Vehicle-mounted data processing method and device, vehicle, medium and program product

Abstract

The invention provides a vehicle-mounted data processing method and device, a vehicle, a medium and a program product, and relates to the field of vehicles using the artificial intelligence technology, and the method comprises the steps: obtaining vehicle-mounted data of the vehicle, carrying out the automatic processing of the vehicle-mounted data through a large model, and obtaining a processing result, the processing result comprises the vehicle-mounted label and / or the scene library file for simulating the vehicle driving process, and compared with a manual processing mode, the processing efficiency of the vehicle-mounted data is improved through a large-model automatic processing mode.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology using artificial intelligence, and more particularly to a method, device, vehicle, medium, and program product for processing vehicle-mounted data. Background Art

[0002] For intelligent driving, data spans the entire lifecycle, from R&D and testing to mass production and operational maintenance. Vehicles generate a large amount of onboard data during use. Currently, this data is primarily processed manually to obtain useful information for subsequent production stages. However, manual processing is inefficient. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a method, device, vehicle, medium and program product for processing in-vehicle data.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for processing vehicle-mounted data is provided, the method comprising: Obtain vehicle-mounted data; The vehicle-mounted data is processed by a large model to obtain a processing result, wherein the processing result includes an on-board label and / or a scenario library file, the on-board label includes a label of the vehicle-mounted data in each of at least two preset scenarios, and the scenario library file is used to simulate the vehicle driving process.

[0005] Optionally, when the processing result includes the vehicle label, the large model obtains the vehicle label in the following manner: Identifying the vehicle-borne data to obtain an identification result; The recognition result is labeled according to the at least two preset scenarios to obtain the vehicle-mounted label.

[0006] Optionally, the data types of the vehicle-borne data are at least two, and labeling the recognition result according to the at least two preset scene categories to obtain the vehicle-borne label includes: Labeling the recognition results according to the at least two preset scenarios to obtain an intermediate label corresponding to each type of the at least two types of vehicle-borne data in each of the preset scenarios; The vehicle-mounted tag is determined according to the intermediate tag.

[0007] Optionally, determining the vehicle-mounted tag according to the intermediate tag includes: If the intermediate tags of the at least two types of vehicle-borne data are the same in the same preset scenario, determining the intermediate tag of any one of the vehicle-borne data as the vehicle-borne tag in the preset scenario; or, when the intermediate labels of the at least two types of vehicle-borne data under the same preset scenario are different, determining the confidence level of each intermediate label among the intermediate labels of the at least two types of vehicle-borne data under the same preset scenario; According to at least two confidence levels, one of at least two intermediate tags is determined as the vehicle-mounted tag.

[0008] Optionally, when the processing result includes the scene library file, the large model obtains the scene library file in the following manner: identifying the vehicle-borne data to obtain a recognition result; According to the recognition result, the scene library file is obtained.

[0009] Optionally, the method further includes: Converting the format of the recognition result into a preset format that matches the scene library; The step of obtaining the scene library file according to the recognition result includes: The scene library file is obtained according to the recognition result of the preset format.

[0010] Optionally, the acquiring of vehicle-mounted data includes: The vehicle-borne data is acquired through a vehicle-borne data acquisition device on the vehicle, wherein the vehicle-borne data acquisition device is connected to the large model through a communication protocol.

[0011] Optionally, the vehicle-mounted data includes at least one of the following: images captured by an imaging device on the vehicle, sensor data captured by sensors on the vehicle, and driving data of the vehicle.

[0012] Optionally, when the processing result includes the on-board label, the preset scene includes at least two of the following: a road scene, a facility scene, a target scene, a self-vehicle scene, and an environmental scene, wherein the road scene is used to describe the road information of the vehicle's location, the facility scene is used to describe the public facility information of the vehicle's location, the target scene is used to describe the object information and / or pedestrian information around the vehicle, the self-vehicle scene is used to describe the vehicle parameters of the vehicle, and the environmental scene is used to describe the environmental information of the vehicle.

