Data processing method and apparatus

Abstract

A data processing method and apparatus are disclosed. In this method, a cloud server acquires the features of risk information (S201), and determines a collection layer based on the features of the risk information. The collection layer includes the features of the road segments for which data collection is required and the data collection needs of the road segments (S202). By analyzing risk information, the cloud server automatically mines the features of the road segments for which data collection is required and the corresponding data collection needs, avoiding manual analysis and identification of problems, improving the efficiency of discovering high-value collection scenarios, and thus improving the quality of the collected data.

Description

Data processing method and device TECHNICAL FIELD

[0001] The present application relates to the technical field of automobiles, and in particular to a data processing method and device. BACKGROUND

[0002] With the development of intelligent driving technology, intelligent driving algorithms gradually develop from rules to artificial intelligence (AI) models. AI models can be trained by inputting a large amount of driving scene data, and the trained AI models can make decisions based on perception data of a scene in a real scene. Currently, driving scene data used to train AI models is mainly collected by manually driving a work vehicle on an actual road and collected by sensors deployed on the vehicle. However, this data collection is inefficient, and since most driving scenes are convergent, the value of the driving scene data collected by the work vehicle is low, which leads to poor performance of the trained AI models in some complex or uncommon driving scenes.

[0003] SUMMARY

[0004] The present application provides a data processing method and device, which can identify high-value collection scenes, thereby improving the quality of collected data.

[0005] The present application will be described from different aspects below. It should be understood that the embodiments and advantages of the different aspects below can be mutually referred to.

[0006] In a first aspect, an embodiment of the present application provides a data processing method, which can be executed by a cloud server. In the method, the cloud server obtains features of risk information; and the cloud server determines at least one collection layer based on the features of the risk information, wherein the collection layer includes features of a collection road segment that needs data collection and data collection requirements of the collection road segment.

[0007] In the present application, the cloud server automatically mines features of a collection road segment that needs data collection and corresponding data collection requirements by analyzing risk information, avoids manual analysis and identification of problems, improves the efficiency of discovering high-value collection scenes, and thereby improves the quality of collected data.

[0008] In a possible design, the risk information includes one or more of the following information:

[0009] an operation and maintenance event for indicating a vehicle operating condition, map composition abnormal information, or indication information of a risk road segment, wherein the risk road segment is a road segment in which a performance of an intelligent driving function of the vehicle is abnormal.

[0010] In this implementation, the risk information can include multiple dimensions of information, such as operation and maintenance events, abnormal information of map composition, or indication information of a risk road section, which is more conducive to subsequent mining of high-value collection scenarios, and thus improves the data collection quality.

[0011] In a possible design, the operation and maintenance event includes an abnormal operation event of an intelligent driving function in the vehicle and / or a vehicle condition abnormal event of the vehicle.

[0012] The abnormal operation event of the intelligent driving function includes at least one of the following events: intelligent driving function degradation, intelligent driving function exit, intelligent driving function failure, intelligent driving function abnormal operation, or traffic violation behavior.

[0013] The vehicle condition abnormal event includes at least one of the following events: an alarm event of the vehicle, or a component abnormal event of the vehicle.

[0014] In a possible design, the feature of the collection road section includes a location of the collection road section, and the location of the collection road section includes one or more of the following information:

[0015] an identifier of the collection road section, a region range of the collection road section, a version of the collection road section, an identifier of a collection track in the collection road section, a collection start position of the collection track, a collection end position of the collection track, and a region of the collection track.

[0016] In a possible design, the data collection requirement includes a collection condition and / or a collection state, the collection condition is used to indicate a condition that needs to be met for data collection, and the collection state is used to indicate whether collection needs to be performed.

[0017] In this implementation, the collection state of a collected track or road section can be set to not needing to be collected, so that the collected region is inhibited, and repeated collection of data is avoided.

[0018] In a possible design, the collection condition includes a dynamic condition and / or a static condition.

[0019] The dynamic condition includes one or more of the following: weather, illumination, traffic characteristics, traffic game, or vehicle state.

[0020] The static condition includes one or more of the following: an identifier of a road, a type of a road, a road surface condition, or a data type.

[0021] In the implementation, the superposition of the dynamic and / or static conditions can make the collected data meet the requirements better, avoid a large amount of collection of low-value data, and improve the data collection quality.

[0022] In a possible design, the method further includes:

[0023] obtaining a position of at least one vehicle;

[0024] sending a corresponding first collection layer to a first vehicle in the at least one vehicle, where the first collection layer belongs to the at least one collection layer, and a position of the first vehicle is associated with a collection road segment in the first collection layer.

[0025] In the implementation, the corresponding collection layer is sent to the vehicle according to the position of the vehicle, which avoids sending all the collection layers to the vehicle to cause a large file, and improves the accuracy of the collection layer.

[0026] In a possible design, the position of the first vehicle is associated with the collection road segment in the first collection layer, including:

[0027] The position of the first vehicle is located in the collection road segment in the first collection layer.

[0028] In a possible design, the method further includes:

[0029] receiving first collection data from the first vehicle, where the first collection data includes scene data of a collection road segment in the first collection layer.

[0030] In a possible design, the collection road segment in the first collection layer includes at least one collection track, the first collection data includes scene data of a first collection track, and the first collection track belongs to the at least one collection track.

[0031] The method further includes:

[0032] updating the first collection layer according to the first collection data.

[0033] In the implementation, after the collection data reported by the vehicle is received, the corresponding collection layer is updated based on the collected data, which avoids repeated collection of data.

[0034] In a possible design, the updated first collection layer does not include indication information of the first collection track, or the collection state indication of the first collection track in the updated first collection layer indicates that collection is not required.

[0035] In a possible design, the method further includes:

[0036] In a case where the received collected data is associated with a collected track satisfying the preset quantity and belonging to at least one collected track included in the collected section in the first collected layer, the intelligent driving function is updated based on the received collected data.

[0037] In this implementation manner, by monitoring the collected saturation of each collected track in the collected section, the uniformity and completeness of data collection are facilitated.

[0038] In a possible design, the collected data is used to update the cloud mapping information.

[0039] In a possible design, the collected section is a lane. Alternatively, the collected section is described as belonging to a lane level, that is, the collected data involved in the present application is lane-level data.

[0040] In a second aspect, an embodiment of the present application provides a data processing method, which can be executed by a first vehicle. In the method, the first vehicle receives a first collected layer, the first collected layer including features of a collected section requiring data collection and data collection requirements of the collected section, wherein a position of the first vehicle is associated with the collected section in the first collected layer; and the first vehicle sends first collected data, the first collected data including scene data of the collected section in the first collected layer.

[0041] In a possible design, the position of the first vehicle associated with the collected section in the first collected layer includes:

[0042] The position of the first vehicle is located in the collected section in the first collected layer.

[0043] In a possible design, before the first collected layer is received, the method further includes:

[0044] Sending a request message, the request message being used to request a collected layer corresponding to the position of the first vehicle;

[0045] Receiving the first collected layer.

[0046] In a possible design, the method further includes:

[0047] Sending an operation and maintenance event, the operation and maintenance event being used to indicate an operating condition of the first vehicle.

[0048] In a possible design, the method further includes:

[0049] Receiving an updated intelligent driving function;

[0050] Perform a driving decision based on the updated intelligent driving function.

[0051] In a possible design, the collection road section is a lane. Alternatively, it is described that the collection road section belongs to a lane level, that is, the collection data involved in the present application is lane-level data.

[0052] In a third aspect, an embodiment of the present application provides a data processing apparatus, which can be a cloud server. The data processing apparatus comprises:

[0053] The transceiver module is configured to acquire features of risk information.

