technical field of electrical fire information analysis and statistics scheme design, in particular to an electrical fire information analysis and statistics method and system based on a knowledge graph. According to the method, through the knowledge credibility evaluation model and the optimization algorithm, the accuracy of knowledge fusion is effectively improved, so that the constructed knowledge graph is more accurate and complete, and electrical fire information analysis and statistics work can be better supported. The introduction of the intelligent inference engine can deeply excavate the potential causal relationship and influence factors of the electrical fire, generates detailed and accurate analysis and statistics results, and provides more comprehensive information support for users. The establishment of a dynamic updating mechanism ensures that the knowledge graph can reflect new electrical fire information and knowledge in real time, the timeliness and effectiveness of the information are always kept, and the practicability and reliability of electrical fire information analysis and statistics are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical fire information analysis and statistical scheme design, and in particular to an electrical fire information analysis and statistical method and system based on a knowledge graph. Background Art

[0002] In the existing technology, since the knowledge related to electrical fires comes from a wide range of sources, including equipment manuals, accident reports, industry standards, etc., when integrating these multi-source heterogeneous knowledge into the knowledge graph, the existing technology is difficult to accurately identify and eliminate conflicts and redundant information, resulting in the accuracy and completeness of the knowledge graph being affected. When faced with complex electrical fire scenarios, the existing solutions have limited reasoning capabilities based on knowledge graphs, and are unable to deeply explore potential electrical fire causal relationships and influencing factors, making it difficult to provide accurate and comprehensive analysis and statistical results. In addition, due to the continuous updating of electrical field technologies and standards, electrical fire cases are also continuing to occur and change. Most of the existing knowledge graph construction solutions lack a dynamic update mechanism for the knowledge graph, and are unable to promptly reflect emerging electrical fire information and knowledge, thus affecting the effectiveness and timeliness of information analysis and statistics.

[0003] Therefore, the prior art needs to be further developed. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a method and system for analyzing and statistically analyzing electrical fire information based on knowledge graphs to solve the problems existing in the prior art.

[0005] To achieve the above technical objectives, according to a first aspect of the present invention, the present invention provides a method for analyzing and statistically analyzing electrical fire information based on a knowledge graph, the method comprising: S100, Data collection and preprocessing: Collect multi-source heterogeneous data related to electrical fires, including equipment manuals, accident reports, and industry standards; clean, remove duplicates, and normalize the collected data to obtain a standardized data set; S200, Knowledge Extraction: Using natural language processing technology and machine learning algorithms, extract entities, attributes and relationships related to electrical fires from standardized data sets to build a preliminary knowledge graph; S300, knowledge fusion evaluation: introduce the knowledge credibility evaluation model, conduct credibility evaluation on the knowledge in the preliminary knowledge graph, and calculate the credibility score of each piece of knowledge; integrate and optimize the conflicting and redundant knowledge according to the credibility score, and generate an optimized knowledge graph; S400, intelligent reasoning engine construction: Build an intelligent reasoning engine, which includes a reasoning algorithm and a rule base; use the intelligent reasoning engine to perform deep reasoning on the optimized knowledge graph, explore the potential causal relationships and influencing factors of electrical fires, and generate analytical statistical results; S500. Dynamic update mechanism establishment: set up a real-time monitoring module to monitor the changes in knowledge sources and the generation of new electrical fire cases in real time; when it is monitored that the knowledge source is updated or a new case appears, use the knowledge update algorithm to integrate the new knowledge and cases into the knowledge graph to achieve dynamic update of the knowledge graph.

[0006] Specifically, in the data collection and preprocessing steps, for the collected multi-source heterogeneous data of electrical fires, a regular expression-based cleaning algorithm is used to remove noise information, a hash algorithm is used to deduplicate data, and the data is normalized according to standard terminology and format in the electrical field. The standardized data set is classified and stored according to different application scenarios related to electrical fires.

[0007] Specifically, in the knowledge extraction step, for the extraction of entities related to electrical fires, a conditional random field algorithm is used in combination with an electrical field knowledge dictionary for identification, and for attribute extraction, a support vector machine algorithm is used to perform attribute value classification extraction based on large-scale training data, and a relationship classification model based on deep learning is used for relationship extraction. The models of the natural language processing technology and machine learning algorithm are pre-trained with labeled data in the field of electrical fires before extraction to improve the accuracy of extraction.

[0008] Specifically, in the knowledge fusion evaluation step, the knowledge credibility evaluation model calculates the credibility score of each piece of knowledge by comprehensively considering the source credibility of the knowledge, the consistency with the existing knowledge, and the frequency of citation. For knowledge whose credibility score is at a critical value, a manual assisted review mechanism is introduced to further screen and evaluate the knowledge.

[0009] Specifically, in the step of building the intelligent reasoning engine, the reasoning algorithms of the intelligent reasoning engine include rule-based reasoning algorithms, Bayesian reasoning algorithms and graph-based reasoning algorithms. The rules in the rule base are stored according to the causes of electrical fires, including electrical equipment failure rules, environmental factor rules and human operation rules. The reasoning process is carried out in the form of multiple rounds of iterations and deep search.

[0010] Specifically, in the step of building an intelligent reasoning engine, the reasoning engine uses the reasoning results to automatically annotate and supplement the knowledge graph, and automatically generates corresponding entities, attributes and relationships for the newly discovered potential causal relationships and influencing factors of electrical fires and adds them to the knowledge graph.

[0011] Specifically, in the step of establishing the dynamic update mechanism, the real-time monitoring module determines whether the knowledge source has changed by monitoring the changes in the web page structure of the knowledge source and identifying the changes in the data version. For the generation of new electrical fire cases, information collection is triggered by monitoring the new records in the electrical fire database. The collected new knowledge enters the knowledge update process after preliminary screening and format conversion.

[0012] Specifically, in the knowledge updating step, the knowledge updating algorithm includes an updating method based on incremental learning and an updating method based on fusion reconstruction. When the sum of the amount of newly added knowledge and the amount of electrical fire cases is less than a first preset threshold, the incremental learning method is used to quickly update the knowledge graph; when the sum of the amount of newly added knowledge and the amount of electrical fire cases is greater than or equal to the first preset threshold, the fusion reconstruction method is used to comprehensively update the knowledge graph.

[0013] Specifically, in the step of generating analysis and statistical results, the generated analysis and statistical results are displayed in grades according to the electrical fire risk levels, and the potential cause-effect relationships and influencing factors of electrical fires are presented in a graphical manner through visualization tools. The graphical display includes node diagrams, flow charts and cause-effect diagrams.

[0014] According to a second aspect of the present invention, there is provided an electrical fire information analysis and statistics system based on a knowledge graph, comprising: Data processing module: used to perform data collection and preprocessing steps, clean, remove duplicates and normalize multi-source heterogeneous data of electrical fires to generate standardized data sets; Knowledge extraction module: uses natural language processing technology and machine learning algorithms to extract entities, attributes and relationships related to electrical fires from standardized data sets and construct a preliminary knowledge graph; Knowledge fusion and optimization module: Use the knowledge credibility evaluation model to evaluate the credibility of the knowledge in the preliminary knowledge graph, integrate and optimize the conflicting and redundant knowledge, and generate an optimized knowledge graph; Reasoning and analysis module: build an intelligent reasoning engine, perform deep reasoning on the optimized knowledge graph, explore the potential causal relationships and influencing factors of electrical fires, and generate analytical statistical results; Dynamic update module: Set up a real-time monitoring module to monitor the changes in knowledge sources and the generation of new electrical fire cases in real time, and realize the dynamic update of the knowledge graph through the knowledge update algorithm.

