CN116431835B - Automatic knowledge graph construction method, equipment and medium in automobile authentication field - Google Patents
Automatic knowledge graph construction method, equipment and medium in automobile authentication field Download PDFInfo
- Publication number
- CN116431835B CN116431835B CN202310660801.XA CN202310660801A CN116431835B CN 116431835 B CN116431835 B CN 116431835B CN 202310660801 A CN202310660801 A CN 202310660801A CN 116431835 B CN116431835 B CN 116431835B
- Authority
- CN
- China
- Prior art keywords
- entity
- class
- model
- authentication
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000004806 packaging method and process Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000004927 fusion Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009193 crawling Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000010348 incorporation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06N5/02—Knowledge representation; Symbolic representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses an automatic knowledge graph construction method, equipment and medium in the field of automobile authentication. The method comprises the following steps: acquiring automobile authentication data of different authentication sources at fixed time; according to the structural characteristics of the authentication data, the automobile authentication data from different authentication sources are packaged into a plurality of entity classes with uniform structures; specifically, if the authentication data of any authentication source is semi-structured data or unstructured data, constructing a relation model of the authentication data; loading at least one entity model class in the authentication data according to the relation model, and packaging the data content in each entity model class into each entity class with uniform structure; and constructing an authentication knowledge graph according to the entity classes.
Description
Technical Field
The embodiment of the application relates to the technical field of artificial intelligence, in particular to an automatic knowledge graph construction method, equipment and medium in the field of automobile authentication.
Background
Knowledge graph is a structured semantic and knowledge base that describes entities and interrelationships between entities in the physical world.
At present, the content contained in the knowledge graph in the automobile field is compared on one side, and particularly in the automobile authentication field, no method is available for fusing various automobile authentication data to form the knowledge graph about authentication information.
Disclosure of Invention
The embodiment of the application provides an automatic knowledge graph construction method, equipment and medium in the field of automobile authentication.
In a first aspect, an embodiment of the present application provides a method for constructing an automated knowledge graph in the field of automobile authentication, including:
acquiring automobile authentication data of different authentication sources at fixed time;
according to the structural characteristics of the authentication data, the automobile authentication data from different authentication sources are packaged into a plurality of entity classes with uniform structures; specifically, if the authentication data of any authentication source is semi-structured data or unstructured data, constructing a relation model of the authentication data; loading at least one entity model class in the authentication data according to the relation model, and packaging the data content in each entity model class into each entity class with uniform structure;
and constructing an authentication knowledge graph according to the entity classes.
In a second aspect, an embodiment of the present application further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the automated knowledge graph construction method for an automotive authentication field according to any of the embodiments.
In a third aspect, an embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the program when executed by a processor implements the method for constructing an automated knowledge graph in the automotive authentication field according to any one of the embodiments.
The embodiment of the application provides a method which can be realized through simple deployment, can realize custom modeling, is automatic, can quickly and efficiently construct a knowledge graph in the automobile authentication field, determines entity types, entity model types and relationship names applicable to the automobile authentication field according to the internal logic of related data in the automobile authentication field, realizes unified packaging processing of data of different authentication sources, and can automatically realize construction, updating and expansion of the knowledge graph by business personnel through simple relationship modeling and deployment. In particular, for unstructured or semi-structured authentication data, entity model classes in the authentication data are automatically loaded according to the constructed relation model, entity parameters and entity relations are analyzed, and the entity parameters and the entity relations are packaged into entity classes with uniform structures, so that information fusion of different authentication sources is realized, and a basis is provided for an authentication domain knowledge graph.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an automated knowledge graph construction method in the field of automobile authentication, which is provided by an embodiment of the application;
FIG. 2 is a schematic diagram of a relationship model of automobile authentication data according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a flowchart of map merging according to an embodiment of the present application;
fig. 4 is a schematic diagram of an authentication knowledge graph in an automotive field according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the application, are within the scope of the application.
In the description of the present application, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present application, it should also be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
The embodiment of the application provides an automatic knowledge graph construction method in the field of automobile authentication. To illustrate the method, several basic concepts of the present application are preferentially described.
Entity: refers to a specific object related to the field of automobile authentication, and comprises a specific automobile model, a specific chassis, a specific engine and the like. An entity is a specific concept.
Entity class: referring to a data structure for storing entity parameter values, the parameter values for each entity are stored in one entity class.
Entity model: the abstract concepts related to the automobile authentication field comprise automobile types, chassis, engines and the like, but refer to a class of entities, and do not refer to a specific entity.
Entity model class: refers to a data structure for storing entity parameter names, what parameters each entity possesses will be stored in one entity model class, but no specific parameter values are stored in the entity model class.
In addition, the entity and the entity model are consistent in type, and each comprises at least one of the following: vehicle model, in-vehicle parts, enterprise, product brand. For example, when the type of a certain entity is a vehicle type, the type of the entity model is also a vehicle type.
Based on the above concepts, fig. 1 is a flowchart of an automated knowledge graph construction method in the field of automobile authentication according to an embodiment of the present application. The method is suitable for fusing the automobile authentication data of different authentication sources into a unified automobile knowledge graph, and is executed by the electronic equipment. As shown in fig. 1, the method specifically includes:
s110, acquiring automobile authentication data of different authentication sources at fixed time.
The authentication source refers to an authentication type in the automotive field and can comprise at least one of the following: product admittance, recommended catalogs, vehicle and ship tax, oil consumption, environmental protection, purchase tax and the like, and provides knowledge sources for the construction of the knowledge graph. Optionally, in this embodiment, the authentication data sources are uniformly managed, and knowledge acquisition in the field of automobile authentication is periodically and repeatedly performed; the acquisition mode can be updated as required, and knowledge acquisition of the change part is executed when the data source is updated or expanded.
S120, according to the structural characteristics of the authentication data, the automobile authentication data from different authentication sources are packaged into a plurality of entity classes with uniform structures.
The method comprises the steps of firstly obtaining data contents in authentication data, including various entities, parameters, relations and the like in the field of automobile authentication, and then carrying out standardization processing on the contents to realize unified packaging of data with different authentication sources. According to the structural characteristics of the authentication data, the process comprises the following two cases:
in case one, the authentication data is semi-structured data or unstructured data, such as text, audio, video, pictures, etc. The data needs to be extracted to further establish a knowledge graph, and the embodiment analyzes and encapsulates the data content in the following manner:
first, a relational model of the authentication data is constructed. The relationship model is used for describing the relationship between the entity model and the entity model, and is constructed for the entity model, not for a specific entity. For the first added authentication source, a relational model of the authentication data needs to be built. Optionally, at least one entity in the authentication data is obtained, and each entity is replaced by each entity model with the same type; and determining the relationship names among the entity models, and constructing a relationship model of the authentication data according to the relationship names. Specifically, the relationship name includes: containing relationships, belonging relationships, owning relationships, flag relationships, loading relationships, loaded relationships. The process can be realized by a service person through a third-party modeling tool, or can be realized automatically by electronic equipment according to a preset program, taking the authentication source of product admission as an example, a finally obtained relation model is shown in fig. 2, and the entity model in fig. 2 comprises: the relationship names among the entity models are shown in figure 2, namely authentication reporting conditions, product admittance update expansion, vehicle types, vehicle interior parts (comprising an engine and a chassis), enterprises and product brands. The primary key in the figure is the primary parameter, and the foreign key is the other parameter. After the relation model is built, the method is applicable to all data of the same authentication source, and when the authentication source has data update, only entity models which are not contained in the existing relation model are required to be added or updated.
And when the relation model is constructed, two data structures of entity model class and entity class can be declared for analyzing and packaging data content. In order to improve the conciseness and the readability of the data structure, four specific data structures of parameter class, relation class, entity model class and entity class can be declared under the same father class, so that the structure and the name can be mutually used. In a specific embodiment, first, a parameter class and a relationship class are declared under the parent class, wherein the parameter class includes a parameter name, a parameter type, and a parameter value, and the relationship class includes a relationship name. Then, based on the parameter class and the relation class, declaring an entity model class and an entity class under the parent class. Specifically, the entity model class includes a type of entity model, an authentication source, a main parameter name, other parameter names, and a relationship name between entity models, where the main parameter is a parameter for distinguishing different entities under the same entity model class, and the other parameter is other parameters except the main parameter, and for an entity model class in which data is written, by using the type of entity model and the main parameter of entity model, it is possible to uniquely identify which entity the entity model class corresponds to; in addition, the main parameter names and other parameter names of the entity models all refer to parameter names in the parameter class, and the relationship names among the entity models refer to relationship names in the relationship class. The entity class comprises an entity type, main parameters (comprising parameter names and parameter values) of the entity, other parameters (comprising parameter names and parameter values) of the entity and relationship names among the entities, wherein the main parameters and the other parameters of the entity have the same meaning as the main parameters and the other parameters of the entity model, and for the entity class written with data, the entity type and the main parameters of the entity can be used for uniquely identifying which entity the entity class corresponds to; in addition, the parameter names of the main parameter and other parameters of the entity all refer to the parameter names in the parameter class, and the relation names among the entities refer to the relation names in the relation class.
The relationship model and the data structure are provided, and at least one entity model class in the authentication data can be loaded according to the relationship model and the data structure. Optionally, acquiring at least one entity in the authentication data; distinguishing a direct entity and at least one indirect entity according to the subject of the authentication data and the parameter detail degree of each entity; constructing a entity model class, and referring to the type of the direct entity as the type of the entity model in the entity model class; and determining the relationship names between the direct entity and each indirect entity according to the relationship model, and taking the relationship names as the relationship names between the entity models in the entity model class. Thus, the entity model class with the direct entity as the object is obtained as follows:
class Model extends CerData {// mockup class Model inherits from parent CerData
UUID Model ID type of the entity Model (type of direct entity)
ParamyKeyprimaryKey;// principal parameter name of entity model (principal parameter name corresponding to direct entity)
Source, i.e. data Source
List < ParamKey > Paramakey;// Parametity List of entity model (Parametity corresponding to direct entity)
List < Relation > Relation; (Relation name between direct entity and each indirect entity)
Illustratively, assuming that the authentication data originates from multiple pages, the relationship model is an overall model built for all entities of the pages. One page is the whole information about the entity of the vehicle model, and relates to the entity of the vehicle interior components such as a chassis, an engine and the like, wherein the data subject can be the vehicle model according to the page title, or the parameters of the entity of knowing the vehicle model are the most detailed through page crawling, and the vehicle model is taken as a direct entity to construct the entity model class taking the vehicle model as an object. The other page is specific information about the chassis entity, and also relates to the entities such as vehicle type, engine and the like, wherein the data subject can be identified as the chassis according to the page title, or the parameters of the entity of the chassis can be obtained through page crawling in the most detailed way, the chassis is taken as a direct entity, and the entity model class taking the chassis as an object is constructed.
And after the entity model class is loaded, packaging the data content in each entity model class into each entity class with uniform structure. Optionally, constructing an entity class under the parent class aiming at any loaded entity model class; referencing the type of the entity model in the entity model class as the entity type in the entity class; the parameter names of the entity models in the entity model class are cited as the parameter names of the entities in the entity class; referencing the relationship names among the entity models in the entity model class as the relationship names among the entities in the entity class; and obtaining a parameter class corresponding to the parameter name, and converting the parameter value into a format of the parameter type according to the parameter type and the parameter value in the parameter class to serve as the parameter value of the entity in the entity class. Optionally, if the direct entity and the indirect entity are distinguished in the process of loading the entity model class, the entity model class for a certain entity may obtain the entity class as follows:
ClassEntityExtendsCerData {// mockup class Model inherits from parent CerData
UUIDType type;// type of direct entity
Param primary Key;// principal parameters of direct entity
List < Param > params;// parameter List of direct entities
List < Relation > relationships;// relationship List of direct entities and indirect entities
ClassParam {// parameter class
ObjectparamValue;// parameter value
Param(ObjectparamValue){
Objecttype=this. ParamTYpe ();// parameter type
Converting parameter values and assigning values according to parameter types
if (typeinstanceofInteger) {// for parameter type as integer, performing parameter conversion
this.paramValue=(Integer)paramValue;}}}
In the embodiment, the basic entity units in the authentication data are loaded through entity model classes, but specific parameter values are not loaded, so that loading time and loading resources are saved; and then analyzing specific parameter values corresponding to the entity model class by taking the parameter class and the relation class as media, and packaging the specific parameter values into entity class with uniform structure, thereby realizing extraction and standardization processing of data information and providing a basis for construction of a knowledge graph.
In the second case, the authentication data is structured data, such as data represented in a certain format, e.g., a table, a database, etc. The data can directly read information of entities, parameters, relations and the like, and the steps of building a relation model, loading entity model classes and the like in the case are not needed to be executed, so that the extracted information of the entities, the parameters and the relation is directly packaged into entity classes consistent with the structure in the case.
S130, constructing an authentication knowledge graph according to the entity classes.
After the entity class is packaged, unified processing is carried out on the authentication data, and an authentication knowledge graph is constructed. Optionally, firstly, cleaning dirty data existing in entity classes, and checking errors in the actual sense of partial data entity parameters (such as that the speed cannot be negative or obviously exceeds a normal range); if the abnormal data still exist after automatic cleaning and checking, the processing is changed into manual processing.
And then, carrying out preliminary integration on the mass data after cleaning, constructing one or more small knowledge graph subgraphs on the authentication data acquired in the current flow, and fusing the subgraphs with the overall graph to improve the overall construction efficiency of the authentication data knowledge graph. Particularly, in the case that the authentication knowledge graph to be constructed takes a vehicle type as a query unit (for example, a user can query related knowledge of any vehicle type after acquiring the authentication knowledge graph, perform activities such as bidding analysis, etc.), the vehicle type can be determined as a key entity for sub-graph construction, and entity names related to each entity class are identified, including names of direct entities and names of relationship name intermediate entities; determining whether each entity class is associated with the same vehicle type according to the entity name; and merging the entity classes associated with the same vehicle model to obtain an authentication knowledge graph sub-graph of the vehicle model. The method can not only finish the information fusion of a single query unit preferentially and provide more complete information for the query of the user, but also improve the construction efficiency of the overall map.
The reason why the efficiency can be improved by combining the subgraph with the whole atlas after constructing the subgraph is described below. In the process of graph merging, node traversal is needed for sub-graphs or whole graphs to be merged, in this embodiment, neo4j graph database is adopted, indexes are built for each entity stored in neo4j according to main parameters, the bottom implementation is to quickly query nodes by maintaining a B+ tree with main parameters, and assuming that the number of nodes in the B+ tree is n, the time complexity of the B+ tree query nodes is logn (in the prior art). With reference to FIG. 3, assume a graph G 1 、G 2 The number of nodes of (a) is m respectively 1 、m 2 In G 2 As the current map, G was taken as 1 Node incorporation G in 2 With a temporal complexity of m 1 ×logm 2 . For a larger scale of the mapAssume, for example, subgraph G 1 、G 2 And G 3 The number of nodes of (a) is m respectively 1 、m 2 And m 3 Existing whole knowledge graph G all Is N and m 1 ,m 2 ,m 3 Much smaller than N, G will be 1 、G 2 And G 3 The time complexity of combining with the integral atlas in turn isAnd G is firstly taken 1 、G 2 And G 3 Combining with the overall profile with a temporal complexity of +.>Is far smaller than the former combination mode, thereby improving the construction efficiency of the whole map.
