CN117909512A

CN117909512A - Query method, generation method, device, equipment and storage medium of automobile manufacturing relation map

Info

Publication number: CN117909512A
Application number: CN202410010322.8A
Authority: CN
Inventors: 郭恩杨; 陈勇
Original assignee: China Automotive Innovation Co Ltd
Current assignee: China Automotive Innovation Co Ltd
Priority date: 2024-01-03
Filing date: 2024-01-03
Publication date: 2024-04-19

Abstract

The application discloses a query method, a generation method, a device, equipment and a storage medium of an automobile manufacturing relation map, and belongs to the technical field of computers. The method comprises the following steps: acquiring an automobile manufacturing relation map; and responding to the query instruction aiming at the first entity object, performing query processing in the automobile manufacturing relation map, and displaying the manufacturing information network corresponding to the first entity object. According to the application, through carrying out natural language extraction processing on various data sources, a knowledge graph model capable of representing the automobile manufacturing relationship is obtained, a manufacturing information network corresponding to a certain automobile entity object, such as a manufacturing information network of an automobile industrial product and a manufacturing information network corresponding to the automobile industrial product manufacturing object, can be automatically and rapidly queried based on the graph, other entity objects having entity relationship with the automobile entity object and relationship types among the entity objects can be rapidly checked through the network, and the structuring degree and query efficiency of automobile manufacturing information are effectively improved.

Description

Query method, generation method, device, equipment and storage medium of automobile manufacturing relation map

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, a device, an apparatus, and a storage medium for querying an automobile manufacturing relationship map.

Background

In the automotive industry, there are many and complex relationships between automotive parts, and part manufacturing information is relatively distributed in a network.

Therefore, in the related art, the work of sorting the manufacturing data information about the automobile parts generally requires a lot of manual collection of data and resources, and the data form of the manually collected data resources is often a list or the like. In addition, the related manufacturing data of the parts has information barriers, and it is difficult to identify effective data sources of the lower-level sub-parts.

The method for collecting and updating the information of the automobile parts by total manpower is low in automation degree, and delay exists in information updating, so that the query efficiency of the automobile manufacturing information is low. In addition, the automobile parts have various relations, the supply relations are in a chain structure, the data structuring degree of the data storage modes such as the list and the like is low, the inquiry information quantity of automobile manufacturing information is small, and the association relations among the data objects cannot be seen.

Disclosure of Invention

The embodiment of the application provides a query method, a query device and a query storage medium for an automobile manufacturing relation map, which can automatically and quickly query manufacturing information networks corresponding to an automobile entity object, such as manufacturing information networks of automobile industry products and manufacturing information networks corresponding to automobile industry product manufacturing objects, and can quickly check other entity objects having entity relation with the automobile entity object and relation types among the entity objects through the networks, thereby improving query efficiency of automobile manufacturing information.

According to an aspect of an embodiment of the present application, there is provided a query method of an automobile manufacturing relationship map, the method including:

acquiring the automobile manufacturing relation map; the automobile manufacturing relation map comprises a plurality of entity objects and a relation among the entities, the plurality of entity objects at least comprise industrial objects and manufacturing objects, the relation among the entities represents the association relation among entity pairs in the plurality of entity objects, and the entity pairs are a pair of entity objects with the relation among the entities in the plurality of entity objects; the automobile manufacturing relation graph is a knowledge graph model obtained by natural language extraction processing based on various data sources;

And responding to a query instruction aiming at a first entity object, carrying out query processing in the automobile manufacturing relation map, and displaying a manufacturing information network corresponding to the first entity object, wherein the manufacturing information network comprises entity object nodes with target relation with the first entity object, the edge in the manufacturing information network represents the relation type between the two entity objects connected by the edge, and the relation type between the entities comprises at least one of assembly relation, manufacturing relation and supply relation.

According to an aspect of an embodiment of the present application, there is provided a method for generating an automobile manufacturing relationship map, the method including:

Acquiring text information corresponding to a plurality of data sources;

Extracting natural language from the text information to obtain an entity identification object associated with the automobile manufacturing relation in the text information and tag information corresponding to the entity identification object;

Generating an automobile manufacturing relationship map based on the entity identification object and the tag information;

The automobile manufacturing relation map comprises a plurality of entity objects and an inter-entity relation, the plurality of entity objects at least comprise industrial objects and manufacturing objects, the inter-entity relation represents the association relation between entity pairs in the plurality of entity objects, the entity pairs are a pair of entity objects with the inter-entity relation in the plurality of entity objects, the plurality of entity objects are determined based on the entity identification objects, and the inter-entity relation is determined based on the label information.

According to an aspect of an embodiment of the present application, there is provided an apparatus for querying an automobile manufacturing relationship map, the apparatus including:

The map acquisition module is used for acquiring an automobile manufacturing relation map; the automobile manufacturing relation map comprises a plurality of entity objects and a relation among the entities, the plurality of entity objects at least comprise industrial objects and manufacturing objects, the relation among the entities represents the association relation among entity pairs in the plurality of entity objects, and the entity pairs are a pair of entity objects with the relation among the entities in the plurality of entity objects; the automobile manufacturing relation graph is a knowledge graph model obtained by natural language extraction processing based on various data sources;

The network query module is used for responding to a query instruction aiming at a first entity object, carrying out query processing in the automobile manufacturing relation map, and displaying a manufacturing information network corresponding to the first entity object, wherein the manufacturing information network comprises entity object nodes with target relation with the first entity object, an edge in the manufacturing information network represents a relation type between two entity objects connected by the edge, and the relation type between the entities comprises at least one of an assembly relation, a manufacturing relation and a supply relation.

