CN116383402A - Intelligent travel map construction method based on graph analysis model - Google Patents
Intelligent travel map construction method based on graph analysis model Download PDFInfo
- Publication number
- CN116383402A CN116383402A CN202310229499.2A CN202310229499A CN116383402A CN 116383402 A CN116383402 A CN 116383402A CN 202310229499 A CN202310229499 A CN 202310229499A CN 116383402 A CN116383402 A CN 116383402A
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge
- map
- model
- travel
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 35
- 238000010276 construction Methods 0.000 title claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims description 44
- 238000002372 labelling Methods 0.000 claims description 27
- 238000007726 management method Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 20
- 230000004927 fusion Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 10
- 238000013136 deep learning model Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000013499 data model Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000008676 import Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010225 co-occurrence analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent travel map construction method based on a map analysis model, which comprises the following steps of: s1, acquiring and analyzing a business flow and business data of a passenger travel system, combing travel venation, and constructing a business model; s2, analyzing the service model to obtain service requirements, and matching a knowledge system framework according to the service requirements; s3, analyzing the identifiable relationship type and entity type according to the travel context, designing a travel pattern system based on the matched knowledge system frame, and constructing a travel pattern model; s4, grabbing multi-source heterogeneous data sources according to a knowledge system framework; s5, extracting and fusing the structured data, the semi-structured data and the unstructured data by adopting a map module, and storing the extracted and fused structured data, the semi-structured data and the unstructured data into a map database in a map form to construct a map library; and S6, carrying out graph analysis and graph calculation on the graph library through a network algorithm, and constructing a travel graph.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent travel map construction method based on a map analysis model.
Background
The knowledge graph is a modern theory which combines the theory and method of subjects such as application mathematics, graphics, information visualization technology, information science and the like with the method of metering introduction analysis, co-occurrence analysis and the like, and utilizes the visualized graph to vividly display the core structure, development history, leading edge field and overall knowledge architecture of the subjects to achieve the aim of multi-subject fusion.
As an important branch of new generation artificial intelligence technology, knowledge maps are often used to fuse multi-source data to build large-scale knowledge bases. In the intelligent traffic field, the construction of traffic knowledge graph can facilitate the inquiry and statistics of traffic data on one hand, and can provide abundant knowledge and more diversified information for traffic situation analysis and prediction on the other hand.
Along with the development of intelligent traffic, the data in the traffic field presents explosive growth, and the data types in the travel field are various, including videos, pictures, geographic position information, sensor data and the like, and the intelligent travel platform has the characteristics of multiple data structures, has the continuously increased requirement on data fusion capability, and is important to construct the intelligent travel platform by fusing multiple source data and introducing knowledge. In addition, the analysis of the research object is carried out between mass entity relations of the knowledge graph, the workload is large, the subjective judgment is excessively depended, and the problem needs to be solved by means of intelligent labeling and model capability.
Disclosure of Invention
The invention aims to provide an intelligent travel map construction method based on a map analysis model, which is used for solving the problems.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an intelligent travel map construction method based on a map analysis model comprises the following steps:
s1, acquiring and analyzing a business flow and business data of a passenger travel system, combing travel venation, and constructing a business model;
s2, analyzing the service model to obtain service requirements, and matching a knowledge system framework according to the service requirements;
s3, analyzing the identifiable relationship type and entity type according to the travel context, designing a travel pattern system based on the matched knowledge system framework, constructing a travel pattern model, and defining the entity, relationship and attribute under the travel system;
s4, grabbing the multi-source heterogeneous data sources according to a knowledge system framework, and converting the multi-source heterogeneous data sources into structured data, semi-structured data and unstructured data;
s5, extracting and fusing the structured data, the semi-structured data and the unstructured data by adopting a map module, storing the extracted and fused data into a map database in a map form, and constructing a map library according to a map model;
and S6, carrying out graph analysis and graph calculation on the graph library through a network algorithm, and constructing a travel graph.
Preferably, the map module comprises a data source processing unit, a data lake management unit, a knowledge modeling unit, a knowledge management unit, a knowledge calculation unit, a knowledge quality unit, a knowledge application unit and a text extraction unit; the data source processing unit performs data cleaning, conversion and mapping on the structured data, the semi-structured data and the unstructured data through a tool provided by the data processing layer; the data lake management unit is used for data set management, file management, data synchronization, data processing, operation log and authority management; the knowledge modeling unit is used for establishing a data model of the knowledge graph; the knowledge management unit is used for storing and managing map data; the knowledge calculation unit is used for carrying out capability output on the knowledge graph and providing fusion, indexing, reasoning and complex graph calculation functions; the knowledge quality unit is used for displaying map quality monitoring, data lake error data and map entering conflict data; the knowledge application unit is used for providing a front-end application component and can directly use or integrate to perform visual exploration, analysis and excavation of the atlas; the text extraction unit is used for providing text knowledge structuring full-flow capacity of corpus uploading, data labeling, quality inspection management, on-line parameter adjustment training production models and model reasoning prediction services.
Preferably, the data model of the knowledge graph includes a schema definition, a schema view, a property group, a schema specification, an import export, an automatic concept specification, and an automatic property specification.
Preferably, the front-end application component includes an edit view, a graph exploration, a time series exploration, a path discovery, an association relationship, an entity tag, a time series path discovery, a time series association relationship, and a graph analysis Pro.
Preferably, the text extraction unit comprises corpus labeling and model training; the corpus labeling is used for labeling and managing the corpus and comprises a text extraction mode, an event extraction mode, a text classification mode and machine reading understanding; the model training comprises deep learning model capability and rule model capability, wherein the deep learning model capability is used for managing a deep learning model generated by training a deep learning algorithm provided by a platform, supporting training of entity recognition, attribute recognition, relation extraction, event extraction, sentence-level text classification, chapter-level text classification and machine reading understanding models, and the rule model capability is used for configuring rules extracted by a formed scheme into a system, realizing text content extraction according to the available configured rules, and supporting entity recognition, attribute recognition, relation extraction and creation of event extraction models.
Preferably, the corpus labeling specifically comprises the following steps:
a1, constructing a labeling mode;
a2, labeling and anticipating the components;
a3, importing the mode into a corpus mode;
a4, uploading the corpus.
Preferably, in step S3, the construction process of the travel map model further includes knowledge iterative update, where the knowledge iterative update specifically includes the following steps:
b1, knowledge extraction is carried out according to concept graphs to capture different data sources;
b2, knowledge fusion is conducted on knowledge fusion through algorithm guidance of entity merging, concept merging and relation extraction;
and B3, carrying out ontology extraction, knowledge reasoning and quality assessment on knowledge processing to obtain a structured and networked knowledge system.
Preferably, the travel map model comprises a viscosity model based on passenger affinity, a passenger relationship presumption model and an influence model based on passenger value.
Preferably, the construction of the map library in step S5 includes entity extraction and relationship identification.
After the technical scheme is adopted, compared with the background technology, the invention has the following beneficial effects:
the invention provides an intelligent travel map construction method based on a map analysis model, which is used for constructing a travel map of passengers, identifying the relative relationship and the absolute relationship among the passengers, researching a viscosity model based on intimacy analysis of the passenger relationship, researching an influence model based on value analysis of a map network and providing basis for individual product recommendation and directional information pushing. The method solves the problem of fusion of multi-source data, extracts the relationship among entities from massive multi-source heterogeneous data, compiles the entity data based on a knowledge reasoning model, and mines potential association relationship between two traffic entities so as to enrich knowledge contained in a knowledge graph, provide corpus labeling and model training capability to be applied to the technical field of intelligent transportation, realize automatic construction and model analysis of traffic knowledge graph, and reduce the workload of graph construction and analysis.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Examples
The invention discloses an intelligent travel map construction method based on a map analysis model, which is shown in a figure 1, and comprises the following steps of:
s1, acquiring and analyzing business processes and business data of a passenger travel system, combing travel venation, including before travel, during travel and after travel, and constructing a business model;
s2, analyzing the service model to obtain service requirements, and matching a knowledge system framework according to the service requirements;
s3, analyzing the identifiable relationship type and entity type according to the travel context, designing a travel pattern system based on the matched knowledge system framework, constructing a travel pattern model, and defining the entity, relationship and attribute under the travel system;
s4, grabbing the multi-source heterogeneous data sources according to a knowledge system framework, and converting the multi-source heterogeneous data sources into structured data, semi-structured data and unstructured data; and extracting concepts, entities, attributes, relations and interrelationships among the entities from various data sources, and forming an ontology knowledge expression on the basis of the concepts, the entities, the attributes, the relations and the interrelationships among the entities.
S5, extracting and fusing the structured data, the semi-structured data and the unstructured data by adopting a map module, researching and storing massive entity (node), relation (side) and attribute data in a map form, storing the entity (node), relation (side) and attribute data into a map database, and constructing a map library according to the map model;
and S6, carrying out graph analysis and graph calculation on the graph library through a network algorithm, constructing a travel graph, providing application of multiple capabilities, multiple industries and multiple scenes for users, reflecting the ideas of data management and semantic connection, and being beneficial to the utilization and migration of large-scale data.
The map module comprises a data source processing unit, a data lake management unit, a knowledge modeling unit, a knowledge management unit, a knowledge calculation unit, a knowledge quality unit, a knowledge application unit and a text extraction unit. The data source processing unit performs data cleaning, conversion and mapping on the structured data, the semi-structured data and the unstructured data through a tool provided by the data processing layer, and performs management, processing and auditing on the source data. The structured data includes database data such as MySQL, oracle, etc., and structured files such as Excel, csv, json. The semi-structured data comprises HTML web page data, and the unstructured data comprises multi-modal data such as text files, pictures, audio, video, and the like.
The data lake management unit is used for data set management, file management, data synchronization, data processing, operation log and authority management. Providing the functions of creating, viewing and editing data sets and tables, supporting connection with an external database, supporting remote mounting of database tables and supporting file importing data; the data synchronization is provided for synchronizing the table data of the multi-source database to the local database in the form of tasks, so that the floor operation of the remote data table is realized; the data processing is used for configuring data processing operation in a dragging mode, cleaning and converting service data to form structured data which can be used for mapping, and providing task creation, task configuration, task execution and state viewing functions.
The knowledge modeling unit is used for establishing a data model of the knowledge graph. Providing a unified knowledge representation model of concept-entity-attribute-relation-event-rule-link, establishing a data model of a knowledge graph, namely constructing an ontology model to describe knowledge, supporting definition of graph elements such as concept, attribute, relation and the like by means of real-time editing and template file importing, visualizing modeling results, providing concept protocol and attribute protocol functions based on entity information in the graph, and realizing data-driven post modeling.
The knowledge management unit is used for storing and managing map data and is in seamless connection with main stream big data computing products in the industry. The knowledge management is a process of evolution and perfecting of the knowledge graph in the whole industry aiming at the continuously-occurring knowledge of the same type and the added new knowledge source after the first construction of the knowledge graph is completed. Knowledge management comprises entity editing, relation editing, knowledge representation, map query, knowledge tracing, import and export, and offline graph entering D2R functions. Aiming at map data access, services such as online editing, file importing and the like are provided, and incremental construction of knowledge maps is realized; aiming at map data management, functions such as map data viewing, map language query, knowledge tracing and the like are provided.
The knowledge calculation unit is used for carrying out capability output on the knowledge graph and providing fusion, indexing, reasoning and complex graph calculation functions. Knowledge calculation provides functions of online fusion, online indexing, online reasoning, automatic fusion, automatic indexing, complex graph analysis, rule calculation reasoning and neural network reasoning. The knowledge redundancy is reduced through entity fusion, and the knowledge quality is improved; extending the knowledge range through entity indexing multi-mode data, entity attributes and relationship reasoning; and analyzing and checking the clustering distribution condition of the map data through the complex graph.
The knowledge quality unit is used for displaying map quality monitoring, data lake error data and map entering conflict data. And monitoring and displaying statistical information of the knowledge graph and knowledge quality indexes, wherein the statistical information comprises graph concepts, entities, attributes and quantity statistics and distribution of relations, and the quality indexes comprise mode integrity and knowledge confidence. And providing the floor storage of error and conflict data in the offline D2R mapping task of the data set data, and supporting the repayment of the mapping after the error and conflict data are modified.
The knowledge application unit is used for providing a front-end application component and can directly use or integrate to perform visual exploration, analysis and mining of the atlas. The front-end application components include edit views, graph exploration, time sequence exploration, path discovery, association, entity tags, time sequence path discovery, time sequence association, and graph analysis Pro.
The text extraction unit is used for providing text knowledge structuring full-flow capacity of corpus uploading, data labeling, quality inspection management, on-line parameter adjustment training production model and model reasoning prediction service.
The data model of the knowledge graph includes pattern definition, pattern view, attribute grouping, pattern specification, import and export, automatic concept specification, and automatic attribute specification.
The text extraction unit comprises corpus labeling and model training. The corpus labeling is used for labeling and managing the corpus, and comprises a text extraction mode, an event extraction mode, a text classification mode and machine reading understanding, labeling is carried out on the corpus of a defined mode label, nested labeling is supported, the corpus mode, corpus quality inspection and labeling statistics of the current corpus set version can be managed, and intelligent labeling is supported on the corpus in a ready state. The model training comprises deep learning model capability and rule model capability, wherein the deep learning model capability is used for managing a deep learning model generated by training a deep learning algorithm provided by a platform, supporting training of entity recognition, attribute recognition, relation extraction, event extraction, sentence-level text classification, chapter-level text classification and machine reading understanding models, and the rule model capability is used for configuring rules extracted by a formed scheme into a system, realizing content extraction of texts according to the available configured rules, and supporting the entity recognition, attribute recognition, relation extraction and creation of event extraction models.
The corpus labeling specifically comprises the following steps:
a1, constructing a labeling mode;
a2, labeling and anticipating the components;
a3, importing the mode into a corpus mode;
a4, uploading the corpus.
In the step S3, the construction process of the travel map model further comprises knowledge iteration updating, each round of iteration updating carries out knowledge extraction, knowledge fusion and knowledge processing, and the knowledge iteration updating specifically comprises the following steps:
b1, knowledge extraction is carried out according to concept graphs to capture different data sources;
b2, knowledge fusion is conducted on knowledge fusion through algorithm guidance of entity merging, concept merging and relation extraction;
and B3, carrying out ontology extraction, knowledge reasoning and quality assessment on knowledge processing to obtain a structured and networked knowledge system.
The travel pattern model comprises a viscosity model based on the passenger affinity, a passenger relationship presumption model and an influence model based on the passenger value.
The construction of the map library in the step S5 comprises entity extraction and relationship identification. Entity extraction researches extract entities such as people, shifts, airplanes/motor cars, stations and the like according to travel characteristics; the relation identification research identifies the relative relation such as the ticket booking relation (ticket booking number), the travel relation (flight booking machine or group booking), the beneficiary relation (beneficiary and beneficiary), the agency relation (agent and agent) and the like according to travel characteristics, and records the occurrence frequency and time sequence of the relation; and (3) studying and reasoning to identify absolute relations (namely social relations) of families, relatives, colleagues, friends and the like by combining the graph relations, and defining weight according to the intimacy degree. After new knowledge is obtained, it needs to be integrated to resolve contradictions and ambiguities, such as that some entities may have multiple expressions, a particular designation may correspond to multiple different entities, etc. For the new knowledge after fusion, the qualified part can be added into the knowledge base after quality evaluation (part needs to be manually screened) so as to ensure the quality of the knowledge base.
The application of the travel map constructed in the step S6 comprises the following steps of
(1) A viscosity model based on passenger affinity is created. The viscosity reflects the relativity and sparsity of users in the travel network, and the viscosity value among passengers is calculated by combining the relative relation with frequency and time sequence characteristics and the absolute relation with weight characteristics among passengers. Providing basis for personalized services, such as family ticket package recommendation, group protection of abnormal flights, and the like.
(2) Absolute relationship reasoning. The study combines symmetry and transitivity of the relationship according to travel relationship network and user characteristics (name, birth time, address, company, etc.), builds a relationship presumption model, and recognizes and presumes absolute relationships such as family, relatives, colleagues, friends, etc.
(3) An impact model based on the value of the passenger is created. The influence reflects the degree of value of the user in the travel network. According to travel patterns (a strong-communication aperiodic directed graph containing n nodes) and graph network analysis and PageRank algorithm, an influence model is built, tour guides, key users or high-value users can be identified, and basis is provided for accurate recommendation.
(4) The travel map and the deep learning method are combined, and the method can be used for predicting urban road traffic situation, creating urban intelligent parking nascent state, predicting traffic/network lane road illegal behaviors and other application scenes, and the knowledge map is combined to excavate diversified spatial relations, so that more abundant space-time information is considered in traffic prediction.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (9)
1. The intelligent travel map construction method based on the graph analysis model is characterized by comprising the following steps of:
s1, acquiring and analyzing a business flow and business data of a passenger travel system, combing travel venation, and constructing a business model;
s2, analyzing the service model to obtain service requirements, and matching a knowledge system framework according to the service requirements;
s3, analyzing the identifiable relationship type and entity type according to the travel context, designing a travel pattern system based on the matched knowledge system framework, constructing a travel pattern model, and defining the entity, relationship and attribute under the travel system;
s4, grabbing the multi-source heterogeneous data sources according to a knowledge system framework, and converting the multi-source heterogeneous data sources into structured data, semi-structured data and unstructured data;
s5, extracting and fusing the structured data, the semi-structured data and the unstructured data by adopting a map module, storing the extracted and fused data into a map database in a map form, and constructing a map library according to a map model;
and S6, carrying out graph analysis and graph calculation on the graph library through a network algorithm, and constructing a travel graph.
2. The intelligent travel map construction method based on the map analysis model as claimed in claim 1, wherein: the map module comprises a data source processing unit, a data lake management unit, a knowledge modeling unit, a knowledge management unit, a knowledge calculation unit, a knowledge quality unit, a knowledge application unit and a text extraction unit; the data source processing unit performs data cleaning, conversion and mapping on the structured data, the semi-structured data and the unstructured data through a tool provided by the data processing layer; the data lake management unit is used for data set management, file management, data synchronization, data processing, operation log and authority management; the knowledge modeling unit is used for establishing a data model of the knowledge graph; the knowledge management unit is used for storing and managing map data; the knowledge calculation unit is used for carrying out capability output on the knowledge graph and providing fusion, indexing, reasoning and complex graph calculation functions; the knowledge quality unit is used for displaying map quality monitoring, data lake error data and map entering conflict data; the knowledge application unit is used for providing a front-end application component and can directly use or integrate to perform visual exploration, analysis and excavation of the atlas; the text extraction unit is used for providing text knowledge structuring full-flow capacity of corpus uploading, data labeling, quality inspection management, on-line parameter adjustment training production models and model reasoning prediction services.
3. The intelligent travel map construction method based on the map analysis model as claimed in claim 2, wherein: the data model of the knowledge graph comprises mode definition, mode view, attribute grouping, mode specification, import and export, automatic concept specification and automatic attribute specification.
4. The intelligent travel map construction method based on the map analysis model as claimed in claim 2, wherein: the front-end application components include edit views, graph exploration, time sequence exploration, path discovery, association, entity tags, time sequence path discovery, time sequence association and graph analysis Pro.
5. The intelligent travel map construction method based on the map analysis model as claimed in claim 2, wherein: the text extraction unit comprises corpus labeling and model training; the corpus labeling is used for labeling and managing the corpus and comprises a text extraction mode, an event extraction mode, a text classification mode and machine reading understanding; the model training comprises deep learning model capability and rule model capability, wherein the deep learning model capability is used for managing a deep learning model generated by training a deep learning algorithm provided by a platform, supporting training of entity recognition, attribute recognition, relation extraction, event extraction, sentence-level text classification, chapter-level text classification and machine reading understanding models, and the rule model capability is used for configuring rules extracted by a formed scheme into a system, realizing text content extraction according to the available configured rules, and supporting entity recognition, attribute recognition, relation extraction and creation of event extraction models.
6. The intelligent travel map construction method based on the map analysis model as claimed in claim 5, wherein: the corpus labeling specifically comprises the following steps:
a1, constructing a labeling mode;
a2, labeling and anticipating the components;
a3, importing the mode into a corpus mode;
a4, uploading the corpus.
7. The intelligent travel map construction method based on the map analysis model as claimed in claim 1, wherein: the construction process of the travel map model in the step S3 further comprises knowledge iteration update, and the knowledge iteration update specifically comprises the following steps:
b1, knowledge extraction is carried out according to concept graphs to capture different data sources;
b2, knowledge fusion is conducted on knowledge fusion through algorithm guidance of entity merging, concept merging and relation extraction;
and B3, carrying out ontology extraction, knowledge reasoning and quality assessment on knowledge processing to obtain a structured and networked knowledge system.
8. The intelligent travel map construction method based on the map analysis model as claimed in claim 1, wherein: the travel map model comprises a viscosity model based on passenger affinity, a passenger relationship presumption model and an influence model based on passenger value.
9. The intelligent travel map construction method based on the map analysis model as claimed in claim 1, wherein: the construction of the map library in the step S5 comprises entity extraction and relationship identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310229499.2A CN116383402A (en) | 2023-03-10 | 2023-03-10 | Intelligent travel map construction method based on graph analysis model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310229499.2A CN116383402A (en) | 2023-03-10 | 2023-03-10 | Intelligent travel map construction method based on graph analysis model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116383402A true CN116383402A (en) | 2023-07-04 |
Family
ID=86964813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310229499.2A Pending CN116383402A (en) | 2023-03-10 | 2023-03-10 | Intelligent travel map construction method based on graph analysis model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116383402A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116911386A (en) * | 2023-09-12 | 2023-10-20 | 中国长江电力股份有限公司 | Knowledge graph construction method of hydroelectric equipment based on knowledge context service-oriented scene |
| CN117235279A (en) * | 2023-09-04 | 2023-12-15 | 上海歆广数据科技有限公司 | Critical task development framework integrating large voice model and knowledge graph |
-
2023
- 2023-03-10 CN CN202310229499.2A patent/CN116383402A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235279A (en) * | 2023-09-04 | 2023-12-15 | 上海歆广数据科技有限公司 | Critical task development framework integrating large voice model and knowledge graph |
| CN117235279B (en) * | 2023-09-04 | 2024-03-19 | 上海峻思寰宇数据科技有限公司 | Critical task development system integrating large language model and knowledge graph |
| CN116911386A (en) * | 2023-09-12 | 2023-10-20 | 中国长江电力股份有限公司 | Knowledge graph construction method of hydroelectric equipment based on knowledge context service-oriented scene |
| CN116911386B (en) * | 2023-09-12 | 2023-11-28 | 中国长江电力股份有限公司 | Knowledge graph construction method of hydroelectric equipment based on knowledge context service-oriented scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112612902B (en) | Knowledge graph construction method and device for power grid main equipment | |
| CN116383402A (en) | Intelligent travel map construction method based on graph analysis model | |
| CN105183869B (en) | Building knowledge mapping database and its construction method | |
| CN109410650B (en) | Scene and semantic-based information aggregation method for whole system information management | |
| Wang et al. | Big trajectory data mining: A survey of methods, applications, and services | |
| Keller | Ontologies for aviation data management | |
| Tan et al. | Research on the construction of a knowledge graph and knowledge reasoning model in the field of urban traffic | |
| Vasconcelos et al. | Smartphone-based outlier detection: a complex event processing approach for driving behavior detection | |
| Shen et al. | Dynamic knowledge modeling and fusion method for custom apparel production process based on knowledge graph | |
| Höpken et al. | Tourism knowledge destination | |
| Zhu et al. | Data integration to create large-scale spatially detailed synthetic populations | |
| Masoumi et al. | City Digital Twins: their maturity level and differentiation from 3D city models | |
| CN115271369A (en) | Equipment information management method, system and storage medium based on knowledge graph | |
| CN114746815A (en) | Method for creating a digital twin of a facility or device | |
| CN115640406A (en) | Multi-source heterogeneous big data analysis processing and knowledge graph construction method | |
| Grangel-González et al. | Analyzing a knowledge graph of industry 4.0 standards | |
| Yahya et al. | A benchmark dataset with Knowledge Graph generation for Industry 4.0 production lines | |
| Lecue et al. | Explaining and predicting abnormal expenses at large scale using knowledge graph based reasoning | |
| Mirarchi | Knowledge network for innovation of construction sector: increasing efficiency through process digitisation of the entire chain | |
| Bai et al. | Development of ontology-based information system using formal concept analysis and association rules | |
| Khruahong et al. | Social media analytics in comments of multiple vehicle brands on social networking sites in Thailand | |
| Sonje et al. | draw2code: Ai based auto web page generation from hand-drawn page mock-up | |
| Wei et al. | A Data-Driven Human–Machine Collaborative Product Design System Toward Intelligent Manufacturing | |
| Prakash et al. | Domain Interoperability for iot application through knowledge extraction | |
| Chen et al. | [Retracted] Automatic Mining Method of Group Behavior Patterns Based on Incremental Spatiotemporal Trajectory Big Data |
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 |