[0054] The processing module is configured to determine at least one collection layer based on the features of the risk information, wherein the collection layer comprises features of a collection road section and data collection requirements of the collection road section.

[0055] In a possible design, the risk information comprises one or more of the following information:

[0056] An operation and maintenance event used to indicate a vehicle operating condition, map composition abnormal information, or indication information of a risk road section, wherein the risk road section is a road section in which an intelligent driving function of the vehicle has performance abnormality.

[0057] In a possible design, the operation and maintenance event comprises an abnormal operation event of the intelligent driving function in the vehicle and / or a vehicle condition abnormal event of the vehicle.

[0058] The abnormal operation event of the intelligent driving function comprises at least one of the following events: intelligent driving function degradation, intelligent driving function exit, intelligent driving function failure, intelligent driving function abnormal operation, or traffic violation behavior.

[0059] The vehicle condition abnormal event comprises at least one of the following events: an alarm event of the vehicle, or a component abnormal event of the vehicle.

[0060] In a possible design, the features of the collection road section comprise a position of the collection road section, and the position of the collection road section comprises one or more of the following information:

[0061] An identifier of the collection road section, a region range of the collection road section, a version of the collection road section, an identifier of a collection track in the collection road section, a collection start position of the collection track, a collection end position of the collection track, and a region of the collection track.

[0062] In a possible design, the data collection requirement includes a collection condition and / or a collection state, where the collection condition is used to indicate a condition that needs to be met for data collection to be performed, and the collection state is used to indicate whether collection needs to be performed.

[0063] In a possible design, the collection condition includes a dynamic condition and / or a static condition.

[0064] The dynamic condition includes one or more of the following: weather, illumination, traffic feature, traffic game, or vehicle state.

[0065] The static condition includes one or more of the following: identification of a road, type of a road, road surface condition, or data type.

[0066] In a possible design, the transceiver module is configured to acquire a position of at least one vehicle, and configured to send, to a first vehicle in the at least one vehicle, a first collection layer corresponding to the first collection layer, where the first collection layer belongs to the at least one collection layer, and a position of the first vehicle is associated with a collection road segment in the first collection layer.

[0067] In a possible design, the position of the first vehicle is located in the collection road segment in the first collection layer.

[0068] The position of the first vehicle is located in the collection road segment in the first collection layer.

[0069] In a possible design, the transceiver module is configured to:

[0070] receive first collection data from the first vehicle, where the first collection data includes scene data of a collection road segment in the first collection layer.

[0071] In a possible design, the collection road segment in the first collection layer includes at least one collection track, the first collection data includes scene data of a first collection track, and the first collection track belongs to the at least one collection track; and the processing module is configured to update the first collection layer according to the first collection data.

[0072] In a possible design, the updated first collection layer does not include indication information of the first collection track, or a collection state of the first collection track in the updated first collection layer indicates that collection is not needed.

[0073] In a possible design, the processing module is configured to:

[0074] In a case where the received collected data is associated with a collected track that meets a preset quantity and belongs to at least one collected track included in the collected section in the first collected layer, the intelligent driving function is updated based on the received collected data.

[0075] In a possible design, the collected section is a lane. Alternatively, it is described that the collected section belongs to a lane level, that is, the collected data involved in the present application is lane-level data.

[0076] In a fourth aspect, an embodiment of the present application provides a data processing apparatus, which can be a first vehicle, and the data processing apparatus comprises:

[0077] A transceiver module is configured to receive a first collected layer, the first collected layer comprising features of a collected section requiring data collection and data collection requirements of the collected section, wherein a location of the first vehicle is associated with the collected section in the first collected layer;

[0078] The transceiver module is configured to send first collected data, the first collected data comprising scene data of the collected section in the first collected layer.

[0079] In a possible design, the location of the first vehicle associated with the collected section in the first collected layer comprises:

[0080] The location of the first vehicle is located in the collected section in the first collected layer.

[0081] In a possible design, before the first collected layer is received, the transceiver module is configured to:

[0082] Send a request message, the request message being used to request a collected layer corresponding to the location of the first vehicle;

[0083] Receive the first collected layer.

[0084] In a possible design, the transceiver module is configured to:

[0085] Send an operation and maintenance event, the operation and maintenance event being used to indicate an operating condition of the first vehicle.

[0086] In a possible design, the transceiver module is configured to receive an updated intelligent driving function, and the processing module is configured to perform driving decision based on the updated intelligent driving function.

[0087] In a possible design, the collected data is used to update cloud configuration information.

[0088] In a possible design, the collection road section is a lane. Alternatively, it is described that the collection road section belongs to a lane level, that is, the collection data involved in the present application is lane-level data.

[0089] In a fifth aspect, an embodiment of the present application provides a data processing apparatus, which comprises a processor. The processor is coupled with a memory and is configured to execute instructions in the memory to implement the method in the first aspect or any possible implementation manner of the first aspect, or to implement the method in the second aspect or any possible implementation manner of the second aspect. Optionally, the data processing apparatus further comprises the memory. Optionally, the data processing apparatus further comprises a communication interface, and the processor is coupled with the communication interface.

[0090] In a sixth aspect, an embodiment of the present application provides a data processing apparatus, which comprises a logic circuit and a communication interface. The communication interface is configured to receive or send information, and the logic circuit is configured to receive or send information through the communication interface, so that the data processing apparatus executes the method in the first aspect or any possible implementation manner of the first aspect, or executes the method in the second aspect or any possible implementation manner of the second aspect.

[0091] In a design, the data processing apparatus is a communication device. When the data processing apparatus is a communication device, the transceiver module can be a transceiver, or the input / output interface; and the processing module can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0092] In another design, the data processing apparatus is a chip (system) or circuit used in a communication device. When the data processing apparatus is a chip (system) or circuit used in a communication device, the transceiver module can be a communication interface (input / output interface), an interface circuit, an output circuit, an input circuit, a pin or related circuit on the chip (system) or circuit; and the processing module can be at least one processor, a processing circuit or a logic circuit.

[0093] In a seventh aspect, an embodiment of the present application provides a computer readable storage medium, which is configured to store a computer program (also referred to as code or instructions). When the computer program runs on a computer, the method in the first aspect or any possible implementation manner of the first aspect, or the method in the second aspect or any possible implementation manner of the second aspect is implemented.

[0094] In an eighth aspect, an embodiment of the present application provides a computer program product, which comprises a computer program (also referred to as code or instructions), and when the computer program is run, causes a computer to execute the method shown in the first aspect or any possible implementation manner of the first aspect, or a method for executing the method shown in the second aspect or any possible implementation manner of the second aspect.

[0095] In a ninth aspect, an embodiment of the present application provides a chip, which comprises a processor, and when the processor executes instructions, causes the chip to execute the method shown in the first aspect or any possible implementation manner of the first aspect, or a method for executing the method shown in the second aspect or any possible implementation manner of the second aspect. Optionally, the chip further comprises a communication interface, which is configured to receive or send signals.

[0096] In a tenth aspect, an embodiment of the present application provides a vehicle end, which comprises at least one data processing apparatus shown in the second aspect, or a data processing apparatus shown in the third aspect, or a data processing apparatus shown in the fourth aspect, or a data processing apparatus shown in the fifth aspect, or a chip shown in the seventh aspect.

