An architecture construction method and device of an autonomous transportation system and a storage medium

Abstract

The application discloses a kind of autonomous traffic system's architecture construction method, device and storage medium, method includes: obtaining the knowledge graph database of autonomous traffic system;According to the knowledge graph database, the definition of demand and the definition of the entity set corresponding to the demand are determined, and a demand-entity set contrast database is obtained;According to the scene definition document of user, extract scene architecture adaptive design requirement, obtain demand set;Query corresponding target entity set from the demand-entity set contrast database;According to the query result of the target entity set, integrate entity set, and obtain the system architecture diagram of specific scene;According to the system architecture diagram, output the knowledge graph of system architecture.The application reduces the computational complexity, improves accuracy, and can be widely applied in information analysis and processing technical field.

Description

Technical Field

[0001] This invention relates to the field of information analysis and processing technology, and in particular to a method, apparatus and storage medium for constructing the architecture of an autonomous transportation system. Background Technology

[0002] With rapid socio-economic development, transportation demands are increasing. On the one hand, users expect proactive services; on the other hand, decision-makers desire autonomous systems. However, the increasing volume of information, the proliferation of systems, and the rapid pace of iteration are constantly raising the complexity of transportation systems, making human-led systems insufficient to meet these demands. Simultaneously, advancements in communication and control technologies are creating new opportunities for the autonomy of road traffic elements. This will drive certain areas of Intelligent Transportation Systems (ITS) towards autonomy, progressing along the path of "assisted autonomy – highly autonomous – fully autonomous." Therefore, building Autonomous Transportation Systems (ATS) capable of supporting self-organization across multiple generations of system architectures has become a development trend.

[0003] Autonomous transportation systems require an architecture that can adaptively construct relevant elements from a knowledge base based on the specific needs of different generations and scenarios. To address this, graph-structured knowledge graphs are well-suited for handling the complex relationships between various elements in autonomous transportation systems. Furthermore, semantic networks are intuitive and easily understood by both humans and computers. However, existing research largely relies on node similarity calculations and knowledge graph representation learning to construct knowledge graphs for reasoning scenarios. These methods suffer from drawbacks such as low accuracy, high computational complexity, and weak interpretability. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus and storage medium for constructing the architecture of an autonomous transportation system with low complexity and high accuracy.

[0005] One aspect of the present invention provides a method for constructing the architecture of an autonomous transportation system, comprising:

[0006] Obtain a knowledge graph database of autonomous transportation systems;

[0007] Based on the knowledge graph database, the definition of the requirement and the definition of the entity set corresponding to the requirement are determined, and a requirement-entity set mapping database is obtained.

[0008] Based on the user's scenario definition document, extract the scenario architecture adaptive design requirements to obtain a set of requirements;

[0009] Query the corresponding target entity set from the demand-entity set mapping database;

[0010] Based on the query results of the target entity set, the entity set is integrated to obtain a system architecture diagram for a specific scenario;

[0011] Based on the system architecture diagram, output the knowledge graph of the system architecture.

[0012] Optionally, the method further includes:

[0013] An adaptive design interface for displaying the architecture of an autonomous transportation system is provided, which includes a scenario definition area and an analysis and display area.

[0014] The scenario definition area is used to receive scenario definition documents, which include the generation base of the scenario and the scenario requirements defined in natural language.

[0015] Based on the input scenario definition document, the system architecture corresponding to the scenario definition document is determined and graphically displayed in the analysis and display area.

[0016] Optionally, the step of determining the definition of a requirement and the definition of the entity set corresponding to the requirement based on the knowledge graph database to obtain a requirement-entity set mapping database includes:

[0017] The system knowledge graph under each generation of the autonomous transportation system can be analyzed to meet the requirements, and corresponding entity sets are defined according to the requirements. The entity sets are knowledge graph subgraphs constructed using knowledge from the autonomous transportation system knowledge graph database, and the knowledge graph subgraphs are used to meet the corresponding requirements. The requirements and the entity sets have a one-to-one or many-to-one relationship.

[0018] All defined entity sets are divided according to their base and stored in the requirement-entity set mapping database.

[0019] Optionally, the step of extracting adaptive design requirements for the scenario architecture based on the user's scenario definition document to obtain a set of requirements includes:

[0020] Construct a requirement thesaurus based on the requirement-entity set reference database;

[0021] The requirement keywords are extracted by judging the degree of matching between the text in the scenario definition document and each word in the requirement terminology.

[0022] Store the aforementioned demand keywords into a demand set;

[0023] The scene definition document is described in a natural language, and the scene definition document includes a generation basis where the scene is located, requirement information contained in the scene, and application range information of the scene.

[0024] The extraction scene architecture adaptive design requirement includes a generation basis where the extraction scene is located and a requirement set contained in the scene.

