CN110083674B - Intellectual property information processing method and device - Google Patents
Intellectual property information processing method and device Download PDFInfo
- Publication number
- CN110083674B CN110083674B CN201910159608.1A CN201910159608A CN110083674B CN 110083674 B CN110083674 B CN 110083674B CN 201910159608 A CN201910159608 A CN 201910159608A CN 110083674 B CN110083674 B CN 110083674B
- Authority
- CN
- China
- Prior art keywords
- similarity
- competitor
- class
- information
- information 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.)
- Active
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 13
- 238000003672 processing method Methods 0.000 title abstract description 6
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012827 research and development Methods 0.000 claims abstract description 9
- 230000009193 crawling Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 77
- 238000005516 engineering process Methods 0.000 claims description 9
- 230000001502 supplementing effect Effects 0.000 claims description 6
- 238000009411 base construction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000013589 supplement Substances 0.000 claims description 2
- 238000012800 visualization Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G06F16/322—Trees
-
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
- G06Q50/184—Intellectual property management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of data processing, and particularly relates to an intellectual property information processing method and device; step two, self patent information is crawled from the patent database, and a self patent information base is formed by adopting the method in the step one; step three, setting competitor information, crawling the patent information of the competitor from the patent database, and forming a competitor patent information base by adopting the method in the step one; step four, according to the index of the classification number, the self patent information base and the competitor patent information base are compared in a crossing way, and the direction similarity and the patent similarity are obtained; step five, visualizing the ordering condition of the direction similarity; according to the intelligent intellectual property information processing analysis method, the patent layout conditions of enterprises and competitors thereof are analyzed from two angles of classification numbers and individual patents, and the enterprises are guided to adjust research and development directions and patent layouts of the enterprises by calculating the direction similarity and the patent similarity, so that intelligent intellectual property information processing analysis is realized.
Description
Technical Field
The invention belongs to the field of data processing, and particularly relates to an intellectual property information processing method and device.
Background
At present, public awareness of intellectual property protection is stronger, patents are effective means for protecting independent innovation for scientific enterprises, however, in the prior art, the enterprises mainly collect the applied patents, analyze and process the applied patents manually, which is time-consuming and labor-consuming, and lack effective means for intelligent analysis of the patents, so that the enterprises lack guidance in the directions of patent layout and technical research and development.
Disclosure of Invention
The invention provides an intellectual property information processing method and device, which are used for solving the technical problem of intelligent processing of intellectual property information, so that enterprises know the current technical development and patent layout condition in advance.
The invention realizes intelligent processing of intellectual property information by the following modes, which comprises the following steps:
constructing a patent information base, namely constructing a multi-way tree index of class numbers according to an international classification table, correspondingly distributing a storage space for each class number, storing class number semantic vectors corresponding to the class numbers, extracting keywords of the class numbers according to class number definition in advance, and storing the keywords into the class number semantic vectors so as to construct a class number index table; supplementing class number semantic vectors in a class number index table according to the patent information crawled from the patent database; generating a patent semantic vector by adopting a text vector generation method aiming at each crawled patent, and generating a patent information base;
step two, self patent information is crawled from the patent database, and a self patent information base is formed by adopting the method in the step one;
step three, setting competitor information, and crawling the patent information of the competitor from the patent database to form a competitor patent information base;
step four, according to the index of the classification number, the self patent information base and the competitor patent information base are compared in a crossing way, and the direction similarity and the patent similarity are obtained; the cross comparison comprises traversing each patent in the same class number in the two information bases, calculating the similarity of the patent according to the semantic vector of the patent, calculating the similarity of the direction according to the semantic vector of the class number in the two information bases;
step five, visualizing the ordering condition of the direction similarity, wherein a user can adjust the research and development direction according to the ordering of the direction similarity; based on the similarity of the patents, given the patented expectations of the patents, the user can refer to the values to determine the manner in which the patents are processed.
Meanwhile, the method also comprises the steps of extracting text vectors of the technical proposal to be submitted, calculating similarity with semantic vectors of all class numbers respectively, taking class numbers with similarity exceeding a certain threshold value as recommended class numbers of the proposal, and determining whether to submit the proposal to a patent application according to the directional similarity of the recommended class numbers.
According to the intelligent intellectual property information processing method and system based on the intelligent intellectual property information processing system, patent layout conditions of enterprises and competitors of the enterprises are analyzed from two angles of classification numbers and individual patents, the computing direction similarity and the patent similarity guide the enterprises to adjust research and development directions and patent layouts of the enterprises, the patenting possibility of the technical scheme to be submitted can be intelligently analyzed, unnecessary application cost is avoided from being wasted by the enterprises, and intelligent intellectual property information processing analysis is realized.
Drawings
FIG. 1 is a flow chart of the method of the present invention
FIG. 2 is a block diagram of the apparatus of the present invention
Detailed Description
The embodiments are described in detail below with reference to the accompanying drawings.
The method of the invention is shown in the flow chart of figure 1:
constructing a patent information base, namely constructing a multi-way tree index of class numbers according to an international classification table, correspondingly distributing a storage space for each class number, storing class number semantic vectors corresponding to the class numbers, extracting keywords of the class numbers according to class number definition in advance, and storing the keywords into the class number semantic vectors so as to construct a class number index table; supplementing class number semantic vectors in a class number index table according to the patent information crawled from the patent database; generating a patent semantic vector by adopting a text vector generation method aiming at each crawled patent, and generating a patent information base;
when the multi-way tree index based on the IPC classification table is established, the root node is a part index of the classification number, a root node is established for each part, the multi-way tree is divided in sequence according to the sequence of the major class, the minor class, the major group and the minor group of the IPC, a corresponding class number semantic vector is generated for each node, and the corresponding class number semantic vector is updated in real time, so that the subsequent classification of other patent information can be guided; meanwhile, the class number index table can be constructed by only selecting a part according to the needs and can be determined according to the specific research field of enterprises, so that the data processing capacity is reduced.
When the semantic vectors of the classification numbers are supplemented, the classification number information given by the patents is utilized, the semantic vectors of the corresponding classification numbers are supplemented and updated according to keywords given by the patents, the weights of the keywords in the semantic vectors are adjusted according to keyword sources, wherein the keyword sources comprise abstracts, background technology, claims and specifications, the summary information relates to the invention point information of the patents, and the background technology can reflect the information of the field to which the patents belong, so that higher weight information is set for the keywords extracted from the abstracts and the background technology.
The text vector generation method can adopt various known text vector generation methods, such as a neural network, doc2vec and the like.
Step two, self patent information is crawled from the patent database, and a self patent information base is formed by adopting the method in the step one;
the self-patent information base comprises patent information formed by a self-classification number index table and self-patent semantic vectors; the class number semantic vector in the self class number index table is updated according to the self patent information.
Step three, setting competitor information, crawling the patent information of the competitor from the patent database, and forming a competitor patent information base by adopting the method in the step one;
the competitor patent information base comprises a competitor class number index table and patent information formed by competitor patent semantic vectors; the classification number semantic vector in the competitor classification number index table is updated according to the competitor patent information.
Step four, according to the index table of the classification number, the self patent information base and the competitor patent information base are compared in a crossing way, and the direction similarity and the patent similarity are obtained; the cross comparison comprises traversing each patent in the same class number in the two information bases, calculating the similarity of the patent according to the semantic vector of the patent, calculating the semantic vector of the class number in the same class number in the two information bases, and calculating the similarity of the direction according to the semantic vector of the class number.
For example, for class a, patents a1, b1, c1 are in the own patent information base, and patents a2, b2 are in the competitor patent information base; then comparing the patent semantic vector similarity of (a 1, a 2), (a 1, b 2), (b 1, a 2), (b 1, b 2), (c 1, a 2), (c 1, b 2), defining a patent similarity; and calculating the similarity between the class number semantic vector of the class number A in the self patent information base and the class number semantic vector of the class number A in the competitor patent information base, and defining the direction similarity.
The directional similarity can be divided into a large group of similarity and a small group of similarity. According to the overlapping condition of competitors and the research field of the competitors, the parameters can be dynamically adjusted to calculate the similarity of a large group or the similarity of a small group, so that finer research and development direction guidance can be provided for the enterprises, and the large group and the small group refer to the structure of the large group and the small group in the classification table.
Step five, visualizing the ordering condition of the direction similarity, wherein a user can adjust the research and development direction according to the ordering of the direction similarity; based on the similarity of the patents, given the patented expectations of the patents, the user can refer to the values to determine the manner in which the patents are processed.
In the third step, the competitor information can be dynamically adjusted.
In another embodiment, the invention further comprises extracting text vectors of the scheme for the technical scheme to be submitted, calculating similarity with semantic vectors of all classification numbers respectively, taking the classification number with the similarity exceeding a certain threshold value as a recommended classification number of the scheme, and determining whether to submit the scheme to the patent application according to the directional similarity of the recommended classification number.
In one embodiment of the present invention as shown in fig. 2, an intellectual property information processing apparatus includes the following modules:
the information base construction module is used for constructing a patent information base, namely constructing a multi-tree index of class numbers according to an international classification table, correspondingly distributing a storage space for each class number, storing class number semantic vectors corresponding to the class numbers, extracting keywords of the class numbers according to class number definition in advance, and storing the keywords into the class number semantic vectors so as to construct a class number index table; supplementing class number semantic vectors in a class number index table according to the patent information crawled from the patent database; generating a patent semantic vector by adopting a text vector generation method aiming at each crawled patent, and generating a patent information base;
the self patent information base generation module is used for crawling self patent information from the patent database and forming a self patent information base by adopting the method in the first step;
the competitor patent information base generation module is used for setting competitor information, crawling the patent information of the competitor from the patent database and forming a competitor patent information base;
the similarity calculation module is used for carrying out cross comparison on the self patent information base and the competitor patent information base according to the index of the classification number to obtain the direction similarity and the patent similarity; the cross comparison comprises traversing each patent in the same class number in the two information bases, calculating the similarity of the patent according to the semantic vector of the patent, calculating the similarity of the direction according to the semantic vector of the class number in the two databases and comparing the similarity of the direction according to the same class number in the two databases;
the visualization module is used for visualizing the ordering condition of the direction similarity, and a user can adjust the research and development direction according to the ordering of the direction similarity; based on the similarity of the patents, given the patented expectations of the patents, the user can refer to the values to determine the manner in which the patents are processed.
When the information base construction module supplements the semantic vectors of the class numbers, the corresponding semantic vectors of the class numbers are supplemented and updated according to the keywords given by the patents according to the class number information given by the patents, the weights of the keywords in the semantic vectors are adjusted according to the keyword sources, the keyword sources comprise abstracts, background technologies, claims and specifications, and higher weight information is set for the keywords extracted from the abstracts and the background technologies.
The competitor information in the competitor patent information base generation module can be dynamically adjusted.
The direction similarity in the similarity calculation module can be divided into a large group of similarity and a small group of similarity.
In another embodiment, the device further includes an analysis module, configured to extract a text vector of the file for a technical solution to be submitted, calculate similarity with semantic vectors of respective classification numbers, use a classification number with similarity exceeding a certain threshold as a recommendation classification number of the solution, and determine whether to submit the solution to the patent application according to the directional similarity of the recommendation classification number.
The above embodiments are merely preferred embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the technical scope of the present invention should 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 (6)
1. A method of intellectual property information processing, the method comprising the steps of: constructing a patent information base, namely constructing a multi-way tree index of class numbers according to an international classification table, correspondingly distributing a storage space for each class number, storing class number semantic vectors corresponding to the class numbers, extracting keywords of the class numbers according to class number definition in advance, and storing the keywords into the class number semantic vectors so as to construct a class number index table; supplementing class number semantic vectors in a class number index table according to the patent information crawled from the patent database; generating a patent semantic vector by adopting a text vector generation method aiming at each crawled patent, and generating a patent information base;
step two, self patent information is crawled from the patent database, and a self patent information base is formed by adopting the method in the step one;
the self-patent information base comprises patent information formed by a self-classification number index table and self-patent semantic vectors; the class number semantic vector in the class number index table is updated according to the self patent information;
step three, setting competitor information, crawling the patent information of the competitor from the patent database, and forming a competitor patent information base by adopting the method in the step one;
the competitor patent information base comprises a competitor class number index table and patent information formed by competitor patent semantic vectors; updating the classification number semantic vector in the classification number index table of the competitor according to the patent information of the competitor;
step four, according to the index of the classification number, the self patent information base and the competitor patent information base are compared in a crossing way, and the direction similarity and the patent similarity are obtained; the cross comparison comprises traversing each patent in the same class number in the two information bases, calculating the similarity of the patent according to the semantic vector of the patent, calculating the similarity of the direction according to the semantic vector of the class number in the two information bases;
step five, visualizing the ordering condition of the direction similarity, wherein a user can adjust the research and development direction according to the ordering of the direction similarity; according to the similarity of the patents, giving an expected value of the patent, and determining the processing mode of the patent by a user referring to the value;
in the first step, when the semantic vectors of the classification numbers are supplemented, the classification number information given by the patents is utilized, the semantic vectors of the corresponding classification numbers are supplemented and updated according to keywords given by the patents, the weights of the keywords in the semantic vectors are adjusted according to keyword sources, the keyword sources comprise abstracts, background technologies, claims and specifications, and higher weight information is set for the keywords extracted from the abstracts and the background technologies; in the third step, the competitor information can be dynamically adjusted.
2. The method of claim 1, wherein in step four, the directional similarity is divided into a large group similarity and a small group similarity.
3. The method of claim 1, further comprising extracting text vectors of the document for the technical solution to be submitted, calculating similarity with semantic vectors of respective class numbers, taking class numbers with similarity exceeding a certain threshold as recommended class numbers of the solution, and determining whether to submit the solution to the patent application according to the directional similarity of the recommended class numbers.
4. An intellectual property information processing apparatus comprising the following modules:
the information base construction module is used for constructing a patent information base, namely constructing a multi-tree index of class numbers according to an international classification table, correspondingly distributing a storage space for each class number, storing class number semantic vectors corresponding to the class numbers, extracting keywords of the class numbers according to class number definition in advance, and storing the keywords into the class number semantic vectors so as to construct a class number index table; supplementing class number semantic vectors in a class number index table according to the patent information crawled from the patent database; generating a patent semantic vector by adopting a text vector generation method aiming at each crawled patent, and generating a patent information base;
the self patent information base generation module is used for crawling self patent information from the patent database and forming a self patent information base by adopting the method in the first step;
the self-patent information base comprises patent information formed by a self-classification number index table and self-patent semantic vectors; the class number semantic vector in the class number index table is updated according to the self patent information;
the competitor patent information base generation module is used for setting competitor information, crawling the patent information of the competitor from the patent database and forming a competitor patent information base;
the competitor patent information base comprises a competitor class number index table and patent information formed by competitor patent semantic vectors; the classification number semantic vector in the competitor classification number index table is updated according to the competitor patent information;
the similarity calculation module is used for carrying out cross comparison on the self patent information base and the competitor patent information base according to the index of the classification number to obtain the direction similarity and the patent similarity; the cross comparison comprises traversing each patent in the same class number in the two information bases, calculating the similarity of the patent according to the semantic vector of the patent, calculating the similarity of the direction according to the semantic vector of the class number in the two databases and comparing the similarity of the direction according to the same class number in the two databases;
the visualization module is used for visualizing the ordering condition of the direction similarity, and a user can adjust the research and development direction according to the ordering of the direction similarity; according to the similarity of the patents, giving an expected value of the patent, and determining the processing mode of the patent by a user referring to the value;
the information base construction module further comprises the steps of utilizing the classification number information given by the patent to supplement and update the corresponding classification number semantic vector according to the keywords given by the patent when supplementing the classification number semantic vector, and adjusting the weight of the keywords in the semantic vector according to the keyword sources, wherein the keyword sources comprise abstracts, background technologies, claims and specifications, and setting higher weight information for the keywords extracted from the abstracts and the background technologies;
the competitor information in the competitor patent information base generation module can be dynamically adjusted.
5. The apparatus of claim 4, wherein the directional similarity in the similarity calculation module is divided into a large group of similarities and a small group of similarities.
6. The apparatus of claim 4, further comprising an analysis module configured to extract text vectors of the document for the technical solution to be submitted, calculate similarities with semantic vectors of respective class numbers, take class numbers with similarities exceeding a certain threshold as recommended class numbers of the solution, and determine whether to submit the solution to the patent application according to directional similarities of the recommended class numbers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910159608.1A CN110083674B (en) | 2019-03-04 | 2019-03-04 | Intellectual property information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910159608.1A CN110083674B (en) | 2019-03-04 | 2019-03-04 | Intellectual property information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110083674A CN110083674A (en) | 2019-08-02 |
| CN110083674B true CN110083674B (en) | 2023-05-12 |
Family
ID=67413128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910159608.1A Active CN110083674B (en) | 2019-03-04 | 2019-03-04 | Intellectual property information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110083674B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111259110A (en) * | 2020-01-13 | 2020-06-09 | 武汉大学 | College patent personalized recommendation system |
| CN113129179A (en) * | 2021-05-13 | 2021-07-16 | 贵阳业勤中小企业促进中心有限公司 | Intellectual property data analysis and management system based on block chain |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015032301A1 (en) * | 2013-09-05 | 2015-03-12 | 江苏大学 | Method for detecting the similarity of the patent documents on the basis of new kernel function luke kernel |
| CN106372226A (en) * | 2016-09-07 | 2017-02-01 | 知识产权出版社有限责任公司 | Information retrieval device and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247780A (en) * | 2017-06-12 | 2017-10-13 | 北京理工大学 | A kind of patent document method for measuring similarity of knowledge based body |
| CN108536677A (en) * | 2018-04-09 | 2018-09-14 | 北京信息科技大学 | A kind of patent text similarity calculating method |
| CN108921737A (en) * | 2018-06-27 | 2018-11-30 | 广州朝舜网络科技有限公司 | A kind of patent distribution intelligent analysis method, device, terminal and storage medium |
| CN109063148A (en) * | 2018-08-07 | 2018-12-21 | 黑龙江阳光惠远信息技术有限公司 | A kind of related patents recommender system and recommended method based on third-party platform |
| CN109145091A (en) * | 2018-09-12 | 2019-01-04 | 合肥汇众知识产权管理有限公司 | Patent agency's recommender system and method based on patent information |
-
2019
- 2019-03-04 CN CN201910159608.1A patent/CN110083674B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015032301A1 (en) * | 2013-09-05 | 2015-03-12 | 江苏大学 | Method for detecting the similarity of the patent documents on the basis of new kernel function luke kernel |
| CN106372226A (en) * | 2016-09-07 | 2017-02-01 | 知识产权出版社有限责任公司 | Information retrieval device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110083674A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11983269B2 (en) | Deep neural network system for similarity-based graph representations | |
| Ceberio et al. | A review on estimation of distribution algorithms in permutation-based combinatorial optimization problems | |
| US10133729B2 (en) | Semantically-relevant discovery of solutions | |
| CN109800307A (en) | Analysis method, device, computer equipment and the storage medium of product evaluation | |
| US20110231350A1 (en) | Active metric learning device, active metric learning method, and active metric learning program | |
| CN103984714B (en) | Ontology semantics-based supply and demand matching method for cloud manufacturing service | |
| CN103049433A (en) | Automatic question answering method, automatic question answering system and method for constructing question answering case base | |
| CN106021457A (en) | Keyword-based RDF distributed semantic search method | |
| CN112905801A (en) | Event map-based travel prediction method, system, device and storage medium | |
| CN104699698A (en) | Graph query processing method based on massive data | |
| CN103425727A (en) | Contextual voice query dilation | |
| CN109636168A (en) | A kind of cloud platform scheduling resource intelligent matching process based on Ontology | |
| Li et al. | RTCRelief-F: an effective clustering and ordering-based ensemble pruning algorithm for facial expression recognition | |
| CN110083674B (en) | Intellectual property information processing method and device | |
| CN116821307B (en) | Content interaction method, device, electronic equipment and storage medium | |
| US20230385317A1 (en) | Information Retrieval Method, Related System, and Storage Medium | |
| Deng et al. | A distributed PDP model based on spectral clustering for improving evaluation performance | |
| CN112131261A (en) | Community query method and device based on community network and computer equipment | |
| CN103823881B (en) | The method and device of the performance optimization of distributed data base | |
| CN114722217A (en) | Content pushing method based on link prediction and collaborative filtering | |
| CN117708270A (en) | Enterprise data query method, device, equipment and storage medium | |
| CN103324644A (en) | Query result diversification method | |
| Hasperué et al. | Rule extraction on numeric datasets using hyper-rectangles | |
| Chung et al. | Fast approach for automatic data retrieval using R programming language | |
| Sun | A mixed integer programming model for multiple-class discriminant analysis |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191011 Address after: 325000 room 402, building B, No. 22, Fapai Road, Wuqiao Industrial Zone, Lucheng District, Wenzhou City, Zhejiang Province Applicant after: Wenzhou yunpan Technology Co.,Ltd. Address before: 325000 First Half of Flourishing North Road, Xianyan Street, Ouhai District, Wenzhou City, Zhejiang Province Applicant before: Wenzhou Yongrun Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230424 Address after: 518031 12B2B3C1, Block A, First World Plaza, No. 7002, Hongli West Road, Jinghua Community, Lianhua Street, Futian District, Shenzhen, Guangdong Applicant after: Shenzhen Yunlian Zhihui IoT Technology Co.,Ltd. Address before: Room 402, Building B, No. 22 Fabai Road, Wuqiao Industrial Zone, Lucheng District, Wenzhou City, Zhejiang Province, 325000 Applicant before: Wenzhou yunpan Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |