CN111401988A - Product configuration demand response system based on semantics and order generation method - Google Patents
Product configuration demand response system based on semantics and order generation method Download PDFInfo
- Publication number
- CN111401988A CN111401988A CN202010134344.7A CN202010134344A CN111401988A CN 111401988 A CN111401988 A CN 111401988A CN 202010134344 A CN202010134344 A CN 202010134344A CN 111401988 A CN111401988 A CN 111401988A
- Authority
- CN
- China
- Prior art keywords
- semantic
- product
- module
- ontology
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0621—Item configuration or customization
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
- G06Q30/0637—Approvals
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention requests to protect a product configuration demand response system based on semantics and an order generation method, and the system comprises the following steps: data layer, semantic layer, service layer and user layer, the data layer gives the semantic layer with product component data and configuration body data, and the semantic layer transmits the data after the semantic processing to the service layer, and the service layer transmits data to the application layer, wherein: the system comprises a data layer, a service layer and a user layer, wherein the data layer comprises a product component database, a configuration body database, an in-production information database and an order database, the semantic layer comprises a requirement body construction module, a semantic matching module, a semantic reasoning inquiry module and a product configuration and order generation module, the service layer comprises a product customization module, an order management module, an order state inquiry module and a product component tracing module, and the user layer comprises a client module and a manager module.
Description
Technical Field
The invention belongs to the field of combination of natural language processing and semantic Web technology, and relates to a product configuration demand response system based on a semantic network.
Background
Strategic goals facing intelligent manufacturing, such as "industrial 4.0" and "chinese manufacturing 2025", are successively proposed, injecting new vitality into the manufacturing industry. The traditional manufacturing industry has the characteristics of large scale and single production mode, and is difficult to meet the increasing personalized requirements of current users, and along with the popularization of mobile internet technology, more and more users utilize internet products to realize personalized customized services. The personalized customization mode effectively improves the customer satisfaction degree by providing personalized products and services according to the characteristics and the preference of customers, and becomes an important means for enterprises to gain market competitiveness. Firstly, most of personalized services are concentrated in an electronic commerce stage and only play a role of an online store; secondly, means for fully and comprehensively displaying the product characteristics, such as interactively and visually displaying the characteristics of the product, are lacked; thirdly, the customer is required to have certain design knowledge to express their personalized requirements, which limits the possibility of realizing personalized selection by the customer. Non-professional customers can only put forward fuzzy requirements on design characteristic attribute parameters of products according to past use experiences or provided examples due to the fact that the degree of knowledge of professional knowledge on the aspects of functions, performances and the like of the products is limited, and the requirements are difficult to describe through professional terms. Therefore, the personalized customization needs to convert fuzzy requirements proposed by customers into specific index parameters of product components through research and analysis on customer requirement information, and the traditional fields of personalized customization, such as automobile customization, computer customization, household appliances and other product modularization, are all selected by users by providing fixed options, so that the personalized requirements of each customer on different characteristics of products cannot be met, and the personalized degree is low.
