Intelligent driving simulation scene management platform and method and electronic equipment

Abstract

The invention provides an intelligent driving simulation scene management platform and method and electronic equipment. The intelligent driving simulation scene management platform comprises a front-end application layer and a cloud end, the front-end application layer is used for responding to the operation of a user on the function module and sending a corresponding operation request to the cloud; wherein the function module comprises a classification management module and a scene management module, and the classification management module is used for constructing a classification scene database and a scene label library; the scene management module is used for labeling and classifying new scenes and performing scene retrieval; the cloud comprises a back-end service layer and a data storage layer; the back-end service layer is used for receiving the operation request sent by the front-end application layer and driving the corresponding function module to execute the corresponding operation based on the operation request; the data storage layer adopts a hierarchical storage architecture and a private cloud architecture to manage scene data; wherein the format of the scene data adopts a preset standard format. According to the invention, problems existing in existing automatic driving scene management are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving simulation testing technology, and in particular to an intelligent driving simulation scenario management platform, method and electronic device. Background Technology

[0002] Before autonomous vehicles can be truly commercialized, they need to undergo extensive road testing to meet commercial requirements. However, optimizing autonomous driving algorithms through road testing is too time-consuming and costly, and open road testing is still subject to regulatory restrictions, making it difficult to reproduce extreme traffic conditions and scenarios, and posing safety risks. Furthermore, due to the vastly different traffic environments, it is difficult to form a universal industry chain system, thus creating numerous practical problems for the development of the autonomous driving industry chain and technology exchange. Therefore, simulation testing based on scenario libraries is an important way to solve the lack of roadside data for autonomous driving.

[0003] Autonomous driving scenario libraries are fundamental data resources for the research and testing of intelligent connected vehicles, and are an important database for evaluating the functional safety of intelligent connected vehicles. However, at present, the construction of simulation scenario libraries by different manufacturers is in a state of fragmentation, mainly facing problems such as inconsistent scenario data formats, low scenario management efficiency, high annotation and generation costs, and security concerns. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an intelligent driving simulation scene management platform, method and electronic device to improve the existing problems in autonomous driving scene management.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides an intelligent driving simulation scene management platform, comprising: a front-end application layer and a cloud; the front-end application layer is used to respond to user operations on functional modules and send corresponding operation requests to the cloud; wherein, the functional modules include: a classification management module and a scene management module, the classification management module is used to construct a classification scene database and a scene tag library; the scene management module is used to label and classify newly created scenes based on the classification scene database and the scene tag library, and to perform scene retrieval based on the classification scene database and the scene tag library during intelligent driving testing to obtain test scenes; the cloud includes: a back-end service layer and a data storage layer; the back-end service layer is used to receive operation requests sent by the front-end application layer and drive the corresponding functional modules to execute corresponding operations based on the operation requests; the data storage layer manages scene data using a layered storage architecture and a private cloud architecture; wherein, the format of the scene data adopts a pre-defined standard format.

[0006] Optionally, the scene management module is specifically used to: obtain the scene data uploaded by the user when creating a new scene, and annotate the scene data based on the scene tag library to obtain the tag file of the new scene; wherein, the scene tag library includes: scene description tags and scene application tags; match the tag file with the categorized scene database to determine the scene category of the new scene; and save the new scene to the categorized scene database corresponding to the scene category.

[0007] Optionally, the front-end application layer also includes: a user login module, a recycling management module, and a basic configuration module; the user login module is used to obtain user account information and perform identity verification and permission verification on the account information; the recycling management module is used to automatically clean up and recycle data during the intelligent driving test process; the basic configuration module is used to manage users and user roles, as well as manage functional modules and system logs.

[0008] Optionally, the cloud also includes a service access layer, which establishes a secure communication channel between the front-end application layer and the cloud when a user logs in or accesses data during intelligent driving testing, and performs user authentication and data encryption based on a pre-built multi-layered access control system.

[0009] Optionally, the backend service layer includes: a service interface layer, a business processing layer, and a data access layer; the service interface layer adopts standardized interface call function modules; the business processing layer is used to extract key element information of the scenario to be retrieved and match the key element information with the scenario tag library to obtain the test scenario; the data access layer is used to access data based on a pre-established structured data storage and caching mechanism.

[0010] Optionally, the cloud also includes: a basic service layer for monitoring intelligent driving tests, issuing alarms and automatically isolating anomalies when they are detected, and performing data backup and anomaly recovery based on preset recovery strategies.

[0011] Optionally, the data storage layer also includes: an intelligent driving data platform for the target automaker built on a private cloud architecture, used to manage the intelligent driving data of the target automaker; wherein, the intelligent driving data includes at least: scenario data and test data.

[0012] Secondly, the present invention provides an intelligent driving simulation scene management method, applied to the intelligent driving simulation scene management platform provided in any of the first aspects above. The intelligent driving simulation scene management platform includes: a front-end application layer and a cloud. The front-end application layer includes multiple functional modules, including a classification management module and a scene management module. The cloud includes a back-end service layer and a data storage layer. The data storage layer manages scene data using a layered storage architecture and a private cloud architecture. The scene data is formatted using a pre-defined standard format. The method includes: responding to user operations on functional modules through the front-end application layer and sending corresponding operation requests to the cloud. The classification management module constructs a classification scene database and a scene tag library. The scene management module labels and classifies newly created scenes based on the classification scene database and scene tag library, and, during intelligent driving testing, performs scene retrieval based on the classification scene database and scene tag library to obtain test scenes. The back-end service layer receives operation requests sent by the front-end application layer and drives the corresponding functional modules to perform corresponding operations based on the operation requests.

[0013] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of the method provided in the second aspect above.

[0014] Fourthly, the present invention provides a computer-readable storage medium on which a computer program is stored, and the computer program, when executed by a processor, performs the steps of the method provided in the second aspect above.

[0015] This invention brings the following beneficial effects: The intelligent driving simulation scene management platform, method, and electronic device provided by this invention include: a front-end application layer and a cloud; the front-end application layer is used to respond to user operations on functional modules and send corresponding operation requests to the cloud; wherein, the functional modules include: a classification management module and a scene management module, the classification management module is used to construct a classification scene database and a scene tag library; the scene management module is used to label and classify newly created scenes based on the classification scene database and the scene tag library, and to retrieve test scenes based on the classification scene database and the scene tag library during intelligent driving testing; the cloud includes: a back-end service layer and a data storage layer; the back-end service layer is used to receive operation requests sent by the front-end application layer and drive the corresponding functional modules to execute corresponding operations based on the operation requests; the data storage layer adopts a layered storage architecture and a private cloud architecture to manage scene data; wherein, the format of the scene data adopts a pre-defined standard format. The aforementioned intelligent driving simulation scenario management platform manages scenario data using a pre-defined standard format, thereby eliminating platform compatibility differences and improving the problem of inconsistent scenario data formats. By constructing a categorized scenario database and a scenario tag library, and using these databases to label, classify, and retrieve newly created scenarios, it improves the issues of low scenario management efficiency and high labeling and generation costs. The data storage layer employs a layered storage architecture and a private cloud architecture to manage scenario data, building a dedicated intelligent driving data platform for automakers. This enables version control, access management, and security protection of scenario data, improving the problem of data security deficiencies.

[0016] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the structure of an intelligent driving simulation scene management platform provided in an embodiment of the present invention; Figure 2 A forward flowchart illustrating scene uploading, scene annotation, scene classification, and scene retrieval in a client browser front-end page, as provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a scene management platform architecture provided in an embodiment of the present invention; Figure 4 A flowchart illustrating an intelligent driving simulation scenario management method provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Currently, different vendors are building their simulation scene libraries independently, mainly facing problems such as inconsistent scene data formats, low scene management efficiency, high annotation and generation costs, and lack of security.

[0022] Based on this, the intelligent driving simulation scene management platform, method and electronic device provided by the embodiments of the present invention can improve the problems existing in the management of existing autonomous driving scenarios.

[0023] To facilitate understanding of this embodiment, a detailed description of the intelligent driving simulation scenario management platform disclosed in this embodiment of the invention will be provided first. See [link to documentation]. Figure 1 The diagram shows the structure of an intelligent driving simulation scene management platform, indicating that the platform mainly includes: a front-end application layer 10 and a cloud layer 20.

[0024] The front-end application layer 10 is used to respond to user operations on functional modules and send the corresponding operation requests to the cloud 20. The functional modules include a classification management module and a scene management module. The classification management module is used to build a classification scene database and a scene tag library. The scene management module is used to label and classify newly created scenes based on the classification scene database and the scene tag library, and to retrieve test scenes based on the classification scene database and the scene tag library during intelligent driving testing.

[0025] In practical implementation, the front-end application layer 10, i.e., the client browser front-end, includes multiple functional modules. Users transmit corresponding function operation requests to the cloud 20 through these modules. The cloud 20 then drives the corresponding modules to execute the corresponding functions based on the function operation requests. These functional modules include a category management module and a scene management module. The category management module is used to build a category scene database and a scene tag library, specifically including: creating, editing, and deleting category scene databases, as well as managing the scene tag library.

[0026] In this embodiment of the invention, the scenario library can be categorized into natural driving scenarios, expert experience scenarios, standard regulatory scenarios, etc., and a corresponding categorized scenario database is constructed for each scenario category. Scenario tags include: scenario description tags and scenario application tags. Scenario description tags describe the scenario itself, such as the number of lanes, straight sections, curves, vehicle behavior, and descriptions of objects; scenario application tags describe how the scenario is applied to specific tests, such as application to functional testing or ACC testing. The scenario tag library stores scenario tags in the form of a tag tree.

[0027] The scene management module is used to label and classify newly created scenes based on a categorized scene database and a scene tag library. During intelligent driving testing, it also retrieves test scenes based on these databases. Specifically, it includes scene file uploading, scene editing, scene data labeling and classification, and scene deletion.

[0028] In practice, when creating a new scene, the scene management module obtains the scene data uploaded by the user and labels the scene data based on the scene tag library to obtain the tag file of the new scene. Then, the tag file is matched with the category scene database to determine the scene category of the new scene. Finally, the new scene is saved to the category scene database corresponding to the scene category.

[0029] For ease of understanding, embodiments of the present invention also provide a forward process for scene uploading, scene annotation, scene classification, and scene retrieval on the client's browser front-end page, see [link to documentation]. Figure 2 As shown.

[0030] (1) Scene upload includes: First, select the tag tree on the client's browser front-end page, and then upload the scene, that is, upload the scene file, which includes scene data such as description information and application information of the newly created scene; then, store the scene file in the data pool.

[0031] (2) Scene annotation includes: After receiving the scene data uploaded by the user, the scene data is automatically annotated by the AI ​​model based on the scene tag library in the platform. If the automatic annotation is missing or the tags need to be modified, the user can manually annotate and modify the tags, and finally generate a tag file.

[0032] (3) Scene classification includes: matching the classification files based on the classification scene database within the platform, listing the matching scene categories, determining the scene category, and moving the newly created scene into the corresponding classification library.

[0033] (4) Scene retrieval includes: When conducting intelligent driving tests, scenes can be selected according to specific test requirements, that is, matching scenes that match the test requirements in the classified scene database and applying the scenes to complete the test.

[0034] The cloud-based 20 includes a backend service layer and a data storage layer. The backend service layer receives operation requests sent by the frontend application layer and drives the corresponding functional modules to perform corresponding operations based on the operation requests. It adopts a layered storage architecture and a private cloud architecture to manage scene data. The scene data is formatted using a pre-defined standard format.

[0035] In practical implementation, the data storage layer adopts a layered storage architecture to construct a raw data storage area, a standardized processing area, and an archive backup area. Scene data is stored according to corresponding partitions, thereby enabling file version management and historical record tracing. The data storage layer also includes: an intelligent driving data platform for the target automaker, built on a private cloud architecture, used to manage the target automaker's intelligent driving data; among which, intelligent driving data includes at least: scene data and test data.

[0036] In this embodiment of the invention, a private cloud architecture is adopted to realize the management and control of data assets, and to build a dedicated intelligent driving data platform for target car companies, thereby realizing scenario data version control, permission management and intellectual property protection, and meeting the data traceability requirements of ISO26262 functional safety.

[0037] Furthermore, the data storage layer can also deploy multi-replica storage and cross-regional disaster recovery solutions, establish data lifecycle management strategies, and build data security mechanisms.

[0038] Specifically, to improve data availability, read / write performance, and tolerance for partial failures, the data storage layer can deploy multiple replicas (e.g., 3) and distribute them across different servers. When writing data, the client writes to the primary replica, and the system synchronously / asynchronously replicates it to other replicas. Success is returned once a majority of replicas confirm the data. When reading data, it can be read from any replica or forced to read from the primary replica.

[0039] To cope with regional disasters (such as earthquakes, power outages, and network interruptions) and ensure business continuity, the data storage layer provided in this embodiment of the invention can adopt a cross-regional disaster recovery solution through a primary / backup mode: the primary region processes all data, and the backup region synchronizes data. When a failure occurs, automatic or manual switching can be performed.

[0040] To optimize storage costs and automatically clean up expired data, the data storage layer provided in this embodiment of the invention can establish a data lifecycle management strategy. Specifically, the entire data lifecycle includes: hot data (frequently accessed), warm data (occasional access), cold data (archived), and deletion. In this embodiment, data can be managed periodically based on time, access frequency, and business tags, and data migration / deletion records can be recorded.

[0041] To prevent data leakage, tampering, and unauthorized access, the data storage layer provided in this embodiment of the invention can encrypt data and encrypt the data channel during data transmission; control the access permissions of users accessing the data and record access logs for all data; and de-identify scenario data before applying it to tests, or encrypt sensitive data.

[0042] The intelligent driving simulation scene management platform provided in this embodiment of the invention manages scene data using a pre-defined standard format, thereby eliminating platform compatibility differences and improving the problem of inconsistent scene data formats. By constructing a categorized scene database and a scene tag library, and performing annotation, classification, and scene retrieval based on the categorized scene database and scene tag library, the platform improves the problems of low scene management efficiency and high annotation and generation costs. The data storage layer adopts a layered storage architecture and a private cloud architecture to manage scene data, building a dedicated intelligent driving data platform for automakers, thereby realizing version control, access management, and security protection of scene data, and improving the problem of lack of data security.

[0043] In one implementation, the front-end application layer further includes: a user login module, a recycling management module, and a basic configuration module; the user login module is used to obtain the user's account information and to verify the account information for authentication and permission verification.

[0044] In practice, the front-end application layer, i.e. the client browser front-end, also includes a user login module (i.e., login interface). Users log in by filling in their account and password on the login interface, but users are not allowed to register their own accounts. The system administrator must create personal accounts and set related permissions.

[0045] The functional modules (i.e. the functional interface after login) also include: a recycling management module, used to automatically clean up and recycle data during the intelligent driving test process; and a basic configuration module, used to manage users and user roles, as well as functional modules, organizational structure, and system logs.

[0046] In one implementation, the cloud 20 further includes a service access layer, which establishes a secure communication channel between the front-end application layer and the cloud when a user logs in or accesses data during intelligent driving testing, and performs user authentication and data encryption based on a pre-built multi-layered access control system.

[0047] In practical implementation, to ensure that all communication between the client and the cloud is not eavesdropped on or tampered with, the service access layer can establish a secure communication channel between the front-end application layer and the cloud, and encrypt sensitive information before data transmission. For example, use the HTTPS protocol, and all external requests must pass through an API gateway, requiring both parties to verify each other's identities. Authentication can use password + multi-factor authentication (e.g., SMS verification code, biometrics, etc.); or involve a third-party identity provider, using ID tokens to transmit user identity information.

[0048] In one implementation, the backend service layer includes: a service interface layer, a business processing layer, and a data access layer; the service interface layer adopts standardized interface call function modules; the business processing layer is used to extract key element information of the scene to be searched and match the key element information with the scene tag library to obtain the test scene; the data access layer is used to access data based on a pre-established structured data storage and caching mechanism.

[0049] In practice, the backend service layer is implemented using a layered business framework, including: (1) Service Interface Layer: Adopting standardized interface specifications, it supports function calls related to scenario management and integrates request verification and traffic control modules. Specifically, the request verification module verifies all requests entering the system. It can use specifications such as OpenAPI / Swagger or Protobuf to define the request parameter structure, type, required fields, and value range for each interface; it intercepts requests at the service entry point and executes the following verification logic: Syntax validation: Checks whether the JSON format is valid, whether the fields exist, and whether the types match.

[0050] Semantic validation: Business rule validation (such as scenario names cannot be repeated, whether the user has permission to operate the scenario).

[0051] Identity authentication and authorization: Verify user identity and permissions through JWT and OAuth2 Token.

[0052] To prevent replay attacks: check the timestamp or nonce in the request.

[0053] In this embodiment of the invention, the request verification module can ensure that all requests entering the system conform to the expected format, have legal content, and valid permissions, thus preventing malicious or invalid requests from affecting backend services.

[0054] The traffic control module can use API gateways for rate limiting, or use middleware for rate limiting, to prevent sudden traffic surges from overwhelming the service, ensuring system availability, and resisting external attacks.

[0055] (2) Business processing layer: The scene parsing module extracts key element information such as roads and traffic participants, and uses the intelligent annotation system to automatically match the preset scene tag library to complete the semantic annotation of scene data, so as to realize the dynamic retrieval function of scene data.

[0056] (3) Data Access Layer: Establish a structured data storage and caching mechanism, and improve the processing capacity for massive scenarios through data sharding strategies. Specifically, relational databases (MySQL, PostgreSQL), distributed databases (CockroachDB), and document databases (MongoDB) can be used as storage engines. When a data access request is received, the data is first queried in the cache. If the data is not found in the cache, the database query is then performed. If the data is found in the cache, the result is returned directly.

[0057] In one implementation, the cloud also includes: a basic service layer for monitoring intelligent driving tests, issuing anomaly alerts and automatically isolating when anomalies are detected, and performing data backup and anomaly recovery based on a preset recovery strategy.

[0058] In practical implementation, the basic service layer builds an operation and maintenance support system, which tracks service performance and resource usage status in real time through a full-link monitoring system, automated operation and maintenance processes, fault self-healing capabilities, and anomaly warning and automatic alarm mechanisms; it establishes a version update and rollback management mechanism to achieve rapid deployment and dynamic expansion of service components; in addition, it establishes automatic isolation and recovery strategies for service anomalies and configures data backup and rapid recovery solutions.

[0059] Specifically, the monitoring metrics of a full-link monitoring system should include at least: CPU, memory, disk, network I / O, QPS, response time (P95 / P99), error rate, scenario creation success rate, API call volume, tenant activity, business metrics, and logs. Monitoring points are placed at service entry points, middleware, and database call points to collect monitoring metrics. Anomaly detection and analysis of these metrics are then performed to determine if system anomalies exist and to locate them. Furthermore, anomaly warnings can be generated through the analysis of monitoring metrics, and automatic alerts can be issued when anomalies are detected.

[0060] When an anomaly is detected, the abnormal instance can be isolated according to the automated operation and maintenance process. For example, if an instance fails continuously or loses its heartbeat, it can be automatically taken offline from the service list, or the circuit breaker status can be maintained locally on the caller. Then, the fault phenomenon can be automatically handled according to the preset self-healing rules. For example, if Redis memory usage is >90%, a key cleanup script or cluster expansion can be triggered.

[0061] For ease of understanding, this embodiment of the invention also provides a schematic diagram of a scene management platform architecture, see [link / reference]. Figure 3 As shown, its architecture includes a front-end application layer and a cloud layer. The cloud layer includes a service access layer, a back-end service layer (API layer, business processing layer, data access layer), a data storage layer (MySQL and Redis cluster), and a basic service layer (operation and maintenance support system). The technical solutions adopted are explained in detail below with reference to the attached diagram: The front-end application layer, or client browser front-end, includes the user login interface and the interfaces of various functional modules after login. Users log in by entering their username and password on the login interface, but users are not allowed to register their own accounts; system administrators must create personal accounts and set related permissions. Functional interfaces include: a scene management interface (scene file upload, scene editing, scene data annotation, and scene deletion, etc.), a category management interface (creating, editing, and deleting category scene libraries, and managing tag libraries), a recycle bin management interface, and a basic configuration interface (user management, role management, module management, organizational structure, and system logs). Users transmit their corresponding functional operation requirements to the cloud through these functional module interfaces, and the cloud drives the corresponding modules to execute the corresponding functions based on these requirements.

[0062] The first step in building the cloud is the service access layer. Secure communication must be established for user login and data access, a multi-level access control system must be established, and data transmission encryption and authentication mechanisms must be implemented.

[0063] Further, a layered business framework is implemented, with a unified service interface layer: a standardized interface specification is designed to support function calls related to scenario management, and then request verification and traffic control modules are integrated; the business processing layer extracts key elements such as roads and traffic participants, develops a scenario parsing module, and builds an intelligent labeling system, thereby automatically matching the preset label system to complete semantic labeling, so as to realize the dynamic retrieval function of scenario data.

[0064] The next step is the implementation of data access management: establishing a structured data storage and caching mechanism, and designing a data sharding strategy to improve the processing capabilities for massive scenarios.

[0065] Further, a data storage system is built, adopting a layered storage architecture to construct a raw data storage area, a standardized processing area, and an archive backup area, enabling file version management and historical record tracing functions. Then, multi-replica storage and cross-regional disaster recovery solutions are deployed, a data lifecycle management strategy is established, and a data security mechanism is constructed.

[0066] Further develop the operation and maintenance support system by establishing a full-link monitoring system, automated operation and maintenance processes, and fault self-healing capabilities. Set up anomaly warning and automatic alarm mechanisms to track service performance and resource usage status in real time. Establish a version update and rollback management mechanism to achieve rapid deployment and dynamic expansion of service components. In addition, design automatic isolation and recovery strategies for service anomalies and configure data backup and rapid recovery solutions.

[0067] The scenario management platform provided in this invention uses ASAMOpenDRIVE and OpenSCENARIO standard formats for scenario data, providing automated import / export functions to achieve seamless data interoperability with platforms such as CARLA and VTD, eliminating platform compatibility differences. Through a hierarchical storage architecture and based on 800+ predefined tag trees (covering traffic participants, road topology, and other elements), combined with AI automatic annotation technology, it achieves millisecond-level cross-database joint retrieval. Adopting a private cloud architecture, it achieves data asset management, building a dedicated intelligent driving data platform for automakers, realizing scenario data version control, access control, and intellectual property protection, meeting the data traceability requirements of ISO 26262 functional safety, and solving data management problems.

[0068] In addition to the intelligent driving simulation scene management platform provided in the foregoing embodiments, this invention also provides an intelligent driving simulation scene management method, applied to the intelligent driving simulation scene management platform provided in the above embodiments. The intelligent driving simulation scene management platform includes: a front-end application layer and a cloud. The front-end application layer includes multiple functional modules, including: a classification management module and a scene management module. The cloud includes a back-end service layer and a data storage layer. The data storage layer adopts a layered storage architecture and a private cloud architecture to manage scene data. The format of the scene data adopts a pre-set standard format.

[0069] See Figure 4 The flowchart shown illustrates a method for managing intelligent driving simulation scenarios, which mainly includes the following steps S401 to S402: Step S401: The front-end application layer responds to the user's operation on the functional module and sends the corresponding operation request to the cloud.

[0070] The classification management module constructs a classification scene database and a scene tag library; the scene management module, based on the classification scene database and scene tag library, labels and classifies newly created scenes, and, during intelligent driving testing, performs scene retrieval based on the classification scene database and scene tag library to obtain test scenes.

[0071] Step S402: Receive the operation request sent by the front-end application layer through the back-end service layer, and drive the corresponding functional module to perform the corresponding operation based on the operation request.

[0072] The intelligent driving simulation scene management method provided in this embodiment of the invention manages scene data using a pre-set standard format, thereby eliminating platform compatibility differences and improving the problem of inconsistent scene data formats. By constructing a categorized scene database and a scene tag library, and performing annotation, classification, and scene retrieval based on the categorized scene database and scene tag library, the method improves the problems of low scene management efficiency and high annotation and generation costs. The data storage layer adopts a layered storage architecture and a private cloud architecture to manage scene data, building a dedicated intelligent driving data platform for automakers, thereby realizing version control, permission management, and security protection of scene data, and improving the problem of lack of data security.

[0073] It should be noted that the method provided in the embodiments of the present invention has the same implementation principle and technical effect as the foregoing embodiments. For the sake of brevity, any part not mentioned in the method embodiments can be referred to the corresponding content in the foregoing embodiments.

[0074] This invention also provides an electronic device, specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and the computer program, when run by the processor, executes the method described in any of the above embodiments.

[0075] Figure 5 The present invention provides a schematic diagram of the structure of an electronic device 100, which includes a processor 50, a memory 51, a bus 52 and a communication interface 53. The processor 50, the communication interface 53 and the memory 51 are connected through the bus 52. The processor 50 is used to execute executable modules, such as computer programs, stored in the memory 51.

[0076] The memory 51 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 53 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0077] Bus 52 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0078] The memory 51 is used to store programs. After receiving an execution instruction, the processor 50 executes the programs. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 50 or implemented by the processor 50.

[0079] Processor 50 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 50 or by instructions in software form. Processor 50 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 51. The processor 50 reads the information in memory 51 and, in conjunction with its hardware, completes the steps of the above method.

[0080] The computer program product of the readable storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0081] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0082] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent driving simulation scenario management platform, characterized in that, include: Front-end application layer and cloud; The front-end application layer is used to respond to user operations on functional modules and send corresponding operation requests to the cloud; wherein, the functional modules include: a classification management module and a scene management module, the classification management module is used to build a classification scene database and a scene tag library; the scene management module is used to label and classify newly created scenes based on the classification scene database and the scene tag library, and to perform scene retrieval based on the classification scene database and the scene tag library during intelligent driving testing to obtain test scenes; The cloud includes a backend service layer and a data storage layer. The backend service layer receives operation requests sent by the frontend application layer and drives the corresponding functional modules to perform corresponding operations based on the operation requests. The data storage layer manages the scene data using a layered storage architecture and a private cloud architecture. The scene data is formatted using a pre-defined standard format.

2. The management platform according to claim 1, characterized in that, The scene management module is specifically used for: When creating a new scene, the scene data uploaded by the user is obtained, and the scene data is labeled based on the scene tag library to obtain the tag file of the new scene; wherein, the scene tag library includes: scene description tags and scene application tags; The tag file is matched with the classification scene database to determine the scene category of the newly created scene; The newly created scene is saved to the category scene database corresponding to the scene category.

3. The management platform according to claim 1, characterized in that, The front-end application layer also includes: a user login module, a recycling management module, and a basic configuration module; The user login module is used to obtain the user's account information and to verify the account information for identity and permissions. The recycling management module is used to automatically clean and recycle data during the intelligent driving test process; The basic configuration module is used to manage the users and user roles, as well as the functional modules and system logs.

4. The management platform according to claim 1, characterized in that, The cloud also includes a service access layer, which is used to establish a secure communication channel between the front-end application layer and the cloud when a user logs in or accesses data during intelligent driving testing, and to authenticate the user and encrypt the transmitted data based on a pre-built multi-layer permission control system.

5. The management platform according to claim 1, characterized in that, The backend service layer includes: a service interface layer, a business processing layer, and a data access layer; The service interface layer uses standardized interfaces to call the functional modules. The business processing layer is used to extract key element information of the scene to be searched, and match the key element information with the scene tag library to obtain the test scene; The data access layer is used for data access based on a pre-established structured data storage and caching mechanism.

6. The management platform according to claim 1, characterized in that, The cloud also includes a basic service layer, which monitors the intelligent driving test, issues anomaly alerts and automatically isolates the system when anomalies are detected, and performs data backup and anomaly recovery based on a preset recovery strategy.

7. The management platform according to claim 1, characterized in that, The data storage layer further includes: an intelligent driving data platform for the target automaker, built on a private cloud architecture, used to manage the intelligent driving data of the target automaker; wherein the intelligent driving data includes at least: scenario data and test data.

8. A method for managing intelligent driving simulation scenarios, characterized in that, The method is applied to the intelligent driving simulation scene management platform according to any one of claims 1 to 7, wherein the intelligent driving simulation scene management platform comprises: a front-end application layer and a cloud, the front-end application layer comprises multiple functional modules, the functional modules comprising: a classification management module and a scene management module, the cloud comprises a back-end service layer and a data storage layer, the data storage layer adopts a layered storage architecture and a private cloud architecture to manage scene data; wherein the format of the scene data adopts a pre-defined standard format; the method comprises: The front-end application layer responds to user operations on the functional modules and sends the corresponding operation requests to the cloud; the classification management module constructs a classification scene database and a scene tag library; the scene management module labels and classifies newly created scenes based on the classification scene database and the scene tag library, and performs scene retrieval based on the classification scene database and the scene tag library during intelligent driving testing to obtain test scenes; The backend service layer receives operation requests sent by the frontend application layer and drives the corresponding functional modules to perform corresponding operations based on the operation requests.

9. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the steps of the method of claim 8.

10. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the steps of the method described in claim 8.

Images