[0015] Beneficial effects: The present invention effectively improves the accuracy of knowledge fusion through the knowledge credibility evaluation model and optimization algorithm, making the constructed knowledge graph more accurate and complete, and better supporting the analysis and statistics of electrical fire information. The introduction of the intelligent reasoning engine can deeply explore the potential causal relationships and influencing factors of electrical fires, generate detailed and accurate analysis and statistical results, and provide users with more comprehensive information support. The establishment of a dynamic update mechanism ensures that the knowledge graph can reflect the emerging electrical fire information and knowledge in real time, always maintain the timeliness and effectiveness of the information, and greatly improve the practicality and reliability of electrical fire information analysis and statistics. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of an electrical fire information analysis and statistical method based on a knowledge graph provided in a specific embodiment of the present invention; Figure 2 It is a schematic diagram of the system composition of the knowledge graph-based electrical fire information analysis and statistics system provided in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by ordinary technicians in this field without making creative work should all fall within the scope of protection of this application. In addition, the directional words mentioned in the following embodiments, such as "up", "down", "left", "right", etc., are only reference to the directions of the accompanying drawings. Therefore, the directional words used are used to illustrate rather than limit the invention.

[0018] The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.

[0019] See also Figure 1 The present invention provides a method for analyzing and statistically analyzing electrical fire information based on a knowledge graph, comprising: S100, data collection and preprocessing: Collect multi-source heterogeneous data related to electrical fires, including equipment manuals, accident reports, and industry standards; clean, deduplicate, and normalize the collected data to obtain a standardized data set.

[0020] It should be noted that the steps before step S100 include: A first preset threshold is preset in the dynamic update module.

[0021] It can be understood that the first preset threshold can be set by the inventors according to needs, and the present invention does not impose any specific limitation on the value of the first preset threshold, as long as it is applicable to the electrical fire information analysis and statistical method based on knowledge graph proposed in the present invention.

[0022] Preferably, the present invention sets the first preset threshold to 100. The above setting is obtained by those skilled in the art through a large number of tests, which further improves the reliability of the knowledge dynamic update scheme of the present invention.

[0023] It is understandable that “the first preset threshold is preferably 100” is obtained through a large number of tests, and the specific basis and acquisition method are as follows: 1. Test data foundation During the development process, a large amount of electrical fire-related data was collected, and multiple experiments were conducted for different application scenarios and processing requirements. These experiments covered various types of data processing tasks, including but not limited to data cleaning, deduplication, fusion, etc., to comprehensively evaluate the impact of different thresholds on system performance and result accuracy.

[0024] 2. Performance Index Evaluation In each experiment, multiple different thresholds were set, and a series of performance indicators were evaluated for each threshold. These performance indicators include but are not limited to the accuracy, completeness, update efficiency of the knowledge graph, and the reliability of the analysis and statistical results. By analyzing and comparing a large amount of experimental data, the changing trends of various performance indicators under different thresholds are observed.

[0025] 3. Determine the optimal threshold After comprehensive analysis of the experimental results, it was found that when the threshold was set to 100, the system showed a good balance in multiple performance indicators. For example, in terms of the accuracy of the knowledge graph, it can effectively identify and handle most knowledge conflicts and redundancy problems while maintaining a high knowledge fusion efficiency; in terms of the reliability of the statistical results, it can provide stable and accurate data support for subsequent reasoning and analysis. Therefore, considering all factors, it is determined that the first preset threshold is preferably 100.

[0026] In summary, the technical solution of the present application has clear basis and detailed implementation method in the calculation steps of the knowledge credibility evaluation model and the determination of the first preset threshold, and there is no problem of insufficient disclosure.

[0027] Specifically, in the data collection and preprocessing steps, for the collected multi-source heterogeneous data of electrical fires, a regular expression-based cleaning algorithm is used to remove noise information, a hash algorithm is used to deduplicate data, and the data is normalized according to standard terminology and format in the electrical field. The standardized data set is classified and stored according to different application scenarios related to electrical fires.

[0028] Specifically, in the data collection and preprocessing step, the collected multi-source heterogeneous data of electrical fires are preprocessed in the following manner: Data cleaning: The regular expression-based cleaning algorithm specifically designs regular expression templates for the characteristics of electrical data. For example, for specific character combinations that may be contained in electrical equipment models (such as specific arrangements of letters and numbers), regular expression matching and replacement operations are used to remove noise information such as comments, extra spaces, and line breaks in the data. At the same time, non-standard characters (such as garbled characters, special symbols, etc.) generated in the data due to collection or input errors are also identified and corrected through corresponding regular expression rules.

[0029] Data deduplication: Use hash algorithm to perform data deduplication. For each piece of electrical fire related data, calculate its hash value and use the hash value as the unique identifier of the data. When storing data, first check whether there is data with the same hash value in the database. If there is, it is considered as duplicate data and deleted.

[0030] Data normalization: Normalize the data according to standard terminology and formats in the electrical field. For aspects such as electrical equipment names, fault types, and technical parameters, refer to the glossary and format specifications established by relevant international and domestic standards (such as IEEE standards, national standards, etc.) for conversion. For example, the different names for the same type of electrical equipment by different equipment manufacturers are unified into standard terms, and the recording format of the fault occurrence time is unified into a specific date and time format (such as "YYYY-MM-DDHH:MM:SS"). Standardized data sets are classified and stored according to different application scenarios related to electrical fires (such as electrical fires in industrial plants, electrical fires in residential areas, etc.), and independent data tables are established in the database for each application scenario to facilitate subsequent data processing and analysis.

[0031] Furthermore, in a preferred embodiment, when analyzing and counting electrical fire information, the first problem faced is the processing of multi-source heterogeneous data. This embodiment collects electrical fire related data from multiple sources, including but not limited to detailed equipment manuals provided by various electrical equipment manufacturers, accident reports compiled and recorded by fire departments, and professional industry standard documents issued by electrical industry associations.

[0032] For the collected data, we start comprehensive data cleaning. Take a common wire and cable product manual as an example. There may be some annotations, such as "This model of wire and cable is an experimental product and is not recommended for use under extreme conditions." Through the pre-designed regular expression template, we can accurately identify and remove such descriptive and annotation content, making the data purer.

[0033] In the data deduplication process, a hash algorithm is used to calculate the hash value of each piece of data. Suppose there are two technical parameter documents about a certain brand of small circuit breakers collected from different channels. Although the descriptions are slightly different, the core information is the same. The hash algorithm will process these two documents separately and generate the same hash value, thus determining that the two documents are duplicate data and only retaining one of them.

[0034] After deduplication is completed, data normalization is performed to unify the form and standard of the data. For example, for the description of the fault type of electrical equipment, different data sources may have multiple expressions such as "short circuit", "short connection", "circuit break", etc. According to the standard terminology and format in the electrical field (such as referring to the terminology definitions of electrical faults in IEEE standards and national standards), they are uniformly converted into the standard term "short circuit". At the same time, the record of the time of occurrence of the fault is standardized in the format of "YYYY-MM-DDHH:MM:SS". The standardized data set is classified and stored according to the application scenario, such as divided into different data sets such as industrial scenarios and residential life scenarios, to facilitate subsequent management and analysis.

[0035] S200, Knowledge Extraction: Use natural language processing technology and machine learning algorithms to extract entities, attributes and relationships related to electrical fires from standardized data sets and build a preliminary knowledge graph.

[0036] Specifically, in the knowledge extraction step, for the extraction of entities related to electrical fires, a conditional random field algorithm is used in combination with an electrical field knowledge dictionary for identification, and for attribute extraction, a support vector machine algorithm is used to perform attribute value classification extraction based on large-scale training data, and a relationship classification model based on deep learning is used for relationship extraction. The models of the natural language processing technology and machine learning algorithm are pre-trained with labeled data in the field of electrical fires before extraction to improve the accuracy of extraction.