[0013] According to a second aspect of an embodiment of the present disclosure, a device for processing vehicle-mounted data is provided, the device comprising: An acquisition module is configured to acquire vehicle-mounted data of a vehicle; A processing module is configured to process the in-vehicle data through a large model to obtain a processing result, wherein the processing result includes an in-vehicle label and / or a scenario library file, the in-vehicle label includes a label of the in-vehicle data in each of at least two preset scenarios, and the scenario library file is used to simulate the vehicle driving process.

[0014] According to a third aspect of an embodiment of the present disclosure, there is provided a vehicle, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the steps of the method described in the first aspect when executing instructions.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method for processing vehicle-mounted data provided by the first aspect of the present disclosure are implemented.

[0016] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0017] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: obtaining the on-board data of the vehicle, automatically processing the on-board data through a large model, and obtaining a processing result, wherein the processing result includes an on-board label and / or a scene library file that simulates the vehicle driving process. Compared with the manual processing method, the automatic processing method of the large model improves the processing efficiency of the on-board data. In the case where the processing result includes an on-board label, automatic labeling of the on-board data can be achieved. The on-board label includes a label of the on-board data in each of at least two preset scenes. By labeling at least two preset scenes, the on-board data can be more comprehensively labeled, and the on-board labels obtained thereby can provide richer scene information. In the case where the processing result includes a scene library file, the scene library file can be automatically created, which improves the efficiency of scene library file generation compared with the manual method.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0020] Figure 1The figure is a flowchart of a method for processing vehicle-mounted data according to an exemplary embodiment.

[0021] Figure 2 The figure is a flowchart of a method for processing vehicle-mounted data according to another exemplary embodiment.

[0022] Figure 3 The figure is a block diagram of a vehicle-mounted data processing device according to an exemplary embodiment.

[0023] Figure 4 is a block diagram of a vehicle according to an exemplary embodiment.

[0024] Figure 5 The figure is a block diagram of a server showing a method for processing vehicle-mounted data according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0026] For intelligent driving, data spans the entire lifecycle, from R&D and testing to mass production and operational maintenance. With the rapid increase in the number and variety of sensors on vehicles and the implementation of Advanced Driver Assistance Systems (ADAS) and intelligent driving technologies, the amount of in-vehicle data generated is also growing exponentially. Data-driven automotive evolution has become a consensus within the industry. Massive amounts of in-vehicle data are merely the foundation. Currently, this data is manually processed to extract valuable information before it can be used in subsequent production stages. For example, this data needs to be labeled for iteration and generalization of intelligent driving models. Currently, in-vehicle data labeling is primarily done manually. For example, during the in-vehicle data collection process, personnel use data collection tools to label POIs (Points of Interest) in the data in real time as it is recorded. However, manual labeling is inefficient and cannot cope with the massive and complex volume of in-vehicle data. Furthermore, manual labeling is costly and has significant limitations. For another example, it is necessary to manually select relevant information from the vehicle-mounted data and manually create a scenario library file, which is used to simulate and restore the vehicle's driving process.

[0027] In order to improve the labeling efficiency, the related art provides an automatic labeling method, which labels the collected vehicle-mounted data with POIs according to the focus of the intelligent driving model. For example, the intelligent driving model focuses on a certain target object (such as other vehicles) during driving, and labels the target object that the model focuses on in the vehicle-mounted data, so as to facilitate the iteration of the intelligent driving model based on the labeled vehicle-mounted data. However, only the targets that the intelligent driving model focuses on are labeled. As driving needs change, when the vehicle's intelligent driving technology needs to focus on more targets, these vehicle-mounted data do not have the new targets marked. Then, when the vehicle-mounted data is applied to a new driving scenario, the vehicle-mounted data needs to be re-labeled to mark the targets that the new driving scenario focuses on.