According to an aspect of an embodiment of the present application, there is provided an apparatus for generating an automobile manufacturing relationship map, the apparatus including:

the text information acquisition module is used for acquiring text information corresponding to the plurality of data sources;

The entity object recognition module is used for extracting natural language from the text information to obtain an entity recognition object associated with the automobile manufacturing relation in the text information and tag information corresponding to the entity recognition object;

The map generation module is used for generating an automobile manufacturing relation map based on the entity identification object and the label information;

According to an aspect of an embodiment of the present application, there is provided a computer device, including a processor and a memory, where at least one instruction, at least one program, a code set, or an instruction set is stored in the memory, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the query method of an automobile manufacturing relationship map or the generation method of an automobile manufacturing relationship map described above.

According to an aspect of the embodiment of the present application, there is provided a computer-readable storage medium having stored therein at least one instruction, at least one program, a code set, or an instruction set, which is loaded and executed by a processor to implement the above-described query method of an automobile manufacturing relationship map or the generation method of an automobile manufacturing relationship map.

According to one aspect of an embodiment of the present application, there is provided a computer program product comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from a computer-readable storage medium, and the processor executes the computer instructions so that the computer device executes to implement the above-described query method of an automobile manufacturing relationship map or the generation method of an automobile manufacturing relationship map.

The technical scheme provided by the embodiment of the application can bring the following beneficial effects:

The knowledge graph model capable of representing the automobile manufacturing relation is obtained by extracting and processing various data sources in natural language, a manufacturing information network corresponding to a certain automobile entity object, such as a manufacturing information network of an automobile industrial product and a manufacturing information network corresponding to the automobile industrial product manufacturing object, can be automatically and rapidly queried based on the graph, other entity objects having entity relation with the automobile entity object and relation types among the entity objects can be rapidly checked through the network, and the structuring degree and query efficiency of automobile manufacturing information are effectively improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an application runtime environment provided by one embodiment of the present application;

FIG. 2 is a flow chart of a method for generating an automobile manufacturing relationship map according to one embodiment of the present application;

FIG. 3 illustrates a schematic technical architecture diagram of an automobile manufacturing relationship map;

FIG. 4 schematically illustrates a schematic diagram of a verification interface;

FIG. 5 is a flow chart of a method for querying an automobile manufacturing relationship map provided by one embodiment of the application;

FIG. 6 illustrates a schematic diagram of a query interface;

FIG. 7 is a schematic diagram illustrating an automotive industry smart sourcing query interface;

FIG. 8 illustrates a schematic diagram of an automotive industry supply chain security query interface;

FIG. 9 is a schematic diagram illustrating an automotive industry price warning interface;

FIG. 10 is a schematic diagram illustrating an automotive industry supply risk early warning interface;

FIG. 11 is a block diagram of an apparatus for querying an automobile manufacturing relationship map provided in one embodiment of the present application;

FIG. 12 is a block diagram of an apparatus for generating an automobile manufacturing relationship map according to an embodiment of the present application;

fig. 13 is a block diagram of a computer device according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

Referring to fig. 1, a schematic diagram of an application running environment according to an embodiment of the present application is shown. The application execution environment may include: a terminal 10 and a server 20.

The terminal 10 includes, but is not limited to, a mobile phone, a computer, a vehicle mounted terminal, etc. The terminal 10 may be provided with a client for an application program or a web page for loading an application program.

In the embodiment of the present application, the application may be any application capable of providing a query function of an automobile manufacturing relationship map. Typically, the application is a web page type application, which is not limited by the embodiments of the present application.

The server 20 is used to provide background services for clients of applications in the terminal 10. For example, the server 20 may be a background server of the application program described above. The server 20 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, cdns (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligence platforms, and the like. Alternatively, the server 20 provides background services for applications in a plurality of terminals 10 at the same time.

Alternatively, the terminal 10 and the server 20 may communicate with each other via the network 30. The terminal 10 and the server 20 may be directly or indirectly connected through wired or wireless communication, and the present application is not limited thereto.

Referring to fig. 2, a flowchart of a method for generating an automobile manufacturing relationship map according to an embodiment of the application is shown. The method can be applied to computer equipment, wherein the computer equipment is electronic equipment with data computing and processing capabilities. The method may include the following steps (210-230).

Step 210, obtaining text information corresponding to a plurality of data sources.

Optionally, the plurality of data sources includes, but is not limited to: a business data source and a financial data source corresponding to a production object related to automobile manufacturing; network media data sources associated with automotive manufacturing (e.g., news websites, industry websites, public numbers, purchasing platforms); academic data sources related to automotive manufacturing (e.g., industry report, paper).

Text information related to automobile manufacture, such as "company a produces B products" or the like, may be obtained from the above-described data sources.

And 220, performing natural language extraction processing on the text information to obtain an entity identification object associated with the automobile manufacturing relation and tag information corresponding to the entity identification object in the text information.

Optionally, inputting the text information into a pre-trained natural language extraction processing model or other data processing models, and using the models to perform natural language processing on the text information to identify and extract entity identification objects associated with the automobile manufacturing relationship in the text information; and classifying and marking the entity identification object to obtain the label information of the entity identification object.

The entity recognition object is an entity object recognized from the text information. Such as "company a" and "product B" in the text of "company a produces product B".