[0037] Specifically, in the knowledge extraction step, the specific algorithms and processes are as follows: Entity extraction: For the extraction of entities related to electrical fires, the conditional random field (CRF) algorithm is combined with the electrical domain knowledge dictionary for identification. First, the electrical domain knowledge dictionary is constructed and preprocessed, and converted into a feature vector form that can be recognized by the CRF algorithm. The knowledge dictionary contains common electrical equipment names, fault types, electrical parameters and other words, and each word is assigned a specific label (such as "electrical equipment", "fault type", "electrical parameters", etc.). Then, the CRF algorithm is used to extract features from the input text data, such as part of speech, contextual information, etc., and combined with the feature vector of the knowledge dictionary for training, finally identifying the electrical fire related entities in the text.

[0038] Attribute extraction: Attribute extraction uses the support vector machine (SVM) algorithm to classify and extract attribute values ​​based on large-scale training data. First, prepare large-scale labeled data to annotate the attributes and attribute values ​​corresponding to each entity. For example, for the "wire and cable" entity, annotate its "conductivity" and "voltage rating" and other attributes and their corresponding attribute values. Then, use these labeled data to train the SVM classification model. The model can classify and extract the attributes of entities in new texts by learning the characteristic patterns of different attribute values.

[0039] Relationship extraction: Relationship extraction uses a relationship classification model based on deep learning, such as using a recurrent neural network (RNN) or its variant, the long short-term memory network (LSTM), to build a relationship judgment model. During the model training process, a text fragment containing entity pairs is input, and the relationship type between entities is judged by learning the contextual semantic information of the entities. At the same time, in order to avoid overfitting, an attention mechanism is introduced so that the model can pay more attention to key information related to relationship judgment. The models of the natural language processing technology and machine learning algorithm are pre-trained with labeled data in the field of electrical fires before extraction. During the pre-training process, the hyperparameters of the model are optimized by cross-validation and other methods to improve the accuracy of extraction.

[0040] Furthermore, in a preferred embodiment, knowledge extraction is a key step in constructing an accurate knowledge graph. In the entity extraction process, for text data related to electrical fires, a combination of a conditional random field (CRF) algorithm and an electrical field knowledge dictionary is used. First, the knowledge dictionary is preprocessed, and common electrical equipment names (such as transformers, distribution boxes, etc.), fault types (overcurrent faults, leakage faults, etc.), electrical parameters (rated power, insulation resistance, etc.) and other vocabulary are entered, and corresponding labels are marked for each vocabulary. When processing a descriptive text about an electrical fire accident, "A transformer in a factory caused a short circuit fire due to an overcurrent fault," the CRF algorithm will accurately identify entities such as "transformer," "overcurrent fault," and "short circuit" based on the feature vectors of the knowledge dictionary and the semantic features in the text, and mark them with corresponding labels.

[0041] Attribute extraction is done with the help of the support vector machine (SVM) algorithm. Prepare a large amount of data with labeled attributes and attribute values ​​as training samples. For example, for the "wire and cable" entity, there are samples with attributes and values ​​labeled with "conductivity is 40% IACS" and "voltage rating is 1000V". The SVM algorithm forms a classification model by learning the characteristic patterns of these samples. When faced with new text data, the model can classify and extract the attributes of the "wire and cable" entity.

[0042] Relation extraction relies on a relation classification model built using a deep learning-based recurrent neural network (RNN) and its variant, the long short-term memory network (LSTM). During the training process, a text segment containing entity pairs is input, such as "aging of electrical switches and electrical lines, which in turn cause electrical fires". The model learns contextual semantic information and determines that there is a causal relationship between "electrical switches", "aging of electrical lines" and "electrical fires". At the same time, the attention mechanism enables the model to focus on key information closely related to relationship judgment, such as the specific vocabulary "which in turn causes" in the text that describes the causal relationship, so as to extract relationships more accurately.

[0043] S300, knowledge fusion evaluation: Introduce a knowledge credibility evaluation model, conduct credibility evaluation on the knowledge in the preliminary knowledge graph, and calculate the credibility score of each piece of knowledge; fuse and optimize conflicting and redundant knowledge based on the credibility score to generate an optimized knowledge graph.

[0044] Specifically, in the knowledge fusion evaluation step, the knowledge credibility evaluation model calculates the credibility score of each piece of knowledge by comprehensively considering the source credibility of the knowledge, the consistency with the existing knowledge, and the frequency of citation. For knowledge whose credibility score is at a critical value, a manual assisted review mechanism is introduced to further screen and evaluate the knowledge.

[0045] Specifically, in the knowledge fusion evaluation step, the construction and calculation process of the knowledge credibility evaluation model is as follows: Credibility score calculation: The knowledge credibility assessment model calculates the credibility score of each piece of knowledge based on multiple dimensions, such as the credibility of the source of the knowledge, the consistency with existing knowledge, and the frequency of citation. In terms of source credibility, different weights are assigned according to the source of knowledge (such as standards issued by authoritative organizations, works by well-known experts in professional fields, and strictly reviewed industry reports). For example, information released by authoritative organizations has a higher weight, while information in personal blogs has a relatively lower weight. In terms of consistency with existing knowledge, semantic similarity is calculated by comparing new knowledge with related knowledge already in the knowledge graph. Word vector models (such as Word2Vec, BERT, etc.) can be used to convert knowledge into vector representations, and then the similarity between vectors is calculated. In terms of citation frequency, the number of citations of knowledge in relevant academic literature, industry reports, etc. is counted, and the number of citations is used as an evaluation indicator. The credibility score of each piece of knowledge is calculated by weighted combination of the scores of these indicators.

[0046] Human-assisted review mechanism: For knowledge with a critical credibility score, a human-assisted review mechanism is introduced to further screen and evaluate the knowledge. An audit team consisting of electrical experts and professional information processing personnel is formed to assign suspicious knowledge to them. Experts judge the credibility of knowledge based on their domain expertise, while information processing personnel provide support from the perspective of data processing and text analysis. The audit team conducts in-depth analysis of the background information and relevant context involved in the suspicious knowledge, and ultimately determines the credibility score of the knowledge.

[0047] Furthermore, in a preferred embodiment, the knowledge fusion evaluation link is intended to ensure the accuracy and consistency of the knowledge in the knowledge graph. For each piece of knowledge, the credibility evaluation model calculates the credibility score from multiple dimensions.

[0048] Take the knowledge that "new smart meters may lose data in complex electromagnetic environments, thereby increasing the risk of electrical fires" as an example. First, evaluate the credibility of its source. If the knowledge comes from a professional and authoritative electrical research institution, the credibility score will be higher; if it comes from a personal blog and is not verified, the credibility score will be lower.

[0049] In terms of consistency with existing knowledge, the new knowledge is compared with similar knowledge already in the knowledge graph. For example, if there is already relevant knowledge in the knowledge graph that "smart meters have high data stability within the normal working range, and only when subjected to extremely strong electromagnetic interference may short-term data anomalies occur", the difference between the new knowledge and the existing knowledge needs to be further analyzed. If the "complex electromagnetic environment" in the new knowledge is clearly defined and clearly different from extremely strong electromagnetic interference, the similarity between the two needs to be re-evaluated; if the difference is large, it needs to be handled with caution.

[0050] Citation frequency is also an important indicator. Count the number of times the knowledge is cited in relevant professional academic literature and industry reports. If the knowledge is frequently cited in multiple authoritative documents, it means that its credibility is high.

[0051] When the credibility score is critical, a manual review mechanism is introduced. A team of electrical experts, combined with their own professional knowledge, judges the new knowledge from the perspectives of electrical principles and industry standards. At the same time, information processing personnel provide support from aspects such as data processing rules and text processing logic to ultimately determine the credibility score of the knowledge.

[0052] It should be noted here that the specific calculation steps and optimization algorithm of the knowledge credibility evaluation model are as follows: The knowledge credibility evaluation model calculates the credibility score of each piece of knowledge based on multiple dimensions, such as the credibility of the source of knowledge, consistency with existing knowledge, and frequency of citation. The specific calculation steps are as follows: 1. Source credibility calculation Determine the categories and weights of knowledge sources: According to the authority and reliability of the knowledge sources, the knowledge sources are divided into different categories, such as standards issued by authoritative organizations, works by well-known experts in professional fields, and strictly reviewed industry reports, and different weights are assigned to each category. For example, the weight of information released by authoritative organizations is set to W. 1 (higher value), the information weight in personal blog is set to W 2 (lower value).

[0053] In a preferred embodiment, the knowledge source categories and weights are defined: the knowledge sources are divided into different categories, such as standards issued by authoritative organizations (weights are set to W 权威 =0.6), works by well-known experts in the professional field (weighted as W 专家 =0.4). The weight is set based on a comprehensive assessment of the reliability of various knowledge sources and can be determined through expert discussions, industry research, etc.

[0054] Evaluate the credibility score of knowledge sources: For each piece of knowledge, determine the category to which its knowledge source belongs, and calculate the source credibility score S1 according to the weight corresponding to the category. The calculation formula is: S1=W 类别 , where W 类别 is the weight corresponding to the knowledge source category.

[0055] 2. Calculation of consistency with existing knowledge Convert new knowledge and existing knowledge into vector representation: Use word vector models (such as Word2Vec, BERT, etc.) to convert new knowledge and existing related knowledge in the knowledge graph into vector representation. Assume that the vector representation of new knowledge is , the vector of existing relevant knowledge is expressed as .

[0056] Calculate semantic similarity: measure the consistency between new knowledge and existing knowledge by calculating the similarity between vectors. Similarity calculation methods include cosine similarity, etc. The calculation formula is: S2=( * ) / ( * ), S2 represents the semantic similarity score.

[0057] 3. Citation frequency calculation Number of citations of statistical knowledge: Collect relevant academic literature, industry reports and other information sources, and the number of citations N of statistical knowledge in these sources.

[0058] Normalized citation counts: To make the citation frequencies comparable in data of different scales, the citation counts are normalized. For example, a maximum citation count Nmax is set (which can be determined based on actual conditions), and the calculation formula for the citation frequency score S3 is: S3=N / Nmax.

[0059] 4. Comprehensive calculation of credibility score Determine the weight of each dimension: Assign weights W to the three dimensions of source credibility, consistency with existing knowledge, and frequency of citation. 1 , W 2 and W 3 , and satisfy W 1 +W 2 +W 3 = 1. The weight can be determined through expert experience, experimental verification, etc.

[0060] Calculate the credibility score: Combine the scores of the above three dimensions according to the weights to obtain the credibility score S of each piece of knowledge. The calculation formula is: S=W 1 ×S1+W 2 ×S2+W 3 ×S3.

[0061] It can be understood that the implementation steps of the specific optimization algorithm for integrating and optimizing conflicting and redundant knowledge according to the credibility score and generating an optimized knowledge graph include: 1. Rule-based optimization algorithm Rule definition: A series of electrical fire reasoning rules are predefined, which formally describe the various conditions and logical relationships for the occurrence of electrical fires. For example, "If the insulation layer of the wire or cable is damaged and the current carried exceeds its rated current, an electrical fire may occur."

[0062] Rule matching and application: traverse the nodes and edges in the knowledge graph, find situations that meet the rule conditions, and draw conclusions based on reasoning based on the rules. For example, when it is found that the current status node of a large motor node in the knowledge graph shows that it has been running at high load for more than 24 hours, and the insulation layer status node shows that the insulation layer is damaged, it can be inferred based on the above rules that the risk of electrical fire at the location of the motor is increased, and the corresponding annotation is made in the knowledge graph.

[0063] 2. Optimization algorithm based on Bayesian reasoning Data collection and model training: Based on historical data and expert experience in the field of electrical fires, data on various factors (such as electrical equipment failure type, ambient humidity, temperature, etc.) in different electrical fire situations are collected and labeled. The labeled data is used to train the Bayesian network model to learn the probability distribution of the possibility of various electrical fires and related factors.

[0064] Probability calculation and update: During reasoning, the probability of an unknown event is calculated using the Bayesian formula based on known evidence (known information in the knowledge graph). For example, if the current humidity and temperature in a certain area are high, combined with the aging of electrical equipment, the probability of an electrical fire in the area can be calculated using the Bayesian reasoning algorithm, and the results are fed back to the knowledge graph to update the probability information of related nodes.

[0065] 3. Graph-based optimization algorithms Graph structure analysis and path search: Using the graph structure characteristics of the knowledge graph, reasoning is performed through path search and propagation algorithms between nodes. For example, by calculating the shortest path or association path between nodes, potential causal relationships of electrical fires can be discovered.

[0066] Information propagation and update: Define a propagation weight model to propagate reasoning information from one node to adjacent nodes based on the connection relationship between nodes and the attributes of the edges (e.g., the weight of the edge represents the closeness of the relationship). For example, if it is found that there is a close correlation between illegal wiring and electrical fires in many places in an old residential area, the information propagation algorithm can be used to establish a corresponding relationship between the electrical equipment nodes and fault type nodes related to the old residential area in the knowledge graph, and update the knowledge graph.

[0067] Specifically, the optimization algorithm based on Bayesian reasoning is as follows: The basic formula of Bayes' theorem is: P(A|B)=P(B|A)P(A) / P(B); Where: P(A|B) represents the probability of event A occurring under the condition that event B occurs, that is, the posterior probability; P(B|A) represents the probability of event B occurring under the condition that event A occurs; P(A) represents the prior probability of event A occurring; P(B) represents the probability of event B occurring.

[0068] It is understandable that in the electrical fire risk assessment scenario of the present invention, we assume that event A represents "electrical fire occurs", and event Bi represents various factors that affect the occurrence of electrical fire, such as B1 represents "electrical equipment failure", B2 represents "high environmental humidity", B3 represents "high temperature", etc. The specific calculation steps are as follows: 1. Calculate the prior probability P(A) The prior probability P(A) can be obtained based on the statistics of historical electrical fire data. Assuming that among the N pieces of electrical fire-related data collected, the number of electrical fire cases is nA, the calculation formula of the prior probability P(A) is: P(A)=nA / N.

[0069] 2. Calculate the conditional probabilities P(Bi|A) and P(Bi) Calculate P(Bi|A): P(Bi|A) represents the probability of a factor Bi occurring in the event of an electrical fire. By analyzing the cases that satisfy event A in the historical electrical fire data, the number of cases n that also satisfy factor Bi is counted. ABi , then the calculation formula of P(Bi|A) is: P(Bi|A)=n ABi / n A For example, among 100 electrical fire cases, 60 cases involved electrical equipment failures, then P(Bi|A)=60 / 100=0.6.

[0070] Calculate P(Bi): P(Bi) represents the probability of occurrence of factor Bi. By analyzing a large amount of electrical system operation data (including data on fire and non-fire), the number of cases n that meet factor Bi is counted. Bi , the total number of cases is N total , then the calculation formula of P(Bi) is: P(Bi)=n Bi / N total。

[0071] For example, among 1000 pieces of electrical system operation data, 200 pieces of data show electrical equipment failure, then P(Bi)=200 / 1000=0.2.

