CN116187868B - Knowledge graph-based industrial chain development quality evaluation method and device - Google Patents
Knowledge graph-based industrial chain development quality evaluation method and device Download PDFInfo
- Publication number
- CN116187868B CN116187868B CN202310468634.9A CN202310468634A CN116187868B CN 116187868 B CN116187868 B CN 116187868B CN 202310468634 A CN202310468634 A CN 202310468634A CN 116187868 B CN116187868 B CN 116187868B
- Authority
- CN
- China
- Prior art keywords
- industrial chain
- entities
- entity
- development
- chain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of knowledge graph and industry chain decision making, and discloses an industry chain development quality evaluation method and device based on the knowledge graph, wherein the method comprises the following steps: acquiring an industrial chain development entity list, and acquiring association relations between every two entities in the industrial chain development entity list; weighting the association relation between every two entities to obtain a weighted association relation between the entities; constructing an industrial chain knowledge graph according to the industrial chain development entity list and the weighted association relation between the entities; constructing an importance evaluation model of key elements of the industrial chain through a random walk strategy according to the knowledge graph of the industrial chain; and evaluating the importance of the key elements in the industrial chain knowledge graph through an industrial chain key element importance evaluation model, and acquiring the development quality score of the industrial chain to be evaluated by combining the coverage condition of the key elements of the industrial chain to be evaluated. The invention realizes the purpose of accurately and effectively evaluating the development quality of the industrial chain.
Description
Technical Field
The invention relates to the technical field of knowledge graph and industry chain decision making, in particular to an industry chain development quality evaluation method and device based on the knowledge graph.
Background
The quality evaluation of the development of the industry chain is helpful for the digital government to make macroscopic decisions on the aspects of safety of the industry chain, layout of the industry chain and the like, and related research works at home and abroad are mostly qualitative researches, for example, key elements forming the industry chain are displayed in a visual mode such as a hierarchical graph, a network graph and the like. Research work on evaluation of the development quality of an industrial chain, particularly research work on development evaluation based on an industrial chain knowledge graph is relatively rare.
Secondly, the traditional industrial chain knowledge graph construction method is generally based on a graph database, and the industrial chain knowledge graph construction is constructed by manually inputting triples or importing structured relational data in batches. The traditional industrial chain knowledge graph construction method has low efficiency in a manual mode, and is easy to miss input or input in error when the data volume is huge, so that accurate reasoning cannot be carried out by utilizing the constructed industrial chain knowledge graph in the follow-up process.
Disclosure of Invention
Based on the above, the embodiment of the invention provides a knowledge graph-based industrial chain development quality evaluation method and device, which aim to solve the problem of how to accurately and effectively evaluate the industrial chain development quality.
In order to solve the above problems, an embodiment of the present invention provides a method for evaluating quality of industrial chain development based on a knowledge graph, including:
acquiring an industrial chain development entity list, and acquiring association relations between every two entities in the industrial chain development entity list;
weighting the association relation between every two entities to obtain a weighted association relation between the entities;
constructing an industry chain knowledge graph according to the industry chain development entity list and the weighted association relation between the entities;
according to the industrial chain knowledge graph, an industrial chain key element importance evaluation model is constructed through a random walk strategy;
and evaluating the importance of the key elements in the industrial chain knowledge graph through the industrial chain key element importance evaluation model, and acquiring the development quality score of the industrial chain to be evaluated by combining the coverage condition of the key elements of the industrial chain to be evaluated.
In addition, the embodiment of the invention also provides an industrial chain development quality evaluation device based on the knowledge graph, which comprises:
the entity and relation processing module is used for acquiring an industrial chain development entity list and acquiring association relation between every two entities in the industrial chain development entity list;
the relation weighting module is used for weighting the association relation between every two entities to obtain a weighted association relation between the entities;
the industrial chain knowledge graph construction module is used for constructing an industrial chain knowledge graph according to the industrial chain development entity list and the weighted association relation between the entities;
the importance evaluation model construction module is used for constructing an importance evaluation model of the key elements of the industrial chain through a random walk strategy according to the industrial chain knowledge graph;
the industrial chain development quality evaluation module is used for evaluating the importance of the key elements in the industrial chain knowledge graph through the industrial chain key element importance evaluation model and acquiring the development quality score of the industrial chain to be evaluated by combining the key element coverage condition of the industrial chain to be evaluated.
