Methods for establishing a coherent scene image library, scene recognition devices, and storage media.

Abstract

This invention discloses a method for establishing a coherent scene image library, a scene recognition device, and a storage medium. The method includes: acquiring source data of a vehicle, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data; fitting the source data to a scene model to obtain multiple single scenes, wherein the multiple single scenes include scene information of the vehicle in different driving environments; classifying and processing the multiple single scenes to obtain a scene image library, which is used to output coherent scenes. The scene image library includes multi-level image units, each level of image unit includes at least one single scene from the multiple single scenes, and the coherent scene includes at least one level of image units. The image units of the output coherent scene include at least one single scene. This invention solves the technical problem of insufficient systematization in scene recognition in related technologies.

Description

Technical Field

[0001] This invention relates to the field of vehicle networking technology, and more specifically, to a method for establishing a coherent scene image library, a scene recognition device, and a storage medium. Background Technology

[0002] With the rapid development of vehicle-to-everything (V2X) and intelligent vehicles, intelligent service scenario recognition has become one of the core technical issues in the research and application of vehicle intelligence and personalized services. The coverage, accuracy, and refinement of scenario recognition have become crucial for improving the user experience. As the service scenarios of intelligent vehicles become increasingly diverse, a systematic and comprehensive understanding of vehicle usage scenarios to support the design and implementation of scenario-based intelligent services is a significant problem to be solved in the research and development of intelligent connected vehicles.

[0003] Many innovative methods have emerged in the analysis and application of big data related to the Internet of Vehicles, laying a foundation for improving subsequent services and experiences. However, in the identification of intelligent vehicle service scenarios, the coverage, accuracy, and systematization of identification for daily life and travel scenarios still need further development.

[0004] Current industry practices involve constructing rules for specific service scenarios. When certain rules are triggered, a scenario state is considered identified, and subsequent service recommendations are made based on the configured scenario rules. Existing technologies often achieve discrete scenario identification through simple signal processing and rule concatenation. For example, the identification process might involve streaming calculations of a vehicle's continuous driving time; when the vehicle triggers certain rules, a scenario state is output, such as triggering a high / moderate fatigue driving state based on the user's gender if the continuous driving time exceeds 3 hours. This method of scenario identification often defines simple rule combinations for single states, lacking a systematic design and encapsulation, and the design of scenario aggregation is not rationally designed. Summary of the Invention

[0005] The main objective of this invention is to provide a method for establishing a coherent scene image library, a scene recognition device, and a storage medium to solve the problem of insufficient systematic scene recognition during driving in the prior art.

[0006] To achieve the above objectives, according to one aspect of the present invention, a method for establishing a coherent scene image library is provided. The method includes: acquiring source data of a vehicle, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data; performing scene fitting on the source data using a scene model to obtain multiple single scenes, wherein the multiple single scenes include scene information of the vehicle in different driving environments; classifying and processing the multiple single scenes to obtain a scene image library, the scene image library being used to output coherent scenes, wherein the scene image library includes multi-level image units, each level of image unit includes at least one single scene from the multiple single scenes, the coherent scene includes at least one level of image units, and the image units of the output coherent scene include at least one single scene.

[0007] Furthermore, the method for establishing a coherent scene image library includes: configuring scene attributes for each individual scene, the scene attributes being used to retrieve the corresponding individual scene, wherein the scene attributes include at least one of the following: storage address, name, status, running mode, running status, running address, creation time, operable items, and logs of the individual scene.

[0008] Furthermore, the classification and processing of multiple single scenarios includes: classifying multiple single scenarios according to the vehicle's driving information, with each single scenario in each category being assigned to an image unit, wherein the driving information includes at least one of the following: the vehicle's driving stage, the vehicle's driving purpose, the vehicle's in-cabin driving scenario, and the driving behavior of the driver operating the vehicle.

[0009] Furthermore, outputting a coherent scene includes: acquiring a first output instruction, which is used to output a coherent scene within a target time period; responding to the first output instruction and outputting a coherent scene within the target time period.