[0028] To solve the above problems, the present disclosure provides a method for processing vehicle data. Figure 1 The vehicle data processing method can be applied to Figure 3 The vehicle data processing device 300 shown, Figure 4 The vehicle 600 shown, Figure 5 The server 1900, computer program product and computer readable storage medium connected to the vehicle are shown. In this embodiment, the application to the vehicle is taken as an example. Figure 1 The process shown in FIG. 1 is described in detail. The method for processing vehicle data may include the following steps: Step S110: Acquire vehicle-mounted data.

[0029] On-board data can include data generated while the vehicle is in motion or when the vehicle is stationary. This data can be collected using an on-board data acquisition device. For example, the on-board data acquisition device includes at least one of the following: an imaging device or a sensor. The imaging device can be an electromagnetic spectrum imaging device, an acoustic imaging device, or an optoelectronic imaging device. The optoelectronic imaging device can be a camera.

[0030] The vehicle-mounted data includes at least one of the following: images captured by the imaging device on the vehicle, sensor data collected by the sensors on the vehicle, and driving data of the vehicle. The camera on the vehicle can be a camera configured on the vehicle to monitor the vehicle's surroundings, or a driving recorder installed on the vehicle, and the image can be a photo or video captured by the camera. The sensors on the vehicle can be millimeter-wave radar, lidar, etc. Vehicle driving data refers to data generated during the use of the vehicle. For example, driving data includes vehicle speed, accelerator pedal status, brake pedal status, etc.

[0031] In one embodiment, the vehicle-mounted data can be obtained via the vehicle's internal links. For example, the vehicle's own vehicle-mounted data can be obtained via the vehicle's internal CAN bus, Ethernet bus, etc. For example, the vehicle-mounted data includes images captured by a camera on the vehicle. The camera captures images of the vehicle's environment, and the vehicle's control system obtains the images captured by the camera via the Ethernet bus.

[0032] In another embodiment, other devices communicating with the vehicle acquire onboard data and transmit the data to the vehicle, thereby enabling the vehicle to obtain the onboard data. For example, the vehicle connects to other devices via V2X (Vehicle-to-Everything) communication technology. These other devices may be roadside equipment such as electronic eyes, traffic lights, and roadside units, or other vehicles connected to the vehicle.

[0033] Step S120: Process the vehicle-mounted data through a large model to obtain a processing result, wherein the processing result includes an on-board label and / or a scene library file, the on-board label includes a label of the vehicle-mounted data in each of at least two preset scenes, and the scene library file is used to simulate the vehicle driving process.

[0034] By automatically processing the vehicle data through a large model, the processing results can be automatically generated.

[0035] Optionally, the large model is connected to the vehicle-mounted data acquisition device via a communication protocol. Through this connection, the large model receives the vehicle-mounted data from the vehicle-mounted data acquisition device, and automatically processes the vehicle-mounted data to generate processing results.

[0036] Optionally, the large model can be deployed on the vehicle or on a server connected to the vehicle.

[0037] The method for processing vehicle-mounted data provided in this embodiment obtains the vehicle-mounted data, automatically processes the vehicle-mounted data through a large model, and obtains a processing result. The processing result includes an on-board label and / or a scene library file that simulates the vehicle driving process. Compared with the manual processing method, the automatic processing method through the large model improves the processing efficiency of the vehicle-mounted data. In the case where the processing result includes an on-board label, automatic labeling of the vehicle-mounted data can be achieved. The on-board label includes a label of the vehicle-mounted data in each of at least two preset scenes. By labeling at least two preset scenes, the vehicle-mounted data can be more comprehensively labeled. The on-board labels obtained thereby can provide richer scene information. In the case where the processing result includes a scene library file, the scene library file can be automatically created, which improves the efficiency of scene library file generation compared with the manual method.

[0038] In the case where the processing result includes the in-vehicle label, the in-vehicle label for the in-vehicle data is obtained through the large model, wherein the in-vehicle label includes a label of the in-vehicle data in each of at least two preset scenarios.