The industrial chain development quality evaluation method and device based on the knowledge graph provided by the embodiment of the invention have the following beneficial effects:
1) According to the embodiment of the invention, the industrial chain knowledge graph is constructed according to the weighted association relationship between the industrial chain development entity and the entity, the knowledge graph can be automatically constructed, the construction efficiency of the knowledge graph is improved, and meanwhile, accurate and error-free data support can be provided for the follow-up knowledge graph reasoning;
2) According to the embodiment of the invention, the importance of the key elements in the knowledge graph is calculated through the industrial chain key element importance evaluation model, and the development quality of the industrial chain to be evaluated is quantified by combining the key element coverage condition of the industrial chain to be evaluated, so that the development quality of the industrial chain can be effectively and accurately evaluated, and the support of the high-quality development of the industrial chain to make macroscopic decision is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an industrial chain development quality evaluation method based on a knowledge graph according to an embodiment of the present invention;
fig. 2 is a flowchart of step S10 in an industrial chain development quality evaluation method based on a knowledge graph according to an embodiment of the present invention;
FIG. 3 is an exemplary diagram of a knowledge graph of a real estate industry chain according to an embodiment of the present invention;
FIG. 4 is a flowchart of another method for evaluating quality of development of an industrial chain based on a knowledge graph according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an industrial chain development quality evaluation device based on a knowledge graph according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another industrial chain development quality evaluation device based on a knowledge graph according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.
Example 1
As shown in fig. 1, a flowchart of an industrial chain development quality evaluation method based on a knowledge graph provided by an embodiment of the present invention includes the following steps:
s10, acquiring an industrial chain development entity list, and acquiring association relations between every two entities in the industrial chain development entity list.
In step S10, the industry chain development entity list includes a plurality of industry chain development entities, and the industry chain development entities are names of various key elements extracted from the industry chain development related articles and forming the industry chain, wherein the key elements include related industries, enterprises and the like.
The association relationship between every two entities can be quantified through the co-occurrence probability between the entities of the industrial chain development, and the co-occurrence probability can represent the semantic association relationship between the entities.
Preferably, as shown in fig. 2, the step S10 includes the steps of:
s101, acquiring an industrial chain development related article, extracting an industrial chain development entity from the industrial chain development related article, and constructing an industrial chain development entity list.
In step S101, an industrial chain development related article may be obtained by a crawler technology, and an industrial chain development entity may be extracted from the industrial chain development related article by a named entity recognition method to form an industrial chain development entity list, which may be expressed as，/>Is the number of entities.
Alternatively, named entity recognition methods may be rule and dictionary based methods or statistical based methods that are currently in common use.
S102, determining two entities which co-occur in the article related to the industrial chain development, calculating the co-occurrence probability of the two entities which co-occur and the occurrence probability of each entity, and calculating the conditional transition probability of the two entities which co-occur.
In step S102, an entity list is developed based on the industry chainCounting two entitiesCo-occurrence probability in industry chain development related literature>The co-occurrence probability represents the probability between two entitiesIs used for counting the occurrence probability of each entity in the industry chain development related literature>At this time, two entities are present in accordance with the co-occurrence +.>Co-occurrence probability>And the occurrence probability of each entity +.>Two entities +.>Conditional transition probability->The conditional transition probability->The calculation formula of (2) is as follows:
。
s103, determining two non-co-occurring entities in the article related to the industrial chain development, and calculating the conditional transition probability of the two non-co-occurring entities according to a first-order Markov chain model and the conditional transition probability of the two co-occurring entities.
In step S103, for two entities that never co-occur in the industry chain development related articlesCalculating two entities +.>Conditional transition probabilities of (2). Wherein the first order Markov chain model may be expressed as:
，
in the above-mentioned method, the step of,for realizing entity->And entity->An associated intermediate entity. It should be noted that two entities +.>And two entities->Are commonly found in industry chain development related articles.
S104, calculating the co-occurrence probability of the two non-co-occurrence entities according to the conditional transition probability of the two non-co-occurrence entities and the occurrence probability of each entity.
I.e. based on two entities not co-occurringConditional transition probability of (2) and occurrence probability of each entity +.>Two entities +.>Co-occurrence probability>The co-occurrence probabilityThe calculation formula of (2) is as follows:
。
s105, obtaining the association relation between every two entities in the industrial chain development entity list according to the co-occurrence probability of the two entities which co-occur and do not co-occur.
I.e. based on two entities co-occurringAnd two entities which do not co-occur +.>And quantifying the association relationship between every two entities.
And S20, weighting the association relation between every two entities to obtain the weighted association relation between the entities.
In step S20, a weight coefficient between every two entities is introduced, and a weighted calculation is performed on the association relationship between every two entities, so as to obtain a weighted association relationship between the entities.