[0097] In addition, in the process of executing the method shown in the first aspect or any possible implementation manner of the first aspect, or the method shown in the second aspect or any possible implementation manner of the second aspect, the process of sending information and / or receiving information in the above method can be understood as the process of outputting information by the processor, and / or the process of receiving input information by the processor. When outputting information, the processor can output the information to the transceiver (or the communication interface or the sending module) so as to be transmitted by the transceiver. After being output by the processor, the information can need to be further processed before reaching the transceiver. Similarly, when the processor receives input information, the transceiver (or the communication interface or the sending module) receives the information and inputs it to the processor. Furthermore, after the transceiver receives the information, the information can need to be further processed before being input to the processor.

[0098] Based on the above principle, for example, the sending information mentioned in the foregoing method can be understood as the processor outputting information. For another example, the receiving information can be understood as the processor receiving input information.

[0099] Optionally, for the transmitting, sending and receiving operations of the processor, if no special description is given, or if it is not contrary to the actual role or inherent logic in the related description, it can be more generally understood as the processor outputting and receiving, inputting and the like.

[0100] Optionally, in the process of executing the method shown in the first aspect or any possible implementation manner of the first aspect, or the method shown in the second aspect or any possible implementation manner of the second aspect, the processor can be a processor specially used for executing the method, or a processor that executes the method by executing computer instructions in a memory, such as a general-purpose processor. The memory can be a non-transitory memory, such as a read only memory (ROM), which can be integrated on the same chip as the processor, or can be separately arranged on different chips. The type of the memory and the arrangement manner of the memory and the processor are not limited in the embodiments of the present application.

[0101] In a possible implementation manner, the at least one memory is located outside the apparatus.

[0102] In another possible implementation manner, the at least one memory is located inside the apparatus.

[0103] In yet another possible implementation manner, part of the at least one memory is located inside the apparatus, and another part of the at least one memory is located outside the apparatus.

[0104] In the present application, the processor and the memory can also be integrated in one device, that is, the processor and the memory can also be integrated together. BRIEF DESCRIPTION OF DRAWINGS

[0105] FIG. 1 is a schematic diagram of an architecture of a data collection system according to an embodiment of the present application;

[0106] FIG. 2 is a flowchart of a data processing method according to an embodiment of the present application;

[0107] FIG. 3 is a schematic diagram of a collection layer according to an embodiment of the present application;

[0108] FIG. 4 is a schematic diagram of hierarchical management of a collection layer according to an embodiment of the present application;

[0109] FIG. 5 is a schematic diagram of a data collection scenario according to an embodiment of the present application;

[0110] FIG. 6 is a schematic diagram of a structure of a data processing apparatus according to an embodiment of the present application;

[0111] FIG. 7 is a schematic diagram of a structure of another data processing apparatus according to an embodiment of the present application;

[0112] FIG. 8 is a schematic diagram of a structure of a chip according to an embodiment of the present application. DETAILED DESCRIPTION

[0113] The embodiments of the present application will be described below in conjunction with the accompanying drawings. It should be noted that the words "exemplary" or "for example" in the application are used to mean "an example of" rather than "an ideal". Any embodiment or design solution described as "exemplary" or "for example" in the application should not be construed as being more preferred or advantageous than other embodiments or design solutions. In fact, the use of the words "exemplary" or "for example" is intended to present concepts in a particular manner.

[0114] The "at least one" mentioned in the embodiments of the present application refers to one or more, and "multiple" refers to two or more. "At least one of the following" or the like refers to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, (a and b), (a and c), (b and c), or (a and b and c), where a, b, and c can be single or multiple. "And / or" describes the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects.

[0115] In addition, unless otherwise stated, the ordinal numbers "first", "second", etc. used in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, time sequence, priority or importance of the multiple objects. For example, the first message and the second message are only used to distinguish different message types, and do not mean that the structures, importance, etc. of the two messages are different.

[0116] First, some terms in the present application are explained and described to facilitate understanding by those skilled in the art.

[0117] 1. Map

[0118] The map refers to an electronic map in the form of electronic data, and the map includes road segment information connected to each other, and other related information (such as the level and type of road segment).

[0119] The map information involved in the present application can be a raster map, or a vector map, etc. without limitation. Alternatively, the map information mentioned in the present application can also refer to crowd-sourcing information, road labeling information, etc. without limitation.

[0120] 2. Operational design domain (ODD)

[0121] ODD is also known as design operational range, or design operational condition (ODC), which refers to the operational condition that a certain autonomous driving system or autonomous driving feature is designed to operate. In simple terms, the operational condition of a certain autonomous driving function. For example, the design operational condition can include but is not limited to environment, geographical location, time limit, traffic and road characteristics, vehicle state, driver state, etc.

[0122] 3. Autonomous driving grading standard

[0123] Based on the driving automation level of the vehicle, the existing autonomous driving grading standard J3016TM divides the autonomous driving technology into 6 levels, namely L0-L5 levels, which are no automation (L0), driver assistance (L1), partial automation (L2), conditional automation (L3), high automation (L4) and full automation (L5). Among them:

[0124] L0 is also known as emergency assistance, which is fully controlled by the driver without any active safety configuration.

[0125] L1 is also known as partial driving assistance, in some cases, the automation driving system (ADS) can assist the driver to complete some driving tasks.

[0126] L2 is also known as combined driving assistance, ADS can complete some driving tasks, but the driver needs to monitor the driving environment and ensure that the vehicle can be taken over at any time in case of problems. In this autonomous driving level, the wrong perception and judgment of ADS can be corrected by the driver at any time. Most car companies can provide L2 level ADS, and L2 level can divide the traffic scene into different use scenes by speed, environment, etc. such as low-speed traffic on ring road, fast driving on highway, automatic parking when driver is in the car, etc.

[0127] L3 is also called conditional automated driving, ADS can complete some driving tasks and monitor the driving environment in some cases, that is, ADS can control the vehicle to complete all dynamic driving tasks within the defined ODD, but the driver must be ready to take control of the vehicle. Specifically, ADS issues a control transfer request when it fails or exceeds the ODD range of the corresponding automatic driving level, and the automatic driving grading standard J3016TM also defines that ADS can continue to control the vehicle for a few seconds after issuing the control transfer request, which is used for the driver to prepare to take over the control of the vehicle, such as the driver's hand on the steering wheel, the driver's eyes looking straight ahead, etc., and ADS can determine whether the driver is ready to take over the vehicle by detecting whether the driver's hand is on the steering wheel through the capacitive steering wheel, whether the driver's eyes are looking at the road through the monitoring camera of the driver's seat, etc. If ADS determines that the driver is ready to take over the vehicle, ADS will transfer the control of the vehicle to the driver. Therefore, under this automatic driving level, the driver cannot sleep or deeply rest.

[0128] L4 can also be called high-level automated driving, ADS can complete driving tasks and monitor the driving environment in some environments and specific conditions, that is, ADS can not only complete dynamic driving tasks within ODD, but also handle system failures without the intervention of the driver (since L4 level vehicles do not require drivers, there is no driver under this automatic driving level, only passengers). Currently, L4 level automated driving is mostly used in cities and can be fully automated valet parking or directly combined with a taxi service. Under this automatic driving level, within the corresponding ODD range, all driving-related tasks and passengers have nothing to do with the outside world, and the responsibility of perception is entirely on ADS.

[0129] L5 can also be called full automated driving, ADS can complete all driving tasks under all conditions, that is, fully automated driving without the need to define ODD, and can complete all dynamic driving tasks and handle all dynamic driving task assistance.

[0130] The data processing method provided in the present application can be applied to vehicles with L1 and above automatic driving functions.

[0131] In order to better understand the data processing method provided by the embodiments of the present application, the system architecture and business scenarios of the embodiments of the present application are described below. It should be noted that the system architecture and business scenarios described in the present application are used to more clearly illustrate the technical solutions of the present application, and do not constitute a limitation on the technical solutions provided by the present application. Those skilled in the art can know that with the evolution of system architecture and the appearance of new business scenarios, the technical solutions provided by the present application are also applicable to similar technical problems.