Based on the analysis, in the process of merging the entity classes associated with the same vehicle model, the entity class with the largest relation name number can be selected as the current subgraph; selecting the entity class with the largest relation name number from the rest entity classes, and merging the entity classes into the current subgraph to obtain a new current subgraph; continuing to select the entity class with the largest relation name number from the rest entity classes and integrating the entity class into the new current subgraph; and repeating the steps until all entity classes are selected, and obtaining a final authentication knowledge graph subgraph of the vehicle type. Wherein the number of relationship names represents the number of nodes (i.e. the number of entities) corresponding to the entity class, still in G 1 、G 2 And G 3 Three entity classes are taken as an example, and the number of nodes is m 1 >m 2 >m 3 Sequentially combining the nodes according to the sequence from the large number to the small number, wherein the time complexity is approximately equal toThe method is the mode with highest efficiency in various merging sequences, and the speed of constructing the map is further improved.
Further, in the process of merging the sub-graph (called a first sub-graph) of a certain vehicle type with the whole graph, a second sub-graph related to the first sub-graph node can be obtained from the existing knowledge graph, the first sub-graph and the second sub-graph are used as new knowledge as input, knowledge calculation including data fusion, relationship reasoning and the like is performed, so that a new knowledge graph with updated and merged differences is constructed, and then the new knowledge graph is merged with the existing knowledge graph, thereby realizing construction, updating or expansion of the knowledge graph and generating a more complete authentication knowledge graph of the certain vehicle type. Fig. 4 shows a schematic diagram of an authentication knowledge graph in the automotive field, which includes two authentication sources: product admission and recommendation catalogs. Product inclusion includes two claims batches 366 and 368. A new product is included in batch 366, the model version of the new product is ZSX097, the chassis version is 3660594, and the engine version is TZ365XS; TX365XS is a brand A branded product version, ZSX097 and 3660594 are both B brand branded product versions, brand A is a brand owned by Enterprise A, and brand B is a brand owned by Enterprise B. The batch 368 includes a change expansion, and the object of the change expansion is ZSX097. Batch 12 is included under the recommended directory, which contains a new product release with a version of ZSX097.
The embodiment provides a method which can be realized through simple deployment, can realize custom modeling, is automatic, and can quickly and efficiently construct a knowledge graph in the automobile authentication field, determines entity types, entity model types and relationship names applicable to the automobile authentication field according to the internal logic of related data in the automobile authentication field, realizes unified packaging processing of data of different authentication sources, and can automatically realize construction, updating and expansion of the knowledge graph by business personnel through simple relationship modeling and deployment.
Specifically, for unstructured or semi-structured authentication data, entity model classes in the authentication data are automatically loaded according to the constructed relation model, entity parameters and entity relations are analyzed, and the entity model classes are packaged into entity classes with uniform structures. In order to improve loading and analysis efficiency, the embodiment constructs four specific data structures under the same parent class, and rapidly realizes information extraction and supports information fusion of different data sources through mutual reference and parameter sharing among the data structures. In addition, in the spectrogram fusion process, key entities and specific methods for sub-graph construction are determined according to the query unit of the spectrogram, so that the information under the query unit can be ensured to be fast perfected, and the efficiency of the spectrogram construction can be improved.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 5, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device may be one or more, one processor 60 being taken as an example in fig. 5; the processor 60, the memory 61, the input means 62 and the output means 63 in the device may be connected by a bus or other means, in fig. 5 by way of example.
The memory 61 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to the automated knowledge graph construction method in the automotive authentication field in the embodiment of the present application. The processor 60 executes various functional applications of the device and data processing by running software programs, instructions and modules stored in the memory 61, i.e., implements the above-described automated knowledge graph construction method in the automotive authentication field.
The memory 61 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 61 may further comprise memory remotely located relative to processor 60, which may be connected to the device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 62 may be used to receive entered numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output 63 may comprise a display device such as a display screen.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the automated knowledge graph construction method of the automobile authentication field of any embodiment.
The computer storage media of embodiments of the application may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the C-programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present application.
Claims (7)
1. An automated knowledge graph construction method in the field of automobile authentication is characterized by comprising the following steps:
acquiring automobile authentication data of different authentication sources at fixed time;
according to the structural characteristics of the authentication data, the automobile authentication data from different authentication sources are packaged into a plurality of entity classes with uniform structures; specifically, if the authentication data of any authentication source is semi-structured data or unstructured data, constructing a relation model of the authentication data; loading at least one entity model class in the authentication data according to the relation model, and packaging the data content in each entity model class into each entity class with uniform structure;
constructing an authentication knowledge graph according to the entity classes;
wherein the constructing the relationship model of the authentication data includes: acquiring at least one entity in the authentication data; replacing each entity with each entity model with the same type; determining a relationship name among the entity models, wherein the relationship name comprises the following components: the relationship comprises a relationship, a belonging relationship, an possession relationship, a flag relationship, a loading relationship and a loaded relationship; constructing a relationship model of the authentication data according to the relationship names among the entity models;
the entity model class includes: the type of the entity model and the relationship name among the entity models; the loading at least one entity model class in the authentication data according to the relation model comprises the following steps: acquiring at least one entity in the authentication data; distinguishing a direct entity and at least one indirect entity according to the subject of the authentication data and the parameter detail degree of each entity; constructing a entity model class, and referring to the type of the direct entity as the type of the entity model in the entity model class; determining the relationship names between the direct entity and each indirect entity according to the relationship model, and taking the relationship names as the relationship names between entity models in the entity model class;
the packaging the data content in each entity model class into each entity class with uniform structure comprises the following steps: constructing an entity class under the parent class aiming at any loaded entity model class; referencing the type of the entity model in the entity model class as the entity type in the entity class; the parameter names of the entity models in the entity model class are cited as the parameter names of the entities in the entity class; referencing the relationship names among the entity models in the entity model class as the relationship names among the entities in the entity class; acquiring a parameter class corresponding to the parameter name of the entity, and converting the parameter value into a format of the parameter type according to the parameter type and the parameter value in the parameter class to serve as a parameter value of the entity in the entity class;
the authentication knowledge graph to be constructed takes a vehicle type as a query unit; the step of constructing an authentication knowledge graph according to the entity classes includes: identifying entity names involved in each entity class; determining whether each entity class is associated with the same vehicle type according to the identified entity name; merging entity classes associated with the same vehicle model to obtain an authentication knowledge graph sub-graph of the vehicle model; and merging the subgraphs of different vehicle types with the original authentication knowledge graph to obtain a final authentication knowledge graph.
2. The method of claim 1, wherein the authentication source comprises at least one of: product admittance, recommended catalogs, vehicle and ship tax, oil consumption, environmental protection and purchase tax.
3. The method of claim 1, wherein the entity and the type of entity model comprise at least one of: vehicle model, in-vehicle parts, enterprise, product brand.
4. The method of claim 1, further comprising, prior to said loading at least one mockup class in said authentication data according to said relational model:
declaring a parent class;
declaring a parameter class under the parent class, the parameter class including a parameter name, a parameter type, and a parameter value;
declaring a entity model class under the parent class, wherein the entity model class comprises the types and parameter names of entity models and the relationship names among the entity models; the parameter names of the entity models refer to the parameter names in the parameter classes;
and declaring an entity class under the parent class, wherein the entity class comprises an entity type, a parameter name and a parameter value of an entity and a relation name among the entities, and the parameter name of the entity refers to the parameter name in the parameter class.
5. The method of claim 1, wherein the merging the entity classes associated with the same vehicle model to obtain the authentication knowledge graph subgraph of the vehicle model comprises:
selecting the entity class with the largest relation name number from all entity classes associated with any vehicle type as a current subgraph;
selecting the entity class with the largest relation name number from the rest entity classes, and merging the entity classes into the current subgraph to obtain a new current subgraph;
and continuing to select the entity class with the largest relation name number in the rest entity classes, merging the entity classes into the new current subgraph, and repeating the steps until all the entity classes are selected, so as to obtain the final authentication knowledge graph subgraph of the vehicle type.
6. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the automated knowledge graph construction method for an automotive authentication field of any one of claims 1 to 5.
7. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the automated knowledge-graph construction method of the automotive authentication field of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310660801.XA CN116431835B (en) | 2023-06-06 | 2023-06-06 | Automatic knowledge graph construction method, equipment and medium in automobile authentication field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310660801.XA CN116431835B (en) | 2023-06-06 | 2023-06-06 | Automatic knowledge graph construction method, equipment and medium in automobile authentication field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116431835A CN116431835A (en) | 2023-07-14 |
| CN116431835B true CN116431835B (en) | 2023-09-15 |
Family
ID=87085792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310660801.XA Active CN116431835B (en) | 2023-06-06 | 2023-06-06 | Automatic knowledge graph construction method, equipment and medium in automobile authentication field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116431835B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN110889014A (en) * | 2019-10-21 | 2020-03-17 | 浙江工业大学 | D 3-based method for displaying enterprise association relationship map |
| CN111930856A (en) * | 2020-07-06 | 2020-11-13 | 北京邮电大学 | Method, device and system for constructing domain knowledge graph ontology and data |
| CN112528036A (en) * | 2020-11-30 | 2021-03-19 | 大连理工大学 | Knowledge graph automatic construction method for evidence correlation analysis |
| CN112699682A (en) * | 2020-12-11 | 2021-04-23 | 山东大学 | Named entity identification method and device based on combinable weak authenticator |
| CN113609233A (en) * | 2021-02-02 | 2021-11-05 | 腾讯科技（深圳）有限公司 | Entity object coding method and device, electronic equipment and storage medium |
| CN114065177A (en) * | 2021-10-20 | 2022-02-18 | 北京淇瑀信息科技有限公司 | User equipment authentication method and device based on knowledge graph and electronic equipment |
| CN114398495A (en) * | 2021-12-31 | 2022-04-26 | 第四范式（北京）技术有限公司 | Method and device for constructing knowledge graph based on multiple rounds of questions and answers and readable storage medium |
| CN114757556A (en) * | 2022-04-26 | 2022-07-15 | 中汽研华诚认证(天津)有限公司 | Automobile industry information security system credibility assessment method and assessment system |
| CN114840983A (en) * | 2022-04-18 | 2022-08-02 | 中汽数据(天津)有限公司 | Power storage battery SOH calculation model construction method and calculation method |
| CN115168620A (en) * | 2022-09-09 | 2022-10-11 | 之江实验室 | Self-supervision joint learning method oriented to knowledge graph entity alignment |
| CN115186136A (en) * | 2022-05-07 | 2022-10-14 | 国家计算机网络与信息安全管理中心 | Knowledge graph structure for network attack and defense confrontation |
| CN115941359A (en) * | 2023-02-06 | 2023-04-07 | 中汽研软件测评(天津)有限公司 | Test case generation method, system and equipment for automobile network security detection |
| CN116010612A (en) * | 2022-12-09 | 2023-04-25 | 中水珠江规划勘测设计有限公司 | River basin flood control knowledge graph construction method and device and electronic equipment |
-
2023
- 2023-06-06 CN CN202310660801.XA patent/CN116431835B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN110889014A (en) * | 2019-10-21 | 2020-03-17 | 浙江工业大学 | D 3-based method for displaying enterprise association relationship map |
| CN111930856A (en) * | 2020-07-06 | 2020-11-13 | 北京邮电大学 | Method, device and system for constructing domain knowledge graph ontology and data |
| CN112528036A (en) * | 2020-11-30 | 2021-03-19 | 大连理工大学 | Knowledge graph automatic construction method for evidence correlation analysis |
| CN112699682A (en) * | 2020-12-11 | 2021-04-23 | 山东大学 | Named entity identification method and device based on combinable weak authenticator |
| CN113609233A (en) * | 2021-02-02 | 2021-11-05 | 腾讯科技（深圳）有限公司 | Entity object coding method and device, electronic equipment and storage medium |
| CN114065177A (en) * | 2021-10-20 | 2022-02-18 | 北京淇瑀信息科技有限公司 | User equipment authentication method and device based on knowledge graph and electronic equipment |
| CN114398495A (en) * | 2021-12-31 | 2022-04-26 | 第四范式（北京）技术有限公司 | Method and device for constructing knowledge graph based on multiple rounds of questions and answers and readable storage medium |
| CN114840983A (en) * | 2022-04-18 | 2022-08-02 | 中汽数据(天津)有限公司 | Power storage battery SOH calculation model construction method and calculation method |
| CN114757556A (en) * | 2022-04-26 | 2022-07-15 | 中汽研华诚认证(天津)有限公司 | Automobile industry information security system credibility assessment method and assessment system |
| CN115186136A (en) * | 2022-05-07 | 2022-10-14 | 国家计算机网络与信息安全管理中心 | Knowledge graph structure for network attack and defense confrontation |
| CN115168620A (en) * | 2022-09-09 | 2022-10-11 | 之江实验室 | Self-supervision joint learning method oriented to knowledge graph entity alignment |
| CN116010612A (en) * | 2022-12-09 | 2023-04-25 | 中水珠江规划勘测设计有限公司 | River basin flood control knowledge graph construction method and device and electronic equipment |
| CN115941359A (en) * | 2023-02-06 | 2023-04-07 | 中汽研软件测评(天津)有限公司 | Test case generation method, system and equipment for automobile network security detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116431835A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8607190B2 (en) | Automation of software application engineering using machine learning and reasoning | |
| CN110032575A (en) | Data query method, apparatus, equipment and storage medium | |
| US10453165B1 (en) | Computer vision machine learning model execution service | |
| US20120054301A1 (en) | Methods and systems for providing a virtual network process context for network participant processes in a networked business process | |
| JP6546653B2 (en) | Method and apparatus for creating mapping rule | |
| CN110866029B (en) | sql statement construction method, device, server and readable storage medium | |
| US9240965B2 (en) | Methods and systems for business interaction monitoring for networked business process | |
| CN113238740B (en) | Code generation method, code generation device, storage medium and electronic device | |
| CN112906206B (en) | Digital twin model construction method and device | |
| CN111858957B (en) | Automatic knowledge graph construction method and system | |
| RU2632414C2 (en) | Method of hierarchical data structure forming, method of data search using hierarchical data structure, server and permanent machine-readable media | |
| CN108228229A (en) | The management method and system that a kind of Maven is relied on | |
| CN109582670B (en) | Recommendation method of vehicle maintenance scheme and related equipment | |
| CN110019207B (en) | Data processing method and device and script display method and device | |
| CN113836454A (en) | Content display page display method, device, medium and equipment | |
| US10303808B2 (en) | Product configuration | |
| CN116431835B (en) | Automatic knowledge graph construction method, equipment and medium in automobile authentication field | |
| CN116244301A (en) | Space-time process mechanism model service chain arrangement method based on directed acyclic graph | |
| CN113791766A (en) | Method for combining data interfaces, electronic device and readable storage medium | |
| CN109117152B (en) | Service generation system and method | |
| CN111126961A (en) | Complex product full life cycle digital mainline service system | |
| CN114519050A (en) | Vehicle part configuration logic constraint relation generation method, device, equipment and medium | |
| CN116595057B (en) | Data query method, device, computer equipment and computer program product | |
| CN116541377B (en) | Processing method and system of materialized view of task and electronic equipment | |
| CN114357054B (en) | Method and device for processing unstructured data based on ClickHouse |
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 |