The tag information may represent an entity type corresponding to the entity identification object, where the entity type includes at least an industrial type, a manufacturing object type, a purchasing object type, a supply object type, and an accessory type. Industrial product type the physical object characterizing the type may be an industrial product in automotive manufacturing, such as automotive parts, equipment, etc. The manufacturing object type may be an object of manufacturing an industrial product, such as a company, a factory, a scientific research institution, or the like. Purchasing object type an entity object that characterizes that type may be an object that purchases an industrial product to other entity objects, such as a company. The provisioning object type characterizes the type of physical object may be an object that provisions industry to other physical objects.

At step 230, an automobile manufacturing relationship map is generated based on the entity identification object and the tag information.

The automobile manufacturing relation map comprises a plurality of entity objects and relations among the entities, the plurality of entity objects are determined based on the entity identification objects, and the relations among the entities are determined based on the label information. Alternatively, the identified entity-identifying object may be determined to be an entity object in an automotive manufacturing relationship map. And determining the relationship between the entities according to the label information corresponding to the entity identification objects, wherein the relationship between the entities can represent the association relationship between entity pairs in the plurality of entity objects, and the entity pairs are a pair of entity objects with the relationship between the entities in the plurality of entity objects.

The plurality of physical objects include at least an industrial object and a manufacturing object. Types of relationships between entities include, but are not limited to, assembly relationships, manufacturing relationships, and provisioning relationships.

For example, a label corresponding to "a company" in the text of "a company produces B product" is a manufactured object type, and a label corresponding to "B product" is an industrial product type, so that it can be determined that an entity relationship between two entity objects of "a company" and "B product" is a manufactured relationship.

For example, the label corresponding to "a company" in the text of "a company supplies a product to C company" is a supply object type, and the label corresponding to "C company" is a purchase object type, so that it can be determined that the relationship between the entities of the two manufacturing objects of "a company" and "B product" is a supply relationship, and the supply relationship includes a supply direction.

For another example, labels corresponding to "B product" and "D product" in the text of "B product and D product assembled into E product" are accessory types, and labels corresponding to "E product" are industrial types, so that it can be determined that the entity relationship between the two industrial objects of "a company", "B product" and "E product" is the assembly relationship.

In summary, according to the technical scheme provided by the embodiment of the application, through natural language extraction processing on various data sources, the entity objects and the corresponding entity type label information thereof can be identified, a knowledge graph model capable of representing the automobile manufacturing relationship can be constructed and generated based on the identified entity objects and labels, a manufacturing information network corresponding to a certain automobile entity object, such as a manufacturing information network of an automobile industrial product and a manufacturing information network corresponding to an automobile industrial product manufacturing object, can be automatically and quickly queried based on the graph, and the relationship types among other entity objects and entity objects having entity relationships with the automobile entity object can be quickly checked through the network, so that the structuring degree and query efficiency of automobile manufacturing information are effectively improved.

In one example, as shown in FIG. 3, a schematic technical architecture diagram of an automobile manufacturing relationship map is schematically shown. FIG. 3 illustrates a four-level technology architecture including a data source layer, a storage computation layer, a data algorithm layer, and an industry application layer. The data source layer is responsible for data collection from a plurality of illustrated data sources and feeding back the data to the storage computing layer. The data collection modes include, but are not limited to, industry knowledge arrangement, crawling and related data source interface calling modes.

The storage and computation layer comprises a large data platform, wherein data which is collected from a data source layer and related to automobile manufacture can be stored, and the data can enter a graph database after being processed and extracted by a Natural Language Processing (NLP) model. The storage computing layer also includes a distributed graph computation engine and a distributed graph deep learning engine that provide data processing capabilities.

The data algorithm layer provides data processing services of knowledge modeling, task management, automatic graph data storage, knowledge graph task monitoring, engine calculation task monitoring, extraction/fusion model management, graph visualization tools and relation calculation.

The industry application layer provides product and supplier searching, intelligent source searching, supply chain wind control, industry chain safety and other application services based on the automobile manufacturing relation map.

In addition, the automobile manufacturing relationship map can be automatically updated according to data updating of various data sources.

In one possible implementation, a computer device obtains text information that is newly added by a plurality of data sources within a target period; extracting natural language from the text information to obtain an entity identification object associated with the automobile manufacturing relationship and tag information corresponding to the entity identification object in the text information; based on the entity identification object and the tag information, the automobile manufacturing relationship map is updated.

The target period is a period corresponding to the update period, for example, the update period is one day, and then the target period is a period of 24 hours after the last update time. The newly added text information refers to the newly acquired multimedia data in the period, and the computer can extract the corresponding text information from the multimedia data. The method for extracting the natural language from the text information added in the part can be the same as that of the training stage, and the entity recognition object and the label information corresponding to the entity recognition object in the text information in the part can be extracted. And then combining and updating the new identified entity identification object and the label thereof with a plurality of entity objects and relationships among the entities in the current map.

If the current atlas includes the newly identified entity identification object, the entity object may not be newly added, otherwise, the newly identified entity identification object is determined as the entity object in the atlas in the current atlas.

If the relationship between the entities newly identified based on the tag information already exists in the current map, the relationship between the entities can not be newly added; if the current map does not include the relationship between the newly identified entities, the relationship between the entities can be newly increased; if the existing entity relationship in the current map conflicts with the newly identified entity relationship, the existing entity relationship can be kept not updated, or the existing entity relationship can be updated into the newly identified entity relationship.

The current knowledge graph can be automatically updated by regularly identifying potential entity objects and label information thereof in the newly added text in various data sources, so that the association relationship between the automobile entity objects of the latest version and the entity objects is obtained.

