A data collection method and device based on policy sandbox

Abstract

The present invention discloses a data collection method and device based on a policy sandbox. The invention comprises the following steps: determining at least one policy script corresponding to data collection, and deploying the at least one policy script in the policy sandbox corresponding to the vehicle; obtaining trigger conditions received by the data collection system, and determining a target policy script based on the trigger conditions; and collecting data generated by the vehicle based on access rights and target collection parameters corresponding to the target policy script. This invention addresses the technical issues in related technologies, such as insufficient vehicle-cloud collaboration for autonomous vehicles, the inability of vehicle-side software to collect data in real time according to policies, and the resulting poor coupling between data and data collection policies.

Description

Technical Field

[0001] The present invention relates to the field of data collection, and in particular to a data collection method and device based on a policy sandbox. Background Art

[0002] Data is the driving force behind the advancement of autonomous driving technology. Data collection is a key technology for autonomous driving, and effective data analysis is crucial. Current technology still struggles to achieve both accurate and efficient data acquisition for autonomous driving. The main reasons for this are: insufficient coordination between the vehicle and the cloud, security issues caused by the coupling of data collection strategies, and the inability to update vehicle software in real time.

[0003] Regarding the technical problem of insufficient vehicle-cloud coordination for autonomous vehicles in related technologies, the vehicle-side software is unable to collect data in real time based on strategies, resulting in poor coupling between data and data collection strategies. Currently, no effective solution has been proposed for the above-mentioned problems. Summary of the Invention

[0004] The main purpose of the present invention is to provide a data collection method and device based on a policy sandbox to solve the technical problems in related technologies such as insufficient vehicle-cloud collaboration of autonomous driving vehicles and inability of vehicle-side software to collect data in real time according to strategies, resulting in poor coupling between data and data collection strategies.

[0005] To achieve the above objectives, according to one aspect of the present invention, a data collection method based on a policy sandbox is provided. The invention comprises: determining at least one policy script corresponding to data collection, and deploying the at least one policy script in the policy sandbox corresponding to the vehicle, wherein the policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, the collection parameters including at least the data type, collection duration, and collection frequency of the data to be collected, and the policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, the access rights including at least the resource access rights and resource utilization rights of the vehicle side; obtaining the trigger conditions received by the data collection system, and determining the target policy script based on the trigger conditions; and collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target policy script.

[0006] Furthermore, determining at least one strategy script corresponding to data collection includes: obtaining data uploaded by at least one vehicle stored in the cloud; matching the data with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data; and determining at least one strategy script based on the missing data.

[0007] Furthermore, the trigger conditions received by the data acquisition system are obtained, and the target policy script is determined based on the trigger conditions, including: matching the obtained trigger conditions with at least one data acquisition trigger condition corresponding to at least one policy script in the policy sandbox; when the trigger conditions successfully match at least one data acquisition trigger condition, determining the policy script corresponding to the data acquisition trigger condition as the target policy script.

[0008] Furthermore, after collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target strategy script, the method includes: caching a copy of the collected data in a storage unit in the data collection system; uploading the collected data to the corresponding data collection platform on the cloud, and sending the data uploaded to the data collection platform to the data analysis platform for analysis.

[0009] Furthermore, the data is matched with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data, including: obtaining multiple dimensions corresponding to the vehicle test model; constructing a multidimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions; and matching the data with the multidimensional data corresponding to the multidimensional space one by one to determine the missing data.

[0010] Furthermore, based on multiple dimensions, a high-dimensional space corresponding to the scenario corresponding to the vehicle test model is constructed, including: discretizing the high-dimensional space to divide the high-dimensional space into multiple regions, wherein the regions correspond one-to-one to the dimensions; corresponding the data stored in the cloud to the multiple dimensions to obtain multi-dimensional data; filling the multi-dimensional data in the regions corresponding to the dimensions, and determining the blank areas where no data exists, and determining the dimensions corresponding to the blank areas as target dimensions; and determining the data corresponding to the target dimensions as missing data.

[0011] In order to achieve the above-mentioned purpose, according to another aspect of the present invention, a data acquisition device based on a policy sandbox is provided. The device includes: a determination unit, which is used to determine at least one policy script corresponding to data acquisition, and deploy the at least one policy script in the policy sandbox corresponding to the vehicle, wherein the policy script contains at least one data acquisition trigger condition and acquisition parameters corresponding to vehicle data acquisition, and the acquisition parameters include at least the data type, acquisition duration, and acquisition frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data acquisition process, and the access rights include at least the resource access rights and resource utilization rights of the vehicle side; an acquisition unit, which is used to obtain the trigger conditions received by the data acquisition system and determine the target policy script based on the trigger conditions; and the acquisition unit collects the data generated by the vehicle based on the access rights and the target acquisition parameters corresponding to the target policy script.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein the program executes any one of the above-mentioned data collection methods based on a policy sandbox.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a processor is provided, which is used to run a program, wherein the program executes any one of the above-mentioned data collection methods based on a policy sandbox.

[0014] Through the present invention, the following steps are adopted: determining at least one policy script corresponding to data collection, and deploying at least one policy script in a policy sandbox corresponding to the vehicle, wherein the policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, and the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, and the access rights include at least the resource access rights and resource utilization rights of the vehicle side; obtaining the trigger conditions received by the data collection system, and determining the target policy script based on the trigger conditions; collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target policy script, thereby solving the problem of insufficient vehicle-cloud collaboration of autonomous driving vehicles in related technologies, and the inability of the vehicle-side software to collect data according to the strategy in real time, resulting in poor coupling between data and data collection strategies, thereby achieving the effect of accurately and efficiently obtaining autonomous driving data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which constitute part of the present invention, are provided to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are provided to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0016] Figure 1 is a flow chart of a data collection method based on a policy sandbox according to an embodiment of the present invention; and

[0017] Figure 2 A schematic diagram of the interaction between cloud and vehicle-side data in a vehicle according to an embodiment of the present application;

[0018] Figure 3 A schematic diagram of bidirectional data interaction between the vehicle-side data management system and the vehicle-side policy sandbox;

[0019] Figure 4 2 is a schematic diagram of a data collection device based on a policy sandbox according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," and the like in the specification and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the embodiments of the present invention described herein. In addition, the terms "including," "having," and any variations thereof 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 necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0023] According to an embodiment of the present invention, a data collection method based on a policy sandbox is provided.

[0024] Figure 1 This is a flow chart of a data collection method based on a policy sandbox according to an embodiment of the present invention. Figure 1 As shown, the invention includes the following steps:

[0025] Step S101: Determine at least one policy script corresponding to data collection and deploy the at least one policy script in a policy sandbox corresponding to the vehicle. The policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection. The collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process. The access rights include at least resource access rights and resource utilization rights of the vehicle side.

[0026] Step S102, obtaining the trigger conditions received by the data acquisition system, and determining the target policy script according to the trigger conditions;

[0027] Step S103 : collecting data generated by the vehicle according to the access rights and the target collection parameters corresponding to the target policy script.

[0028] The above-mentioned data collection method based on the policy sandbox first determines at least one policy script corresponding to data collection and deploys the at least one policy script in the policy sandbox corresponding to the vehicle. The policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection. The collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process. The access rights include at least resource access rights and resource utilization rights of the vehicle side. Then, the trigger conditions received by the data collection system are obtained, and the target policy script is determined based on the trigger conditions. Finally, the data generated by the vehicle is collected based on the access rights and the target collection parameters corresponding to the target policy script. By collecting the policy script and determining the target policy script based on the trigger conditions, the collected data can be flexibly and quickly deployed to the vehicle side.

[0029] As mentioned above, the current acquisition of autonomous driving data cannot be both accurate and efficient. The reason is that there is insufficient coordination between the vehicle and the cloud, and the vehicle-side software cannot be updated in real time. In the embodiment provided by this application, the cloud uses big data statistics and analysis technology to analyze the scenarios corresponding to the existing data statistics and models (vehicle test models), and extract which scenarios have insufficient data (such as lack of rainy day data, lack of night data, etc.); or find abnormal trajectory data, etc. At the same time, based on the above analysis results, a collection strategy script is created, and the collection strategy; the strategy script only supports simple mathematical calculations, logical operations, etc. to ensure safety, and can be flexibly and quickly deployed to the vehicle side.

[0030] like Figure 2 As shown, Figure 2 A schematic diagram of the interaction between cloud and vehicle-side data of a vehicle provided in an embodiment of the present application, in which the cloud obtains data uploaded by the vehicle from the data acquisition platform, and the data analysis platform edits and verifies the obtained data, and then generates a policy script, which is then sent to the vehicle-side data management system through the policy management and issuance platform and deployed in the policy sandbox. It should be noted that the policy script deployment in this application, that is, the policy update does not need to go through the OTA channel, which shortens the policy update cycle.

[0031] At the same time, the cloud analyzes the data uploaded by the vehicle in real time and analyzes the vehicle status. The analysis results are sent to the policy sandbox and matched with the trigger conditions corresponding to the policy script. After a successful match, the corresponding policy script is triggered, and the vehicle data is collected according to the policy script, achieving purposeful data collection, while improving data collection accuracy and saving data storage space.

[0032] The vehicle-side data management system also collects vehicle-side information through the vehicle data bus. The vehicle-side data management system and the vehicle-side policy sandbox exchange data in a two-way manner. Finally, the vehicle-side data management system transmits this information to the cloud-based data collection platform.

[0033] An embodiment of the present invention provides a data collection method based on a policy sandbox, which determines at least one policy script corresponding to data collection and deploys at least one policy script in a policy sandbox corresponding to a vehicle, wherein the policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, and the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, and the access rights include at least resource access rights and resource utilization rights of the vehicle side; obtain the trigger conditions received by the data collection system, and determine the target policy script based on the trigger conditions; collect the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target policy script, thereby solving the technical problem in related technologies that the vehicle-cloud collaboration of autonomous driving vehicles is insufficient, the vehicle-side software cannot collect data according to the strategy in real time, resulting in poor coupling between data and data collection strategies, thereby achieving the effect of accurately and efficiently obtaining autonomous driving data.

[0034] In an optional embodiment, determining at least one strategy script corresponding to data collection includes: obtaining data uploaded by at least one vehicle stored in the cloud; matching the data with scenario data corresponding to at least one vehicle test model to determine missing data corresponding to the scenario data; and determining at least one strategy script based on the missing data.

[0035] As mentioned above, in this application, the data collected by the data collection platform and the scene data corresponding to the vehicle test model are analyzed and matched to determine the missing data in the scene data, and a strategy script is produced based on the missing data.

[0036] In an optional embodiment, the data is matched with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data, including: obtaining multiple dimensions corresponding to the vehicle test model; constructing a multidimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions; and matching the data with the multidimensional data corresponding to the multidimensional space one by one to determine the missing data.

[0037] The present application provides an optional embodiment, in which a high-dimensional space corresponding to a scene corresponding to a vehicle test model is constructed based on multiple dimensions, including: discretizing the high-dimensional space to divide the high-dimensional space into multiple regions, wherein the regions correspond one-to-one to the dimensions; corresponding the data stored in the cloud to the multiple dimensions to obtain multidimensional data; filling the multidimensional data in the regions corresponding to the dimensions, and determining blank areas where no data exists, and determining the dimensions corresponding to the blank areas as target dimensions; and determining the data corresponding to the target dimensions as missing data.

[0038] As mentioned above, each scenario is expressed in multiple dimensions on the machine side. For example, the dimensions corresponding to a scenario are: weather, vehicle speed, time, and space. The corresponding scenario is made into a multi-dimensional space through the above four dimensions, and the high-dimensional space is discretized. After discretization, each dimension becomes multiple grids, and the corresponding dimension data is stored in the grid. The data is displayed in the dimension grid. Through the grid, the data distribution is balanced or unbalanced to determine the dimension with missing data. For example, if there is missing data in the grid corresponding to the weather dimension, a strategy script is made based on the missing data corresponding to the weather data to obtain the missing data corresponding to the weather dimension in a targeted manner for use in subsequent test scenarios.

[0039] In an optional embodiment, a trigger condition received by a data acquisition system is obtained, and a target policy script is determined based on the trigger condition, including: matching the obtained trigger condition with at least one data acquisition trigger condition corresponding to at least one policy script in a policy sandbox; and when the trigger condition successfully matches at least one data acquisition trigger condition, determining the policy script corresponding to the data acquisition trigger condition as the target policy script.

[0040] Specifically, the cloud analyzes the data uploaded by the vehicle in real time. For example, if the vehicle data uploaded by the vehicle indicates that the wipers are turned on, or if the current real-time weather obtained through the weather forecast is rainy, the condition of "rainy day" is sent to the policy sandbox, and the condition is matched with at least one policy script in the policy sandbox. If any policy script contains the trigger condition of "rainy day", the policy script is triggered and data is collected according to the data collection parameters corresponding to the policy script. The collection parameters can be used to determine the type of data to be collected, the duration of the collection, the time period in which the vehicle generates the data, or the frequency of data collection.

[0041] At the same time, it should be noted that in this application, the policy script is deployed in the policy sandbox. Since the policy sandbox itself limits the access rights of the policy collection process in the vehicle, when collecting data according to the policy script, the collection process only targets the CPU, hard disk, files, network or disk space with permissions, etc. At the same time, the policy sandbox can also limit the data collection process's permissions such as CPU usage.

[0042] In an optional embodiment, after collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target strategy script, the method includes: caching a copy of the collected data in a storage unit in the data collection system; uploading the collected data to the corresponding data collection platform on the cloud, and sending the data uploaded to the data collection platform to the data analysis platform for analysis.

[0043] As described above, after collecting the data on the vehicle side according to the strategy script, one copy of the data is stored in the data cache file on the vehicle side, and another copy of the data is uploaded to the data collection platform on the cloud side, forming a data closed loop between the vehicle side and the cloud side.

[0044] Through the policy sandbox-based data collection method provided by the present application, the required data can be collected effectively instead of collecting a large amount of duplicate and useless data.

[0045] At the same time, it also has the following advantages: first, it can save traffic costs; second, it can save cloud storage costs; third, flexible strategy deployment reduces maintenance costs.

[0046] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0047] Figure 3 A schematic diagram of bidirectional data interaction between the vehicle-side data management system and the vehicle-side policy sandbox, as shown in Figure 3As shown, when updating a policy, the cloud sends the new policy to the data management system. The data management system then passes the policy update event to the policy sandbox and transmits the policy script. The data management system transmits the "Ready" message to the policy sandbox, which then sequentially sends feedback, including the acquisition signal registration, policy signal registration, event registration, and the "Ready" signal, to the data management system. When triggering a policy, for example, if the wipers are on continuously for one minute, the front camera data collection begins and continues for 10 minutes; or if the wipers stop, the data management system transmits the wiper-on event to the policy sandbox, which triggers the wiper event policy. The timer counts for one minute and then passes the data collection to the data management system. The data management system caches the camera data and uploads the front camera data. The policy sandbox also uploads the data, and the timer counts for 10 minutes before stopping the collection. Through this data interaction, flexible policy deployment and reduced maintenance costs are achieved.

[0048] The present invention also provides a data collection device based on a policy sandbox. It should be noted that the data collection device based on a policy sandbox according to the present invention can be used to execute the data collection method based on a policy sandbox according to the present invention. The following describes the data collection device based on a policy sandbox according to the present invention.

[0049] Figure 4 Schematic diagram of a data collection device based on a policy sandbox according to an embodiment of the present invention. Figure 4 As shown, the device includes: a determination unit 401, which is used to determine at least one policy script corresponding to data collection, and deploy the at least one policy script in a policy sandbox corresponding to the vehicle, wherein the policy script contains at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, and the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, and the access rights include at least the resource access rights and resource utilization rights of the vehicle side; an acquisition unit 402, which is used to obtain the trigger conditions received by the data collection system, and determine the target policy script based on the trigger conditions; a collection unit 403, which is used to collect the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target policy script.

[0050] In an optional embodiment, the determination unit 401 includes: an acquisition subunit, used to obtain data uploaded by at least one vehicle stored in the cloud; a first determination subunit, used to match the data with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data; and a second determination subunit, used to determine at least one strategy script based on the missing data.

[0051] In an optional embodiment, the acquisition unit 402 includes: a matching sub-unit, used to match the acquired trigger condition with at least one data collection trigger condition corresponding to at least one policy script in the policy sandbox; and a third determination sub-unit, used to determine the policy script corresponding to the data collection trigger condition as the target policy script when the trigger condition successfully matches the at least one data collection trigger condition.

[0052] In an optional embodiment, the collection unit 403 includes: a cache subunit, which is used to cache a copy of the collected data in a storage unit in the data collection system; an analysis subunit that uploads the collected data to a corresponding data collection platform on the cloud, and sends the data uploaded to the data collection platform to the data analysis platform for analysis.

[0053] In an optional embodiment, the first determination subunit includes: an acquisition module for acquiring multiple dimensions corresponding to the vehicle test model; a construction module for constructing a multidimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions; and a determination module that matches the data with the multidimensional data corresponding to the multidimensional space one by one to determine the missing data.

[0054] In an optional embodiment, it is characterized in that the construction module includes: a segmentation submodule, which is used to perform discrete processing on the high-dimensional space to divide the high-dimensional space into multiple regions, wherein the regions correspond one-to-one to the dimensions; an acquisition submodule, which is used to correspond the data stored in the cloud to multiple dimensions to obtain multidimensional data; a first determination submodule, which is used to fill the multidimensional data in the regions corresponding to the dimensions, and determine the blank areas where no data exists, and determine the dimensions corresponding to the blank areas as the target dimensions; a second determination submodule, which is used to determine the data corresponding to the target dimension as missing data.

[0055] An embodiment of the present invention provides a data acquisition device based on a policy sandbox, which is used to determine at least one policy script corresponding to data acquisition through a determination unit 401, and deploy the at least one policy script in the policy sandbox corresponding to the vehicle, wherein the policy script includes at least one data acquisition trigger condition and acquisition parameters corresponding to vehicle data acquisition, and the acquisition parameters include at least the data type, acquisition duration, and acquisition frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data acquisition process, and the access rights include at least resource access rights and resource utilization rights of the vehicle side; an acquisition unit 402 is used to obtain the trigger conditions received by the data acquisition system, and determine the target policy script based on the trigger conditions; a collection unit 403 is used to collect data generated by the vehicle based on the access rights and the target acquisition parameters corresponding to the target policy script, thereby solving the technical problem in the related technology that the vehicle-cloud collaboration of the autonomous driving vehicle is insufficient, the vehicle-side software cannot collect data according to the strategy in real time, resulting in poor coupling between data and data acquisition strategy, thereby achieving the effect of accurately and efficiently acquiring autonomous driving data.

[0056] The data acquisition device based on the policy sandbox includes a processor and a memory. The above units are all stored in the memory as program units, and the processor executes the above program units stored in the memory to realize corresponding functions.

[0057] The processor contains a core, which retrieves the corresponding program unit from the memory. One or more cores can be configured, and the kernel parameters can be adjusted to accurately and efficiently obtain autonomous driving data.

[0058] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0059] An embodiment of the present invention provides a storage medium storing a program, which implements a data collection method based on a policy sandbox when executed by a processor.

[0060] An embodiment of the present invention provides a processor, which is used to run a program. When the program is running, a data collection method based on a policy sandbox is executed.

[0061] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and runnable on the processor. When the processor executes the program, the following steps are implemented: determining at least one policy script corresponding to data collection, and deploying the at least one policy script in a policy sandbox corresponding to the vehicle, wherein the policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, and the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, and the access rights include at least the resource access rights and resource utilization rights of the vehicle side; obtaining the trigger conditions received by the data collection system, and determining the target policy script based on the trigger conditions; and collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target policy script.

[0062] Furthermore, determining at least one strategy script corresponding to data collection includes: obtaining data uploaded by at least one vehicle stored in the cloud; matching the data with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data; and determining at least one strategy script based on the missing data.

[0063] Furthermore, the trigger conditions received by the data acquisition system are obtained, and the target policy script is determined based on the trigger conditions, including: matching the obtained trigger conditions with at least one data acquisition trigger condition corresponding to at least one policy script in the policy sandbox; when the trigger conditions successfully match at least one data acquisition trigger condition, determining the policy script corresponding to the data acquisition trigger condition as the target policy script.

[0064] Furthermore, after collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target strategy script, the method includes: caching a copy of the collected data in a storage unit in the data collection system; uploading the collected data to the corresponding data collection platform on the cloud, and sending the data uploaded to the data collection platform to the data analysis platform for analysis.

[0065] Furthermore, the data is matched with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data, including: obtaining multiple dimensions corresponding to the vehicle test model; constructing a multidimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions; and matching the data with the multidimensional data corresponding to the multidimensional space one by one to determine the missing data.

[0066] Furthermore, based on multiple dimensions, a high-dimensional space corresponding to the scenario corresponding to the vehicle test model is constructed, including: discretizing the high-dimensional space to divide it into multiple regions, where the regions correspond one-to-one with the dimensions; correlating the data stored in the cloud with the multiple dimensions to obtain multidimensional data; filling the multidimensional data in the regions corresponding to the dimensions, determining blank regions without data, and determining the dimensions corresponding to the blank regions as target dimensions; and determining the data corresponding to the target dimensions as missing data. The device in this article can be a server, PC, PAD, mobile phone, etc.

[0067] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: determining at least one policy script corresponding to data collection, and deploying at least one policy script in a policy sandbox corresponding to the vehicle, wherein the policy script contains at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, and the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, and the access rights include at least the resource access rights and resource utilization rights of the vehicle side; obtaining the trigger conditions received by the data collection system, and determining the target policy script based on the trigger conditions; and collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target policy script.

[0068] Furthermore, determining at least one strategy script corresponding to data collection includes: obtaining data uploaded by at least one vehicle stored in the cloud; matching the data with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data; and determining at least one strategy script based on the missing data.

[0069] Furthermore, the trigger conditions received by the data acquisition system are obtained, and the target policy script is determined based on the trigger conditions, including: matching the obtained trigger conditions with at least one data acquisition trigger condition corresponding to at least one policy script in the policy sandbox; when the trigger conditions successfully match at least one data acquisition trigger condition, determining the policy script corresponding to the data acquisition trigger condition as the target policy script.

[0070] Furthermore, after collecting the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target strategy script, the method includes: caching a copy of the collected data in a storage unit in the data collection system; uploading the collected data to the corresponding data collection platform on the cloud, and sending the data uploaded to the data collection platform to the data analysis platform for analysis.

[0071] Furthermore, the data is matched with scene data corresponding to at least one vehicle test model to determine missing data corresponding to the scene data, including: obtaining multiple dimensions corresponding to the vehicle test model; constructing a multidimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions; and matching the data with the multidimensional data corresponding to the multidimensional space one by one to determine the missing data.

[0072] Furthermore, based on multiple dimensions, a high-dimensional space corresponding to the scenario corresponding to the vehicle test model is constructed, including: discretizing the high-dimensional space to divide the high-dimensional space into multiple regions, wherein the regions correspond one-to-one to the dimensions; corresponding the data stored in the cloud to the multiple dimensions to obtain multi-dimensional data; filling the multi-dimensional data in the regions corresponding to the dimensions, and determining the blank areas where no data exists, and determining the dimensions corresponding to the blank areas as target dimensions; and determining the data corresponding to the target dimensions as missing data.

[0073] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0078] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0079] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0081] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A data collection method based on a policy sandbox, characterized in that: include: Determining at least one policy script corresponding to data collection, and deploying the at least one policy script in a policy sandbox corresponding to the vehicle, wherein the policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, wherein the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected. The policy sandbox is used to limit the access rights of the vehicle side corresponding to the data collection process, wherein the access rights include at least resource access rights and resource utilization rights of the vehicle side; Obtaining a trigger condition received by a data acquisition system, and determining a target policy script based on the trigger condition; Collect the data generated by the vehicle based on the access rights and the target collection parameters corresponding to the target strategy script, Determining at least one policy script corresponding to data collection includes: Obtaining data uploaded by at least one vehicle stored in the cloud; matching the data with scenario data corresponding to at least one vehicle test model to determine missing data corresponding to the scenario data; At least one of the policy scripts is determined based on the missing data.

2. The method according to claim 1, characterized in that Acquiring a trigger condition received by the data acquisition system and determining a target policy script according to the trigger condition, including: Matching the acquired trigger condition with at least one data collection trigger condition corresponding to at least one policy script in the policy sandbox; In the case that the trigger condition successfully matches at least one of the data collection trigger conditions, the policy script corresponding to the data collection trigger condition is determined as the target policy script.

3. The method according to claim 1, characterized in that After collecting data generated by the vehicle according to the access rights and the target collection parameters corresponding to the target strategy script, the method includes: Cache a copy of the collected data in a storage unit in the data collection system; The collected data is uploaded to the corresponding data collection platform on the cloud, and the data uploaded to the data collection platform is sent to the data analysis platform for analysis.

4. The method according to claim 1, wherein Matching the data with scenario data corresponding to at least one vehicle test model to determine missing data corresponding to the scenario data includes: Obtaining multiple dimensions corresponding to the vehicle test model; Constructing a multidimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions; The data is matched one by one with the multidimensional data corresponding to the multidimensional space to determine the missing data.

5. The method according to claim 4, characterized in that Constructing a high-dimensional space corresponding to the scene corresponding to the vehicle test model based on the multiple dimensions includes: Performing discretization processing on the high-dimensional space to divide the high-dimensional space into a plurality of regions, wherein the regions correspond one-to-one to the dimensions; Matching the data stored in the cloud with the multiple dimensions to obtain multidimensional data; Filling the multidimensional data in the area corresponding to the dimension, determining a blank area where the data does not exist, and determining the dimension corresponding to the blank area as the target dimension; The data corresponding to the target dimension is determined as the missing data.

6. A data collection device based on a policy sandbox, characterized in that: include: a determination unit, configured to determine at least one policy script corresponding to data collection, and deploy the at least one policy script in a policy sandbox corresponding to the vehicle, wherein the policy script includes at least one data collection trigger condition and collection parameters corresponding to vehicle data collection, wherein the collection parameters include at least the data type, collection duration, and collection frequency of the data to be collected; and the policy sandbox is configured to limit access rights of the vehicle side corresponding to the data collection process, wherein the access rights include at least resource access rights and resource utilization rights of the vehicle side; an acquisition unit, configured to acquire a trigger condition received by the data acquisition system and determine a target policy script according to the trigger condition; A collection unit is used to collect data generated by the vehicle according to the access rights and the target collection parameters corresponding to the target strategy script, Identify units, including: an acquisition subunit, configured to acquire data uploaded by at least one vehicle from cloud storage; a first determining subunit, configured to match the data with scenario data corresponding to at least one vehicle test model to determine missing data corresponding to the scenario data; The second determining subunit is configured to determine at least one of the policy scripts according to the missing data.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the data collection method based on the policy sandbox according to any one of claims 1 to 5.

8. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the data collection method based on a policy sandbox as described in any one of claims 1 to 5.

Images