The semantic network is an assumption of a future network and is an intelligent network. It can not only understand words and concepts, but also understand logical relations between them, which can make communication more efficient and valuable. Structured data can be extracted from unstructured data by utilizing a semantic Web technology, and a corresponding ontology is constructed, so that the data can be well understood by a machine. In order to meet the personalized requirements of customers and quickly configure products meeting the requirements of the customers, the customers can respond to the personalized requirements of product configuration by using a semantic Web technology.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. The semantic-based product configuration demand response system and the order generation method are provided, which convert customer demands into specific index parameters of product components, enable the customized products to meet the customer personalized demands and improve the product configuration efficiency. The technical scheme of the invention is as follows:
a product configuration demand response system and an order generation method based on semantics comprise the following steps: data layer, semantic layer, service layer and user layer, the data layer gives the semantic layer with product component data and configuration body data, and the semantic layer transmits the data after the semantic processing to the service layer, and the service layer transmits data to the application layer, wherein:
the data layer comprises a product component database, a configuration body database, an in-production information database and an order database, wherein the product component database is used for storing information including component parameters, component storage time and price of a product; the configuration ontology database is used for storing configuration ontology models and semantic data related to products; the on-production information database is used for acquiring and storing on-production information data of the production line in real time; the order database is used for storing relevant information data of the user order;
the semantic layer comprises a requirement body construction module, a semantic matching module, a semantic reasoning inquiry module and a product configuration and order generation module, wherein the requirement body construction module is used for constructing a customer requirement body by analyzing the accurate requirement and the fuzzy requirement of a customer and transmitting the customer requirement body to the semantic matching module; the semantic matching module is used for processing ontology mapping and product component and customer requirement membership calculation; the semantic reasoning module is used for processing the reasoning request from the semantic matching module and pushing a reasoning result to the product configuration and order generation module; the product configuration and order generation module generates a product configuration table and order information according to the reasoning result, and stores the product configuration table and the order information into an order database after the product configuration and order information is confirmed by a user;
the service layer comprises a product customization module, an order management module, an order state query module and a product component tracing module, wherein the product customization module is used for submitting personalized customization requirements by a client and feeding back a matching result to the client; the order management module provides order adding, deleting and modifying operations for clients and managers; the order state query module provides the query of the order state information of the customer; the product component tracing module provides information including the source and the warehousing time of the order component inquired by the client and the administrator;
the user layer comprises a client module and an administrator module, and the client module and the administrator module are used for analyzing the login identity of the current user so as to provide different operation authorities.
Furthermore, semantic data in a product component database of the data layer comprises attributes of product components and corresponding attribute values thereof; and storing the order information and the estimated order completion time information in the current production line in a production information database.
Further, the requirement ontology building module of the semantic layer specifically includes: precision requirements and fuzzy requirements; the semantic matching module specifically comprises: the method comprises the steps of ontology mapping and membership calculation, wherein the ontology mapping completes mapping between concepts by calculating the similarity between the concepts in a customer requirement ontology and a product configuration ontology, and the membership calculation is used for calculating the matching degree between product components and requirements in a database.
Further, the ontology mapping is to construct a mapping relationship between the ontology concepts of the domain through similarity calculation to construct a semantic corresponding relationship of knowledge in the domain, so as to realize an interconnection relationship of the knowledge on a semantic level and complete multi-level matching between the customer requirement ontology and the product configuration ontology; the semantic similarity is calculated based on a semantic dictionary, and the similarity between concepts is calculated by utilizing the structural hierarchical relationship between the concepts and the superior-inferior relationship between the concepts. The similarity calculation formula is as follows:
where w1, w2 represents word 1 and word 2, c1 and c2 are respectively one of concepts contained in words w1 and w2, leaves (c) represents the number of leaf nodes possessed by concept c in the ontology structure, max _ leaves represents the number of leaf nodes contained in the ontology, sitting (c) represents the number of sibling nodes with concept c, depth (c) represents the depth value of concept c in the ontology structure, max _ depth represents the maximum depth value of the ontology structure, lch (c1, c2) represents concept c1, the common parent node of c2, and IC (lch (c1, c2)) represents IC values contained in the common parent nodes of concepts c1 and c 2.
When w1 and w2 are "#" at the end of the code, 1 is returned, when w1 and w2 are "#" at the end of the code, 0.36 is returned, otherwise, the similarity between all meanings of the two words is calculated by sim (c1, c2) and the maximum value is taken as a result.
Furthermore, the membership degree calculation module is used for converting the customer requirements into triangular fuzzy numbers and calculating membership degree values of the customer requirements and the component attribute values in the building database through a membership degree function so as to obtain a product component set meeting the user requirements. Where the triangular fuzzy number a ═ is (a, b, c), where a, b, c are the lower limit of the ideal value, and the upper limit of the ideal value, respectively, for the customer demand, and where the membership function μA(x) Is expressed as follows:
when x is<at a time, muA(x)＝0；
When a is less than or equal to x is less than or equal to b,
when b is more than x and less than or equal to c,
when x is>c is, muA(x)＝0；
Furthermore, in the semantic reasoning and query module, the semantic reasoning is based on semantic rules to carry out reasoning and filter incompatible or unsatisfied product components, the semantic query is carried out by using a standard query language SPARQ L of RDF, and the semantic rule file is used for storing rules related to reasoning needed by matching with the product components.