Preferably, the weight coefficient between every two entities is used to represent importance of association relationship between every two entities to the field of industrial chain development. At this time, the step S20 includes the steps of:
s201, acquiring weight coefficients of every two entities in the industry chain development related literature through a TF-IDF algorithm; the calculation formula of the weight coefficient between every two entities is as follows:
，
in the above-mentioned method, the step of,for every two entities->Weight coefficient between->Is common between every two entitiesProbability of occurrence of->For the statistical function of quantity->For the development of a relevant document collection of an industrial chain,for all documents total->The representation comprises two entities->Is a total number of documents.
S202, weighting the association relation between every two entities according to the weight coefficient between every two entities to obtain the weighted association relation between the entities.
In step S202, the quantization formula of the weighted association relationship between entities is:
，
in the above-mentioned method, the step of,and weighting association relations among the entities. It can be understood that in this embodiment, the association relationship between the industrial chain development entities is extracted by the markov chain model, and then weighted by the TF-IDF algorithm, so that quantification of the association relationship between the entities can be achieved, and data support is provided for construction of the industrial chain knowledge graph.
S30, constructing an industrial chain knowledge graph through a triplet expression method according to the industrial chain development entity list and the weighted association relation between the entities.
In step S30, first, determining entity nodes of a knowledge graph according to the industry chain development entities in the industry chain development entity list; then determining the relationship side of the knowledge graph and the attribute of the relationship side according to the weighted association relationship among the entities; and finally, constructing an industrial chain knowledge graph according to the entity nodes, the relation edges and the attributes of the relation edges.
S40, constructing an industrial chain key element importance evaluation model through a random walk strategy according to the industrial chain knowledge graph.
In step S40, the industrial chain key element importance assessment model, which is used to calculate the importance of the key element in the industrial chain knowledge graph, may be expressed as:
，
in the above-mentioned method, the step of,is any entity in the industrial chain knowledge graph; />For entity->Is a set of inbound entities; />For entity->Is a set of outbound entities; />Is any entity in the entity set of the degree of importation; />Is any entity in the outbound entity set; />For entity->And entity->Is a weighted association relationship of (1);for entity->And entity->Is a weighted association relationship of (1); />Is an experience coefficient; />An operator is evaluated for key element importance.
Alternatively, empirical coefficientsSet to 0.85.
S50, evaluating the importance of the key elements in the industrial chain knowledge graph through the industrial chain key element importance evaluation model, and acquiring the development quality score of the industrial chain to be evaluated by combining the coverage condition of the key elements of the industrial chain to be evaluated.
In step S50, the importance of all entities in the industrial chain knowledge graph is initialized and set according to the coverage condition of the key elements of the industrial chain to be evaluated, and then the importance of all entities is calculated in multiple iterations through the industrial chain key element importance evaluation model, and the development quality of the industrial chain to be evaluated is estimated according to the final iteration calculation result. The industrial chain to be evaluated refers to an industrial chain under the current development stage.
Preferably, the step S50 includes the steps of:
s501, initializing importance scores of all entities in the industrial chain knowledge graph according to the coverage condition of key elements of the industrial chain to be evaluated.
In step S501, in combination with the coverage situation of the key elements of the industrial chain to be evaluated, the importance score initialization for all covered entities in the industrial chain knowledge graph is set to 1, and the importance score initialization for all uncovered entities in the industrial chain knowledge graph is set to 0.
S502, performing multi-round iterative computation through the industrial chain key element importance evaluation model.
Preferably, the step S502 may include the steps of:
s5021, initializing and setting the maximum iteration times and a preset convergence value, and enabling the current iteration times to be initial values;
s5022, calculating importance scores of all entities in the industrial chain knowledge graph after current round iteration through the industrial chain key element importance evaluation model;
s5023, judging whether the iteration stop condition is met by judging whether the current iteration times are the maximum iteration times or whether the absolute value of the difference between the importance scores of all entities of the current iteration calculation and the importance scores of all entities of the last iteration calculation is smaller than or equal to a preset convergence value;
s5024, if yes, stopping iteration; otherwise, after the current iteration number is added by one, the step S5022 is returned.
I.e. the maximum number of iterations is set initiallyAnd a preset convergence value +.>Afterwards, the importance scores of all entities in the industry chain knowledge graph initially set in step S501 are +.>As the input of the first iteration, calculating the importance scores of all entities after the first iteration through the industrial chain key element importance evaluation model, and then detecting the importance scores of all entities after the first iteration +.>Importance scores to all entities of the initialization setupAbsolute value of difference between +.>Whether or not is less than or equal to a preset convergence valueIf->Then enter the second round of iterative computation until the current iterative times are detected>Or->And stopping iteration and outputting importance scores of all entities in the last round of iterative computation.
