CN111898371A - Ontology construction method and device for rational design knowledge and computer storage medium - Google Patents
Ontology construction method and device for rational design knowledge and computer storage medium Download PDFInfo
- Publication number
- CN111898371A CN111898371A CN202010662266.8A CN202010662266A CN111898371A CN 111898371 A CN111898371 A CN 111898371A CN 202010662266 A CN202010662266 A CN 202010662266A CN 111898371 A CN111898371 A CN 111898371A
- Authority
- CN
- China
- Prior art keywords
- design
- information
- relationship
- rational
- knowledge
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000010276 construction Methods 0.000 title claims description 18
- 238000009510 drug design Methods 0.000 title abstract description 15
- 238000013461 design Methods 0.000 claims abstract description 411
- 238000000605 extraction Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 39
- 230000008901 benefit Effects 0.000 claims abstract description 27
- 230000007547 defect Effects 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000012512 characterization method Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000008451 emotion Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000009411 base construction Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000007435 diagnostic evaluation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- NQLVQOSNDJXLKG-UHFFFAOYSA-N prosulfocarb Chemical compound CCCN(CCC)C(=O)SCC1=CC=CC=C1 NQLVQOSNDJXLKG-UHFFFAOYSA-N 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
A method, a device and a computer storage medium for constructing an ontology of design rational knowledge are disclosed, which comprise the following steps: determining an extraction object of design rational knowledge; extracting entity information and relationship information in an extraction object of the design rational knowledge; establishing association between entity information by using relationship information; the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship. By adopting the scheme in the application, the ontology of the rational design knowledge is constructed, reference or inspiration is provided for the innovative design of designers, and the knowledge reuse of information resources is facilitated.
Description
Technical Field
The present application relates to a design rational knowledge technology, and in particular, to a method and an apparatus for ontology construction of design rational knowledge, a computer storage medium, and an electronic device.
Background
The design is a key link of product innovation, and is a knowledge-intensive activity. All innovations were designed without exception. Design-wise knowledge, which is knowledge explaining why a design is designed in this way, is knowledge about the design process, and is usually not systematically recorded with respect to design-result knowledge.
Problems existing in the prior art:
at present, no construction method for designing rational knowledge exists.
Disclosure of Invention
The embodiment of the application provides a method and a device for constructing an ontology of design rational knowledge, a computer storage medium and electronic equipment, so as to solve the technical problems.
According to a first aspect of embodiments of the present application, there is provided a method for ontology construction of design rationality knowledge, comprising:
determining an extraction object of design rational knowledge;
extracting entity information and relationship information in an extraction object of the design rational knowledge;
establishing association between entity information by using relationship information;
the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship.
According to a second aspect of the embodiments of the present application, there is provided an ontology construction apparatus for designing rational knowledge, including:
the object determination module is used for determining an extraction object of design rational knowledge;
the information extraction module is used for extracting entity information and relationship information in an extraction object of the design rational knowledge;
the association module is used for establishing association between the entity information by utilizing the relationship information;
the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship.
According to a third aspect of embodiments of the present application, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as described above.
According to a fourth aspect of embodiments herein, there is provided an electronic device comprising one or more processors, and memory for storing one or more programs; the one or more programs, when executed by the one or more processors, implement the method as described above.
By adopting the method and the device for constructing the ontology of the design rational knowledge, the computer storage medium and the electronic equipment, six kinds of entity information and six kinds of relation information are designed, the entity information and the relation information are extracted from an extraction object containing the design rational knowledge, and then the entity information and the relation information are associated with each other, so that the ontology of the design rational knowledge is constructed, reference or inspiration is provided for the innovative design of designers, and the knowledge reuse of information resources is facilitated.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart showing an implementation of an ontology construction method for designing rational knowledge in an embodiment of the present application;
FIG. 2 is a diagram illustrating a structure of a typical sentence containing design intent in the first embodiment of the present application;
FIG. 3 is a schematic structural diagram of an ontology construction device for designing rational knowledge in the second embodiment of the present application;
fig. 4 shows a schematic structural diagram of an electronic device in the fourth embodiment of the present application;
FIG. 5 is a schematic diagram illustrating a design rational knowledge acquisition process in the fifth embodiment of the present application;
fig. 6 shows a schematic representation of design rationality knowledge in example five of the present application.
Detailed Description
The inventor notices in the process of invention that:
in prior art documents, for example: technical documents such as design specifications, patent documents, academic articles, technical reports, technical standards, technical review records, and technical archives of products in other enterprises include more or less design rational information, for example: designer's intentions, considerations of advantages and disadvantages of solution selection, approval/disapproval attitudes and reasons held by the interested parties, and the like. If the rational design knowledge in the documents in the prior art is mined, the method has extremely important significance for designers, knowledge base construction and innovation management.
However, in the conventional knowledge base management, books are usually only classified and coded, and the like, and the retrieval is still inconvenient through manual reading and understanding word by word or sentence by sentence or full-text retrieval of keywords, and the retrieval result usually contains a large amount of redundant information, and the whole article still needs to be read through if the exact key knowledge point is to be found from a large number of results.
Therefore, the inventor of the present application thinks of a method for acquiring design rational knowledge from a technical document, quickly extracts a design scheme, a design intention, design advantages and disadvantages and the like from a document, and constructs an ontology with the design rational knowledge, so that a designer can reuse knowledge of information resources.
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example one
The embodiment of the application provides an ontology construction method for designing rational knowledge, which is explained below.
Fig. 1 shows a schematic flow chart of an implementation of an ontology construction method for designing rational knowledge in an embodiment of the present application.
As shown in the figure, the ontology construction method of the design rational knowledge comprises the following steps:
102, extracting entity information and relationship information in an extraction object of the design rational knowledge;
103, establishing association between the entity information by using the relationship information;
the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship.
