Automatic construction method of live-line work site violation knowledge graph taking behavior node as center

Through the automated construction method centered on behavior nodes, a complete knowledge graph of violations on live operations was established, which solved the problem of one-sided and isolated islands of knowledge graph content in the existing technology, and achieved effective identification and risk analysis support for violations. .

CN119005315AActive Publication Date: 2024-11-22TONGHUA POWER SUPPLY COMPANY STATE GRID JILIN ELECTRIC POWER
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411039784.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-22
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

The existing methods to construct the knowledge graph of violations at live operations have problems such as one-sided content, knowledge islands, unknown reasoning, and cognitive hollowness, which is difficult to effectively support the identification and risk analysis of violations in artificial intelligence.

Method used

An automated construction method centered on behavior nodes is adopted. By entering violation case data and hazard descriptions, a related knowledge graph of behavior and risk points is established, and nodes and links are automatically added to form a complete violation knowledge graph.

Benefits of technology

Without human intervention, a complete knowledge graph of violations on live operations was established, which solved the one-sided and isolated problems of the knowledge graph content, provided effective support for automated analysis, and reduced unknown reasoning and misjudgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005315A_ABST
    Figure CN119005315A_ABST
Patent Text Reader

Abstract

The invention discloses an automatic construction method of a live-line work site violation knowledge graph taking a behavior node as a center, and belongs to the technical field of live-line work site violation monitoring. According to the method, the problems that the content of a knowledge graph constructed by adopting an existing method is one-sided, knowledge islands are formed, and unknown reasoning and cognitive holes are included are solved. According to the method, the knowledge graph of the violation behaviors of the live-line work site can be established only by using the input case data of the violation behaviors of the live-line work site without human intervention and additional input of the incidence relation; according to the method, behaviors, cases, risks and association relationships among the behaviors, the cases and the risks can be obtained from the knowledge graph, the problem that unknown reasoning and cognitive cavities are included in the knowledge graph constructed by adopting an existing method is solved, and effective support is provided for automatic analysis of a live working site. The method can be applied to automatic construction of the live-line work site violation knowledge graph.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of monitoring illegal behaviors at live working sites, and specifically relates to an automated construction method of a knowledge graph of illegal behaviors at live working sites centered on behavior nodes. Background Art

[0002] Live working is an important means to ensure power supply reliability, but the operation is risky and illegal behavior endangers the safety of workers and the stability of the power grid. Constructing a knowledge graph of illegal behavior at live working sites can assist artificial intelligence programs in discovering on-site violations and inferring possible risks, which is of great significance for safe construction, power supply safety and workers' personal safety.

[0003] The current traditional methods for constructing a knowledge graph of violations at live working sites include: 1) manual construction, where domain experts analyze violations at live working sites and manually input each node one by one. This method consumes a lot of manpower and time, is difficult to scale, and is difficult to update. At the same time, since violations are diverse and some violations are not thought of by experts, the knowledge graph of this method is often one-sided and cannot effectively provide support for intelligent identification. 2) Provide clear concept definitions and relationship structures and use ontology to automatically construct; although the efficiency has been improved, a key problem of this method is that violations at live working sites are independent of each other and have low correlation in the original data set (unless the same person violates the rules multiple times). Therefore, the knowledge graph established using this method will form a relatively isolated knowledge island, which is difficult to form effective reasoning support for artificial intelligence programs. 3) Natural language processing knowledge matching: In order to solve the isolation problem caused by the ontology, the vector database is used to match and associate the case description content. This method can semantically find the relationship between different violations; however, the natural language processing vectorization process (or model) is usually established for general application scenarios. This processing procedure often ignores key content and words, resulting in many unknown reasoning and cognitive gaps in the knowledge graph, which leads to missed judgments and misjudgments of violations.

[0004] It can be seen that it is very important to quickly and effectively establish a knowledge graph of illegal behaviors at live working sites and maintain valid graph nodes, attributes and relationships. Summary of the invention

[0005] The purpose of the present invention is to solve the problems that the knowledge graph constructed by the existing method has one-sided content, forms knowledge islands, contains unknown reasoning and cognitive gaps, and proposes an automated construction method for the knowledge graph of illegal behaviors at live working sites centered on behavior nodes. Based on the case data of illegal behaviors at live working sites and the behaviors and resulting hazards of the case data, the corresponding knowledge graph is automatically established with the behavior nodes as the associated center.