[0025] Optionally, the corresponding target entity set is queried from the requirement-entity set correspondence database, including:

[0026] For each entity set, a node set, a relation triple set and an attribute triple set contained in the entity set are extracted as a knowledge base of the entity set, and the knowledge base is stored into an entity set knowledge base set.

[0027] Optionally, the target entity set is integrated according to the query result of the target entity set, and a system architecture diagram of a specific scene is obtained.

[0028] The entity sets with correlations are processed.

[0029] The processed entity sets are output in the form of a knowledge graph, and a system architecture diagram of the specific scene under the target generation basis is obtained.

[0030] The entity sets with correlations include entity sets that can be associated through granularity relations or entity sets that can be associated through extended entity sets.

[0031] Optionally, the knowledge graph of the system architecture is output according to the system architecture diagram, including:

[0032] The system architecture diagram of the specific scene under the target generation basis is received through gRPC, so that the architecture knowledge graph is output in the form of a document.

[0033] Alternatively, the output architecture knowledge graph is visualized and analyzed through a webVOWL program on a web side, so that the architecture knowledge graph is output in a web-side visualized form.

[0034] Another aspect of the embodiment of the application further provides an architecture construction device of an autonomous transportation system, including:

[0035] A first module is configured to acquire a knowledge graph database of the autonomous transportation system.

[0036] A second module is configured to determine definitions of requirements and definitions of entity sets corresponding to the requirements according to the knowledge graph database, and obtain a requirement-entity set correspondence database.

[0037] A third module is configured to extract scene architecture adaptive design requirements according to a scene definition document of a user, and obtain a requirement set.

[0038] a fourth module configured to query a corresponding target entity set from the demand-entity set correspondence database;

[0039] a fifth module configured to integrate entity sets according to the query result of the target entity set, and obtain a system architecture diagram of a specific scenario;

[0040] a sixth module configured to output a knowledge graph of the system architecture according to the system architecture diagram.

[0041] Another aspect of the embodiment of the present application further provides an electronic device, comprising a processor and a memory.

[0042] The memory is configured to store a program.

[0043] The processor executes the program to realize the method as described above.

[0044] Another aspect of the embodiment of the present application further provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the method as described above.

[0045] The embodiment of the present application further discloses a computer program product or a computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method as described above.

[0046] The embodiment of the present application obtains a knowledge graph database of an autonomous transportation system; according to the knowledge graph database, the definition of a demand and the definition of an entity set corresponding to the demand are determined, and a demand-entity set correspondence database is obtained; according to a scenario definition document of a user, a scenario architecture adaptive design requirement is extracted, and a demand set is obtained; a corresponding target entity set is queried from the demand-entity set correspondence database; entity sets are integrated according to the query result of the target entity set, and a system architecture diagram of a specific scenario is obtained; and according to the system architecture diagram, a knowledge graph of the system architecture is output. The present application reduces the computational complexity and improves the accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0048] Figure 1A flowchart of an adaptive construction method of an autonomous traffic system architecture provided by an embodiment of the present application is shown in FIG. 1.

[0049] Figure 2 A technical schematic diagram of an adaptive construction method of an autonomous traffic system architecture provided by an embodiment of the present application is shown in FIG. 2.

[0050] Figure 3 A flowchart of an entity set fusion provided by an embodiment of the present application is shown in FIG. 3.

[0051] Figure 4 A driving automation knowledge graph under an L3 generation basis is shown in FIG. 4.

[0052] Figure 5 An entity set satisfying the requirement of performing a monitoring under an L3 generation basis is shown in FIG. 5.

[0053] Figure 6 An entity set satisfying the requirement of performing a dynamic driving task under an L3 generation basis is shown in FIG. 6.

[0054] Figure 7 A system architecture diagram output according to a scene requirement is shown in FIG. 7. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0056] In view of the problems in the prior art, an adaptive construction method, device and storage medium of an autonomous traffic system architecture are provided by an embodiment of the present application, which can design a scene architecture satisfying a specific scene requirement under different generation bases completely and effectively according to an autonomous traffic system knowledge graph database.

[0057] An aspect of the present application provides an adaptive construction method of an autonomous traffic system architecture, comprising:

[0058] acquiring a knowledge graph database of an autonomous traffic system;

[0059] determining a definition of a requirement and a definition of an entity set corresponding to the requirement according to the knowledge graph database, to obtain a requirement-entity set correspondence database;

[0060] extracting scene architecture adaptive design requirements according to a scene definition document of a user, to obtain a requirement set;

[0061] querying a corresponding target entity set from the requirement-entity set correspondence database;

[0062] integrating the entity sets according to the query result of the target entity set, to obtain a system architecture diagram of a specific scene.

[0063] According to the system architecture diagram, a knowledge graph of the output system architecture is output.

[0064] Optionally, the method further comprises:

[0065] An adaptive design interface of the autonomous transportation system architecture is displayed, and the adaptive design interface comprises a scenario definition area and an analysis display area.