[0010] Furthermore, outputting a coherent scene includes: acquiring a second output instruction, which is used to output a coherent scene at a target time node; responding to the second output instruction and outputting a coherent scene at the target time node.

[0011] Furthermore, multiple scenario models are used to fit the source data to obtain multiple single scenarios, including: vehicle travel chain, multi-source data inside the cabin, multi-source data outside the cabin to analyze vehicle driving trajectory and user context; and fitting environmental information, points of interest information, dwell time information, destination information, external environment information, internal environment information, and the operator's state information to obtain multiple single scenarios.

[0012] According to another aspect of the present invention, a scene recognition device is provided, the device comprising: a first acquisition module for acquiring source data of a vehicle, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data; a fitting module for performing scene fitting on the source data using a scene model to obtain multiple single scenes, wherein the multiple single scenes include scene information of the vehicle in different driving environments; and a classification module for classifying the multiple single scenes to obtain a scene image library, the scene image library being used to output a coherent scene, wherein the scene image library includes multi-level image units, each level of image unit includes at least one single scene from multiple single scenes, the coherent scene includes at least one level of image units, and the image units of the output coherent scene include at least one single scene.

[0013] Furthermore, the scene recognition device includes: a second acquisition module for acquiring output instructions, the output instructions being used to output a coherent scene; a preprocessing module for preprocessing individual scenes in the coherent scene to be output according to the output instructions, the preprocessing including at least one of the following: verifying, evaluating, or optimizing the individual scenes; and an output module for outputting the coherent scene.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, comprising a stored program, wherein the program executes the method described above when it is run.

[0015] According to another aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute the above-described method by means of the computer program.

[0016] By applying the technical solution of this invention, multiple scene models are used to obtain multiple single scenes, and multiple single scenes are aggregated to obtain a scene image library. The scene image library includes multi-level image units, and each level of image unit includes at least one single scene from multiple single scenes. When outputting a coherent scene from the scene image library, real-time aggregation can be achieved based on the single scenes in each level of image unit. The coherent scene image library established by this method makes it more flexible to aggregate single scenes and has a wider coverage of scene recognition, thus solving the problem of insufficient systematic scene recognition in the prior art. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0018] Figure 1 This is a hardware structure block diagram of a computer terminal for a method of establishing a coherent scene image library according to one embodiment of the present invention.

[0019] Figure 2 This is a flowchart of a method for establishing a coherent scene image library according to one optional embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of a scene recognition device according to an optional embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram illustrating the principle of a scenario with coherent output according to one optional embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram illustrating the principle of a scene recognition engine according to one optional embodiment of the present invention;

[0023] Figure 6 This is a classification system diagram of a scene image library according to one embodiment of the present invention;

[0024] Figure 7 This is a schematic diagram of a software architecture according to one embodiment of the present invention. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Exemplary embodiments according to this application will now be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of this application is thorough and complete, and that the concept of these exemplary embodiments is fully conveyed to those skilled in the art. In the drawings, for clarity, the thickness of layers and regions may be exaggerated, and the same reference numerals are used to denote the same devices, and therefore their description will be omitted.

[0029] The methods and embodiments provided in this application can be executed on a computer terminal, a computer terminal, or a similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of a computer terminal for a method of establishing a coherent scene image library according to an embodiment of the present invention. For example... Figure 1 As shown, a computer terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. In one exemplary embodiment, the computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 Equivalent functions or ratios shown Figure 1 The functions shown have more different configurations.

[0030] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the data request processing method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the computer terminal. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0032] Display device 110 may be, for example, a touchscreen liquid crystal display (LCD) and a touch display (also referred to as a "touchscreen" or "touch display"). The LCD allows a user to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), which allows the user to interact with the GUI via finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, a call interface, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0033] According to one embodiment of the present invention, an embodiment of a method for establishing a coherent scene image library is provided. It should be noted that, in the appendix... Figure 2 The steps shown in the flowchart can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0034] like Figure 2 As shown, the process includes the following steps:

[0035] Step S21: Obtain the vehicle's source data, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data;

[0036] Step S22: Use a scene model to fit the source data to obtain multiple single scenes, where the multiple single scenes include scene information of the vehicle in different driving environments.

[0037] Step S23: Classify and process multiple single scenes to obtain a scene image library. The scene image library is used to output coherent scenes. The scene image library includes multi-level image units. Each level of image unit includes at least one single scene from multiple single scenes. A coherent scene includes at least one level of image units. The image units of the output coherent scene include at least one single scene.

[0038] By applying the technical solution of this embodiment, multiple scene models are used to obtain multiple single scenes, and multiple single scenes are aggregated to obtain a scene image library. The scene image library includes multi-level image units, and each level of image unit includes at least one single scene from multiple single scenes. When outputting a coherent scene from the scene image library, real-time aggregation can be achieved based on the single scenes in each level of image unit. The coherent scene image library established by this method makes it more flexible to aggregate single scenes and has a wider coverage of scene recognition, thus solving the problem of insufficient systematic scene recognition in the prior art.

[0039] Optionally, the method for establishing a coherent scene image library further includes: configuring scene attributes for each individual scene. Scene attributes are used to retrieve the corresponding individual scene. The scene attributes include at least one of the following: storage address, name, status, running mode, running status, running address, creation time, operable items, and logs for the individual scene. Configuring scene attributes for each individual scene facilitates the addition, modification, and scheduled execution of individual scene tasks, enabling centralized management of multiple tasks. Specifically, in one embodiment of this application, the scene attributes may be: 8123e718a, ScenarioModelName, Closed, YARN_PER, Running, application_1626872989805_0377, 2021-07-28 16:00:00, Start / Stop / Modify, Log Details, and Historical Logs.

[0040] Optionally, in step S23, the classification processing of multiple single scenarios includes: classifying multiple single scenarios according to the vehicle's driving information, with each single scenario in each category being assigned to an image unit. The driving information includes at least one of the following: the vehicle's driving stage, the vehicle's driving purpose, the vehicle's in-cabin driving scenario, and the driver's driving behavior. Classifying single scenarios according to driving information facilitates the systematic management of single scenarios and the output of coherent scenarios. In one embodiment of this application, the driving information includes: the vehicle's driving stage, the vehicle's driving purpose, the vehicle's in-cabin driving scenario, the driver's driving behavior, special time information, vehicle status information, environmental information, trip characteristics, and vehicle user-defined or proactive interaction information. Specifically, the driving stages of a vehicle can include five stages: before getting in the vehicle, after getting in the vehicle but before driving, during driving, before leaving after driving, and at the end of the trip. The purpose of driving a vehicle can include four purposes: commuting, leisure, regular long-distance travel, and daily driving. The driving scenario inside the vehicle can include the behavior and characteristics of the driver and passengers. The driving behavior of the driver operating the vehicle can include three types of driving behavior: aggressive driving, continuous driving during mealtimes, and long-distance fatigue driving.

[0041] In one embodiment of this application, when classifying driving information, a single scenario can be divided into three categories, as shown in Table 1. The single scenario can be classified into Level 1, Level 2, and Level 3 scenarios. Level 1 scenarios are defined based on the vehicle's driving stage; Level 2 scenarios are defined based on the vehicle's driving purpose; and Level 3 scenarios are defined based on the vehicle's in-cabin driving scenario, the driver's driving behavior, specific times, vehicle status, trip characteristics, and user-defined or actively interacted information. Dividing a single scenario into Level 1, Level 2, and Level 3 scenarios according to the above definitions allows users to understand their current scenario from multiple dimensions.

[0042] Table 1:

[0043]

[0044] Furthermore, as shown in Table 2, the single scenarios included in the first-level scenario can be: before getting on the vehicle, after getting on the vehicle, before driving, during driving, after driving, before leaving, and after the trip.

[0045] Table 2:

[0046]

[0047] Furthermore, as shown in Table 3, the individual scenarios included in the secondary scenarios can be further divided. In one embodiment of this application, the secondary scenarios can be divided into four categories: commuting, leisure, regular long-distance travel, and daily life. Specifically, the individual scenarios included in the commuting category can be going to work and commuting to get off work; the individual scenarios included in the leisure category can be long-distance driving and short-distance travel; the individual scenarios included in the regular long-distance travel category can be business, long-distance commuting, and visiting relatives; and the individual scenarios included in the daily life category can be secondary scenarios other than those mentioned above.

[0048] Table 3:

[0049]

[0050] Furthermore, the model logic used when fitting each individual scene in the three-level scenario is shown in Table 4.

[0051] Table 4:

[0052]

[0053]

[0054] When obtaining a scene image library by classifying driving information, the single-scene classification system formed in the scene image library can be as follows: Figure 6 As shown in the diagram, the purpose of vehicle use is the same as the aforementioned driving purpose. Figure 6 The single-scene classification system shown can achieve accurate classification and output of a single scene.

[0055] Specifically, outputting a coherent scene includes: obtaining a first output instruction, which is used to output a coherent scene within a target time period; and responding to the first output instruction to output the coherent scene within the target time period. The first output instruction facilitates users in obtaining a coherent scene within a target time period, and makes it easier for users to query vehicle driving information within a specific time period.

[0056] Further, outputting a coherent scene includes: acquiring a second output instruction, the second output instruction being used to output a coherent scene at a target time node; and responding to the second output instruction to output the coherent scene at the target time node. In one embodiment of this application, when outputting a coherent scene at a target time node, the output coherent scene can be: vehicle identification code, output time, output of all single scenes under different categories, and the occurrence time of each single scene. This setting facilitates users' understanding of the vehicle's driving situation at a certain time node. In practical applications, the scene image library can output different coherent scenes according to different output instructions. For example, the scene image library can output all time nodes within a specified single scene, and the scene image library can also proactively output coherent scenes within a preset time period or at preset time nodes according to a pre-set timing function.

[0057] In one embodiment of this application, according to Figure 6 The single-scene classification system shown can output the following coherent scene content after classifying a single scene: vehicle identification code, output time, (Level 1 scene, scene occurrence time), (Level 2 scene, scene occurrence time), (Level 3 scene, scene occurrence time). When outputting Level 3 scenes, according to the single-scene classification system, there can be multiple Level 3 scenes.

[0058] Specifically, multiple scene models are used to fit the source data to obtain multiple single scenes, including: vehicle travel chain analysis, multi-source data inside the cabin, multi-source data outside the cabin analyzing the vehicle's driving trajectory, and user context; and fitting environmental information, points of interest information, dwell time information, destination information, external environment information, internal environment information, and the operator's state information to obtain multiple single scenes. Using multiple scene models to fit the source data allows for broader coverage of single scene recognition. The user context can refer to the user's situation inside the cabin, for example, it can include the relationships between people inside the vehicle (e.g., father and son traveling together) and the operator's state information (e.g., mood).

[0059] The process of using multiple scene models to fit the source data into multiple single scenes also includes: cleaning the source data to obtain target data, and then using multiple scene models to fit the target data into multiple single scenes. The cleaned data may include time information, vehicle identification codes, longitude information, latitude information, and vehicle control information.

[0060] By employing the aforementioned method to establish a coherent scene image library, real-time acquisition and processing of vehicle-to-everything (V2X) data can be achieved. Multiple individual scenes can be identified and categorized according to pre-defined driving information. Based on different received output commands, corresponding coherent scenes can be output. This scene image library enables real-time identification, systematic management, and coherent scene output for V2X scenarios. Furthermore, the systematic setting of scenes facilitates developers in updating and redefining individual scenes and managing the scene image library.

[0061] Figure 3 This is a schematic diagram of a scene recognition device according to one optional embodiment of the present invention. Figure 3As shown, the scene recognition device includes: a first acquisition module 31, used to acquire source data of the vehicle, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data; a fitting module 32, used to perform scene fitting on the source data using a scene model to obtain multiple single scenes, wherein the multiple single scenes include scene information of the vehicle in different driving environments; and a classification module 33, used to classify the multiple single scenes to obtain a scene image library, wherein the scene image library is used to output a coherent scene, wherein the scene image library includes multi-level image units, each level of image unit includes at least one single scene from multiple single scenes, the coherent scene includes at least one level of image units, and the image units of the output coherent scene include at least one single scene.

[0062] Furthermore, the scene recognition device includes: a second acquisition module 34, used to acquire output instructions, the output instructions being used to output a coherent scene; a preprocessing module 35, used to preprocess individual scenes in the coherent scene to be output according to the output instructions, the preprocessing including at least one of the following: verifying, evaluating, or optimizing individual scenes; and an output module 36, the output module being used to output the coherent scene.

[0063] The principle behind the above scene recognition device outputting a continuous scene is as follows: Figure 4 As shown, after fitting multiple single scenes, the fitting module 32 (i.e., the scene recognition module shown in the figure) fits and obtains them. Then, the classification module 33 (i.e., the scene aggregation module shown in the figure) classifies the multiple single scenes. After classification, the multiple single scenes are under different branches of the single scene classification system. According to different categories, a coherent scene is output. The coherent scene can include multiple single scenes of different classifications.

[0064] According to another specific embodiment of this application, a computer-readable storage medium is provided, which includes a stored program, wherein the program executes the above-described method when it runs.

[0065] Specifically, the program execution steps are as follows:

[0066] S1: Obtain the vehicle's source data, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data;

[0067] S2: Use a scene model to fit the source data to obtain multiple single scenes, which include scene information of the vehicle in different driving environments;

[0068] S3: Classify and process multiple single scenes to obtain a scene image library. The scene image library is used to output coherent scenes. The scene image library includes multi-level image units. Each level of image unit includes at least one single scene from multiple single scenes. A coherent scene includes at least one level of image units. The image units of the output coherent scene include at least one single scene.

[0069] According to another specific embodiment of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute the above-described method through the computer program.

[0070] According to another specific embodiment of this application, a scene recognition engine is provided. The engine architecture mainly includes data access, a streaming computing engine cluster, a task management and centralized scheduling module, and a model library supporting active and passive output. Figure 5 As shown, the scene recognition engine is used to implement functions such as source data acquisition, scene modeling, scene aggregation, task scheduling management, scene evaluation, optimization, and output. Source data acquisition refers to the aforementioned steps of obtaining vehicle source data. Scene modeling involves fitting scene models to the source data to obtain multiple individual scenes. Scene aggregation refers to classifying and processing multiple individual scenes to obtain a scene image library. Task scheduling management refers to configuring scene attributes for each individual scene, where scene attributes are used to retrieve the corresponding individual scene. Scene evaluation, optimization, and output refer to verifying, evaluating, and optimizing individual scenes.

[0071] According to another specific embodiment of this application, a software architecture is provided, such as... Figure 7 As shown, from bottom to top, the layers are: the basic layer for data access and storage, the real-time / offline computing layer (i.e., the technology layer) that supports complex algorithms and modeling, and the application layer for back-end output.

[0072] For ease of description, spatial relative terms such as "above," "on top of," "on the upper surface of," "above," etc., are used herein to describe the spatial positional relationship of a device or feature as shown in the figures to other devices or features. It should be understood that spatial relative terms are intended to encompass different orientations in use or operation beyond the orientation of the device as described in the figures. For example, if the device in the figures were inverted, a device described as "above" or "on top of" other devices or structures would subsequently be positioned as "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below." The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatial relative descriptions used herein will be interpreted accordingly.

[0073] In addition to the above, it should be noted that the terms "one embodiment," "another embodiment," and "embodiment" used in this specification refer to specific features, structures, or characteristics described in connection with that embodiment, which are included in at least one embodiment described in the general description of this application. The appearance of the same expression in multiple places in the specification does not necessarily refer to the same embodiment. Furthermore, when a specific feature, structure, or characteristic is described in connection with any embodiment, the intention is to suggest that implementing such a feature, structure, or characteristic in conjunction with other embodiments also falls within the scope of this invention.

[0074] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0075] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for establishing a coherent scene image library, characterized in that, include: Acquire source data of the vehicle, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data of the vehicle; The source data is fitted with a scene model to obtain multiple single scenes, wherein the multiple single scenes include scene information of the vehicle in different driving environments; Multiple single scenes are classified and processed to obtain a scene image library. The scene image library is used to output a coherent scene. The scene image library includes a multi-level image unit. Each level of the image unit includes at least one single scene from multiple single scenes. The coherent scene includes at least one level of the image unit. The image unit of the output coherent scene includes at least one single scene. Configure scene attributes for each of the single scenes. The scene attributes are used to retrieve the corresponding single scene. The scene attributes include at least one of the following: storage address, name, status, running mode, running status, running address, creation time, operable items, and logs of the single scene. The classification processing of multiple single scenarios includes: classifying multiple single scenarios according to the vehicle's driving information, with each single scenario in each category being assigned to an image unit, wherein the driving information includes at least one of the following: the vehicle's driving stage, the vehicle's driving purpose, the vehicle's in-cabin driving scenario, and the driving behavior of the driver operating the vehicle.

2. The method for establishing a coherent scene image library according to claim 1, characterized in that, Output the coherent scene, including: Obtain a first output instruction, which is used to output the continuous scene within the target time period; In response to the first output instruction, the continuous scene within the target time period is output.

3. The method for establishing a coherent scene image library according to claim 1, characterized in that, Output the coherent scene, including: Obtain a second output instruction, which is used to output the continuous scene at the target time node; In response to the second output instruction, the continuous scene at the target time node is output.

4. The method for establishing a coherent scene image library according to claim 1, characterized in that, Multiple scene models are used to fit the source data to obtain multiple single scenes, including: Based on the vehicle's travel chain, in-cabin multi-source data, and out-of-cabin multi-source data, the vehicle's driving trajectory and user context are analyzed. By combining environmental information, points of interest information, dwell time information, destination information, external environment information, internal environment information, and the state information of the operator operating the vehicle at the locations along the driving trajectory, multiple single scenes are obtained.

5. A scene recognition device, characterized in that, The device includes: The first acquisition module is used to acquire source data of the vehicle, wherein the source data includes at least one of the following: vehicle network data, map data, image data, audio data, and environmental data of the vehicle; The fitting module uses a scene model to fit the source data to obtain multiple single scenes, wherein the multiple single scenes include scene information of the vehicle in different driving environments; A classification module is used to classify and process multiple single scenes to obtain a scene image library. The scene image library is used to output a coherent scene. The scene image library includes multi-level image units. Each level of the image unit includes at least one single scene from multiple single scenes. The coherent scene includes at least one level of the image unit. The image units of the output coherent scene include at least one single scene. Configure scene attributes for each of the single scenes. The scene attributes are used to retrieve the corresponding single scene. The scene attributes include at least one of the following: storage address, name, status, running mode, running status, running address, creation time, operable items, and logs of the single scene. The classification processing of multiple single scenarios includes: classifying multiple single scenarios according to the vehicle's driving information, with each single scenario in each category being assigned to an image unit, wherein the driving information includes at least one of the following: the vehicle's driving stage, the vehicle's driving purpose, the vehicle's in-cabin driving scenario, and the driving behavior of the driver operating the vehicle.

6. The scene recognition device according to claim 5, characterized in that, The scene recognition device includes: The second acquisition module is used to acquire output instructions, which are used to output the continuous scene. The preprocessing module is used to preprocess the single scene in the continuous scene to be output according to the output instruction. The preprocessing includes at least one of the following: verifying, evaluating, and optimizing the single scene. An output module is used to output the continuous scene.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 4.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 4 through the computer program.

Images