Vehicle terminal data processing method, device and electronic equipment based on YTS engine

Abstract

The present application provides a vehicle terminal data processing method, device and electronic device based on the YTS engine, which relates to the field of vehicle data technology and solves the technical problem of low communication efficiency between the server and the vehicle terminal. The method includes: identifying and analyzing the target object, the appearance data of the target object and the appearance time and appearance position of the target object in the rendered driving video data; generating a timeline for the target object according to the appearance time, generating prompt text description data for each appearance time on the timeline according to the target object, appearance data and appearance position, and generating comprehensive text description data for the driving video data based on the timeline and all prompt text description data corresponding to all appearance times; sending the comprehensive text description data to the server through the vehicle terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data.

Description

Technical Field

[0001] The present application relates to the field of vehicle-mounted data technology, and in particular to a vehicle-mounted terminal data processing method, device and electronic equipment based on a YTS engine. Background Art

[0002] At present, the driving recorder is an instrument that records relevant information such as images and sounds while a vehicle is driving. After the driving recorder is installed, the video images and sounds of the entire driving process can be recorded, which can provide evidence for traffic accidents.

[0003] In order for the background server to obtain the driving video content of the vehicle terminal, the vehicle terminal needs to send the driving video to the server. However, the data volume of the driving video is large, which will slow down the data transmission speed and time between the server and the vehicle terminal. As a result, it takes a long time for the server to obtain all the driving video content, which makes the communication efficiency between the server and the vehicle terminal low. Summary of the Invention

[0004] The purpose of the present invention is to provide a vehicle-mounted terminal data processing method, device and electronic equipment based on the YTS engine to solve the technical problem of low communication efficiency between the server and the vehicle-mounted terminal.

[0005] In a first aspect, the present application provides a vehicle terminal data processing method based on the YTS engine, the method comprising:

[0006] Collect driving video data through the vehicle terminal;

[0007] In the process of rendering the driving video data using the YTS engine in the vehicle terminal, identifying and analyzing the target object contained in the rendered driving video data, the appearance data of the target object, and the appearance time and location of the target object in the driving video data;

[0008] A timeline for the target object is generated based on the appearance time, prompt text description data is generated for each appearance time on the timeline based on the target object, the appearance data, and the appearance position, and comprehensive text description data for the driving video data is generated based on the timeline and all the prompt text description data corresponding to all the appearance times; wherein the appearance time corresponds to an appearance prompt text of the target object at a target time point on the timeline, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object;

[0009] The comprehensive text description data is sent to a server via the vehicle-mounted terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data.

[0010] In one possible implementation, the target object includes a road object and a vehicle object; in the process of rendering the driving video data using the YTS engine in the vehicle terminal, after identifying and analyzing the target object contained in the rendered driving video data, the appearance data of the target object, and the appearance time and location of the target object in the driving video data, the method further includes:

[0011] Analyzing the road congestion data of each of the road objects according to the vehicle appearance positions and vehicle appearance times corresponding to all the vehicle objects;

[0012] Determine a number of target vehicle objects around the vehicle terminal according to the vehicle appearance position and vehicle appearance time corresponding to each vehicle object;

[0013] In response to a first selection instruction for a plurality of the road objects, determining a target road object selected corresponding to the first selection instruction from the plurality of the road objects;

[0014] According to the target road congestion data corresponding to the target road object and the several target vehicle objects, several feasible driving schemes of the vehicle-mounted terminal through the target road object and the road passing time corresponding to each feasible driving scheme are analyzed.

[0015] In one possible implementation, after analyzing several feasible driving plans of the vehicle-mounted terminal through the target road object based on the target road congestion data corresponding to the target road object and the several target vehicle objects, the method further includes:

[0016] In response to a second selection instruction for the plurality of feasible driving solutions, determining a target feasible driving solution corresponding to the second selection instruction from the plurality of road objects;

[0017] Determine the relative position of each target vehicle object relative to the vehicle-mounted terminal according to the target vehicle appearance position corresponding to each target vehicle object in the driving video data;

[0018] The driving process prompt information corresponding to the target feasible driving plan is determined and displayed based on the target feasible driving plan, the relative position and the target appearance data corresponding to the several target vehicle objects.

