CN112784057A - Three-network industrial map construction method based on regional industrial enterprises - Google Patents
Three-network industrial map construction method based on regional industrial enterprises Download PDFInfo
- Publication number
- CN112784057A CN112784057A CN202110029149.2A CN202110029149A CN112784057A CN 112784057 A CN112784057 A CN 112784057A CN 202110029149 A CN202110029149 A CN 202110029149A CN 112784057 A CN112784057 A CN 112784057A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- industry
- network
- associated network
- representing
- 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.)
- Granted
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
- G06F16/36—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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a three-network industrial map construction method based on regional industrial enterprises. The method comprises the steps of obtaining input-output information, industry description information, administrative division relations and enterprise related attribute information from an official website; acquiring news public opinion data from a news website; respectively calculating the enterprise operation range and the patent information by using a co-occurrence and similarity algorithm to obtain enterprise cooperation and competition networks, and weighting the enterprise cooperation and competition networks to obtain an enterprise associated network; calculating an industry associated network according to the input-output table; calculating a regional association network according to the administrative division relation; calculating the mapping from the enterprise to the industry by using an unsupervised method; updating the industry associated network according to the enterprise associated network; and forming a three-network industry map by utilizing the area associated network, the industry associated network and the enterprise associated network. The invention dynamically reflects the public sentiment information in the enterprise associated network and updates the public sentiment information to the industry associated network, thereby helping decision-making departments to capture the development and change of regional industries more quickly.
Description
Technical Field
The invention belongs to the technical field of knowledge maps, and particularly relates to a three-network industrial map construction method based on regional industrial enterprises.
Background
In recent years, the development of regional industries has been a key development target of the nation. At present, the development of national regional industry policies mainly depends on an industry input-output table and statistical data of each region, which are issued once every 5 years, a directed graph is constructed based on the input-output data, and the regional industry association is analyzed by determining a threshold value to extract a strong association relation and construct an industry complex network. The method can accurately count the industrial development status of each area.
However, the industrial association constructed by the input-output table mainly considers the input-output relationship among industries, and has less concern on the relation among related enterprises, and the report is issued every 5 years, so that the decision basis cannot be provided for government departments in real time. Meanwhile, the emergent events and the rapidly developing emerging industries which are interfered by the external environment cannot provide a rapid and accurate judgment basis. Meanwhile, the existing industry association trend judgment lacks an effective metering method, and cannot be popularized by experience only through statistical data and management experience.
Disclosure of Invention
The project aims to help decision-making departments to make industrial policies, quickly capture the current industrial development situation by knowing and predicting the development trend of regional industries, and make effective industrial development policies. The invention forms a set of industrial map construction method based on regional industrial enterprises based on the existing structured and unstructured data of enterprises and industries. The invention also solves the problems that the traditional method based on the industrial input-output table is slow in updating, can not find the development of new industries and can not integrate richer enterprise information, and provides the industrial map construction method which can integrate regional information, industrial information and enterprise information and can provide a measuring tool for decision makers.
The technical scheme adopted by the invention is as follows: a three-network industry map construction method based on regional industry enterprises is characterized by comprising the following steps:
step 1: acquiring latest input-output information from an official website, and acquiring input-output tables and industry description information among industry departments; acquiring an administrative division relation from an official website; obtaining enterprise related attribute information from an official website; acquiring news public sentiments from news websites and acquiring news related texts, wherein the enterprise related attribute information comprises enterprise names, registered funds, enterprise addresses, enterprise business ranges and enterprise patents;
step 2: the enterprise operation range is calculated by using the co-occurrence to obtain an enterprise cooperation associated network, the enterprise patents are calculated by using a text matching algorithm to obtain an enterprise competition associated network, and the enterprise cooperation associated network and the enterprise competition associated network are calculated by weighting to obtain the enterprise associated network;
and step 3: calculating an industry associated network according to the input-output table;
and 4, step 4: calculating a regional association network by using enterprise address information according to the administrative division relation;
and 5: calculating mapping from the enterprise to the industry by using an unsupervised classification method according to the enterprise operation range;
step 6: updating the industry associated network according to the enterprise associated network;
and 7: forming a three-network industry map by utilizing the regional associated network, the industry associated network and the enterprise associated network;
preferably, the input-output table in step 1 is as follows:
Iij
1≤i≤N，1≤j≤N
wherein, IijThe investment of the ith industrial department to the jth industrial department is shown, and N represents the total number of industries;
step 1, the description information of the industrial department is as follows:
Di
wherein D isiDescription information indicating the ith industrial sector;
step 1, recording the administrative division relationship as A;
step 1, the enterprise related attribute information is:
C＝{Cname，Ccapital，Caddress，Cbusiness，Cpatent}
wherein the content of the first and second substances,Cnamerepresenting the name of the business, CcapitalIndicating registered funds, CaddressRepresenting a business address, CbusinessRepresenting the extent of business, CpatentRepresenting an enterprise patent;
step 1, marking the News public sentiment as News;
preferably, the enterprise cooperation correlation network in the step 2 is corporation;
each element in the Cooperation is specifically calculated as:
computing Enterprise CpAnd Enterprise CqThe number of News public sentiments News which belong to the common News public sentiments is m;
cooperationpq＝mpq
wherein the CooperationpqRepresenting Enterprise CpAnd Enterprise CqThe cooperative association of (a);
step 2, the enterprise competition correlation network is competition;
each element in the composition is specifically calculated as:
wherein, compositionpqRepresenting Enterprise CpAnd Enterprise CqThe competition association relationship of (1), cos (-) represents cosine similarity,
the word vector, representing all patent components for the p-th enterprise, is calculated as:
wherein
Representing a function that is converted into a word vector;
step 2, the enterprise cooperation associated network and the enterprise competition associated network are weighted and calculated to obtain an enterprise associated network, namely an entrprise, and each element in the entrprise is specifically calculated as:
enterprisepq＝αcooperationpq+βcompetitionpq
wherein, the enterprisepqRepresenting Enterprise CpAnd Enterprise CqThe business association of (a), and (beta) represent weights;
preferably, in step 3, the industry-related network is calculated according to the input-output table:
for the input-output table I, utilizing a Leonth inverse matrix to calculate an industry associated network matrix index, wherein the index isijRepresenting the association relationship between the ith industrial department and the jth industrial department;
preferably, the step 4 of calculating the area-related network by using the enterprise address information according to the administrative division relation includes:
for administrative division relation A, the enterprise address C is combinedaddressEach element is specifically calculated as:
wherein the content of the first and second substances,
representing Enterprise CpThe enterprise address of (a);
determining the three-level areas of province, city and district of the enterprise according to the administrative division relation A;
preferably, in step 5, the unsupervised classification method is used to calculate the mapping from the enterprise to the industry according to the enterprise operation range, that is, the affiliated industry department is determined according to the enterprise operation range, and the specific calculation is as follows:
and (3) calculating the similarity between the ith industry department and the p enterprise operation range by using a cosine similarity method:
wherein
A business scope word vector representing the pth business,
the word vector, which represents all the description information for the ith industry sector, is calculated as:
wherein D isiDescription information indicating the ith industrial sector,
representing a function that is converted into a word vector;
the first K enterprises with the operation range of the p-th enterprise having the minimum similarity with all the industrial departments are taken to represent the K industrial departments to which the p-th enterprise belongs, namely the mapping from the enterprise to the industry is recorded as Cp∈I。
Preferably, in step 6, the updating of the industry associated network according to the enterprise associated network is NET, and each element in NET is specifically calculated as:
wherein, NETijExpressing the association relationship of the i industry department to the j industry department of the dynamically updated industry association network, wherein alpha is a weight coefficient, M represents the total number of enterprises, K represents K minimum values before the similarity of each enterprise and the industry, and indexijShowing the association relationship between the ith industry department and the jth industry department,
indicating registered funds, enterprise, for the p-th businesspqRepresenting the incidence relation between the p-th enterprise and the q-th enterprise.
Preferably, in step 7, the three-network industry map formed by using the regional associated network, the industry associated network, and the enterprise associated network is G (a, NET, enterprise, θ), where θ represents an association relationship between networks, and is calculated as:
θ＝(Cp∈A，Cp∈I，Ii∈A)
wherein the mapping of enterprises to industries, C, according to step 5pE is A to represent the area to which the p-th enterprise belongs, CpE.g. I represents the industry department to which the p-th enterprise belongs, IiAnd epsilon A represents the area to which the ith industry belongs.
The invention relates to a three-network industry map construction method based on regional industry enterprises, which utilizes an industry input-output table to calculate an industry associated network. And constructing the area association network by using the administrative region code data. And calculating the cooperative association and competitive association of the enterprises according to the matching of the business scope co-occurrence of the enterprises and the similarity of the patent texts, and fusing to obtain the enterprise association network. And further mapping the enterprises to industries according to the operation range according to an unsupervised classification algorithm, so as to realize the dynamic update of the industry associated network. Finally, the three-network industry map is fused, and the association relation of each area and each industry, including the affiliated areas and enterprises of the industry, can be reflected more clearly and definitely. When more emerging cross fields and industries appear in public sentiment, the information can be dynamically reflected in a cooperation association network among enterprises and mapped to an industry association relationship network, so that a decision-making department can quickly catch the change trend of regional industry development, and a better policy theory and a better measuring tool are provided for the decision-making department.
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 introduced below, and it is obvious that the drawings in the following description are 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 an embodiment of the present invention;
Detailed Description
In order to facilitate the understanding and implementation of the present invention for those of ordinary skill in the art, the present invention is further described in detail with reference to the accompanying drawings and examples, it is to be understood that the embodiments described herein are merely illustrative and explanatory of the present invention and are not restrictive thereof.
An embodiment of the present invention will be described with reference to fig. 1.
Please refer to FIG. 1, the present invention provides the technical scheme adopted by the present invention as follows: a three-network industry map construction method based on regional industry enterprises is characterized by comprising the following steps:
step 1: acquiring latest input-output information from an official website, and acquiring input-output tables and industry description information among industry departments; acquiring an administrative division relation from an official website; obtaining enterprise related attribute information from an official website; acquiring news public sentiments from news websites and acquiring news related texts, wherein the enterprise related attribute information comprises enterprise names, registered funds, enterprise addresses, enterprise business ranges and enterprise patents;
step 1 the input-output table is as follows:
Iij
1≤i≤N，1≤j≤N
wherein, IijRepresents the investment of the ith industrial department to the jth industrial department, N represents the total number of industries, and N is 149 in the embodiment;
step 1, the description information of the industrial department is as follows:
Di
wherein D isiDescription information indicating the ith industrial sector;
step 1, recording the administrative division relationship as A;
step 1, the enterprise related attribute information is:
C＝{Cname，Ccapital，Caddress，Cbusiness，Cpatent}
wherein, CnameRepresenting the name of the business, CcapitalIndicating registered funds, CaddressRepresenting a business address, CbusinessRepresenting the extent of business, CpatentRepresenting an enterprise patent;
step 1, marking the News public sentiment as News;
step 2: the enterprise operation range is calculated by using the co-occurrence to obtain an enterprise cooperation associated network, the enterprise patents are calculated by using a text matching algorithm to obtain an enterprise competition associated network, and the enterprise cooperation associated network and the enterprise competition associated network are calculated by weighting to obtain the enterprise associated network;
step 2, the enterprise cooperation associated network is Cooperation;
each element in the Cooperation is specifically calculated as:
computing Enterprise CpAnd Enterprise CqThe number m of News public sentiments News belonging to the samepq；
cooperationpq＝mpq
Wherein the CooperationpqRepresenting Enterprise CpAnd Enterprise CqThe cooperative association of (a);
step 2, the enterprise competition correlation network is competition;
each element in the composition is specifically calculated as:
wherein, compositionpqRepresenting Enterprise CpAnd Enterprise CqThe competition association relationship of (1), cos (-) represents cosine similarity,
the word vector, representing all patent components for the p-th enterprise, is calculated as:
wherein
Representing a function that is converted into a word vector;
step 2, the enterprise cooperation associated network and the enterprise competition associated network are weighted and calculated to obtain an enterprise associated network, namely an entrprise, and each element in the entrprise is specifically calculated as:
enterprisepq＝αcooperationpq+βcompetitionpq
wherein, the enterprisepqRepresenting Enterprise CpAnd Enterprise CqThe enterprise association relationship of (1), alpha and beta represent weights, and are positively correlated with the average value in the cooperation and competition network, and the average value calculation formula of the cooperation network is as follows:
the average value in the competition network is calculated according to the formula:
count (C) represents the total number of businesses;
and step 3: calculating an industry associated network according to the input-output table;
and 3, calculating an industry associated network according to the input-output table:
for the input-output table I, utilizing a Leonth inverse matrix to calculate an industry associated network matrix index, wherein the index isijRepresenting the association relationship between the ith industrial department and the jth industrial department;
and 4, step 4: calculating a regional association network by using enterprise address information according to the administrative division relation;
step 4, calculating the area association network by using the enterprise address information according to the administrative division relation:
for administrative division relation A, the enterprise address C is combinedaddressEach element is specifically calculated as:
wherein the content of the first and second substances,
representing Enterprise CpThe enterprise address of (a);
determining the three-level areas of province, city and district of the enterprise according to the administrative division relation A;
and 5: calculating mapping from the enterprise to the industry by using an unsupervised classification method according to the enterprise operation range;
step 5, calculating the mapping from the enterprise to the industry by using an unsupervised classification method according to the enterprise operation range, namely determining the affiliated industry department according to the enterprise operation range, and specifically calculating as follows:
and (3) calculating the similarity between the ith industry department and the p enterprise operation range by using a cosine similarity method:
wherein
A business scope word vector representing the pth business,
the word vector, which represents all the description information for the ith industry sector, is calculated as:
wherein D isiDescription information indicating the ith industrial sector,
representing a function that is converted into a word vector;
taking the first K enterprises with the p-th enterprise operation range and the smallest similarity with all the industrial departments, wherein K is 3, the K industrial departments to which the p-th enterprise belongs are represented, namely the mapping from the enterprise to the industry is recorded as Cp∈I。
Step 6: updating the industry associated network according to the enterprise associated network;
and 6, updating the industry associated network to be NET according to the enterprise associated network, wherein each element in the NET is specifically calculated as follows:
wherein, NETijExpressing the association relationship of the i industry department to the j industry department of the dynamically updated industry association network, wherein alpha is a weight coefficient, M represents the total number of enterprises, K represents K minimum values before the similarity of each enterprise and the industry, and indexijShowing the association relationship between the ith industry department and the jth industry department,
indicating registered funds, enterprise, for the p-th businesspqRepresenting the incidence relation between the p-th enterprise and the q-th enterprise.
And 7: forming a three-network industry map by utilizing the regional associated network, the industry associated network and the enterprise associated network;
step 7, forming a three-network industry map G (a, NET, enterprise, θ) by using the area association network, the industry association network, and the enterprise association network, where θ represents an association relationship between networks, and is calculated as:
θ＝(Cp∈A，Cp∈I，Ii∈A)
wherein the mapping of enterprises to industries, C, according to step 5pE is A to represent the area to which the p-th enterprise belongs, CpE.g. I represents the industry department to which the p-th enterprise belongs, IiAnd epsilon A represents the area to which the ith industry belongs.
It should be understood that parts of the specification not set forth in detail are well within the prior art.
It should be understood that the above description of the preferred embodiments is given for clarity and not for any purpose of limitation, and that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A three-network industry map construction method based on regional industry enterprises is characterized by comprising the following steps:
step 1: acquiring latest input-output information from an official website, and acquiring input-output tables and industry description information among industry departments; acquiring an administrative division relation from an official website; obtaining enterprise related attribute information from an official website; acquiring news public sentiments from news websites and acquiring news related texts, wherein the enterprise related attribute information comprises enterprise names, registered funds, enterprise addresses, enterprise business ranges and enterprise patents;
step 2: the enterprise operation range is calculated by using the co-occurrence to obtain an enterprise cooperation associated network, the enterprise patents are calculated by using a text matching algorithm to obtain an enterprise competition associated network, and the enterprise cooperation associated network and the enterprise competition associated network are calculated by weighting to obtain the enterprise associated network;
and step 3: calculating an industry associated network according to the input-output table;
and 4, step 4: calculating a regional association network by using enterprise address information according to the administrative division relation;
and 5: calculating mapping from the enterprise to the industry by using an unsupervised classification method according to the enterprise operation range;
step 6: updating the industry associated network according to the enterprise associated network;
and 7: and forming a three-network industry map by utilizing the area associated network, the industry associated network and the enterprise associated network.
2. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
step 1 the input-output table is as follows:
Iij
1≤i≤N，1≤j≤N
wherein, IijThe investment of the ith industrial department to the jth industrial department is shown, and N represents the total number of industries;
step 1, the description information of the industrial department is as follows:
Di
wherein D isiDescription information indicating the ith industrial sector;
step 1, recording the administrative division relationship as A;
step 1, the enterprise related attribute information is:
C＝{Cname，Ccapital，Caddress，Cbusiness，Cpatent}
wherein, CnameRepresenting the name of the business, CcapitalIndicating registered funds, CaddressRepresenting a business address, CbusinessRepresenting the extent of business, CpatentRepresenting an enterprise patent;
and 1, recording the News public sentiment as News.
3. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
step 2, the enterprise cooperation associated network is Cooperation;
each element in the Cooperation is specifically calculated as:
computing Enterprise CpAnd Enterprise CqThe number of News public sentiments News which belong to the common News public sentiments is m;
cooperationpq＝mpq
wherein the CooperationpqRepresenting Enterprise CpAnd Enterprise CqThe cooperative association of (a);
step 2, the enterprise competition correlation network is competition;
each element in the composition is specifically calculated as:
wherein, compositionpqRepresenting Enterprise CpAnd Enterprise CqThe competition association relationship of (1), cos (-) represents cosine similarity,
the word vector, representing all patent components for the p-th enterprise, is calculated as:
wherein
Representing a function that is converted into a word vector;
step 2, the enterprise cooperation associated network and the enterprise competition associated network are weighted and calculated to obtain an enterprise associated network, namely an entrprise, and each element in the entrprise is specifically calculated as:
enterprisepq＝αcooperationpq+βcompetitionpq
wherein, the enterprisepqRepresenting Enterprise CpAnd Enterprise CqAnd alpha and beta represent weights.
4. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
and 3, calculating an industry associated network according to the input-output table:
for the input-output table I, utilizing a Leonth inverse matrix to calculate an industry associated network matrix index, wherein the index isijIndicating a relationship between the ith industrial division and the jth industrial divisionAnd (4) connection relation.
5. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
step 4, calculating the area association network by using the enterprise address information according to the administrative division relation:
for administrative division relation A, the enterprise address C is combinedaddressEach element is specifically calculated as:
wherein the content of the first and second substances,
representing Enterprise CpThe enterprise address of (a);
and determining the three-level areas of province, city and district of the enterprise according to the administrative division relation A.
6. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
step 5, calculating the mapping from the enterprise to the industry by using an unsupervised classification method according to the enterprise operation range, namely determining the affiliated industry department according to the enterprise operation range, and specifically calculating as follows:
and (3) calculating the similarity between the ith industry department and the p enterprise operation range by using a cosine similarity method:
wherein
A business scope word vector representing the pth business,
the word vector, which represents all the description information for the ith industry sector, is calculated as:
wherein D isiDescription information indicating the ith industrial sector,
representing a function that is converted into a word vector;
the first K enterprises with the operation range of the p-th enterprise having the minimum similarity with all the industrial departments are taken to represent the K industrial departments to which the p-th enterprise belongs, namely the mapping from the enterprise to the industry is recorded as Cp∈I。
7. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
and 6, updating the industry associated network to be NET according to the enterprise associated network, wherein each element in the NET is specifically calculated as follows:
wherein, NETijExpressing the association relationship of the i industry department to the j industry department of the dynamically updated industry association network, wherein alpha is a weight coefficient, M represents the total number of enterprises, K represents K minimum values before the similarity of each enterprise and the industry, and indexijShowing the association relationship between the ith industry department and the jth industry department,
indicating registered funds, enterprise, for the p-th businesspqRepresenting the incidence relation between the p-th enterprise and the q-th enterprise.
8. The regional industry enterprise-based three-network industry atlas construction method of claim 1, wherein:
step 7, forming a three-network industry map G (a, NET, enterprise, θ) by using the area association network, the industry association network, and the enterprise association network, where θ represents an association relationship between networks, and is calculated as:
θ＝(Cp∈A，Cp∈I，Ii∈A)
wherein the mapping of enterprises to industries, C, according to step 5pE is A to represent the area to which the p-th enterprise belongs, CpE.g. I represents the industry department to which the p-th enterprise belongs, IiAnd epsilon A represents the area to which the ith industry belongs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110029149.2A CN112784057B (en) | 2021-01-11 | 2021-01-11 | Three-network industrial map construction method based on regional industrial enterprises |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110029149.2A CN112784057B (en) | 2021-01-11 | 2021-01-11 | Three-network industrial map construction method based on regional industrial enterprises |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112784057A true CN112784057A (en) | 2021-05-11 |