In one embodiment, the extraction objects of the design rational knowledge include technical documents such as design specifications, patent documents, academic articles, technical reports, technical standards, technical review records, or technical archives of other products inside enterprises.
In one embodiment, the extraction of rational knowledge of design is determined from libraries, patent databases, data houses, design literature libraries, and the like.
In one embodiment, after determining the extraction object of the design rational knowledge, the method further comprises:
and preprocessing or data cleaning is carried out on the data of the extraction object of the rational design knowledge.
The pre-processing or data cleaning comprises: converting the extracted object of the rational design knowledge into a design document in a pure text format, processing characters (such as "+", "e.g", "[ ]", and the like) in the design document, and processing spelling of upper and lower case letters and the like.
By adopting the ontology construction method for designing rational knowledge provided by the embodiment of the application, six kinds of entity information and six kinds of relation information are designed, the entity information and the relation information are extracted from the extraction object containing the rational design knowledge, and then the entity information and the relation information are associated with each other, so that an ontology for obtaining the rational design knowledge is constructed, reference or inspiration is provided for the innovative design of designers, and the knowledge reuse of information resources is facilitated.
In one embodiment, the associating the entity information with the relationship information includes:
establishing association between the design literature information and the design object information through a description relation;
establishing association between the design scheme information and the design intention information through an implementation relation;
the design scheme information comprises a plurality of design objects, and the plurality of design objects are associated through a structural relationship;
establishing association between the design intention information and the design problem information through a solution relation;
establishing association between the design scheme information and the design problem information through the existence of relationship;
establishing association between the design problem information and the defect description information through an expression relationship;
and establishing association by having relationship between the design scheme information and the alternative scheme information.
In specific implementation, the association between the entity information and the relationship information is as follows:
(design literature) - - [ description ] - - > (design object)
(design scheme) - - [ implementation ] - - > (design intent)
[ design solution ] ═ design object) - - [ structure ] - > (design object)
(design intent) - - [ solution ] - - > (design problem)
[ Presence ] - - > (design problem) - - [ manifestation ] - > (negative description)
(design) - - [ with ] - > (alternative).
In one embodiment, the extracting entity information and relationship information in the object of the extraction of the design rational knowledge includes:
extracting sentences containing design rational information in the extraction objects of the design rational knowledge;
and identifying entity information and relationship information in the sentence containing the design rationality information.
In one embodiment, the extracting the sentence containing design rational information in the object of extracting the design rational knowledge includes:
matching characteristic words in a pre-constructed design rational sentence pattern library;
calculating the credibility of the design rational information according to the feature words obtained by matching, and extracting sentences containing the design rational information in the extraction object of the design rational knowledge;
the design rational sentence pattern library comprises design rational typical sentence patterns, and the typical sentence patterns comprise a plurality of rational characteristic words and professional characteristic words.
In specific implementation, a typical sentence pattern can be constructed according to the writing specification and writing examples of design documents, and the typical sentence pattern comprises a plurality of design rational characteristic words and professional characteristic words.
Fig. 2 shows a schematic structural diagram of a typical sentence pattern including design intent in the first embodiment of the present application.
In one embodiment, a typical schema containing design intent includes: the design literature information is connected with the design scheme information through a description relationship, the design scheme information comprises a plurality of design objects, the design objects are connected through a structural relationship, and the design scheme information is connected with the design intention through an implementation relationship;
the credibility calculation formula containing the design intention information comprises the following steps:
DRC＝Max(Ilib,Ides)*Idef*Iimp
wherein, IlibTo design the weighting coefficients of the characteristic words of the document, IdesTo describe the weight coefficient of the relational feature words, IdefWeight of feature words for design objects, IimpTo realize the weight coefficient of the relation characteristic word, the value range is [0,1 ]]；
IobFor the weight coefficient of the design object, the parameter takes the value of [0,2 ] in one embodiment]；
In particular, a typical schema including design intent includes: (design literature) - [ describing relationships]->[ (design object) - [ structural relationship]->(design object)]- [ effecting relationship]Whether or not design rationality is included depends on the weight coefficient of a feature word such as a design document, a description relation, a design object, and an implementation relation. The design document characteristic words or the description relation characteristic words can be one with a large weight or factor value, the more the number of the design objects appears, the larger the weight coefficient is, and the closer the weight of the design object characteristic words is to 1. For example:Embodiments disclosed herein[ DESIGN DOCUMENT ] provide [ descriptiveness ]systems and methods[ DESIGN OBJECT ] for [ IMPLEMENTING RELATIONS ] obstacle detection and station information detection [ DESIGN INTENSION ].
Wherein,
“Embodiments
disclosed
the herein is a 'document characteristic word' in a 'design rationality characteristic word library', and the herein is a
libThe weight coefficient is that I is 0.99; "provides" is "descriptive relation feature words" in "design rationality feature word stock", and its weight
desThe coefficient is I-0.90; the value between the two is taken to be 0.99.
systems and methods are preset design object feature words, and are assumed to be a professional field of great interest
The feature words may have their weight coefficients set to 1.5 and 1.5.
Then it is determined that, defI＝2/3.14*arctan(1.5+1.5)＝0.795570556≈0.80。
the weight coefficient for implementing the relational feature word for is 0.85.
DRC＝0.99*0.80*0.85＝0.6732。
A typical schema that contains design issues, including: existence of relationship feature words and question feature words;
the credibility calculation formula containing the design problem information is as follows:
DRC＝Max(Ithr)*Iiss
wherein, IthrThe weight coefficient of the relation characteristic word exists, and Iiss is the weight of the characteristic word of the design problem;
in specific implementation, a typical schema including design issues is: - [ Presence of relationship]->(design problem), if there are a plurality of existing relation characteristic words, the value with the maximum weight coefficient is taken. For example: this creates [ existence relation, Ithr＝0.6】problems of[ problem characterization word, IissMobility, soil compatibility, as well interpretation schemes [ design issues ], as well as: from the above, it is event that the domains [ existence relationship, I ]thr＝0.9】a need[ problem characterization word, Iiss0.8 in the induced for more effective minimizing techniques at not more than five more than one less solution of the above described above [ design problem ].
A typical schema containing the structural relationships of a design scenario includes: the design literature information is connected with the design scheme information through a description relationship, the design scheme information comprises a plurality of design objects, and the design objects are connected through a structural relationship;
the reliability calculation formula containing the structural relationship of the design scheme comprises the following steps:
DRC＝Max(Ilib,Ides)*Istr
wherein, IlibTo design the weighting coefficients of the characteristic words of the document, IdesTo describe the weight coefficient of the relational feature words, IstrThe weight of the structural relation characteristic word;
arctan () is an arctangent function and an increasing function, and the theoretical value range is-pi/2; i issThe weight coefficient of a single structural relation has a value range of [0, 2%]The more the number of occurrences, the weighting factor IstrThe larger, thestrThe closer to 1; istr actually takes the value of [0,1]In the meantime.
In specific implementation, a typical sentence pattern including the structural relationship of the design scheme is: (design literature) - [ describing relationships]->[ (design object) - [ structural relationship]->(design object)]For example: one implementation [ design literature feature word ]includes(structural relationship) an appaatus (design object), where the appaatus (design object) includes a beacon, a designer (design object) configured to have a structural relationship/implementation relationship between a general operator more than one main loop of a controlled playback more than one anti-patent (CRPA) (design intention), where the CRPA (design object) includes a design objectis attached(structural relationship), direct or index, to object (design object); and a processor (design object)configured:to"structural relationship/implementation relationship" of associated signals structure of signals at variables directions [ design intent ]with physical locations of (structural relationship)a plurality of spaces [ design objects ], the family of spaces [ design objects ]comprise [ structural relationship ]sources of the signals [ design objects ]; andto (todo sth, implementation relation) determinationat least one of the above mentioned aspects of an individual of the object [ design intent ]based at least partly on(structural relationship) the orientation of the object with the prescription to the physical locations of space vehicles.
The sentence pattern is a complex sentence containing a plurality of semicolons, and in the actual processing, it will be carried out as a sentence
And (6) processing. "; "does not serve as a basis for segmenting sentences. The reliability calculation formula of whether the design scheme structural relationship is contained is as follows:
DRC＝Max(Ilib,Ides)*Istr
“One libthe embodiment is a 'document feature word' in a 'design rationality feature word library', and the weight coefficient of the embodiment is I des0.90; without the relational characterization word, I is 0, thenMax(Ilib,Ides)＝0.90；
includes,configured to，is attached，comprise，with physical locations of，based at least syntax partly on, etc. as structural relationship feature words. It is assumed that the inclusion thereof,configuredto，is the characteristic words of structure relation such as attached, contain, etc. are recorded into 'design rationality characteristic word stock', and the weighting coefficient thereof sI is 1.8, 1.5, 1.2, 1.8 respectively, then
Reliability:
DRC＝0.90*0.90024169≈0.81。
appaatus, beamform, CRPA, object, processor, space vehicles, sources, signs, etc. as design object feature words;
in the design rational feature word library, the appaatus, the processor and the space events are predefined design object feature words defDT, and the weighting coefficients Iob (the weighting coefficients of the feature words of the customized/predefined design object) are respectively 1, 1.5 and 1.8; assuming that the remaining feature words (templates, CRPA, objects, sources of the signatures) are not predefined in the design rationale feature lexicon; then Idef＝2/3.14*arctan(1+1.5+1.8)＝0.854967954。
Generally, the technical literature describes technical solutions in a neutral language without accompanying personal emotions. However, designers can analyze and judge the defects of other design schemes; the problems and the requirements of the current situation are described by the defect words, the negative words, the depreciation words and the like. For the design scheme which is popular and advocated by the designer, recognition, positive expression and advantageous vocabulary are used for expression. Therefore, the visual angle of a designer can be found out through emotion analysis, and the advantage information and the defect information of the design scheme can be found out. Therefore, the advantages of the design, the disadvantages of the design, and the like can be determined by the advantage characteristic words and the disadvantage characteristic words, and the typical sentence pattern may not be adopted.
The reliability calculation formula containing the advantage and disadvantage information is as follows:
wherein, IproThe influence factor of the ith advantageous feature word in the sentence takes a positive value, (0, 1), IconIs the influence factor of a single i defect feature words in the sentence, and takes a negative value (-1, 0).
For example: the instability schemes [ Defect characteristics word, Icon0.9 of produced fan VTOLUAVs, documents [ Defect signatures, Icon0.9 still haunt [ shortcoming signatures, I ]con0.9 even the best success ful [ advantageous characteristics word, Ipro0.9 quern [ advantageous characteristics word, I ]con＝0.7】vehicles。
In one embodiment, if the target sentence does not conform to the typical sentence pattern, the grammatical rules of the design rationality information in the sentence can be further analyzed, such as:
(a) the design intent information can be identified and extracted through NLTK grammar rule analysis. The design intention structure is grammars such as 'to do sounding' or 'for sounding' and 'for doing sounding', an NLTK grammar rule is established, and design intention information in the NLTK grammar rule is extracted through a tree node method;
(b) for the design problem information, in view of the wide variety of design problem expression modes, the whole sentence can be taken as design rational information for extraction, and the feature words are not extracted any more;
(c) for design alternatives, the expression mode is also large, and the whole sentence can be extracted as design rational information. Alternatives with a better structure of a particular format, such as patent document No. may also extract information such as patent number.
In one embodiment, the identifying entity information and relationship information in the sentence containing design rationality information includes:
identifying entity information and relationship information in the sentence containing the design rationality information according to a pre-constructed design rationality feature word stock;
the design rational feature word library comprises stop words, professional feature words and rational feature words, and any rational feature word has a weight value; the rational characteristic words comprise design rational entity information characteristic words and design rational relation information characteristic words, the design rational entity information characteristic words comprise design scheme characteristic words, document characteristic words, problem characteristic words, advantage characteristic words, defect characteristic words and alternative scheme characteristic words, and the design rational relation information characteristic words comprise description relation characteristic words, implementation relation characteristic words, structural relation characteristic words and existence relation characteristic words.
In specific implementation, the feature word library comprises stop words, professional feature words and rational feature words. The stop words can be articles, conjunctions, prepositions, etc. that do not affect the acquisition of design rationality knowledge, such as: a. an, the, we've, which, while, etc. The weight of the rational feature words can mean an influence importance degree coefficient of the feature words for determining whether the rational design information is contained, and the value is generally 0-1. The rational characteristic words can comprise design rational entity information characteristic words and design rational relation information characteristic words.
The design rational entity information feature words comprise:
(1) design object feature words
The design object feature words may be design field feature words concerned by the user, and may be used as input for design rational knowledge extraction, for example: un-manual Material Vehicle, unmanaged aerol System, UAV, methods and systems, base station, organizational recovery mode, organizational safety beacon, etc.
(2) Characteristic words of documents
A document feature word may be a feature word describing a document title, such as: thisdisclosure, Disclosed, Embodiments of The present invention, The presentinvention, etc. among The patent information.
(3) Question feature word
The question feature words may be feature words for marking questions, requirements, such as: static publications, technical issues, the project of, the projects, complex issues, requisition for, etc.
(4) Character word with advantages
The advantage feature words can be feature words used for expressing the advantages of good application prospect, special quality effect and the like of the design scheme. In specific implementation, according to the degree of association between the feature words and the actual advantages, influence factors/weights can be introduced.
The merit characteristics words can be divided into two categories: one category is a general advantageous feature word, applicable to various professional fields, but may have low expressive force and accuracy, and small impact factors/weights, such as: available, benefifits, clear, easy, famous, match, etc.; the other is a typical feature word special for a specific field, and the influence factor/weight is large, such as: lesscomplex, high speed, easy to assign, small sizes, etc.
(5) Defect character word
The defect feature words are opposite to the advantage feature words, and the feature words for expressing the design defects and the design defects are closely related to the design requirements and the design problems. Defect signatures can be divided into two categories: one category is a general defect signature, applicable to various professional areas, but may have low expressive power and accuracy, and small impact factors/weights, such as: errors, fail, famine, fatigue, gloomy, obstacles, etc.; the other is a typical feature word special for a specific field, and the influence factor/weight is large, such as: not chemical, not commercial visual, limiting factors, compositional safety, etc.
(6) Alternative feature words
Alternative feature words may be feature words used to label alternatives, other designs cited or referenced, such as: US Patent Application, u.s.patent.no. etc.
The design intention represents various forms, has no specific characteristic words, and can find the design intention information by combining context and other related characteristic words when in specific implementation.
Designing a rational relation information characteristic word, comprising:
(1) describing relational feature words such as: are featured, descriptions, are, arespecified to, areisolated, areprovided, etc.
(2) Implementing relational feature words, such as: to do something, for doing something, so as to; are designed to, etc.
(3) There are relational feature words, such as: there is, there exists, there domains, etc.
(4) Structural relationship feature words including composition/inclusion relationship, arrangement relationship, association relationship, connection relationship, etc., such as: the component, continain, include, etc. represent the composition relationship; other relational feature words such as is located between, is coupled to, be attached to, isconfigured to, and the like.
The solution relation is an implicit relation between the design scheme and the design problem, the expression relation is an implicit relation between the design problem and the defect information, the possessed relation is a relation between the design scheme and the alternative scheme, and the solution relation, the expression relation and the possessed relation can be expressed without explicit characteristic words during specific implementation.
In specific implementation, the sentence containing the design rationality information is extracted and determined according to the typical sentence pattern, and after the target sentence containing the design rationality information is determined, the design rationality information can be further identified according to the characteristic words. For example:
The design must have objectives of automation,intelligence,and zero-configuration for objects and related devices in order to achieve scalabilityand interoperability.
stop words: the, must, and;
rational characteristic words: design (document feature words), have objects of (implementation relation feature words), and order to achievee (implementation relation feature words);
the extracted design rationality information:
the design intention is as follows: automatic, interpretation, zero-configuration for objects and dried devices;
the design intention is as follows: scalability; interoperability;
professional characteristic words: automation, interference, zero-configuration, objects, devices, scalability, interoperability.
For another example:
Thus,there is a strong desire,from both a cost and safetyperspective,to reduce the number of tower climbs.
rational characteristic words: there is a string default (design problem feature word);
implementing a relational feature sentence pattern: to do something;
the extracted design rationality information:
design issue/requirement: from bottom a cost and availability property, to reduce the number of top clips.
In specific implementation, the process of establishing the feature sentence pattern library and the feature word library (or called feature dictionary library) comprises the following steps:
(1) and selecting a certain number of design documents (the more the number is, the higher the accuracy is) as objects for training the characteristic sentence patterns and the characteristic words.
(2) And manually marking the selected training documents by a person with certain design rational identification capability.
(3) Typical characteristic sentence patterns and characteristic words are marked.
(4) The weighting coefficients of the feature words are evaluated manually or by a specific algorithm. (the rational feature word weight value refers to an influence importance degree coefficient of the feature word for determining whether the design rational information is contained, and the value is generally 0-1).
And summarizing and processing the marked characteristic sentence patterns and characteristic words, removing inaccurate and inappropriate contents, and sorting and storing the inaccurate and inappropriate contents in a characteristic sentence pattern library and a characteristic word library.
After a typical sentence pattern with rational design is constructed, whether a target sentence contains related characteristic words or not is matched in the modes of vocabulary/phrase traversal, regular operation retrieval matching and the like, and if the characteristic words are matched, the reliability DRC of the rational design information is calculated according to a reliability calculation formula of the rational design information.
For example: this disclosure [ design literature characterization words ] is directed to [ description relation characterization words ] evaluation and avoidanceapparatusforan (stop words)unmanned aerial vehicle("UAV")andsystems,devices,andtechniques[ predefined/input design object feature words ] relating to [ implementation relation feature words ] automatic object detection and avidity during UAV flight [ design intent to extract ].
For, an, and etc. in the design object are required to be removed [ stop words ].
For another example: the computing device [ design object feature word ] may [ implementation relation feature word ] include UAV to collection mapping on The property using one or more templates [ design object feature word ] of The UAV [ design object feature word ].
The, one or more, of The, is a stop word; however, the instruction the UAV to collect information on the property. The intermediate to the words may not be removed, which affects the readability/intelligibility of the feature words.
The following steps are repeated: in an aspect of the present application [ design literature characterization ],there is disclosed[ description relation characteristics word ] a UAV [ design object characteristics word ]including[ structural relationship: containing relationship (design object, which can be predefined or newly extracted)disposed on[ structural relationship: the UAV [ design object ], andconfigured[ structural relationship: arrangement relation to [ to dosth, which is an implementation relation ] capture image data [ extracted design intention ];and acontroller chip [ design object ] consistent to [ structural relationship: the image capturing module (design object)to[ todo sth, is an implementation relation ] receive and process the image data [ design intent of extraction ]; and the [ stop words ] controller chip [ design object ] is configured to [ structural relationship: arrangement of the UAV [ design intent of extraction ].
In one embodiment, the extracting entity information and relationship information in the object of the extraction of the design rational knowledge includes:
dividing the data in the extraction object of the design rational knowledge into sentences as units;
judging a target sentence by using a design rationality information identification model obtained by pre-training, and extracting entity information and relationship information in an extraction object of the design rationality knowledge;
and the design rational information identification model obtained by pre-training is obtained by training the training text data by adopting a Fasttext algorithm.
In specific implementation, sentences containing information such as design intentions, design problems, design objects, advantage/disadvantage descriptions, alternative schemes and the like can be marked to form trained text data, and a Fasttext algorithm is adopted to train the trained text data to obtain a recognition model of design rational information; and judging the target sentence according to the identification model, and judging which design rationality information is contained, thereby realizing the extraction of information such as design problems, design intentions, structural relationships, alternative schemes, design advantages and disadvantages and the like.
In particular, the training process for machine learning data includes:
(1) and selecting a certain number of design documents (the more the number is, the higher the accuracy is) as objects for training the characteristic sentence patterns and the characteristic words.
(2) And marking the selected training documents by a person with certain design rational identification capability.
(3) Based on a FastText classification algorithm, sentences containing information such as design intents, design problems, design objects, advantage and disadvantage descriptions, alternative schemes and the like are marked to form trained text data.
(4) And summarizing and processing the marked characteristic sentence patterns and characteristic words, removing inaccurate and inappropriate contents, and sorting and storing the inaccurate and inappropriate contents in a characteristic sentence pattern library and a characteristic word library.
In one embodiment, the method further comprises:
representing the extraction object of the design rational knowledge in the following way:
designing document information as a node, and pointing to a plurality of sentence nodes containing design rational information contained in the extraction object of the design rational knowledge respectively;
pointing to defect description information nodes in a relationship, wherein the defect description information nodes point to specific feature words contained in the defect description information respectively;
directing design scheme information nodes by structural relations, wherein the design scheme information nodes respectively direct design object nodes contained in the design scheme information by the structural relations so as to achieve the effect that the relations point to design intention information nodes and the relations point to alternative scheme information nodes; the design intention information node points to a design problem information node in a solution relationship;
pointing to a plurality of design object information in a descriptive relationship;
the design issue information nodes are pointed to by the presence relationship, and the design issue information nodes are pointed to by the representation relationship.
The embodiment of the application forms the extracted rational design information into an organic whole. Associating the extracted information of design objects, design problems or design intentions, design schemes, design scheme advantages and disadvantages, decision reasons and the like by relating relationships, solving relationships, having relationships, being in accordance with relationships and the like; and storing the extracted design rational information into a knowledge map database through a triple structure of the knowledge map to form the design rational knowledge base with the design venation in the field.
Example two
Based on the same invention concept, the embodiment of the application provides a body construction device for designing rational knowledge, the principle of the device for solving the problems is similar to that of a body construction method for designing rational knowledge, and repeated parts are not repeated.
Fig. 3 shows a schematic structural diagram of an ontology construction device for designing rational knowledge in the second embodiment of the present application.
As shown in the figure, the ontology construction device for designing rational knowledge comprises:
an object determination module 301, configured to determine an extraction object of design rationality knowledge;
an information extraction module 302, configured to extract entity information and relationship information in an extraction object of the design rationality knowledge;
the association module 303 is configured to establish association between the entity information by using the relationship information;
the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship.
By adopting the ontology construction device for designing rational knowledge provided by the embodiment of the application, six kinds of entity information and six kinds of relation information are designed, the entity information and the relation information are extracted from the extraction object containing the design rational knowledge, and then the entity information and the relation information are associated with each other, so that an ontology for obtaining the design rational knowledge is constructed, reference or inspiration is provided for the innovative design of designers, and the knowledge reuse of information resources is facilitated.
In one embodiment, the information extraction module includes:
the sentence extraction unit is used for matching the feature words in a pre-constructed design rational sentence pattern library, calculating the credibility of the design rational information according to the feature words obtained by matching, and extracting sentences containing the design rational information in the extraction object of the design rational knowledge;
the information identification unit is used for identifying entity information and relationship information in the sentence containing the design rationality information according to a pre-constructed design rationality feature word stock;
the design rational sentence pattern library comprises design rational typical sentence patterns, and the typical sentence patterns comprise a plurality of rational characteristic words and professional characteristic words; the design rational characteristic word library comprises stop words, professional characteristic words and rational characteristic words.
EXAMPLE III
Based on the same inventive concept, embodiments of the present application provide a computer storage medium, which is described below.
The computer storage medium has a computer program stored thereon, which, when being executed by a processor, carries out the steps of the method according to an embodiment.
By adopting the computer storage medium provided by the embodiment of the application, six kinds of entity information and six kinds of relation information are designed, the entity information and the relation information are extracted from an extraction object containing design rational knowledge, and then the entity information and the relation information are associated to construct an ontology of the design rational knowledge, so that reference, reference or inspiration is provided for the innovative design of designers, and the knowledge reuse of information resources is facilitated.
Example four
Based on the same inventive concept, embodiments of the present application provide an electronic device, which is described below.
Fig. 4 shows a schematic structural diagram of an electronic device in the fourth embodiment of the present application.
As shown, the electronic device includes a memory for storing one or more programs, and one or more processors; the one or more programs, when executed by the one or more processors, implement the method of embodiment one.
By adopting the electronic equipment provided by the embodiment of the application, six kinds of entity information and six kinds of relation information are designed, the entity information and the relation information are extracted from an extraction object containing design rational knowledge, and then the entity information and the relation information are associated, so that a body of the design rational knowledge is constructed, reference or inspiration is provided for the innovative design of designers, and the knowledge reuse of information resources is facilitated.
EXAMPLE five
In order to facilitate the implementation of the present application, the embodiments of the present application are described with a specific example.
FIG. 5 shows a schematic diagram of a design rational knowledge acquisition process in the fifth embodiment of the present application.
The first step, data are collected from related patent office websites and stored in a database, and the collected data comprise: patent literature information such as patent names and patent numbers, and related text data such as patent abstract information, patent description information (including background description information, brief description information, and claim information).
Assume that the patent names of the patent documents are: an unmanned vehicle servicing tool.
And secondly, carrying out pretreatment such as data cleaning on the data in the database, and extracting effective data, wherein the pretreatment comprises the following steps: patent name (Patent Title), Patent Number (Patent Number), Abstract information (Abstract), Background description information (Background), Summary information (Summary, extract the first 6 sentences).
And thirdly, reading the source data and cutting the source data of the patent documents into sentence lists.
And fourthly, identifying sentences containing design rational knowledge.
Judging whether the sentence contains corresponding characteristic words and characteristic sentence patterns or not by utilizing a pre-established typical sentence pattern library, judging whether each sentence contains design rational knowledge or not, and identifying the sentence containing the design rational knowledge;
or judging whether each sentence contains design rational information or not by using labeled text data obtained by pre-training and using a FastText algorithm, and identifying the sentence containing the design rational knowledge.
Suppose that the sentence containing design rationality information in the patent is extracted, including:
there are design problems, "the is thermal between the new and the product associated with operation on the fire and the other electronic device located in the area of the same and the same as the as and the new to the new and the same as the entity associated with the same and the human body for the same"
Contains a design object, realizes a design intention, "In one aspect,the present inventionprovides asystem for maintaining equipmentwithin a predetermined area,including afirst unmanned vehicleconfiguredto perform a diagnostic evaluation of the equipment,asecond unmanned vehicleconfiguredto perform a maintenance operation,and athird unmanned vehicleconfiguredto perform a safety operation.”
a design object, "Acomputer-implemented methodof performing anautomated maintenance operation on a piece of equipment includingdetermining,using aprocessor system,adiagnostic status of the piece of equipmentusing a firstunmanned vehicle,and determined using theprocessor system,amaintenance condition of the piece of equipment.”
With the disadvantage of "A service person' slimitedmaneuverability when on a ladderincreases theriskoffallingor seriousinjuryduring a maintenanceoperation.”
Describes a design object "Maintenance of infrastructurethat includesfixturesor otherequipmentcan be difficult depending on thelocation of the equipment.”
And fifthly, extracting design rational information from the sentences containing the design rational knowledge.
Extracting design rational information in the sentence by using typical characteristic word recognition analysis; or, the machine learning mode is utilized to extract the design rationality information.
The design rationality information includes: design, advantages and disadvantages, design intent, design issues, alternatives, and the like.
And sixthly, storing, expressing and displaying the rational design knowledge through a knowledge graph.
And forming the extracted rational design information into an organic whole. Associating the extracted information of design objects, design problems or design intentions, design schemes, design scheme advantages and disadvantages, decision reasons and the like by relating relationships, solving relationships, having relationships, being in accordance with relationships and the like;
fig. 6 shows a schematic representation of design rationality knowledge in example five of the present application.
And storing the extracted design rational information into a knowledge map database through a triple structure of the knowledge map to form the design rational knowledge base with the design venation in the field.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (12)
1. A method for ontology construction of design rational knowledge, comprising:
determining an extraction object of design rational knowledge;
extracting entity information and relationship information in an extraction object of the design rational knowledge;
establishing association between entity information by using relationship information;
the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship.
2. The method of claim 1, wherein the associating entity information with relationship information comprises:
establishing association between the design literature information and the design object information through a description relation;
establishing association between the design scheme information and the design intention information through an implementation relation;
the design scheme information comprises a plurality of design objects, and the plurality of design objects are associated through a structural relationship;
establishing association between the design intention information and the design problem information through a solution relation;
establishing association between the design scheme information and the design problem information through the existence of relationship;
establishing association between the design problem information and the defect description information through an expression relationship;
and establishing association by having relationship between the design scheme information and the alternative scheme information.
3. The method of claim 1, wherein the extracting entity information and relationship information in the object of extraction of the design rationality knowledge comprises:
extracting sentences containing design rational information in the extraction objects of the design rational knowledge;
and identifying entity information and relationship information in the sentence containing the design rationality information.
4. The method according to claim 3, wherein the extracting the sentence containing design rational information in the object of extraction of the design rational knowledge comprises:
matching characteristic words in a pre-constructed design rational sentence pattern library;
calculating the credibility of the design rational information according to the feature words obtained by matching, and extracting sentences containing the design rational information in the extraction object of the design rational knowledge;
the design rational sentence pattern library comprises design rational typical sentence patterns, and the typical sentence patterns comprise a plurality of rational characteristic words and professional characteristic words.
5. The method of claim 4,
the credibility calculation formula containing the design intention information comprises the following steps:
DRC＝Max(Ilib，Ides)*Idef*Iimp
wherein, IlibTo design the weighting coefficients of the characteristic words of the document, IdesTo describe the weight coefficient of the relational feature words, IdefCharacteristic word weight coefficient for design object, IimpTo implement the weight coefficient of the relational feature word; i isdef＝2/π*arctan(∑Iob) In which IobWeight coefficients for the predefined design objects;
the credibility calculation formula containing the design problem information is as follows:
DRC＝Max(Ithr)*Iiss
wherein, IthrWeight coefficient for existence of relational feature words, IissWeights for feature words of the design problem;
the reliability calculation formula containing the structural relationship of the design scheme comprises the following steps:
DRC＝Max(Ilib，Ides)*Istr
wherein, IlibTo design the weighting coefficients of the characteristic words of the document, IdesTo describe the weight coefficient of the relational feature words, IstrThe weight of the structural relation characteristic word; i isstr＝2/π*arctan(∑Is)；IsThe arctan () arctangent function is the weight coefficient for a single structural relationship.
6. The method of claim 3, wherein the identifying entity information and relationship information in the sentence containing design rationality information comprises:
identifying entity information and relationship information in the sentence containing the design rationality information according to a pre-constructed design rationality feature word stock;
the design rational feature word library comprises stop words, professional feature words and rational feature words, and any rational feature word has a weight value; the rational characteristic words comprise design rational entity information characteristic words and design rational relation information characteristic words, the design rational entity information characteristic words comprise design scheme characteristic words, document characteristic words, problem characteristic words, advantage characteristic words, defect characteristic words and alternative scheme characteristic words, and the design rational relation information characteristic words comprise description relation characteristic words, implementation relation characteristic words, structural relation characteristic words and existence relation characteristic words.
7. The method of claim 1, wherein the extracting entity information and relationship information in the object of extraction of the design rationality knowledge comprises:
dividing the data in the extraction object of the design rational knowledge into sentences as units;
judging a target sentence by using a design rationality information identification model obtained by pre-training, and extracting entity information and relationship information in an extraction object of the design rationality knowledge;
and the design rational information identification model obtained by pre-training is obtained by training the training text data by adopting a Fasttext algorithm.
8. The method of claim 1, further comprising:
representing the extraction object of the design rational knowledge in the following way:
designing document information as a node, and pointing to a plurality of sentence nodes containing design rational information contained in the extraction object of the design rational knowledge respectively;
pointing to defect description information nodes in a relationship, wherein the defect description information nodes point to specific feature words contained in the defect description information respectively;
directing design scheme information nodes by structural relations, wherein the design scheme information nodes respectively direct design object nodes contained in the design scheme information by the structural relations so as to achieve the effect that the relations point to design intention information nodes and the relations point to alternative scheme information nodes; the design intention information node points to a design problem information node in a solution relationship;
pointing to a plurality of design object information in a descriptive relationship;
the design issue information nodes are pointed to by the presence relationship, and the design issue information nodes are pointed to by the representation relationship.
9. An ontology-building apparatus for designing rational knowledge, comprising:
the object determination module is used for determining an extraction object of design rational knowledge;
the information extraction module is used for extracting entity information and relationship information in an extraction object of the design rational knowledge;
the association module is used for establishing association between the entity information by utilizing the relationship information;
the entity information comprises design literature information, design scheme information, alternative scheme information, design intention information, design problem information and advantage and disadvantage description information; the relationship information includes description relationship, implementation relationship, structural relationship, solution relationship, existence relationship, and existence relationship.
10. The apparatus of claim 9, wherein the information extraction module comprises:
the sentence extraction unit is used for matching the feature words in a pre-constructed design rational sentence pattern library, calculating the credibility of the design rational information according to the feature words obtained by matching, and extracting sentences containing the design rational information in the extraction object of the design rational knowledge;
the information identification unit is used for identifying entity information and relationship information in the sentence containing the design rationality information according to a pre-constructed design rationality feature word stock;
the design rational sentence pattern library comprises design rational typical sentence patterns, and the typical sentence patterns comprise a plurality of rational characteristic words and professional characteristic words; the design rational characteristic word library comprises stop words, professional characteristic words and rational characteristic words.