[0019] In one possible implementation, the method further includes:

[0020] Analyzing the environmental data in the driving video data to obtain driving environment data;

[0021] The determining of driving process prompt information corresponding to the target feasible driving scheme according to the target feasible driving scheme, the relative position, and target appearance data corresponding to the plurality of target vehicle objects includes:

[0022] The driving process prompt information corresponding to the target feasible driving plan is determined based on the driving environment data, the target feasible driving plan, the relative position and the target appearance data corresponding to the several target vehicle objects.

[0023] In one possible implementation, the driving environment data includes any one or more of the following:

[0024] Climate data, surrounding road environment, and surrounding pedestrian data.

[0025] In one possible implementation, the server is provided with a specified deep learning model; after the comprehensive text description data is sent to the server via the vehicle-mounted terminal, the method further includes:

[0026] Dynamically adjusting, by the server, a pruning threshold corresponding to the deep learning model according to the weight distribution data of the deep learning model, so that important weights in the weight distribution data are not pruned;

[0027] The comprehensive text description data is analyzed by the target deep learning model after dynamically adjusting the pruning threshold to obtain the video content of the driving video data.

[0028] In one possible implementation, analyzing the comprehensive text description data by the target deep learning model after dynamically adjusting the pruning threshold to obtain the video content of the driving video data includes:

[0029] Analyzing the comprehensive text description data by using the first target deep learning model after dynamically adjusting the pruning threshold to obtain initial video content of the driving video data;

[0030] regularly sampling the initial video content to obtain sampling results, and detecting scene complexity in the initial video content based on the sampling results;

[0031] Predicting future scene change data in the initial video content by machine learning based on historical scene data corresponding to the scene complexity, and adjusting parameters of the first target deep learning model in advance based on the future scene change data to obtain a second target deep learning model after adjusting the parameters;

[0032] The initial video content and the comprehensive text description data are analyzed by the second target deep learning model to obtain the final video content of the driving video data.

[0033] In a second aspect, the present application provides a vehicle-mounted terminal data processing device based on a YTS engine, comprising:

[0034] The acquisition module is used to collect driving video data through the vehicle terminal;

[0035] an identification module for identifying and analyzing, during the process of rendering the driving video data using the YTS engine in the vehicle-mounted terminal, a target object contained in the rendered driving video data, appearance data of the target object, and an appearance time and location of the target object in the driving video data;

[0036] a generation module for generating a timeline for the target object based on the appearance time, generating prompt text description data for each appearance time on the timeline based on the target object, the appearance data, and the appearance position, and generating comprehensive text description data for the driving video data based on the timeline and all the prompt text description data corresponding to all the appearance times; wherein the appearance time corresponds to an appearance prompt text of the target object at a target time point on the timeline, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object;

[0037] The sending module is used to send the comprehensive text description data to the server through the vehicle-mounted terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data.

[0038] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method described in the first aspect above.

[0040] This application brings the following beneficial effects:

[0041] The present application provides a vehicle terminal data processing method, device and electronic device based on the YTS engine, which can collect driving video data through the vehicle terminal; in the process of rendering the driving video data using the YTS engine in the vehicle terminal, identify and analyze the target object, the appearance data of the target object and the appearance time and appearance position of the target object in the rendered driving video data; generate a time axis for the target object according to the appearance time, generate prompt text description data for each appearance time on the time axis according to the target object, the appearance data and the appearance position, and generate comprehensive text description data for the driving video data based on the time axis and all the prompt text description data corresponding to all the appearance times; wherein, the appearance time corresponds to the target time point on the time axis with the appearance prompt text of the target object, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object; send the comprehensive text description data to the server through the vehicle terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data. In this solution, driving video is collected in real time by on-board equipment, and the YTS engine on the on-board terminal is used to perform real-time analysis on the driving video. The key information in the video can be quickly identified. Based on the identified target objects and their related information, the system generates a timeline and creates a specific prompt text description for each target object. This method converts a large amount of unprocessed video data into a compact and meaningful text description, greatly reducing the amount of data. All prompt text descriptions are further integrated to form a comprehensive integrated text description. Since only processed and structured integrated text description data is sent instead of original video data, this greatly reduces the amount of transmitted data, reduces the demand for network bandwidth, improves the communication efficiency between the on-board terminal and the server, and solves the technical problem of low communication efficiency between the server and the on-board terminal.

[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 A flowchart of a vehicle terminal data processing method based on a YTS engine provided in an embodiment of the present application;

[0045] Figure 2 Another flowchart of the vehicle terminal data processing method based on the YTS engine provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of a vehicle-mounted terminal data processing device based on a YTS engine provided in an embodiment of the present application;

[0047] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0049] The terms "including," "having," and any variations thereof, as used in the embodiments of this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0050] Currently, the communication efficiency between the server and the vehicle terminal is low. Based on this, the embodiments of the present application provide a vehicle terminal data processing method, device and electronic device based on the YTS engine, which can solve the technical problem of low communication efficiency between the server and the vehicle terminal.

[0051] The embodiments of the present invention are further described below with reference to the accompanying drawings.

[0052] Figure 1 The flowchart of a vehicle terminal data processing method based on the YTS engine provided in the embodiment of the present application is as follows. Figure 1 As shown, the method includes:

[0053] Step S110: collecting driving video data through the vehicle terminal.

[0054] It should be noted that the YTS (Unity TV Service) engine in this embodiment represents the Unity Visual Rendering Service engine. Unity is a real-time 3D interactive content creation and operation platform. All creators, including those in game development, art, architecture, automotive design, and film and television, use Unity to turn their ideas into reality. The platform provides a complete set of software solutions for creating, operating, and monetizing any real-time interactive 2D and 3D content, supporting platforms including mobile phones, tablets, PCs, game consoles, augmented reality, and virtual reality devices.

[0055] Step S120, in the process of rendering the driving video data using the YTS engine in the vehicle terminal, identifies and analyzes the target object, the appearance data of the target object, and the appearance time and location of the target object in the driving video data contained in the rendered driving video data.

[0056] As an optional implementation, after collecting the raw video data generated by the dashcam, the data is preprocessed, including but not limited to format conversion, resolution adjustment, and noise filtering, to ensure efficient and accurate data processing in subsequent steps. Computer vision techniques (such as deep learning models) are used to detect and classify target objects (such as vehicles, pedestrians, and traffic signs) in each frame. Tracking algorithms (such as Kalman filters or DeepSORT) are employed to track the movement paths of the same target objects in the video. For each identified target object, its appearance features, such as color, shape, and size, are further extracted. The time (corresponding to the video timestamp) and location (calculated using GPS data or relative position within the video frame) of each identified target object in the video are recorded. The collected data is analyzed, which may include statistical analysis and behavioral pattern recognition, to provide deeper insights, such as traffic flow analysis and accident prevention recommendations. The analysis results are overlaid on the original video for rendering, for example, displaying the bounding box, category label, and trajectory of the identified object in the video. Visualization tools can be used to display data analysis results in different dimensions, such as using charts to show traffic flow changes over a specific period of time. Based on user needs, a report containing all the above analysis results or directly outputting a rendered video file is generated. Based on user feedback and new data input, the system performance is continuously optimized to improve the accuracy of target detection and recognition.

[0057] Step S130, generating a timeline for the target object based on the appearance time, generating prompt text description data for each appearance time on the timeline based on the target object, appearance data and appearance position, and generating comprehensive text description data for the driving video data based on the timeline and all prompt text description data corresponding to all appearance times.

[0058] The target time point corresponding to the appearance time on the time axis corresponds to the appearance prompt text of the target object, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object.

[0059] The system takes the dashcam data and the list of target objects obtained in the previous steps (including target object categories, appearance data, appearance time, and location). A timeline is created based on the total length of the dashcam video, with each point on the timeline representing a specific time point. The time points at which all target objects appear are then marked on the timeline, forming a series of keyframes. For each target object, its appearance data is converted into a textual description. For example, if the target object is a red car, the description might be "a small red car." The target object's location information is converted into a readily understandable textual description. This might involve its relative position relative to the surrounding environment, such as "located on the right side of the road." Combining the target object's appearance and location information, a specific prompt is generated, for example, "At 5 seconds, a small red car appeared on the right side of the road." All prompts are then combined according to their order on the timeline to form a complete narrative textual description. Through these steps, the system effectively extracts valuable information from dashcam data and presents it in an intuitive and easy-to-understand manner, which not only helps improve understanding of various driving events but also facilitates subsequent data analysis.

[0060] Step S140 : sending the comprehensive text description data to the server via the vehicle-mounted terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data.

[0061] In the embodiment of the present application, the vehicle-mounted equipment first collects driving video in real time, and then uses the YTS engine on the vehicle-mounted terminal to perform real-time analysis on the driving video. It can quickly identify key information in the video (such as the target object and its appearance, location, etc.). Based on the identified target object and its related information, the system generates a timeline and creates a specific prompt text description for each target object. This method converts a large amount of unprocessed video data into a compact and meaningful text description, greatly reducing the amount of data. All prompt text descriptions are further integrated to form a comprehensive integrated text description. Since only processed and structured integrated text description data is sent instead of the original video data, this greatly reduces the amount of transmitted data, reduces the demand for network bandwidth, and improves the communication efficiency between the vehicle-mounted terminal and the server.

[0062] By reducing unnecessary data transmission and storage, this solution also helps save computing resources and storage costs. By intelligently preprocessing and streamlining data on the vehicle terminal, this solution significantly improves the efficiency of communication between the vehicle terminal and the server. This not only reduces network load and accelerates information processing, but also enhances the user experience.

[0063] In some embodiments, the target object includes a road object and a vehicle object; after the above step S120, as Figure 2 As shown, the method may further include the following steps:

[0064] Step S122, analyzing the road congestion data of each road object according to the vehicle appearance positions and vehicle appearance times corresponding to all vehicle objects;

[0065] Step S124, determining a number of target vehicle objects around the vehicle-mounted terminal according to the vehicle appearance position and vehicle appearance time corresponding to each vehicle object;

[0066] Step S126, in response to the first selection instruction for the plurality of road objects, determining a target road object selected corresponding to the first selection instruction from the plurality of road objects;

[0067] Step S128, based on the target road congestion data corresponding to the target road object and several target vehicle objects, analyze several feasible driving plans of the vehicle-mounted terminal through the target road object and the road passing time corresponding to each feasible driving plan.

[0068] In the embodiment of the present application, other vehicle objects in the adjacent area are determined based on the position and time information of the vehicles around the vehicle terminal itself. This helps to more accurately assess the state of nearby traffic flow and predict factors that may affect the driving path. In response to the user's instructions, the specific road object that the user is interested in is selected from multiple optional roads as the "target road", which reflects the user interactivity and personalized service functions of the system. Finally, combined with the congestion level of the selected target road and the distribution of surrounding vehicles, the system can generate several feasible driving routes and calculate the estimated time required for each route. This not only helps the driver avoid congested sections, but also effectively reduces travel time and improves travel efficiency.

[0069] In summary, the system's primary technical benefit is dynamic, real-time, and highly personalized route planning, enabling drivers to make more informed choices in complex traffic environments, saving time and fuel, reducing traffic stress, and improving the overall travel experience. Furthermore, this intelligent analysis and recommendation mechanism can facilitate urban traffic management and alleviate congestion.

[0070] In some embodiments, after analyzing several feasible driving plans of the vehicle-mounted terminal through the target road object based on the target road congestion data corresponding to the target road object and several target vehicle objects, the method may further include the following steps:

[0071] In response to a second selection instruction for several feasible driving plans, a target feasible driving plan corresponding to the second selection instruction is determined from multiple road objects; the relative position of each target vehicle object relative to its own on-board terminal is determined based on the target vehicle appearance position corresponding to each target vehicle object in the driving video data; and the driving process prompt information corresponding to the target feasible driving plan is determined and displayed based on the target feasible driving plan, the relative position and the target appearance data corresponding to the several target vehicle objects.

[0072] In this embodiment of the present application, by analyzing driving video data, the system can accurately determine the position of each surrounding target vehicle object relative to its own in-vehicle terminal. This utilizes visual recognition technology to enhance understanding of the surrounding traffic environment, improving driving safety and decision-making accuracy. Combining the selected target feasible driving plan, the relative positions of surrounding vehicles, and their appearance characteristics (such as size and color), the system can provide detailed driving process prompts. This information may include, but is not limited to, road conditions ahead, recommended speed adjustments, lane change timing, etc., aiming to help drivers complete their journey more safely and efficiently.

[0073] In summary, this system not only provides personalized route planning but also offers intuitive and practical driving guidance to drivers by monitoring and analyzing the surrounding traffic environment in real time. This approach significantly improves driving safety, efficiency, and comfort, especially in complex or congested traffic conditions. Furthermore, such a system helps reduce traffic accidents and improve overall road efficiency.

[0074] In some embodiments, the method may further include the following steps: analyzing the environmental data in the driving video data to obtain driving environment data; determining the driving process prompt information corresponding to the target feasibility driving scheme based on the target feasibility driving scheme, relative position and target appearance data corresponding to several target vehicle objects, including: determining the driving process prompt information corresponding to the target feasibility driving scheme based on the driving environment data, the target feasibility driving scheme, relative position and target appearance data corresponding to several target vehicle objects.

[0075] Driving environment data includes any one or more of the following: climate data, surrounding road conditions, and pedestrian data. By analyzing driving video data, the system can extract environmental data including climate conditions (such as rain, snow, and fog), surrounding road conditions (such as slippery road conditions and construction areas), and pedestrian movements. This comprehensive environmental perception capability enables the system to more accurately understand the current driving environment. After understanding the detailed driving environment, the system combines this data with target feasible driving plans, the relative positions of surrounding vehicles, and their appearance characteristics to provide the driver with personalized driving instructions. These instructions not only consider the most efficient driving route but also take into account real-time environmental factors and the movements of other traffic participants. Based on this analysis and processing, the system's driving recommendations are more tailored to actual driving situations, helping drivers make more informed decisions. For example, in inclement weather, the system may recommend reducing speed or avoiding certain road sections. When pedestrians are detected ahead, the system will remind the driver to slow down and evade them. In summary, this solution significantly enhances driving safety and efficiency, providing drivers with immediate and accurate guidance in complex and changing road environments. In addition, by integrating multi-source data and utilizing advanced algorithm processing, the system can effectively reduce the occurrence of traffic accidents and promote smoother urban traffic flow.

[0076] In some embodiments, a specified deep learning model is set in the server; after sending the comprehensive text description data to the server via the vehicle terminal, the method may further include the following steps:

[0077] According to the weight distribution data of the deep learning model, the pruning threshold corresponding to the deep learning model is dynamically adjusted through the server to ensure that important weights in the weight distribution data are not pruned; the comprehensive text description data is analyzed by the target deep learning model after dynamically adjusting the pruning threshold to obtain the video content of the driving video data.

[0078] In the embodiments of the present application, the server dynamically adjusts the pruning threshold based on the weight distribution data of the deep learning model, ensuring that important weights are not mistakenly removed during the model compression process. This helps maintain or even improve model performance, which is particularly important when running deep learning models in resource-constrained environments. Furthermore, it can greatly improve the model's operational efficiency while maintaining or improving model accuracy, and enable more accurate analysis of driving video content.

[0079] In some embodiments, the target deep learning model after dynamically adjusting the pruning threshold analyzes the comprehensive text description data to obtain the video content of the driving video data, which may specifically include the following steps:

[0080] The first target deep learning model after dynamically adjusting the pruning threshold is used to analyze the comprehensive text description data to obtain the initial video content of the driving video data. The initial video content is sampled regularly to obtain sampling results, and the scene complexity in the initial video content is detected based on the sampling results.

[0081] Based on the historical scene data corresponding to the scene complexity, future scene change data in the initial video content is predicted through machine learning, and the parameters of the first target deep learning model are adjusted in advance based on the future scene change data to obtain the second target deep learning model with adjusted parameters; the initial video content and comprehensive text description data are analyzed by the second target deep learning model to obtain the final video content of the driving video data.

[0082] In the embodiments of the present application, through a series of sophisticated designs and optimizations, a deep understanding of the content of driving video footage and forward-looking predictions of its future changes are achieved, greatly improving processing efficiency and accuracy.

[0083] Figure 3 A schematic diagram of the structure of a vehicle terminal data processing device based on the YTS engine is provided. Figure 3 As shown, the vehicle terminal data processing device 300 based on the YTS engine includes:

[0084] The acquisition module 301 is used to collect driving video data through the vehicle terminal;

[0085] An identification module 302 is configured to identify and analyze a target object, appearance data of the target object, and an appearance time and location of the target object in the rendered driving video data during the rendering process of the driving video data by the YTS engine in the vehicle terminal;

[0086] A generation module 303 is configured to generate a timeline for the target object based on the appearance time, generate prompt text description data for each appearance time on the timeline based on the target object, the appearance data, and the appearance position, and generate comprehensive text description data for the driving video data based on the timeline and all the prompt text description data corresponding to all the appearance times; wherein the appearance time corresponds to an appearance prompt text of the target object at a target time point on the timeline, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object;

[0087] The sending module 304 is configured to send the comprehensive text description data to a server via the vehicle-mounted terminal, so that the server can obtain the video content of the driving video data according to the comprehensive text description data.

[0088] The vehicle-mounted terminal data processing device based on the YTS engine provided in the embodiment of the present application has the same technical features as the vehicle-mounted terminal data processing method based on the YTS engine provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0089] An electronic device provided in an embodiment of the present application is Figure 4 As shown, the electronic device 400 includes a processor 402 and a memory 401 , wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the above embodiment when executing the computer program.

[0090] See also Figure 4 The electronic device further includes: a bus 403 and a communication interface 404, a processor 402, a communication interface 404 and a memory 401 connected via the bus 403; the processor 402 is used to execute executable modules stored in the memory 401, such as computer programs.

[0091] Memory 401 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive. Communication between the system network element and at least one other network element is achieved via at least one communication interface 404 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0092] The bus 403 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0093] Among them, the memory 401 is used to store programs, and the processor 402 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 402 or implemented by the processor 402.

[0094] The processor 402 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 402 or by instructions in the form of software. The above-mentioned processor 402 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 401, and processor 402 reads the information in memory 401 and, in conjunction with its hardware, completes the steps of the above method.

[0095] Corresponding to the above-mentioned vehicle-mounted terminal data processing method based on the YTS engine, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned vehicle-mounted terminal data processing method based on the YTS engine.

[0096] The vehicle-mounted terminal data processing device based on the YTS engine provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0097] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0098] For another example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0099] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0100] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0101] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the vehicle-mounted terminal data processing method based on the YTS engine described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0102] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0103] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. However, these modifications, changes, or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application. They should all be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A vehicle terminal data processing method based on the YTS engine, characterized in that: The method comprises: Collect driving video data through the vehicle terminal; In the process of rendering the driving video data using the YTS engine in the vehicle terminal, the target objects contained in the rendered driving video data are identified, the target objects in each frame image of the driving video data are detected and classified, the moving path of the same target object in the driving video data is tracked using a Kalman filter tracking algorithm, the appearance data of the target object and the appearance time and location of the target object in the driving video data are identified and analyzed by means of behavioral pattern recognition, and analysis results of traffic flow and accident prevention are obtained. The analysis results are superimposed on the original video of the driving video data for rendering, so as to display the bounding box, category label and behavior trajectory of the identified target object in the video; the target objects include road objects and vehicle objects; Analyzing the road congestion data of each of the road objects according to the vehicle appearance positions and vehicle appearance times corresponding to all the vehicle objects; Determine several target vehicle objects around the vehicle terminal according to the vehicle appearance position and vehicle appearance time corresponding to each vehicle object; In response to a first selection instruction for a plurality of the road objects, determining a target road object selected corresponding to the first selection instruction from the plurality of the road objects; Analyzing, based on the target road congestion data corresponding to the target road object and the target vehicle objects, several feasible driving plans of the vehicle-mounted terminal passing through the target road object and the road passing time corresponding to each of the feasible driving plans; A timeline for the target object is generated based on the appearance time, prompt text description data is generated for each appearance time on the timeline based on the target object, the appearance data, and the appearance position, and comprehensive text description data for the driving video data is generated based on the timeline and all the prompt text description data corresponding to all the appearance times; wherein the appearance time corresponds to an appearance prompt text of the target object at a target time point on the timeline, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object; The comprehensive text description data is sent to a server via the vehicle-mounted terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data.

2. The method according to claim 1, characterized in that After analyzing several feasible driving plans of the vehicle-mounted terminal through the target road object based on the target road congestion data corresponding to the target road object and the several target vehicle objects, the method further includes: In response to a second selection instruction for the plurality of feasible driving solutions, determining a target feasible driving solution corresponding to the second selection instruction from the plurality of road objects; Determine the relative position of each target vehicle object relative to the vehicle-mounted terminal according to the target vehicle appearance position corresponding to each target vehicle object in the driving video data; The driving process prompt information corresponding to the target feasible driving plan is determined and displayed based on the target feasible driving plan, the relative position and the target appearance data corresponding to the several target vehicle objects.

3. The method according to claim 2, characterized in that The method further comprises: Analyzing the environmental data in the driving video data to obtain driving environment data; The determining of driving process prompt information corresponding to the target feasible driving scheme according to the target feasible driving scheme, the relative position, and target appearance data corresponding to the plurality of target vehicle objects includes: The driving process prompt information corresponding to the target feasible driving plan is determined based on the driving environment data, the target feasible driving plan, the relative position and the target appearance data corresponding to the several target vehicle objects.

4. The method according to claim 3, characterized in that The driving environment data includes any one or more of the following: Climate data, surrounding road environment, and surrounding pedestrian data.

5. The method according to claim 1, wherein The server is provided with a specified deep learning model; after the comprehensive text description data is sent to the server through the vehicle terminal, the method further includes: Dynamically adjusting, by the server, a pruning threshold corresponding to the deep learning model according to the weight distribution data of the deep learning model, so that important weights in the weight distribution data are not pruned; The comprehensive text description data is analyzed by the target deep learning model after dynamically adjusting the pruning threshold to obtain the video content of the driving video data.

6. The method according to claim 5, characterized in that The target deep learning model after dynamically adjusting the pruning threshold is used to analyze the comprehensive text description data to obtain the video content of the driving video data, including: Analyzing the comprehensive text description data by using the first target deep learning model after dynamically adjusting the pruning threshold to obtain initial video content of the driving video data; regularly sampling the initial video content to obtain sampling results, and detecting scene complexity in the initial video content based on the sampling results; Predicting future scene change data in the initial video content by machine learning based on historical scene data corresponding to the scene complexity, and adjusting parameters of the first target deep learning model in advance based on the future scene change data to obtain a second target deep learning model after adjusting the parameters; The initial video content and the comprehensive text description data are analyzed by the second target deep learning model to obtain the final video content of the driving video data.

7. A vehicle-mounted terminal data processing device based on the YTS engine, characterized in that: include: The acquisition module is used to collect driving video data through the vehicle terminal; an identification module for identifying target objects contained in the rendered driving video data during the rendering process of the driving video data by the YTS engine in the vehicle-mounted terminal, detecting and classifying target objects in each frame of the driving video data, tracking the movement path of the same target object in the driving video data using a Kalman filter tracking algorithm, identifying and analyzing the appearance data of the target object and the appearance time and location of the target object in the driving video data through behavioral pattern recognition, obtaining analysis results of traffic flow and accident prevention, and superimposing the analysis results on the original video of the driving video data for rendering, so as to display the bounding box, category label and behavior trajectory of the identified target object in the video; the target objects include road objects and vehicle objects; An analysis module is configured to analyze the road congestion data of each of the road objects according to the vehicle appearance positions and vehicle appearance times corresponding to all the vehicle objects; Determining a plurality of target vehicle objects existing around the vehicle-mounted terminal based on the vehicle appearance position and vehicle appearance time corresponding to each of the vehicle objects; determining, in response to a first selection instruction for a plurality of the road objects, a target road object selected corresponding to the first selection instruction from the plurality of the road objects; analyzing, based on target road congestion data corresponding to the target road object and the plurality of target vehicle objects, a plurality of feasible driving plans for the vehicle-mounted terminal to pass through the target road object and a road passing time corresponding to each of the feasible driving plans; a generation module for generating a timeline for the target object based on the appearance time, generating prompt text description data for each appearance time on the timeline based on the target object, the appearance data, and the appearance position, and generating comprehensive text description data for the driving video data based on the timeline and all the prompt text description data corresponding to all the appearance times; wherein the appearance time corresponds to an appearance prompt text of the target object at a target time point on the timeline, and the appearance prompt text includes text description data of the appearance data corresponding to the target object and text description data of the appearance position corresponding to the target object; The sending module is used to send the comprehensive text description data to the server through the vehicle-mounted terminal, so that the server obtains the video content of the driving video data according to the comprehensive text description data.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 6.

Images