The method comprises the steps of firstly mapping natural language input by a user into classes, attributes and attribute values defined in an ontology to obtain customer fuzzy requirements, then calculating the customer fuzzy requirement ontology and a product configuration ontology through semantic similarity to complete multilevel matching mapping between the customer requirement ontology and the product configuration ontology, obtaining a SPARQ L query statement corresponding to the requirements according to the mapping, then querying a product component database through Jena by utilizing SPARQ L statements, loading rules through an inference engine to obtain a product component result set meeting conditions, wherein the rules are semantic inference rules related to product configuration such as interface matching and component quantity matching, and finally combining the result set to generate a product configuration order.
Furthermore, when the domain knowledge ontology model is constructed, the attributes contained in the product component and the component are defined, and the association relationship between the components is defined, so that when the system performs semantic reasoning, unmatched components are filtered through the association relationship between the components.
A system-based order generation method, comprising the steps of:
reading user requirements and performing semantic matching, and forming an association relation between the user requirements and the components in the configuration body;
inquiring and matching the components in the constructed database according to the requirements of the clients through the incidence relation to obtain a component set meeting the requirements of the clients;
screening components which meet the customer requirements and are in a construction set by relying on an inference engine to load inference rules, filtering incompatible and combinable components, and finally forming a component configuration combination which meets the customer requirements;
calculating the membership degree of the price of the constructed configuration combination and the price of the customer demand, and selecting the optimal product configuration combination;
inquiring the stock number of components in the configuration combination, if the stock number can not meet the order requirement, calculating the predicted delivery time according to the purchase period, and if the stock number meets the order requirement, calculating the predicted delivery time according to the load state of the production line;
and pushing the delivery time and product configuration combination information to the client.
The invention has the following advantages and beneficial effects:
the innovation points of the invention are as follows:
1) the semantic Web technology is utilized to improve the product configuration efficiency. When the domain knowledge ontology model is constructed, the component modules required by the product and the parameters of performance, interfaces, price and the like contained in each component are defined, and the incidence relation among the product components (such as the matching between the interfaces) is defined, so that when the system is used for product configuration, other relevant components can be associated by matching the components meeting the customer requirements through the incidence relation among the product components, and a complete product meeting the customer requirements is formed.
2) And analyzing the customer requirements through natural language processing, and realizing the mapping and conversion from the customer requirements to product parameters. The method comprises the steps of analyzing requirements described by a customer through a natural semantic processing technology, extracting structured data from unstructured data, separating attributes such as product performance and price and customer requirements corresponding to the attributes, and constructing a customer requirement body. And completing the concept mapping relation between the customer requirement ontology and the product configuration ontology through similarity calculation, thereby realizing the mapping and conversion from the customer requirement to the product parameters.
Drawings
FIG. 1 is a diagram of a preferred embodiment semantic Web-based product configuration demand response system framework.
FIG. 2 is a flowchart of the mapping process of the requirement ontology and the product configuration ontology according to the present invention.
FIG. 3 is a diagram of a requirement ontology model according to the present invention.
FIG. 4 is a schematic diagram of a product configuration ontology model according to the present invention.
FIG. 5 is a flow chart of the customer demand response and product configuration order generation job of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings. The described embodiments are only some of the embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
as shown in fig. 1, the present application provides an architecture diagram of a semantic-based product configuration demand response system and an order generation method, where the architecture diagram includes the following parts:
(1) and (6) a data layer. The data layer comprises a product component database, a configuration body database, a production information database and an order database. The product component database is used for storing parameters (such as color, price, performance index and the like) of real product component components, warehousing time and other information; the configuration ontology database is used for storing an ontology model and semantic data related to a product, wherein the configuration ontology model is a configuration ontology (domain knowledge ontology model) constructed by using ontology modeling software TopBraidComperser and is stored in an AllegroGraph graphic database; the on-production information database is used for acquiring and storing on-production information data of the production line in real time; the order database is used for storing the relevant information data (such as order generation time, delivery time, amount of money and the like) of the user order.