[0072] 3. Calculate the posterior probability P(A|B1,B2,⋯,Bn) In practical applications, we usually need to calculate the probability of electrical fires based on the simultaneous occurrence of multiple factors, that is, P(A|B1,B2,⋯,Bn). According to the total probability formula of Bayes' theorem and the chain rule, it can be expanded as: P(A∣B1,B2,⋯,Bn)=P(B1,B2,⋯,Bn∣A)P(A) / P(B1,B2,⋯,Bn).

[0073] Assuming that each factor is independent of each other (in practical applications, the correlation between factors can be considered according to specific circumstances), P(B1,B2,⋯,Bn|A) can be approximately expressed as P(B1|A)P(B2|A)⋯P(Bn|A), and P(B1,B2,⋯,Bn) can be approximately expressed as P(B1)P(B2)⋯P(Bn).

[0074] Therefore, the calculation formula of P(A|B1,B2,⋯,Bn) can be simplified to: P(A∣B1,B2,⋯,Bn)=P(B1∣A)P(B2∣A)⋯P(Bn∣A)P(A) / P(B1)P(B2)⋯P(Bn).

[0075] In a preferred embodiment of the present invention, it is assumed that P(A)=0.1 (i.e., the probability of electrical fires occurring historically is 10%), P(B1|A)=0.6 (the probability of electrical equipment failure when an electrical fire occurs is 60%), P(B1)=0.2 (the overall probability of electrical equipment failure is 20%), P(B2|A)=0.7 (the probability of high ambient humidity when an electrical fire occurs is 70%), P(B2)=0.3 (the overall probability of high ambient humidity is 30%), P(B3|A)=0.5 (the probability of high temperature when an electrical fire occurs is 50%), and P(B3)=0.4 (the overall probability of high temperature is 40%).

[0076] Then, when the three factors of electrical equipment failure, high ambient humidity and high temperature occur simultaneously, the probability of electrical fire P(A|B1,B2,B3) is: P(A∣B1,B2,B3)=P(B1∣A)P(B2∣A)P(B3∣A)P(A) / P(B1)P(B2)P(B3)=0.6×0.7×0.5×0.1 / 0.2×0.3×0.4=0.9167. Through the above formula and calculation process, we can dynamically evaluate the risk probability of electrical fires under different conditions based on the known probability information of electrical fire-related factors, thereby providing decision support for the prevention and control of electrical fires. In this technical solution, this probability information can be used to update the attributes of relevant nodes and edges in the knowledge graph to reflect the real-time changes in electrical fire risks.

[0077] Through the above detailed calculation steps, fusion optimization method and implementation steps of specific optimization algorithms, the technical solution of the present application can effectively evaluate the credibility of knowledge, integrate and optimize conflicting and redundant knowledge, and generate an optimized knowledge graph, thereby providing more accurate and comprehensive support for electrical fire information analysis and statistics.

[0078] S400, intelligent reasoning engine construction: Build an intelligent reasoning engine, which includes a reasoning algorithm and a rule base; use the intelligent reasoning engine to perform deep reasoning on the optimized knowledge graph, explore the potential cause-effect relationships and influencing factors of electrical fires, and generate analytical statistical results.

[0079] Specifically, in the step of building the intelligent reasoning engine, the reasoning algorithms of the intelligent reasoning engine include rule-based reasoning algorithms, Bayesian reasoning algorithms and graph-based reasoning algorithms. The rules in the rule base are stored according to the causes of electrical fires, including electrical equipment failure rules, environmental factor rules and human operation rules. The reasoning process is carried out in the form of multiple rounds of iterations and deep search.

[0080] Specifically, in the step of building an intelligent reasoning engine, the reasoning engine uses the reasoning results to automatically annotate and supplement the knowledge graph, and automatically generates corresponding entities, attributes and relationships for the newly discovered potential causal relationships and influencing factors of electrical fires and adds them to the knowledge graph.

[0081] Specifically, in the step of building the intelligent reasoning engine, the specific implementation method and rule base organization method are as follows: Inference algorithm: Rule-based reasoning algorithm: A large number of electrical fire reasoning rules are predefined in the rule base. These rules formally describe the various conditions and logical relationships for the occurrence of electrical fires. For example, "If the insulation layer of the wire and cable is damaged and the current carried exceeds its rated current, an electrical fire may occur." During the reasoning process, the engine traverses the nodes and edges in the knowledge graph, finds situations that meet the rule conditions, and draws conclusions based on the reasoning of the rules.

[0082] Bayesian reasoning algorithm: used to handle reasoning with uncertainty and probabilistic information. Based on historical data and expert experience in the field of electrical fires, the probability distribution of the probability of various electrical fires and related factors is modeled. For example, the probability of electrical fires in different regions and different types of electrical equipment, as well as the impact of various environmental factors (such as humidity, temperature, etc.) on the probability of electrical fires, are counted. When reasoning, the probability of unknown events is calculated using the Bayesian formula based on known evidence (known information in the knowledge graph).

[0083] Graph-based reasoning algorithm: Utilize the graph structure characteristics of the knowledge graph to perform reasoning through path search and propagation algorithms between nodes. For example, by calculating the shortest path or association path between nodes, potential causal relationships of electrical fires can be discovered. A propagation weight model can be defined to propagate reasoning information from one node to adjacent nodes based on the connection relationship between nodes and the attributes of the edges (such as the weight of the edge indicating the closeness of the relationship).

[0084] Rule base organization: The rules in the rule base are stored according to the causes of electrical fires, including electrical equipment failure rules, environmental factor rules, and human operation rules. Each type of rule is further subdivided. For example, electrical equipment failure rules can be divided into short circuit rules, overload rules, insulation failure rules, etc. This classification storage method facilitates the rapid location and application of relevant rules during reasoning.

[0085] Specifically, in the step of building an intelligent reasoning engine, the process of the reasoning engine automatically annotating and supplementing the knowledge graph using the reasoning results is as follows: Automatic labeling: The inference engine automatically labels the potential causal relationships and influencing factors of electrical fires in the knowledge graph. For example, if it is inferred that a certain electrical equipment is prone to failure and fire under certain environmental conditions, then the corresponding labels are added to the corresponding entities (electrical equipment) and relationships (the relationship between failure and environmental conditions) in the knowledge graph to mark its fire risk characteristics in this context.

[0086] Relationship supplement: For the newly discovered potential causal relationships and influencing factors of electrical fires, the corresponding entities, attributes, and relationships are automatically generated and added to the knowledge graph. For example, if reasoning finds that a new electrical connection method may increase the risk of electrical fires, a new "electrical connection method" entity is created in the knowledge graph, and the "fire risk factor" attribute is added to it, and a new relationship is established between the entity and the related electrical equipment and fault type entities. In order to ensure the consistency and integrity of the knowledge graph, consistency checks and verifications are performed when new content is added, such as checking whether the new entities and relationships comply with the logical constraints and semantic rules of the knowledge graph. At the same time, the newly added content is regularly sorted and archived for subsequent maintenance and use.

[0087] Furthermore, in a preferred embodiment, the intelligent reasoning engine includes multiple reasoning algorithms and a rich rule base for deep mining of electrical fire information.

[0088] In terms of rule-based reasoning algorithms, the rule base defines many rules related to electrical fires. For example, "If electrical equipment is in a high-load operating state for a long time (the current exceeds 80% of the rated current and lasts for more than 24 hours), the risk of electrical fire increases significantly." When the reasoning engine analyzes the current state node of a large motor node in the knowledge graph and shows that it has been running at a high load for more than 24 hours, it can be inferred based on this rule that the risk of electrical fire at the location of the motor increases.

[0089] Bayesian reasoning algorithms play an important role in processing uncertain information. Taking the relationship between electrical fire risk and factors such as humidity and temperature as an example, a Bayesian network model is established by collecting humidity and temperature data and the corresponding electrical system status when a large number of electrical fires occurred in history. The model learns that under conditions of high humidity (such as relative humidity greater than 80%) and high temperature (such as ambient temperature above 40°C), combined with the aging of electrical equipment (such as equipment service life of more than 15 years), the probability of electrical fires will increase significantly. When receiving real-time monitoring of humidity and temperature data in a certain area and information such as the service life of local electrical equipment, the Bayesian reasoning algorithm can calculate the possibility of electrical fires in the area.

[0090] Graph-based reasoning algorithms use the graph structure characteristics of knowledge graphs. For example, by searching for paths between nodes and calculating associated paths, it was found that "there is a close correlation between illegal wiring in many places in an old community (with complex wiring connections) and electrical fire cases", and thus it can be inferred that the risk of electrical fires in the community is increased due to illegal wiring.

[0091] During the reasoning process, if new potential causal relationships and influencing factors of electrical fires are obtained through these reasoning algorithms, the engine will use the reasoning results to automatically annotate and supplement the knowledge graph. For example, between the node representing "illegal wiring of wires" in the knowledge graph and the node of the electrical equipment connected to it, the relationship label "increases fire risk" is added, and "illegal wiring of wires" is added to the knowledge graph as a new electrical connection method entity, and it is given relevant attributes and relationships.

[0092] S500. Dynamic update mechanism establishment: set up a real-time monitoring module to monitor the changes in knowledge sources and the generation of new electrical fire cases in real time; when it is monitored that the knowledge source is updated or a new case appears, use the knowledge update algorithm to integrate the new knowledge and cases into the knowledge graph to achieve dynamic update of the knowledge graph.

[0093] Specifically, in the step of establishing the dynamic update mechanism, the real-time monitoring module determines whether the knowledge source has changed by monitoring the changes in the web page structure of the knowledge source and identifying the changes in the data version. For the generation of new electrical fire cases, information collection is triggered by monitoring the new records in the electrical fire database. The collected new knowledge enters the knowledge update process after preliminary screening and format conversion.

[0094] Specifically, in the step of establishing the dynamic update mechanism, the specific implementation method of real-time monitoring and information collection is as follows: Knowledge source web page structure change monitoring: The real-time monitoring module crawls the web pages of knowledge sources (such as electrical industry websites, academic literature databases, etc.) regularly (for example, every certain time interval, such as 1 hour) to obtain the source code of the web pages. The newly crawled web page source code is compared line by line with the previously stored web page source code, and the changes in HTML tag structure, text position, etc. are analyzed to determine whether the web page structure has changed. For the parts with changed structure, new data and information are extracted.

[0095] Data version change identification: For knowledge sources with clear data version identification, such as databases and document libraries, the data version number is parsed to identify whether the data has changed. The real-time monitoring module is connected to the version management system of the knowledge source, obtains the latest version number of each data object (such as documents, records, etc.), and compares it with the version number stored locally. If the version number changes, the latest data content is obtained.

[0096] Monitoring of new electrical fire cases: By establishing an interface connection with an electrical fire database (such as the fire case database of the fire department, the case library of relevant research institutions, etc.), the latest added records can be obtained in real time. In order to improve monitoring efficiency, data acquisition can be carried out in an asynchronous pull or event-driven manner. When a new electrical fire case is detected, the new knowledge collected is initially screened (such as filtering out content that is obviously not in line with the electrical fire theme) and formatted (converting it into a standard format compatible with the knowledge graph) and enters the knowledge update process.

[0097] Specifically, in the knowledge updating step, the knowledge updating algorithm includes an updating method based on incremental learning and an updating method based on fusion reconstruction. When the sum of the amount of newly added knowledge and the amount of electrical fire cases is less than a first preset threshold, the incremental learning method is used to quickly update the knowledge graph; when the sum of the amount of newly added knowledge and the amount of electrical fire cases is greater than or equal to the first preset threshold, the fusion reconstruction method is used to comprehensively update the knowledge graph.

[0098] Specifically, in the knowledge updating step, the knowledge updating algorithm is implemented as follows: Incremental learning method: When the amount of new knowledge and cases is small, the incremental learning method is used to quickly update the knowledge graph. First, feature extraction and representation learning are performed on the new knowledge and cases and the existing data in the knowledge graph to convert them into feature vector form. Then, these new feature vectors are integrated into the model of the existing knowledge graph using predefined learning rules and strategies. For example, for a knowledge graph model based on deep learning, new hidden layer nodes can be added to the original model or the weights of existing nodes can be adjusted to adapt to changes in new knowledge. This method can quickly adapt to changes in small-scale data without significantly affecting the structure of the entire knowledge graph.

[0099] Fusion reconstruction method: When the amount of new knowledge and cases is large, that is, when it has a great impact on the existing knowledge graph structure, the fusion reconstruction method is used to comprehensively update the knowledge graph. First, the new knowledge and cases are deeply integrated with the data in the original knowledge graph to construct a temporary knowledge graph. In this process, conflicts and redundancies are eliminated by comparing and integrating the same or similar knowledge from different sources. Then, the temporary knowledge graph is optimized and verified, including but not limited to checking the integrity and logical consistency of nodes and relationships. Next, based on the optimized temporary knowledge graph, the model structure of the original knowledge graph is redesigned and adjusted, such as redefining entity types, relationship types, and inference rules. Finally, the optimized temporary knowledge graph replaces the original knowledge graph to complete the update process.

[0100] Furthermore, in a preferred embodiment, in order for the knowledge graph to reflect new information and knowledge in real time, a dynamic update mechanism is essential.

[0101] The real-time monitoring module ensures the monitoring of knowledge sources in multiple ways. For the monitoring of changes in the webpage structure of the knowledge source, taking an authoritative website in the electrical industry as an example, the update module crawls the webpage source code of the website every hour. The newly crawled source code is compared line by line with the previously stored version. If the webpage structure change information such as the increase or decrease of HTML tags and the change of text position is found, the corresponding new electrical fire-related data and information are extracted.

[0102] For data version change identification, when connected to the electrical fire database, the database system itself will mark the version of data modification, addition and other operations. The real-time monitoring module obtains the latest version number of each data object in real time through the interface connection with the version management system, and compares it with the locally stored version number. Once the version number changes, the updated content is obtained.

[0103] In terms of monitoring new electrical fire cases, a real-time interface connection is established with the electrical fire database. When a new case record is detected and added to the database, the collected case data will first be preliminarily screened to remove obviously irrelevant content, such as records containing non-electrical fire keywords (such as "geological disasters", etc.). The data is then formatted and adjusted to a standard format compatible with the knowledge graph, such as converting the time format to "YYYY-MM-DDHH:MM:SS" and unifying the text encoding to UTF-8, etc., before entering the knowledge update process.

[0104] The knowledge update process uses different methods according to the scale of new knowledge and cases. When the amount of new knowledge and cases is small, the incremental learning method is used. Taking the example of adding 10-20 pieces of information related to electrical equipment failures and electrical fires each time, these new information features are extracted as vectors in the knowledge graph, and these vectors are integrated into the existing model through predefined rules and strategies. For example, for the knowledge graph model based on deep learning, by adding a small number of hidden layer nodes or fine-tuning the weights of existing nodes, the model can adapt to new knowledge and quickly update model parameters.