[0006] The technical solution adopted by the present invention to solve the above technical problems is: an automated construction method of a knowledge graph of illegal behaviors at live working sites centered on behavior nodes, the method specifically comprising the following steps:

[0007] Step S1, inputting a data list of illegal behaviors on live working sites DDDataSet, a dangerous behavior word list WXDict, and a risk point word list FXDict;

[0008] Establish a behavior candidate list DDKeyDict of illegal behavior data list at live working site; establish a risk point candidate list DDFXDict of illegal behavior at live working site;

[0009] Step S2, establish a knowledge graph KG of illegal behaviors at live working sites, add behavior nodes to KG based on DDKeyDict, and add risk point nodes to KG based on DDFXDict;

[0010] Step S3, based on DDDataSet and existing behavior nodes, establish knowledge nodes and links in the knowledge graph KG.

[0011] Furthermore, the specific process of step S1 is as follows:

[0012] S101, inputting a live working site violation behavior case data list DDDataSet, each element of which corresponds to a live working site violation behavior case data, including 4 fields;

[0013] DDID: the number of a live work site violation case;

[0014] DDImage: Image data of illegal behaviors at live working sites;

[0015] DDXWDesc: Description of illegal behaviors at live working sites, using natural language to describe illegal behaviors at live working sites;

[0016] DDFXDesc: Risk point behavior description, using natural language to describe the risk points existing at the live working site and the hazards and damage caused;

[0017] S102, inputting a dangerous behavior word list WXDict, where each element of the list corresponds to a dangerous behavior word entry during live working;

[0018] S103, inputting a risk point word list FXDict, where each element of the list corresponds to a descriptive entry of a consequence caused by a dangerous behavior during live working;

[0019] S104, behavior counter DDCounter = 1; behavior candidate list DDKeyDict of live working site illegal behavior data list = empty list; establish live working site illegal behavior risk point candidate list DDFXDict = empty list;

[0020] S105, behavior temporary storage data DDTemp = taking out the DDCounterth data of DDDataSet;

[0021] S106, extract the content of the DDXWDesc field of DDTemp, search for words that appear in WXDict in the extracted content, and put all the found words into the single case behavior list DDXWCT; extract the content of the DDFXDesc field of DDTemp, search for words that appear in FXDict in the extracted content, and put all the found words into the behavior single case risk list DDFXCT;

[0022] S107, DDKeyDict=obtain the union of DDKeyDict and DDXWCT; DDFXDict=obtain the union of DDFXDict and DDFXCT;

[0023] S108, set DDCounter=DDCounter+1;

[0024] S109, if DDCounter is less than or equal to the number of elements in DDDataSet, go to S105, otherwise go to S110;

[0025] S110, step S1 ends, and the final behavior candidate list DDKeyDict and risk point candidate list DDFXDict are obtained.

[0026] Furthermore, the specific process of step S2 is as follows:

[0027] S201, establish a knowledge graph of illegal behaviors at live working sites KG = empty knowledge graph;

[0028] S202, behavior node counter KGCCounter used for knowledge graph establishment = 1;

[0029] S203, establish a new knowledge graph behavior node NXWNode;

[0030] S204, setting the name NNodeName attribute of NXWNode to the KGCCounterth element of DDKeyDict;

[0031] S205, create a new behavior description vector KGDescVector = a vector with the same dimension as the number of elements in DDKeyDict and all zeros;

[0032] S206, setting the KGCCounterth element of KGDescVector to 1;

[0033] S207, setting the behavior attribute NnodeAction of NXWNode to KGDescVector;

[0034] S208, add NXWNode to KG;

[0035] S209, KGCCounter=KGCCounter+1;

[0036] S210, if KGCCounter is less than or equal to the number of elements of DDKeyDict, go to S203; otherwise go to S211;

[0037] S211, risk point counter KGFXCounter for knowledge graph establishment = 1;

[0038] S212, establish a new knowledge graph risk node NFXNode;

[0039] S213, the risk name NFXNodeName attribute of NFXNode is the KGFXCounterth element of DDFXDict;

[0040] S214, add NFXNode to KG;

[0041] S215, set KGFXCounter=KGFXCounter+1;

[0042] S216, if KGFXCounter is less than or equal to the number of elements of DDFXDict, go to S212, otherwise go to S217;

[0043] S217, end.

[0044] Furthermore, the specific process of step S3 is as follows:

[0045] S301, establish process counter DDCCCounter=1;

[0046] S302, establishing a new knowledge graph case node NANNode;

[0047] S303, establish a process temporary storage case DDCCTemp = take out the DDCCCounterth element of DDDataSet;

[0048] S304, extract the content of the DDXWDesc field of DDCCTemp, search for words that appear in WXDict in the extracted content, and put all the found words into the single case behavior list DDCCXW of the establishment process; extract the content of the DDFXDesc field of DDCCTemp, search for words that appear in FXDict in the extracted content, and put all the found words into the single behavior case risk list DDCCFX of the establishment process;

[0049] S305, the establishment process finds the behavior node list DDCCFindXWList = searches in the behavior nodes of KG and finds all nodes whose name NNodeName attribute appears in DDCCXW;

[0050] S306, establish links from all nodes of DDCCFindXWList to NANNode in KG;

[0051] S307, the establishment process finds the risk node list DDCCFindFXList = searches in the behavior nodes of KG and finds all nodes whose name NFXNodeName attribute appears in DDFXDict;

[0052] S308, establishing links from NANNode to all nodes in DDCCFindFXList in KG;

[0053] S309, establish a process behavior description vector DDCCXWVector = a vector with the same dimension as the number of DDKeyDict elements, and all elements are 0;

[0054] S310, establish process behavior entry location DDCCXWPos=find the entry that appears in DDCCXW in DDKeyDict and obtain the position list of the entry;

[0055] S311, set the element corresponding to the position recorded by DDCCXWPos in DDCCXWVector to 1;

[0056] S312, establish a process risk description vector DDCCFXVector = a vector whose dimension is consistent with the number of elements in DDFXDict, and all elements are 0;

[0057] S313, establish process risk term position DDCCFXPos = find the term in DDFXDict that appears in DDCCFX and obtain the position list of the term;

[0058] S314, setting the element corresponding to the position recorded by DDCCFXPos in DDCCFXVector to 1;

[0059] S315, the case behavior description attribute ANXW of NANNode = DDCCXWVector;

[0060] S316, the case risk description attribute ANFX of NANNode = DDCCFXVector;

[0061] S317, source case attribute LYAN of NANNode = DDID attribute of DDCCTemp;

[0062] S318, the source image attribute LYTP of NANNode = DDImage attribute of DDCCTemp;

[0063] S319, specific description of the source of NANNode LYContet = DDXWDesc attribute of DDCCTemp + DDFXDesc attribute of DDCCTemp, where the + sign indicates string combination;

[0064] S320, adding NANNode to KG;

[0065] S321, store the KG and complete the knowledge graph construction process.

[0066] The beneficial effects of the present invention are:

[0067] The present invention can establish a knowledge graph of illegal behaviors at live working sites by using only the input case data of illegal behaviors at live working sites without the need for human intervention and additional input of association relationships; behaviors, cases, risks and the associations between them can be obtained from the knowledge graph, which solves the problems of unknown reasoning and cognitive gaps in knowledge graphs constructed using existing methods, provides effective support for automated analysis of live working sites, and solves the problems of one-sided content and knowledge islands in knowledge graphs constructed using existing methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a flow chart of a method for automatically constructing a knowledge graph of illegal behaviors at live working sites centered on behavior nodes of the present invention. DETAILED DESCRIPTION

[0069] Specific implementation method 1: Combination Figure 1The present embodiment describes a method for automatically constructing a knowledge graph of illegal behaviors at live working sites centered on behavior nodes, and the method specifically includes the following steps:

[0070] Step S1, inputting a data list of illegal behaviors on live working sites DDDataSet, a dangerous behavior word list WXDict, and a risk point word list FXDict;

[0071] Establish a behavior candidate list DDKeyDict of illegal behavior data list at live working site; establish a risk point candidate list DDFXDict of illegal behavior at live working site;

[0072] Step S2, establish a knowledge graph KG of illegal behaviors at live working sites, add behavior nodes to KG based on DDKeyDict, and add risk point nodes to KG based on DDFXDict;

[0073] Step S3, based on DDDataSet and existing behavior nodes, establish knowledge nodes and links in the knowledge graph KG.