(2) And (5) a semantic layer. The semantic layer comprises a requirement body construction module, a semantic matching module, a semantic reasoning module and a product configuration and order generation module. The demand ontology construction module analyzes the demands described by the customers through a natural semantic processing technology, extracts the structured data from the unstructured data, separates the attributes such as product performance and price and the customer demands of the corresponding attributes, and constructs a customer demand ontology. And the semantic matching module completes the mapping relation between the concepts in the customer requirement ontology and the product configuration ontology through similarity calculation, so that the mapping and conversion from the customer requirements to the product parameters are realized. Semantic reasoning is used for processing a reasoning request, and a reasoning rule is stored in an AllegroGraph graphic database. And loading rules through an inference machine to obtain a product component result set meeting the conditions, and finally combining the result set to generate a product configuration order.
(3) And (4) a service layer. The service layer comprises a product customization service, an order management service, an order state inquiry service and a product component tracing service. The product customization service mainly provides product personalized customization service for customers in a user layer. The order management service mainly provides order adding, deleting, modifying and checking service for managers in a user layer. The order state query service mainly provides order state information query for the client in the user layer; the product component tracing service mainly provides information such as the source and the warehousing time of the query order component for managers and users in a user layer.
(4) And (4) a user layer. The user layer includes a client module and an administrator module. The client module and the administrator module are used for analyzing the current user login identity so as to provide different operation rights.
FIG. 2 shows the following process for mapping the requirement ontology and the product configuration ontology:
(1) firstly, reading user requirements under classification requirements in a requirement body, and reading functions and components in a configuration body.
(2) And calculating the semantic similarity between the user requirement and the functions and components in the configuration ontology by using a similarity algorithm.
(3) And matching the functional component most similar to the user requirement by using a bipartite graph matching algorithm to complete the mapping between concepts.
(4) Reading the attribute of the requirement, and calculating the similarity between the attribute and the attribute of the function or the component forming the mapping relation.
(5) And finding the attribute which is most similar to the requirement attribute in the configuration ontology by using a bipartite graph matching algorithm to form a mapping relation between the attributes.
FIG. 3 is a diagram of a demand ontology model, which is divided into the following parts.
(1) Performance requirements, appearance requirements, price requirements, and the like.
(2) Each category requirement contains the fuzzy or precise requirements of the customer.
(3) Each requirement contains attributes (precise requirement means that a user specifies a specific parameter requirement on an attribute, fuzzy requirement means that a user does not specify a value on the attribute).
Fig. 4 is a diagram of a product configuration body model, which is divided into the following parts.
(1) The configuration body comprises a component and a functional sub-body.
(2) The component body includes component concepts such as components a, b, and c, and the function body includes function concepts such as functions 1 and 2.
(3) Each building block concept has an indefinite number of attributes.
(4) The characteristic concept forms an association relationship between the attributes of the components and the functions, so that when the customer requirements are matched with the functions, the attributes corresponding to the customer requirements can be found through the characteristic relationship, and the proper components can be found according to the requirements.
FIG. 5 illustrates a customer demand response and product configuration order generation workflow as follows:
(1) reading user requirements and performing semantic matching, and forming an association relation between the user requirements and the components in the configuration body.
(2) And querying and matching the components in the constructed database according to the requirements of the clients through the incidence relation to obtain a component set meeting the requirements of the clients.
(3) And (4) screening the components which meet the customer requirements and are in a construction set by loading inference rules by an inference engine, and filtering incompatible and combinable components to finally form a component configuration combination meeting the customer requirements.
(4) And calculating the membership degree of the price of the constructed configuration combination and the price of the customer demand, and selecting the optimal product configuration combination.