And S503, after iteration is stopped, carrying out normalization and superposition processing on importance scores of all entities in the last round of iterative computation to obtain a development quality score of the industrial chain to be evaluated.
In step S503, after the iteration is stopped, obtaining importance scores of all the converged entities, normalizing the importance scores of all the converged entities to obtain normalized importance scores of each entity, and overlapping the normalized importance scores of all the entities to obtain a development quality score of the industry chain to be priced。
It should be noted that, in other embodiments, after the iteration is stopped, normalization and weight superposition processing may be performed on importance scores of all entities in the last iteration calculation to obtain a development quality score of the industry chain to be priced. Taking an industrial chain as an real estate industrial chain as an example, the industrial chain development quality evaluation method based on the knowledge graph can comprise the following steps:
firstly, acquiring articles related to real estate industry chain development, extracting real estate industry chain development entities, and extracting association relations among the real estate industry chain development entities through a Markov chain model; and then weighting the association relation between the financial industry chain development entities through a TF-IDF algorithm to obtain a weighted association relation, combining the real estate industry chain development entities, constructing a real estate industry chain knowledge graph through a triplet representation method, referring to an example graph of the real estate industry chain knowledge graph shown in FIG. 3, wherein the real estate industry chain knowledge graph entities are related industries and related enterprises, and the relationship edges are quantized weighted association relation.
Further, based on the real estate industry chain knowledge graph, a real estate industry chain key element importance evaluation model is built by combining a random walk strategy, importance scores of all key elements in the real estate industry chain knowledge graph are calculated, and real estate industry chain development quality is quantized by combining key element coverage conditions of the real estate industry chain in the current development stage.
In summary, the industrial chain development quality evaluation method based on the knowledge graph provided by the embodiment of the invention has the following beneficial effects:
1) According to the embodiment of the invention, the industrial chain knowledge graph is constructed according to the weighted association relationship between the industrial chain development entity and the entity, the knowledge graph can be automatically constructed, the construction efficiency of the knowledge graph is improved, and meanwhile, accurate and error-free data support can be provided for the follow-up knowledge graph reasoning;
2) According to the embodiment of the invention, the importance of the key elements in the knowledge graph is calculated through the industrial chain key element importance evaluation model, and the development quality of the industrial chain to be evaluated is quantified by combining the key element coverage condition of the industrial chain to be evaluated, so that the development quality of the industrial chain can be effectively and accurately evaluated, and the support of the high-quality development of the industrial chain to make macroscopic decision is facilitated.
In an alternative embodiment, as shown in fig. 4, the method for evaluating the quality of industrial chain development based on a knowledge graph further includes the following steps:
s60, after the importance initial scores are given to all entities in the industrial chain knowledge graph, performing iterative computation for a plurality of times through the industrial chain key element importance evaluation model, and obtaining the development quality scores when the industrial chain key elements are fully covered according to the iterative computation result.
In step S60, the importance initial score is set to 1.
That is, the importance score of all entities in the industry chain knowledge graph is initialized to 1, i.eThen, carrying out multiple iterative computation through an industrial chain key element importance evaluation model, stopping iteration when detecting that the current iteration number reaches the maximum iteration number or detecting that the iteration convergence condition is met, obtaining importance scores of all entities in the last iterative computation, and carrying out normalization and superposition processing to obtain a development quality score + & gt when the industrial chain key element is fully covered>。
The step S60 may be performed simultaneously with the step S50, or may be performed after the step S50. The flowchart of the industrial chain development quality evaluation method based on the knowledge graph shown in fig. 4 is only one preferred embodiment.
And S70, obtaining the development gap of the industrial chain to be evaluated by calculating the difference between the development quality score of the industrial chain to be evaluated and the development quality score of the industrial chain when the key elements of the industrial chain are fully covered.
In step S70, a development quality score of the industrial chain to be evaluated is calculatedDevelopment quality score +.>Difference between->Thereby quantifying the development gap of the industrial chain to be evaluated. Further, according to the development gap of the industrial chain to be evaluated, an industrial chain development decision scheme is obtained based on an expert experience reasoning method, so that a macroscopic decision of development quality evaluation development of the industrial chain is supported.
