CN114547247A

CN114547247A - Architecture construction method and device of autonomous traffic system and storage medium

Info

Publication number: CN114547247A
Application number: CN202210161627.XA
Authority: CN
Inventors: 由林麟; 方明辉; 郝迈; 李宏立; 陈耿祥
Original assignee: Sun Yat Sen University
Current assignee: Sun Yat Sen University
Priority date: 2022-02-22
Filing date: 2022-02-22
Publication date: 2022-05-27

Abstract

The invention discloses a method, a device and a storage medium for constructing an architecture of an autonomous traffic system, wherein the method comprises the following steps: acquiring a knowledge map database of an autonomous traffic system; determining the definition of a demand and the definition of an entity set corresponding to the demand according to the knowledge map database to obtain a demand-entity set contrast database; extracting a scene architecture self-adaptive design requirement according to a scene definition document of a user to obtain a demand set; querying a corresponding target entity set from the requirement-entity set comparison database; integrating the entity sets according to the query result of the target entity set to obtain a system architecture diagram of a specific scene; and outputting a knowledge graph of the system architecture according to the system architecture graph. The invention reduces the calculation complexity, improves the accuracy and can be widely applied to the technical field of information analysis and processing.

Description

Architecture construction method and device of autonomous traffic system and storage medium

Technical Field

The invention relates to the technical field of information analysis and processing, in particular to a method and a device for constructing an architecture of an autonomous traffic system and a storage medium.

Background

With the rapid development of social economy, the traffic demand is further improved, on one hand, users want to obtain active services, on the other hand, decision makers want systems to respond autonomously, the information amount is large, the systems are increased, iteration is accelerated, the complexity of the traffic system is continuously increased, and people can not meet the demand by leading the traffic system. Meanwhile, with the development of related technologies such as communication and control, the autonomy of road traffic elements is leading to a new development opportunity, which will promote the transition of partial fields of Intelligent Transportation Systems (ITS) to autonomy direction and develop along the direction of "assisted autonomy-highly autonomy-fully autonomy". Therefore, it is a trend to construct an Autonomous Transportation System (ATS) that can support the self-organization of a plurality of systems between generations.

The autonomous traffic system requires that the system architecture can select relevant elements from the knowledge base for self-adaptive construction according to the requirements of specific scenes under different generation bases. Aiming at the problem, the knowledge graph of the graph structure is convenient for processing the complicated and intricate relation among various elements in the autonomous traffic system, and moreover, the semantic network has the characteristics of intuition and easy understanding for human beings and computers. However, most of the existing researches are based on the constitution of inference scene architecture knowledge maps such as similarity calculation of nodes, knowledge map representation learning and the like, and the existing methods have the defects of low accuracy, high calculation complexity, weak interpretability and the like.

Disclosure of Invention

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

One aspect of the present invention provides an architecture construction method for an autonomous transportation system, including:

acquiring a knowledge map database of an autonomous traffic system;

determining the definition of a demand and the definition of an entity set corresponding to the demand according to the knowledge map database to obtain a demand-entity set contrast database;

extracting a scene architecture self-adaptive design requirement according to a scene definition document of a user to obtain a demand set;

querying a corresponding target entity set from the requirement-entity set comparison database;

integrating the entity sets according to the query result of the target entity set to obtain a system architecture diagram of a specific scene;

and outputting a knowledge graph of the system architecture according to the system architecture graph.

Optionally, the method further comprises:

displaying an adaptive design interface of an autonomous traffic 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 base of a scene and scene requirements defined by a natural language;

and 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.

Optionally, the determining, according to the knowledge graph database, a definition of a requirement and a definition of an entity set corresponding to the requirement to obtain a requirement-entity set comparison database includes:

analyzing the requirements which can be met by the system knowledge graph under each generation of the autonomous traffic system, and defining a corresponding entity set according to the requirements; the entity set is a knowledge graph subgraph constructed by using knowledge in an autonomous traffic system knowledge graph database, and the knowledge graph subgraph is used for meeting corresponding requirements; the requirements and the entity sets are in one-to-one or many-to-one relationship;

and dividing all the defined entity sets according to the generation basis and storing the entity sets in the requirement-entity set comparison database.