(5) And inquiring the stock number of the components in the configuration combination, if the stock number cannot meet the order requirement, calculating the predicted delivery time according to the purchase period, and if the stock number meets the order requirement, calculating the predicted delivery time according to the load state of the production line.
(6) And pushing the delivery time and product configuration combination information to the client.
The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (9)
1. A semantics-based product configuration demand response system, comprising: data layer, semantic layer, service layer and user layer, the data layer gives the semantic layer with product component data and configuration body data, and the semantic layer transmits the data after the semantic processing to the service layer, and the service layer transmits data to the application layer, wherein:
the data layer comprises a product component database, a configuration body database, an in-production information database and an order database, wherein the product component database is used for storing information including component parameters, component storage time and price of a product; the configuration ontology database is used for storing configuration ontology models and semantic data related to products; the on-production information database is used for acquiring and storing on-production information data of the production line in real time; the order database is used for storing relevant information data of the user order;
the semantic layer comprises a requirement body construction module, a semantic matching module, a semantic reasoning inquiry module and a product configuration and order generation module, wherein the requirement body construction module is used for constructing a customer requirement body by analyzing the accurate requirement and the fuzzy requirement of a customer and transmitting the customer requirement body to the semantic matching module; the semantic matching module is used for processing ontology mapping and product component and customer requirement membership calculation; the semantic reasoning module is used for processing the reasoning request from the semantic matching module and pushing a reasoning result to the product configuration and order generation module; the product configuration and order generation module generates a product configuration table and order information according to the reasoning result, and stores the product configuration table and the order information into an order database after the product configuration and order information is confirmed by a user;
the service layer comprises a product customization module, an order management module, an order state query module and a product component tracing module, wherein the product customization module is used for submitting personalized customization requirements by a client and feeding back a matching result to the client; the order management module provides order adding, deleting and modifying operations for clients and managers; the order state query module provides the query of the order state information of the customer; the product component tracing module provides information including the source and the warehousing time of the order component inquired by the client and the administrator;
the user layer comprises a client module and an administrator module, and the client module and the administrator module are used for analyzing the login identity of the current user so as to provide different operation authorities.
2. The semantic-based product configuration demand response system of claim 1, wherein the semantic data in the product component database of the data layer comprises attributes of product components and their corresponding attribute values; and storing the order information and the estimated order completion time information in the current production line in a production information database.
3. The semantic-based product configuration demand response system of claim 1, wherein the demand ontology building module of the semantic layer specifically comprises: precision requirements and fuzzy requirements; the semantic matching module specifically comprises: the method comprises the steps of ontology mapping and membership calculation, wherein the ontology mapping completes mapping between concepts by calculating the similarity between the concepts in a customer requirement ontology and a product configuration ontology, and the membership calculation is used for calculating the matching degree between product components and requirements in a database.
4. The semantic-based product configuration demand response system according to claim 3, wherein the ontology mapping is to construct a semantic correspondence of the domain knowledge by constructing a mapping relationship between domain ontology concepts through similarity calculation, to realize an interconnection relationship of the knowledge on a semantic level, and to complete multi-level matching between a customer demand ontology and a product configuration ontology; the semantic similarity is calculated based on a semantic dictionary, the similarity between the concepts is calculated by utilizing the structural hierarchical relationship between the concepts and the superior-inferior relationship between the concepts, and the similarity calculation formula is as follows:
wherein w1, w2 represents word 1 and word 2, c1 and c2 are respectively one of concepts contained in words w1 and w2, leaves (c) represents the number of leaf nodes possessed by concept c in the ontology structure, max _ leaves represents the number of leaf nodes contained in the ontology, sitting (c) represents the number of sibling nodes with concept c, depth (c) represents the depth value of concept c in the ontology structure, max _ depth represents the maximum depth value of the ontology structure, lch (c1, c2) represents concept c1, the common parent node of c2, and IC (lch (c1, c2)) represents IC value contained in the common parent node of concept c1, c 2;
when w1 and w2 are "#" at the end of the code, 1 is returned, when w1 and w2 are "#" at the end of the code, 0.36 is returned, otherwise, the similarity between all meanings of the two words is calculated by sim (c1, c2) and the maximum value is taken as a result.