It can be appreciated that according to the industrial chain development quality evaluation method based on the knowledge graph provided by the embodiment of the invention, the development gap of the industrial chain is quantified by calculating the difference between the development quality score of the industrial chain to be evaluated and the development quality score of the industrial chain when the key elements of the industrial chain are fully covered, so that the development quality of the industrial chain can be evaluated in a multi-dimensional manner, and a richer data support is provided for the macro decision of the high-quality development of the industrial chain.
Example 2
As shown in fig. 5, a schematic structural diagram of an industrial chain development quality evaluation device based on a knowledge graph according to an embodiment of the present invention includes:
the entity and relationship processing module 110 is configured to obtain an industry chain development entity list, and obtain an association relationship between every two entities in the industry chain development entity list;
the relationship weighting module 120 is configured to weight the association relationship between the two entities to obtain a weighted association relationship between the entities;
the industry chain knowledge graph construction module 130 is configured to construct an industry chain knowledge graph according to the industry chain development entity list and the weighted association relationship between the entities;
the importance evaluation model construction module 140 is configured to construct an importance evaluation model of the industrial chain key element through a random walk strategy according to the industrial chain knowledge graph;
the industrial chain development quality evaluation module 150 is configured to evaluate importance of key elements in the industrial chain knowledge graph through the industrial chain key element importance evaluation model, and obtain a development quality score of the industrial chain to be evaluated in combination with a coverage situation of the key elements of the industrial chain to be evaluated.
In some alternative embodiments, as shown in fig. 6, the knowledge-graph-based industrial chain development quality evaluation device further includes:
the full coverage development quality evaluation module 160 is configured to perform multiple iterative computations through the industrial chain key element importance evaluation model after assigning an importance initial score to all entities in the industrial chain knowledge graph, and obtain a development quality score when the industrial chain key element is fully covered according to an iterative computation result;
the development gap quantifying module 170 is configured to obtain a development gap of the industrial chain to be evaluated by calculating a difference between the development quality score of the industrial chain to be evaluated and the development quality score when the key elements of the industrial chain are fully covered.
In some alternative embodiments, the entity and relationship processing module 110 includes:
the entity extraction sub-module is used for acquiring an industrial chain development related article, extracting an industrial chain development entity from the industrial chain development related article and constructing an industrial chain development entity list;
a co-occurrence entity processing sub-module, configured to determine two entities that co-occur in the article related to industrial chain development, calculate a co-occurrence probability of the two entities that co-occur and an occurrence probability of each entity, and calculate a conditional transition probability of the two entities that co-occur;
the non-common entity processing submodule is used for determining two non-common entities in the industrial chain development related article, and calculating the conditional transition probability of the two non-common entities according to a first-order Markov chain model and the conditional transition probability of the two common entities; calculating the co-occurrence probability of the two non-co-occurrence entities according to the conditional transition probability of the two non-co-occurrence entities and the occurrence probability of each entity;
and the entity association relation processing sub-module is used for obtaining association relation between every two entities in the industrial chain development entity list according to co-occurrence probability of two co-occurrence and non-co-occurrence entities.
In some alternative embodiments, the relationship weighting module 120 includes:
the weight coefficient acquisition sub-module is used for acquiring weight coefficients of every two entities in the industry chain development related literature through a TF-IDF algorithm;
and the weighting sub-module is used for weighting the association relation between the two entities according to the weight coefficient between the two entities to obtain the weighted association relation between the entities.
In some alternative embodiments, the industry chain development quality assessment module 150 includes:
the importance initializing sub-module is used for initializing and setting importance scores of all entities in the industrial chain knowledge graph according to the coverage condition of key elements of the industrial chain to be evaluated;
the iterative computation sub-module is used for carrying out multi-round iterative computation through the industrial chain key element importance evaluation model;
and the development quality evaluation sub-module is used for obtaining the development quality score of the industrial chain to be evaluated by carrying out normalization and superposition processing on the importance scores of all entities calculated in the last round of iteration after the iteration is stopped.
In some alternative embodiments, the iterative computation submodule includes:
the parameter initialization unit is used for initializing and setting the maximum iteration times and a preset convergence value, and enabling the current iteration times to be initial values;
the iteration calculation unit is used for calculating importance scores of all entities in the industrial chain knowledge graph after the current round of iteration through the industrial chain key element importance evaluation model;
the stopping condition detection unit is used for judging whether the iteration stopping condition is met or not by judging whether the current iteration times are the maximum iteration times or whether the absolute value of the difference between the importance scores of all entities of the current iteration calculation and the importance scores of all entities of the last iteration calculation is smaller than or equal to a preset convergence value or not;
the iteration output processing unit is used for stopping iteration if yes; otherwise, after the current iteration times are added by one, the iteration calculation unit is returned.