[0039] The vehicle data is automatically labeled through the large model to obtain the vehicle label. The vehicle label is the label of the vehicle data in each preset scenario in at least two preset scenarios, which can be used to label the vehicle data more comprehensively. Exemplarily, the preset scenes include at least two of the following: road scenes, facility scenes, target scenes, self-vehicle scenes, and environmental scenes, wherein the road scene is used to describe the road information at the location of the vehicle, for example, the described road information includes ramps, number of lanes, and road types; the facility scene is used to describe the public facility information at the location of the vehicle, for example, public facility information may include roadside facilities, signs, logos, lane lines, and traffic lights; the target scene is used to describe object information and / or pedestrian information around the vehicle, and the object information may be other vehicles, piles of rocks, piles of earth, and other obstacles during driving; the self-vehicle scene is used to describe the vehicle parameters of the vehicle, for example, vehicle parameters may be gear position, speed, acceleration, steering wheel angle, throttle opening, brake opening, pedal status, throttle status, etc.; the environmental scene is used to describe the environmental information of the vehicle, for example, environmental information may be green belts, weather, temperature, visibility, etc.

[0040] In one embodiment, the large model can be deployed on a vehicle. The vehicle calls the local large model and uses it to obtain onboard labels for the vehicle data. For example, the vehicle calls the local large model and then inputs the vehicle data into the onboard large model. The onboard large model automatically labels the vehicle data and obtains the onboard labels output by the onboard large model. In this embodiment, the large model is deployed on the vehicle. When the onboard large model is needed for labeling, it can be quickly called upon to quickly label the vehicle data, thereby improving the labeling speed of the vehicle data.

[0041] In another embodiment, the large model can be deployed on a server connected to the vehicle. The vehicle retrieves the large model from the server and uses it to obtain onboard labels for the vehicle data. For example, when labeling is required, the vehicle calls the onboard large model from the server, then inputs the vehicle data into the onboard large model. The onboard large model automatically labels the vehicle data and outputs the onboard labels. In this embodiment, deploying the large model on the server can reduce the vehicle's local storage space.

[0042] The method for processing on-board data provided in this embodiment obtains the on-board data of the vehicle, obtains on-board labels for the on-board data through a large model, and realizes automatic labeling of the on-board data. The on-board labels include labels for the on-board data in each of at least two preset scenes. By labeling at least two preset scenes, the on-board data can be more comprehensively labeled, and the on-board labels obtained can provide richer scene information. Compared with the manual labeling method, this embodiment automatically labels through a large model, thereby improving the production cost and efficiency of the labels. Compared with the aforementioned method of only labeling a certain target object that the intelligent driving model pays attention to during driving, this embodiment can label the on-board data in at least two preset scenes, and can provide richer and more comprehensive labels, so that the on-board labels are not only applicable to the current intelligent driving model, but also to richer scenes.

[0043] Exemplarily, the large model may obtain the vehicle label by: identifying the vehicle data to obtain a recognition result, and then labeling the recognition result according to the at least two preset scenarios to obtain the vehicle label.

[0044] The on-board data is identified to obtain an identification result. For example, when the on-board data includes an image captured by a camera on the vehicle, the image is identified to obtain text describing the image. It is not difficult to understand that the text describing the image is the identification result. When the on-board data includes sensor data collected by sensors on the vehicle, the sensor data is identified to obtain scene information carried by the sensor data. For example, if the sensor includes a millimeter-wave radar, the scene information carried by the sensor data may be the distance to an obstacle, relative speed, etc. measured by the millimeter-wave radar. When the on-board data includes driving data of the vehicle, the driving data is identified to obtain the vehicle state represented by the driving data. For example, if the driving data is collected data of the accelerator pedal, the driving data represents whether the vehicle state is in a braking state or a non-braking state.

[0045] Optionally, the large model may include a vision-language model (VLM), a visual large model, a multimodal large model, etc.

[0046] Optionally, when the data type of the on-board data is at least two, the recognition result is labeled according to the at least two preset scene categories to obtain the on-board label. This can be done as follows: first, the recognition result is labeled according to the at least two preset scenes to obtain the intermediate label corresponding to each of the at least two types of on-board data in each of the preset scenes. For example, if the at least two preset scenes are road scene A1 and facility scene A2, and the types of on-board data are image B1 and sensor data B2, then the intermediate labels obtained include the label of image B1 in road scene A1, the label of sensor data B2 in road scene A1, the label of image B1 in facility scene A2, and the label of sensor data B2 in facility scene A2. The on-board label is then determined based on the intermediate labels. In one case, if the intermediate labels of the at least two types of on-board data in the same preset scene are the same, the intermediate label of any one of the on-board data is determined as the on-board label in the preset scene. For example, for the same preset scene road scene A1, the label of image B1 is cement road, and the label of sensor data B2 is cement road. If the two labels are the same, it is considered that the labels obtained through both image B1 and sensor data B2 are correct, and any one of the labels is determined as the vehicle-mounted label under road scene A1.

[0047] In another case, when the intermediate labels of the at least two types of vehicle-borne data in the same preset scene are different, the confidence of each intermediate label in the intermediate labels of the at least two types of vehicle-borne data in the same preset scene is determined. According to the at least two confidences, one of the at least two intermediate labels is determined as the vehicle-borne label. It can be that the intermediate label corresponding to the largest confidence is determined from the at least two confidences as the vehicle-borne label. For example, continuing with the above example, for the same preset scene road scene A1, the label of the image B1 is cement road, and the label of the sensor data B2 is asphalt road. The two labels are different, then the first confidence of 90% corresponding to the cement road and the second confidence of 70% corresponding to the asphalt road are obtained. Of the two confidences, the intermediate label corresponding to the larger confidence is selected as the vehicle-borne label, that is, the cement road is selected as the label of the road scene.

[0048] Label all preset scenes in the above manner to obtain the final vehicle labels.

[0049] For example, the preset scenarios include road scenarios, facility scenarios, target scenarios, vehicle scenarios, and environmental scenarios. Each preset scenario includes at least one classification indicator. For example, the road scenario includes classification indicators such as slope, number of lanes, road surface material, road curvature, and road type. The classification indicators included in the facility scenario, target scenario, vehicle scenario, and environmental scenario are shown in the following table. Table 1 shows an example of a vehicle label obtained by the vehicle data processing method provided by the present disclosure, as shown in Table 1: Table 1

[0050] When the processing result includes a scene library file, the large model obtains the scene library file by: performing recognition on the vehicle data to obtain a recognition result, and then obtaining the scene library file based on the recognition result.

[0051] The on-board data is identified to obtain an identification result. For example, when the on-board data includes an image captured by a camera on the vehicle, the image is identified to obtain text describing the image. It is not difficult to understand that the text describing the image is the identification result. When the on-board data includes sensor data collected by sensors on the vehicle, the sensor data is identified to obtain scene information carried by the sensor data. For example, if the sensor includes a millimeter-wave radar, the scene information carried by the sensor data may be the distance to an obstacle, relative speed, etc. measured by the millimeter-wave radar. When the on-board data includes driving data of the vehicle, the driving data is identified to obtain the vehicle state represented by the driving data. For example, if the driving data is collected data of the accelerator pedal, the driving data represents whether the vehicle state is in a braking state or a non-braking state.

[0052] Based on the recognition results, a scenario library for the vehicle is constructed, wherein the scenario library is used to simulate the vehicle's driving process. The scenario library can be used to simulate and restore the vehicle's driving process to replay the vehicle's driving process.

[0053] Optionally, the format of the recognition result can be converted into a preset format that matches the scene library, and the scene library for the vehicle can be constructed based on the recognition result in the preset format. For example, the preset format includes XML format with a suffix of .xosc.

[0054] Since the in-vehicle data obtained by the present invention is relatively rich, and the recognition results obtained based on the in-vehicle data are also based on at least two preset scenarios, the recognition results can have richer details. The scene library constructed using the recognition results can be used for simulation to restore the vehicle driving scene with a high degree of restoration.

[0055] Optionally, the present disclosure provides a method for processing vehicle-mounted data, see Figure 2 , the method comprising: Step S210: Acquire vehicle data.

[0056] The vehicle-mounted data may include at least one of the following: images captured by a camera on the vehicle, sensor data collected by sensors on the vehicle, and driving data of the vehicle.

[0057] When the in-vehicle data includes images, the images may be collected by seven cameras installed around the vehicle and four surround-view cameras.

[0058] Step S220: Identify the vehicle-borne data using the large model to obtain a recognition result.

[0059] Step S230: Obtain the vehicle tag based on the recognition result using the large model.

[0060] Step S240: Output the vehicle tag.

[0061] Optionally, the vehicle labels output by the large model are obtained.

[0062] Step S250: Build a scene library.

[0063] Build a scene library based on the recognition results.

[0064] Among them, steps S210 to S250 refer to the above steps and are not repeated here.

[0065] Based on the same inventive concept, the present disclosure provides a vehicle data processing device 300, see Figure 3 The vehicle data processing device 300 includes: The acquisition module 310 is configured to acquire vehicle-mounted data of the vehicle; The processing module 320 is configured to process the in-vehicle data through a large model to obtain a processing result, wherein the processing result includes an in-vehicle label and / or a scenario library file, the in-vehicle label includes a label of the in-vehicle data in each of at least two preset scenarios, and the scenario library file is used to simulate the vehicle driving process.

[0066] Optionally, when the processing result includes the vehicle-mounted tag, the processing module 320 includes: A first recognition module is configured to recognize the vehicle-borne data and obtain a recognition result; The labeling module is configured to label the recognition result according to the at least two preset scenarios to obtain the vehicle-mounted label.

[0067] Optionally, the vehicle-borne data has at least two data types, and the labeling module includes: an intermediate label marking module configured to mark the recognition result according to the at least two preset scenarios, and obtain an intermediate label corresponding to each type of the at least two types of vehicle-borne data under each of the preset scenarios; The vehicle-mounted label marking module is configured to determine the vehicle-mounted label according to the intermediate label.

[0068] Optionally, the vehicle label marking module includes: The first vehicle-mounted label marking module is configured to, when the intermediate labels of the at least two types of vehicle-mounted data in the same preset scenario are the same, determine the intermediate label of any one of the vehicle-mounted data as the vehicle-mounted label in the preset scenario.

[0069] Optionally, the vehicle label marking module includes: a confidence acquisition module configured to determine the confidence of each intermediate label of the at least two types of vehicle-borne data in the same preset scenario when the intermediate labels of the at least two types of vehicle-borne data in the same preset scenario are different; The second vehicle-mounted label marking module is configured to determine one of the at least two intermediate labels as the vehicle-mounted label based on at least two confidence levels.

[0070] Optionally, the second vehicle-mounted label marking module includes: The vehicle-mounted label determination module is configured to determine an intermediate label corresponding to the maximum confidence level from the at least two confidence levels as the vehicle-mounted label.

[0071] Optionally, the processing module 320 includes: A second recognition module is configured to recognize the vehicle-borne data and obtain a recognition result; The building module is configured to obtain a scene library file according to the recognition result.

[0072] Optionally, the vehicle data processing device 300 further includes: a conversion module, configured to convert the format of the recognition result into a preset format matching the scene library; The building blocks include: The scene library construction module is configured to obtain the scene library file according to the recognition result of the preset format.

[0073] Optionally, the large model is deployed on the vehicle or a server connected to the vehicle.

[0074] Optionally, the vehicle-mounted data includes at least one of the following: images captured by an imaging device on the vehicle, sensor data captured by sensors on the vehicle, and driving data of the vehicle.

[0075] Optionally, when the processing result includes the on-board label, the preset scene includes at least two of the following: a road scene, a facility scene, a target scene, a self-vehicle scene, and an environmental scene, wherein the road scene is used to describe the road information of the vehicle's location, the facility scene is used to describe the public facility information of the vehicle's location, the target scene is used to describe the object information and / or pedestrian information around the vehicle, the self-vehicle scene is used to describe the vehicle parameters of the vehicle, and the environmental scene is used to describe the environmental information of the vehicle.

[0076] Regarding the vehicle-mounted data processing device 300 in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0077] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon. When the program instructions are executed by a processor, the steps of the vehicle-mounted data processing method provided by the present disclosure are implemented.

[0078] Figure 4 6 is a block diagram illustrating a vehicle 600 according to an exemplary embodiment. For example, vehicle 600 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or another type of vehicle. Vehicle 600 may be an intelligent driving vehicle, a semi-intelligent driving vehicle, or a non-intelligent driving vehicle.

[0079] Please refer to Figure 4 Vehicle 600 may include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. Vehicle 600 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of vehicle 600 may be interconnected via wired or wireless means.

[0080] In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, a navigation system, and the like.

[0081] The perception system 620 may include several sensors for sensing information about the environment surrounding the vehicle 600. For example, the perception system 620 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera.

[0082] The decision control system 630 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0083] The drive system 640 may include components that provide power to the vehicle 600. In one embodiment, the drive system 640 may include an engine, an energy source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination thereof. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0084] Some or all functions of the vehicle 600 are controlled by a computing platform 650. The computing platform 650 may include at least one processor 651 and a memory 652. The processor 651 may execute instructions 653 stored in the memory 652.

[0085] The processor 651 can be any conventional processor, such as a commercially available CPU. The processor can also include a graphics processor (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0086] The memory 652 may be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0087] In addition to instructions 653 , memory 652 may also store data, such as road maps, route information, and vehicle location, direction, speed, etc. The data stored in memory 652 may be used by computing platform 650 .

[0088] In the embodiment of the present disclosure, the processor 651 may execute the instruction 653 to complete all or part of the steps of the above-mentioned method for processing vehicle data.

[0089] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device, and has a code portion for executing the above-mentioned method for processing in-vehicle data when executed by the programmable device.

[0090] Figure 5 This is a block diagram of a server for a method for processing vehicle-mounted data according to an exemplary embodiment. Figure 5 The server 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as applications, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.

[0091] The server 1900 may also include a power supply component 1926 configured to perform power management of the server 1900, a wired or wireless network interface 1950 configured to connect the server 1900 to a network, and an input / output interface 1958. The server 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2000. TM , MacOS X TM , Unix TM , Linux TM , FreeBSD TM or similar.

[0092] A large model is deployed on the server, and the server can connect to the vehicle through the wireless network interface 1950 to obtain the vehicle's on-board data, and label the on-board data according to the local large model to obtain an on-board label, which includes the label of the on-board data in each of at least two preset scenarios.

[0093] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented through electronic hardware, computer software, or a combination of both. Whether such functions are implemented through hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0094] Furthermore, the word "exemplary" is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as advantageous over other aspects or designs. Rather, the use of the word exemplary is intended to present concepts in a concrete manner. As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X applies to A or B" is intended to mean any of the natural inclusive permutations. That is, if X applies to A; X applies to B; or X applies to both A and B, then "X applies to A or B" satisfies any of the aforementioned instances. Furthermore, the articles "a" and "an," as used in this application and the appended claims, are generally understood to mean "one or more," unless otherwise specified or clear from the context to refer to the singular form.

[0095] Likewise, although the present disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. The present disclosure includes all such modifications and variations and is limited only by the scope of the claims. With particular regard to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, terms used to describe such components are intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if not structurally equivalent to the disclosed structure. In addition, although particular features of the present disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations as may be desired and advantageous for any given or particular application. Furthermore, to the extent that the terms "include," "have," "have," "have," or variations thereof are used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term "comprising."

[0096] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the appended claims.

[0097] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0098] Although terms such as "first", "second" and "third" may be used herein to describe various components, parts, regions, layers or sections, these components, parts, regions, layers or sections are not limited to these terms. On the contrary, these terms are only used to distinguish one component, part, region, layer or section from another component, part, region, layer or section. Therefore, without departing from the teachings of each example, the first component, part, region, layer or section mentioned in the examples described herein may also be referred to as the second component, part, region, layer or section. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" can explicitly or implicitly include at least one such feature. In the description herein, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically defined.

Claims

1. A method for processing vehicle-mounted data, characterized in that: The method comprises: Obtain vehicle-mounted data; The vehicle-mounted data is processed by a large model to obtain a processing result, wherein the processing result includes an on-board label and / or a scenario library file, the on-board label includes a label of the vehicle-mounted data in each of at least two preset scenarios, and the scenario library file is used to simulate the vehicle driving process.

2. The method according to claim 1, characterized in that When the processing result includes the vehicle tag, the large model obtains the vehicle tag in the following manner: Identifying the vehicle-borne data to obtain an identification result; The recognition result is labeled according to the at least two preset scenarios to obtain the vehicle-mounted label.

3. The method according to claim 2, characterized in that The data types of the vehicle-borne data are at least two, and labeling the recognition result according to the at least two preset scene categories to obtain the vehicle-borne label includes: Labeling the recognition result according to the at least two preset scenarios to obtain an intermediate label corresponding to each type of vehicle-borne data in the at least two types of vehicle-borne data under each of the preset scenarios; The vehicle-mounted tag is determined according to the intermediate tag.

4. The method according to claim 3, characterized in that The determining the vehicle-mounted tag according to the intermediate tag includes: If the intermediate labels of the at least two types of vehicle-borne data are the same in the same preset scenario, determining the intermediate label of any one of the vehicle-borne data as the vehicle-borne label in the preset scenario; or When the intermediate labels of the at least two types of vehicle-borne data under the same preset scenario are different, determining the confidence level of each intermediate label among the intermediate labels of the at least two types of vehicle-borne data under the same preset scenario; According to at least two confidence levels, one of at least two intermediate tags is determined as the vehicle-mounted tag.

5. The method according to claim 1, wherein When the processing result includes the scene library file, the large model obtains the scene library file in the following manner: Identifying the vehicle-borne data to obtain an identification result; The scene library file is obtained according to the recognition result.

6. The method according to claim 5, characterized in that The method further comprises: Converting the format of the recognition result into a preset format that matches the scene library; The step of obtaining the scene library file according to the recognition result includes: The scene library file is obtained according to the recognition result of the preset format.

7. The method according to claim 1, characterized in that The obtaining of vehicle-mounted data includes: The vehicle-borne data is acquired through a vehicle-borne data acquisition device on the vehicle, wherein the vehicle-borne data acquisition device is connected to the large model through a communication protocol.

8. The method according to any one of claims 1 to 7, characterized in that The vehicle-mounted data includes at least one of the following: images collected by an imaging device on the vehicle, sensor data collected by sensors on the vehicle, and driving data of the vehicle.

9. The method according to any one of claims 1 to 7, characterized in that In the case where the processing result includes the on-board label, the preset scene includes at least two of the following: a road scene, a facility scene, a target scene, a self-vehicle scene, and an environmental scene, wherein the road scene is used to describe the road information at the location of the vehicle, the facility scene is used to describe the public facility information at the location of the vehicle, the target scene is used to describe the object information and / or pedestrian information around the vehicle, the self-vehicle scene is used to describe the vehicle parameters of the vehicle, and the environmental scene is used to describe the environmental information of the vehicle.

10. A vehicle-mounted data processing device, characterized in that: The device comprises: An acquisition module is configured to acquire vehicle-mounted data of a vehicle; A processing module is configured to process the in-vehicle data through a large model to obtain a processing result, wherein the processing result includes an in-vehicle label and / or a scenario library file, the in-vehicle label includes a label of the in-vehicle data in each of at least two preset scenarios, and the scenario library file is used to simulate the vehicle driving process.

11. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the steps of the method according to any one of claims 1 to 9 when executing instructions.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

13. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

Images