5. The semantic-based product configuration demand response system of claim 3, wherein the membership calculation module obtains the product component set meeting the user demand by converting the customer demand into triangle fuzzy numbers, and calculating membership values of the customer demand and the component attribute values in the building database through a membership function, wherein the triangle fuzzy numbers A ═ (a, b, c), wherein a, b, c are respectively a lower limit of an ideal value of the customer demand, an ideal value and an upper limit of the ideal value, and wherein the membership function μA(x) Is expressed as follows:
when x is<at a time, muA(x)＝0；
When a is less than or equal to x is less than or equal to b,
when b is<When x is less than or equal to c,
when x is>c is, muA(x)＝0。
6. The semantic-based product configuration demand response system of any one of claims 1 to 5, wherein in the semantic reasoning and query module, semantic reasoning is used for reasoning based on semantic rules and filtering incompatible or unsatisfied product components, semantic query is performed by using a standard query language SPARQ L of RDF, and the semantic rule files are used for storing rules related to reasoning required for matching product components.
7. The product configuration demand response system based on the semantics as claimed in one of claims 1 to 5, wherein the product customization module of the service layer specifically comprises mapping natural language input by a user to classes, attributes and values defined in an ontology to obtain a customer fuzzy demand, then completing multi-level matching mapping between the customer demand ontology and a product configuration ontology through semantic similarity calculation, obtaining a corresponding demand SPARQ L query statement according to the mapping, then querying a product component database through Jena by using the SPARQ L statement, and loading a semantic reasoning rule file through a reasoning machine, wherein the semantic rule file is used for storing rules related to reasoning required by product configuration, including self-defined rules such as component interface matching, and obtaining a product component result set meeting conditions, and finally combining the result sets to generate a product configuration order.
8. The semantic-based product configuration demand response system of claim 7, wherein when constructing the domain ontology model, the attributes included in the product components and the attributes included in the components are defined, and the association relationship between the components is defined, so that when the system performs semantic reasoning, the unmatched components are filtered through the association relationship between the components.
9. An order generation method based on the system of any one of claims 1 to 8, comprising the steps of:
reading user requirements and performing semantic matching, and forming an association relation between the user requirements and the components in the configuration body;
inquiring and matching the components in the constructed database according to the requirements of the clients through the incidence relation to obtain a component set meeting the requirements of the clients;
screening components which meet the customer requirements and are in a construction set by relying on an inference engine to load inference rules, filtering incompatible and combinable components, and finally forming a component configuration combination which meets the customer requirements;
calculating the membership degree of the price of the constructed configuration combination and the price of the customer demand, and selecting the optimal product configuration combination;
inquiring the stock number of components in the configuration combination, if the stock number can not meet the order requirement, calculating the predicted delivery time according to the purchase period, and if the stock number meets the order requirement, calculating the predicted delivery time according to the load state of the production line;
and pushing the delivery time and product configuration combination information to the client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010134344.7A CN111401988B (en) | 2020-03-02 | 2020-03-02 | Product configuration demand response system based on semantics and order generation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010134344.7A CN111401988B (en) | 2020-03-02 | 2020-03-02 | Product configuration demand response system based on semantics and order generation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401988A true CN111401988A (en) | 2020-07-10 |