11. A computer storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
12. An electronic device comprising one or more processors, and memory for storing one or more programs; the one or more programs, when executed by the one or more processors, implement the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010662266.8A CN111898371B (en) | 2020-07-10 | 2020-07-10 | Ontology construction method and device for rational design knowledge and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010662266.8A CN111898371B (en) | 2020-07-10 | 2020-07-10 | Ontology construction method and device for rational design knowledge and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111898371A true CN111898371A (en) | 2020-11-06 |
| CN111898371B CN111898371B (en) | 2022-08-16 |
Family
ID=73192239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010662266.8A Active CN111898371B (en) | 2020-07-10 | 2020-07-10 | Ontology construction method and device for rational design knowledge and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898371B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113987212A (en) * | 2021-11-17 | 2022-01-28 | 武汉理工大学 | Knowledge graph construction method for process data in numerical control machining field |
| CN117217308A (en) * | 2023-11-08 | 2023-12-12 | 中国标准化研究院 | Construction method, device and storage medium of design rationality knowledge network |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050120001A1 (en) * | 2003-09-06 | 2005-06-02 | Oracle International Corporation | SQL structure analyzer |
| EP1639510A1 (en) * | 2003-06-24 | 2006-03-29 | BAE Systems PLC | A method, tool and system for increasing the efficiency of a design process |
| CN107194609A (en) * | 2017-06-15 | 2017-09-22 | 北京理工大学 | A kind of product design system and method |
| CN107590319A (en) * | 2017-08-23 | 2018-01-16 | 南京理工大学 | A kind of knowledge modeling method and system for engineering goods scheme Computer Aided Design |
| CN107622047A (en) * | 2017-09-04 | 2018-01-23 | 北京航空航天大学 | A kind of extraction of design decision knowledge and expression |
| CN107644257A (en) * | 2017-09-28 | 2018-01-30 | 北京航空航天大学 | A kind of individual design decision-making train of thought extracting method based on design concept knowledge model |
| CN108491581A (en) * | 2018-02-27 | 2018-09-04 | 中国空间技术研究院 | A kind of design process knowledge reuse method and system based on design concept model |
| CN109840270A (en) * | 2018-12-23 | 2019-06-04 | 国网浙江省电力有限公司 | A kind of grid equipment approaches to IM based on Neo4j |
| CN111026842A (en) * | 2019-11-29 | 2020-04-17 | 微民保险代理有限公司 | Natural language processing method, natural language processing device and intelligent question-answering system |
-
2020
- 2020-07-10 CN CN202010662266.8A patent/CN111898371B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1639510A1 (en) * | 2003-06-24 | 2006-03-29 | BAE Systems PLC | A method, tool and system for increasing the efficiency of a design process |
| US20050120001A1 (en) * | 2003-09-06 | 2005-06-02 | Oracle International Corporation | SQL structure analyzer |
| CN107194609A (en) * | 2017-06-15 | 2017-09-22 | 北京理工大学 | A kind of product design system and method |
| CN107590319A (en) * | 2017-08-23 | 2018-01-16 | 南京理工大学 | A kind of knowledge modeling method and system for engineering goods scheme Computer Aided Design |
| CN107622047A (en) * | 2017-09-04 | 2018-01-23 | 北京航空航天大学 | A kind of extraction of design decision knowledge and expression |
| CN107644257A (en) * | 2017-09-28 | 2018-01-30 | 北京航空航天大学 | A kind of individual design decision-making train of thought extracting method based on design concept knowledge model |
| CN108491581A (en) * | 2018-02-27 | 2018-09-04 | 中国空间技术研究院 | A kind of design process knowledge reuse method and system based on design concept model |
| CN109840270A (en) * | 2018-12-23 | 2019-06-04 | 国网浙江省电力有限公司 | A kind of grid equipment approaches to IM based on Neo4j |
| CN111026842A (en) * | 2019-11-29 | 2020-04-17 | 微民保险代理有限公司 | Natural language processing method, natural language processing device and intelligent question-answering system |
Non-Patent Citations (2)
| Title |
|---|
| YING ZHONGZHANG 等: "A semantic representation model for design rationale of products", 《ADVANCED ENGINEERING INFORMATICS》 * |
| 刘继红 等: "设计决策脉络挖掘方法", 《计算机辅助设计与图形学学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113987212A (en) * | 2021-11-17 | 2022-01-28 | 武汉理工大学 | Knowledge graph construction method for process data in numerical control machining field |
| CN117217308A (en) * | 2023-11-08 | 2023-12-12 | 中国标准化研究院 | Construction method, device and storage medium of design rationality knowledge network |
| CN117217308B (en) * | 2023-11-08 | 2024-02-27 | 中国标准化研究院 | Construction method, device and storage medium of design rationality knowledge network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111898371B (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108121829B (en) | Software defect-oriented domain knowledge graph automatic construction method | |
| US10489439B2 (en) | System and method for entity extraction from semi-structured text documents | |
| Zubrinic et al. | The automatic creation of concept maps from documents written using morphologically rich languages | |
| CN111914558A (en) | Course knowledge relation extraction method and system based on sentence bag attention remote supervision | |
| US12039272B2 (en) | Method of training a natural language search system, search system and corresponding use | |
| CN112732934A (en) | Power grid equipment word segmentation dictionary and fault case library construction method | |
| CN106126619A (en) | A kind of video retrieval method based on video content and system | |
| JP2022508737A (en) | A system for searching natural language documents | |
| CN113168499A (en) | Method for searching patent document | |
| CN113254507B (en) | Intelligent construction and inventory method for data asset directory | |
| CN112328800A (en) | System and method for automatically generating programming specification question answers | |
| CN116501875B (en) | Document processing method and system based on natural language and knowledge graph | |
| CN107562919A (en) | A kind of more indexes based on information retrieval integrate software component retrieval method and system | |
| CN113919366A (en) | Semantic matching method and device for power transformer knowledge question answering | |
| CN106874397B (en) | Automatic semantic annotation method for Internet of things equipment | |
| CN111898371B (en) | Ontology construction method and device for rational design knowledge and computer storage medium | |
| CN107357765A (en) | Word document flaking method and device | |
| CN114997288A (en) | Design resource association method | |
| CN115858807A (en) | Question-answering system based on aviation equipment fault knowledge map | |
| Nabavi et al. | Leveraging Natural Language Processing for Automated Information Inquiry from Building Information Models. | |
| Sun | A natural language interface for querying graph databases | |
| CN116432965B (en) | Post capability analysis method and tree diagram generation method based on knowledge graph | |
| TW201502812A (en) | Text abstract editing system, text abstract scoring system and method thereof | |
| Dachapally et al. | In-depth question classification using convolutional neural networks | |
| CN111898370B (en) | Method and device for acquiring design rational knowledge and computer storage medium |
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 |