CN113849659A - Construction method of audit system time sequence knowledge graph - Google Patents
Construction method of audit system time sequence knowledge graph Download PDFInfo
- Publication number
- CN113849659A CN113849659A CN202110952014.3A CN202110952014A CN113849659A CN 113849659 A CN113849659 A CN 113849659A CN 202110952014 A CN202110952014 A CN 202110952014A CN 113849659 A CN113849659 A CN 113849659A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- audit system
- entity
- time sequence
- audit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012550 audit Methods 0.000 title claims abstract description 127
- 238000010276 construction Methods 0.000 title claims description 15
- 238000000034 method Methods 0.000 claims abstract description 57
- 230000004927 fusion Effects 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 10
- 238000013136 deep learning model Methods 0.000 claims description 8
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000005295 random walk Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a method for constructing an audit system time sequence knowledge graph, which comprises the following steps: step 1, establishing an audit system body; step 2, extracting entity knowledge in the body of the audit system constructed in the step 1; step 3, carrying out knowledge fusion on the entity knowledge of the audit system extracted in the step 2; step 4, carrying out knowledge optimization on the result of the audit system entity knowledge fusion in the step 3; step 5, establishing an audit system knowledge graph according to the result of the audit system entity knowledge optimization in the step 4; step 6, extracting entity time sequence knowledge from the audit system library document according to the audit system body constructed in the step 1; and 7, constructing an audit system time sequence knowledge graph. The invention can fuse the time sequence information of the entity into the entity knowledge.
Description
Technical Field
The invention belongs to the technical field of knowledge maps, relates to a construction method of a knowledge map, and particularly relates to a construction method of an audit system time sequence knowledge map.
Background
The knowledge graph is used as a new big data technology, has the characteristics of visualization, is convenient for analyzing the relation before an entity, has the advantages of intuition, quantification, knowledge discovery and the like, has the capacity of managing and understanding mass information through a knowledge network established by the entity and the side, has good conjunction with the auditing work in the process of combing the knowledge structure, and can effectively accelerate the process of auditing informatization by the technology of fusing the knowledge graph; under the current big data environment, the knowledge map not only has the advantages of knowledge expression, but also plays a great role in the application aspects of information retrieval, intelligent question answering, intelligent recommendation and the like, can effectively solve the contradiction between heavy audit task and insufficient audit force, explores the change and development of the knowledge map technology which can bring to the audit field, and also becomes the inevitable trend of scientific and technological deep application of the audit field, and promotes the quality improvement and efficiency improvement of the audit work.
The first responsibility of the audit work carries out audit supervision on the implementation situation of the national major policy, and the national policy laws and regulations need to be mastered; in the process of auditing and developing inside a company, the execution condition of an audited unit needs to be checked according to the system specification of the company. The audit work needs to face the professional management conditions of company marketing, finance, materials, engineering, human resources and the like, and the coverage is wide. In the development process of an audit project, the compilation of audit records, audit manuscripts and audit reports needs to search for the basis of a positioning audit system, particularly when the historical audit records are checked, the corresponding historical audit system basis needs to be searched, the accurate audit system basis can be found mainly by depending on the working experience of auditors or by inquiring and reading in a plurality of systems and a plurality of system files, the support of an informatization means is lacked, and the working efficiency is low.
Therefore, the auditing system related in the digital auditing process is taken as a data object according to the document, the auditing system text is analyzed through a natural language processing technology, the key knowledge in the auditing system text is extracted, the system clauses in the document are subjected to labeling classification, and the relations among the system clauses, the inside of the clauses and the new and old clauses are automatically constructed, so that the time sequence knowledge graph of the auditing system is constructed, and a data basis is provided for the convenient and efficient auditing according to retrieval requirements.
Through search, the following two patent documents of the prior art are found:
1. a construction method for a knowledge graph in the tax field comprises the following steps: 202010238326.3, respectively; CN 111428053A;
the invention relates to the technical field of tax, and the method comprises the following steps: the invention discloses a construction method of a knowledge graph facing to the tax field. The construction method adopts a mode of combining top-down and bottom-up. The method comprises the following steps: firstly, constructing a mode of a tax knowledge map based on tax knowledge in a tax expert system; then, data processing is carried out, including selection and acquisition of tax data sources, cleaning of data and the like; then, information extraction is carried out, and the processed data is obtained by carrying out information extraction according to different types according to the pattern diagram; and then tax knowledge fusion is carried out, the knowledge sources in the tax knowledge map are different, and the problems of repeated knowledge, redundant relation and the like exist, and the knowledge fusion is finished by carrying out pattern matching, entity alignment and the like and then is stored in a knowledge base. And finally, knowledge feedback, namely solving knowledge conflicts in the construction of the intelligent tax model by using a tax expert system. Finally, the problem that the combination of the knowledge graph and the tax scene is not tight is solved.
2. A domain audit knowledge map construction method based on machine learning comprises the following steps: 201910585450.4, respectively; CN 110334212A;
the invention relates to the field of audit map construction, and the method comprises the following steps: the method comprises the steps of firstly, acquiring data from multiple sources; then preprocessing the acquired data; an entity recognition and relation processing module and an expert knowledge engineering module are adopted to realize the recognition of the entity; then, according to the entity obtained by the two steps of the entity identification and relation processing module and the expert knowledge engineering module, entering a natural language understanding module, and extracting feature words by using a topic model; entering a feature machine learning module according to the feature words extracted by the natural language understanding module, adjusting the weight according to specific scenes, and classifying the feature words; and finally, generating a knowledge graph. The established knowledge graph can reveal the multidimensional association between audit related subjects; thereby improving the efficiency of searching and correlating comparison of audit regulations and cases.
In the two technical schemes, the time sequence knowledge of the entity is not considered, and the fact that the actual application scene is judged by the invalid entity knowledge cannot be avoided.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for constructing an audit system time sequence knowledge graph, which can be used for fusing the time sequence information of an entity into entity knowledge.
The invention solves the practical problem by adopting the following technical scheme:
a construction method of an audit system time sequence knowledge graph comprises the following steps:
step 1, establishing an audit system body;
step 2, extracting entity knowledge in the body of the audit system constructed in the step 1;
step 3, carrying out knowledge fusion on the entity knowledge of the audit system extracted in the step 2;
step 4, carrying out knowledge optimization on the result of the audit system entity knowledge fusion in the step 3;
step 5, establishing an audit system knowledge graph according to the result of the audit system entity knowledge optimization in the step 4;
step 6, extracting entity time sequence knowledge from the audit system library document according to the audit system body constructed in the step 1;
and 7, constructing an audit system time sequence knowledge graph.
Moreover, the specific method of step 1 is:
and clustering system entities by adopting a top-down auditing system ontology semi-automatic construction method and a Gaussian mixture model clustering algorithm so as to construct an auditing system ontology.
Further, the specific steps of step 2 include:
(1) on the basis of the audit system body constructed in the step 1, extracting entity knowledge exclusive to the audit system, and dividing the extraction into an audit system entity knowledge extraction part and an audit system entity relationship extraction part;
(2) extracting entity knowledge of an auditing system from a large amount of auditing system documents by adopting a composite technical route of an auditing network sequence labeling and rule extraction method based on a BI-LSTM-CRF deep learning model;
(3) and extracting the entity relationship of the audit system by adopting a Bootstrapping semi-supervision method.
The specific method of step 3 is:
and (3) carrying out knowledge fusion on the extracted physical knowledge of the audit system by adopting an entity knowledge fusion technology based on a vectorization model according to the entity knowledge of the audit system obtained in the step (2).
Moreover, the specific method of the step 4 is as follows:
and 3, automatically correcting the entity knowledge of the audit system by adopting a knowledge-graph knowledge optimization method based on a fuzzy theory according to the result of the audit system entity knowledge fusion in the step 3.
Moreover, the specific method of the step 5 is as follows:
and (4) importing the optimized result data into a Neo4j database according to the result of the audit system entity knowledge optimization in the step 4, thereby constructing an audit system knowledge map.
The specific method of step 6 is:
and (2) analyzing massive audit system library files by adopting an LSTM deep learning model according to the audit system body constructed in the step (1) to capture time interaction knowledge among system terms, and judging time interaction of aggregation concurrency of the system files by a neighbor aggregator based on GIN (general information network), thereby extracting entity time sequence knowledge from a large amount of audit system library files.
The specific method of step 7 is:
and (5) on the basis of the audit system entity time sequence knowledge obtained in the step (6), adopting an entity linking method of fusing a convolutional neural network and restarting random walk to link the time sequence knowledge of the system entity to the audit system knowledge map in the step (5), thereby automatically constructing the audit system time sequence knowledge map.