[0132] Exemplarily, FIG. 1 is a schematic diagram of an architecture of a data collection system provided by an embodiment of the present application. The system includes a network side device and a data collection vehicle, wherein the network side device and the data collection vehicle communicate in a wired or wireless manner.

[0133] The network side device can be a device with computing function, for example, the network side device can be a server deployed at the network side, or a component or chip in the server. Alternatively, the network side device can be deployed in a cloud environment / cloud, or in an edge environment. Alternatively, the network side device can be an integrated device, or a plurality of distributed devices, and the present application does not make a specific limitation. For example, the network side device includes but is not limited to: a server or an access point (AP), such as a road side unit (RSU), an evolved Node B (eNB), a radio network controller (RNC), a Node B (NB), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a wireless relay node, a wireless backhaul node, a transmission and reception point (TRP or TP), etc., and can also be a gNB in a new radio (NR) system of 5G, or a transmission point (TRP or TP), one or a group of (including a plurality of antenna panels) antenna panels of a base station in a 5G system, or a network node constituting the gNB or the transmission point, such as a base band unit (BBU), or a distributed unit (DU), etc. For the convenience of understanding, the network side device is taken as a cloud server for example in the following description.

[0134] The data collection vehicle may be, for example, a vehicle with environmental perception capability, decision planning capability and communication capability, or a device, component or chip in the vehicle, such as a vehicle terminal, a vehicle module, an on board unit (OBU), a chip (system) or other components or assemblies, and the embodiments of the present application are not limited in this regard. The perception devices on the vehicle include a vehicle radar (such as a millimeter wave radar, an infrared radar, a light detection and ranging (LiDAR), an ultrasonic radar, a Doppler radar, etc.), a light quantity sensor, a rain quantity sensor, an audio and video sensor (such as a camera, a vehicle event data recorder), a vehicle posture sensor (such as a gyroscope), or a speed sensor (such as a Doppler radar), an inertial measurement unit (IMU), etc.

[0135] By way of example, the data collection vehicle may be a special vehicle for collecting map data, or may be a social vehicle selectively performing data collection, and the present application is not limited in this regard. Here, the number and type of data collection vehicles are not limited.

[0136] In the system, the communication between the network side device and the data collection vehicle can use cellular communication technology, for example, 2G cellular communication, such as global system for mobile communication (GSM), general packet radio service (GPRS); or 3G cellular communication, such as wideband code division multiple access (WCDMA), time division-synchronous code division multiple access (TS-SCDMA), code division multiple access (CDMA), or 4G cellular communication, such as long term evolution (LTE), LTE-vehicle to everything (V2X) wireless communication technology, PC5 communication, or 5G cellular communication, such as new radio (NR)-V2X PC5 communication, or other evolved cellular communication technology. The wireless communication system can also use non-cellular communication technology, such as Wi-Fi and wireless local area network (WLAN) communication, which is not limited herein. In some embodiments, the communication between the above devices can also use infrared link, Bluetooth or ZigBee for direct communication. In some embodiments, the communication between the above devices can also use other wireless protocols, such as various vehicle communication systems, for example, the system can include one or more dedicated short range communications (DSRC) devices, which can include public and / or private data communication between vehicles and / or roadside stations, which is not limited herein.

[0137] The communication system shown in FIG. 1 can be applied in various application scenarios, such as the following application scenarios: mobile internet (MI), self driving, transportation safety, internet of things (IoT), smart city, or smart home, and various scenarios with data collection requirements.

[0138] It should be noted that FIG. 1 is only an exemplary architecture diagram, but does not limit the number of network elements included in the system shown in FIG. 1. Although FIG. 1 does not show, in addition to the functional entities shown in FIG. 1, FIG. 1 can also include other functional entities. In addition, the method provided by the embodiments of the present application can be applied to the data acquisition system shown in FIG. 1, and of course the method provided by the embodiments of the present application can also be applicable to other systems, which are not limited by the embodiments of the present application.

[0139] It can be understood that for the convenience of description, the data acquisition vehicle is referred to as a vehicle in the following description. In the present application, autonomous driving can also be described as intelligent driving, etc., which is not limited.

[0140] Currently, the driving scene data used to train the AI model is mainly obtained by manually driving the work vehicle on the actual road and collecting it through the sensors deployed on the vehicle. However, the efficiency of such data collection is low, and since most driving scenes are convergent, the value of the driving scene data collected by the work vehicle is low, which leads to the AI model trained to perform poorly in some complex or uncommon driving scenes. In addition, there are some collection technologies that manually configure collection rules and vehicle groups according to needs in the cloud, and manually issue specified collection rules to the vehicle group in the specified city, but such manual configuration and issuance exist problems such as untimely data collection, and the specified vehicle group may not be running in the specified city, thereby failing to collect data.

[0141] Based on this, the present application provides a data processing method which can identify high-value collection scenes, and thus can collect higher-quality, more general valuable data, improving data collection quality and efficiency.

[0142] Please refer to FIG. 2, which is a flowchart of a data processing method provided by an embodiment of the present application. The method can be applied to the system architecture described above. The method includes but is not limited to the following steps:

[0143] S201, the cloud server acquires the features of the risk information.

[0144] The feature of the risk information can be the location of the risk information or other features of the risk information, and is not limited. Generally, the location of the risk information can be understood as a location prone to accidents or a location that can have risks, and the like. For example, the location of the risk information can be a latitude and longitude location prone to traffic accidents, a Cartesian coordinate location in the Gauss plane, a location of a road, a location of a road section, and the like, and is not limited. Alternatively, the location of the risk information can also be represented by a risk layer. The other features of the risk information can be features of a location prone to accidents or features of a location that can have risks, and the like. For example, assuming that a road section corresponding to a latitude and longitude range 1 is a road section 1 prone to accidents, and the road section 1 is a T-shaped super-wide intersection, the other features of the risk information can be a T-shaped super-wide intersection. For ease of understanding, the feature of the risk information is taken as the location of the risk information in the following exemplary description.

[0145] Exemplarily, the above risk information can include one or more of the following information: an operation and maintenance event for indicating a vehicle operating condition, map composition abnormal information, indication information of a risk road section, congestion state information, and the like, and is not limited.

[0146] For example, when the risk information is an operation and maintenance event, the location of the risk information can be understood as a location where the operation and maintenance event occurs. When the risk information is map composition abnormal information, the location of the risk information can be understood as a location prone to composition abnormalities in the map composition process. When the risk information is indication information of a risk road section, the location of the risk information can be understood as a location of the risk road section indicated by the indication information, and the like. It should be understood that the cloud server in the present application can automatically mine a collection road section (for example, the collection road section can be a difficult example road section or a difficult example intersection) that needs to be collected according to one or more of the operation and maintenance event, the map composition abnormal information, the indication information of the risk road section, and the like. In this way, manual analysis and identification of road sections prone to problems can be avoided, and the discovery efficiency of the collection road section is improved.

[0147] The operation and maintenance event includes an abnormal operation event of the intelligent driving function in the vehicle and / or an abnormal vehicle condition event of the vehicle. Generally, the operation and maintenance event of the vehicle can be reported by the vehicle to the cloud server. For example, the abnormal operation event of the intelligent driving function includes at least one of the following events: intelligent driving function degradation, intelligent driving function exit, intelligent driving function failure, intelligent driving function abnormal operation, or traffic violation behavior, etc. For example, the intelligent driving function degradation can be, for example, from L2 to L1, and for example, the intelligent driving function degradation can also be from lane centering control (LCC) plus to LCC, etc. The intelligent driving function exit can be, for example, LCC exit, or driver takeover, etc. The intelligent driving function failure can be, for example, autonomous emergency braking (AEB) failure or AEB stop trigger failure, etc. The intelligent driving function abnormal operation can be, for example, AEB abnormal stop, solid line lane change, etc. The traffic violation behavior can be, for example, detection of a solid line, etc.

[0148] For example, the abnormal vehicle condition event of the vehicle includes at least one of the following events: an alarm event of the vehicle, or a component abnormal event of the vehicle. For example, the alarm event of the vehicle can be, for example, a vehicle distance alarm triggered by a too close distance between vehicles, or a collision alarm triggered by a vehicle collision, etc. The component abnormal event of the vehicle can be, for example, tire pressure abnormality, or power battery abnormality, or radar abnormality caused by foggy weather, etc.

[0149] For example, the map configuration abnormal information can be, for example, missing road segment information, low road segment configuration fluency, road complexity, or low configuration and actual road condition fitting degree, etc. For example, the missing road segment information can be the lack of information of a certain country road. The low road segment configuration fluency can be, for example, an error in the connection of the intersection of the crossroads in the configuration of a certain overpass, etc. The road complexity can be, for example, a crossroads, a T-shaped intersection, etc. The low configuration and actual road condition fitting degree can be, for example, the configuration of the exit of a certain roundabout is different from the actual road condition, etc.

[0150] For example, the indication information of the risk road segment can be, for example, the identification of the risk road segment, or the name of the risk road segment, etc. The risk road segment is a road segment where the intelligent driving function of the vehicle has performance abnormalities, for example, assuming that the intelligent driving function of the vehicle has intelligent driving function degradation in a certain road segment A, then the road segment A can be determined as a risk road segment. Alternatively, the risk road segment can also be a road segment prone to traffic congestion, a road segment prone to traffic accidents, a road segment with complex roads, etc.

[0151] S202, determine at least one collection layer based on the features of the risk information.

[0152] One of the collection layers includes the features of one or more collection road segments that need to be collected and the data collection requirements of the one or more collection road segments. For ease of understanding, the following will mainly be described by taking one collection road segment as an example. In one possible design, the collection road segment is a lane. Or it can be described that the collection road segment belongs to the lane level, that is, the collection data involved in the present application is lane-level data. The features of the collection road segment can be the position of the collection road segment or other features, which are not limited in the present application. For example, the other features can be understood as the features of the position of the collection road segment, such as an ultra-wide lane or a large-curvature bend. For example, assuming that the position prone to risk problems is road segment 1, and the road segment 1 is a T-shaped ultra-wide intersection, when determining the collection layer, the collection layer can not only include the T-shaped ultra-wide intersection (i.e., the road segment 1) prone to problems, but also search for other T-shaped ultra-wide intersections in the map as the collection road segments that need to be collected. That is, the collection solution is not a single specific intersection problem, but a type of problem with similar features. For ease of understanding, the following will mainly be described by taking the features of the collection road segment as the position of the collection road segment as an example.

[0153] In one possible implementation, the cloud server can determine the position of the collection road segment according to the position of the risk information. For example, taking the risk information as an operation and maintenance event as an example, assuming that the operation and maintenance event is a downgrade of intelligent driving function, such as a downgrade of intelligent driving function from L2 to L1, and the position of the intelligent driving function downgrade is road segment X, the position of the collection road segment can be determined as road segment X.

[0154] In another possible implementation, the cloud server can also determine the position of the collection road segment according to the position of the risk information in the map. For example, taking the risk information as a congestion state as an example, assuming that the position prone to congestion is the latitude and longitude position range 1, the road segment where the latitude and longitude position range 1 is located can be determined in combination with the map information, for example, road segment Y, and therefore the road segment Y can be determined as the collection road segment that needs to be collected.

[0155] In another possible implementation, the position of the risk information can also be represented by a risk layer, or the position of the risk information included in the risk layer, for example, as shown in FIG. 3, the road and the congestion state of the road can be included in the risk layer, and by analyzing the risk layer shown in FIG. 3, it can be found that the position of the collection section that needs to be collected is intersection 1, and then the data collection requirement corresponding to intersection 1 is determined to obtain a corresponding collection layer. Alternatively, the collection layer involved in the present application is not limited to generating a new layer, but can also be floating on an existing layer. It should be understood that the present application automatically generates the collection layer, which avoids manual formulation of the collection rule and is beneficial to improving the efficiency of formulating the collection rule.

[0156] It should be understood that the position of the collection section can represent the passing information of each direction of the section, such as straight, left turn, right turn, and other direction information, as well as information such as entry and exit points of the intersection. For example, the position of the collection section can include one or more of the following information: the identification of the collection section, the area range of the collection section, the version of the collection section, the identification of the collection track in the collection section, the collection start position of the collection track, the collection end position of the collection track, or the area of the collection track. For example, as shown in FIG. 3, the collection section can be an intersection, for example, a crossroad. For example, taking intersection 1 as the collection section, the position of the intersection that needs to be collected can include the identification of the intersection (i.e., intersection 1), the area range of the intersection, the collection start position of the collection track (e.g., A4), the collection end position of the collection track (e.g., B4), and other information.

[0157] It should be understood that the data collection requirement includes a collection condition and / or a collection state. The collection condition is used to indicate the condition that needs to be met when collecting data. The collection state is used to indicate whether collection is needed or has been completed.

[0158] The above-mentioned collection condition includes a dynamic condition and / or a static condition. For example, the dynamic condition includes one or more of the following: weather, illumination, traffic characteristics, traffic game, or vehicle state. For example, the weather includes sunny, rainy, snowy, foggy, sandstorm, haze, and the like, without limitation. For example, rainy weather can be further divided into light rain, moderate rain, heavy rain, heavy rain, heavy rain, and heavy rain. Illumination includes daytime, nighttime, tunnel, and the like. Alternatively, illumination can also be measured by illuminance (unit: lux). For example, traffic characteristics can include traffic flow, traffic density, and the like. For example, traffic game includes overtaking, pedestrian crossing, and the like. For example, vehicle state can include speed, acceleration, turning, U-turn, uphill, downhill, angle of steering wheel, and the like.

[0159] Exemplarily, the static condition comprises one or more of the following: an identity of the road, a type of the road, a road surface condition, or a data type. For example, the type of the road can comprise a highway, an urban road, a factory road, a forest road, a mountain road, a rural road, etc. The road surface condition can comprise a straight road, a curved road, an obstacle, a slope, a curvature, etc. The data type can comprise data collected by a camera (e.g., video data, image data, etc.), data collected by a radar (e.g., point cloud data, etc.).

[0160] It can be understood that the collection state involved in the present application can comprise a collection state for a collection road section, and / or a collection state for each collection track in the collection road section. For example, assuming that the collection road section is intersection 1, and assuming that intersection 1 comprises 12 directional collection tracks, the collection state can be a collection state for intersection 1, for example, the collection state of intersection 1 is that collection needs to be performed. Alternatively, the collection state can also be a collection state for each collection track in intersection 1, for example, the collection states of collection track 0 to collection track 10 in intersection 1 are that collection needs to be performed, and the collection state of collection track 11 in intersection 1 is that collection does not need to be performed. The present application sets the collection state in this way, which is beneficial to avoid incomplete data collection and repeated data collection.

[0161] Generally, after the cloud server obtains at least one collection layer, the cloud server can manage the corresponding collection layer according to regions and intersections in a hierarchical manner, so that the collection layer of the location of the vehicle or the feature of the location of the vehicle can be accurately issued according to the position of the vehicle in the future. The region in the present application can be a smaller range than a city, for example, a region at the district level, street level, county level, road level, intersection level, etc. For example, as shown in FIG. 4, for city B located in country A, it can comprise a plurality of regions, for example, region 1, region 2, …, region n, wherein each region can comprise a plurality of roads, for example, region 1 comprises road ID1-1 and road ID1-2. Further, road ID1-1 comprises road section ID1-1-1 and road section ID1-1-2, and road ID1-2 comprises road section ID1-2-1 and road section ID1-2-2. Each road section corresponds to a collection layer, for example, road section ID1-1-1 corresponds to collection layer 1, road section ID1-1-2 corresponds to collection layer 2, road section ID1-2-1 corresponds to collection layer 3, and road section ID1-2-2 corresponds to collection layer 4.

[0162] In some possible implementation manners, for the cloud server, when performing the delivery of the collection layer, the cloud server can obtain the position or the feature of the position of the at least one vehicle, and send the corresponding collection layer to the vehicle according to the position or the feature of the position of the vehicle. For example, taking the first vehicle as an example, the cloud server can send the corresponding first collection layer to the first vehicle based on the position of the first vehicle. Correspondingly, the first vehicle receives the first collection layer from the cloud server. It should be understood that the number of the first collection layer can be one or more, and the present application does not limit this. For the convenience of understanding, the first collection layer is taken as one in the following exemplary description.

[0163] The first collection layer belongs to the at least one collection layer, and the position of the first vehicle or the feature of the position of the first vehicle is associated with the collection road segment in the first collection layer. In a possible implementation, the first vehicle can report the position of the first vehicle to the cloud server in real time, so that the cloud server can send the corresponding collection layer to the first vehicle according to the position of the first vehicle. Alternatively, the first vehicle can also send a request message to the cloud server, and the request message is used to request the collection layer corresponding to the position of the first vehicle. It should be understood that the implementation manner that the cloud server delivers the collection layer to the vehicle based on the position of the vehicle reported by the vehicle or based on the request of the vehicle avoids the problem that the cloud server sends all collection layers to the vehicle, resulting in too large file size. At the same time, it also avoids the problem that the position of the vehicle changes, resulting in inaccurate collection information.

[0164] Exemplarily, the position of the first vehicle is associated with the collection road segment in the first collection layer, which can be understood as that the position of the first vehicle is located in the collection road segment in the first collection layer. Alternatively, the position of the first vehicle is associated with the collection road segment in the first collection layer, which can also be understood as that the navigation route between the position of the first vehicle and the destination of the first vehicle overlaps with the collection road segment. Alternatively, the position of the first vehicle is associated with the collection road segment in the first collection layer, which can also be understood as that the area where the collection road segment in the first collection layer is located is the same area as the area to which the position of the first vehicle belongs. Alternatively, the feature of the position of the first vehicle is associated with the collection road segment in the first collection layer, which can be understood as that the feature of the position of the first vehicle is the same as or similar to the feature of the collection road segment. For example, it is assumed that road segment 1 is a T-shaped super-wide intersection, and road segment 2 is a T-shaped super-wide intersection, so it can be considered that the features of road segment 1 and road segment 2 are the same. For another example, it is assumed that road segment 3 is a cross-shaped intersection, and road segment 4 is an X-shaped intersection, so it can be considered that road segment 3 and road segment 4 are similar intersections. For another example, since road segment 1, road segment 2, road segment 3 and road segment 4 are all intersections, it can be considered that the features of road segment 1, road segment 2, road segment 3 and road segment 4 are the same.

[0165] Generally, for the first vehicle, after the first vehicle receives the first data collection layer, the first vehicle can collect corresponding data according to the description of the first data collection layer. For example, the first vehicle can parse the first collection layer, and then determine whether the collection condition is met according to the position of the first vehicle and the position of the collection section and the data collection requirement of the collection section in the first collection layer. If the collection condition is met, the data collection is triggered, and if the collection condition is not met, the data collection is not triggered.

[0166] For example, assuming that the position of the collection section is intersection 1, the identifier of the collection track is track 1, the collection start position of track 1 is A4, and the collection end position of track 1 is B4. The data collection requirement of track 1 is: road ID 1-1, urban road, straight road, camera, sunny day, light intensity > 5 lux, and vehicle speed > 30 km / h. Then, for the first vehicle, the first vehicle can collect the scene data of the collection start position A4 to the collection end position B4 in track 1 through the camera configured by the first vehicle when the first vehicle reaches the intersection 1 of the urban road corresponding to road ID 1-1, drives on the straight road at the intersection 1, and the weather condition is sunny, the light intensity is > 5 lux, and the vehicle speed is > 30 km / h.

[0167] For ease of description, the data collected by the first vehicle can be referred to as first collection data, wherein the first collection data includes scene data of the collection section in the first collection layer. Alternatively, more specifically, in the case where the collection section in the first collection layer includes at least one collection track, the first collection data can include scene data of the first collection track, and the first collection track belongs to the at least one collection track. The number of first collection tracks can be one or more, which is not limited in the present application. Hereinafter, the case where the number of first collection tracks is one will be mainly taken as an example for understanding.

[0168] In some possible implementation manners, after the first vehicle collects the first collection data, the first vehicle can send the first collection data to the cloud server, and correspondingly, the cloud server receives the first collection data from the first vehicle. Further, the cloud server can update the first collection layer according to the first collection data. For example, the cloud server can parse the received first collection data, and perform trajectory matching with the collection trajectory to be collected. For the collection trajectory that matches, the collection state of the collection trajectory included in the first collection layer is modified to obtain an updated first collection layer. For example, taking the first collection data collected by the first vehicle as the scene data of the first collection trajectory, the updated first collection layer can not include the indication information (such as the identifier of the first collection trajectory) of the first collection trajectory, or the collection state of the first collection trajectory in the updated first collection layer indicates that collection is not needed or has been completed. Alternatively, for a collection trajectory, for example, taking the first collection trajectory as an example, a corresponding collection number can also be set. When the actual collection number of the first collection trajectory meets the preset collection number, the first collection layer is updated, that is, the collection state of the first collection trajectory in the first collection layer is modified to be not needed or has been completed.

[0169] In some possible implementation manners, after obtaining the updated first collection layer, if there is a second vehicle requesting a collection layer corresponding to a location or a feature of a location where the second vehicle is located from the cloud server, and the location or the feature of the location where the second vehicle is located is associated with a collection section in the first collection layer, the cloud server can send the updated first collection layer to the second vehicle, which can effectively avoid repeated collection of data. That is, the cloud server can perform trajectory matching on the collected data to suppress the trajectory of the collected data and update the collection layer, and then send the updated collection layer to the vehicle to avoid repeated collection of data.

[0170] Alternatively, the cloud server can also stop sending the collection layer to the vehicle when the collection trajectory associated with the received collection data meets a preset number and belongs to the at least one collection trajectory. That is, the cloud server can perform saturation monitoring on the collected data, which can guarantee the uniformity and completeness of the collection data.

[0171] Optionally, after the cloud server obtains the collected data meeting the requirement, the cloud server can further train / update the intelligent driving function based on the received collected data. Optionally, the cloud server can send the updated intelligent driving function to the vehicle (e.g., the first vehicle) after the training / update is completed, so that the first vehicle can perform driving decision based on the updated intelligent driving function. That is, for the collected data of the collected section of which the trajectory has been completely collected or meets the requirement, data labeling and model (e.g., intelligent driving function model) training are performed. Exemplarily, as shown in FIG. 5, a scene diagram of data collection is shown.

[0172] Optionally, after the cloud server obtains the collected data meeting the requirement, the cloud server can further construct / update the map / update the cloud mapping information based on the received collected data. Optionally, the cloud server can send the updated map / mapping to the vehicle (e.g., the first vehicle) after the map / mapping update is completed. Optionally, after the vehicle receives the updated map / mapping, the first vehicle can use the updated map / mapping for navigation, etc.

[0173] As described above, the present application provides a vehicle-cloud joint data processing method, which can collect data as fine as lane level under limited resources (e.g., traffic limit, transmission speed, etc.). In addition, based on the data processing method provided by the present application, more valuable difficult example data with higher quality and generalization can be collected, and the data collection quality and efficiency are improved.

[0174] The above describes the method of the embodiments of the present application in detail, and the following provides an apparatus for implementing any one of the methods of the embodiments of the present application, for example, an apparatus including modules / units (or means) for implementing each step performed by the device in any one of the above methods.

[0175] Please refer to FIG. 6, which is a structural schematic diagram of a data processing apparatus provided by the embodiments of the present application.

[0176] As shown in FIG. 6, the data processing apparatus 60 can include a transceiver module 601 and a processing module 602. The transceiver module 601 and the processing module 602 can be software, hardware, or a combination of software and hardware.

[0177] The transceiver module 601 can implement the sending function and / or the receiving function, and the transceiver module 601 can also be described as a transceiver module. The transceiver module 601 can also be a unit integrating an acquisition unit (or a receiving unit) and a sending unit, wherein the acquisition unit is used to implement the receiving function, and the sending unit is used to implement the sending function. Optionally, the transceiver module 601 can be used to receive information sent by other apparatuses, and can also be used to send information to other apparatuses.

[0178] In a possible design, the data processing apparatus 60 can correspond to the cloud server or the chip in the first vehicle in the method embodiment shown in FIG.2. The data processing apparatus 60 can include units / modules for performing the operations performed by the cloud server or the first vehicle in the method embodiment shown in FIG.2, and each unit / module in the data processing apparatus 60 is configured to implement the operations performed by the cloud server or the first vehicle in the method embodiment shown in FIG.2. Specifically, the units / modules are as follows:

[0179] In an implementation, when the data processing apparatus 60 is configured to implement the function of the cloud server in the method embodiment shown in FIG.2, the data processing apparatus 60 includes:

[0180] The transceiver 601 is configured to obtain the feature of the risk information.

[0181] The processing module 602 is configured to determine at least one collection layer based on the feature of the risk information, where the collection layer includes the feature of a collection road segment and the data collection requirement of the collection road segment.

[0182] In an implementation, when the data processing apparatus 60 is configured to implement the function of the first vehicle in the method embodiment shown in FIG.2, the data processing apparatus 60 includes:

[0183] The transceiver 601 is configured to receive a first collection layer, where the first collection layer includes the feature of a collection road segment and the data collection requirement of the collection road segment, and the location of the first vehicle is associated with the collection road segment in the first collection layer.

[0184] The transceiver 601 is configured to send first collection data, where the first collection data includes the scene data of the collection road segment in the first collection layer.

[0185] For more details of the processing module 602 and the transceiver 601, refer to the related description in the method embodiment shown in FIG.2.

[0186] Optionally, in the design of the data processing apparatus 60 shown in FIG.6, the data processing apparatus 60 includes:

[0187] In an implementation, the data processing apparatus is a cloud server. When the data processing apparatus is a cloud server, the transceiver can be a transceiver, or an input / output interface; the processing module can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0188] In an implementation, the data processing apparatus is a chip (system) or circuit used in the cloud server. When the data processing apparatus is a chip (system) or circuit used in the cloud server, the transceiving module can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pin, or related circuit on the chip (system) or circuit; and the processing module can be at least one processor, processing circuit, or logic circuit.

[0189] In an implementation, the data processing apparatus is the first vehicle. When the data processing apparatus is the first vehicle, the transceiving module can be a transceiver, or an input / output interface; and the processing module can be at least one processor. Optionally, the transceiver can be a transceiving circuit. Optionally, the input / output interface can be an input / output circuit.

[0190] In an implementation, the data processing apparatus is a chip (system) or circuit used in the first vehicle. When the data processing apparatus is a chip (system) or circuit used in the first vehicle, the transceiving module can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pin, or related circuit on the chip (system) or circuit; and the processing module can be at least one processor, processing circuit, or logic circuit.

[0191] According to the embodiments of the present application, each unit in the apparatus shown in FIG. 6 can be combined into one or several other units respectively or all, or some of the units can be further split into a plurality of units with smaller functions to constitute, which can realize the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above units are divided based on logical functions. In actual application, the function of one unit can also be realized by a plurality of units, or the functions of a plurality of units can be realized by one unit. In other embodiments of the present application, the electronic device can also include other units. In actual application, these functions can also be realized by other units, and can be realized by cooperation of a plurality of units.

[0192] It should be noted that the implementation of each unit can also correspond to the description of the corresponding method embodiments of the above-mentioned FIG. 2, which will not be repeated here.

[0193] Please refer to FIG. 7, which is a structural schematic diagram of another data processing apparatus provided by the embodiments of the present application.

[0194] It should be understood that the data processing apparatus 70 shown in FIG. 7 is only an example, and the data processing apparatus of the embodiments of the present application can also include other components, or include components similar in function to the components in FIG. 7, or not include all the components in FIG. 7.

[0195] The data processing apparatus 70 comprises a communication interface 701 and at least one processor 702.

[0196] The data processing apparatus 70 can correspond to a cloud server or a first vehicle. The communication interface 701 is configured to receive and send signals, and the at least one processor 702 executes program instructions, so that the data processing apparatus 70 implements the corresponding processes of the method performed by the corresponding device in the above-mentioned method embodiment of FIG. 2.

[0197] For the case that the data processing apparatus is a chip or a chip system, the structure of the chip can be referred to the structure of the chip shown in FIG. 8.

[0198] As shown in FIG. 8, the chip 80 comprises a processor 801 and an interface 802. The number of the processor 801 can be one or more, and the number of the interface 802 can be multiple. It should be noted that the functions of the processor 801 and the interface 802 can be realized by hardware design, software design or a combination of hardware and software, which is not limited here.

[0199] Optionally, the chip 80 can further comprise a memory 803, and the memory 803 is configured to store necessary program instructions and data.

[0200] In the present application, the processor 801 can be configured to call the implementation program of one or more devices of the cloud server or the first vehicle in the data processing method provided by one or more embodiments of the present application from the memory 803, and execute the instructions contained in the program. The interface 802 can be configured to output the execution result of the processor 801. In the present application, the interface 802 can be specifically configured to output each message or information of the processor 801.

[0201] The data processing method provided by one or more embodiments of the present application can refer to the above-mentioned embodiments shown in FIG. 2, which will not be repeated here.

[0202] The processor in the embodiments of the present application can be a central processing module (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0203] The memory in the embodiments of the present application is used to provide a storage space, and the storage space can store data such as an operating system and a computer program. The memory includes but is not limited to a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a compact disc read-only memory (CD-ROM).

[0204] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program runs on one or more processors, the method shown in FIG. 2 can be implemented.

[0205] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a computer program product, and the computer program product includes a computer program. When the computer program runs on a processor, the method shown in FIG. 2 can be implemented.

[0206] The embodiments of the present application further provide a system, and the system includes at least one data processing apparatus 60 or data processing apparatus 70 or chip 80 described above, which is used to execute the steps executed by the corresponding devices in any of the embodiments of FIG. 2.

[0207] The embodiments of the present application further provide a system, and the system includes a cloud server and a first vehicle. The cloud server is used to execute the steps executed by the corresponding devices of the cloud server in the embodiments shown in FIG. 2. The first vehicle is used to execute the steps executed by the corresponding devices of the first vehicle in the embodiments shown in FIG. 2.

[0208] The embodiments of the present application further provide a data processing apparatus, and the data processing apparatus includes a processor and an interface. The processor is used to execute the method in any of the method embodiments.

[0209] It should be appreciated that the above data processing apparatus can be a chip. For example, the data processing apparatus can be a field programmable gate array (FPGA), can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, can also be a system chip (SoC), can also be a central processor unit (CPU), can also be a network processor (NP), can also be a digital signal processing circuit (DSP), can also be a micro controller unit (MCU), can also be a programmable logic device (PLD) or other integrated chip. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware code processor execution, or executed by hardware and software module combination in code processor. The software module can be located in random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, register and other mature storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above method.

[0210] It is to be appreciated that the memory in the embodiments of the application can be volatile, nonvolatile, or a combination of both. The non-volatile memory can be, for example, read only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. The volatile memory can be, for example, random access memory (RAM), which acts as external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It is to be appreciated that the system and method described herein can employ any of such memories or drives or a combination thereof.

[0211] In the embodiments described above, all or some of the steps can be implemented by using software, hardware, firmware or any combination thereof. When implemented by using software, all or some of the steps can be implemented by using one or more computer programs. When the computer programs are loaded into and executed by a computer, all or some of the steps described in the embodiments of the present application are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatuses. The computer programs can be stored in a computer readable storage medium, or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer programs can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium or a set of one or more available media that is accessible by a computer, or a data storage device such as a server, data center, etc. that includes one or more available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, high-density digital video disc (DVD)), or a semiconductor medium (for example, solid state disk (SSD)), etc.

[0212] The units in the various device embodiments described above and the electronic devices in the method embodiments correspond completely, and the corresponding steps are performed by the corresponding modules or units, for example, the transceiving module (transceiver) performs the steps of receiving or transmitting in the method embodiments, and other steps except for transmitting and receiving can be performed by the processing module (processor). The functions of the specific units can refer to the corresponding method embodiments. The processor can be one or more.

[0213] It can be understood that the electronic device in the embodiments of the present application can perform some or all of the steps in the embodiments of the present application, and these steps or operations are only examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, each step can be performed in a different order from the order presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application are performed.

[0214] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0215] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0216] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0217] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0218] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0219] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk, and various media that can store program codes.

[0220] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A data processing method, characterized by, The method comprises: obtaining risk information features; determining at least one collection layer based on the risk information features, the collection layer comprising features of a collection section and data collection requirements of the collection section.

2. The method of claim 1, wherein, The risk information comprises one or more of the following information: operation and maintenance events indicating vehicle operating conditions, map composition anomaly information, or indication information of a risk section, wherein the risk section is a section where the performance of the intelligent driving function of the vehicle is abnormal.

3. The method of claim 2, wherein, The operation and maintenance events comprise abnormal operation events of the intelligent driving function in the vehicle and / or vehicle condition abnormal events of the vehicle. The abnormal operation events of the intelligent driving function comprise at least one of the following events: intelligent driving function degradation, intelligent driving function exit, intelligent driving function failure, intelligent driving function abnormal operation, or traffic violation behavior. The vehicle condition abnormal events comprise at least one of the following events: an alarm event of the vehicle, or a component abnormal event of the vehicle.

4. The method according to any one of claims 1 to 3, characterized in that, The features of the collection section comprise the location of the collection section, which comprises one or more of the following information: the identification of the collection section, the area range of the collection section, the version of the collection section, the identification of a collection track in the collection section, the collection start position of the collection track, the collection end position of the collection track, and the area of the collection track.

5. The method according to any one of claims 1 to 4, characterized in that, The data collection requirements comprise collection conditions and / or collection states, the collection conditions being used to indicate conditions that need to be met for data collection, and the collection states being used to indicate whether collection is needed.

6. The method of claim 5, wherein, The collection conditions comprise dynamic conditions and / or static conditions. The dynamic conditions comprise one or more of the following: weather, light, traffic features, traffic game, or vehicle state. The static conditions comprise one or more of the following: road identification, road type, road surface condition, or data type.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: obtaining the location of at least one vehicle; sending a corresponding first collection layer to a first vehicle in the at least one vehicle, wherein the first collection layer belongs to the at least one collection layer, and the location of the first vehicle is associated with a collection section in the first collection layer.

8. The method of claim 7, wherein, The location of the first vehicle is located within the collection section in the first collection layer. The method further comprises:

9. The method according to claim 7 or 8, characterized in that, receiving first collection data from the first vehicle, the first collection data comprising scene data of a collection section in the first collection layer. The collection section in the first collection layer comprises at least one collection track, the first collection data comprises scene data of a first collection track, and the first collection track belongs to the at least one collection track.

10. The method of claim 9, wherein, The method further comprises: updating the first collection layer according to the first collection data. The updated first collection layer does not comprise indication information of the first collection track, or the collection state of the first collection track in the updated first collection layer indicates that collection is not needed.

11. The method of claim 10, wherein, ​ 12. The method according to any one of claims 9-11, characterized in that, The method further comprises: In a case where the received collection data is associated with a collection track satisfying a preset number and belonging to at least one collection track included in the collection section of the first collection layer, updating the intelligent driving function based on the received collection data.

13. The method according to any one of claims 1 to 12, characterized in that, The collection section is a lane.

14. A data processing method, characterized by, Comprise: receiving a first collection layer, the first collection layer comprising characteristics of a collection section requiring data collection and data collection requirements of the collection section, wherein a position of the first vehicle is associated with the collection section in the first collection layer; sending first collection data, the first collection data comprising scene data of the collection section in the first collection layer.

15. The method of claim 14, wherein, The position of the first vehicle is associated with the collection section in the first collection layer, comprising: The position of the first vehicle is located in the collection section in the first collection layer.

16. The method according to claim 14 or 15, characterized in that Before the method further comprises: sending a request message, the request message being used to request a collection layer corresponding to the position of the first vehicle; receiving the first collection layer.

17. The method of claim 14 or 15, wherein, The method further comprises: sending an operation and maintenance event, the operation and maintenance event being used to indicate the running status of the first vehicle.

18. The method according to any one of claims 14-17, characterized by, The method further comprises: receiving an updated intelligent driving function; performing driving decisions based on the updated intelligent driving function.

19. The method according to any one of claims 14-18, characterized by, The collection section is a lane.

20. A data processing apparatus, characterized in that, Comprise units or modules for performing the method as claimed in any one of claims 1-13, or comprise units or modules for performing the method as claimed in any one of claims 14-19.

21. A data processing apparatus, characterized in that, Comprise a processor and a communication interface, The communication interface is used to receive computer execution instructions and transmit to the processor; The processor is used to execute the computer execution instructions to enable the data processing device to perform the method as claimed in any one of claims 1-13, or perform the method as claimed in any one of claims 14-19.

22. A computer-readable storage medium, characterized in that, Comprise: The computer readable storage medium is used to store instructions or computer programs; when the instructions or the computer programs are executed, the method as claimed in any one of claims 1-13 is realized, or the method as claimed in any one of claims 14-19 is realized.

23. A computer program product, characterised in that, Comprise computer program code, when the computer program code is run on a computer, to realize the method as claimed in any one of claims 1-13, or to realize the method as claimed in any one of claims 14-19.

Images