It can be understood that the industrial chain development quality evaluation device based on the knowledge graph provided in this embodiment is used to implement the industrial chain development quality evaluation method based on the knowledge graph in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
It should be noted that in the description of the present invention, reference to the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise indicated, the meaning of "plurality" means at least two.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (6)
1. The industrial chain development quality evaluation method based on the knowledge graph is characterized by comprising the following steps of:
acquiring an industrial chain development entity list, and acquiring association relations between every two entities in the industrial chain development entity list;
the obtaining the industrial chain development entity list and obtaining the association relationship between every two entities in the industrial chain development entity list comprises the following steps:
acquiring an industrial chain development related article, extracting an industrial chain development entity from the industrial chain development related article, and constructing an industrial chain development entity list;
determining two entities which co-occur in the industrial chain development related article, calculating the co-occurrence probability of the two entities which co-occur and the occurrence probability of each entity, and calculating the conditional transition probability of the two entities which co-occur;
determining two non-co-occurring entities in the industrial chain development related article, and calculating the conditional transition probability of the two non-co-occurring entities according to a first-order Markov chain model and the conditional transition probability of the two co-occurring entities;
calculating the co-occurrence probability of the two non-co-occurrence entities according to the conditional transition probability of the two non-co-occurrence entities and the occurrence probability of each entity;
obtaining association relations between every two entities in the industrial chain development entity list according to co-occurrence probabilities of two entities which co-occur and do not co-occur;
weighting the association relation between every two entities to obtain a weighted association relation between the entities;
constructing an industry chain knowledge graph according to the industry chain development entity list and the weighted association relation between the entities;
according to the industrial chain knowledge graph, an industrial chain key element importance evaluation model is constructed through a random walk strategy;
the industrial chain key element importance evaluation model is as follows:
，
in the method, in the process of the invention,is any entity in the industrial chain knowledge graph; />For entity->Is a set of inbound entities; />For entity->Is a set of outbound entities; />Is any entity in the entity set of the degree of importation; />Is any entity in the outbound entity set; />For entity->And entity->Is a weighted association relationship of (1);for entity->And entity->Is a weighted association relationship of (1); />Is an experience coefficient;IM(e i ) Representing entitiese i Key element importance assessment scores of (2);IM(e j ) Representing entitiese j Key element importance assessment scores of (2);
the importance of the key elements in the industrial chain knowledge graph is evaluated through the industrial chain key element importance evaluation model, and the development quality score of the industrial chain to be evaluated is obtained by combining the key element coverage condition of the industrial chain to be evaluated;
after the importance initial scores are given to all entities in the industrial chain knowledge graph, performing iterative computation for a plurality of times through the industrial chain key element importance evaluation model, and obtaining development quality scores when the industrial chain key elements are fully covered according to iteration computation results;
and obtaining the development gap of the industrial chain to be evaluated by calculating the difference between the development quality score of the industrial chain to be evaluated and the development quality score of the industrial chain when the key elements of the industrial chain are fully covered.
2. The knowledge-graph-based industrial chain development quality evaluation method of claim 1, wherein weighting the association relationship between the two entities to obtain a weighted association relationship between the entities comprises:
acquiring weight coefficients of every two entities in the industry chain development related literature through a TF-IDF algorithm;
and weighting the association relation between every two entities according to the weight coefficient between every two entities to obtain the weighted association relation between the entities.
3. The knowledge-based industrial chain development quality evaluation method according to claim 1, wherein the evaluating the importance of the key elements in the industrial chain knowledge-based by the industrial chain key element importance evaluation model and combining the coverage of the key elements of the industrial chain to be evaluated to obtain the development quality score of the industrial chain to be evaluated comprises:
according to the coverage condition of key elements of an industrial chain to be evaluated, initializing importance scores of all entities in the industrial chain knowledge graph;
performing multi-round iterative computation through the industrial chain key element importance evaluation model;
and after the iteration is stopped, carrying out normalization and superposition processing on importance scores of all entities in the last round of iterative computation to obtain the development quality score of the industrial chain to be evaluated.
4. The knowledge-graph-based industrial chain development quality evaluation method according to claim 3, wherein the performing multiple rounds of iterative computation by the industrial chain key element importance evaluation model comprises:
initializing and setting the maximum iteration times and a preset convergence value, and enabling the current iteration times to be initial values;
calculating importance scores of all entities in the industrial chain knowledge graph after current round iteration through the industrial chain key element importance evaluation model;
judging whether the iteration stop condition is met by judging whether the current iteration times are the maximum iteration times or whether the absolute value of the difference between the importance scores of all entities of the current iteration calculation and the importance scores of all entities of the last iteration calculation is smaller than or equal to a preset convergence value;
if yes, iteration is stopped; otherwise, after adding one operation to the current iteration number, returning to the step: and calculating importance scores of all entities in the industrial chain knowledge graph after the current round of iteration through an industrial chain key element importance evaluation model.