According to the technical scheme provided by the embodiment of the application, the supply chain atlas is constructed by means of the data algorithm and the language processing model, the algorithm model is trained by establishing the label system, the matching degree of labels and algorithms is improved, the self-learning capacity of the model is improved, the iterative atlas is updated continuously, and the atlas self-adaptive growth and accurate source searching are realized

After the step 220, the result of the natural language extraction processing may be cleaned in a verification manner, so as to further improve the accuracy of the atlas. In one possible implementation, verification information corresponding to each of the entity identification object and the tag information is obtained. The verification information is entity object information and tag information obtained by verifying the entity identification object and the tag information. If the identified entity identification object and the tag information are accurate, the verification information can be a confirmation information; if at least one of the identified entity identification object and the tag information is inaccurate, the verification information may include at least one of a modified entity identification object and modified tag information.

Correspondingly, updating the automobile manufacturing relation map based on the entity identification object and the label information comprises the following steps: and generating or updating an automobile manufacturing relation map based on the verification information corresponding to the entity identification object and the label information.

And the entity identification result and the label classification result of the natural language extraction processing are checked again, so that the model accuracy of the knowledge graph can be effectively improved.

The verification mode may be manual verification or automatic verification, which is not limited in the embodiment of the present application. In one example, as shown in FIG. 4, a schematic diagram of a verification interface is illustratively shown. In the verification interface 40, textual information 401, specific relationship information 402 between entities, an entity identification object 403, an entity identification object 404, an entity type 405 corresponding to the entity identification object 403, and an entity type 406 corresponding to the entity identification object 404 are displayed. Each recognition result includes a corresponding modification component 407 alongside, and the device may generate the verification information described above in response to operation of the modification component 407.

The above part describes the query method of the automobile manufacturing relation map, and the following description describes the query method of the map.

Referring to fig. 5, a flowchart of a query method of an automobile manufacturing relationship map according to an embodiment of the application is shown. The method can be applied to a computer device, wherein the computer device is an electronic device with data computing and processing capabilities, and the execution subject of each step can be the terminal 10 in the application running environment shown in fig. 1. The method may include the following steps (510-520).

Step 510, obtaining an automobile manufacturing relationship map.

Similar to the foregoing embodiment, the automobile manufacturing relationship map includes a plurality of entity objects and a relationship between entities, the plurality of entity objects including at least an industrial object and a manufacturing object, the relationship between entities representing an association relationship between a pair of entities in the plurality of entity objects, the pair of entities being a pair of entity objects having a relationship between entities in the plurality of entity objects; the automobile manufacturing relation graph is a knowledge graph model obtained by natural language extraction processing based on various data sources.

For the method for generating the automobile manufacturing relationship map, reference may be made to the foregoing, and details are not repeated here.

In step 520, in response to the query instruction for the first entity object, query processing is performed in the automobile manufacturing relationship map, and the manufacturing information network corresponding to the first entity object is displayed.

The manufacturing information network characterizes a corresponding relationship network of the first entity object throughout the automotive manufacturing industry. The manufacturing information network comprises entity object nodes with target relations with the first entity objects, and the relation type between the entities of the two entity objects connected by the edge characterization and the edge in the manufacturing information network comprises at least one of assembly relations, manufacturing relations and supply relations.

The first entity object may be any node in the manufacturing information network, such as a central node, a start node, etc.

In one possible implementation, the computer device may display a query interface corresponding to an automobile manufacturing relationship map. The query interface may be a web page in a browser, which is not limited in the embodiment of the present application. The query interface may specifically include an object input component, where the object input component is configured to receive identification information, such as an object name, corresponding to the first entity object.

Optionally, the query interface is configured to receive a query instruction, where the query instruction includes a first entity object and a target relationship, and the target relationship is based on one or more relationship types between entities configured by the query interface. The query instruction may be triggered by a query option in the interface, for example, after the user inputs the name of the first entity object, clicking the query option triggers the query instruction.

The target relationship may be one or more relationship types between entities selected by a user through a relationship selection component in the query interface, or may be one or more relationship types between entities configured by default in the query interface. Different types of query interfaces can correspond to different query functions, so that different relationships among entities can be configured as target relationships by default. For example, the query interface is an upstream-downstream relation query interface for realizing the query of the upstream-downstream assembly relation of the industrial product, and the assembly relation is set as a target relation by default. For another example, the query interface is a manufacturing relationship query interface for implementing a query for an industrial manufacturing relationship, and the interface default configuration may be a manufacturing relationship. The supply relationships are similar.

Accordingly, the specific implementation manner of step 520 may be: and based on the first entity object and the target relation, inquiring in the automobile manufacturing relation map, and displaying the manufacturing information network.

In one example, as shown in FIG. 6, a schematic diagram of a query interface is illustratively shown. Included in the query interface 60 is an entity object type selection box 601 in which the user can select the type of entity object to be queried, such as an industrial type or a manufactured object type (e.g., a company or factory type). Also included in the query interface 60 is an entity object identification input box 602 in which the user may enter an object identification, such as a name, of the first entity object described above.

The query interface 60 also includes configured target relationships 603 (assembly relationships). After confirming the information, the user can click the query button 604 in the query interface to trigger the query instruction, and the system searches according to the input entity object and target relation, and displays the manufacturing information network 605 of the entity object. In addition, list information corresponding to the network nodes is also available, wherein entity objects and attribute information corresponding to each node, such as the price of the industrial product, the nature of the company manufacturing the object, etc., can be displayed.

In one possible use scenario provided in the foregoing embodiment, the first entity object includes an industrial object to be queried, and the query instruction further includes an object attribute search condition. The object attribute searching condition comprises parameter information corresponding to the target attribute parameter. The object attribute searching condition is used for screening the entity object with the target attribute conforming to the parameter information. The target attribute may be one or more of a plurality of object attributes. The target attribute, i.e. the parameter information thereof, may be selectively configured in the query interface, or may be configured by default in the query interface, which is similar to the selection configuration manner of the target relationship.

Correspondingly, under the scene, the computer equipment can perform query processing in the automobile manufacturing relation map based on the industrial object, the target relation and the object attribute searching condition, and display a supply chain information network corresponding to the industrial object;

the manufacturing information network comprises a supply chain information network, a central node of the supply chain information network represents an industrial object, a branch node of the supply chain information network represents an entity object which directly or indirectly has a target relation with the industrial object, and attribute information of the entity object corresponding to the branch node meets object attribute searching conditions.

For example, the target attribute is a manufacturing property corresponding to the industrial object, and the corresponding parameter information is a domestic identifier. The entity object corresponding to the branch node in the supply chain information network may be: and a domestic industrial object directly or indirectly having an assembly relationship with the industrial object.

Optionally, in the case that the first entity object is an industrial object, the query instruction may be a supply chain query instruction, where the corresponding target relationship includes at least one of the assembly relationship, the manufacturing relationship, and the supply relationship, so that a supply chain network with the industrial object as a central node may be flexibly displayed.

In one possible example, as shown in fig. 7, a schematic diagram of an automotive industry wisdom sourcing query interface is shown. The intelligent sourcing query interface 70 shown in fig. 7 is one of the above-mentioned query interfaces, and the intelligent sourcing query interface 70 is used for providing supply chain source traceability services. The default configuration of the target relationships of the intelligent sourcing query interface 70 includes the assembly relationships, manufacturing relationships, and supply relationships described above, such that the supply chain network 702 centered on the industrial object 701 can be displayed in all aspects and dimensions.

Optionally, the intelligent sourcing query interface 70 may further display a parameter selection component 703 corresponding to a plurality of attributes (i.e. the target attributes), and the user may configure parameter information corresponding to the plurality of attributes through the parameter selection component 703, so as to generate the object attribute searching condition.

Based on the design, in the technical field of automobile manufacturing, supply chain intelligent source searching can be realized based on a knowledge graph. Specifically, based on multiple data sources (enterprise business data, industry websites, public numbers, bidding platforms, industry research reports, financial reports of marketing companies and the like), a data algorithm model, natural language processing and label establishment are utilized to conduct knowledge extraction and expert checking, an automobile supply chain map based on a multi-dimensional relationship of parts/equipment-suppliers is constructed, a model is continuously trained by improving the matching degree of labels and algorithms, the cyclic reciprocation is achieved, the self-adaptive growth and accurate source searching of the map are achieved, the self-learning capability of the model is achieved, and the accurate source searching and intelligent pushing according to label classification are achieved.

In another possible use scenario provided in the foregoing embodiment, the first entity object includes an industrial object to be queried, and the query instruction further includes a target attribute; in this scenario, the target attribute refers to an entity object attribute whose attribute information needs to be displayed in the supply chain information network.

Accordingly, in this scenario, the computer device may perform query processing in the automobile manufacturing relationship graph based on the industrial object and the target relationship, and determine the supply chain information network corresponding to the industrial object and the target entity object in the supply chain information network, where the target attribute has been associated. The manufacturing information network includes a supply chain information network. The target entity object refers to an entity object that is associated with the target attribute because entity objects in the supply chain information network are not necessarily all associated with the target attribute.

Displaying a supply chain information network; and displaying attribute information corresponding to the target entity object on the target attribute based on the node corresponding to the target entity object. In this scenario, for the entity object associated with the target attribute, the attribute information of the corresponding target attribute needs to be displayed, so that the user can clearly see what the attribute information is.

The target attributes include, but are not limited to, price attributes, attribution attributes. The price attribute represents price parameters corresponding to the industrial product. The attribution attribute can represent attribution properties corresponding to the manufactured objects, such as national pose, foreign materials and the like.

In one example, as shown in FIG. 8, a schematic diagram of an automotive industry supply chain security query interface is illustratively shown. The supply chain network 802 corresponding to the entity object 801 is displayed in the supply chain security query interface 80 shown in fig. 8. In this example, the target attribute is a home attribute, and the target entity object associated with the home attribute is a manufacturing object. Accordingly, home attribute information 804 corresponding to the manufacturing object 803 and hint information 805 associated with the home attribute (i.e., target attribute) such as "homemade autonomous controllable" are displayed on the supply chain network 802.

Based on the design, in the technical field of automobile manufacturing, industrial chain autonomous safety identification can be realized based on a knowledge graph. Specifically, a certain part or equipment node in the industrial chain is taken as an object, a provider core label is identified, and the association relation between the provider structure (such as enterprise property, quantity, scale and the like) of the part or equipment node and the industrial autonomous security is analyzed by establishing an algorithm model and expert checking, so that the autonomous security identification of the node and the whole industrial chain is realized. Specifically, the domestic autonomous controllable degree in the product field of parts or equipment and the like is identified through algorithm models and data analysis, so that the safety monitoring of an industrial chain is realized. According to the technical scheme, based on the supplier resource structural analysis of a certain part or equipment node in the supply chain map, an association relation evaluation model of a supplier structure and autonomous controllability is established, the autonomous controllability degree of the node and an associated industry chain is identified, and a reference basis is provided for industry planning, industry guidance and policy formulation.

In one possible implementation manner, the map may also perform a function of monitoring and early warning of related attributes. In order to realize the monitoring and early warning of the related attributes, the method further comprises the following steps:

Monitoring attribute information of each entity object in the knowledge graph; the attribute information includes, but is not limited to, the following attributes:

Price attribute, productivity attribute, source material price attribute and other industrial product attributes corresponding to the industrial product object; attribution attribute, business attribute, legal attribute, financial attribute and the like corresponding to the manufacturing object.

Triggering a query instruction under the condition that the attribute information of the first entity object is detected to be changed;

the query instruction triggered in this case will be used to trigger the execution of the following steps:

determining a supply chain information network corresponding to the first entity object in the automobile manufacturing relation map; the manner of determining the supply chain information network may refer to several manners mentioned in the foregoing embodiments, and will not be described herein.

And displaying the change attribute information corresponding to the supply chain information network and the first entity object.

In this way, when the attribute information of a certain entity object changes, the push display of the supply chain network can be timely performed, and the changed attribute information corresponding to the entity object can be displayed in the push display. The change attribute information is used for indicating at least one of an attribute parameter and a parameter change content in which the attribute information change occurs.

In one example, as shown in FIG. 9, a schematic diagram of an automotive industry price warning interface is illustratively shown. In this example, the target attribute may be a price attribute. The price pre-warning interface 90 shown in fig. 9 shows an assembly relationship network 902 corresponding to the entity object 901. Wherein, the corresponding network node of each industrial object displays the corresponding source material price change information 903. Based on the design, the intelligent monitoring and transmission of the upstream and downstream of the change of the core elements of the supply chain can be realized by depending on industry and provider big data.

In one possible design, the supply chain information network described above may be displayed as follows:

The computer equipment determines a corresponding network branch of the first entity object in the supply chain information network, and displays the network branch in a marked display state in the supply chain information network; and displaying the change attribute information based on the network node corresponding to the first entity object.

The network branch may be a network branch in which the first entity object is located. The above-described marker display state may be a display state different from other network branches to distinguish, for example, a display state of bolded, highlighted, blinking display, or the like.

In another possible design, in addition to displaying the network branches and the change attribute information, in a case that the change attribute information meets the prompt triggering condition corresponding to the second entity object, prompt information corresponding to the prompt triggering condition may be displayed based on the network node corresponding to the second entity object; wherein the second entity object is an entity object in the supply chain information network.

The prompt triggering condition may be a threshold condition or a state condition, which is not limited in the embodiment of the present application. The change attribute information may be a value type information, such as a price, and the prompt trigger condition may be a threshold condition. For example, the first entity object is an industrial object, the second entity object is an upstream industrial object of the first entity object, and if the price of the first entity object changes, the price of the second entity object is affected, so that the prompt triggering condition that the second entity object can be associated with may be a downstream product price change prompt condition, specifically, a threshold condition, and if the price change condition of the first entity object meets the threshold condition, if the fluctuation exceeds the threshold, prompt information of price early warning may be displayed based on a network node corresponding to the second entity object.

In one example, as shown in fig. 10, a schematic diagram of an automotive industry supply risk early warning interface is illustratively shown. The supply-risk early warning interface 100 shown in fig. 10 displays a supply-chain network 1001, which includes a manufacturing object 1002, and displays a business change risk prompt message 1003 beside a node of the manufacturing object 1002 because of a change in a business attribute corresponding to the manufacturing object 1002, and highlights a network branch 1004 where the manufacturing object 1002 is located. Since there is an entity relationship between the manufacturing object 1005 and the manufacturing object 1002 in the network branch 1004, and the manufacturing object 1005 is associated with a vendor change warning condition, if the vendor attribute corresponding to the manufacturing object 1002 is changed, vendor risk presentation information 1006 corresponding to the vendor change warning condition can be displayed near the node of the manufacturing object 1005.

Based on the design, in the technical field of automobile manufacturing, supply chain risk monitoring can be achieved based on a knowledge graph. Specifically, a supply chain map in the field of parts/equipment is used as a business bottom layer, the supply chain management core elements (such as business basic data, supplier core business change, bulk material price fluctuation and the like) are arranged in a layer-by-layer layout manner, the elements and algorithms are matched, an upstream and downstream transmission path of supply chain core element change is identified, and multi-stage supply chain risk early warning and intelligent pushing are realized. According to the technical scheme, based on layering and grading of the supply chain map, risks of specific enterprises, risks of industrial core elements (such as bulk material prices) and the like can be rapidly and comprehensively conducted to upstream and downstream enterprises of an industrial chain through intelligent monitoring and pushing of the system, and multi-level, timely and comprehensive transfer of risks is achieved.

In summary, according to the technical scheme provided by the embodiment of the application, through carrying out natural language extraction processing on various data sources, a knowledge graph model capable of representing the automobile manufacturing relationship is obtained, and based on the graph, a manufacturing information network corresponding to a certain automobile entity object, such as a manufacturing information network of an automobile industrial product and a manufacturing information network corresponding to an automobile industrial product manufacturing object, can be automatically and rapidly queried, and other entity objects having entity relationship with the automobile entity object and relationship types among the entity objects can be rapidly checked through the network, so that the structuring degree and query efficiency of automobile manufacturing information are effectively improved.

Specifically, the technical scheme provided by the embodiment of the application has the following technical functions:

defining data sources and data types, including supply chain base data, business data, industry data sources, and the like;

Data NLP extraction model establishment, extracting part/equipment names, suppliers and relations from specified data sources;

Constructing a supply chain map, namely performing map modeling on the extracted data, performing algorithm analysis and label classification to form a map relationship, and continuously perfecting and expanding the supply chain map in an automatic warehouse entry or expert checking mode;

Through model training and label iteration, an intelligent screening database (synonym library/blacklist library) is established, and the accuracy of data extraction is improved;

Knowledge precipitation of an algorithm model is adopted, so that the knowledge and growth of the atlas are continuously expanded, the data value is fully mined, and intelligent source searching is realized;

The method comprises the steps of performing external collection of core element information (industrial and commercial basic data, supplier core business change, bulk material price fluctuation and the like) through supply chain management, calculating and storing the collected data according to preset risk calculation rules, comparing a risk calculation result with a threshold value, and notifying enterprise risk details of relevant nodes of the supply chain along a hierarchical route in an industrial map when the risk value exceeds the threshold value;

The autonomous controllable degree of the industrial chain node is defined by carrying out supplier structure analysis on a part or equipment node in the industrial chain, and the data analysis result is periodically updated.

The following are examples of apparatus of the application that may be used to perform the method embodiments of the application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method of the present application.

Referring to fig. 11, a block diagram of an apparatus for querying an automobile manufacturing relationship map according to an embodiment of the application is shown. The device has the function of realizing the query method of the automobile manufacturing relation graph, and the function can be realized by hardware or by executing corresponding software by the hardware. The device may be a computer device or may be provided in a computer device. The apparatus 1100 may include:

a map acquisition module 1110 for acquiring an automobile manufacturing relationship map; the automobile manufacturing relation map comprises a plurality of entity objects and a relation among the entities, the plurality of entity objects at least comprise industrial objects and manufacturing objects, the relation among the entities represents the association relation among entity pairs in the plurality of entity objects, and the entity pairs are a pair of entity objects with the relation among the entities in the plurality of entity objects; the automobile manufacturing relation graph is a knowledge graph model obtained by natural language extraction processing based on various data sources;

the network query module 1120 is configured to perform query processing in the automobile manufacturing relationship graph in response to a query instruction for a first entity object, and display a manufacturing information network corresponding to the first entity object, where the manufacturing information network includes entity object nodes having a target relationship with the first entity object, an edge in the manufacturing information network characterizes a relationship type between two entity objects connected by the edge, and the relationship type between entities includes at least one of an assembly relationship, a manufacturing relationship, and a supply relationship.

Referring to fig. 12, a block diagram of an apparatus for generating an automobile manufacturing relationship map according to an embodiment of the present application is shown. The device has the function of realizing the method for generating the automobile manufacturing relation graph, and the function can be realized by hardware or by executing corresponding software by the hardware. The device may be a computer device or may be provided in a computer device. The apparatus 1200 may include:

a text information obtaining module 1210, configured to obtain text information corresponding to a plurality of data sources;

The entity object recognition module 1220 is configured to perform natural language extraction processing on the text information to obtain an entity recognition object associated with an automobile manufacturing relationship in the text information and tag information corresponding to the entity recognition object;

A map generation module 1230 for generating an automobile manufacturing relationship map based on the entity recognition object and the tag information;

It should be noted that, in the apparatus provided in the foregoing embodiment, when implementing the functions thereof, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be implemented by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the apparatus and the method embodiments provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the apparatus and the method embodiments are detailed in the method embodiments and are not repeated herein.

Referring to fig. 13, a block diagram of a computer device according to an embodiment of the present application is shown. The computer device may be a terminal. The computer device is used for implementing the query method of the automobile manufacturing relation map or the generation method of the automobile manufacturing relation map provided in the above embodiment. Specifically, the present application relates to a method for manufacturing a semiconductor device.

In general, the computer device 1300 includes: a processor 1301, and a memory 1302.

Processor 1301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. Processor 1301 may be implemented in at least one hardware form of DSP (DIGITAL SIGNAL processing), FPGA (Field Programmable GATE ARRAY ), PLA (Programmable Logic Array, programmable logic array). Processor 1301 may also include a main processor, which is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 1301 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, processor 1301 may also include an AI (ARTIFICIAL INTELLIGENCE ) processor for processing computing operations related to machine learning.

Memory 1302 may include one or more computer-readable storage media, which may be non-transitory. Memory 1302 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 1302 is used to store at least one instruction, at least one program, code set, or instruction set configured to be executed by one or more processors to implement the above-described query method of an automobile manufacturing relationship map or generation method of an automobile manufacturing relationship map.

In some embodiments, the computer device 1300 may further optionally include: a peripheral interface 1303 and at least one peripheral. The processor 1301, the memory 1302, and the peripheral interface 1303 may be connected by a bus or signal lines. The respective peripheral devices may be connected to the peripheral device interface 1303 through a bus, a signal line, or a circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 1304, a touch display screen 1305, a camera assembly 1306, audio circuitry 1307, a positioning assembly 1308, and a power supply 1309.

The memory also includes a computer program stored in the memory and configured to be executed by the one or more processors to implement the above-described query method of an automobile manufacturing relationship map or generation method of an automobile manufacturing relationship map.

Those skilled in the art will appreciate that the architecture shown in fig. 13 is not limiting of the computer device 900, and may include more or fewer components than shown, or may combine certain components, or employ a different arrangement of components.

In an exemplary embodiment, a computer readable storage medium is also provided, where at least one instruction, at least one program, a code set, or an instruction set is stored, where the at least one instruction, the at least one program, the code set, or the instruction set, when executed by a processor, implement the above-mentioned query method of an automobile manufacturing relationship map or the generation method of an automobile manufacturing relationship map.

Alternatively, the computer-readable storage medium may include: ROM (read only memory), RAM (Random Access Memory ), SSD (solid STATE DRIVES), or optical disk, etc. The random access memory may include, among other things, reRAM (RESISTANCE RANDOM ACCESS MEMORY, resistive random access memory) and DRAM (Dynamic Random Access Memory ).

In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-described query method of the automobile manufacturing relationship map or the generation method of the automobile manufacturing relationship map.

It should be understood that references herein to "a plurality" are to two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. In addition, the step numbers described herein are merely exemplary of one possible execution sequence among steps, and in some other embodiments, the steps may be executed out of the order of numbers, such as two differently numbered steps being executed simultaneously, or two differently numbered steps being executed in an order opposite to that shown, which is not limiting.

In addition, in the specific embodiment of the present application, related data such as user information is related, when the above embodiment of the present application is applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use and processing of related data need to comply with related laws and regulations and standards of related countries and regions.

The foregoing description of the exemplary embodiments of the application is not intended to limit the application to the particular embodiments disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the application.

Claims

1. A method for querying an automotive manufacturing relationship graph, the method comprising:

2. The method according to claim 1, wherein the method further comprises:

Displaying a query interface corresponding to the automobile manufacturing relation map, wherein the query interface is used for receiving the query instruction, the query instruction comprises the first entity object and the target relation, and the target relation is one or more entity relation types configured based on the query interface;

The responding to the inquiry instruction for the first entity object carries out inquiry processing in the automobile manufacturing relation map, displays the manufacturing information network corresponding to the first entity object, and comprises the following steps:

And carrying out query processing in the automobile manufacturing relation map based on the first entity object and the target relation, and displaying the manufacturing information network.

3. The method of claim 2, wherein the first entity object comprises an industrial object to be queried, and the query instruction further comprises an object attribute lookup condition;

The query processing is performed in the automobile manufacturing relation map based on the first entity object and the target relation, and the manufacturing information network is displayed, including:

Based on the industrial object, the target relation and the object attribute searching condition, carrying out query processing in the automobile manufacturing relation map, and displaying a supply chain information network corresponding to the industrial object;

The manufacturing information network comprises the supply chain information network, a central node of the supply chain information network represents the industrial object, a branch node of the supply chain information network represents an entity object directly or indirectly in the target relation with the industrial object, and attribute information of the entity object corresponding to the branch node meets the object attribute searching condition.

4. The method of claim 2, wherein the first entity object comprises an industrial object to be queried, the query instruction further comprising a target attribute;

Based on the industrial object and the target relation, carrying out query processing in the automobile manufacturing relation map, and determining a supply chain information network corresponding to the industrial object and a target entity object in the supply chain information network, which is related to the target attribute, wherein the manufacturing information network comprises the supply chain information network;

Displaying the supply chain information network; and displaying attribute information corresponding to the target entity object on the target attribute based on the node corresponding to the target entity object.

5. The method according to claim 1, wherein the method further comprises:

monitoring attribute information of each entity object in the knowledge graph;

triggering the query instruction under the condition that the attribute information of the first entity object is detected to be changed;

Determining a supply chain information network corresponding to the first entity object in the automobile manufacturing relation map;

6. The method of claim 5, wherein the method further comprises:

Determining a corresponding network branch of the first entity object in the supply chain information network;

The displaying the supply chain information network and the change attribute information corresponding to the first entity object includes:

displaying the network branches in the supply chain information network in a marked display state;

And displaying the change attribute information based on the network node corresponding to the first entity object.

7. A method according to claim 5 or6, characterized in that the method comprises:

Displaying prompt information corresponding to prompt triggering conditions based on the network node corresponding to the second entity object under the condition that the change attribute information meets the prompt triggering conditions corresponding to the second entity object;

Wherein the second entity object is an entity object in the supply chain information network.

8. The method according to claim 1, wherein the method further comprises:

Acquiring newly added text information of the plurality of data sources in a target period;

Updating the automobile manufacturing relationship map based on the entity identification object and the tag information.

9. The method of claim 8, wherein the method further comprises:

acquiring verification information corresponding to the entity identification object and the label information;

The updating the automobile manufacturing relationship map based on the entity identification object and the tag information comprises the following steps:

And updating the automobile manufacturing relation map based on the verification information corresponding to the entity identification object and the label information.

10. A method for generating an automotive manufacturing relationship map, the method comprising:

Acquiring text information corresponding to a plurality of data sources;

11. A query device for an automotive manufacturing relationship map, the device comprising:

12. An apparatus for generating an automobile manufacturing relationship map, the apparatus comprising:

13. A computer device, characterized in that it comprises a processor and a memory, in which at least one instruction, at least one program, a set of codes or a set of instructions is stored, which is loaded and executed by the processor to implement the query method of an automobile manufacturing relationship map according to any one of claims 1 to 9 or to implement the generation method of an automobile manufacturing relationship map according to claim 10.

14. A computer-readable storage medium, characterized in that at least one instruction, at least one program, a code set, or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the query method of the automobile manufacturing relationship map according to any one of claims 1 to 9, or to implement the generation method of the automobile manufacturing relationship map according to claim 10.