CN114612071A - Data management method based on knowledge graph - Google Patents
Data management method based on knowledge graph Download PDFInfo
- Publication number
- CN114612071A CN114612071A CN202210261586.1A CN202210261586A CN114612071A CN 114612071 A CN114612071 A CN 114612071A CN 202210261586 A CN202210261586 A CN 202210261586A CN 114612071 A CN114612071 A CN 114612071A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge graph
- data
- classification
- graph
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data management method based on a knowledge graph, belonging to the technical field of data management, and the specific method comprises the following steps: the method comprises the following steps: identifying the organization architecture of the current enterprise, marking the organization architecture as a single component, and merging the single components to obtain a structure analysis part; step two: acquiring a classification knowledge graph corresponding to each structural analysis part, and manufacturing a knowledge graph template corresponding to the structural analysis part; step three: acquiring a data type and a structure analysis part corresponding to each template part in a knowledge graph template, and marking the template parts with corresponding data type labels and structure analysis part labels; step four: setting an atlas label table according to the data type labels and the structural analysis part labels of the template parts in the knowledge atlas template; step five: establishing a migration index item according to the map label table, and establishing a corresponding storage node in the enterprise database according to a characteristic index item contained in the migration index item; step six: and establishing a data migration model in the enterprise database.
Description
Technical Field
The invention belongs to the technical field of data management, and particularly relates to a data management method based on a knowledge graph.
Background
The knowledge map is called knowledge domain visualization or knowledge domain mapping map in the book intelligence world, is a series of different graphs for displaying the relationship between the knowledge development process and the structure, describes knowledge resources and carriers thereof by using visualization technology, and excavates, analyzes, constructs, draws and displays knowledge and the mutual relation between the knowledge resources and the carriers.
Knowledge graphs are widely used in the field of data management; however, the current use of the knowledge graph is to generally represent data of an enterprise, and with the rapid development of digitization, the number of stored data in the enterprise is increased, and the management is more and more difficult, so that a data management method based on the knowledge graph is needed to be provided at present, and the stored data in the enterprise is managed by using the current knowledge graph.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a data management method based on a knowledge graph.
The purpose of the invention can be realized by the following technical scheme:
a data management method based on a knowledge graph comprises the following specific steps:
the method comprises the following steps: identifying the organization architecture of the current enterprise, marking the organization architecture as a single component, and merging the single components to obtain a structure analysis part;
step two: acquiring a classification knowledge graph corresponding to each structural analysis part, and manufacturing a knowledge graph template corresponding to the structural analysis part;
step three: acquiring a data type and a structure analysis part corresponding to each template part in a knowledge graph template, and marking the template parts with corresponding data type labels and structure analysis part labels;
step four: setting an atlas label table according to the data type labels and the structural analysis part labels of the template parts in the knowledge atlas template;
step five: establishing a migration index item according to the map label table, and establishing a corresponding storage node in the enterprise database according to a characteristic index item contained in the migration index item;
step six: and establishing a data migration model in the enterprise database, and migrating the data stored in the enterprise database to the corresponding storage node by the data migration model according to the migration index item.
Further, the method for single component merging includes:
acquiring the function range and the generated data type information of each single component, establishing a knowledge graph library of the current enterprise, identifying the application range information of a target knowledge graph in the knowledge graph library, classifying the target knowledge graph, selecting N target knowledge graphs in each classification as classification knowledge graphs, marking corresponding classification labels, marking N as positive integers as knowledge graph classification templates, matching the function range and the data type information of the single component with the application range information of the knowledge graph classification templates, merging the single components belonging to the same knowledge graph classification template classification, and marking the single components as a structure analysis part.
Further, the method for establishing the knowledge map library of the current enterprise comprises the following steps:
acquiring a knowledge graph retrieval formula, retrieving the knowledge graph according to the acquired knowledge graph retrieval formula to acquire the knowledge graph, screening the acquired knowledge graph to acquire a target knowledge graph, establishing a first database, inputting the target knowledge graph into the first database, and marking the current first database as a knowledge graph database.
Further, the method for obtaining the knowledge graph searching formula comprises the following steps:
the method comprises the steps of obtaining the business range of a current enterprise, integrating the business range and the function range of each single component into range data, extracting key words in the range data, setting voice recognition nodes, enabling corresponding managers to supplement and narrate the extracted key words through the voice recognition nodes, recognizing narration content of the managers, establishing a retrieval model, inputting the key words and the narration content into the retrieval model, and obtaining a knowledge map retrieval formula.
Further, the method for screening the acquired knowledge graph comprises the following steps:
acquiring an enterprise characteristic interval, identifying a chart structure and text data of a knowledge graph to be screened, performing characteristic assignment on the knowledge graph according to the identified chart structure and text data, marking the knowledge graph as matching assignment, marking the knowledge graph to be screened with the matching assignment in the enterprise characteristic interval as a target knowledge graph, deleting a non-target knowledge graph, and marking the target knowledge graph with corresponding characteristic assignment; and finishing the screening of the knowledge graph.
Further, the method for acquiring the enterprise characteristic interval comprises the following steps:
and obtaining historical chart data, historical text induction data and historical knowledge map data of the current enterprise, and performing assignment and induction on the historical chart data, the historical text induction data and the historical knowledge map data to obtain an enterprise characteristic interval.
Further, the method for selecting N target knowledge-maps as classification knowledge-maps in each classification comprises the following steps:
the method comprises the steps of obtaining enterprise characteristic intervals, dividing the enterprise characteristic intervals according to sources of corresponding data in the process of establishing the enterprise characteristic intervals, marking the enterprise characteristic intervals as source intervals, combining the corresponding source intervals according to the classification of target knowledge maps to obtain classification intervals, setting core points of the classification intervals, identifying the matching assignment of the target knowledge maps and the distance between the core points of the classification intervals, marking the core points as deviation distances, sequencing according to the deviation distances, and marking N target knowledge maps before classification arrangement as classification knowledge maps.
Further, the method for establishing the migration index entry according to the map label table comprises the following steps:
identifying data type labels and structural analysis part labels corresponding to knowledge graph templates in a graph label table, integrating the data type labels and the structural analysis part labels corresponding to the knowledge graph template classification, marking the data type labels and the structural analysis part labels as classification integration labels, setting corresponding characteristic index items for the classification integration labels, and integrating all the characteristic index items to obtain a migration index item.
Compared with the prior art, the invention has the beneficial effects that: the further description of the keywords is described through the voice recognition node, the retrieval range can be limited through the further description of the keywords, the problem that the retrieval is particularly difficult because some ideas are easier to write can be solved, and the subsequently obtained knowledge graph retrieval formula is more suitable for the current enterprise situation; the method comprises the steps of analyzing the organization structure and historical data of the current enterprise to obtain a knowledge map template suitable for the current enterprise, and realizing real-time management of data stored in an enterprise database according to the set knowledge map template and a data migration model, so that disordered storage of the stored data is avoided, and the management burden of workers is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a data management method based on a knowledge graph specifically includes:
the method comprises the following steps: identifying the organization architecture of the current enterprise, such as which departments, branch companies, subsidiaries and other organization architectures the current enterprise has, and marking as a single component, wherein the single component refers to the departments, the branch companies, the subsidiaries and other components in the organization architecture; merging the single components to obtain a structural analysis part;
the method for single component merging comprises the following steps:
acquiring a function range and generated data type information of each single component, wherein the function range refers to a duty range and a function range, the data type information comprises information such as a data format, a data purpose and a data source, the data purpose refers to what the corresponding data is used for, such as CAD data used by an engineering department in a construction company, the data purpose is used for drawing, and the data source is CAD drawing software; establishing a knowledge graph library of a current enterprise, identifying application range information of a target knowledge graph in the knowledge graph library, wherein the application range information comprises information such as an application field and an application data type, classifying the target knowledge graph, selecting N target knowledge graphs in each classification as classification knowledge graphs, marking corresponding classification labels, wherein N is a positive integer and is marked as a knowledge graph classification template, matching the function range and the data type information of a single component with the application range information of the knowledge graph classification template, merging the single components belonging to the same knowledge graph classification template classification, and marking the single components as a structure analysis part.
The method for establishing the knowledge map library of the current enterprise comprises the following steps:
acquiring the business range of the current enterprise, integrating the business range and the function range of each single component into range data, extracting keywords in the range data, and performing retraining on the keywords by using the existing extraction algorithm or based on the existing keyword extraction model to enable the keywords to be more suitable for current keyword extraction; the method comprises the steps of setting a voice recognition node, wherein the voice recognition node is used for recognizing voice content of a user, a corresponding manager carries out supplementary narration on extracted keywords through the voice recognition node, recognizes narration content of the manager, establishes a retrieval model, inputs the keywords and the narration content into the retrieval model, obtains a knowledge graph retrieval formula, carries out knowledge graph retrieval according to the obtained knowledge graph retrieval formula, obtains a large number of knowledge graphs, screens the obtained knowledge graphs after being overweight, obtains a target knowledge graph, establishes a first database, inputs the target knowledge graph into the first database, and marks the current first database as a knowledge graph database.
The further description of the keywords is described by the speech recognition node, the retrieval range can be limited by the further description of the keywords, and the problem that some ideas are difficult to write because of the easiness in dictating can be avoided.
The retrieval model is established based on the CNN network or the DNN network, is used for establishing aiming at the corresponding knowledge graph website, is convenient for rapidly retrieving the corresponding knowledge graph, and has common knowledge in the field in the specific establishing and training process, so detailed description is not needed.
The method for screening the acquired knowledge graph comprises the following steps:
obtaining historical chart data, historical text induction data and historical knowledge map data of a current enterprise, and carrying out assignment and induction on the historical chart data, the historical text induction data and the historical knowledge map data to obtain an enterprise characteristic interval; identifying a chart structure and text data of the knowledge graph to be screened, performing characteristic assignment on the knowledge graph according to the identified chart structure and text data, marking the knowledge graph as matching assignment, marking the knowledge graph to be screened with the matching assignment in an enterprise characteristic interval as a target knowledge graph, deleting a non-target knowledge graph, and marking the target knowledge graph with corresponding characteristic assignment; and finishing the screening of the knowledge graph.
The style characteristics of the knowledge graph of the enterprise are analyzed through the historical chart data, the historical text induction data and the historical knowledge graph data, and the knowledge graph more suitable for the enterprise is convenient to manufacture.
The method for assigning and summarizing the historical chart data, the historical text summarization data and the historical knowledge map data comprises the following steps:
an intelligent model is established based on a CNN network or a DNN network, graph data, text induction data, knowledge graph data and correspondingly set enterprise characteristic intervals are used as training sets for training, the corresponding enterprise characteristic intervals are set by expert groups, and the specific establishing and training process is common knowledge in the field, so detailed description is omitted.
The method for performing characteristic assignment on the knowledge graph according to the recognized graph structure and the text data is similar to the method for acquiring the enterprise characteristic interval, and analysis is performed based on a CNN network or DNN network establishing model, so detailed description is not given.
The method for selecting N target knowledge graphs in each classification as classification knowledge graphs comprises the following steps:
the method comprises the steps of obtaining enterprise characteristic intervals, dividing the enterprise characteristic intervals according to sources of corresponding data in the process of establishing the enterprise characteristic intervals, marking the enterprise characteristic intervals as source intervals, combining the corresponding source intervals according to the classification of target knowledge maps to obtain classification intervals, setting core points of the classification intervals, identifying the matching assignment of the target knowledge maps and the distance between the core points of the classification intervals, marking the core points as deviation distances, sequencing according to the deviation distances, and marking N target knowledge maps before classification arrangement as classification knowledge maps.
The core points of all classification intervals are set according to the source data, the styles most suitable for all the functional departments of the current enterprise are determined, and discussion setting is carried out by expert groups.
Step two: acquiring a classification knowledge graph corresponding to each structural analysis part, and manufacturing a knowledge graph template corresponding to the structural analysis part;
the generation of the knowledge-graph template corresponding to the structural analysis section from the classification knowledge-graph is common knowledge in the art and will not be described in detail.
Step three: acquiring a data type and a structure analysis part corresponding to each template part in a knowledge graph template, and marking the template parts with corresponding data type labels and structure analysis part labels;
step four: setting an atlas label table according to the data type labels and the structural analysis part labels of the template parts in the knowledge atlas template;
step five: establishing a migration index item according to the map label table, and establishing a corresponding storage node in the enterprise database according to a characteristic index item contained in the migration index item;
the method for establishing the migration index items according to the atlas label table comprises the following steps:
identifying data type labels and structural analysis part labels corresponding to knowledge graph templates in a graph label table, integrating the data type labels and the structural analysis part labels corresponding to the knowledge graph template classification, marking the data type labels and the structural analysis part labels as classification integration labels, setting corresponding characteristic index items for the classification integration labels, and integrating all the characteristic index items to obtain a migration index item.
The feature index items corresponding to the classified and integrated tags are set according to data type tags and structural analysis part tags, such as CAD tags and engineering part tags, and can be files from the engineering part in a format of 'dwg' corresponding to CAD, and can be adjusted as required.
Step six: and establishing a data migration model in the enterprise database, and migrating the data stored in the enterprise database to the corresponding storage node by the data migration model according to the migration index item. The real-time management of the data stored in the enterprise database is realized, and the unordered storage of the stored data is avoided.
The data migration model is established based on the CNN network or the DNN network, and is trained by establishing a training set according to the migration index item, and the specific establishment and training process is common knowledge in the art, and therefore, detailed description is not given.
The working principle of the invention is as follows: identifying the organization architecture of the current enterprise, marking the organization architecture as a single component, and merging the single components to obtain a structure analysis part; acquiring a classification knowledge graph corresponding to each structural analysis part, and manufacturing a knowledge graph template corresponding to the structural analysis part; acquiring a data type and a structure analysis part corresponding to each template part in a knowledge graph template, and marking the template parts with corresponding data type labels and structure analysis part labels; setting an atlas label table according to the data type labels and the structural analysis part labels of the template parts in the knowledge atlas template; establishing a migration index item according to the map label table, and establishing a corresponding storage node in the enterprise database according to a characteristic index item contained in the migration index item; and establishing a data migration model in the enterprise database, and migrating the data stored in the enterprise database to the corresponding storage node by the data migration model according to the migration index item.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (8)
1. A data management method based on knowledge graph is characterized by comprising the following steps:
the method comprises the following steps: identifying the organization architecture of the current enterprise, marking the organization architecture as a single component, and merging the single components to obtain a structure analysis part;
step two: acquiring a classification knowledge graph corresponding to each structural analysis part, and manufacturing a knowledge graph template corresponding to the structural analysis part;
step three: acquiring a data type and a structure analysis part corresponding to each template part in a knowledge graph template, and marking the template parts with corresponding data type labels and structure analysis part labels;
step four: setting an atlas label table according to the data type labels and the structural analysis part labels of the template parts in the knowledge atlas template;
step five: establishing a migration index item according to the map label table, and establishing a corresponding storage node in the enterprise database according to a characteristic index item contained in the migration index item;
step six: and establishing a data migration model in the enterprise database, and migrating the data stored in the enterprise database to the corresponding storage node by the data migration model according to the migration index item.
2. The method of knowledge-graph-based data management of claim 1, wherein the method of single component consolidation comprises:
acquiring the function range and the generated data type information of each single component, establishing a knowledge graph library of the current enterprise, identifying the application range information of a target knowledge graph in the knowledge graph library, classifying the target knowledge graph, selecting N target knowledge graphs in each classification as classification knowledge graphs, marking corresponding classification labels, marking N as positive integers as a knowledge graph classification template, matching the function range and the data type information of the single component with the application range information of the knowledge graph classification template, combining the single components belonging to the same knowledge graph classification template classification, and marking the single components as a structure analysis part.
3. The knowledge-graph-based data management method of claim 2, wherein the method for establishing the knowledge-graph library of the current enterprise comprises the following steps:
acquiring a knowledge graph retrieval formula, retrieving the knowledge graph according to the acquired knowledge graph retrieval formula to acquire the knowledge graph, screening the acquired knowledge graph to acquire a target knowledge graph, establishing a first database, inputting the target knowledge graph into the first database, and marking the current first database as a knowledge graph database.
4. The method of claim 3, wherein the method of obtaining the knowledge-graph search formula comprises:
the method comprises the steps of obtaining the business range of a current enterprise, integrating the business range and the function range of each single component into range data, extracting key words in the range data, setting voice recognition nodes, enabling corresponding managers to supplement and narrate the extracted key words through the voice recognition nodes, recognizing narration content of the managers, establishing a retrieval model, inputting the key words and the narration content into the retrieval model, and obtaining a knowledge map retrieval formula.
5. The method for data management based on knowledge-graph according to claim 3, wherein the method for screening the acquired knowledge-graph comprises:
acquiring an enterprise characteristic interval, identifying a chart structure and text data of a knowledge graph to be screened, performing characteristic assignment on the knowledge graph according to the identified chart structure and text data, marking the knowledge graph as matching assignment, marking the knowledge graph to be screened with the matching assignment in the enterprise characteristic interval as a target knowledge graph, deleting a non-target knowledge graph, and marking the target knowledge graph with corresponding characteristic assignment; and finishing the screening of the knowledge graph.
6. The method of claim 5, wherein the method of obtaining enterprise characteristic intervals comprises:
obtaining historical chart data, historical text induction data and historical knowledge map data of the current enterprise, and carrying out assignment and induction on the historical chart data, the historical text induction data and the historical knowledge map data to obtain an enterprise characteristic interval.
7. The method of knowledge-graph based data management of claim 5 wherein the method of selecting N target knowledge-graphs for each classification as classification knowledge-graphs comprises:
the method comprises the steps of obtaining enterprise characteristic intervals, dividing the enterprise characteristic intervals according to sources of corresponding data in the process of establishing the enterprise characteristic intervals, marking the enterprise characteristic intervals as source intervals, combining the corresponding source intervals according to the classification of target knowledge maps to obtain classification intervals, setting core points of the classification intervals, identifying the matching assignment of the target knowledge maps and the distance between the core points of the classification intervals, marking the core points as deviation distances, sequencing according to the deviation distances, and marking N target knowledge maps before classification arrangement as classification knowledge maps.
8. The method of claim 5, wherein the method of creating migration index entries according to the graph tag table comprises:
identifying data type labels and structural analysis part labels corresponding to knowledge graph templates in a graph label table, integrating the data type labels and the structural analysis part labels corresponding to the knowledge graph template classification, marking the data type labels and the structural analysis part labels as classification integration labels, setting corresponding characteristic index items for the classification integration labels, and integrating all the characteristic index items to obtain a migration index item.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210261586.1A CN114612071A (en) | 2022-03-16 | 2022-03-16 | Data management method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210261586.1A CN114612071A (en) | 2022-03-16 | 2022-03-16 | Data management method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114612071A true CN114612071A (en) | 2022-06-10 |
Family
ID=81863115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210261586.1A Pending CN114612071A (en) | 2022-03-16 | 2022-03-16 | Data management method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114612071A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996483A (en) * | 2022-08-03 | 2022-09-02 | 国网浙江省电力有限公司信息通信分公司 | Event map data processing method based on variational self-encoder |
-
2022
- 2022-03-16 CN CN202210261586.1A patent/CN114612071A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996483A (en) * | 2022-08-03 | 2022-09-02 | 国网浙江省电力有限公司信息通信分公司 | Event map data processing method based on variational self-encoder |
| CN114996483B (en) * | 2022-08-03 | 2022-10-21 | 国网浙江省电力有限公司信息通信分公司 | Event map data processing method based on variational self-encoder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111708773B (en) | Multi-source scientific and creative resource data fusion method | |
| CN109189942A (en) | A kind of construction method and device of patent data knowledge mapping | |
| CN109492077A (en) | The petrochemical field answering method and system of knowledge based map | |
| CN110825882A (en) | Knowledge graph-based information system management method | |
| CN107705066A (en) | Information input method and electronic equipment during a kind of commodity storage | |
| CN111709235A (en) | Text data statistical analysis system and method based on natural language processing | |
| CN103425740B (en) | A kind of material information search method based on Semantic Clustering of internet of things oriented | |
| CN108664599A (en) | Intelligent answer method, apparatus, intelligent answer server and storage medium | |
| CN113190687B (en) | Knowledge graph determining method and device, computer equipment and storage medium | |
| CN116127090B (en) | Aviation system knowledge graph construction method based on fusion and semi-supervision information extraction | |
| CN114218333A (en) | Geological knowledge map construction method and device, electronic equipment and storage medium | |
| CN114612071A (en) | Data management method based on knowledge graph | |
| CN114911893A (en) | Method and system for automatically constructing knowledge base based on knowledge graph | |
| CN117151659B (en) | Ecological restoration engineering full life cycle tracing method based on large language model | |
| CN110781297A (en) | Classification method of multi-label scientific research papers based on hierarchical discriminant trees | |
| CN111737498A (en) | Domain knowledge base establishing method applied to discrete manufacturing production process | |
| CN116401338A (en) | Design feature extraction and attention mechanism based on data asset intelligent retrieval input and output requirements and method thereof | |
| CN115905705A (en) | Industrial algorithm model recommendation method based on industrial big data | |
| CN115982322A (en) | Water conservancy industry design field knowledge graph retrieval method and retrieval system | |
| CN113076468B (en) | Nested event extraction method based on field pre-training | |
| CN115496830A (en) | Method and device for generating product demand flow chart | |
| CN112668836B (en) | Risk spectrum-oriented associated risk evidence efficient mining and monitoring method and apparatus | |
| CN106649219A (en) | Automatic generation method for communication satellite design documents | |
| Yu et al. | Workflow recommendation based on graph embedding | |
| CN117608545B (en) | Standard operation program generation method based on knowledge graph |
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 |