| CN112784057B CN112784057B (en) | 2022-05-13 |
Family
ID=75756424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110029149.2A Active CN112784057B (en) | 2021-01-11 | 2021-01-11 | Three-network industrial map construction method based on regional industrial enterprises |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112784057B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160085850A1 (en) * | 2014-09-23 | 2016-03-24 | Kaybus, Inc. | Knowledge brokering and knowledge campaigns |
| CN109255054A (en) * | 2017-07-14 | 2019-01-22 | 元素征信有限责任公司 | A kind of community discovery algorithm in enterprise's map based on relationship weight |
| CN109885698A (en) * | 2019-02-13 | 2019-06-14 | 北京航空航天大学 | A kind of knowledge mapping construction method and device, electronic equipment |
| CN110134842A (en) * | 2019-04-03 | 2019-08-16 | 深圳价值在线信息科技股份有限公司 | Information matching method, device, storage medium and server based on Information Atlas |
| CN110197280A (en) * | 2019-05-20 | 2019-09-03 | 中国银行股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN110597870A (en) * | 2019-08-05 | 2019-12-20 | 长春市万易科技有限公司 | Enterprise relation mining method |
| CN111104522A (en) * | 2019-12-20 | 2020-05-05 | 武汉理工大学 | Regional industry association effect trend prediction method based on knowledge graph |
-
2021
- 2021-01-11 CN CN202110029149.2A patent/CN112784057B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160085850A1 (en) * | 2014-09-23 | 2016-03-24 | Kaybus, Inc. | Knowledge brokering and knowledge campaigns |
| CN109255054A (en) * | 2017-07-14 | 2019-01-22 | 元素征信有限责任公司 | A kind of community discovery algorithm in enterprise's map based on relationship weight |
| CN109885698A (en) * | 2019-02-13 | 2019-06-14 | 北京航空航天大学 | A kind of knowledge mapping construction method and device, electronic equipment |
| CN110134842A (en) * | 2019-04-03 | 2019-08-16 | 深圳价值在线信息科技股份有限公司 | Information matching method, device, storage medium and server based on Information Atlas |
| CN110197280A (en) * | 2019-05-20 | 2019-09-03 | 中国银行股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN110597870A (en) * | 2019-08-05 | 2019-12-20 | 长春市万易科技有限公司 | Enterprise relation mining method |
| CN111104522A (en) * | 2019-12-20 | 2020-05-05 | 武汉理工大学 | Regional industry association effect trend prediction method based on knowledge graph |
Non-Patent Citations (1)
| Title |
|---|
| 王洋: "大数据产业图谱评述与构建研究", 《调研世界》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112784057B (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Seasonal ARIMA forecasting of inbound air travel arrivals to Taiwan | |
| CN104321794B (en) | A kind of system and method that the following commercial viability of an entity is determined using multidimensional grading | |
| Huang et al. | Dynamic network topology and market performance: A case of the Chinese stock market | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| Tong et al. | Developing econometrics | |
| CN109767225B (en) | Network payment fraud detection method based on self-learning sliding time window | |
| Wang et al. | Data-driven prediction of contract failure of public-private partnership projects | |
| CN111178614A (en) | Enterprise risk prediction method and system | |
| Grinberger et al. | An analysis of the spatial and temporal distribution of large‐scale data production events in OpenStreetMap | |
| Fronzetti Colladon et al. | Forecasting financial markets with semantic network analysis in the COVID‐19 crisis | |
| Crociata et al. | Creative workforce and economic development in precrisis Europe: Main trends and causality relationships | |
| Song et al. | An stochastic multiattribute acceptability analysis‐based method for the multiattribute project portfolio selection problem with rank‐level information | |
| CN112784057B (en) | Three-network industrial map construction method based on regional industrial enterprises | |
| Reggi et al. | Information strategies for open government in Europe: EU regions opening up the data on structural funds | |
| CN109543712B (en) | Method for identifying entities on temporal data set | |
| CN109885797B (en) | Relational network construction method based on multi-identity space mapping | |
| Kipkogei et al. | Business success prediction in Rwanda: a comparison of tree-based models and logistic regression classifiers | |
| Ragapriya et al. | Machine Learning Based House Price Prediction Using Modified Extreme Boosting | |
| CN110399382A (en) | Civil aviaton's master data recognition methods and system based on cloud model and rough set | |
| CN111882421B (en) | Information processing method, wind control method, device, equipment and storage medium | |
| CN110311991B (en) | Street-level landmark obtaining method based on SVM classification model | |
| Chi et al. | Delineating the Spatio‐Temporal Pattern of House Price Variation by Local Authority in England: 2009 to 2016 | |
| CN112016004A (en) | Multi-granularity information fusion-based job crime screening system and method | |
| Vnukova et al. | Identifying changes in insurance companies’ competitiveness on the travel services market | |
| Ma et al. | User portrait-based hybrid recommendation method of web services |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |