CN114218406A - Transmission solution generation method and system based on transmission knowledge graph - Google Patents
Transmission solution generation method and system based on transmission knowledge graph Download PDFInfo
- Publication number
- CN114218406A CN114218406A CN202210145492.8A CN202210145492A CN114218406A CN 114218406 A CN114218406 A CN 114218406A CN 202210145492 A CN202210145492 A CN 202210145492A CN 114218406 A CN114218406 A CN 114218406A
- Authority
- CN
- China
- Prior art keywords
- transmission
- entity
- solution
- knowledge
- corpus
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 333
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013507 mapping Methods 0.000 claims abstract description 37
- 238000000605 extraction Methods 0.000 claims description 36
- 230000004927 fusion Effects 0.000 claims description 33
- 238000007781 pre-processing Methods 0.000 claims description 17
- 238000002372 labelling Methods 0.000 claims description 16
- 239000003638 chemical reducing agent Substances 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 13
- 238000005461 lubrication Methods 0.000 claims description 10
- 238000007789 sealing Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000010129 solution processing Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 16
- 238000012549 training Methods 0.000 description 14
- 239000013598 vector Substances 0.000 description 14
- 238000004140 cleaning Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000002457 bidirectional effect Effects 0.000 description 4
- 125000004432 carbon atom Chemical group C* 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 206010033307 Overweight Diseases 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 230000001050 lubricating effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000314 lubricant Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a transmission solution generation method and a system based on a transmission knowledge graph, wherein the method comprises the following steps: collecting a transmission solution, and constructing a transmission knowledge information corpus based on the transmission solution; extracting core elements of the transmission solution, constructing a mode layer based on the core elements, constructing a data layer by utilizing entity information, relationship information and attribute information in the transmission knowledge information corpus, establishing association mapping between the data layer and the mode layer, and generating a transmission knowledge map based on the association mapping; the method includes collecting transmission solution expected factors, identifying solution requirements based on the solution expected factors, determining entity logical associations based on the solution expected factors and the transmission knowledge graph, and generating the transmission solution according to the solution requirements and the entity logical associations. The method can simplify the generation process of the transmission solution based on the transmission knowledge graph.
Description
Technical Field
The invention relates to the technical field of knowledge maps, in particular to a transmission solution generation method and system based on a transmission knowledge map.
Background
A Knowledge Graph (knowledgegraph) is a semantic network that describes conceptual entity events of an objective world and their relationships between them. Compared with the traditional database, the method has the advantages that only simple data storage is carried out, the knowledge graph takes entity concepts as nodes and relations as edges, potential semantic relations among knowledge are obtained through data mining, knowledge reasoning and other technologies and are visually displayed in a triple form, the knowledge graph converts massive unstructured or semi-structured knowledge into standard and reliable structured data, the semantic relations are mined through data processing and reasoning, accordingly, a highly interconnected semantic network is formed, support is provided for data mining and intelligent services, and the knowledge graph is constructed through key technologies such as knowledge modeling, knowledge extraction, knowledge representation, knowledge fusion, knowledge reasoning and the like.
The transmission solution determines a transmission mode according to factors such as power transmission requirements, environmental conditions, application duration, application intensity, space conditions and the like of specific application products and scenes, and further provides a motor, a speed reducer, various accessories and performance parameters thereof, a model selection collocation, a combined assembly mode, a lubrication sealing mode and the like to form an integrated solution.
The generation of the transmission solution needs specialized skills and knowledge, the design of a transmission mode, the model selection of equipment, the presetting of performance parameters, the measurement and calculation and the check of parameters such as execution power, torque, transmission ratio and the like are realized, the transmission solution needs to be designed independently for each specific case, the requirement on the professional degree of participators is high, and the consumed time is large.
Therefore, how to simplify the generation process of the transmission solution based on the transmission knowledge graph, improve the generation efficiency, and reduce the specialized dependence degree is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above problems, the present invention is intended to solve the problems that specialized skills and knowledge are required for the generation of a transmission solution, the requirement on the degree of expertise of a participant is high, and the number of man-hours is large.
The embodiment of the invention provides a transmission solution generation method based on a transmission knowledge graph, which comprises the following steps:
collecting a transmission solution, and constructing a transmission knowledge information corpus based on the transmission solution;
extracting core elements of the transmission solution, constructing a mode layer based on the core elements, constructing a data layer by utilizing entity information, relationship information and attribute information in the transmission knowledge information corpus, establishing association mapping between the data layer and the mode layer, and generating a transmission knowledge map based on the association mapping;
the method includes collecting transmission solution expected factors, identifying solution requirements based on the solution expected factors, determining entity logical associations based on the solution expected factors and the transmission knowledge graph, and generating the transmission solution according to the solution requirements and the entity logical associations.
In one embodiment, the collecting the driving solution and constructing a driving knowledge information corpus based on the driving solution comprises:
collecting an original description file of a transmission solution, and performing text preprocessing on the original description file to generate a transmission knowledge corpus;
and according to a preset rule, carrying out label marking on the transmission knowledge corpus to generate corpus marking, and constructing the transmission knowledge information corpus based on the transmission knowledge corpus and the corpus marking.
In one embodiment, the extracting core elements of the transmission solution, constructing a mode layer based on the core elements, defining a three-component framework by using entity information, relationship information and attribute information in the transmission knowledge information corpus, generating a data layer, establishing an association mapping between the data layer and the mode layer, and generating a transmission knowledge graph based on the association mapping includes:
extracting core elements of the transmission solution, constructing the triple framework based on the core elements, and generating the mode layer; the core elements of the transmission solution include, but are not limited to: the transmission solution comprises a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, a transmission mode, performance parameters, a combined assembly relation, lubrication sealing, application duration and application strength; and analyzing the entity, relationship, attribute and logic association of the core elements in the existing transmission solution, and constructing a three-tuple frame of 'entity-relationship-entity' or 'entity-attribute value';
extracting the transmission knowledge corpus based on the corpus label, and acquiring entity information, relationship information and attribute information in the transmission knowledge corpus by knowledge extraction;
filling the three-tuple frame based on the entity information, the relationship information and the attribute information, and associating the filled three-tuple frame based on a semantic relationship;
performing entity fusion by using a knowledge fusion algorithm to generate a data entity, and associating the filled three-tuple frame with the data entity to generate the data layer;
establishing the association mapping between the data layer and the mode layer, and combining the data layer and the mode layer based on the association mapping to generate a transmission knowledge graph.
In one embodiment, the performing entity fusion by using a knowledge fusion algorithm to generate a data entity includes:
comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
In one embodiment, the collecting transmission solution expectation factors, identifying a solution requirement based on the solution expectation factors, and determining an entity logical association based on the solution expectation factors and the transmission knowledge graph, the generating the transmission solution from the solution requirement and the entity logical association, comprises:
collecting the expected factors of the transmission solution, and preprocessing the expected factors of the transmission solution to generate keywords;
identifying solution requirements based on the keywords, and classifying the solution requirements by adopting a requirement classifier;
determining an entity in the transmission knowledge graph based on the keyword, determining an associated entity and an attribute value according to an entity relationship by taking the entity as a core node, and generating entity logic association based on the associated entity and the attribute value;
and screening the transmission solution by using the entity relation according to the logic association between the solution requirement and the entity, and sending the transmission solution to the user.
In a second aspect, the present invention also provides a transmission solution generation system based on a transmission knowledge-graph, comprising:
the transmission knowledge information corpus establishing module is used for acquiring a transmission solution and establishing a transmission knowledge information corpus based on the transmission solution;
the transmission knowledge map generation module is used for extracting core elements of the transmission solution, constructing a mode layer based on the core elements, constructing a data layer by utilizing entity information, relationship information and attribute information in the transmission knowledge information corpus, establishing association mapping between the data layer and the mode layer, and generating a transmission knowledge map based on the association mapping;
a transmission solution generation module to collect transmission solution expected factors, identify a solution requirement based on the solution expected factors, determine an entity logical association based on the solution expected factors and the transmission knowledge graph, and generate the transmission solution according to the solution requirement and the entity logical association.
In one embodiment, the driven knowledge information corpus construction module includes:
the transmission knowledge corpus generating unit is used for acquiring an original description file of a transmission solution, and performing text preprocessing on the original description file to generate a transmission knowledge corpus;
and the transmission knowledge information corpus establishing unit is used for labeling the transmission knowledge corpus according to a preset rule to generate corpus labels, and establishing the transmission knowledge information corpus based on the transmission knowledge corpus and the corpus labels.
In one embodiment, the transmission knowledge map generation module comprises:
the mode layer generating unit is used for extracting core elements of the transmission solution, constructing the triple framework based on the core elements and generating the mode layer; the core elements of the transmission solution include, but are not limited to: the transmission solution comprises a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, a transmission mode, performance parameters, a combined assembly relation, lubrication sealing, application duration and application strength; and based on the core elements of the transmission solution, analyzing the entities, relationships, attributes and logic associations of the core elements in the existing transmission solution, and constructing a ternary group frame of 'entity-relationship-entity' or 'entity-attribute value';
the knowledge extraction unit is used for extracting the transmission knowledge corpus based on the corpus label and acquiring entity information, relationship information and attribute information in the transmission knowledge corpus by knowledge extraction;
the triple frame filling unit is used for filling the triple frame based on the entity information, the relationship information and the attribute information, and associating the filled triple frame based on a semantic relationship;
the data layer generating unit is used for performing entity fusion by using a knowledge fusion algorithm to generate a data entity, and associating the filled three-tuple frame with the data entity to generate the data layer;
and the association mapping unit is used for establishing the association mapping between the data layer and the mode layer, combining the data layer and the mode layer based on the association mapping and generating the transmission knowledge graph.
In one embodiment, the performing entity fusion by using a knowledge fusion algorithm to generate a data entity includes:
comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
In one embodiment, the transmission solution generation module includes:
the keyword generation unit is used for acquiring the expected factors of the transmission solution, preprocessing the expected factors of the transmission solution and generating keywords;
a solution requirement identification unit, which is used for identifying solution requirements based on the keywords and classifying the solution requirements by adopting a requirement classifier;
the entity logic association generating unit is used for determining an entity in the transmission knowledge graph based on the key words, determining an associated entity and an attribute value according to an entity relationship by taking the entity as a core node, and generating entity logic association based on the associated entity and the attribute value;
and the transmission solution generating unit is used for screening the transmission solution by using the entity relation according to the logic association between the solution requirement and the entity, and sending the transmission solution to the user.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the method for generating the transmission solution based on the transmission knowledge graph provided by the embodiment of the invention generates the transmission knowledge graph based on the existing transmission solution, defines entity, relation and attribute information aiming at the transmission solution, generates the triple frame, associates the data entity by taking the triple frame as a basic composition unit, realizes the process of constructing the transmission knowledge graph aiming at the core elements of the transmission solution, realizes the quick matching of the corresponding transmission solution aiming at the expected factors of a user based on the logic association of the entities in the transmission knowledge graph, simplifies the generation process of the transmission solution, improves the generation efficiency and reduces the specialized dependence degree.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a transmission knowledge-map based transmission solution generation method provided by an embodiment of the present invention;
FIG. 2 is a flowchart of a step S101 provided in an embodiment of the present invention;
FIG. 3 is a flowchart of step S102 according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a BERT-BilSTM-CRF model provided in an embodiment of the present invention;
FIG. 5 is a flowchart of step S103 according to an embodiment of the present invention;
FIG. 6 is a block diagram of a transmission knowledge-map based transmission solution generation system provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, an embodiment of the present invention provides a transmission solution generation method based on a transmission knowledge graph, including: S101-S103;
s101, collecting a transmission solution, and constructing a transmission knowledge information corpus based on the transmission solution.
Specifically, the collected original description file of the existing transmission solution is subjected to text preprocessing to generate a structured transmission knowledge corpus, the structured transmission knowledge corpus is subjected to label marking according to a preset rule, and a corpus label is generated based on the transmission knowledge corpus and the corpus label.
S102, extracting core elements of the transmission solution, constructing a mode layer based on the core elements, constructing a data layer by utilizing entity information, relationship information and attribute information in the transmission knowledge information corpus, establishing association mapping between the data layer and the mode layer, and generating a transmission knowledge graph based on the association mapping; the core elements of the transmission solution include, but are not limited to: the transmission solution comprises a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, a transmission mode, performance parameters, a combination and assembly relation, lubrication sealing, application duration and application strength.
Specifically, the transmission knowledge graph comprises a mode layer and a data layer, the mode layer specifies a concept body, an attribute type, a relation and a structure level, the data layer stores entity data, and associates various data entities by taking triples as basic composition units to build an entity network of the transmission knowledge graph.
Further, the mode layer is constructed in a top-down mode, based on core elements of the transmission solution, entities, relations, attributes and logic associations of the core elements in the existing transmission solution are analyzed, a triple frame of the entity-relation-entity or the entity-attribute value is constructed, a triple frame of the entity-relation-entity or the entity-attribute value of the transmission knowledge graph is set, and therefore a concept setting basis is provided for construction of the data layer, hierarchical relations, semantic relations and attribute relations among all ontologies are defined, and the mode layer is defined.
Furthermore, the data layer is constructed in a bottom-up mode, from the transmission knowledge information corpus, knowledge extraction is applied, information such as entities, relations and attributes in the transmission knowledge corpus is obtained according to corpus labeling in the transmission knowledge information corpus, triples of types of entities-relations-entities and entities-attributes-attribute values are filled, and the triples are associated with each other according to semantic relations.
S103, collecting expected factors of a transmission solution, identifying solution requirements based on the expected factors of the solution, determining entity logic association based on the expected factors of the solution and the transmission knowledge graph, and generating the transmission solution according to the solution requirements and the entity logic association.
Specifically, a user inputs expected application products and scenes of the transmission scheme, expected factors such as power transmission requirements, environmental conditions, application duration, application intensity and space conditions, and performs solution requirement identification and generation of the transmission solution according to the expected factors.
In the embodiment, the transmission knowledge graph is generated based on the existing transmission solution, the entity, the relationship and the attribute information are defined aiming at the transmission solution, the triple frame is generated, the triple frame is taken as the basic composition unit, the data entity is associated, the process of constructing the transmission knowledge graph aiming at the core elements of the transmission solution is realized, the corresponding transmission solution is quickly matched aiming at the expected factors of the user based on the logic association of the entity in the transmission knowledge graph, the generation process of the transmission solution is simplified, the generation efficiency is improved, and the specialized dependence degree is reduced.
In one embodiment, referring to fig. 2, the acquiring a transmission solution and constructing a transmission knowledge information corpus based on the transmission solution in step S101 includes:
s1011, collecting an original description file of the transmission solution, and performing text preprocessing on the original description file to generate a transmission knowledge corpus.
Specifically, the text preprocessing comprises the steps of standardizing the character coding format of an original description file, and then carrying out corpus de-weighting and corpus cleaning, wherein the corpus de-weighting is to delete repeated contents by calculating the similarity between corpuses and prevent repeated repetition of a corpus, the corpus cleaning is to carry out text cleaning on the corpus after de-weighting, and irrelevant or meaningless corpus contents are filtered by matching the corpus contents after de-weighting with a stop word dictionary.
And S1012, according to a preset rule, labeling the transmission knowledge corpus to generate corpus labels, and constructing the transmission knowledge information corpus based on the transmission knowledge corpus and the corpus labels.
Specifically, according to a predetermined rule, labeling the transmission knowledge corpus includes: for the corpora which express the application products and the scenes in the transmission knowledge corpora, labels such as power transmission requirements, environmental conditions, application duration, application intensity, space conditions and the like are marked according to the content of each transmission knowledge corpora, and for the corpora which are related to the transmission solution expression in the transmission knowledge corpora, marks such as a transmission mode, a motor type selection, a speed reducer type selection, an accessory type selection, motor/speed reducer/accessory performance parameters, a combined assembly mode, a lubricating sealing mode and the like can be marked.
In one embodiment, referring to fig. 3, the extracting core elements of the transmission solution in step S102, constructing a mode layer based on the core elements, defining a three-component framework by using entity information, relationship information and attribute information in the transmission knowledge information corpus, generating a data layer, establishing an association mapping between the data layer and the mode layer, and generating a transmission knowledge graph based on the association mapping includes:
s1021, extracting core elements of the transmission solution, constructing the triple frame based on the core elements, and generating the mode layer.
Specifically, the core elements of the transmission solution include, but are not limited to: the transmission solution comprises a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, a transmission mode, performance parameters, a combination and assembly relation, lubrication sealing, application duration and application strength.
Specifically, aiming at the transmission solution, the transmission solution may include a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, and the like defined as entities, and the transmission solution may include a transmission mode, a combination assembly relationship, a lubrication seal, and the like defined as a "relationship", and the performance parameters, application duration, application intensity, etc. included in the transmission solution are defined as "attributes", the specific value is taken as an attribute value, and then based on core elements such as a transmission mode, performance parameters, a combined assembly relation, a lubrication seal, application duration, application strength and the like of a transmission solution, the entity, the relation, the attribute and the logic association of the core elements in the existing transmission solution are analyzed, and a three-group frame of 'entity-relation-entity' or 'entity-attribute value' is constructed. For example, the "motor-assembly-reducer", "reducer-filling lubricant-lubricant" is a "entity-relationship-entity" type ternary set frame, and the "reducer-torque value" is a "entity-attribute value" type ternary set frame.
And S1022, extracting the transmission knowledge corpus based on the corpus labeling, and acquiring entity information, relationship information and attribute information in the transmission knowledge corpus by knowledge extraction.
Specifically, the knowledge extraction includes entity extraction, relationship extraction and attribute extraction. The method comprises the following steps that an algorithm adopted by entity extraction adopts a named entity recognition algorithm, on the basis of early training, the natural language processing technology is used for automatically collecting entity contents in a corpus, meanwhile, collected data are added into a model, training is continuously carried out to improve accuracy, and finally, entity information in a text is sorted and summarized to establish an entity library; the relation extraction algorithm essentially obtains the concrete description of the logic association between entities or between entities and attributes in the text corpus, and obtains the potential meanings through the concrete description to construct the semantic relation between the entities, and the current relation extraction algorithm mainly comprises the following steps: manual marking combined with entity extraction, semantic relation recognition based on machine learning, relation recognition based on deep learning and a joint extraction algorithm combined with named entity recognition; the attribute extraction is to acquire attribute information of the entity, and the content form of the entity is richer through the attribute extraction.
Furthermore, as the named entity recognition algorithm has high labeling efficiency, but needs a large amount of data for training, has relatively low accuracy, and the selection of the entity labeling algorithm is often determined according to the data situation and the working requirement, the BERT-BilSTM-CRF model is adopted for entity extraction, and is a named entity recognition model formed by combining a BERT pre-training language model and a bidirectional long-short term memory network-conditional random field model (BilSTM-CRF).
Referring to fig. 4, the BERT-BilSTM-CRF model is divided into three layers, namely a first BERT layer, and the characteristics of the transmission knowledge information word vectors are extracted through a large amount of Chinese general linguistic data and a BERT general language model obtained through great calculation training to obtain low-dimensional word vectors; the second layer is a BilSTM layer, the bidirectional long-term and short-term memory network is trained by using a large amount of corpus labeled transmission knowledge corpus based on the understanding of the pre-training layer to the vector characteristics of the transmission knowledge information words, the inference labeling is carried out on the corpus entity sequence by using the context semantic information according to the model training result, and the entity types are further screened by setting the weight through the attention mechanism; and the third layer is a CRF layer, and according to the corpus entity sequence output by the BilSTM layer, a probability model is used for predicting and outputting an optimal expression of sequence tags, so that automatic sequence labeling of the corpus is realized, and named entity identification is completed.
S1023, filling the three-tuple frame based on the entity information, the relationship information and the attribute information, and associating the filled three-tuple frame based on a semantic relationship.
And S1024, performing entity fusion by using a knowledge fusion algorithm to generate a data entity, and associating the filled triple-component frame with the data entity to generate the data layer.
Specifically, the knowledge fusion is divided into two parts, namely ontology alignment and entity matching; the ontology alignment refers to comparing and confirming an ontology concept and a hierarchy of an entity to be confirmed, if the similarity of the hierarchy and the concept is high, the ontology is considered to be aligned, and the entity matching refers to confirming the similarity of the two entities on the contents such as entity names, entity relationships, attributes and the like.
Further, the performing entity fusion by using a knowledge fusion algorithm to generate a data entity includes: comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
Further, semantic similarity of the two entities on the contents of entity names, hierarchical categories, attributes and the like is calculated, wherein a comprehensive similarity vector is obtained by synthesizing single attribute similarity, and whether entity redundancy exists or not is determined, wherein a calculation formula of the single attribute similarity is as follows:
in the above formula, the first and second carbon atoms are,S AmBm representing the similarity of some attribute m of entity A, B,A m a certain attribute m representing the entity a,B m a certain attribute m representing the entity B,a i representing attributesA m The word frequency of the word-segmentation is high,b i representing attributesB m The word frequency of the participle, n represents the number of the participle.
Further, the air conditioner is provided with a fan,A m 、B m the total number of n participles in the semantic space is determined by statistical attributesA m 、B m Word frequency of each participlea i 、b i The word frequency vector (i.e. the comprehensive similarity vector) is constructed, and the similarity of the two sentences is determined through vector cosine value calculation.
Further, the similarity ratio of the entities a and B is generated by calculating the ratio of the semantic similarity of the entities a and B to the number of the attributes, and the calculation formula is as follows:
in the above formula, the first and second carbon atoms are,S A,B representing the similarity ratio of entities a, B, s representing the number of attributes,S A,B between 0 and 1, closer to 1 indicating a higher semantic similarity between the two entities.
S1025, establishing the association mapping between the data layer and the mode layer, and combining the data layer and the mode layer based on the association mapping to generate a transmission knowledge graph.
Specifically, the body in the mode layer and the relation thereof are mapped to a plurality of data entities of the data layer, the mapping between the data layer and the mode layer is established, and the data layer and the mode layer are combined to realize the construction of the transmission knowledge graph.
In one embodiment, referring to fig. 5, the collecting transmission solution expected factors, identifying solution requirements based on the solution expected factors, determining entity logical associations based on the solution expected factors and the transmission knowledge graph, and generating the transmission solution according to the entity logical associations and the solution requirements in step S103 includes:
and S1031, collecting the expected factors of the transmission solution, preprocessing the expected factors of the transmission solution, and generating keywords.
Specifically, for the expected factors of the transmission solution input by the user, if the input by the user is in a natural language format, preprocessing the expected factors input by the user, including word splitting processing, text disambiguation and keyword identification, wherein the word splitting processing means splitting the input problem of the user into a plurality of groups of words for representation; the text disambiguation is to remove meaningless components in the word segmentation result, eliminate the ambiguity of the text and prevent the phenomenon of word ambiguity from influencing the accuracy of applicability identification, and the text disambiguation mainly comprises the removal of stop words and part of speech tagging; and performing keyword identification aiming at the disambiguated text, and screening out core entities, relations or descriptions of the user question content.
Further, a TF-IDF (term frequency-inverse document frequency) weighting model is adopted for identifying and extracting the keywords, and the method comprises the following steps: inputting text into TF-IDF weighting model, determining wordst i Word frequency in texttf i The calculation formula is as follows:
wherein,n ij meaning termt i In the textd j The number of occurrences of (a) is,
is represented in textd j The sum of the number of occurrences of all words in (b).
Calculating reverse file frequencyidf i The calculation formula is as follows:
in the above equation, | D | represents the total number of texts in the corpus,
meaning including wordst i The number of texts.
Word calculation based on word frequency and reverse file frequencyt i TF-IDF value oftf idfi The calculation formula is as follows:
as can be seen from the above formula, the high word frequency in a specific document and the low document frequency of the word in the whole document set can generate a high-weight TF-IDF value, and further, the TF-IDF values of the words in the text are counted, and the word corresponding to the TF-IDF value compounded with the preset weight threshold value is selected as the keyword.
S1032, identifying solution requirements based on the keywords, and classifying the solution requirements by adopting a requirement classifier.
Specifically, the solution requirements in the expected factors of the transmission solution input by the user are analyzed, so that the solution generation conforming to the solution requirements is obtained in the subsequent matching process.
S1033, determining an entity in the transmission knowledge graph based on the keyword, determining an associated entity and an attribute value according to an entity relation by taking the entity as a core node, and generating entity logic association based on the associated entity and the attribute value.
S1034, according to the logic association between the solution requirement and the entity, screening the transmission solution by using the entity relation, and sending the transmission solution to the user.
Based on the same inventive concept, the embodiment of the invention also provides a transmission solution generation system based on the transmission knowledge graph, and as the principle of the problem solved by the system is similar to the transmission solution generation method based on the transmission knowledge graph, the implementation of the system can refer to the implementation of the method, and repeated parts are not repeated.
The transmission solution generation system based on the transmission knowledge graph provided by the embodiment of the invention is shown in fig. 6 and comprises:
and the transmission knowledge information corpus establishing module 61 is used for acquiring a transmission solution and establishing a transmission knowledge information corpus based on the transmission solution.
Specifically, the collected original description file of the existing transmission solution is subjected to text preprocessing to generate a structured transmission knowledge corpus, the structured transmission knowledge corpus is subjected to label marking according to a preset rule, and a corpus label is generated based on the transmission knowledge corpus and the corpus label.
And a transmission knowledge map generation module 62, configured to extract core elements of the transmission solution, construct a mode layer based on the core elements, construct a data layer by using entity information, relationship information, and attribute information in the transmission knowledge information corpus, establish an association mapping between the data layer and the mode layer, and generate a transmission knowledge map based on the association mapping.
Specifically, the transmission knowledge graph comprises a mode layer and a data layer, the mode layer specifies a concept body, an attribute type, a relation and a structure level, the data layer stores entity data, and associates various data entities by taking triples as basic composition units to build an entity network of the transmission knowledge graph.
Further, the mode layer is constructed in a top-down mode, a three-tuple frame of 'entity-relation-entity' or 'entity-attribute value' of the transmission knowledge graph is set based on core elements of the transmission solution, so that a concept setting basis is provided for construction of the data layer, and hierarchical relations, semantic relations and attribute relations among all ontologies are defined, so that the mode layer is defined.
Furthermore, the data layer is constructed in a bottom-up mode, from the transmission knowledge information corpus, knowledge extraction is applied, information such as entities, relations and attributes in the transmission knowledge corpus is obtained according to corpus labeling in the transmission knowledge information corpus, triples of types of entities-relations-entities and entities-attributes-attribute values are filled, and the triples are associated with each other according to semantic relations.
A transmission solution generation module 63 configured to collect transmission solution expected factors, identify a solution requirement based on the solution expected factors, determine an entity logical association based on the solution expected factors and the transmission knowledge graph, and generate the transmission solution according to the solution requirement and the entity logical association.
Specifically, a user inputs expected application products and scenes of the transmission scheme, expected factors such as power transmission requirements, environmental conditions, application duration, application intensity and space conditions, and performs solution requirement identification and generation of the transmission solution according to the expected factors.
In one embodiment, the driving knowledge information corpus constructing module 61 includes:
the driving knowledge corpus generating unit 611 is configured to collect an original description file of a driving solution, perform text preprocessing on the original description file, and generate a driving knowledge corpus.
Specifically, the text preprocessing comprises the steps of standardizing the character coding format of an original description file, and then carrying out corpus de-weighting and corpus cleaning, wherein the corpus de-weighting is to delete repeated contents by calculating the similarity between corpuses and prevent repeated repetition of a corpus, the corpus cleaning is to carry out text cleaning on the corpus after de-weighting, and irrelevant or meaningless corpus contents are filtered by matching the corpus contents after de-weighting with a stop word dictionary.
A driving knowledge information corpus establishing unit 612, configured to label the driving knowledge corpus according to a predetermined rule, generate corpus labels, and establish the driving knowledge information corpus based on the driving knowledge corpus and the corpus labels.
Specifically, according to a predetermined rule, labeling the transmission knowledge corpus includes: for the corpora which express the application products and the scenes in the transmission knowledge corpora, labels such as power transmission requirements, environmental conditions, application duration, application intensity, space conditions and the like are marked according to the content of each transmission knowledge corpora, and for the corpora which are related to the transmission solution expression in the transmission knowledge corpora, marks such as a transmission mode, a motor type selection, a speed reducer type selection, an accessory type selection, motor/speed reducer/accessory performance parameters, a combined assembly mode, a lubricating sealing mode and the like can be marked.
In one embodiment, the transmission knowledge map generation module 62 includes:
and a mode layer generating unit 621, configured to extract core elements of the transmission solution, construct the triple frame based on the core elements, and generate the mode layer.
Specifically, for a transmission solution, a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, and the like may be defined as entities, and then a "entity-relationship-entity" or a "entity-attribute value" ternary group framework is constructed based on a transmission manner, performance parameters, a combination assembly relationship, lubrication sealing, application duration, application strength, and the like of the transmission solution.
A knowledge extraction unit 622, configured to extract the transmission knowledge corpus based on the corpus label, and obtain entity information, relationship information, and attribute information in the transmission knowledge corpus by using knowledge extraction.
Specifically, the knowledge extraction includes entity extraction, relationship extraction and attribute extraction. The method comprises the following steps that an algorithm adopted by entity extraction adopts a named entity recognition algorithm, on the basis of early training, the natural language processing technology is used for automatically collecting entity contents in a corpus, meanwhile, collected data are added into a model, training is continuously carried out to improve accuracy, and finally, entity information in a text is sorted and summarized to establish an entity library; the relation extraction algorithm essentially obtains the concrete description of the logic association between entities or between entities and attributes in the text corpus, and obtains the potential meanings through the concrete description to construct the semantic relation between the entities, and the current relation extraction algorithm mainly comprises the following steps: manual marking combined with entity extraction, semantic relation recognition based on machine learning, relation recognition based on deep learning and a joint extraction algorithm combined with named entity recognition; the attribute extraction is to acquire attribute information of the entity, and the content form of the entity is richer through the attribute extraction.
Furthermore, as the named entity recognition algorithm has high labeling efficiency, but needs a large amount of data for training, has relatively low accuracy, and the selection of the entity labeling algorithm is often determined according to the data situation and the working requirement, the BERT-BilSTM-CRF model is adopted for entity extraction, and is a named entity recognition model formed by combining a BERT pre-training language model and a bidirectional long-short term memory network-conditional random field model (BilSTM-CRF).
The method comprises the following steps that a BERT-BilSTM-CRF model is divided into three layers, wherein the first BERT layer extracts the vector characteristics of transmission knowledge information words through a large amount of Chinese general linguistic data and a BERT general language model obtained through great calculation training to obtain low-dimensional word vectors; the second layer is a BilSTM layer, the bidirectional long-term and short-term memory network is trained by using a large amount of corpus labeled transmission knowledge corpus based on the understanding of the pre-training layer to the vector characteristics of the transmission knowledge information words, the inference labeling is carried out on the corpus entity sequence by using the context semantic information according to the model training result, and the entity types are further screened by setting the weight through the attention mechanism; and the third layer is a CRF layer, and according to the corpus entity sequence output by the BilSTM layer, a probability model is used for predicting and outputting an optimal expression of sequence tags, so that automatic sequence labeling of the corpus is realized, and named entity identification is completed.
A triple frame filling unit 623, configured to fill the triple frame based on the entity information, the relationship information, and the attribute information, and associate the filled triple frame based on a semantic relationship.
And the data layer generating unit 624 is configured to perform entity fusion by using a knowledge fusion algorithm to generate a data entity, and associate the filled triple-component frame with the data entity to generate the data layer.
Specifically, the knowledge fusion is divided into two parts, namely ontology alignment and entity matching; the ontology alignment refers to comparing and confirming an ontology concept and a hierarchy of an entity to be confirmed, if the similarity of the hierarchy and the concept is high, the ontology is considered to be aligned, and the entity matching refers to confirming the similarity of the two entities on the contents such as entity names, entity relationships, attributes and the like.
Further, the performing entity fusion by using a knowledge fusion algorithm to generate a data entity includes: comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
Further, semantic similarity of the two entities on the contents of entity names, hierarchical categories, attributes and the like is calculated, wherein a comprehensive similarity vector is obtained by synthesizing single attribute similarity, and whether entity redundancy exists or not is determined, wherein a calculation formula of the single attribute similarity is as follows:
in the above formula, the first and second carbon atoms are,
representing the similarity of some attribute m of entity A, B,A m a certain attribute m representing the entity a,B m a certain attribute m representing the entity B,a i representing attributesA m The word frequency of the word-segmentation is high,b i representing attributesB m The word frequency of the participle, n represents the number of the participle.
Further, the air conditioner is provided with a fan,A m 、B m the total number of n participles in the semantic space is determined by statistical attributesA m 、B m Word frequency of each participlea i 、b i To construct word frequency vectors (i.e., synthetic similarity vectors) for determining two sentences by vector cosine value calculationSimilarity.
Further, the similarity ratio of the entities a and B is generated by calculating the ratio of the semantic similarity of the entities a and B to the number of the attributes, and the calculation formula is as follows:
in the above formula, the first and second carbon atoms are,S A,B representing the similarity ratio of entities a, B, s representing the number of attributes,S A,B between 0 and 1, closer to 1 indicating a higher semantic similarity between the two entities.
An association mapping unit 625, configured to establish the association mapping between the data layer and the mode layer, and combine the data layer and the mode layer based on the association mapping to generate a transmission knowledge graph.
Specifically, the body in the mode layer and the relation thereof are mapped to a plurality of data entities of the data layer, the mapping between the data layer and the mode layer is established, and the data layer and the mode layer are combined to realize the construction of the transmission knowledge graph.
In one embodiment, the transmission solution generation module 63 includes:
and the keyword generating unit 631 is configured to collect the expected factors of the transmission solution, and preprocess the expected factors of the transmission solution to generate keywords.
Specifically, for the expected factors of the transmission solution input by the user, if the input by the user is in a natural language format, preprocessing the expected factors input by the user, including word splitting processing, text disambiguation and keyword identification, wherein the word splitting processing means splitting the input problem of the user into a plurality of groups of words for representation; the text disambiguation is to remove meaningless components in the word segmentation result, eliminate the ambiguity of the text and prevent the phenomenon of word ambiguity from influencing the accuracy of applicability identification, and the text disambiguation mainly comprises the removal of stop words and part of speech tagging; and performing keyword identification aiming at the disambiguated text, and screening out core entities, relations or descriptions of the user question content.
Further, a TF-IDF (term frequency-inverse document frequency) weighting model is adopted for identifying and extracting the keywords, and the method comprises the following steps: inputting text into TF-IDF weighting model, determining wordst i Word frequency in texttf i The calculation formula is as follows:
wherein,n ij meaning termt i In the textd j The number of occurrences of (a) is,
is represented in textd j The sum of the number of occurrences of all words in (b).
Calculating reverse file frequencyidf i The calculation formula is as follows:
in the above equation, | D | represents the total number of texts in the corpus,
meaning including wordst i The number of texts.
Word calculation based on word frequency and reverse file frequencyt i TF-IDF value oftf idfi The calculation formula is as follows:
as can be seen from the above formula, the high word frequency in a specific document and the low document frequency of the word in the whole document set can generate a high-weight TF-IDF value, and further, the TF-IDF values of the words in the text are counted, and the word corresponding to the TF-IDF value compounded with the preset weight threshold value is selected as the keyword.
A solution requirement identification unit 632, configured to identify solution requirements based on the keywords, and classify the solution requirements by using a requirement classifier.
Specifically, the solution requirements in the expected factors of the transmission solution input by the user are analyzed, so that the solution generation conforming to the solution requirements is obtained in the subsequent matching process.
And the entity logical association generating unit 633 is used for determining an entity in the transmission knowledge graph based on the keyword, determining an associated entity and an attribute value according to an entity relationship by taking the entity as a core node, and generating an entity logical association based on the associated entity and the attribute value.
A driving solution generating unit 634, configured to logically associate the solution requirement with the entity, filter the driving solution by using the entity relationship, and send the driving solution to the user.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A transmission solution generation method based on a transmission knowledge graph is characterized by comprising the following steps:
collecting a transmission solution, and constructing a transmission knowledge information corpus based on the transmission solution;
extracting core elements of the transmission solution, constructing a mode layer based on the core elements, constructing a data layer by utilizing entity information, relationship information and attribute information in the transmission knowledge information corpus, establishing association mapping between the data layer and the mode layer, and generating a transmission knowledge map based on the association mapping;
the method includes collecting transmission solution expected factors, identifying solution requirements based on the solution expected factors, determining entity logical associations based on the solution expected factors and the transmission knowledge graph, and generating the transmission solution according to the solution requirements and the entity logical associations.
2. The method of claim 1, wherein the collecting a driving solution and constructing a driving knowledge information corpus based on the driving solution comprises:
collecting an original description file of a transmission solution, and performing text preprocessing on the original description file to generate a transmission knowledge corpus;
and according to a preset rule, carrying out label marking on the transmission knowledge corpus to generate corpus marking, and constructing the transmission knowledge information corpus based on the transmission knowledge corpus and the corpus marking.
3. The method of claim 2, wherein the extracting core elements of the gear solution, constructing a mode layer based on the core elements, defining a three-component framework by using entity information, relationship information and attribute information in the gear knowledge information corpus, generating a data layer, establishing an association mapping of the data layer and the mode layer, and generating a gear knowledge graph based on the association mapping comprises:
extracting core elements of the transmission solution, constructing the triple framework based on the core elements, and generating the mode layer; the core elements of the transmission solution include, but are not limited to: the transmission solution comprises a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, a transmission mode, performance parameters, a combined assembly relation, lubrication sealing, application duration and application strength; and based on the core elements of the transmission solution, analyzing the entities, relationships, attributes and logic associations of the core elements in the existing transmission solution, and constructing a ternary group frame of 'entity-relationship-entity' or 'entity-attribute value';
extracting the transmission knowledge corpus based on the corpus label, and acquiring entity information, relationship information and attribute information in the transmission knowledge corpus by knowledge extraction;
filling the three-tuple frame based on the entity information, the relationship information and the attribute information, and associating the filled three-tuple frame based on a semantic relationship;
performing entity fusion by using a knowledge fusion algorithm to generate a data entity, and associating the filled three-tuple frame with the data entity to generate the data layer;
establishing the association mapping between the data layer and the mode layer, and combining the data layer and the mode layer based on the association mapping to generate a transmission knowledge graph.
4. The method of claim 3, wherein said performing entity fusion using a knowledge fusion algorithm to generate data entities comprises:
comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
5. The method of claim 1, wherein the collecting drive solution expected factors, identifying a solution need based on the solution expected factors, and determining an entity logical association based on the solution expected factors and the drive knowledge-graph, the generating the drive solution from the solution need and the entity logical association, comprises:
collecting the expected factors of the transmission solution, and preprocessing the expected factors of the transmission solution to generate keywords;
identifying solution requirements based on the keywords, and classifying the solution requirements by adopting a requirement classifier;
determining an entity in the transmission knowledge graph based on the keyword, determining an associated entity and an attribute value according to an entity relationship by taking the entity as a core node, and generating entity logic association based on the associated entity and the attribute value;
and screening the transmission solution by using the entity relation according to the logic association between the solution requirement and the entity, and sending the transmission solution to a user.
6. A transmission solution generation system based on a transmission knowledge graph, comprising:
the transmission knowledge information corpus establishing module is used for acquiring a transmission solution and establishing a transmission knowledge information corpus based on the transmission solution;
the transmission knowledge map generation module is used for extracting core elements of the transmission solution, constructing a mode layer based on the core elements, constructing a data layer by utilizing entity information, relationship information and attribute information in the transmission knowledge information corpus, establishing association mapping between the data layer and the mode layer, and generating a transmission knowledge map based on the association mapping;
a transmission solution generation module to collect transmission solution expected factors, identify a solution requirement based on the solution expected factors, determine an entity logical association based on the solution expected factors and the transmission knowledge graph, and generate the transmission solution according to the solution requirement and the entity logical association.
7. The system of claim 6, wherein the driven knowledge information corpus construction module comprises:
the transmission knowledge corpus generating unit is used for acquiring an original description file of a transmission solution, and performing text preprocessing on the original description file to generate a transmission knowledge corpus;
and the transmission knowledge information corpus establishing unit is used for labeling the transmission knowledge corpus according to a preset rule to generate corpus labels, and establishing the transmission knowledge information corpus based on the transmission knowledge corpus and the corpus labels.
8. The system of claim 7, wherein the transmission knowledge map generation module comprises:
the mode layer generation unit is used for extracting core elements of the transmission solution, constructing a three-component framework based on the core elements and generating the mode layer; the core elements of the transmission solution include, but are not limited to: the transmission solution comprises a motor, a speed reducer, various accessories, transmission requirements, environmental conditions, space conditions, a transmission mode, performance parameters, a combined assembly relation, lubrication sealing, application duration and application strength; and based on the core elements of the transmission solution, analyzing the entities, relationships, attributes and logic associations of the core elements in the existing transmission solution, and constructing a ternary group frame of 'entity-relationship-entity' or 'entity-attribute value';
the knowledge extraction unit is used for extracting the transmission knowledge corpus based on the corpus label and acquiring entity information, relationship information and attribute information in the transmission knowledge corpus by knowledge extraction;
the triple frame filling unit is used for filling the triple frame based on the entity information, the relationship information and the attribute information, and associating the filled triple frame based on a semantic relationship;
the data layer generating unit is used for performing entity fusion by using a knowledge fusion algorithm to generate a data entity, and associating the filled three-tuple frame with the data entity to generate the data layer;
and the association mapping unit is used for establishing the association mapping between the data layer and the mode layer, combining the data layer and the mode layer based on the association mapping and generating the transmission knowledge graph.
9. The system of claim 8, wherein said performing entity fusion using a knowledge fusion algorithm to generate data entities comprises:
comparing the ontology concept of the entity with the hierarchy, judging the ontology alignment according to the comparison result, calculating the semantic similarity of the entity according to the judgment result, setting a similarity threshold, and performing entity fusion based on the semantic similarity to generate a data entity.
10. The system of claim 6, wherein the transmission solution generation module comprises:
the keyword generation unit is used for acquiring the expected factors of the transmission solution, preprocessing the expected factors of the transmission solution and generating keywords;
a solution requirement identification unit, which is used for identifying solution requirements based on the keywords and classifying the solution requirements by adopting a requirement classifier;
the entity logic association generating unit is used for determining an entity in the transmission knowledge graph based on the key words, determining an associated entity and an attribute value according to an entity relationship by taking the entity as a core node, and generating entity logic association based on the associated entity and the attribute value;
and the transmission solution generating unit is used for screening the transmission solution by using the entity relation according to the logic association between the solution requirement and the entity, and sending the transmission solution to a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210145492.8A CN114218406A (en) | 2022-02-17 | 2022-02-17 | Transmission solution generation method and system based on transmission knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210145492.8A CN114218406A (en) | 2022-02-17 | 2022-02-17 | Transmission solution generation method and system based on transmission knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114218406A true CN114218406A (en) | 2022-03-22 |
Family
ID=80709268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210145492.8A Pending CN114218406A (en) | 2022-02-17 | 2022-02-17 | Transmission solution generation method and system based on transmission knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114218406A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115146081A (en) * | 2022-08-31 | 2022-10-04 | 合肥中科迪宏自动化有限公司 | Construction method and diagnosis method of fault diagnosis knowledge graph of production equipment |
| CN116681305A (en) * | 2023-06-05 | 2023-09-01 | 中国标准化研究院 | Emergency decision method based on knowledge graph |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008355A (en) * | 2019-04-11 | 2019-07-12 | 华北科技学院 | The disaster scene information fusion method and device of knowledge based map |
| CN111444351A (en) * | 2020-03-24 | 2020-07-24 | 清华苏州环境创新研究院 | Method and device for constructing knowledge graph in industrial process field |
| CN113326358A (en) * | 2021-08-04 | 2021-08-31 | 中国测绘科学研究院 | Earthquake disaster information service method and system based on knowledge graph semantic matching |
| CN113449526A (en) * | 2021-08-27 | 2021-09-28 | 杭萧钢构股份有限公司 | Method and system for analyzing applicability of steel structure production scheduling strategy |
-
2022
- 2022-02-17 CN CN202210145492.8A patent/CN114218406A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008355A (en) * | 2019-04-11 | 2019-07-12 | 华北科技学院 | The disaster scene information fusion method and device of knowledge based map |
| CN111444351A (en) * | 2020-03-24 | 2020-07-24 | 清华苏州环境创新研究院 | Method and device for constructing knowledge graph in industrial process field |
| CN113326358A (en) * | 2021-08-04 | 2021-08-31 | 中国测绘科学研究院 | Earthquake disaster information service method and system based on knowledge graph semantic matching |
| CN113449526A (en) * | 2021-08-27 | 2021-09-28 | 杭萧钢构股份有限公司 | Method and system for analyzing applicability of steel structure production scheduling strategy |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115146081A (en) * | 2022-08-31 | 2022-10-04 | 合肥中科迪宏自动化有限公司 | Construction method and diagnosis method of fault diagnosis knowledge graph of production equipment |
| CN116681305A (en) * | 2023-06-05 | 2023-09-01 | 中国标准化研究院 | Emergency decision method based on knowledge graph |
| CN116681305B (en) * | 2023-06-05 | 2024-04-26 | 中国标准化研究院 | Emergency decision method based on knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117453921B (en) | Data information label processing method of large language model | |
| WO2020224097A1 (en) | Intelligent semantic document recommendation method and device, and computer-readable storage medium | |
| CN114064918B (en) | Multi-modal event knowledge graph construction method | |
| Sebastiani | Classification of text, automatic | |
| CN111914087B (en) | Public opinion analysis method | |
| CN108304468A (en) | A kind of file classification method and document sorting apparatus | |
| CN112395395B (en) | Text keyword extraction method, device, equipment and storage medium | |
| Kmail et al. | An automatic online recruitment system based on exploiting multiple semantic resources and concept-relatedness measures | |
| WO2015043075A1 (en) | Microblog-oriented emotional entity search system | |
| CN117171333B (en) | Electric power file question-answering type intelligent retrieval method and system | |
| CN110750648A (en) | Text emotion classification method based on deep learning and feature fusion | |
| CN114218406A (en) | Transmission solution generation method and system based on transmission knowledge graph | |
| CN115017303A (en) | Method, computing device and medium for enterprise risk assessment based on news text | |
| CN113434688B (en) | Data processing method and device for public opinion classification model training | |
| CN112989208A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN114239828A (en) | Supply chain affair map construction method based on causal relationship | |
| CN114742071A (en) | Chinese cross-language viewpoint object recognition and analysis method based on graph neural network | |
| CN114443842A (en) | Strategic emerging industry classification method and device, storage medium and electronic equipment | |
| CN114896387A (en) | Military intelligence analysis visualization method and device and computer readable storage medium | |
| Shah et al. | Cyber-bullying detection in hinglish languages using machine learning | |
| CN117056510A (en) | Automatic collecting method for multi-element social contradiction dispute information | |
| CN112527963A (en) | Multi-label emotion classification method and device based on dictionary, equipment and storage medium | |
| CN117216617A (en) | Text classification model training method, device, computer equipment and storage medium | |
| Ezzat et al. | Topicanalyzer: A system for unsupervised multi-label arabic topic categorization | |
| CN116186241A (en) | Event element extraction method and device based on semantic analysis and prompt learning, electronic equipment and 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 |