[0074] Specific implementation method 2: This implementation method is different from the specific implementation method 1 in that the specific process of step S1 is as follows:

[0075] S101, inputting a live working site violation behavior case data list DDDataSet, each element of which corresponds to a live working site violation behavior case data, including 4 fields;

[0076] DDID: the number of a live work site violation case;

[0077] DDImage: image data of violations at live working sites, including violations at the entire live working site;

[0078] DDXWDesc: Description of illegal behaviors at live working sites, using natural language to describe illegal behaviors at live working sites;

[0079] DDFXDesc: Risk point behavior description, using natural language to describe the main risk points and possible hazards and damages at the live working site;

[0080] S102, inputting a dangerous behavior word list WXDict, where each element of the list corresponds to a dangerous behavior word entry during live working, such as: not wearing a safety helmet, not grounding;

[0081] S103, input the risk point word list FXDict, each element of the list corresponds to a descriptive term of a dangerous behavior during live working, such as electric shock, breakdown, explosion;

[0082] S104, behavior counter DDCounter = 1; behavior candidate list DDKeyDict of live working site illegal behavior data list = empty list; establish live working site illegal behavior risk point candidate list DDFXDict = empty list;

[0083] S105, behavior temporary storage data DDTemp = taking out the DDCounterth data of DDDataSet;

[0084] S106, extract the content of the DDXWDesc field of DDTemp, search for words that appear in WXDict in the extracted content, and put all the found words into the single case behavior list DDXWCT; extract the content of the DDFXDesc field of DDTemp, search for words that appear in FXDict in the extracted content, and put all the found words into the behavior single case risk list DDFXCT;

[0085] S107, DDKeyDict=obtain the union of DDKeyDict and DDXWCT; DDFXDict=obtain the union of DDFXDict and DDFXCT;

[0086] S108, set DDCounter=DDCounter+1;

[0087] S109, if DDCounter is less than or equal to the number of elements in DDDataSet, go to S105, otherwise go to S110;

[0088] S110, step S1 ends, and the final behavior candidate list DDKeyDict and risk point candidate list DDFXDict are obtained.

[0089] The other steps and parameters are the same as those in the first embodiment.

[0090] Specific implementation method three: This implementation method is different from specific implementation methods one or two in that the specific process of step S2 is as follows:

[0091] S201, establish a knowledge graph of illegal behaviors at live working sites KG = empty knowledge graph;

[0092] S202, behavior node counter KGCCounter used for knowledge graph establishment = 1;

[0093] S203, establish a new knowledge graph behavior node NXWNode;

[0094] S204, setting the name NNodeName attribute of NXWNode to the KGCCounterth element of DDKeyDict;

[0095] S205, create a new behavior description vector KGDescVector = a vector with the same dimension as the number of elements in DDKeyDict and all zeros;

[0096] S206, setting the KGCCounterth element of KGDescVector to 1;

[0097] S207, setting the behavior attribute NnodeAction of NXWNode to KGDescVector;

[0098] S208, add NXWNode to KG;

[0099] S209, KGCCounter=KGCCounter+1;

[0100] S210, if KGCCounter is less than or equal to the number of elements of DDKeyDict, go to S203; otherwise go to S211;

[0101] S211, risk point counter KGFXCounter for knowledge graph establishment = 1;

[0102] S212, establish a new knowledge graph risk node NFXNode;

[0103] S213, the risk name NFXNodeName attribute of NFXNode is the KGFXCounterth element of DDFXDict;

[0104] S214, add NFXNode to KG;

[0105] S215, set KGFXCounter=KGFXCounter+1;

[0106] S216, if KGFXCounter is less than or equal to the number of elements of DDFXDict, go to S212, otherwise go to S217;

[0107] S217, end.

[0108] The other steps and parameters are the same as those in the first or second embodiment.

[0109] Specific implementation method 4: This implementation method is different from any one of the specific implementation methods 1 to 3 in that the specific process of step S3 is as follows:

[0110] S301, establish process counter DDCCCounter=1;

[0111] S302, establishing a new knowledge graph case node NANNode;

[0112] S303, establish a process temporary storage case DDCCTemp = take out the DDCCCounterth element of DDDataSet;

[0113] S304, extract the content of the DDXWDesc field of DDCCTemp, search for words that appear in WXDict in the extracted content, and put all the found words into the single case behavior list DDCCXW of the establishment process; extract the content of the DDFXDesc field of DDCCTemp, search for words that appear in FXDict in the extracted content, and put all the found words into the single behavior case risk list DDCCFX of the establishment process;

[0114] S305, the establishment process finds the behavior node list DDCCFindXWList = searches in the behavior nodes of KG and finds all nodes whose name NNodeName attribute appears in DDCCXW;

[0115] S306, establish links from all nodes of DDCCFindXWList to NANNode in KG;

[0116] S307, the establishment process finds the risk node list DDCCFindFXList = searches in the behavior nodes of KG and finds all nodes whose name NFXNodeName attribute appears in DDFXDict;

[0117] S308, establishing links from NANNode to all nodes in DDCCFindFXList in KG;

[0118] S309, establish a process behavior description vector DDCCXWVector = a vector with the same dimension as the number of DDKeyDict elements, and all elements are 0;

[0119] S310, establish process behavior entry location DDCCXWPos=find the entry that appears in DDCCXW in DDKeyDict and obtain the position list of the entry;

[0120] S311, set the element corresponding to the position recorded by DDCCXWPos in DDCCXWVector to 1;

[0121] S312, establish a process risk description vector DDCCFXVector = a vector whose dimension is consistent with the number of elements in DDFXDict, and all elements are 0;

[0122] S313, establish process risk term position DDCCFXPos = find the term in DDFXDict that appears in DDCCFX and obtain the position list of the term;

[0123] S314, setting the element corresponding to the position recorded by DDCCFXPos in DDCCFXVector to 1;

[0124] S315, the case behavior description attribute ANXW of NANNode = DDCCXWVector;

[0125] S316, the case risk description attribute ANFX of NANNode = DDCCFXVector;

[0126] S317, source case attribute LYAN of NANNode = DDID attribute of DDCCTemp;

[0127] S318, the source image attribute LYTP of NANNode = DDImage attribute of DDCCTemp;

[0128] S319, specific description of the source of NANNode LYContet = DDXWDesc attribute of DDCCTemp + DDFXDesc attribute of DDCCTemp, where the + sign indicates string combination;

[0129] S320, adding NANNode to KG;

[0130] S321, store the KG and complete the knowledge graph construction process.

[0131] The other steps and parameters are the same as those in Specific Embodiments 1 to 3.

[0132] The above calculation examples of the present invention are only used to explain the calculation model and calculation process of the present invention in detail, and are not intended to limit the implementation methods of the present invention. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. An automated construction method for the knowledge graph of illegal behaviors at live working sites centered on behavior nodes, It is characterized in that The method specifically comprises the following steps: Step S1, inputting a data list of illegal behaviors on live working sites DDDataSet, a dangerous behavior word list WXDict, and a risk point word list FXDict; Establish a behavior candidate list DDKeyDict of illegal behavior data list at live working site; establish a risk point candidate list DDFXDict of illegal behavior at live working site; Step S2, establish a knowledge graph KG of illegal behaviors at live working sites, add behavior nodes to KG based on DDKeyDict, and add risk point nodes to KG based on DDFXDict; Step S3, based on DDDataSet and existing behavior nodes, establish knowledge nodes and links in the knowledge graph KG.

2. According to claim 1, a method for automatically constructing a knowledge graph of illegal behaviors at live working sites centered on behavior nodes, It is characterized in that The specific process of step S1 is as follows: S101, inputting a live working site violation behavior case data list DDDataSet, each element of which corresponds to a live working site violation behavior case data, including 4 fields; DDID: the number of a live work site violation case; DDImage: Image data of illegal behaviors at live working sites; DDXWDesc: Description of illegal behaviors at live working sites, using natural language to describe illegal behaviors at live working sites; DDFXDesc: Risk point behavior description, using natural language to describe the risk points existing at the live working site and the hazards and damage caused; S102, inputting a dangerous behavior word list WXDict, where each element of the list corresponds to a dangerous behavior word entry during live working; S103, inputting a risk point word list FXDict, where each element of the list corresponds to a descriptive entry of a consequence caused by a dangerous behavior during live working; S104, behavior counter DDCounter=1; The behavior candidate list of the live working site illegal behavior data list DDKeyDict = empty list; establish the live working site illegal behavior risk point candidate list DDFXDict = empty list; S105, behavior temporary storage data DDTemp = taking out the DDCounterth data of DDDataSet; S106, extract the content of the DDXWDesc field of DDTemp, search for words that appear in WXDict in the extracted content, and put all the found words into the single case behavior list DDXWCT; extract the content of the DDFXDesc field of DDTemp, search for words that appear in FXDict in the extracted content, and put all the found words into the behavior single case risk list DDFXCT; S107, DDKeyDict=obtain the union of DDKeyDict and DDXWCT; DDFXDict=obtain the union of DDFXDict and DDFXCT; S108, set DDCounter=DDCounter+1; S109, if DDCounter is less than or equal to the number of elements in DDDataSet, go to S105, otherwise go to S110; S110, step S1 ends, and the final behavior candidate list DDKeyDict and risk point candidate list DDFXDict are obtained.

3. According to claim 2, a method for automatically constructing a knowledge graph of illegal behaviors at live working sites centered on behavior nodes, It is characterized in that The specific process of step S2 is: S201, establish a knowledge graph of illegal behaviors at live working sites KG = empty knowledge graph; S202, behavior node counter KGCCounter used for knowledge graph establishment = 1; S203, establish a new knowledge graph behavior node NXWNode; S204, setting the name NNodeName attribute of NXWNode to the KGCCounterth element of DDKeyDict; S205, create a new behavior description vector KGDescVector = a vector with the same dimension as the number of elements in DDKeyDict and all zeros; S206, setting the KGCCounterth element of KGDescVector to 1; S207, setting the behavior attribute NnodeAction of NXWNode to KGDescVector; S208, add NXWNode to KG; S209, KGCCounter=KGCCounter+1; S210, if KGCCounter is less than or equal to the number of elements of DDKeyDict, go to S203; otherwise go to S211; S211, risk point counter KGFXCounter for knowledge graph establishment = 1; S212, establish a new knowledge graph risk node NFXNode; S213, the risk name NFXNodeName attribute of NFXNode is the KGFXCounterth element of DDFXDict; S214, add NFXNode to KG; S215, set KGFXCounter=KGFXCounter+1; S216, if KGFXCounter is less than or equal to the number of elements of DDFXDict, go to S212, otherwise go to S217; S217, end.

4. According to claim 3, a method for automatically constructing a knowledge graph of illegal behaviors at live working sites centered on behavior nodes, It is characterized in that The specific process of step S3 is: S301, establish process counter DDCCCounter=1; S302, establishing a new knowledge graph case node NANNode; S303, establish a process temporary storage case DDCCTemp = take out the DDCCCounterth element of DDDataSet; S304, extract the content of the DDXWDesc field of DDCCTemp, search for words that appear in WXDict in the extracted content, and put all the found words into the single case behavior list DDCCXW of the establishment process; extract the content of the DDFXDesc field of DDCCTemp, search for words that appear in FXDict in the extracted content, and put all the found words into the single behavior case risk list DDCCFX of the establishment process; S305, the establishment process finds the behavior node list DDCCFindXWList = searches in the behavior nodes of KG and finds all nodes whose name NNodeName attribute appears in DDCCXW; S306, establish links from all nodes of DDCCFindXWList to NANNode in KG; S307, the establishment process finds the risk node list DDCCFindFXList = searches in the behavior nodes of KG and finds all nodes whose name NFXNodeName attribute appears in DDFXDict; S308, establishing links from NANNode to all nodes in DDCCFindFXList in KG; S309, establish a process behavior description vector DDCCXWVector = a vector with the same dimension as the number of DDKeyDict elements, and all elements are 0; S310, establish process behavior entry location DDCCXWPos=find the entry that appears in DDCCXW in DDKeyDict and obtain the position list of the entry; S311, set the element corresponding to the position recorded by DDCCXWPos in DDCCXWVector to 1; S312, establish a process risk description vector DDCCFXVector = a vector whose dimension is consistent with the number of elements in DDFXDict, and all elements are 0; S313, establish process risk term position DDCCFXPos = find the term in DDFXDict that appears in DDCCFX and obtain the position list of the term; S314, setting the element corresponding to the position recorded by DDCCFXPos in DDCCFXVector to 1; S315, the case behavior description attribute ANXW of NANNode = DDCCXWVector; S316, the case risk description attribute ANFX of NANNode = DDCCFXVector; S317, source case attribute LYAN of NANNode = DDID attribute of DDCCTemp; S318, the source image attribute LYTP of NANNode = DDImage attribute of DDCCTemp; S319, specific description of the source of NANNode LYContet = DDXWDesc attribute of DDCCTemp + DDFXDesc attribute of DDCCTemp, where the + sign indicates string combination; S320, adding NANNode to KG; S321, store the KG and complete the knowledge graph construction process.

Citation Information

Patent Citations

  • Construction behavior safety risk analysis and dangerous point identification method based on knowledge graph

    CN113127606A

  • Security knowledge graph construction method and system for smart power plant

    CN113254594A

  • Building elevation risk assessment method based on knowledge graph

    CN116205492A

  • Military software defect multi-modal knowledge graph construction method, device and system

    CN116860986A

  • Method and system for judging violation behaviors of different underground posts

    CN117391457A