| CN111401988B CN111401988B (en) | 2022-08-23 |
Family
ID=71432135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010134344.7A Active CN111401988B (en) | 2020-03-02 | 2020-03-02 | Product configuration demand response system based on semantics and order generation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401988B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967746A (en) * | 2020-08-07 | 2020-11-20 | 江苏海岸线互联网科技有限公司 | Quality collaborative management system |
| CN112835944A (en) * | 2021-02-20 | 2021-05-25 | 浙江三方控制阀股份有限公司 | Control valve product query configuration system and query configuration method |
| CN114565429A (en) * | 2022-02-22 | 2022-05-31 | 哈尔滨工程大学 | Intelligent supplier matching method based on semantic graph model |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246509A (en) * | 2008-02-28 | 2008-08-20 | 上海交通大学 | Entire car personalized configuration system based on case illation technology |
| US20100131502A1 (en) * | 2008-11-25 | 2010-05-27 | Fordham Bradley S | Cohort group generation and automatic updating |
| CN102253933A (en) * | 2010-05-18 | 2011-11-23 | 北京耐特永通科技有限公司 | Semantic search system for automobile information analysis and service |
| CN103593752A (en) * | 2013-11-29 | 2014-02-19 | 武汉大学 | Business process adaptability configuring method and system based on situation constraint |
| CN104054075A (en) * | 2011-12-06 | 2014-09-17 | 派赛普申合伙公司 | Text mining, analysis and output system |
| CN104182454A (en) * | 2014-07-04 | 2014-12-03 | 重庆科技学院 | Multi-source heterogeneous data semantic integration model constructed based on domain ontology and method |
| CN105022736A (en) * | 2014-04-18 | 2015-11-04 | 中国科学院深圳先进技术研究院 | Demand analysis system and method of pedigree high-speed train |
| CN106845645A (en) * | 2008-05-01 | 2017-06-13 | 启创互联公司 | Method, system and computer program that the dynamic of semantic network and the media synthesis for user's driving is produced |
| CN107341675A (en) * | 2017-07-17 | 2017-11-10 | 重庆邮电大学 | A kind of intelligent grid remote bill control decision-making framework and method based on semantic knowledge |
| CN107944060A (en) * | 2018-01-02 | 2018-04-20 | 天津大学 | A kind of product information search method towards automotive vertical website |
| CN108053138A (en) * | 2017-12-27 | 2018-05-18 | 华侨大学 | A kind of community manufacture system manufacturing service capability assessment method towards order demand |
| CN108229779A (en) * | 2016-12-21 | 2018-06-29 | 中国科学院沈阳自动化研究所 | A kind of Intelligent Dynamic service combining method and system towards producing line |
| CN110322217A (en) * | 2019-06-11 | 2019-10-11 | 同济大学 | Manufacture cloud service Requirement Decomposition system and method based on template |
| CN110851621A (en) * | 2019-10-31 | 2020-02-28 | 中国科学院自动化研究所 | Method, device and storage medium for predicting video wonderful level based on knowledge graph |
-
2020
- 2020-03-02 CN CN202010134344.7A patent/CN111401988B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246509A (en) * | 2008-02-28 | 2008-08-20 | 上海交通大学 | Entire car personalized configuration system based on case illation technology |
| CN106845645A (en) * | 2008-05-01 | 2017-06-13 | 启创互联公司 | Method, system and computer program that the dynamic of semantic network and the media synthesis for user's driving is produced |
| US20100131502A1 (en) * | 2008-11-25 | 2010-05-27 | Fordham Bradley S | Cohort group generation and automatic updating |
| CN102253933A (en) * | 2010-05-18 | 2011-11-23 | 北京耐特永通科技有限公司 | Semantic search system for automobile information analysis and service |
| CN104054075A (en) * | 2011-12-06 | 2014-09-17 | 派赛普申合伙公司 | Text mining, analysis and output system |
| CN103593752A (en) * | 2013-11-29 | 2014-02-19 | 武汉大学 | Business process adaptability configuring method and system based on situation constraint |
| CN105022736A (en) * | 2014-04-18 | 2015-11-04 | 中国科学院深圳先进技术研究院 | Demand analysis system and method of pedigree high-speed train |
| CN104182454A (en) * | 2014-07-04 | 2014-12-03 | 重庆科技学院 | Multi-source heterogeneous data semantic integration model constructed based on domain ontology and method |
| CN108229779A (en) * | 2016-12-21 | 2018-06-29 | 中国科学院沈阳自动化研究所 | A kind of Intelligent Dynamic service combining method and system towards producing line |
| CN107341675A (en) * | 2017-07-17 | 2017-11-10 | 重庆邮电大学 | A kind of intelligent grid remote bill control decision-making framework and method based on semantic knowledge |
| CN108053138A (en) * | 2017-12-27 | 2018-05-18 | 华侨大学 | A kind of community manufacture system manufacturing service capability assessment method towards order demand |
| CN107944060A (en) * | 2018-01-02 | 2018-04-20 | 天津大学 | A kind of product information search method towards automotive vertical website |
| CN110322217A (en) * | 2019-06-11 | 2019-10-11 | 同济大学 | Manufacture cloud service Requirement Decomposition system and method based on template |
| CN110851621A (en) * | 2019-10-31 | 2020-02-28 | 中国科学院自动化研究所 | Method, device and storage medium for predicting video wonderful level based on knowledge graph |
Non-Patent Citations (5)
| Title |
|---|
| XIAONAN WANG等: "Interpreting the Fuzzy Semantics of NaturalLanguage Spatial Relation Terms with the Fuzzy Random Forest Algorithm", 《INTERNARIONAL JOURNAL OF GEO-INFORMATION》 * |
| 但斌等: "基于本体映射面向模糊客户需求的产品配置研究", 《计算机集成制造系统》 * |
| 杜一峰: "基于语义的产品配置需求响应机制研究与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 胡雨: "基于综合模糊相似度的云制造需求—服务双向匹配", 《计算机应用与软件》 * |
| 陈静等: "面向客户需求基于本体的产品配置方法研究", 《现代制造工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967746A (en) * | 2020-08-07 | 2020-11-20 | 江苏海岸线互联网科技有限公司 | Quality collaborative management system |
| CN112835944A (en) * | 2021-02-20 | 2021-05-25 | 浙江三方控制阀股份有限公司 | Control valve product query configuration system and query configuration method |
| CN114565429A (en) * | 2022-02-22 | 2022-05-31 | 哈尔滨工程大学 | Intelligent supplier matching method based on semantic graph model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401988B (en) | 2022-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401988B (en) | Product configuration demand response system based on semantics and order generation method | |
| Roszkowska | Multi-criteria decision making models by applying the TOPSIS method to crisp and interval data | |
| Klein et al. | Serching for services on the semantic web using process ontologies. | |
| CN109741120B (en) | Product deep personalized customization method for user requirements | |
| Froeschl | Metadata management in statistical information processing: a unified framework for metadata-based processing of statistical data aggregates | |
| Bernstein et al. | Discovering services: Towards high-precision service retrieval | |
| WO2003040888A2 (en) | Method and system for identifying purchasing cost savings | |
| CN115329215A (en) | Recommendation method and system based on self-adaptive dynamic knowledge graph in heterogeneous network | |
| Chen et al. | Personalized product configuration rules with dual formulations: A method to proactively leverage mass confusion | |
| Chen et al. | Using data mining to provide recommendation service | |
| Gill et al. | A fuzzy linguistic approach to data quantification and construction of distance measures for the part family formation problem | |
| Sarraf et al. | Business rules in retail: the Tesco. com story | |
| CN110942082B (en) | Talent value evaluation method | |
| Qing et al. | Data Mining Technology in Business Data Analysis | |
| JP2003524812A (en) | How to generate a star schema data model | |
| Portinale et al. | A fuzzy case retrieval approach based on SQL for implementing electronic catalogs | |
| Liu et al. | Matrix factorization recommendation algorithm based on user characteristics | |
| CN112487185B (en) | Data classification method in power customer field | |
| Pan et al. | Research on E-Commerce Automatic Question Answering System Model Based on Data Mining | |
| CN117495512B (en) | Order data management method, device, equipment and storage medium | |
| Guo et al. | Concept exchange: Constructing interoperable electronic product catalogues in an emergent environment | |
| Ding et al. | Multistage Cloud-Service Matching and Optimization Based on Hierarchical Decomposition of Design Tasks | |
| Ong et al. | Online design reuse tool for the support of the generation, embodiment and detailed design of products | |
| Su | Accurate Marketing Algorithm of Network Video Based on User Big Data Analysis | |
| Temitope | A Model of Intelligent Recommender System with Explicit Feedback Mechanism for Performance Improvement |
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 |