[0066] The scenario definition area is configured to receive a scenario definition document, and the scenario definition document comprises a generation base in which a scenario is located and a scenario requirement defined in a natural language.

[0067] According to the input scenario definition document, a system architecture corresponding to the scenario definition document is determined, and a graphical display is performed in the analysis display area.

[0068] Optionally, the determination of the definition of a requirement and the definition of an entity set corresponding to the requirement according to the knowledge graph database comprises:

[0069] The system knowledge graph under each generation base of the autonomous transportation system is analyzed to determine a requirement that can be met by the system knowledge graph, and a corresponding entity set is defined according to the requirement; the entity set is a knowledge graph subgraph constructed by using knowledge in the autonomous transportation system knowledge graph database, and the knowledge graph subgraph is used to meet the corresponding requirement; the requirement and the entity set are in a one-to-one or many-to-one relationship.

[0070] All defined entity sets are divided according to generation bases and stored in a requirement-entity set correspondence database.

[0071] Optionally, the extraction of the scenario architecture adaptive design requirement according to the scenario definition document of the user comprises:

[0072] A requirement word table is constructed according to the requirement-entity set correspondence database.

[0073] A requirement keyword is extracted by judging a matching degree of a word in the scenario definition document and each word in the requirement word table.

[0074] The requirement keyword is stored in a requirement set.

[0075] The scenario definition document is described in a natural language, and the scenario definition document comprises a generation base in which a scenario is located, requirement information contained in the scenario, and scenario application range information.

[0076] The extraction of the scenario architecture adaptive design requirement comprises the extraction of a generation base in which a scenario is located and a requirement set contained in the scenario.

[0077] Optionally, the querying the corresponding target entity set from the demand-entity set correspondence database comprises:

[0078] For each entity set, the node set, the relation triple set and the attribute triple set contained in the entity set are extracted as the knowledge base of the entity set, and the knowledge base is stored into the entity set knowledge base set.

[0079] Optionally, the integrating the entity set according to the query result of the target entity set comprises:

[0080] processing the entity sets with correlations;

[0081] The processed entity sets are output in the form of a knowledge graph to obtain a system architecture diagram of a specific scenario under a target paradigm;

[0082] The entity sets with correlations include entity sets that can be associated through granularity relations or entity sets that can be associated through extended entity sets.

[0083] Optionally, the outputting the knowledge graph of the system architecture according to the system architecture diagram comprises:

[0084] The system architecture diagram file of a specific scenario under a target paradigm is received through gRPC, so that the architecture knowledge graph is output in the form of a document;

[0085] Alternatively, the output architecture knowledge graph is visualized and analyzed through a webVOWL program on a web side, so that the architecture knowledge graph is output in the form of web-side visualization.

[0086] Another aspect of the embodiment of the application further provides an architecture construction device of an autonomous transportation system, comprising:

[0087] A first module is configured to acquire a knowledge graph database of the autonomous transportation system.

[0088] A second module is configured to determine the definition of a demand and the definition of an entity set corresponding to the demand according to the knowledge graph database, to obtain a demand-entity set correspondence database.

[0089] A third module is configured to extract a scene architecture adaptive design requirement according to a scene definition document of a user, to obtain a demand set.

[0090] A fourth module is configured to query a corresponding target entity set from the demand-entity set correspondence database.

[0091] A fifth module is configured to integrate the entity set according to the query result of the target entity set, to obtain a system architecture diagram of a specific scenario.

[0092] A sixth module is configured to output a knowledge graph of the system architecture according to the system architecture diagram.

[0093] Another aspect of the embodiments of the present application further provides an electronic device, including a processor and a memory.

[0094] The memory is configured to store a program.

[0095] The processor executes the program to implement the method as described above.

[0096] Another aspect of the embodiments of the present application further provides a computer readable storage medium, which stores a program, and the program is executed by a processor to implement the method as described above.

[0097] The embodiments of the present application further disclose a computer program product or a computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the method as described above.

[0098] The specific implementation principles of the present application are described in detail as follows:

[0099] The embodiments of the present application provide a method for adaptive design of an autonomous transportation system architecture, which can design a complete, accurate and highly interpretable scenario architecture knowledge graph according to the requirements of a specific scenario under different generations, and includes the following steps:

[0100] Step 1: Construct and store an autonomous transportation system knowledge graph database.

[0101] Step 2: Define and store an entity set according to the knowledge model constructed in step 1. The entity set is a knowledge graph subgraph constructed by using the knowledge in the autonomous transportation system knowledge graph database, and the subgraph can meet specific requirements. All defined entity sets are stored in a requirement-entity set comparison database.

[0102] Step 3: Extract the generation information of the scenario and the requirement set contained in the scenario according to the scenario definition document submitted by the user.

[0103] Step 4: Query the corresponding entity set according to the requirement set extracted in step 3.

[0104] Step 5: Integrate the entity set according to the query result of step 4. Obtain the system architecture diagram of the specific scenario under the target generation.

[0105] Step 6: The architecture knowledge graph obtained in step 5 is output in the form of a document or a Web visual form, and is called by a computer program or analyzed by an autonomous traffic system manager according to different utilization scenarios.

[0106] In step 1, the autonomous traffic system knowledge graph database data is graph structure data represented in the form of triples, including a set of information related to each entity and entity attribute required to express a specific thing, and each piece of knowledge can be represented by a triple;

[0107] The node represents an entity in the autonomous traffic system, such as a function, a technology, a service, a component, and the like.

[0108] The node contains attributes, which represent the description of the entity, the parameter type contained in the entity, and the parameter value, and the attributes of the node can be represented by a triple in the form of (node, attribute name, attribute value).

[0109] The association between nodes is defined by the relationship, such as the hierarchical relationship of entities at the granularity and the flow relationship of information flow between entities, and the relationship between nodes can be represented by a triple in the form of (node 1, relationship name, node 2).

[0110] There is evolution between each generation of the autonomous traffic system, so the knowledge graph data of the autonomous traffic system in each generation needs to be stored in the database.

[0111] According to the order of each generation of the autonomous traffic system, the knowledge graph data of each generation of the autonomous traffic system is stored in the graph database according to the generation, and the autonomous traffic system knowledge graph database is obtained.

[0112] In step 2, the professional personnel analyzes the requirements that can be met by the system knowledge graph of each generation of the autonomous traffic system through visualization technology, and defines the corresponding entity set according to the requirements. The entity set is a knowledge graph subgraph constructed by using the knowledge in the autonomous traffic system knowledge graph database, and the subgraph can meet the corresponding requirements.

[0113] The knowledge in the entity set comes from the autonomous traffic system knowledge graph database.

[0114] The requirements and the entity set have a one-to-one relationship.

[0115] All defined entity sets are stored in the requirement-entity set correspondence database according to the generation.

[0116] In step 3, the scene definition document is described in natural language, including the generation in which the scene is located, various requirements contained in the scene, and the scope of application of the scene, and the like.

[0117] The extraction scenario architecture adaptive design requirements include: the generation in which the scenario is located, and the requirement set contained in the scenario. The scheme uses natural language processing (NLP) technology to identify the requirement set contained in the definition document of the scenario;

[0118] The step of identifying the requirement set contained in the definition document of the scenario using natural language processing technology includes: constructing a rich and perfect word table according to the requirement set defined in step 2, and then extracting keywords by judging the matching degree of the text in the definition document of the scenario with each word in the word table.

[0119] In step 4, the scheme queries the entity set corresponding to each requirement in the target generation from the requirement-entity set correspondence database according to the requirement set extracted in step 3.

[0120] For each entity set, extract the node set, relation triple set and attribute triple set it contains as the knowledge base of the entity set, and store it in the entity set knowledge base set.

[0121] In step 5, the integration of the entity set is completed by integrating the triples in the entity set knowledge base and storing the integrated knowledge base as an architecture knowledge graph. Triples are the skeleton of knowledge, so as long as the triples of the entity set are integrated, the integration of the entity set can be completed.

[0122] Different entity set integration processes may produce isolated subgraphs. The isolated subgraph refers to a subgraph that does not have any association with other entity sets. This method integrates isolated subgraphs based on the granularity classification of entities. The granularity classification is represented by the parent-child node relationship. The parent-child relationship is a kind of relationship, and its triple representation form is (child node, is a subclass of parent node). The parent node is a coarse-grained representation of the child node, and the child node is a fine-grained representation of the parent node.

[0123] The integration of the entity set includes the following steps:

[0124] Step 501: processing entity sets with direct associations, including:

[0125] Determine whether the entity sets can be fused according to whether the node sets in any two entity sets have an intersection. If the fusion can be performed, further fusion of the two entity sets is performed to generate a fused entity set. Wherein, the fusion of the two entity sets according to the intersection of the node sets and the generation of a fused entity set include:

[0126] Assign the node set in the fused entity set knowledge base to the union set of the node sets in the two entity set knowledge bases that are fused;

[0127] The relation set in the fused entity set knowledge base is assigned as the union of the relation sets in the two entity set knowledge bases to be fused;

[0128] The attribute set in the fused entity set knowledge base is assigned as the union of the attribute sets in the two entity set knowledge bases to be fused;

[0129] Step 502: repeat step 501 until any two entity sets cannot be fused by the method described in step 501.

[0130] Step 503: query the number of entity sets at this time, if equal to 1, it means that the entity set has been integrated, go to step 511; otherwise, there is an isolated subgraph, because according to the method described in step 501, if there are any two entity sets that cannot be fused, then these two entity sets do not have direct association, and go to step 504.

[0131] Step 504: process the entity sets that can be fused by hierarchical relationship connection, that is, if two entity sets can be associated by hierarchical relationship, it means that the entity sets have relevance in granularity, including:

[0132] According to whether there is a hierarchical relationship between the node sets in any two entity sets, it is determined whether the entity sets can be fused. If they can be fused, the fusion of the two entity sets is further performed to generate a fused entity set. Wherein, the fusion of the two entity sets according to the hierarchical relationship and the generation of a fused entity set include:

[0133] Query the parent node of the node set in the first entity set knowledge base, if the node set in the second entity set knowledge base contains the parent node of the node set in the first entity set knowledge base, the fusion can be performed;

[0134] Query the parent node of the node set in the second entity set knowledge base, if the node set in the first entity set knowledge base contains the parent node of the node set in the second entity set knowledge base, the fusion can be performed.

[0135] Any one of the above conditions is met, that is, the fusion of the entity sets can be performed. Record these nodes and store them as associated node sets.

[0136] If the fusion can be performed, the two entity sets are fused. Wherein, the fusion of the two entity sets includes:

[0137] The node set in the fused entity set knowledge base is assigned as the union of the node sets in the two entity set knowledge bases to be fused;

[0138] The relation set in the fused entity set knowledge base is assigned as the union of the relation sets in the two entity set knowledge bases being fused;

[0139] The attribute set in the fused entity set knowledge base is assigned as the union of the attribute sets in the two entity set knowledge bases being fused;

[0140] The hierarchical relation between the two entity sets is added to the relation set in the fused entity set knowledge base;

[0141] Step 505: Repeat step 504 until any two entity sets cannot be fused by the method described in step 504.

[0142] Step 506: Query the number of entity sets. If the value is greater than 1, it means that the integration of isolated subgraphs in step 505 has not been completed, i.e., the entity sets cannot be completely fused by hierarchical relations, and go to step 507. If the value is equal to 1, go to step 510.

[0143] Step 507: Traverse the entity sets. For each entity set, expand its parent node at the previous level of granularity and related hierarchical relations and attributes, including:

[0144] Add the hierarchical relation between the parent node at the previous level of granularity of the first entity set and the nodes in the entity set to the relation set of the entity set;

[0145] Add the parent node at the previous level of granularity of each node in the entity set to the node set of the entity set;

[0146] Add the attributes contained in the parent node to the attribute set of the entity set.

[0147] Step 508: Store the parent node at the previous level described in step 507 as a temporary node set.

[0148] Step 509: Use steps 504-506 to process the above entity sets again.

[0149] Step 510: Delete the redundant expansion information in the entity set generated in step 507. The redundant expansion information refers to the fact that the entity set expanded by step 507 can be associated by the temporary node set, and there may be some nodes in the temporary node set that are not used for association. Therefore, these artificially expanded information needs to be removed. The nodes that can be associated are stored in an associated node set, so step 510 includes:

[0150] Delete the nodes in the temporary node set except for the associated node set and the attributes contained therein;

[0151] Delete the relations corresponding to the nodes in the temporary node set except for the associated node set;

[0152] Step 511: process the final entity set to output in RDF / XML format as the system architecture diagram of the specific scene under the target paradigm, including:

[0153] Using OWLAPI, add all node sets in the entity set to the knowledge graph;

[0154] Using OWLAPI, connect the nodes in the knowledge graph by taking the relationship triplets in the entity set as input;

[0155] Using OWLAPI, add attributes to the nodes in the knowledge graph by taking the attribute triplets in the entity set as input.

[0156] In step 6, the computer can receive the system architecture diagram file of the specific scene under the target paradigm through gRPC for system architecture simulation analysis. Users can also analyze the output architecture knowledge graph by means of the webVOWL program on the web side.

[0157] The specific implementation process of the present application will be described in detail in conjunction with the drawings in the specification:

[0158] Figure 1 The figure is a schematic diagram of the autonomous traffic system architecture adaptive construction method provided by the embodiment of the present application, and the method comprises:

[0159] Obtain the autonomous traffic system knowledge graph database;

[0160] Experts define the requirements and entity sets according to the data in the autonomous traffic system knowledge graph database, and store them in the requirement-entity set correspondence database;

[0161] The user inputs the scene definition document, and the system extracts the scene requirement set according to the user input scene definition document, and extracts the corresponding entity set from the requirement-entity set correspondence database according to the scene requirement set;

[0162] Integrate the entity set to further obtain the system architecture diagram of the specific scene under the target paradigm;

[0163] According to different application scenes, output the system architecture diagram of the specific scene under the target paradigm for system calling or system architecture design personnel analysis.

[0164] Figure 2 The figure is a technical schematic diagram of the autonomous traffic system architecture adaptive construction method provided by the embodiment of the present application, comprising:

[0165] The expert defines the requirement set and the entity set group of each generation base of the autonomous traffic system knowledge graph; and the user selects the corresponding entity set according to the generation base and the requirement of the specific scene, and integrates the entity set to generate the system architecture diagram of the specific scene under the target generation base.

[0166] It is worth noting that for any generation base, as long as the mapping between the requirements and the entity set extracted from the scene definition document is complete, the embodiments of the present scheme can adaptively generate the scene architecture under different generation bases.

[0167] It should be noted that the autonomous traffic system knowledge graph includes a set of information related to each entity and entity attribute required for the normal operation of the autonomous traffic system, which is represented by nodes, relationships and attributes. The set of information is a series of knowledge graph files of different versions that meet the same ontology defined according to the RDF / XML standard; each node represents a knowledge entity and has a unique ID; nodes can be connected by relationships, and relationships can be: "is a subclass (instance)", "contains", "perception", "response", etc. Each node can contain attributes, and attribute relationships can be: "synonyms", "whether the concept is obsolete", "dimension", etc. The autonomous traffic system knowledge graph is a set of knowledge that meets the above definitions.

[0168] To facilitate human-computer interaction with users and obtain the operation logic of the users, a user interface is usually needed. The user interface is a medium for interaction and information exchange between the system and the user, which can realize the conversion between the internal form of the computer and the form acceptable by the human. Visualization is also essential in the process of human-computer interaction through the user interface. Visualization technology is a theory, method or technology that uses computer graphics and image processing technology to convert data into graphics or images displayed on the screen and interact with the user. Visualization technology enables users to directly operate information with a shape in the graphical interface, improving the work efficiency of communication with the computer. In some embodiments, the method further comprises:

[0169] The architecture adaptive design interface includes a scene definition area and an analysis display area. The scene definition area is used to receive a scene definition document, including the generation base of the scene, the natural language defined scene requirements, and optional other information. The scene definition instruction is received.

[0170] In response to the scene definition instruction, the embodiment of the method of the present application is called to obtain the architecture knowledge graph data corresponding to the scene definition document, and the data is displayed in the analysis display area in a preset form.

[0171] The application will be further described in detail below with reference to a specific adaptive design of an autonomous traffic system architecture, combined with the accompanying drawings and specific data. It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0172] Taking the driving automation classification defined by SAE (Society of Automotive Engineer) as an example, the driving automation level increases from L0 to L5. In the definition of the classification, it is implied that with the improvement of the automation level, what kind of technology is used for auxiliary driving and what opportunities are responded to, and then evolved / improved to higher automation level of autonomous driving. The driving automation system has similar characteristics as the autonomous traffic system, including:

[0173] The system evolves between generations and develops in the direction of "auxiliary autonomous-highly autonomous-fully autonomous";

[0174] The system has various entity types, the correlation between entities is complex, and the interaction between entities jointly contributes to a large-scale complex system.

[0175] Therefore, the driving automation knowledge graph can be constructed according to the requirements defined by the autonomous traffic system knowledge graph.

[0176] In the definition of SAE, L3 is called "conditional automation". Compared with L2, the system completes most of the driving operations, at this time, the system replaces humans and monitors the surrounding environment. Only when an emergency occurs, the driver gives appropriate responses as appropriate.

[0177] According to the definition of SAE, the L3 level knowledge graph of driving automation is constructed as shown in Figure 4 It represents the functional knowledge, system state knowledge, user role knowledge of the autonomous driving system and the knowledge of how to interact between the user and the autonomous driving system with nodes, relationships and attributes. Among them, the system function, system state, user role knowledge of the autonomous driving system are all sub-nodes of the L3 level autonomous driving system node, similarly, various functions contained in the autonomous driving system are also all sub-nodes of the system function node. In addition to hierarchical relationships, there are other interaction relationships between nodes, such as with the change of application scenarios, the role of the user in the driver's seat in the autonomous driving system may evolve between "in-vehicle driver" and "dynamic driving task takeover user".

[0178] The relationship between nodes includes SubClassOf, take_over, identify, etc., and the attributes of the nodes are not shown in the graph.

[0179] According to the driving automation L3 level knowledge graph, professionals invite a number of requirements and their corresponding entity sets from the knowledge graph.

[0180] According to the definition of SAE, the following defines a scenario definition document:

[0181] In the L3 level autonomous driving system knowledge graph, when the autonomous driving system runs, the system monitors its running conditions, and executes all dynamic driving tasks under the design running conditions.

[0182] According to Figure 2 The adaptive design method inputs the above scenario definition document, and the natural language processing engine matches two requirements: "monitoring" and "executing dynamic driving tasks". They are respectively used to represent how the autonomous driving system implements the monitoring system running conditions and how the vehicle executes the dynamic driving tasks.

[0183] The entity sets corresponding to the two requirements are shown in Figure 5 , Figure 6 The entity set corresponding to the "monitoring" requirement contains the architecture of the autonomous driving system for runtime monitoring. In this entity set, the system monitoring function continuously monitors the takeover ability of the dynamic driving task, the running state of the current system, whether the autonomous driving system fails, and whether other vehicle systems fail, to serve the rapid response of the system in abnormal operation. The entity set corresponding to the "executing dynamic driving tasks" requirement contains the architecture of the autonomous driving system for executing dynamic driving tasks. In this entity set, the system activates the dynamic driving task processing flow under the design running conditions and continuously executes the dynamic driving tasks, including vehicle lateral and longitudinal control, target and event detection and response, driving decision, and vehicle lighting and signal device control.

[0184] As shown in Figure 3 , the embodiment of the present application performs fusion operation on the above two entity sets. Figure 5 and Figure 6 From the scenario definition document submitted by the user, both entity sets contain semantic relationships, but there is no direct association between the two entity sets, so the program associates according to the hierarchical relationship, finds that in the entity set corresponding to the "executing dynamic driving tasks" requirement, the "system function" node and the "design running condition" node have hierarchical relationships with the "monitoring" node and the "vehicle condition" node in the entity set corresponding to the "monitoring" requirement. Therefore, they can perform fusion operation according to the scheme described in step 504. At the same time, because the number of fused entity sets is 1, the fused entity set can be directly output as the system architecture, and the output scenario architecture is shown in Figure 7The scenario architecture contains the entity set in the two requirements described above, indicating that when the L3 autonomous driving system is running, the system performs all dynamic driving tasks under the design running condition, while also synchronously monitoring the system running condition.

[0185] In summary, the present application firstly acquires an autonomous traffic system knowledge graph database, wherein the autonomous traffic system knowledge graph database includes a set of information related to each entity and entity attribute required to express a specific matter, represented by nodes, relationships and attributes; then, experts in the relevant field are invited to define the requirements and their corresponding entity sets according to the autonomous traffic system knowledge graph database; subsequently, the requirements set in the scenario is extracted using natural language processing technology according to the scenario definition document as the adaptive design requirement of the scenario architecture; then, the entity set corresponding to the requirement set is determined according to the requirement set and the requirement-entity set database; finally, the architecture knowledge graph result is obtained by summarizing the entity set. Based on the autonomous traffic system knowledge graph database and according to the requirement set and its corresponding entity set defined by experts, the present application can output the system architecture diagram of a specific scenario under the target basis according to the user input completely and accurately, and can realize the automatic analysis of the system architecture according to the corresponding method process.

[0186] In some alternative embodiments, the functions / operations mentioned in the block diagram can not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two blocks shown in succession can actually be executed substantially simultaneously with each other or the blocks can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flowcharts of the present application are provided by way of example, with the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are independently executed.

[0187] Furthermore, although the present application is described in the context of functional modules, it is to be understood that one or more of the described functions and / or features can be integrated in a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It will also be appreciated that detailed discussion of the actual implementation of each module is not necessary to an understanding of the application. Rather, the actual implementation of the modules, in combination with their attributes, functions, and internal relationships, are to be understood within the context of the devices disclosed herein. Thus, those skilled in the art with access to patents, scientific journals, and other public sources known by those skilled in the art will be able, using ordinary skill, to practice the application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and that the scope of the present application is to be determined by the entire scope of the claims, along with all equivalents of the claims, and that the claims are to be accorded their broadest interpretation under the patent statutes.

[0188] If the functions are implemented in software, the functions can be stored in or implemented as one or more computer program products, which can be incorporated into a computer-readable medium for use by or in connection with an apparatus, method or system as described herein. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, an article of manufacture or a computer program product. The computer-readable medium can be a non-transitory computer-readable medium. The computer-readable medium can be a computer-readable non-transitory storage medium. The computer-readable medium can be a tangible computer-readable medium. The computer-readable medium can be a computer-readable tangible non-transitory medium.

[0189] Logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be embodied in non-transitory computer-readable media, which can be executed by an instruction execution system, apparatus, or device such as a computer-based system, processor, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a computer- readable storage medium. The computer-readable storage medium can be a tangible computer- readable storage medium.

[0190] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0191] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following techniques can be used to implement the hardware used in the described embodiments: discrete logic circuitry having logic gates for implementing logic functions upon data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and so forth.

[0192] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or more embodiments or examples.

[0193] Although embodiments of the present application have been shown and described, it would be recognized by those of ordinary skill in the art that various changes, modifications, alternatives, and variations can be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.

[0194] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the described embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method of constructing an architecture of an autonomous transportation system, characterized by, The method comprises the following steps: acquiring a knowledge graph database of an autonomous transportation system; determining definitions of demands and definitions of entity sets corresponding to the demands according to the knowledge graph database, and obtaining a demand-entity set correspondence database; the demands are demands met by system knowledge graphs at various generations of the autonomous transportation system; extracting scene architecture adaptive design requirements according to a scene definition document of a user, and obtaining a demand set; querying corresponding target entity sets from the demand-entity set correspondence database; integrating the target entity sets according to the query results of the target entity sets, and obtaining a system architecture graph of a specific scene; the specific scene is a scene of the autonomous transportation system; outputting a knowledge graph of the system architecture according to the system architecture graph. The integration step of the entity sets comprises the following steps: processing entity sets having direct correlations, and repeating the step until any two entity sets are not fused according to the step, and then going to the next step; querying the number of current entity sets, and if the number of current entity sets is equal to one, going to the last step, otherwise processing entity sets fused by hierarchical relationship connection, and repeating the step until any two entity sets are not fused according to the step, and then going to the next step; if two entity sets are correlated by a hierarchical relationship, the two entity sets are entity sets fused by hierarchical relationship connection; querying the number of current entity sets, and if the number of current entity sets is greater than one, expanding parent nodes of a previous layer granularity and related hierarchical relationships and attributes for each entity set, storing the parent nodes of the previous layer granularity as a temporary node set, returning to execute the step of processing entity sets fused by hierarchical relationship connection once, and then going to the next step; if the number of current entity sets is equal to one, going to the next step; deleting redundant expansion information existing in the expanded entity sets; the redundant expansion information is a node in the temporary node set that is not used for correlation; outputting the processed entity sets, and obtaining the system architecture graph.

2. The method of claim 1, wherein, The method further comprises the following steps: displaying an adaptive design interface of the autonomous transportation system architecture, wherein the adaptive design interface comprises a scene definition area and an analysis display area; the scene definition area is used for receiving a scene definition document, and the scene definition document comprises a generation at which a scene is located and a scene demand defined in a natural language; determining a system architecture corresponding to the scene definition document according to the input scene definition document, and graphically displaying the system architecture in the analysis display area.

3. The method of claim 1, wherein, The step of determining definitions of demands and definitions of entity sets corresponding to the demands according to the knowledge graph database, and obtaining a demand-entity set correspondence database, comprises the following steps: analyzing demands met by system knowledge graphs at various generations of the autonomous transportation system, and defining corresponding entity sets according to the demands; the entity sets are knowledge graph subgraphs constructed by using knowledge in the autonomous transportation system knowledge graph database, and the knowledge graph subgraphs are used for meeting corresponding demands; the demands and the entity sets are in a one-to-one or many-to-one relationship; dividing all defined entity sets according to generations, and storing the entity sets in the demand-entity set correspondence database.

4. The method of claim 1, wherein, The method comprises the following steps: According to the requirement-entity set correspondence database, a requirement word table is constructed; By judging the matching degree of the text in the scene definition document and each word in the requirement word table, requirement keywords are extracted; The requirement keywords are stored in the requirement set; The scene definition document is described in natural language, and the scene definition document includes the generation basis of the scene, the requirement information contained in the scene, and the application range information of the scene; The extraction of the scene architecture adaptive design requirements includes the generation basis of the scene and the requirement set contained in the scene.

5. The method of claim 1, wherein, The method comprises the following steps: For each entity set, the node set, the relationship triple set and the attribute triple set contained in the entity set are extracted as the knowledge base of the entity set, and the knowledge base is stored in the entity set knowledge base set.

6. The method of claim 1, wherein, The method comprises the following steps: Through gRPC, a system architecture graph file of a specific scene under a target generation basis is received, so that the architecture knowledge graph is output in the form of a document; Or, through the webVOWL program of the web side, the output architecture knowledge graph is visualized and analyzed, so that the architecture knowledge graph is output in the form of web-side visualization.

7. An architecture building apparatus of an autonomous transportation system, characterized by, The device is applied to the method of any one of claims 1-6, and the device comprises: A first module is configured to acquire a knowledge graph database of an autonomous transportation system; A second module is configured to determine the definition of a requirement and the definition of an entity set corresponding to the requirement according to the knowledge graph database, to obtain a requirement-entity set correspondence database; the requirement is a requirement met by a system knowledge graph under each generation basis of the autonomous transportation system; A third module is configured to extract scene architecture adaptive design requirements according to a scene definition document of a user, to obtain a requirement set; A fourth module is configured to query a target entity set from the requirement-entity set correspondence database; A fifth module is configured to integrate entity sets according to the query result of the target entity set, to obtain a system architecture graph of a specific scene; the specific scene is a scene of the autonomous transportation system; and a sixth module is configured to output a knowledge graph of a system architecture according to the system architecture graph.

8. An electronic device, comprising: The device comprises a processor and a memory; The memory is configured to store a program; The processor executes the program to implement the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a program, and the program is executed by a processor to implement the method of any one of claims 1-6.

Images