The invention has the advantages and beneficial effects that:
1. on the basis of establishing the static knowledge graph of the auditing system, the invention extracts the time sequence knowledge of the auditing system based on the LSTM time sequence event extraction model and the GIN-based neighbor aggregation model, and integrates the time sequence knowledge into the knowledge graph of the auditing system, thereby establishing the time sequence knowledge graph of the auditing system. And extracting entity knowledge of a system library by adopting a semi-supervised method, capturing time interaction knowledge among system terms by adopting an LSTM deep learning model, and judging time interaction of aggregation and concurrency of system files by using a neighbor aggregator based on GIN (general information network), so that the whole system timing sequence knowledge is established and fused into an audit system static knowledge map.
2. The invention provides an LSTM-based time sequence event extraction model and a GIN-based neighbor aggregation model, which are used for extracting time sequence knowledge of an audit system and fusing the time sequence knowledge into an audit system knowledge map so as to construct the time sequence knowledge map of the audit system. Compared with the prior art, the method has the following advantages: a large amount of auditing system library files are analyzed by adopting an LSTM deep learning model to capture time interaction knowledge among system terms, and the neighbor aggregator based on GIN is used for judging time interaction of aggregation and concurrency of the system files, so that auditing system time sequence knowledge with clear veins is established and is fused into an auditing system knowledge map, so that the auditing system knowledge map contains the time sequence knowledge of the system, the condition that the application scene of auditing is judged by using invalid entity knowledge is avoided, and meanwhile, matched historical auditing system basis can be conveniently obtained when historical problems are audited.
Drawings
FIG. 1 is a process flow diagram of the present invention.
Detailed Description
The embodiments of the invention will be described in further detail below with reference to the accompanying drawings:
a method for constructing an audit system time sequence knowledge graph is shown in figure 1 and comprises the following steps:
step 1, establishing an audit system body;
the specific method of the step 1 comprises the following steps:
and clustering system entities by adopting a top-down auditing system ontology semi-automatic construction method and a Gaussian mixture model clustering algorithm so as to construct an auditing system ontology.
In this embodiment, the body of the auditing system is used to describe the concept and relevant knowledge of the auditing system, and implement unified specification and management of entities, relationships between entities, entity attributes and time sequence relationships between entities in the auditing system.
Step 2, extracting entity knowledge in the body of the audit system constructed in the step 1;
the specific steps of the step 2 comprise:
(1) on the basis of the audit system body constructed in the step 1, extracting entity knowledge exclusive to the audit system, and dividing the extraction into an audit system entity knowledge extraction part and an audit system entity relationship extraction part;
(2) extracting entity knowledge of an auditing system from a large amount of auditing system documents by adopting a composite technical route of an auditing network sequence labeling and rule extraction method based on a BI-LSTM-CRF deep learning model;
(3) and extracting the entity relationship of the audit system by adopting a Bootstrapping semi-supervision method.
Step 3, carrying out knowledge fusion on the entity knowledge of the audit system extracted in the step 2;
the specific method of the step 3 comprises the following steps:
and (3) according to the entity knowledge of the auditing system obtained in the step (2), adopting an entity knowledge fusion technology based on a vectorization model, wherein the entity knowledge fusion technology comprises a frame matching technology, an entity alignment technology, a conflict detection and resolution technology and the like. And the extracted physical knowledge of the audit system is subjected to knowledge fusion, so that the accuracy and consistency of the knowledge are improved, and a foundation is laid for constructing a high-quality audit system knowledge map.
Step 4, carrying out knowledge optimization on the result of the audit system entity knowledge fusion in the step 3;
the specific method of the step 4 comprises the following steps:
and 3, automatically correcting the entity knowledge of the audit system by adopting a knowledge map knowledge optimization method based on a fuzzy theory according to the result of the audit system entity knowledge fusion in the step 3, and ensuring the high quality and the availability of the audit system knowledge map.
Step 5, establishing an audit system knowledge graph according to the result of the audit system entity knowledge optimization in the step 4;
the specific method of the step 5 comprises the following steps:
and (4) importing the optimized result data into a Neo4j database according to the result of the audit system entity knowledge optimization in the step 4, thereby constructing an audit system knowledge map.
In this embodiment, there are two main data types in Neo4j, nodes (nodes) and Edges (Edges), where a Node may correspond to an entity in a knowledge graph, an edge may correspond to a relationship between entities in the knowledge graph, and attributes may be stored in both the Node and the edge.