Optionally, the extracting a scene architecture adaptive design requirement according to a scene definition document of a user to obtain a requirement set includes:

constructing a requirement word list according to the requirement-entity set contrast database;

extracting to obtain a required keyword by judging the matching degree of the characters in the scene definition document and each word in the required word list;

storing the requirement keywords into a requirement set;

the scene definition document is described in natural language, and comprises a generation base where a scene is located, demand information contained in the scene and scene application range information;

the extraction scene architecture adaptive design requirement comprises a generation base where the extraction scene is located and a requirement set contained by the scene.

Optionally, the querying the corresponding target entity set from the requirement-entity-set comparison database includes:

and for each entity set, extracting a node set, a relation triple set and an attribute triple set contained in the entity set to serve as a knowledge base of the entity set, and storing the knowledge base into an entity set knowledge base set.

Optionally, the integrating the entity set according to the query result of the target entity set to obtain the system architecture diagram of the specific scene includes:

processing the entity set with the association;

outputting the processed entity set in a knowledge graph form to obtain a system architecture diagram of a specific scene under a target generation base;

wherein the entity sets with associations comprise entity sets that can be associated by granular relationships or entity sets that can be associated by expanding entity sets.

Optionally, the outputting a knowledge graph of a system architecture according to the system architecture diagram includes:

receiving a system architecture map file of a specific scene under a target generation basis through a gPC (gateway GPRS), and outputting the architecture knowledge map in a document form;

or, performing visual analysis on the output architecture knowledge graph through a webVOWL program at a Web end, so that the architecture knowledge graph is output in a Web end visual form.

Another aspect of the embodiments of the present invention further provides an architecture construction apparatus for an autonomous transportation system, including:

the system comprises a first module, a second module and a third module, wherein the first module is used for acquiring a knowledge map database of an autonomous traffic system;

the second module is used for determining the definition of the demand and the definition of the entity set corresponding to the demand according to the knowledge map database to obtain a demand-entity set contrast database;

the third module is used for extracting the adaptive design requirements of the scene architecture according to the scene definition document of the user to obtain a demand set;

a fourth module for querying a corresponding target entity set from the requirement-entity set comparison database;

a fifth module, configured to integrate the entity sets according to the query result of the target entity set, so as to obtain a system architecture diagram of a specific scene;

and the sixth module is used for outputting the knowledge graph of the system architecture according to the system architecture graph.

Another aspect of the embodiments of the present invention further provides an electronic device, including a processor and a memory;

the memory is used for storing programs;

the processor executes the program to implement the method as described above.

Yet another aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores a program, which is executed by a processor to implement the method as described above.

The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.

The embodiment of the invention acquires a knowledge map database of an autonomous traffic system; determining the definition of a demand and the definition of an entity set corresponding to the demand according to the knowledge map database to obtain a demand-entity set contrast database; extracting a scene architecture self-adaptive design requirement according to a scene definition document of a user to obtain a demand set; querying a corresponding target entity set from the requirement-entity set comparison database; integrating the entity sets according to the query result of the target entity set to obtain a system architecture diagram of a specific scene; and outputting a knowledge graph of the system architecture according to the system architecture diagram. The invention reduces the calculation complexity and improves the accuracy.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of an architecture construction method of an autonomous transportation system according to an embodiment of the present invention;

fig. 2 is a technical schematic diagram of an architecture construction method of an autonomous transportation system according to an embodiment of the present invention;

FIG. 3 is a flowchart of entity set fusion provided by an embodiment of the present invention;

FIG. 4 is a driving automation knowledge map based on generation L3;

FIG. 5 is a set of entities satisfying the requirement of performing "monitoring" under the L3 generation basis;

FIG. 6 is a set of entities meeting the need to perform a "dynamic driving task" on an L3 generation basis;

FIG. 7 is a diagram of system architecture output according to scene requirements.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

Aiming at the problems in the prior art, the embodiment of the invention provides a self-adaptive construction method, a self-adaptive construction device and a storage medium for an autonomous traffic system architecture, which can completely and effectively design a scene architecture meeting the requirements of a specific scene under different generation bases according to an autonomous traffic system knowledge map database.

acquiring a knowledge map database of an autonomous traffic system;

Optionally, the method further comprises:

storing the requirement keywords into a requirement set;

the extraction scene architecture adaptive design requirement comprises a generation basis of an extraction scene and a requirement set contained in the scene.

Optionally, the querying a corresponding target entity set from the requirement-entity-set comparison database includes:

processing the entity sets with the association;

wherein the entity sets with associations comprise entity sets that can be related by granular relationships or entity sets that can be related by expanding entity sets.

Another aspect of the embodiments of the present invention further provides an electronic device, which includes a processor and a memory;

the memory is used for storing programs;

the processor executes the program to implement the method as described above.

The following describes in detail the specific implementation principles of the present invention:

the embodiment of the invention provides a self-adaptive design method of an autonomous traffic system architecture, which can design a complete, accurate and highly interpretable scene architecture knowledge graph according to the requirements of specific scenes under different generation bases, and comprises the following steps:

step 1, constructing and storing an autonomous traffic system knowledge map database.

And 2, defining and storing the entity set according to the knowledge model constructed in the step 1. The entity set is a knowledge graph subgraph constructed by using knowledge in an autonomous traffic system knowledge graph database, and the subgraph can meet specific requirements. All the defined entity sets are stored in a requirements-entity set comparison database.

And 3, extracting the generation-based information of the scene and the requirement set contained in the scene according to the scene definition document submitted by the user.

And 4, inquiring the corresponding entity set according to the requirement set extracted in the step 3.

And 5, integrating the entity set according to the query result in the step 4. And obtaining a system architecture diagram of a specific scene under the target generation basis.

And 6, outputting the architecture knowledge graph obtained in the step 5 in a document form or a Web end visualization form, and calling a computer program or analyzing by an autonomous traffic system manager according to different utilization scenes.

In step 1, the knowledge map database data of the autonomous traffic system is map structure data expressed in a form of triples, and comprises entities and information sets related to entity attributes, wherein the entities and the information sets are expressed in terms of nodes, relations and attributes and are used for expressing specific things, and each piece of knowledge can be expressed by one triplet;

nodes represent entities in the autonomous traffic system, such as functions, technologies, services, components, etc.;

the node comprises attributes which represent the description of the entity, the type of the parameters and the parameter values contained in the entity, and the like; the attribute of the node can be represented by a triple in the format of (node, attribute name, attribute value);

the association between nodes is defined by relationship, such as hierarchical relationship of entities on granularity and flow relationship of information flow between entities; the relationship between the nodes can be represented by a triple in the format of (node 1, relationship name, node 2);

evolution exists among all generation bases of the autonomous traffic system, so that the data of the autonomous traffic system knowledge graph under all generation bases needs to be stored in the database;

and according to the sequence of each generation basis of the autonomous traffic system, dividing and storing the knowledge map data of each generation basis of the autonomous traffic system into a map database according to the generation basis to obtain a knowledge map database of the autonomous traffic system.

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

the knowledge in the entity set is from an autonomous traffic system knowledge map database;

the requirements and the entity sets present a one-to-one relationship;

all the defined entity sets are stored in the demand-entity-set comparison database as generation-based partitions.

In step 3, the scene definition document is described in natural language, and includes information such as the generation basis of the scene, various requirements included in the scene, and the application range of the scene;

the extracting of the adaptive design requirement of the scene architecture comprises the following steps: a generation base where a scene is located and a requirement set contained in the scene, wherein the scheme adopts a Natural Language Processing (NLP) technology to identify the requirement set contained in the scene definition document;

the step of identifying the requirement set contained in the definition document of the scene by adopting a natural language processing technology comprises the following steps: and (3) constructing a rich and perfect word list according to the requirement set defined in the step (2), and then extracting the keywords by judging the matching degree of the characters in the scene definition document and each word in the word list.

In step 4, the scheme queries an entity set corresponding to each demand in the target generation from the demand-entity set comparison database according to the demand set extracted in step 3.

And for each entity set, extracting the node set, the relation triple set and the attribute triple set contained in the entity set, using the extracted node set, the relation triple set and the attribute triple set as a knowledge base of the entity set, and storing the knowledge base set of the entity set.

In step 5, the entity set integration is performed by integrating the triples in the entity set knowledge base and storing the integrated knowledge base as the architecture knowledge graph. The triples are the skeleton of knowledge, so that the integration of the entity set can be completed as long as the triples of the entity set are integrated.

Isolated subgraphs may be generated during the integration of different entity sets. The isolated subgraph refers to a subgraph without any association with other entity sets. The method integrates isolated subgraphs based on granularity grading of entities. The granularity hierarchy is represented by a relationship of a parent node and a child node, the relationship of a parent class and a child class is one of the relationships, and the representation form of a triplet is (child node, child class of …, parent node). A parent node is a coarse-grained representation of a child node, which is a fine-grained representation of the parent node.

The integration of entity sets comprises the following steps:

step 501: processing a set of entities having direct associations, comprising:

and judging 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, the two entity sets are further fused to generate a fused entity set. Wherein, the merging of two entity sets according to the intersection of the node sets and generating a merged entity set comprises:

assigning the node sets in the entity set knowledge base after fusion to be a union set of the node sets in the two entity set knowledge bases for fusion;

assigning the relation set in the fused entity set knowledge base to be a union set of the relation sets in the two entity set knowledge bases for fusion;

assigning the attribute set in the fused entity set knowledge base to be a union set of the attribute sets in the two entity set knowledge bases for fusion;

step 502, repeating step 501 until any two entity sets can not be fused according to the method described in step 501.

Step 503, inquiring the number of the entity sets at this time, if the number is equal to 1, indicating that the entity sets are integrated, and turning to step 511; otherwise, it indicates that 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, there is no direct association between these two entity sets, and the step 504 is performed in an isolated manner.

Step 504, processing the entity sets which can be fused through the connection of the hierarchical relations, wherein the entity sets which can be fused through the connection of the hierarchical relations, namely if the two entity sets can be associated through the hierarchical relations, the entity sets are related in granularity, and the step includes:

and judging whether the entity sets can be fused according to whether a hierarchical relation exists between the node sets in any two entity sets. If the fusion can be performed, the two entity sets are further fused to generate a fused entity set. Wherein, the merging of the two entity sets according to the hierarchical relationship and generating a merged entity set includes:

querying a parent node of the node set in the first entity set knowledge base, and if the node set in the second entity set knowledge base comprises the parent node of the node set in the first entity set knowledge base, performing fusion;

and inquiring the father node of the node set in the second entity set knowledge base, and if the node set in the first entity set knowledge base comprises the father node of the node set in the second entity set knowledge base, performing fusion.

The fusion of entity sets can be performed by satisfying any one of the above conditions. The nodes are recorded and stored as a set of associated nodes.

If the fusion can be performed, the two entity sets are fused. Wherein, the fusing two entity sets comprises:

assigning the relation set in the entity set knowledge base after fusion to be a union set of the relation sets in the two entity set knowledge bases for fusion;

adding the hierarchical relationship existing between the two entity sets to a relationship set in the fused entity set knowledge base;

and 505, repeating the step 504 until any two entity sets can not be fused according to the method in the step 504.

Step 506, the number of entity sets is queried. If the value is greater than 1, it indicates that the integration of the isolated subgraphs is not completed in step 505, i.e., the entity sets cannot be completely fused through the hierarchical relationship, and step 507 is performed. If the value equals 1, go to step 510.

Step 507, traversing the entity sets, and for each entity set, expanding the father node and the related hierarchical relationship and the attributes of the granularity of the previous layer, wherein the step comprises the following steps:

adding a hierarchical relationship existing between a parent node of a higher-level granularity in the first entity set and nodes in the entity set into a relationship set of the entity set;

adding a parent node of the previous layer of granularity of each node in the entity set into the node set of the entity set;

the attributes contained by the parent node are added to the set of attributes of the entity set.

Step 508, storing the parent node of the previous layer in step 507 as a temporary storage node set.

Step 509, the entity set is processed again using steps 504 and 506.

Step 510, deleting redundant extended information which is generated in the step 507 and exists in the entity set, wherein the redundant extended information refers to: since the entity set expanded in step 507 may be associated by using the temporary storage node, and there may be some nodes in the temporary storage node set that are not used for association, it is necessary to eliminate the artificially expanded information. The nodes that can be associated are stored in a set of associated nodes, so step 510 includes:

deleting the nodes except the associated node set and the attributes contained in the nodes in the temporary storage node set;

deleting the relationship corresponding to the nodes except the associated node set in the temporary storage node set;

step 511, processing the finally obtained entity set, outputting the entity set in an RDF/XML format as a system architecture diagram of a specific scene under a target generation base, and comprising the following steps:

using OWLAPI to add all the node sets in the entity set into the knowledge graph;

connecting nodes in the knowledge graph by using an OWLAPI (ontology Web page API) and taking a relation triple in an entity set as an input;

and using OWLAPI, taking the attribute triple in the entity set as input, and adding attributes for the nodes in the knowledge graph.

In step 6, the computer can receive a system architecture diagram file of a specific scene under a target generation base through the gPC, and the system architecture diagram file is used for simulation analysis of a system architecture. The user can also analyze the output architecture knowledge graph by means of the webVOWL program at the web end.

The following detailed description of the embodiments of the invention is provided in conjunction with the accompanying drawings:

fig. 1 is a schematic diagram illustrating a self-adaptive construction method of an autonomous transportation system architecture according to an embodiment of the present invention, where the method includes:

acquiring a knowledge map database of an autonomous traffic system;

the expert defines the demand and the entity set thereof according to the data in the knowledge map database of the main traffic system and stores the demand and the entity set into the demand-entity set comparison database;

a user inputs a scene definition document, and a system extracts a scene requirement set according to the scene definition document input by the user; extracting a corresponding entity set from a requirement-entity set contrast database according to a scene requirement set;

integrating the entity set to further obtain a system architecture diagram of a specific scene under a target generation base;

and according to different application scenes, outputting a system architecture diagram of a specific scene under a target generation basis for system call or system architecture designer analysis.

Fig. 2 is a technical schematic diagram of an autonomous transportation system architecture adaptive construction method according to an embodiment of the present invention, including:

the expert defines a demand set and an entity set for the knowledge graph of the autonomous traffic system of each generation base; and the user selects the corresponding entity set to integrate according to the generation basis of the specific scene and the requirement thereof, and generates a system architecture diagram of the specific scene under the target generation basis.

It is to be noted that, for any generation basis, as long as the mapping between the requirement extracted from the scene definition document and the entity set is complete, the embodiment of the present solution may adaptively generate the scene architecture under different generation bases.

It should be noted that the autonomous transportation system knowledge graph includes information sets represented by nodes, relationships, and attributes and used for expressing each entity and related entity attributes required for the normal operation of the autonomous transportation system. The information set is a series of knowledge graph files which meet the same ontology and are different in version and are defined according to the RDF/XML standard; each node represents a knowledge entity and has a unique ID; the nodes can be connected through a relationship, and the relationship can be as follows: "is a subclass (instance) of … …", "contained", "sensed", "responsive", etc. Each node may contain attributes, and the attribute relationship may be: attribute information such as "synonyms", "whether a concept is outdated", "dimensions", and the like; the autonomous traffic system knowledge graph is a knowledge set that satisfies the above definition basis.

In order to facilitate human-computer interaction with a user and acquire operation logic of the user, the operation logic is generally completed based on a user interface. The user interface is a medium for interaction and information exchange between the system and the user, and can realize conversion between the internal form of the computer and the human-acceptable form of the information. In the process of man-machine interaction through a user interface, visualization is also an indispensable link, and the visualization technology is a theory, a method or a technology which utilizes computer graphics and image processing technology to convert data into graphics or images to be displayed on a screen and carry out interactive processing; the visualization technology enables a user to directly operate the information with the body in the graphical interface, and the work efficiency of communication with a computer is improved. In some embodiments, the method further comprises:

displaying a framework adaptive design interface, wherein the framework adaptive design interface comprises a scene definition area and an analysis display area, and the scene definition area is used for receiving a scene definition document, including a generation base of a scene, scene requirements defined by a natural language and optional other information. For receiving scene definition instructions;

and responding to the scene definition instruction, calling the embodiment of the method of the invention to obtain the architecture knowledge graph data corresponding to the scene definition document, and displaying the architecture knowledge graph data in the analysis display area in a preset form.

The present invention will be described in further detail with reference to the accompanying drawings and specific data, taking a specific autonomous transportation system architecture adaptive design as an example. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Taking the driving automation hierarchy defined by sae (society of automatic engineering) as an example, the driving automation level is increased from L0 to L5. The hierarchical definition implies that with the increased level of automation, the assisted driving is based on what kind of technology and which opportunities to comply with, and then evolves/advances to automated driving with a higher level of automation. Drive automation systems have similar features to autonomous traffic systems, including:

the system has evolution among generation bases and develops along the direction of auxiliary autonomy-high autonomy-complete autonomy;

the types of entities in the system are various, the complexity of the incidence relation among the entities is high, and the interaction among the entities jointly promotes a large-scale complex system.

Thus, a driving automation knowledge graph may be constructed as required by the autonomous traffic system knowledge graph definition.

In the definition of SAE, L3 is called "conditionally automated", and compared to L2, the system performs most of the driving operations, when it takes over the human being, monitoring the surroundings. The driver gives an appropriate response as appropriate only when an emergency situation occurs.

According to the definition of SAE, a driving automation L3 level knowledge graph is constructed as shown in fig. 4, which represents the function knowledge, system state knowledge, user role knowledge and knowledge of how the user interacts with the automatic driving system, which are contained in the automatic driving system, by nodes, relations and attributes. The system function, the system state and the user role knowledge of the automatic driving system are all child nodes of the L3-level automatic driving system node, and similarly, various functions included in the automatic driving system are all child nodes of the system function node. Besides the hierarchical relationship, other interactive relationships exist among the nodes, for example, as the application scene changes, the role of the user in the driver seat in the automatic driving system may evolve between the "driver in the vehicle" and the "dynamic driving task takeover user".

The relationships between nodes include parent-child relationship (subclasof), take-over (take _ over), authentication (identification), and the like, and the attributes of the nodes are not shown in the figure.

According to the driving automation L3 level knowledge graph, a professional is invited to analyze a plurality of requirements and corresponding entity sets from the knowledge graph.

According to the definition of SAE, a scenario definition document is defined as follows:

in the class L3 autopilot system knowledge base, the autopilot system monitors its operating conditions as it operates and performs all dynamic driving tasks under the design operating conditions.

According to the adaptive design method described in fig. 2, the scene definition document is input, and the natural language processing engine matches two requirements: "monitoring" and "performing dynamic driving tasks". Are the set of entities used to represent how the autonomous driving system performs monitoring of the system operating conditions and how the vehicle performs dynamic driving tasks, respectively.

The entity sets corresponding to the two requirements are shown in fig. 5 and fig. 6, respectively. The entity set corresponding to the 'monitoring' requirement comprises a framework for monitoring the operation of the automatic driving system. In the entity set, the system monitoring function can continuously monitor the taking over capability of the dynamic driving task taking over users, the running state of the current system, whether the automatic driving system is in failure or not and whether other vehicle systems are in failure or not, and the system monitoring function can provide a quick response service when the system is in abnormal running. The entity set corresponding to the requirement of executing the dynamic driving task comprises a framework for executing the dynamic driving task by the automatic driving system. In the entity set, the system activates a dynamic driving task processing flow under a design operation condition and continuously executes a dynamic driving task, and the dynamic driving task processing flow comprises the following steps: the control of the lateral and longitudinal operation of the vehicle, the detection and response of targets and events, driving decisions, and the control of vehicle lighting and signaling devices.

As shown in fig. 3, in the embodiment of the present invention, the two entity sets are fused, and as shown in fig. 5 and fig. 6, the scene definition documents submitted by the user both include semantic relationships between the two entity sets, but no direct association exists between the two entity sets, so that the program associates according to a hierarchical relationship to find that an entity set corresponding to a "dynamic driving task execution" requirement, and a "system function" node and a "design operation condition" node respectively have a hierarchical relationship with a "monitoring" node and a "vehicle condition" node in the entity set corresponding to a "monitoring" requirement. So that both may perform a fusion operation according to the scheme described in step 504. Meanwhile, because the number of the fused entity sets is 1, the fused entity sets can be directly output as a system architecture, and the output scene architecture is shown in fig. 7. The scenario architecture comprises the entity set of the two requirements, which shows that when the automatic driving system at level L3 is running, the system performs all dynamic driving tasks under the designed running condition, and simultaneously monitors the running condition of the system.

In summary, the invention first obtains an autonomous traffic system knowledge graph database, wherein the autonomous traffic system knowledge graph database includes entities and information sets related to the attributes of the entities, which are represented by nodes, relationships and attributes and are used for expressing specific things; then, inviting experts in the related field to define the requirements and the corresponding entity sets thereof according to the knowledge map database of the autonomous traffic system; then, according to the scene definition document as the adaptive design requirement of the scene architecture, extracting a requirement set under the scene by using a natural language processing technology; then, according to the requirement set and a requirement-entity set comparison database, determining an entity set corresponding to the requirement set; and finally, summarizing according to the entity set to obtain a structure knowledge graph result. The invention is based on the knowledge map database of the autonomous traffic system, and can completely and accurately output the system architecture map of a specific scene under a target generation base according to the requirement set defined by an expert and the entity set corresponding to the requirement set, and can realize the automatic analysis of the system architecture according to the corresponding method flow.

In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic 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 performed independently.

Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, 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.

More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance 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.

It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. An architecture construction method of an autonomous transportation system is characterized by comprising the following steps:

acquiring a knowledge map database of an autonomous traffic system;

2. The architecture construction method of an autonomous transportation system according to claim 1, characterized in that the method further comprises:

3. The architecture construction method of an autonomous transportation system according to claim 1, wherein the determining the definition of the demand and the definition of the entity set corresponding to the demand according to the knowledge map database to obtain the demand-entity set comparison database comprises:

4. The architecture construction method of an autonomous transportation system according to claim 1, wherein the extracting a scene architecture adaptive design requirement according to a scene definition document of a user to obtain a demand set comprises:

storing the requirement keywords into a requirement set;

5. The architecture construction method of an autonomous transportation system according to claim 1, wherein said querying the corresponding target entity set from the demand-entity-set comparison database comprises:

6. The architecture construction method of an autonomous transportation system according to claim 1, wherein the integrating of the entity sets according to the query result of the target entity set to obtain the system architecture diagram of the specific scene comprises:

processing the entity sets with the association;

7. The architecture construction method of an autonomous transportation system according to claim 1, wherein the outputting a knowledge graph of a system architecture according to the system architecture diagram comprises:

8. An architecture construction device for an autonomous transportation system, comprising:

9. An electronic device comprising a processor and a memory;

the memory is used for storing programs;

the processor executing the program realizes the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method according to any one of claims 1 to 7.