[0105] When the amount of new knowledge and cases is large and has a significant impact on the structure of the knowledge graph, such as when more than 100 new pieces of knowledge related to electrical fires are added at one time, a fusion reconstruction method is used. First, a temporary knowledge graph is constructed to merge the new knowledge and cases with the original knowledge to eliminate conflicts and redundancies. For example, if the new knowledge mentions the risk mechanism of electrical fires caused by a new type of electrical connection method, and there is no relevant content in the original knowledge graph, the connection method entity is first added to the temporary knowledge graph, and a relationship is established with the relevant electrical equipment and fault type entities. Next, the temporary knowledge graph is optimized and verified, the integrity and logical consistency of the nodes and relationships are checked, and the model structure of the knowledge graph is redesigned, such as adding entity types, relationship types, and inference rules related to the new connection method. Finally, the optimized temporary knowledge graph replaces the original knowledge graph to complete the comprehensive update.

[0106] Specifically, in the step of generating analysis and statistical results, the generated analysis and statistical results are displayed in grades according to the electrical fire risk levels, and the potential cause-effect relationships and influencing factors of electrical fires are presented in a graphical manner through visualization tools. The graphical displays include node diagrams, flow charts and cause-effect diagrams.

[0107] Specifically, in the step of generating analysis and statistical results, the specific implementation methods of hierarchical display and visual display are as follows: Grading display: The generated analysis and statistical results are graded and displayed according to the electrical fire risk level. The risk level is divided based on multiple pre-set indicators (such as fire possibility, potential hazard level, etc.). For example, the risk level is divided into three levels: high, medium, and low. For the results of each risk level, independent statistical reports and descriptive information are provided, including the number, distribution, main characteristics, etc. of the level. For example, in the high risk level section, the number of high-risk electrical fire cases, the main types of electrical equipment involved, and common fault types are displayed.

[0108] Visualization: Visualization tools are used to graphically present the potential causal relationships and influencing factors of electrical fires. Graphical displays include node diagrams, flow charts, causal relationship diagrams, and other forms: Node graph: Entities related to electrical fires (such as electrical equipment, electrical parameters, environmental factors, etc.) are represented as nodes, and the relationships between entities are represented as edges. The size and color of the nodes can be distinguished according to the importance or risk level of the entity, and the thickness of the edge can indicate the closeness of the relationship. For example, the node graph can intuitively show the relationship between an electrical fire event and the various factors involved.

[0109] Flowchart: used to show the process of electrical fire and the mechanism of influencing factors. In chronological order, the various stages of fire occurrence (such as hidden dangers, trigger conditions, fire development and spread, etc.) are used as nodes of the process, and the connections in the middle represent the development sequence and cause-and-effect relationship of events.

[0110] Cause and effect diagram: Focuses on showing the cause and effect relationship between various factors affecting electrical fires. Through the connection of nodes and edges, it clearly shows how different causes (such as electrical equipment failure, environmental conditions, etc.) work together to cause electrical fires.

[0111] Customization and interactive functions: To facilitate users to display and operate according to specific needs, the visualization tool also provides customization functions, where users can choose the content to be displayed and adjust the display method (such as node size, color, edge style, etc.). At the same time, interactive functions are provided, such as clicking on a node to view detailed entity information, hovering on an edge to display a detailed description of the relationship, etc.

[0112] Furthermore, in a preferred embodiment, the generated analysis and statistical results are presented in a hierarchical manner and in a variety of visualization methods to facilitate user understanding and operation.

[0113] In terms of graded display, the results are classified and displayed according to the electrical fire risk level (high, medium, and low). For example, in the high-risk level section, the number of high-risk electrical fire cases, typical electrical equipment types involved (such as large industrial motors, data center server power modules, etc.), and common fault types (such as overcurrent short circuit, insulation damage, etc.) are displayed in detail. Through statistical data, users are informed of the proportion of high-risk cases in the total cases, the distribution of high-risk electrical fires in different industries, etc.

[0114] Visual presentation takes many forms: Node diagram: electrical fire related entities (electrical equipment, electrical parameters, environmental factors, etc.) are taken as nodes, and the relationship between entities is taken as edges. Taking the electrical system of an industrial plant as an example, various equipment in the plant, such as transformers, distribution cabinets, motors, etc., are taken as nodes, and the connection lines and power supply relationships between the equipment are taken as edges. The color of the node indicates the importance of the electrical equipment (such as red for key equipment and green for secondary equipment), and the thickness of the edge indicates the closeness of the relationship between the equipment (such as thick edges indicate a closely connected combination of equipment). Users can intuitively see the relationship between the various parts of the entire factory electrical system and the key nodes.

[0115] Flowchart: With time as the axis, it shows the process of electrical fire. For example, from the aging of electrical equipment (node ​​one), to the degradation of insulation performance (node ​​two), to the occurrence of local overheating (node ​​three), and finally to the occurrence of electrical fire (node ​​four), the connection between each node represents the sequence and cause-and-effect relationship of the development of events, so that users can clearly understand the formation process of electrical fire.

[0116] Cause and effect diagram: It highlights the cause and effect relationship between various factors affecting electrical fires. For example, it shows the relationship between the humidity of the operating environment of electrical equipment (factor A), the degree of insulation aging of the equipment (factor B), and electrical fires (result C). Through the connection of nodes and edges, it intuitively shows how increased humidity accelerates insulation aging, thereby increasing the risk of electrical fires.

[0117] In addition, in order to meet the personalized needs of users, the visualization tool provides customization functions. Users can choose the content to be displayed and adjust the display method according to specific needs. For example, users can choose to only view electrical fire information related to a specific type of electrical equipment, or adjust the size, color, and edge style of the node. At the same time, interactive functions are set up, and users can obtain detailed entity information by clicking on the node, such as the specific parameters of the electrical equipment, fault records, etc.; hovering on the edge can view a detailed description of the relationship, such as the specific mechanism of a certain electrical connection method causing a fire.

[0118] It can be understood that the present invention effectively improves the accuracy of knowledge fusion through the knowledge credibility evaluation model and optimization algorithm, making the constructed knowledge graph more accurate and complete, and better supporting the analysis and statistics of electrical fire information. The introduction of the intelligent reasoning engine can deeply explore the potential causal relationships and influencing factors of electrical fires, generate detailed and accurate analysis and statistical results, and provide users with more comprehensive information support. The establishment of a dynamic update mechanism ensures that the knowledge graph can reflect the emerging electrical fire information and knowledge in real time, always maintain the timeliness and effectiveness of the information, and greatly improve the practicality and reliability of electrical fire information analysis and statistics.

[0119] See also Figure 2 The present invention provides another embodiment, which provides an electrical fire information analysis and statistics system based on a knowledge graph, and the electrical fire information analysis and statistics system based on a knowledge graph includes: Data processing module 100: used to perform data collection and preprocessing steps, clean, remove duplicates and normalize multi-source heterogeneous data of electrical fires, and generate a standardized data set; Knowledge extraction module 200: extracting entities, attributes and relationships related to electrical fires from standardized data sets using natural language processing technology and machine learning algorithms, and constructing a preliminary knowledge graph; Knowledge fusion optimization module 300: performs credibility evaluation on the knowledge in the preliminary knowledge graph through the knowledge credibility evaluation model, integrates and optimizes the conflicting and redundant knowledge, and generates an optimized knowledge graph; Reasoning analysis module 400: construct an intelligent reasoning engine, perform deep reasoning on the optimized knowledge graph, explore potential causal relationships and influencing factors of electrical fires, and generate analysis and statistical results; Dynamic update module 500: A real-time monitoring module is set up to monitor the changes in knowledge sources and the generation of new electrical fire cases in real time, and to realize the dynamic update of the knowledge graph through the knowledge update algorithm.

[0120] It should be noted here that the present invention effectively improves the accuracy of knowledge fusion through the knowledge credibility evaluation model and optimization algorithm, making the constructed knowledge graph more accurate and complete, and better supporting the analysis and statistics of electrical fire information. The introduction of the intelligent reasoning engine can deeply explore the potential causal relationships and influencing factors of electrical fires, generate detailed and accurate analysis and statistical results, and provide users with more comprehensive information support. The establishment of a dynamic update mechanism ensures that the knowledge graph can reflect the emerging electrical fire information and knowledge in real time, always maintain the timeliness and effectiveness of the information, and greatly improve the practicality and reliability of electrical fire information analysis and statistics.

[0121] Furthermore, in a preferred embodiment, the present application also provides an electronic device, the electronic device comprising: A memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the electrical fire information analysis and statistics method based on the knowledge graph is implemented. The computer device can be broadly a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, the steps of the method of the present invention are performed.

[0122] The present invention may be implemented as a computer-readable storage medium having a computer program stored thereon, which causes the steps of the method of an embodiment of the present invention to be executed when executed by a processor. In one embodiment, the computer program is distributed on a plurality of computer devices or processors coupled to a network so that the computer program is stored, accessed and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be performed by one or more computer devices or processors, and one or more other method steps / operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step / operation, or perform two or more method steps / operations.

[0123] It will be appreciated by a person skilled in the art that the method steps of the present invention may be performed by instructing related hardware such as a computer device or a processor through a computer program, and the computer program may be stored in a non-temporary computer-readable storage medium, which causes the steps of the present invention to be performed when the computer program is executed. Depending on the circumstances, any reference to memory, storage, database, or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0124] It can be understood that the present invention effectively improves the accuracy of knowledge fusion through the knowledge credibility evaluation model and optimization algorithm, making the constructed knowledge graph more accurate and complete, and better supporting the analysis and statistics of electrical fire information. The introduction of the intelligent reasoning engine can deeply explore the potential causal relationships and influencing factors of electrical fires, generate detailed and accurate analysis and statistical results, and provide users with more comprehensive information support. The establishment of a dynamic update mechanism ensures that the knowledge graph can reflect the emerging electrical fire information and knowledge in real time, always maintain the timeliness and effectiveness of the information, and greatly improve the practicality and reliability of electrical fire information analysis and statistics.

[0125] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

[0126] The specific implementation of the present invention described above does not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A statistical method for analyzing electrical fire information based on knowledge graph, characterized in that: The method comprises: S100, Data collection and preprocessing: Collect multi-source heterogeneous data related to electrical fires, including equipment manuals, accident reports, and industry standards; clean, remove duplicates, and normalize the collected data to obtain a standardized data set; S200, Knowledge Extraction: Using natural language processing technology and machine learning algorithms, extract entities, attributes and relationships related to electrical fires from standardized data sets to build a preliminary knowledge graph; S300, knowledge fusion evaluation: introduce the knowledge credibility evaluation model, conduct credibility evaluation on the knowledge in the preliminary knowledge graph, and calculate the credibility score of each piece of knowledge; integrate and optimize the conflicting and redundant knowledge according to the credibility score, and generate an optimized knowledge graph; S400, intelligent reasoning engine construction: Build an intelligent reasoning engine, which includes a reasoning algorithm and a rule base; use the intelligent reasoning engine to perform deep reasoning on the optimized knowledge graph, explore the potential causal relationships and influencing factors of electrical fires, and generate analytical statistical results; S500. Dynamic update mechanism establishment: set up a real-time monitoring module to monitor the changes in knowledge sources and the generation of new electrical fire cases in real time; when it is monitored that the knowledge source is updated or a new case appears, use the knowledge update algorithm to integrate the new knowledge and cases into the knowledge graph to achieve dynamic update of the knowledge graph.

2. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the data collection and preprocessing steps, for the collected multi-source heterogeneous data of electrical fires, a regular expression-based cleaning algorithm is used to remove noise information, a hash algorithm is used to deduplicate data, and the data is normalized according to standard terminology and format in the electrical field. The standardized data set is classified and stored according to different application scenarios related to electrical fires.

3. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the knowledge extraction step, for the extraction of entities related to electrical fires, a conditional random field algorithm is used in combination with an electrical field knowledge dictionary for identification. For attribute extraction, a support vector machine algorithm is used to perform attribute value classification extraction based on large-scale training data. Relationship extraction adopts a relationship classification model based on deep learning. The models of the natural language processing technology and machine learning algorithm are pre-trained with labeled data in the field of electrical fires before extraction to improve the accuracy of extraction.

4. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the knowledge fusion evaluation step, the knowledge credibility evaluation model calculates the credibility score of each piece of knowledge by comprehensively considering the credibility of the knowledge source, the consistency with the existing knowledge and the frequency of citation. For knowledge whose credibility score is at a critical value, a manual assisted review mechanism is introduced to further screen and evaluate the knowledge.

5. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the intelligent reasoning engine construction step, the reasoning algorithms of the intelligent reasoning engine include rule-based reasoning algorithms, Bayesian reasoning algorithms and graph-based reasoning algorithms. The rules in the rule base are stored according to the causes of electrical fires, including electrical equipment failure rules, environmental factor rules and human operation rules. The reasoning process is carried out in the form of multiple rounds of iterations and deep search.

6. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the step of building an intelligent reasoning engine, the reasoning engine automatically annotates and supplements the knowledge graph using the reasoning results, and automatically generates corresponding entities, attributes, and relationships for newly discovered potential causal relationships and influencing factors of electrical fires and adds them to the knowledge graph.

7. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the step of establishing the dynamic update mechanism, the real-time monitoring module determines whether the knowledge source has changed by monitoring the changes in the web page structure of the knowledge source and identifying the changes in the data version. For the generation of new electrical fire cases, information collection is triggered by monitoring the new records in the electrical fire database. The collected new knowledge enters the knowledge update process after preliminary screening and format conversion.

8. The method for analyzing and statistically analyzing electrical fire information based on knowledge graph according to claim 1, characterized in that: In the knowledge updating step, the knowledge updating algorithm includes an updating method based on incremental learning and an updating method based on fusion reconstruction. When the sum of the amount of newly added knowledge and the amount of electrical fire cases is less than a first preset threshold, the incremental learning method is used to quickly update the knowledge graph; when the sum of the amount of newly added knowledge and the amount of electrical fire cases is greater than or equal to the first preset threshold, the fusion reconstruction method is used to comprehensively update the knowledge graph.

9. The electrical fire information analysis and statistical method based on knowledge graph according to claim 1 is characterized in that: In the step of generating analysis and statistical results, the generated analysis and statistical results are displayed in grades according to the electrical fire risk levels, and the potential cause-effect relationships and influencing factors of electrical fires are presented in a graphical manner through visualization tools. The graphical presentation includes node diagrams, flow charts and cause-effect diagrams.

10. An electrical fire information analysis and statistics system based on knowledge graph, characterized in that: include: Data processing module: used to perform data collection and preprocessing steps, clean, remove duplicates and normalize multi-source heterogeneous data of electrical fires to generate standardized data sets; Knowledge extraction module: uses natural language processing technology and machine learning algorithms to extract entities, attributes and relationships related to electrical fires from standardized data sets and construct a preliminary knowledge graph; Knowledge fusion and optimization module: Use the knowledge credibility evaluation model to evaluate the credibility of the knowledge in the preliminary knowledge graph, integrate and optimize the conflicting and redundant knowledge, and generate an optimized knowledge graph; Reasoning and analysis module: build an intelligent reasoning engine, perform deep reasoning on the optimized knowledge graph, explore the potential causal relationships and influencing factors of electrical fires, and generate analytical statistical results; Dynamic update module: Set up a real-time monitoring module to monitor the changes in knowledge sources and the generation of new electrical fire cases in real time, and realize the dynamic update of the knowledge graph through the knowledge update algorithm.

Images