5. An industrial chain development quality evaluation device based on a knowledge graph is characterized by comprising:
the entity and relation processing module is used for acquiring an industrial chain development entity list and acquiring association relation between every two entities in the industrial chain development entity list;
the entity and relationship processing module comprises:
the entity extraction sub-module is used for acquiring an industrial chain development related article, extracting an industrial chain development entity from the industrial chain development related article and constructing an industrial chain development entity list;
a co-occurrence entity processing sub-module, configured to determine two entities that co-occur in the article related to industrial chain development, calculate a co-occurrence probability of the two entities that co-occur and an occurrence probability of each entity, and calculate a conditional transition probability of the two entities that co-occur;
the non-common entity processing submodule is used for determining two non-common entities in the industrial chain development related article, and calculating the conditional transition probability of the two non-common entities according to a first-order Markov chain model and the conditional transition probability of the two common entities; calculating the co-occurrence probability of the two non-co-occurrence entities according to the conditional transition probability of the two non-co-occurrence entities and the occurrence probability of each entity;
the entity association relation processing sub-module is used for obtaining association relation between every two entities in the industrial chain development entity list according to co-occurrence probability of two co-occurrence and non-co-occurrence entities;
the relation weighting module is used for weighting the association relation between every two entities to obtain a weighted association relation between the entities;
the industrial chain knowledge graph construction module is used for constructing an industrial chain knowledge graph according to the industrial chain development entity list and the weighted association relation between the entities;
the importance evaluation model construction module is used for constructing an importance evaluation model of the key elements of the industrial chain through a random walk strategy according to the industrial chain knowledge graph;
the industrial chain key element importance evaluation model is as follows:
，
in the method, in the process of the invention,is any entity in the industrial chain knowledge graph; />For entity->Is a set of inbound entities; />For entity->Is a set of outbound entities; />Is any entity in the entity set of the degree of importation; />Is any entity in the outbound entity set; />For entity->And entity->Is a weighted association relationship of (1);for entity->And entity->Is a weighted association relationship of (1); />Is an experience coefficient;IM(e i ) Representing entitiese i Key element weight of (2)A desirability assessment score;IM(e j ) Representing entitiese j Key element importance assessment scores of (2);
the industrial chain development quality evaluation module is used for evaluating the importance of the key elements in the industrial chain knowledge graph through the industrial chain key element importance evaluation model and acquiring the development quality score of the industrial chain to be evaluated by combining the key element coverage condition of the industrial chain to be evaluated;
the full coverage development quality evaluation module is used for carrying out multiple iterative computation through the industrial chain key element importance evaluation model after giving the importance initial score to all entities in the industrial chain knowledge graph, and obtaining the development quality score when the industrial chain key elements are fully covered according to the iterative computation result;
and the development gap quantifying module is used for obtaining the development gap of the industrial chain to be evaluated by calculating the difference between the development quality score of the industrial chain to be evaluated and the development quality score of the industrial chain when the key elements of the industrial chain are fully covered.
6. The knowledge-based industrial chain development quality evaluation device according to claim 5, wherein the development quality evaluation module comprises:
the initialization sub-module is used for initializing and setting importance scores of all entities in the industrial chain knowledge graph according to the coverage condition of key elements of the industrial chain to be evaluated;
the iterative computation sub-module is used for carrying out multi-round iterative computation through the industrial chain key element importance evaluation model;
and the development quality evaluation sub-module is used for carrying out normalization and superposition processing on the importance scores of all entities in the last round of iterative computation after iteration is stopped, so as to obtain the development quality score of the industrial chain to be evaluated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310468634.9A CN116187868B (en) | 2023-04-27 | 2023-04-27 | Knowledge graph-based industrial chain development quality evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310468634.9A CN116187868B (en) | 2023-04-27 | 2023-04-27 | Knowledge graph-based industrial chain development quality evaluation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116187868A CN116187868A (en) | 2023-05-30 |
| CN116187868B true CN116187868B (en) | 2023-07-21 |
Family
ID=86434865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310468634.9A Active CN116187868B (en) | 2023-04-27 | 2023-04-27 | Knowledge graph-based industrial chain development quality evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187868B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117670145A (en) * | 2024-01-26 | 2024-03-08 | 中国标准化研究院 | Knowledge graph-based industrial chain development quality evaluation method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988724A (en) * | 2021-12-28 | 2022-01-28 | 深圳市迪博企业风险管理技术有限公司 | Risk analysis method for financial activity knowledge graph of listed company |
| CN114897167A (en) * | 2022-05-13 | 2022-08-12 | 内蒙古大学 | Method and device for constructing knowledge graph in biological field |
| CN115983385A (en) * | 2023-03-21 | 2023-04-18 | 航天宏图信息技术股份有限公司 | Novel space environment entity construction method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110609907A (en) * | 2019-09-17 | 2019-12-24 | 湖南大学 | Medicine field knowledge reasoning method based on random walk |
| CN112434169B (en) * | 2020-11-13 | 2024-03-15 | 海创汇科技创业发展股份有限公司 | Knowledge graph construction method and system and computer equipment thereof |
| CN112417166B (en) * | 2020-11-20 | 2022-08-26 | 山东省计算中心（国家超级计算济南中心） | Knowledge graph triple confidence evaluation method |
| CN113051365A (en) * | 2020-12-10 | 2021-06-29 | 深圳证券信息有限公司 | Industrial chain map construction method and related equipment |
| CN113111185A (en) * | 2021-03-04 | 2021-07-13 | 浙江工业大学 | Key path construction method and system for knowledge graph completion task |
| CN114048742A (en) * | 2021-10-26 | 2022-02-15 | 北京师范大学 | Knowledge entity and relation extraction method of text information and text quality evaluation method |
| CN114549195A (en) * | 2021-12-31 | 2022-05-27 | 上海华鑫股份有限公司 | Market value reevaluation analysis method based on industry chain map and visual analysis system |
-
2023
- 2023-04-27 CN CN202310468634.9A patent/CN116187868B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988724A (en) * | 2021-12-28 | 2022-01-28 | 深圳市迪博企业风险管理技术有限公司 | Risk analysis method for financial activity knowledge graph of listed company |
| CN114897167A (en) * | 2022-05-13 | 2022-08-12 | 内蒙古大学 | Method and device for constructing knowledge graph in biological field |
| CN115983385A (en) * | 2023-03-21 | 2023-04-18 | 航天宏图信息技术股份有限公司 | Novel space environment entity construction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116187868A (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Varshney | Engineering safety in machine learning | |
| CN109117380B (en) | Software quality evaluation method, device, equipment and readable storage medium | |
| CN116187868B (en) | Knowledge graph-based industrial chain development quality evaluation method and device | |
| US20150134578A1 (en) | Discriminator, discrimination program, and discrimination method | |
| CN107480895A (en) | A kind of reliable consumer goods methods of risk assessment based on Bayes enhancing study | |
| CN111625516A (en) | Method and device for detecting data state, computer equipment and storage medium | |
| CN113379238A (en) | Risk assessment method and device and electronic equipment | |
| CN113298288A (en) | Power supply station operation and maintenance cost prediction method integrating time sequence and neural network | |
| Verma et al. | Handling imprecision in inputs using fuzzy logic to predict effort in software development | |
| Gandy et al. | MMCTest—a safe algorithm for implementing multiple Monte Carlo tests | |
| Gou | Quick multiple test procedures and p-value adjustments | |
| CN114363004B (en) | Risk assessment method, risk assessment device, computer equipment and storage medium | |
| CN115619563A (en) | Stock price analysis method based on neural network | |
| CN114638421A (en) | Method for predicting requirement of generator set spare parts | |
| CN113537638A (en) | Short-term wind pressure prediction method and abnormal data completion method and device for high-rise building | |
| CN113902272A (en) | Service scoring method, device and storage medium | |
| CN109300025B (en) | Big data and deep learning-based auditing method and robot system | |
| CN113393023A (en) | Mold quality evaluation method, apparatus, device and storage medium | |
| Chu et al. | Novel robust approach for constructing Mamdani-type fuzzy system based on PRM and subtractive clustering algorithm | |
| CN114510518B (en) | Self-adaptive aggregation method and system for massive structured data and electronic equipment | |
| CN110852536A (en) | Storage tank maintenance decision determining method and device | |
| CN112149806B (en) | Access control strategy generation method and device based on machine learning | |
| CN117010283B (en) | Method and system for predicting deformation of steel pipe column structure of PBA station | |
| CN112579667B (en) | Data-driven engine multidisciplinary knowledge machine learning method and device | |
| CN110737773B (en) | Information classification method and system based on neural network |
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 |