CN113377905A - Urban brain theory system and platform system based on three-dimensional digital base - Google Patents
Urban brain theory system and platform system based on three-dimensional digital base Download PDFInfo
- Publication number
- CN113377905A CN113377905A CN202110634747.2A CN202110634747A CN113377905A CN 113377905 A CN113377905 A CN 113377905A CN 202110634747 A CN202110634747 A CN 202110634747A CN 113377905 A CN113377905 A CN 113377905A
- Authority
- CN
- China
- Prior art keywords
- module
- entity
- platform
- dimensional digital
- digital base
- 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
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention provides an urban brain theory system and platform system based on a three-dimensional digital base, which comprises the three-dimensional digital base, wherein the three-dimensional digital base comprises a smart fused data middle platform and a space-time big data middle platform, the smart fused data middle platform comprises a service interaction management platform, a data maintenance platform, a service registration management platform and a query analysis module, the query analysis module comprises a semantic extraction module, an entity recognition and extraction module and an entity recognition and relationship extraction combined learning module, the urban brain theory system and platform system based on the three-dimensional digital base is reasonable in design, the query analysis module comprises the semantic extraction module, the entity recognition and extraction module and the entity recognition and relationship extraction combined learning module, text input in various formats and forms can be accurately extracted, and core semantics of a user can be accurately obtained, and then can be accurate quick for the user provides corresponding service, improve user experience and feel.
Description
Technical Field
The invention belongs to the technical field of GIS application, and particularly relates to an urban brain theory system and a platform system based on a three-dimensional digital base.
Background
The method aims at the problems that the department cuts the data, the information is isolated and the information can not be interconnected and intercommunicated in the existing independent information system. The invention provides a city brain theory system and a platform system based on a three-dimensional digital base, which have the advantages that top-level design is needed, the problem of business collaborative fusion and data sharing exchange is solved while the construction of a basic intelligent business application system is guaranteed, a new intelligent island cannot be generated, the city overall three-dimension is constructed, two-three-dimension integration is considered, the one-screen printing-out of one picture is realized by combining the requirements of all business systems, the overall management display is more visual, multi-source data fusion and visualization are facilitated, the external propaganda display and the internal real-time control command are facilitated, in addition, the core semantics of a user are not easily and accurately obtained when the user inputs a text, redundant information can be obtained, and the error rate is further improved.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a city brain theoretical system and a platform system based on a three-dimensional digital base, the city brain theoretical system and the platform system based on the three-dimensional digital base are reasonable in design, a query analysis module of a smart fusion data center comprises a semantic extraction module, an entity recognition and extraction module and an entity recognition and relationship extraction combined learning module, text input in various formats and forms can be accurately extracted, core semantics of a user can be accurately obtained, and then corresponding services can be accurately and rapidly provided for the user, and user experience is improved.
In order to achieve the purpose, the invention is realized by the following technical scheme: the utility model provides a city brain theory system and platform system based on three-dimensional digital base, includes three-dimensional digital base, three-dimensional digital base includes platform in the wisdom amalgamation data and the platform in the big data of space-time, platform includes service interaction management platform, data maintenance platform, service registration management platform and inquiry analysis module in the wisdom amalgamation data, inquiry analysis module includes that semantic extraction module, entity discernment and relation extraction unite the study module, semantic extraction module is used for extracting specific factual information from the text, and the method of machine learning and natural language processing is utilized in the extraction of general information is after extracting specific information from above-mentioned text, preserves in the middle of the database for user's inquiry and use, the route divide into two:
firstly, extracting information from structured and semi-structured data based on a KDD and data mining method;
discovering new knowledge from unstructured open text by adopting a natural language processing and text mining method;
the entity recognition and extraction module comprises an entity recognition module and an open domain entity extraction module, wherein the entity recognition module is used for recognizing seven types of named entities in a text to be processed, namely, a name of a person, a name of an organization, a place name, time, date, currency and percentage, among the seven types, the time, the date, the currency and the percentage have obvious rules relatively, and are relatively easy to recognize, but the remaining three types have high recognition difficulty due to flexible word use, the internal constitution and the external language environment of the named entities have certain characteristics, and the context characteristics of the entities and the internal characteristics of the entities are fully discovered and utilized in any method;
the open domain entity extraction module does not limit the category of extracted texts, has great flexibility, and has the basic idea that the seed words and the target words have the same or similar context in a webpage, including the webpage structure and the context, and a template is required to be extracted by using the seed words firstly, and then more similar entities are extracted by using the template;
the entity identification and relation extraction joint learning module inputs a sentence by adopting a pipeline method, firstly carries out named entity identification, then carries out pairwise combination on the identified entities, carries out relation classification, finally takes the triples with entity relations as input, and combines and learns the triples into an input sentence, and directly obtains the entity triples with the relations through the entity identification and relation extraction joint model.
As a preferred embodiment of the present invention, each type of named entity in the entity identification module has different features, and entities of different types are suitable to use different identification models, such as: name of person: describing its internal composition with a word-based model; place name and organization name: described with a word-based model; meanwhile, the feature weight is calculated by using sequence labeling tools such as MEMM, HMM, CRF and the like.
As a preferred embodiment of the present invention, the database in the semantic extraction module is a structured database.
As a preferred embodiment of the present invention, a mainstream framework of the open domain entity extraction module is: start, seed, decimator/decimate template, candidate, scorer, result.
As a preferred embodiment of the present invention, the text in the semantic extraction module can be structured, semi-structured or unstructured data.
The invention has the beneficial effects that: the invention discloses an urban brain theory system and platform system based on a three-dimensional digital base, which comprises the three-dimensional digital base, a smart fusion data middle platform, a space-time big data middle platform, a service interaction management platform, a data maintenance platform, a service registration management platform, an inquiry analysis module, a semantic extraction module, an entity identification and relationship extraction combined learning module, an entity identification module and an open domain entity extraction module.
1. The three-dimensional digital base of the urban brain theory system and platform system based on the three-dimensional digital base comprises an intelligent fusion data middle platform and a space-time big data middle platform, the construction of a three-dimensional digital base is jointly completed through a space-time big data middle station and a smart fusion data middle station in the data middle station, a basic map support service is provided for applications such as urban comprehensive treatment application, smart city construction and the like, a GIS service capability support is established for each application scene, the construction of the three-dimensional digital base aggregates data and service interfaces of each department to perform business process reconstruction by relying on data storage and data basic management service, has flexible and expandable capability, and provides functions of data fusion aggregation and data service such as data exchange, knowledge map and the like, the method can realize comprehensive application and data sharing of cross-industry, cross-department and cross-region, and provides basic support for intelligent application of various elements of cities.
2. This inquiry analysis module of platform in city brain theoretical system based on three-dimensional digital base and platform system's wisdom fusion data has included semantic extraction module, entity discernment and extraction module and entity discernment and relation extraction joint learning module, and the text input of various formats and form of extraction that can be accurate, the accurate core semantic that obtains the user, and then can be accurate quick provide corresponding service for the user, improve user experience and feel.
Drawings
FIG. 1 is a schematic structural diagram of an urban brain theory system and a platform system based on a three-dimensional digital base;
FIG. 2 is a schematic sectional view of a mounting base of an urban brain theory system and a platform system based on a three-dimensional digital base;
in the figure: 1. a three-dimensional digital base; 2. intelligently fusing data platforms; 3. a space-time big data middle station; 4. a service interaction management platform; 5. a data maintenance platform; 6. a service registration management platform; 7. a query analysis module; 8. a semantic extraction module; 9. an entity identification and extraction module; 10. an entity identification and relation extraction joint learning module; 11. an entity identification module; 12. and an open domain entity extraction module.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
Referring to fig. 1 to 2, the present invention provides a technical solution: the utility model provides a three-dimensional digital base based city brain theory system and platform system, includes three-dimensional digital base 1, three-dimensional digital base 1 includes platform 2 in the wisdom amalgamation data and platform 3 in the big data of space-time, platform 2 includes service interaction management platform 4, data maintenance platform 5, service registration management platform 6 and inquiry analysis module 7 in the wisdom amalgamation data, inquiry analysis module 7 includes semantic extraction module 8, entity discernment and extraction module 9, entity discernment and relation extraction joint learning module 10, semantic extraction module 8 is used for extracting specific factual information from the text, and the method of machine learning and natural language processing is utilized in the extraction of general information after extracting specific information from above-mentioned text, preserves in the middle of the database for user's inquiry and use, and the route divide into two:
firstly, extracting information from structured and semi-structured data based on a KDD and data mining method;
discovering new knowledge from unstructured open text by adopting a natural language processing and text mining method;
the entity recognition and extraction module 9 comprises an entity recognition module 11 and an open domain entity extraction module 12, wherein the entity recognition module 11 is used for recognizing seven types of named entities in the text to be processed, including name of a person, name of an organization, name of a place, time, date, currency and percentage, among the seven types, the time, the date, the currency and the percentage have obvious rules relatively to the composition, and are relatively easy to recognize, but the remaining three types have great recognition difficulty due to flexible use of words, the internal composition and the external language environment of the named entities have some characteristics, and the context characteristics of the entities and the internal characteristics of the entities are fully discovered and utilized in any method;
the open domain entity extraction module 12 does not limit the category of extracted text, and has great flexibility, and the basic idea is that the seed word and the target word have the same or similar context in the webpage, including the webpage structure and context, and the template needs to be extracted by using the seed word first, and then more similar entities are extracted by using the template;
the entity identification and relationship extraction joint learning module 10 inputs a sentence by adopting a pipeline method, firstly carries out named entity identification, then carries out pairwise combination on the identified entities, carries out relationship classification, finally takes the triples with entity relationship as input, combines and learns into an input sentence, and directly obtains the entity triples with relationship through an entity identification and relationship extraction joint model.
As a preferred embodiment of the present invention, each named entity in the entity identification module 11 has different features, and entities in different classes are suitable to use different identification models, such as: name of person: describing its internal composition with a word-based model; place name and organization name: described with a word-based model; meanwhile, the feature weight is calculated by using sequence labeling tools such as MEMM, HMM, CRF and the like.
As a preferred embodiment of the present invention, the database in the semantic extraction module is a structured database.
As a preferred embodiment of the present invention, the main flow framework of the open domain entity extraction module 12 is: start, seed, decimator/decimate template, candidate, scorer, result.
As a preferred embodiment of the present invention, the text in the semantic extraction module 8 may be structured, semi-structured or unstructured data.
As a preferred embodiment of the invention, the three-dimensional digital base 1 comprises a smart fused data middle platform 2 and a space-time big data middle platform 3, the construction of the three-dimensional digital base 1 is completed together through the space-time big data middle platform 3 and the smart fused data middle platform 2 in the data middle platform, basic map support services are provided for applications such as urban comprehensive management application, smart city construction and the like, GIS service capability support is established for each application scene, the construction of the three-dimensional digital base 1 is realized by converging data and service interfaces of each department and performing business flow reconstruction by relying on data storage and data basic management service, the three-dimensional digital base has elastic expandable capability, the functions of data fusion convergence and data service such as data exchange and knowledge map are provided, the comprehensive application and data sharing of cross-industry, cross-department and cross region can be realized, and the basic support is provided for the smart application of each element of the city, the query analysis module 7 of the intelligent fusion data center 2 comprises a semantic extraction module 8, an entity identification and extraction module 9, and an entity identification and relationship extraction combined learning module 10, so that text input in various formats and forms can be accurately extracted, core semantics of a user can be accurately acquired, corresponding services can be accurately and quickly provided for the user, and user experience is improved.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (5)
1. A city brain theory system and platform system based on a three-dimensional digital base comprises a three-dimensional digital base (1) and is characterized in that the three-dimensional digital base (1) comprises a smart fused data center (2) and a space-time big data center (3), the smart fused data center (2) comprises a service interaction management platform (4), a data maintenance platform (5), a service registration management platform (6) and a query analysis module (7), the query analysis module (7) comprises a semantic extraction module (8), an entity recognition and extraction module (9) and an entity recognition and relationship extraction combined learning module (10), the semantic extraction module (8) is used for extracting specific fact information from a text, and after the specific information is extracted from the text by using methods of machine learning and natural language processing in the conventional information extraction, the route is divided into two routes:
firstly, extracting information from structured and semi-structured data based on a KDD and data mining method;
discovering new knowledge from unstructured open text by adopting a natural language processing and text mining method;
the entity recognition and extraction module (9) comprises an entity recognition module (11) and an open domain entity extraction module (12), wherein the entity recognition module (11) is used for recognizing seven types of named entities in a text to be processed, namely, a person name, an organization name, a place name, time, date, currency and percentage, wherein the seven types of named entities have obvious rules in time, date, currency and percentage and are relatively easy to recognize, but the remaining three types of named entities have great recognition difficulty due to flexible word usage, the internal constitution and the external language environment of the named entities have certain characteristics, and the context characteristics of the entities and the internal characteristics of the entities are fully discovered and utilized in any method;
the open domain entity extraction module (12) does not limit the category of extracted text, has great flexibility, and has the basic idea that the seed words and the target words have the same or similar context in a webpage, including the webpage structure and the context, and a template needs to be extracted by the seed words first, and then more similar entities are extracted by the template;
the entity identification and relation extraction combined learning module (10) inputs a sentence by adopting a pipeline method, firstly carries out named entity identification, then carries out pairwise combination on the identified entities, carries out relation classification, finally takes the triples with entity relations as input, combines and learns into an input sentence, and directly obtains the entity triples with the relations through an entity identification and relation extraction combined model.
2. The urban brain theory system and platform system based on the three-dimensional digital base as claimed in claim 1, wherein: each type of named entity in the entity recognition module (11) has different characteristics, and different types of entities are suitable to use different recognition models, such as: name of person: describing its internal composition with a word-based model; place name and organization name: described with a word-based model; meanwhile, the feature weight is calculated by using sequence labeling tools such as MEMM, HMM, CRF and the like.
3. The urban brain theory system and platform system based on the three-dimensional digital base as claimed in claim 1, wherein: and the database in the semantic extraction module is a structured database.
4. The urban brain theory system and platform system based on the three-dimensional digital base as claimed in claim 1, wherein: the main flow framework of the open domain entity extraction module (12) is as follows: start, seed, decimator/decimate template, candidate, scorer, result.
5. The urban brain theory system and platform system based on the three-dimensional digital base as claimed in claim 1, wherein: the text in the semantic extraction module (8) can be structured, semi-structured or unstructured data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110634747.2A CN113377905A (en) | 2021-06-08 | 2021-06-08 | Urban brain theory system and platform system based on three-dimensional digital base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110634747.2A CN113377905A (en) | 2021-06-08 | 2021-06-08 | Urban brain theory system and platform system based on three-dimensional digital base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113377905A true CN113377905A (en) | 2021-09-10 |
Family
ID=77576265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110634747.2A Pending CN113377905A (en) | 2021-06-08 | 2021-06-08 | Urban brain theory system and platform system based on three-dimensional digital base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113377905A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114428991A (en) * | 2022-03-31 | 2022-05-03 | 成都柔水科技有限公司 | Internet of things perception data display method based on CIM digital base |
-
2021
- 2021-06-08 CN CN202110634747.2A patent/CN113377905A/en active Pending
Non-Patent Citations (3)
| Title |
|---|
| WITTPENG: "语义抽取学习与实践", 《HTTPS://WWW.CNBLOGS.COM/WITTPENG/P/9084981.HTML》 * |
| 匿名: "时空大数据平台，构建智慧城市数字底盘"", 《HTTPS://WWW.QXWZ.COM/ZIXUN/4944432027》 * |
| 本刊编辑部: "阿里云大数据赋能城市智慧", 《劳动保护》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114428991A (en) * | 2022-03-31 | 2022-05-03 | 成都柔水科技有限公司 | Internet of things perception data display method based on CIM digital base |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112131275B (en) | Enterprise portrait construction method of holographic city big data model and knowledge graph | |
| CN112329467B (en) | Address recognition method and device, electronic equipment and storage medium | |
| CN110472066B (en) | Construction method of urban geographic semantic knowledge map | |
| Toor et al. | Transportation and sustainable campus communities: Issues, examples, solutions | |
| CN104183166A (en) | Integration electronic lesson preparation system and method | |
| CN107943810A (en) | The construction method of building information map | |
| CN107562451A (en) | A kind of local chronicle document method for visualizing based on WebGIS | |
| Tulić Ceballos | The impact of web 3.0 technologies on tourism information systems | |
| CN113377905A (en) | Urban brain theory system and platform system based on three-dimensional digital base | |
| CN116340541A (en) | Method for constructing knowledge graph system of Wenbo | |
| Lüpke et al. | Language contact in West Africa | |
| Kumar et al. | Information and communication technology for improving livelihoods of tribal community in India | |
| CN112329450A (en) | Insurance medical code mapping dictionary table production method | |
| Masser | The Regional Research Laboratory initiative A progress report | |
| Meirelles | Visualizing data: new pedagogical challenges | |
| CN115757720A (en) | Project information searching method, device, equipment and medium based on knowledge graph | |
| Zhang et al. | Research on the construction of geographic knowledge graph integrating natural disaster information | |
| Teles et al. | Automatic generation of human-like route descriptions: a corpus-driven approach | |
| Coelho et al. | Online platform for case studies in smart cities | |
| CN110781283A (en) | Chain brand word bank generation method and device and electronic equipment | |
| CN110008340A (en) | A kind of multi-source text knowledge indicates, obtains and emerging system | |
| CN109977419A (en) | A kind of knowledge mapping building system | |
| Barrett | Picturing Chinese science: wartime photographs in Joseph Needham's science diplomacy | |
| Stoltenberg et al. | Geolocalization of digital data | |
| CN105260407A (en) | Generation system of cross border tour map |
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 |