Step 6, extracting entity time sequence knowledge from the audit system library document according to the audit system body constructed in the step 1;
the specific method of the step 6 comprises the following steps:
and (2) analyzing massive audit system library files by adopting an LSTM deep learning model according to the audit system body constructed in the step (1) to capture time interaction knowledge among system terms, and judging time interaction of aggregation concurrency of the system files by a neighbor aggregator based on GIN (general information network), thereby extracting entity time sequence knowledge from a large amount of audit system library files.
Step 7, constructing an audit system time sequence knowledge graph;
the specific method of the step 7 comprises the following steps:
and (5) on the basis of the audit system entity time sequence knowledge obtained in the step (6), adopting an entity linking method of fusing a convolutional neural network and restarting random walk to link the time sequence knowledge of the system entity to the audit system knowledge map in the step (5), thereby automatically constructing the audit system time sequence knowledge map.
It should be emphasized that the examples described herein are illustrative and not restrictive, and thus the present invention includes, but is not limited to, those examples described in this detailed description, as well as other embodiments that can be derived from the teachings of the present invention by those skilled in the art and that are within the scope of the present invention.
Claims (8)
1. A construction method of an audit system time sequence knowledge graph is characterized by comprising the following steps: the method comprises the following steps:
step 1, establishing an audit system body;
step 2, extracting entity knowledge in the body of the audit system constructed in the step 1;
step 3, carrying out knowledge fusion on the entity knowledge of the audit system extracted in the step 2;
step 4, carrying out knowledge optimization on the result of the audit system entity knowledge fusion in the step 3;
step 5, establishing an audit system knowledge graph according to the result of the audit system entity knowledge optimization in the step 4;
step 6, extracting entity time sequence knowledge from the audit system library document according to the audit system body constructed in the step 1;
and 7, constructing an audit system time sequence knowledge graph.
2. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific method of the step 1 comprises the following steps: and clustering system entities by adopting a top-down auditing system ontology semi-automatic construction method and a Gaussian mixture model clustering algorithm so as to construct an auditing system ontology.
3. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific steps of the step 2 comprise:
(1) on the basis of the audit system body constructed in the step 1, extracting entity knowledge exclusive to the audit system, and dividing the extraction into an audit system entity knowledge extraction part and an audit system entity relationship extraction part;
(2) extracting entity knowledge of an auditing system from a large amount of auditing system documents by adopting a composite technical route of an auditing network sequence labeling and rule extraction method based on a BI-LSTM-CRF deep learning model;
(3) and extracting the entity relationship of the audit system by adopting a Bootstrapping semi-supervision method.
4. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific method of the step 3 comprises the following steps:
and (3) carrying out knowledge fusion on the extracted physical knowledge of the audit system by adopting an entity knowledge fusion technology based on a vectorization model according to the entity knowledge of the audit system obtained in the step (2).
5. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific method of the step 4 comprises the following steps:
and 3, automatically correcting the entity knowledge of the audit system by adopting a knowledge-graph knowledge optimization method based on a fuzzy theory according to the result of the audit system entity knowledge fusion in the step 3.
6. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific method of the step 5 comprises the following steps:
and (4) importing the optimized result data into a Neo4j database according to the result of the audit system entity knowledge optimization in the step 4, thereby constructing an audit system knowledge map.
7. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific method of the step 6 comprises the following steps:
and (2) analyzing massive audit system library files by adopting an LSTM deep learning model according to the audit system body constructed in the step (1) to capture time interaction knowledge among system terms, and judging time interaction of aggregation concurrency of the system files by a neighbor aggregator based on GIN (general information network), thereby extracting entity time sequence knowledge from a large amount of audit system library files.
8. The method for constructing the audit system time sequence knowledge graph according to claim 1, wherein the method comprises the following steps: the specific method of the step 7 comprises the following steps:
and (5) on the basis of the audit system entity time sequence knowledge obtained in the step (6), adopting an entity linking method of fusing a convolutional neural network and restarting random walk to link the time sequence knowledge of the system entity to the audit system knowledge map in the step (5), thereby automatically constructing the audit system time sequence knowledge map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952014.3A CN113849659A (en) | 2021-08-18 | 2021-08-18 | Construction method of audit system time sequence knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952014.3A CN113849659A (en) | 2021-08-18 | 2021-08-18 | Construction method of audit system time sequence knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113849659A true CN113849659A (en) | 2021-12-28 |
Family
ID=78975981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110952014.3A Pending CN113849659A (en) | 2021-08-18 | 2021-08-18 | Construction method of audit system time sequence knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113849659A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204875A (en) * | 2023-05-06 | 2023-06-02 | 天津南大通用数据技术股份有限公司 | Method for realizing reasoning capacity of database audit record |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840282A (en) * | 2019-03-01 | 2019-06-04 | 东北大学 | A kind of knowledge mapping optimization method based on fuzzy theory |
| CN110334212A (en) * | 2019-07-01 | 2019-10-15 | 南京审计大学 | A kind of territoriality audit knowledge mapping construction method based on machine learning |
| CN111428053A (en) * | 2020-03-30 | 2020-07-17 | 西安交通大学 | Tax field knowledge graph construction method |
| CN111915090A (en) * | 2020-08-10 | 2020-11-10 | 哈尔滨安天科技集团股份有限公司 | Prediction method and device based on knowledge graph, electronic equipment and storage medium |
| CN112463981A (en) * | 2020-11-26 | 2021-03-09 | 福建正孚软件有限公司 | Enterprise internal operation management risk identification and extraction method and system based on deep learning |
| CN112613611A (en) * | 2020-12-29 | 2021-04-06 | 上海永骁智能技术有限公司 | Tax knowledge base system based on knowledge graph |
-
2021
- 2021-08-18 CN CN202110952014.3A patent/CN113849659A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840282A (en) * | 2019-03-01 | 2019-06-04 | 东北大学 | A kind of knowledge mapping optimization method based on fuzzy theory |
| CN110334212A (en) * | 2019-07-01 | 2019-10-15 | 南京审计大学 | A kind of territoriality audit knowledge mapping construction method based on machine learning |
| CN111428053A (en) * | 2020-03-30 | 2020-07-17 | 西安交通大学 | Tax field knowledge graph construction method |
| CN111915090A (en) * | 2020-08-10 | 2020-11-10 | 哈尔滨安天科技集团股份有限公司 | Prediction method and device based on knowledge graph, electronic equipment and storage medium |
| CN112463981A (en) * | 2020-11-26 | 2021-03-09 | 福建正孚软件有限公司 | Enterprise internal operation management risk identification and extraction method and system based on deep learning |
| CN112613611A (en) * | 2020-12-29 | 2021-04-06 | 上海永骁智能技术有限公司 | Tax knowledge base system based on knowledge graph |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204875A (en) * | 2023-05-06 | 2023-06-02 | 天津南大通用数据技术股份有限公司 | Method for realizing reasoning capacity of database audit record |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106934014B (en) | Hadoop-based network data mining and analyzing platform and method thereof | |
| CN111967761B (en) | Knowledge graph-based monitoring and early warning method and device and electronic equipment | |
| US20110191277A1 (en) | Automatic data mining process control | |
| CN112579852B (en) | Interactive webpage data accurate acquisition method | |
| LU503512B1 (en) | Operating method for construction of knowledge graph based on naming rule and caching mechanism | |
| CN109039710B (en) | Routing data auditing method, device, server and storage medium | |
| CN111475625A (en) | News manuscript generation method and system based on knowledge graph | |
| CN111737477A (en) | Intellectual property big data-based intelligence investigation method, system and storage medium | |
| CN112181960A (en) | Intelligent operation and maintenance framework system based on AIOps | |
| CN112181428A (en) | Abstract syntax tree-based open-source software defect data classification method and system | |
| CN113282599A (en) | Data synchronization method and system | |
| CN116361487A (en) | Multi-source heterogeneous policy knowledge graph construction and storage method and system | |
| CN107086925B (en) | Deep learning-based internet traffic big data analysis method | |
| CN113849659A (en) | Construction method of audit system time sequence knowledge graph | |
| CN103870489A (en) | Chinese name self-extension recognition method based on search logs | |
| CN111046059B (en) | Low-efficiency SQL statement analysis method and system based on distributed database cluster | |
| CN112966162A (en) | Scientific and technological resource integration method and device based on data warehouse and middleware | |
| CN109213909A (en) | A kind of big data analysis system and its analysis method fusion search and calculated | |
| CN115827885A (en) | Operation and maintenance knowledge graph construction method and device and electronic equipment | |
| CN112464668A (en) | Method and system for extracting dynamic information of smart home industry | |
| CN112732845A (en) | End-to-end-based large-scale knowledge graph construction and storage method and system | |
| CN111460046A (en) | Scientific and technological information clustering method based on big data | |
| Visalli et al. | ESG Data Collection with Adaptive AI. | |
| CN114692595B (en) | Repeated conflict scheme detection method based on text matching | |
| CN115292274B (en) | Data warehouse topic model construction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |