Data processing method, system and device applied to mobile control and storage medium

Abstract

The embodiment of the invention provides a data processing method, system and device applied to mobile control and a storage medium. The method comprises the steps that road features related to a target area are acquired, the target area comprises a target normal area and a target auxiliary area, and the road complexity of the target normal area is lower than that of the target auxiliary area; obtaining a road information generation model, wherein the road information generation model is a machine learning model; generating target auxiliary information corresponding to the target auxiliary area according to a road information generation model and the road features; based on the target auxiliary information, a first road element set corresponding to the target auxiliary area is obtained, and the first road element set is used for assisting a second road element set corresponding to the target auxiliary area so that the terminal can execute a first movement control operation degree corresponding to the target auxiliary area.

Description

Technical Field

[0001] The present invention relates to the field of mobile control technology, and in particular to a data processing method, system, device and storage medium applied to mobile control. Background Art

[0002] The field of mobile control, such as autonomous driving and intelligent robots, is a way to achieve unmanned real-time operation of terminals through a processor-based automation system. Taking autonomous driving as an example, autonomous vehicles rely on the collaboration of artificial intelligence, visual computing, detection radar, monitoring devices and positioning systems to enable the system to automatically and safely control vehicles without real-time human operation. During the driving process of autonomous vehicles, the stability and safety of autonomous driving are reduced due to the difficulty of perception, positioning, prediction, decision-making and planning for more complex scenes such as intersections with complex road conditions and multi-layer areas.

[0003] Therefore, it is hoped to provide a data processing solution for mobile control, which can efficiently and accurately perform mobile control operations such as perception, positioning, prediction, decision-making and planning when passing through complex scenarios during the mobile control process. Summary of the invention

[0004] This specification provides a data processing solution for mobile control, which can efficiently and accurately perform mobile control perception, positioning, prediction, decision-making and planning operations when passing through complex scenarios during the mobile control process.

[0005] One or more embodiments of the present specification provide a data processing method for mobile control, the data processing method for mobile control comprising: acquiring road features related to a target area, the target area comprising a target normal area and a target auxiliary area, the road complexity of the target normal area being lower than the road complexity of the target auxiliary area; acquiring a road information generation model, the road information generation model being a machine learning model; generating target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features; acquiring a first road element set corresponding to the target auxiliary area based on the target auxiliary information, the first road element set being used to assist a second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, the accuracy of the first road element set being greater than the accuracy of the second road element set.

[0006] One or more embodiments of the present specification provide a data processing method for mobile control, the data processing method for mobile control comprising: acquiring historical mobile data of a target area, a terminal generating historical mobile data based on movement of a fourth road element set in the target area, the target area comprising a target normal area and a target auxiliary area, the road complexity of the target normal area being lower than the road complexity of the target auxiliary area; determining abnormal data based on the historical mobile data; determining target auxiliary information corresponding to the target auxiliary area based on the abnormal data; acquiring a first road element set corresponding to the target auxiliary area based on the target auxiliary information, the first road element set being used to assist a second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, the accuracy of the first road element set being greater than the accuracy of the second road element set and the fourth road element set.

[0007] One or more embodiments of the present specification provide a data processing system for mobile control, the data processing system for mobile control comprising: a feature acquisition module, for acquiring road features related to a target area, the target area comprising a target normal area and a target auxiliary area, the road complexity of the target normal area being lower than the road complexity of the target auxiliary area; a model acquisition module, for acquiring a road information generation model, the road information generation model being a machine learning model; an information generation module, for generating target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features; a road element set generation module, for acquiring a first road element set corresponding to the target auxiliary area based on the target auxiliary information, the first road element set being used to assist a second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, the accuracy of the first road element set being greater than the accuracy of the second road element set.

[0008] One or more embodiments of the present specification provide a data processing device applied to mobile control, wherein the data processing device applied to mobile control includes: at least one storage medium storing computer instructions; and at least one processor executing the computer instructions to implement a data processing method applied to mobile control.

[0009] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a data processing method applied to mobile control. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0011] Figure 1 is an exemplary schematic diagram of an application scenario of a data processing system applied to mobile control according to some embodiments of this specification;

[0012] Figure 2 is an exemplary module diagram of a data processing device applied to mobile control according to some embodiments of this specification;

[0013] Figure 3 is an exemplary flow chart of a data processing method applied to mobile control according to some embodiments of this specification;

[0014] Figure 4 is an exemplary flow chart of a terminal performing a first mobile control operation and a second mobile control operation according to some embodiments of this specification;

[0015] Figure 5A and Figure 5B is an exemplary schematic diagram of a road information generation model according to some embodiments of this specification;

[0016] Figure 6 is an exemplary flow chart of obtaining a road information generation model according to some embodiments of this specification;

[0017] Figure 7 is an exemplary schematic diagram of an area that a terminal is about to pass through according to some embodiments of this specification;

[0018] Figure 8 is an exemplary schematic diagram of a sample area according to some embodiments of the present specification;

[0019] Fig. 9 This is another exemplary flow chart of the data processing method applied to mobile control according to some embodiments of the present specification. DETAILED DESCRIPTION

[0020] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0021] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0022] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0023] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes.

[0024] Figure 1 It is an exemplary schematic diagram of the application scenario of the data processing system applied to mobile control according to some embodiments of this specification. The system and method in this application can be applied to the scenario of autonomous driving vehicles, for example, pure unmanned driving scenarios without drivers, assisted driving modules in vehicles and other scenarios. The assisted driving module in the vehicle can autonomously control the vehicle's driving, and can also output driving prompts to the driver. The vehicle can be applied to land, sea, aerospace, etc., or any combination thereof. The vehicle may include taxis, private cars, ride-sharing, shared vehicles, buses, trains, motor vehicles, high-speed railways, subways, ships, airplanes, spacecraft, hot air balloons, bicycles, tricycles, motorcycles, robots, etc., or any combination thereof. The system and method of this application can also be applied to the scenario of automatic mobile robots, for example, food delivery robots, inspection robots and other scenarios. In some embodiments, the data processing system 100 applied to mobile control can implement the methods and / or processes disclosed in this specification to achieve efficient and accurate operations such as perception, positioning, prediction, decision-making and planning of autonomous driving when passing through complex scenes during autonomous driving.

[0025] In some embodiments, Figure 1 As shown, an application scenario 100 of a data processing system for mobile control may include a processing device 110 , a terminal 120 , a user terminal 130 , a storage device 140 and a network 150 .

[0026] The processing device 110 may be used to process data and / or information from at least one component of the data processing system 100 applied to mobile control or an external data source (e.g., a cloud data center). For example, the processing device 110 may obtain a road information generation model. For another example, the processing device 110 may use the road information generation model to determine the classification category of the area that the terminal is about to pass. For another example, the processing device may obtain a first road element set and a second road element set of the target auxiliary area, and a third road element set corresponding to the target normal area, and control the terminal to perform a first mobile control operation and / or a second mobile control operation. In some embodiments, the processing device 110 may include a central processing unit (CPU), a digital signal processor (DSP), a system on a chip (SoC), a microcontroller unit (MCU), a computer, a user console, etc., or any combination thereof. In some embodiments, the processing device 110 may include a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 110 may be local or remote. In some embodiments, the processing device 110 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof. In some embodiments, the processing device 110 may be integrated or included in one or more other components (eg, the terminal 120 , the user terminal 130 ) of the data processing system 100 for mobile control.

[0027] The terminal 120 may be a mobile device for a data processing system applied to mobile control. For example, the terminal 120 may be a vehicle, a robot, etc. In some embodiments, the terminal 120 may receive instructions issued by the processing device 110 and complete corresponding tasks according to the instructions. For example, the terminal 120 may receive instructions for executing a first mobile control operation and a second mobile control operation, and automatically control the terminal 120 to complete the corresponding operations. In some embodiments, the terminal 120 may include a control component, a positioning component (e.g., a GPS module), a timing component (e.g., a timer), a sensor component (e.g., a motion sensor, a pressure sensor, a radar sensor, an infrared sensor, and a camera), a communication component (e.g., a GPS communication module, a short-range wireless communication module, etc.), etc. The terminal 120 may also autonomously control the terminal under the coordinated action of the control component, the positioning component, the timing component, the sensor component, and the communication component. In some embodiments, the terminal 120 may realize communication with at least one component of the data processing system 100 applied to mobile control through the network 150. For example, the terminal 120 may send the current location information of the terminal to the processing device 110 and / or the user terminal 130 through the network 150.

[0028] The user terminal 130 can realize the interaction between the user and the data processing system 100 applied to mobile control. In some embodiments, the user terminal 130 can be a terminal device used by the user when using the data processing service. In some embodiments, the user terminal 130 can display the current path planning of the terminal 120 to the user. In some embodiments, the user terminal 130 can include a mobile device, a tablet computer, a laptop computer, other devices with input and / or output functions, etc. or any combination thereof.

[0029] The storage device 140 may be used to store data, instructions, and / or any other information. For example, the storage device may store a trained path generation model, an electronic map of standard accuracy, and the like. In some embodiments, the storage device may include a random access memory (RAM), a read-only memory (ROM), a mass storage device, a removable memory, a volatile read-write memory, and the like, or any combination thereof. In some embodiments, the storage device may be integrated or included in one or more other components (e.g., the processing device 110, the terminal 120, the user terminal 130) of the data processing system 100 for mobile control.

[0030] The network 150 can facilitate the exchange of information and / or data. In some embodiments, one or more components of the data processing system 100 applied to mobile control (e.g., the processing device 110, the terminal 120, the user terminal 130, the storage device 140) can send information and / or data to other components of the data processing system 100 applied to mobile control through the network 150. For example, the terminal 120 can obtain the trained road information generation model from the processing device 110 via the network 150. For another example, the processing device 110 can obtain the current location information of the terminal from the processing device 110 via the network 150. In some embodiments, the network 150 may include any one or more of a wired network or a wireless network. In some embodiments, the network 150 may include a cable network, an optical fiber network, a telecommunications network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network (ZigBee), a near field communication (NFC), an in-device bus, an in-device line, a cable connection, etc. or any combination thereof. In some embodiments, the network connection between the components of the data processing system 100 for mobile control can adopt one of the above methods or multiple methods. In some embodiments, the network can be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures.

[0031] Positioning system 160 may include one or more satellites, such as satellite 160-1, satellite 160-2, and satellite 160-3. In some embodiments, positioning system 160 may be a global positioning system (GPS), a global navigation satellite system (GLONASS), a compass navigation system (COMPASS), a Beidou navigation satellite system, a Galileo positioning system, a quasi-zenith satellite system (QZSS), etc. Positioning system 160 may send navigation signals to a positioning component in terminal 120 via a wireless connection.

[0032] It is worth noting that the data processing system 100 applied to mobile control is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made according to the description of this specification. For example, the data processing system 100 applied to mobile control may also include a database, an information source, etc. For another example, the data processing system 100 applied to mobile control may be implemented on other devices to achieve similar or different functions. However, these changes and modifications will not deviate from the scope of this specification.

[0033] Figure 2 200 is an exemplary block diagram of a data processing device for mobile control according to some embodiments of the present specification. In some embodiments, the data processing device 200 for mobile control may be implemented by a control component in the processing device 110 or the terminal 120. In some embodiments, Figure 2 As shown, the data processing device 200 applied to mobile control may include: a feature acquisition module 210 , a model acquisition module 220 , an information generation module 230 , a road element set generation module 240 and / or a control module 250 .

[0034] The feature acquisition module 210 can be used to acquire road features related to the target area. In some embodiments, the target area may include a target normal area and a target auxiliary area. In some embodiments, the road complexity of the target normal area is lower than the road complexity of the target auxiliary area. In some embodiments, the feature acquisition module 210 can perform one or more of the following operations: acquiring a first road feature of the target area; dividing the target area into a target normal area and a target auxiliary area based on the road information generation model and the first road feature. In some embodiments, the feature acquisition module 210 can divide the target area into a target auxiliary area and a target normal area based on abnormal data.

[0035] The model acquisition module 220 can be used to acquire a road information generation model. In some embodiments, the road information generation model is a machine learning model. In some embodiments, the model acquisition module 220 can perform one or more of the following operations: acquiring road features of the sample area as training samples; acquiring a sample normal area, a sample auxiliary area, and sample auxiliary information corresponding to the sample auxiliary area corresponding to the sample area as label data; training an initial road information generation model based on the training samples and label data, and acquiring a trained road information generation model. In some embodiments, the road complexity of the sample normal area is lower than the road complexity of the sample auxiliary area. In some embodiments, the model acquisition module 220 can perform one or more of the following operations: acquiring historical movement data of the sample area; determining driving abnormality data based on the historical movement data; determining the sample normal area, the sample auxiliary area, and the sample auxiliary information corresponding to the sample auxiliary area based on the driving abnormality data. In some embodiments, the historical movement data can be generated based on the sample road element set corresponding to the sample area. In some embodiments, the accuracy of the sample road element set corresponds to the accuracy of the second road element set and / or the third road element set. In some embodiments, the model acquisition module 220 may perform one or more of the following operations: clustering the driving abnormality data based on the spatial position to obtain at least one abnormal data set; obtaining the abnormal information corresponding to each abnormal data set; determining the sample normal area and the sample auxiliary area based on the abnormal information corresponding to each abnormal data set. In some embodiments, the abnormal information includes at least one of the following: the number of driving abnormalities, the driving abnormality characteristics, and the severity of the driving abnormality. In some embodiments, the model acquisition module 220 may perform one or more of the following operations: determining the cause of the driving abnormality according to the driving abnormality data corresponding to the sample auxiliary area; determining the sample auxiliary information corresponding to the sample auxiliary area based on the driving abnormality cause.

[0036] The information generation module 230 can be used to generate target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features. In some embodiments, the road information generation model may include a first model and a second model. In some embodiments, the road features associated with the target area may include the first road features of the target area and the second road features of the target auxiliary area. In some embodiments, the information generation module 230 may perform one or more of the following operations: input the first road features of the target area to the first model; the first model outputs the target normal area and the target auxiliary area; input the second road features of the target auxiliary area to the second model; the second model outputs the target auxiliary information corresponding to the target auxiliary area. In some embodiments, the road features associated with the target area include the first road features of the target area. In some embodiments, the information generation module 230 may perform one or more of the following operations: input the first road features of the target area to the road information generation model; the road information generation model outputs the target normal area, the target auxiliary area, and the target auxiliary information corresponding to the target auxiliary area of ​​the target area. In some embodiments, the information generation module 230 may perform one or more of the following operations: obtain the historical movement data of the target area; determine the abnormal data based on the historical movement data; determine the target auxiliary information corresponding to the target auxiliary area based on the abnormal data. In some embodiments, the terminal generates historical movement data based on the fourth road element set in the target area.

[0037] The road element set generation module 240 may be used to obtain a first road element set corresponding to the target auxiliary area based on the target auxiliary information. In some embodiments, the first road element set is used to assist the second road element set corresponding to the target auxiliary area so that the terminal performs a first movement control operation corresponding to the target auxiliary area. In some embodiments, the accuracy of the first road element set is greater than the accuracy of the second road element set.

[0038] The control module 250 is used to control the terminal to perform a mobile operation. In some embodiments, the control module 250 may perform one or more of the following operations: obtaining the current location information of the terminal; based on the current location information, determining whether the terminal is currently located in the target auxiliary area or the target normal area; in response to the terminal being currently located in the target auxiliary area, obtaining the first road element set and the second road element set corresponding to the target auxiliary area; according to the first road element set and the second road element set, causing the terminal to perform a first mobile control operation corresponding to the target auxiliary area; in response to the terminal being currently located in the target normal area, obtaining the third road element set corresponding to the target normal area; according to the third road element set, causing the terminal to perform a second mobile control operation corresponding to the target normal area. In some embodiments, the accuracy of the first road element set is greater than the accuracy of the third road element set. In some embodiments, the control module 250 may perform one or more of the following operations: in response to the terminal being currently located in the target normal area, determining whether the terminal is about to enter the target auxiliary area based on the current location information; in response to the terminal being about to enter the target auxiliary area, loading the first road element set corresponding to the target auxiliary area.

[0039] It should be noted that the above description of the data processing device 200 and its modules for mobile control is only for convenience of description and cannot limit the present specification to the scope of the embodiments. It is understandable that after understanding the principle of the device, those skilled in the art may arbitrarily combine the modules or form sub-devices to connect with other modules without deviating from the principle. In some embodiments, Figure 2 The modules disclosed in the specification may be different modules in a system, or one module may realize the functions of two or more modules. For example, each module may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0040] Figure 3 It is an exemplary flow chart of a data processing method applied to mobile control according to some embodiments of the present specification. In some embodiments, process 300 can be executed by a control component of the processing device 110 or the terminal 120. For example, process 300 can be executed by a data processing device 200 applied to mobile control implemented by a control component of the processing device 110 or the terminal 120. For example, process 300 can be stored in a storage device in the form of a program or an instruction, and when the data processing device 200 applied to mobile control executes the instruction, process 300 can be implemented. The operational diagram of process 300 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 3The order in which the operations of flow 300 are illustrated and described below is not intended to be limiting.

[0041] Step 310 , obtaining road features related to the target area. Specifically, step 310 may be performed by the feature acquisition module 210 .

[0042] The target area can be an administrative division area (for example, a city, a district, etc.), or a dedicated area for mobile control, or other areas, and this application is not limited. In some embodiments, the target area may include a target normal area and a target auxiliary area. The target auxiliary area refers to an area where the terminal needs to be controlled to pass smoothly based on a high-precision (for example, an accuracy of centimeters or higher than centimeters) road element set. The target normal area refers to an area where the terminal can be controlled to pass smoothly without a high-precision road element set. In some embodiments, the road complexity of the target normal area is lower than the road complexity of the target auxiliary area. Road complexity can characterize the complexity of the road structure and / or traffic conditions. For example, the road structure of a certain target normal area is a straight road, and the road structure of a certain target auxiliary area is a multi-layer road, a confluence area of ​​multiple straight roads or a complex intersection, etc. For another example, there is less traffic in a certain target normal area, and more traffic in a certain target auxiliary area.

[0043] In some embodiments, the feature acquisition module 210 may divide the target area into a target normal area and a target auxiliary area. In some embodiments, the feature acquisition module 210 may use a road information generation model to divide the target area into a target normal area and a target auxiliary area. Specifically, the feature acquisition module 210 may acquire a first road feature of the target area. For a detailed description of the first road feature, see below. Further, the feature acquisition module 210 may divide the target area into a target normal area and a target auxiliary area based on the road information generation model and the first road feature. For a detailed description of dividing the target area into a target normal area and a target auxiliary area based on the road generation model and the first road feature, see Figure 5A and Figure 5B and its related description.

[0044] In some embodiments, the feature acquisition module 210 can divide the target area into one or more target auxiliary areas and / or one or more target normal areas based on preset judgment rules. For example, the key elements of the target area can be obtained, and then it is determined whether the key elements meet the preset judgment rules, so as to divide the target area. As an example only, the key elements of the target area such as "multi-layer roads", "number of intersections", "number of merging lanes", "number of traffic-sensitive areas (such as schools, hospitals, etc.)", "peak traffic volume", etc. can be obtained based on the existing map. The preset judgment rules may include: the area in the target area that meets two or more of the following conditions: "number of intersections ≥ 3", "number of merging lanes ≥ 3", "number of traffic-sensitive areas (such as schools, hospitals, etc.) ≥ 1", "peak traffic volume ≥ 50 / lane / minute", and "multi-layer roads" is judged as a target auxiliary area, otherwise it is a target normal area. For example, Figure 7 As shown, the key elements of area 1 are "number of intersections = 0", "number of merging lanes = 0" and "number of traffic sensitive areas = 0", and the key elements of area 2 are "number of merging lanes = 4" and "number of traffic sensitive areas = 1", then area 1 is judged as the target normal area and area 2 is the target auxiliary area.

[0045] In some embodiments, the feature acquisition module 210 may determine the division result of the target area based on the manual annotation of the user.

[0046] In some embodiments, the feature acquisition module 210 may divide the target area into a target auxiliary area and a target normal area according to the abnormal data.

[0047] Abnormal data may be data that indicates that the terminal cannot travel normally based on the fourth road element set during the historical process of passing through the target area. Specifically, the feature acquisition module 210 may acquire historical movement data of the target area. The historical movement data may be historical operation data of the terminal when traveling in the target area. The terminal generates historical movement data based on the fourth road element set when traveling in the target area. In some embodiments, the accuracy of the first road element set is greater than the accuracy of the fourth road element set. For more descriptions of historical movement data, see the relevant description of historical autonomous driving data in step 620. Further, the feature acquisition module 210 may determine abnormal data based on historical movement data. For a detailed description of determining abnormal data based on historical movement data, see the relevant description of determining driving abnormal data based on historical autonomous driving data in step 620. For dividing the target area into a target auxiliary area and a target normal area based on abnormal data, see the relevant description of determining a sample normal area and a sample auxiliary area based on driving abnormal data in step 620.

[0048] In some embodiments, the target area division result may also vary according to time. For example, for target area A, the peak traffic period may be divided into the target auxiliary area, and other time periods with less traffic may be divided into the target normal area.

[0049] Road features may be features that reflect road environment information. In some embodiments, road features may include at least one of road structure features, traffic control sign information, and traffic flow features. Road structure features are features that can reflect road structures and the correlation between roads. For example, road structure features may include road types (such as motor vehicle lanes, non-motor vehicle lanes, sidewalks, etc.), number of roads, number of merging lanes, intersection types (such as crossroads, T-junctions, etc.), number of intersections, road connection structures, road topology, etc. Traffic control sign information may be information on traffic signs and / or traffic control signs. For example, traffic control sign information may include signs or road surface signs for traffic-sensitive areas (such as schools, hospitals, etc.), driving rules (such as speed limits, one-way streets, lane lines, turn signs, sidewalks, stop lines, etc.), and traffic light logic rules, such as the current indication color of a traffic light (such as red, green, and yellow), the remaining time of the current indication color, and the color change rule (such as 20s red light-5s yellow light-20s green light-5s yellow light). Traffic flow characteristics may be characteristics that reflect the amount of traffic of traffic participants (such as vehicles, pedestrians, etc.) per unit time. For example, traffic flow characteristics may include the current vehicle flow of each lane, the pedestrian flow on the crosswalk, etc. In some embodiments, the feature acquisition module 210 may acquire road structure characteristics and traffic control sign information from a map stored in the terminal 120. In some embodiments, the feature acquisition module 210 may acquire traffic flow characteristics based on big data (for example, including real-time traffic trajectories uploaded by vehicles and pedestrians).

[0050] The road feature associated with the target area may include a first road feature of the target area or a second road feature of the auxiliary area. The first road feature may be a feature reflecting the road environment information of the target area. The second road feature may be a feature reflecting the road environment information of the target auxiliary area.

[0051] In some embodiments of the present specification, road characteristics include road structure characteristics, traffic control sign information and traffic flow characteristics, so that the road characteristics are defined based on the complexity of the road structure itself and the real-time changing traffic complexity, so that the division results and the first element set of the target area obtained based on the road characteristics are more realistic.

[0052] In some embodiments of the present specification, the road information generation model is used to obtain the classification category of the target area and the target auxiliary information of the target auxiliary area, which can improve the accuracy of the division and improve the richness of the elements in the first road element set.

[0053] Step 320 , obtaining the road information to generate the model. Specifically, step 320 may be performed by the model acquisition module 220 .

[0054] The road information generation model may be a model for generating road information of a target area. The road information may include the division result of the target area and the target auxiliary elements corresponding to the target auxiliary area. In some embodiments, the road information generation model may be a machine learning model. Specifically, in some embodiments, the road information generation model may include but is not limited to a Gaussian distribution Bayesian model, a decision tree model, a random forest model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, or a combination of one or more thereof. For a description of obtaining a road information generation model, see Figure 6 and its description.

[0055] In some embodiments, the road generation model may also be a model obtained based on preset rules, which is not limited in this embodiment.

[0056] Step 330 , generating target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features. Specifically, step 330 may be performed by the information generation module 230 .

[0057] The target auxiliary information corresponding to the target auxiliary area may be information related to the first road element set. For a detailed description of the first road element set, see step 340. The target auxiliary information includes one or a combination of the accuracy, type, location, quantity, etc. of the road elements in the first road element set.

[0058] For a detailed description of generating a model and road features based on road information and generating target auxiliary information corresponding to the target auxiliary area, see Figure 5A and Figure 5B Related description.

[0059] In some embodiments, the first control module 230 may also input the current traffic period of the terminal (eg, morning rush hour, evening rush hour, idle period), weather information (eg, heavy fog, rainy days), etc. into the second model.

[0060] In some embodiments, the feature acquisition module 210 may determine the target auxiliary information corresponding to the target auxiliary area according to the abnormal data. For a detailed description of determining the target auxiliary information corresponding to the target auxiliary area according to the abnormal data, refer to the description of determining the sample auxiliary information corresponding to the sample auxiliary area according to the driving abnormal data in step 620.

[0061] Step 340 : Based on the target auxiliary information, obtain a first road element set corresponding to the target auxiliary area. Specifically, step 340 may be performed by the road element set generation module 240 .

[0062] The first road element set corresponding to the target auxiliary area may be a set of road elements with greater precision in the target auxiliary area. Among them, the road elements may be elements on the road that have an impact on driving. In some embodiments, the first road element set corresponding to the target auxiliary area is used to assist the second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area. Among them, the second road element set corresponding to the target auxiliary area may be a set of road elements with less precision in the target auxiliary area. In some embodiments, the precision of the first road element set is greater than that of the second road element set. Specifically, the more types of road elements in the road element set and the higher the accuracy, the greater the precision of the corresponding road element set. As an example only, the road elements in the first road element set may include physical lane lines, virtual lane lines at intersections, operating logic of traffic lights, multi-layer road space structures, road signs (e.g., sidewalks, stop lines, turn arrows, road signs, road signs, etc.), road edges, obstacles on the road (e.g., electric poles, street lights, road separators, etc.), buildings on both sides of the road and their entrances and exits, etc., and the road elements in the second road element set may include lanes, intersections, landmark buildings on both sides of the road, etc. As another example, the position and size errors of the road elements in the first road element set are at or below the centimeter level, and the position and size errors of the road elements in the second road element set are greater than the centimeter level, for example, at the decimeter level or the meter level.

[0063] In some embodiments, the road element set generation module 240 can generate the high-precision road elements required for the target auxiliary information by extracting and annotating the historical autonomous driving data (also referred to as historical mobile data) of the target auxiliary area using automated algorithms and / or manual labeling, thereby generating a first road element set.

[0064] In some embodiments, the processing device 110 may pre-generate a first road element set corresponding to the target auxiliary area, and store the first road element set in the storage device 140 and / or a storage device in the processing device 110, or send the first road element set to the terminal 120. In some embodiments, the road element set generation module 240 may obtain the first road element set from the processing device 110, the storage device 140, or the terminal 120.

[0065] In some embodiments, the target area division result and the first road element set can be verified. For example, the target area division result and the first road element set are verified by means of advanced simulator simulation test, terminal actual test, etc. It is judged whether the terminal can smoothly pass through the target normal area and the target auxiliary area according to the low-precision map. If the terminal can smoothly pass through the target normal area according to the low-precision map, but cannot smoothly pass through the target auxiliary area, it is considered that the target area division result has passed the verification. It is judged whether the terminal can normally pass through the target auxiliary area according to the first road element set and the second road element set. If the terminal can normally pass through the target auxiliary area according to the first road element set and the second road element set, it is considered that the first road element set has passed the verification. For another example, through rule verification, it is verified whether the target area division result and the first road element set meet some rules summarized in history. For example, the rules may include that high-risk scenes such as complex intersections, multi-layer areas, and intersection ramps need to be divided into target auxiliary areas, and complex intersections at least need to know the traffic light control logic and road right information, multi-layer areas at least need to know the hierarchical division and inter-layer connection information, and ramp merging areas at least need to know the intersection and whether there is traffic light protection. If the target area division result and / or the first road element set fails to pass the verification, the test result is added to the historical autonomous driving data, and the target area division result and / or the first road element set are re-determined.

[0066] For a detailed description of the terminal performing the first movement control operation corresponding to the target auxiliary area, please refer to Figure 4 and its related description.

[0067] It should be noted that the above description of process 300 is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made according to the description of this specification. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, process 300 may include one or more additional operations, or one or more operations may be omitted.

[0068] Figure 4It is an exemplary flow chart of the terminal performing the first mobile control operation and the second mobile control operation according to some embodiments of the present specification. In some embodiments, process 400 can be executed by the control component of the processing device 110 or the terminal 120. For example, process 400 can be executed by a data processing device 200 (for example, a control module 250) applied to mobile control implemented by the control component of the processing device 110 or the terminal 120. For example, process 400 can be stored in a storage device in the form of a program or instructions, and when the data processing device 200 (for example, the processing device 110) applied to mobile control or the data processing device 200 (for example, the control module 250) applied to mobile control executes the instructions, process 400 can be implemented. The operational diagram of process 400 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 4 The order in which the operations of flow 400 are illustrated and described below is not intended to be limiting.

[0069] Step 410, obtaining the current location information of the terminal.

[0070] The current location information of the terminal may include the current positioning position of the terminal. In some embodiments, the control module 250 may obtain the current location of the terminal through the positioning component of the terminal. The current location information of the terminal may further include environmental information corresponding to the current positioning position of the terminal. In some embodiments, the control module 250 may obtain corresponding environmental information using an electronic map and / or a sensor (e.g., a camera, a lidar, etc.). The environmental information corresponding to the current location of the terminal may be road features (e.g., road structure, road elements, etc.) within a preset range (e.g., 10m, 20m, 50m, etc.) of the current location of the terminal, or may be related information (e.g., moving trajectory, moving speed, position, moving direction, size, category, etc.) of other terminals and pedestrians within a preset range (e.g., 10m, 20m, 50m, etc.) of the current location of the terminal.

[0071] Step 420: Based on the current location information, determine whether the terminal is currently located in the target auxiliary area or the target normal area.

[0072] In some embodiments, the processing device 110 may pre-divide the target area into one or more target auxiliary areas and / or one or more target normal areas (eg, offline). Detailed description of dividing the target area may refer to the related description of step 310 .

[0073] Specifically, the control module 250 may obtain the division result of the target area, and determine whether the current location of the terminal is located in the target auxiliary area or the target normal area based on the division result. In some embodiments, the processing device 110 may pre-divide the target area into one or more target auxiliary areas and / or one or more target normal areas to obtain the division result, and store the division result in the storage device 140 and / or the storage device in the processing device 110, or send it to the terminal 120. In some embodiments, the control module 250 may obtain the division result from the processing device 110, the storage device 140, or the terminal 120.

[0074] Step 430 , in response to the terminal currently being located in the target auxiliary area, executing steps 332 and 334 .

[0075] Step 432: Acquire a first road element set and a second road element set corresponding to the target auxiliary area.

[0076] In some embodiments, the control module 250 may generate the first road element set based on the target auxiliary information. For the description of generating the first road element set based on the target auxiliary information, please refer to step 340 and its related description, which will not be repeated here.

[0077] In some embodiments, the control module 250 may generate target auxiliary information corresponding to the target auxiliary area based on the driving abnormality data in the historical autonomous driving data of the target auxiliary area, and then generate a first road element set corresponding to the target auxiliary area according to the target auxiliary information. For detailed description, see Figure 6 And the related description will not be repeated here.

[0078] In some embodiments, the control module 250 may obtain the second road element set corresponding to the target auxiliary area from a relatively low-precision electronic map. For example, the control module 250 may obtain map data of the target auxiliary area from a standard-precision electronic map. For another example, the relatively low-precision electronic map may also be a map with a precision between a standard-precision map and a high-precision map.

[0079] In some embodiments, the second road element set may include road elements in the target auxiliary area collected in real time by a camera, a sensor (eg, a laser radar), etc. of the terminal 120 .

[0080] Step 434: According to the first road element set and the second road element set, the terminal is enabled to perform a first movement control operation corresponding to the target auxiliary area.

[0081] The first mobile control operation may be an operation for controlling the terminal to drive in the target auxiliary area. Specifically, the control module 250 may automatically control the terminal to perform operations such as perception, positioning, prediction, decision-making, and planning based on the first road element set and the second road element set, so that the terminal can smoothly pass through the target auxiliary area. The first mobile control operation may also include outputting a driving operation prompt for the terminal to pass through the first target auxiliary area for the driver's reference.

[0082] Step 440 , in response to the terminal currently being located in the target normal area, execute steps 442 and 444 .

[0083] Step 442: Acquire a third road element set corresponding to the target normal area.

[0084] The third road element set corresponding to the target normal area may be a road element set of the target normal area with lower precision. In some embodiments, the precision of the first road element set is greater than that of the third road element set. For more description of the third road element set, see the description of the second road element set in step 432.

[0085] In some embodiments, the control module 250 may obtain the third road element set corresponding to the target normal area from a relatively low-precision electronic map. For example, the control module 250 may obtain map data of the target normal area from a standard-precision electronic map. For another example, the relatively low-precision electronic map may also be a map with a precision between a standard-precision map and a high-precision map.

[0086] In some embodiments, the third road element set includes road elements in the target normal area collected in real time by a camera, sensor (eg, lidar) or the like of the terminal.

[0087] Step 444: According to the third road element set, the terminal is enabled to perform a second movement control operation corresponding to the target normal area.

[0088] The second mobile control operation may be an operation for controlling the terminal to drive in the target normal area. Specifically, the control module 250 may automatically control the terminal to perform operations such as perception, positioning, prediction, decision-making, and planning according to the third road element set, so that the terminal can smoothly pass through the target normal area. The second mobile control operation may also include outputting a driving operation prompt for the terminal to pass through the target normal area for the driver's reference.

[0089] In some embodiments of the present specification, the target area is divided into a target auxiliary area and a target normal area, and then road element sets of different precisions are obtained for different division categories, so that the terminal can dynamically adjust the precision of the obtained road element set according to the road environment that actually changes during driving, so that the precision of the road element set matches the actual environment, while avoiding the waste of terminal computing resources and improving the efficiency and accuracy of terminal autonomous driving.

[0090] In some embodiments, in response to the terminal being currently located in the target normal area, the control module 250 may determine whether the terminal is about to enter the target auxiliary area based on the current location information. Specifically, the control module 250 may determine the area that the terminal is about to enter based on the current location information. The area that the terminal is about to enter may be an area corresponding to the estimated location where the terminal is located after traveling a preset time and / or a preset distance from the current positioning location.

[0091] In some embodiments, the acquisition control module 250 can further acquire the path planning information of the terminal. The path planning information of the terminal can be the path of the terminal from the current position to the target position and the environmental information corresponding to the path. The environmental information corresponding to the path can be the road characteristics of the path (for example, road structure, road elements, etc.). In some embodiments, the acquisition module 210 can determine the path based on the current position and the target position through a path planning algorithm, and then obtain the corresponding environmental information using an electronic map. In some embodiments, the path planning algorithm can include but is not limited to a combination of one or more of the Dijkstra algorithm, the graph search method, the fast search random tree algorithm, the artificial potential field algorithm, etc.

[0092] In some embodiments, in the absence of path planning information, the control module 250 can determine the possible driving path of the terminal based on the current location information of the terminal. For example, if the terminal is currently driving on a road without an intersection, the corresponding possible driving path of the terminal is the path along the road. For another example, if the terminal is currently driving on a road with an intersection ahead, the corresponding possible driving path of the terminal includes the following four: go straight, turn left, turn right, and turn around.

[0093] The preset time may be a preset default time, for example, 5s, 10s, 15s, 20s, 30s, 1min, 2min, 5min, 10min, etc. The preset distance may be a preset default distance, for example, 10m, 20m, 50m, 100m, 200m, 500m, etc.

[0094] The preset time and / or preset distance can also be set according to the actual situation of the driving path. For example, when the current time is in the peak period (for example, 7:00-9:00 am, 5:00-7:00 pm), the driving speed is slow due to the large traffic volume on the road, and the preset time can be set to be longer, for example, 2min, 5min, 10min, etc. For another example, when the current time is in the idle period (for example, 2:00-4:00 pm), the traffic volume on the road is small and the driving speed is fast, so the preset time can be set to be shorter, for example, 5s, 10s, 15s, 20s, 30s, 1min, etc. For another example, when the terminal is driving on a highway, since the road structure changes less within a certain distance, the preset distance and / or preset time can be set to be longer, for example, the preset distance is 500m, 600m, etc., and the preset time is 2min, 5min, 10min, etc. For another example, when the terminal is traveling on a city road, since the road structure varies greatly within a certain distance, the preset distance and / or preset time can be set shorter, for example, the preset distance is 10m, 20m, 50m, 100m, etc., and the preset time is 5s, 10s, 15s, 20s, 30s, 1min, etc.

[0095] In some embodiments, the control module 250 may obtain the division result of the target area, and determine based on the division result whether the estimated position of the terminal after traveling a preset time and / or a preset distance from the current positioning position is located in the target auxiliary area or the target normal area. Specifically, the control module 250 may determine the estimated position of the terminal after traveling a preset time and / or a preset distance from the current positioning position based on the path planning information or the possible driving path, and then determine whether the estimated position is located in the target auxiliary area or the target normal area.

[0096] As an example, Figure 7 As shown, the control module 250 is based on the current location A of the terminal and the path planning information between the current location A and the target location (for example, Figure 7 The estimated position of the terminal is determined to be B, and the estimated position B is judged to be located in the target auxiliary area (area 2), then the control module 250 believes that the terminal is about to enter the target auxiliary area.

[0097] In some embodiments, in response to the terminal about to enter the target auxiliary area, the control module 250 may load the first road element set corresponding to the target auxiliary area. Loading the first road element set corresponding to the target auxiliary area refers to reading the first road element set stored in the storage space (e.g., hard disk) into the running space (e.g., memory).

[0098] In some embodiments of the present specification, the first road element set corresponding to the target auxiliary area is loaded in advance when the terminal is about to enter the target auxiliary area. When the terminal is actually located in the target auxiliary area, the first road element set can be directly run, thereby saving time for obtaining the first road element set and avoiding problems in control operations caused by insufficient loading.

[0099] It should be noted that the above description of process 300 is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made according to the description of this specification. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, process 300 may include one or more additional operations, or one or more operations may be omitted.

[0100] It should be noted that the above description of process 400 is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made according to the description of this specification. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, process 400 may include one or more additional operations, or one or more operations may be omitted.

[0101] Figure 5A and Figure 5B is an exemplary schematic diagram of a road information generation model according to some embodiments of this specification. In some embodiments, Figure 5A and Figure 5B It may be executed by a control component of the processing device 110 or the terminal 120. For example, Figure 5A and Figure 5B The data processing device 200 for mobile control may be implemented by a control component of the processing device 110 or the terminal 120. For example, Figure 5A and Figure 5B It can be stored in the storage device in the form of a program or instruction. When the automatic driving control device 200 executes the instruction, it can achieve Figure 5A and Figure 5B The following is presented Figure 5A and Figure 5B The schematic diagram of the execution process of is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 5A and Figure 5B The order in which the operations are illustrated and described below is not intended to be limiting.

[0102] like Figure 5A As shown, the road information generation model may include a first model and a second model.

[0103] The first model may be a model for dividing the target area. Figure 5A As shown, the processing device 110 may input a first road feature of a target area into the first model, and the first model may output a target normal area and a target auxiliary area.

[0104] In some embodiments, the first model may first vectorize the first road feature of the target area to obtain a first road vector, then encode the first road vector to obtain a first road code, then map the first road code to a numerical value or probability, and then obtain the target normal area or the target auxiliary area based on the numerical value or probability.

[0105] In some embodiments, the first model may be a classification model. In some embodiments, the classification model may be, but is not limited to, a support vector machine model, a logistic regression model, a naive Bayes classification model, a Gaussian distribution Bayes classification model, a decision tree model, a random forest model, a KNN classification model, a neural network model, or a combination of one or more thereof.

[0106] In some embodiments, the processing device 110 may also input the traffic time period (e.g., morning peak, evening peak, idle time period) and weather information (e.g., foggy, rainy days) of the terminal's current travel into the first model, which is not limited in this embodiment. As an example only, the processing device 110 inputs the traffic flow characteristics of the morning peak, evening peak, and idle time period into the first model respectively, and the processing device 110 may output the division results of the target areas corresponding to the three traffic time periods respectively.

[0107] The second model may be a model for determining target auxiliary information. Figure 5A As shown, the processing device 110 can input the second road feature of the target auxiliary area into the second model, and the second model outputs the target auxiliary information corresponding to the target auxiliary area.

[0108] In some embodiments, the processing device 110 may obtain the second road feature from the first road feature based on the target auxiliary area. For example, the processing device 110 may use the road feature of area 2 as the second road feature from the first road feature based on area 2 being the target auxiliary area.

[0109] In some embodiments, the second model may first vectorize the second road feature of the target auxiliary area to obtain a second road vector, then encode the second road vector to obtain a second road code, and then decode the second road code to obtain target auxiliary information corresponding to the target auxiliary area.

[0110] like Figure 5BAs shown, the road information generation model can be a model that simultaneously outputs the target area division and the target auxiliary area corresponding to the target auxiliary area. In some embodiments, the processing device 110 can input the first road feature of the target area to the road information generation model, and the road information generation model outputs the target normal area, the target auxiliary area, and the target auxiliary area corresponding to the target auxiliary area.

[0111] In some embodiments, the road information generation model can first vectorize the first road feature of the target area to obtain a third road vector, then encode the third road vector to obtain a third road code, and then obtain the target normal area, target auxiliary area and target auxiliary information corresponding to the target auxiliary area based on the third road code.

[0112] As an example only, the processing device 110 can input the first road feature of the target area 700 into the road information generation model, and the road information generation model can output: the target auxiliary area "area 2", the target normal area "the remaining areas of the target area 700 except area 2 (including area 1)" and the target auxiliary information corresponding to the target auxiliary area "area 2".

[0113] In some embodiments, the road information generation model may include but is not limited to a combination of one or more of a Logistic regression model, a Naive Bayes classification model, a Gaussian distribution Bayes classification model, a decision tree model, a random forest model, a KNN classification model, an ELMo (Embedding from Language Models) model, a GPT (Generative Pre-Traxining) model, a BERT (Bidirectional Encoder Representation from Transformers) model, and the like.

[0114] In some embodiments of the present specification, the road information generation model can be flexibly set to two structures according to needs: when the determination method of the target area division category is diverse or manual annotation is required for further correction, the road information generation model can be set to a first model and a second model respectively, so as to correct and / or verify the judgment result of the first model; when it is necessary to quickly obtain road information, the road information generation model can be set to a model that simultaneously outputs the target area division category and the target auxiliary information, so as to improve the efficiency of road information generation.

[0115] Figure 6 is an exemplary schematic diagram of obtaining a road information generation model according to some embodiments of this specification. In some embodiments, Figure 6The processing device 110 or the data processing apparatus 200 for mobile control (eg, the model acquisition module 220) may be executed, or the processing device 110 may be executed by a third party. Figure 6 The schematic diagram is illustrative. In some embodiments, the process may be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 6 The order in which the operations are illustrated and described below is not intended to be limiting.

[0116] Step 610: Acquire road features in the sample area as training samples.

[0117] The sample area may be a historical travel area of ​​the terminal. The road feature of the sample area may be a feature reflecting the road environment information of the sample area. For a detailed description of the sample road feature, please refer to the related description of the first road feature, which will not be repeated here.

[0118] In some embodiments, the model acquisition module 220 can obtain road features of the sample area from maps and / or big data (for example, including real-time traffic trajectories uploaded by terminals and pedestrians).

[0119] Step 620 , obtaining a sample normal area, a sample auxiliary area, and sample auxiliary information corresponding to the sample auxiliary area corresponding to the sample area as label data.

[0120] The sample auxiliary area is an area in the sample area that requires auxiliary information to control the terminal to drive automatically. The sample normal area is an area in the sample area that does not require auxiliary information to control the terminal to drive automatically. In some embodiments, the road complexity of the sample normal area is lower than the road complexity of the sample auxiliary area. For a detailed description of the road complexity, please refer to the relevant description of step 320. The sample auxiliary information corresponding to the sample auxiliary area can be information of road elements with higher precision in the sample auxiliary area.

[0121] Specifically, the model acquisition module 220 can acquire the historical automatic driving data of the sample area. The historical automatic driving data of the sample area can be the operation data of the terminal when driving in the sample area. In some embodiments, the historical automatic driving data can be generated based on the sample road element set corresponding to the sample area. Among them, the sample road element set corresponding to the sample area can be a road element set of the sample area with lower precision. In some embodiments, the precision of the sample road element set corresponds to the precision of the second road element set and / or the third road element set. For a detailed description of the sample road element set, please refer to the relevant description of the second road element set, which will not be repeated here.

[0122] In some embodiments, when the terminal passes through the sample area, the terminal can automatically control the terminal to perform perception, positioning, prediction, decision-making and planning operations based on the sample road element set, so that the terminal passes through the sample auxiliary area and obtains historical automatic driving data during the terminal's driving process.

[0123] In some embodiments, the model acquisition module 220 can obtain historical automatic driving data from the storage device of the terminal. The historical automatic driving data includes a historical driving trajectory. The historical driving trajectory includes a plurality of trajectory points, each trajectory point corresponds to a time point, and the time point corresponds to a position, speed, and driving direction. The historical automatic driving data further includes the surrounding environment information perceived and observed by the terminal during the historical driving trajectory (for example, road information, surrounding vehicles, pedestrian information, etc.).

[0124] Furthermore, in some embodiments, the model acquisition module 220 may determine driving abnormality data based on historical automatic driving data. Driving abnormality data may be data indicating that the terminal cannot drive normally based on the sample road element set during the passage of the sample area. For example, the terminal deviates from the historical planned path, the speed of the terminal does not meet the driving speed corresponding to the historical planned path, the terminal collides, stops driving, etc.

[0125] Furthermore, in some embodiments, the model acquisition module 220 may determine the sample normal area, the sample auxiliary area, and the sample auxiliary information corresponding to the sample auxiliary area according to the abnormal driving data.

[0126] In some embodiments, the model acquisition module 220 may cluster the driving abnormality data based on the spatial position to obtain at least one abnormal data set. The abnormal data set may be a collection of driving abnormality data at abnormal positions in the sample area. Specifically, the model acquisition module 220 may cluster the driving abnormality data with similar occurrence distances based on the occurrence location of the driving abnormality data, obtain at least one abnormal data set, and determine the center position (position center or frequency center) of the occurrence location of multiple driving abnormality data in each abnormal data set as the abnormal position. In some embodiments, clustering may include but is not limited to a combination of one or more of the following algorithms: K-MEANS clustering algorithm, mean shift clustering algorithm, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm, etc.

[0127] In some embodiments, the model acquisition module 220 can obtain the abnormal information corresponding to each abnormal data set. The abnormal information can be the abnormal data statistics of each abnormal data set. In some embodiments, the abnormal information includes at least one of the following: the number of driving abnormalities, the driving abnormality characteristics, and the severity of driving abnormalities. Among them, the driving abnormality characteristics can be the specific manifestation characteristics of the terminal driving abnormality, such as collision, sudden braking, slowing down, etc. The driving abnormality characteristics can include the description of the abnormal problem. For example, the problem description of the terminal conflicting with other terminals at an intersection with heavy traffic and unable to pass through the intersection smoothly includes: on which side the terminal conflict occurs, resulting in the terminal having no way to pass; the environmental information around the terminal (surrounding vehicles, etc.); the field data perceived and observed by the terminal sensor when the conflict occurs. For another example, the problem description of the terminal entering the wrong intersection at a complex intersection or multi-layer area includes: which intersections the terminal faces; the positional relationship between these intersections; which is the correct intersection;; which intersection the terminal chooses; the environmental information around the terminal (surrounding vehicles, etc.); the field data perceived and observed by the terminal sensor during the terminal's passage through the intersection.

[0128] The severity of driving anomalies can indicate the degree of completion of the terminal on the historical planned path and the risk caused by the anomaly. For example, the severity of driving anomalies may include: not serious "the terminal drives according to the historical planned path, but the driving time exceeds the planned time by less than 15 minutes"; more serious "the terminal drives according to the historical planned path, but the driving time exceeds the planned time by more than 15 minutes", "the terminal drives according to the historical planned path, but there are sudden brakes and / or multiple decelerations"; serious "the terminal deviates from the historical planned path", "the terminal collides", "the terminal stops driving", "the terminal is manually taken over", etc.

[0129] In some embodiments, the model acquisition module 220 can determine the sample normal area and the sample auxiliary area based on the abnormal information corresponding to each abnormal data set. Specifically, the model acquisition module 220 can screen the calibrated abnormal data set whose abnormal information meets the judgment rules from the abnormal data set, and then determine the abnormal position corresponding to the calibrated abnormal data set as the calibrated position, and then circle all the calibrated positions according to the preset division range as one or more sample auxiliary areas, and determine the remaining areas without calibrated positions as one or more sample normal areas according to the preset division range. As an example only, the judgment rules may include: the number of driving abnormalities exceeds 3 times; and / or the abnormal information includes more than 2 times of "more serious" or more than 1 time of "serious".

[0130] Just as an example, Figure 8 is an exemplary schematic diagram of a sample area according to some embodiments of this specification, such as Figure 8As shown, the model acquisition module 220 determines the abnormal positions D, E, ... I corresponding to the calibrated abnormal data set as the calibration positions, and then circles the area containing the calibration positions D, E, and F as the sample auxiliary area 1 according to a preset division range (represented by a dotted ellipse in the figure), and circles the area containing the calibration positions G, H, and I as the sample auxiliary area 2, and determines the remaining uncalibrated positions as one or more sample normal areas, such as the sample normal area 1, according to the preset division range (represented by a dotted ellipse in the figure).

[0131] In some embodiments, the model acquisition module 220 can determine the cause of the driving abnormality based on the driving abnormality data corresponding to the sample auxiliary area. As an example only, the driving abnormality cause may include the driving abnormality caused by the lack of a certain road element in the road element set corresponding to the sample auxiliary area and / or the low accuracy of a certain road element. Specifically, the model acquisition module 220 can obtain the calibration abnormality data set corresponding to the calibration position in the sample auxiliary area, and then analyze the abnormality cause of each calibration abnormality data set to obtain the driving abnormality cause corresponding to each sample auxiliary area.

[0132] In some embodiments, the model acquisition module 220 may determine the sample auxiliary information corresponding to the sample auxiliary area based on the driving abnormality cause. Specifically, the model acquisition module 220 may determine the road elements missing from the sample road element set, the road elements with too low precision, etc. in each sample auxiliary area based on the driving abnormality cause corresponding to each sample auxiliary area, and then acquire the corresponding missing road elements and road elements with higher precision, and use the corresponding missing road elements and road elements with higher precision as the corresponding sample auxiliary information.

[0133] In some embodiments, the division of the sample normal area, the sample auxiliary area, and the sample auxiliary information can be verified. For example, the division of the sample normal area, the sample auxiliary area, and the sample auxiliary information are verified by means of advanced simulator simulation testing, terminal actual testing, etc. It is determined whether the terminal can smoothly pass through the sample normal area and the sample auxiliary area according to the low-precision map (sample road element set). If the terminal can smoothly pass through the sample normal area according to the low-precision map, but cannot smoothly pass through the sample auxiliary area, it is considered that the division result of the sample normal area and the sample auxiliary area has passed the verification. Generate a high-precision road element set corresponding to the sample auxiliary information. It is determined whether the terminal can normally pass through the sample auxiliary area according to the high-precision road element set and the part of the sample road element set corresponding to the sample auxiliary area. If the terminal can normally pass through the sample auxiliary area according to the high-precision road element set and the part of the sample road element set corresponding to the sample auxiliary area, the abnormal problem corresponding to the sample auxiliary area has not been reproduced and there is no other negative effect caused by the sample auxiliary information, then it is considered that the sample auxiliary information has passed the verification. For another example, through rule verification, it is verified whether the division of the sample normal area, the sample auxiliary area, and the sample auxiliary information conform to some rules summarized in history. If the division of the sample normal area, sample auxiliary area and / or the sample auxiliary information fails to pass the verification, the test result is added to the historical automatic driving data, and the division of the sample normal area, sample auxiliary area and / or the sample auxiliary information is re-determined.

[0134] Step 630: Train an initial road information generation model based on the training samples and label data to obtain a trained road information generation model.

[0135] In some embodiments, the model acquisition module 220 can input training samples into the initial road information generation model, and construct a first loss function based on the predicted normal area, predicted auxiliary area, predicted auxiliary information corresponding to the predicted auxiliary area and label data output by the initial road information generation model, and update the parameters of the initial road generation model by minimizing the first loss function, thereby obtaining a trained road information generation model.

[0136] In some embodiments, the model acquisition module 220 may first train the first model based on the training samples. Specifically, the model acquisition module 220 may input the training samples into the initial first model, and construct a second loss function based on the predicted normal region, predicted auxiliary region output by the initial first model and the sample normal region and sample auxiliary region in the label data, and update the parameters of the initial first model by minimizing the second loss function, thereby acquiring the trained first model.

[0137] Furthermore, in some embodiments, the model acquisition module 220 can acquire road features corresponding to the sample auxiliary areas based on the sample auxiliary areas in the label data and based on the sample auxiliary areas in the training samples and the label data, input the road features corresponding to the sample auxiliary areas into the initial second model, and construct a third loss function based on the predicted auxiliary information corresponding to the sample auxiliary areas output by the initial second model and the sample auxiliary information set in the label data, update the parameters of the initial second model by minimizing the third loss function, and thereby obtain the trained second model.

[0138] In some embodiments, joint training can be performed to obtain the first model and the second model. Specifically, the model acquisition module 220 can input the training sample into the initial first model, and output the predicted normal area and the predicted auxiliary area based on the initial first model. The road features corresponding to the predicted auxiliary area are acquired based on the training sample and the predicted auxiliary area, the road features corresponding to the predicted auxiliary area are input into the initial second model, and the predicted auxiliary information is output based on the initial second model. A fourth loss function is constructed based on the predicted auxiliary information corresponding to the predicted auxiliary area output by the initial second model and the sample auxiliary information set in the label data, a fifth loss function is constructed based on the predicted normal area, the predicted auxiliary area output by the initial first model and the sample normal area and the sample auxiliary area in the label data, and the parameters of the initial first model and the parameters of the initial second model are updated by minimizing the fourth loss function and the fifth loss function, thereby obtaining the trained first model and the second model.

[0139] In some embodiments of the present specification, by analyzing historical automatic driving data, it is determined that there are insufficient road elements in the sample road element set, and sample auxiliary information is determined as label data based on the insufficiency of the sample road element set, so that the road information generation model can learn to obtain the first road element set by analyzing the insufficiency of the second road element set.

[0140] In some embodiments, the target normal area, the target auxiliary area and the target auxiliary information can be directly determined according to the method of acquiring the label data in step 620.

[0141] In some embodiments, the road information generation model may be updated periodically or aperiodically, thereby updating the division result of the target area and the first road element set.

[0142] It can be seen from the way of obtaining the label data in step 620 that the first road element set is not a set of high-precision road elements in the global target area, nor is it a set of all high-precision road elements in the target auxiliary area. The first road element set is used to supplement the deficiencies of road elements in the target auxiliary area in the low-precision map (for example, insufficient accuracy, insufficient variety of road elements, etc.), and therefore includes fewer high-precision road elements. Therefore, the terminal 120 requires less operating space when running the first road element set, and the cost of generating, updating and maintaining the first road element set is also lower.

[0143] It should be noted that the above description of process 600 is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made according to the description of this specification. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, process 600 may include one or more additional operations, or one or more operations may be omitted.

[0144] Fig. 9 It is another exemplary flow chart of the data processing method applied to mobile control shown in some embodiments of this specification. In some embodiments, process 900 can be executed by the control component of the processing device 110 or the terminal 120. For example, process 900 can be executed by a data processing device 200 applied to mobile control implemented by the control component of the processing device 110 or the terminal 120. For example, process 900 can be stored in a storage device in the form of a program or an instruction, and when the data processing device 200 applied to mobile control executes the instruction, process 900 can be implemented. The operational diagram of process 900 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 3 The order in which the operations of flow 900 are illustrated and described below is not intended to be limiting.

[0145] In step 910, the feature acquisition module 210 acquires historical movement data of the target area, and the terminal generates the historical movement data by moving in the target area based on the fourth road element set, wherein the target area includes a target normal area and a target auxiliary area, and the road complexity of the target normal area is lower than the road complexity of the target auxiliary area. For a detailed description of the historical movement data, refer to the relevant description of the historical automatic driving data in step 620, and the fourth road element set is similar to the sample road element set, and will not be repeated here.

[0146] Step 920: The information generation module 230 determines abnormal data based on the historical movement data. For a detailed description of determining abnormal data based on historical movement data, please refer to the description of determining driving abnormal data based on historical autonomous driving data in step 620.

[0147] Step 930: The information generation module 230 determines the target auxiliary information corresponding to the target auxiliary area according to the abnormal data. For a detailed description of determining the target auxiliary information corresponding to the target auxiliary area according to the abnormal data, refer to the description of determining sample auxiliary information based on driving abnormal data in step 620.

[0148] Step 940: The road element set generation module 240 obtains a first road element set corresponding to the target auxiliary area based on the target auxiliary information (see the description of step 340 for details), wherein the first road element set is used to assist the second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, and the accuracy of the first road element set is greater than that of the second road element set and the fourth road element set.

[0149] In some embodiments, the target area may be divided into a target normal area and a target auxiliary area, and the specific division method is described in step 310. For example, according to abnormal data, the target area is divided into a target auxiliary area and a target normal area.

[0150] In this application, the autonomous driving scenario is taken as an example. Figure 2-Figure 9 Describe it, so you can understand it. Figure 2-Figure 9 The described method and / or system may also be applicable to other mobile control scenarios, such as intelligent robots, etc.

[0151] The present application provides a control device for data processing and autonomous driving for mobile control, the device comprising: at least one storage medium storing computer instructions; at least one processor executing the computer instructions to implement the control method for data processing and autonomous driving for mobile control described in the present application (for example, Figure 3 , Figure 5A , Figure 5B , Figure 6 , Fig. 9 The process) and / or the mobile control method (for example, Figure 4 The process 400).

[0152] The present application provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions, the computer executes the control method for data processing and automatic driving for mobile control described in the present application (for example, Figure 3 , Figure 5A , Figure 5B , Figure 6 , Fig. 9 The process) and / or the mobile control method (for example, Figure 4 The process 400).

[0153] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) dividing the target area into a target auxiliary area and a target normal area, and then obtaining road element sets of different precisions for different division categories, so that the terminal can dynamically adjust the precision of the obtained road element set according to the road environment that changes in reality during driving, so that the precision of the road element set matches the actual environment, while avoiding the waste of terminal computing resources and improving the efficiency and accuracy of terminal automatic driving; (2) using the road information generation model to obtain the division category of the target area and the target auxiliary information of the target auxiliary area, which can improve the accuracy of the division and improve the richness of the elements in the first road element set; (3) the road information generation model can be flexibly set to two structures according to needs: when the judgment method of the division category of the target area is diverse or manual annotation is required for further correction, the road information generation model can be set separately The first model and the second model are used to correct and / or verify the judgment result of the first model; when it is necessary to quickly obtain road information, the road information generation model can be set to simultaneously output the target area classification category and the target auxiliary information model to improve the efficiency of road information generation; (4) by analyzing the historical automatic driving data, it is determined that the road elements in the sample road element set are insufficient, and the sample auxiliary information is determined as label data based on the insufficiency of the sample road element set, so that the road information generation model can learn to obtain the first road element set by analyzing the insufficiency of the second road element set; (5) when the terminal is about to enter the target auxiliary area, the first road element set corresponding to the target auxiliary area is loaded in advance, and when the terminal is actually in the target auxiliary area, the first road element set can be directly run, thereby saving the time of obtaining the first road element set and avoiding problems in the control operation caused by insufficient loading.

[0154] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0155] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0156] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0157] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0158] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0159] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0160] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0161] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0162] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A data processing method for mobile control, characterized in that: include: Acquire road features related to a target area, wherein the target area includes a target normal area and a target auxiliary area, and the road complexity of the target normal area is lower than the road complexity of the target auxiliary area; Acquire a road information generation model, where the road information generation model is a machine learning model; Generating target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features; Based on the target auxiliary information, the first road element set corresponding to the target auxiliary area is obtained, and the first road element set is used to assist the second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, and the accuracy of the first road element set is greater than the accuracy of the second road element set.

2. The method according to claim 1, characterized in that The method further comprises: Acquire a first road feature of the target area; The target area is divided into the target normal area and the target auxiliary area according to the road information generation model and the first road feature.

3. The method according to claim 2, characterized in that The road information generation model includes a first model and a second model; the road features related to the target area include a first road feature of the target area and a second road feature of the target auxiliary area; The generating of the target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features comprises: inputting a first road feature of the target area into the first model; The first model outputs the target normal area and the target auxiliary area; inputting a second road feature of the target auxiliary area into the second model; The second model outputs the target auxiliary information corresponding to the target auxiliary area.

4. The method according to claim 2, characterized in that: The road feature associated with the target area includes a first road feature of the target area; The generating of the target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road features comprises: Inputting a first road feature of the target area into the road information generation model; The road information generation model outputs the target normal area of ​​the target area, the target auxiliary area, and the target auxiliary information corresponding to the target auxiliary area.

5. The method according to claim 1, characterized in that The road information generation model is obtained based on the following operations: Obtain road features in the sample area as training samples; Acquire a sample normal area, a sample auxiliary area, and sample auxiliary information corresponding to the sample auxiliary area as label data, wherein the road complexity of the sample normal area is lower than the road complexity of the sample auxiliary area; An initial road information generation model is trained based on the training samples and the label data to obtain a trained road information generation model.

6. The method according to claim 5, characterized in that The obtaining, as label data, a sample normal area, a sample auxiliary area, and sample auxiliary information corresponding to the sample auxiliary area corresponding to the sample area includes: Acquire historical movement data of the sample area, where the historical movement data is generated based on a sample road element set corresponding to the sample area, and the accuracy of the sample road element set corresponds to the accuracy of the second road element set and / or the third road element set; Determining abnormal driving data based on the historical movement data; The sample normal area, the sample auxiliary area, and the sample auxiliary information corresponding to the sample auxiliary area are determined according to the abnormal driving data.

7. The method according to claim 6, characterized in that The determining the sample normal area and the sample auxiliary area according to the abnormal driving data includes: Clustering the abnormal driving data based on spatial positions to obtain at least one abnormal data set; Acquire abnormal information corresponding to each of the abnormal data sets, wherein the abnormal information includes at least one of the following: the number of driving abnormalities, the driving abnormality characteristics, and the severity of the driving abnormality; The sample normal area and the sample auxiliary area are determined based on the abnormal information corresponding to each of the abnormal data sets.

8. The method according to claim 6, characterized in that The step of determining the sample auxiliary information corresponding to the sample auxiliary area according to the abnormal driving data includes: determining a cause of the driving abnormality according to the driving abnormality data corresponding to the sample auxiliary area; Based on the abnormal driving cause, the sample auxiliary information corresponding to the sample auxiliary area is determined.

9. The method according to claim 1, characterized in that: The first movement control operation is performed based on the following operations: Acquiring current location information of the terminal; Based on the current location information, determining whether the terminal is currently located in the target auxiliary area or the target normal area; In response to the terminal currently being located in the target auxiliary area, acquiring the first road element set and the second road element set corresponding to the target auxiliary area; According to the first road element set and the second road element set, the terminal is enabled to perform a first movement control operation corresponding to the target auxiliary area; In response to the terminal currently being located in the target normal area, Acquire a third road element set corresponding to the target normal area, wherein the accuracy of the first road element set is greater than the accuracy of the third road element set; According to the third road element set, the terminal is enabled to perform a second movement control operation corresponding to the target normal area.

10. The method according to claim 9, characterized in that The first movement control operation is further performed based on the following operations: In response to the terminal being currently located in the target normal area, determining whether the terminal is about to enter the target auxiliary area based on the current location information; In response to the terminal about to enter the target auxiliary area, the first road element set corresponding to the target auxiliary area is loaded.

11. A data processing method for mobile control, characterized in that: include: Acquire historical movement data of a target area, where the terminal moves in the target area based on a fourth road element set to generate the historical movement data, where the target area includes a target normal area and a target auxiliary area, where the road complexity of the target normal area is lower than that of the road complexity of the target auxiliary area; Based on the historical movement data, determining abnormal data; Determining target auxiliary information corresponding to the target auxiliary area according to the abnormal data; Based on the target auxiliary information, a first road element set corresponding to the target auxiliary area is obtained, the first road element set is used to assist the second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, and the accuracy of the first road element set is greater than that of the second road element set and the fourth road element set.

12. The method according to claim 11, characterized in that The method further comprises: According to the abnormal data, the target area is divided into the target auxiliary area and the target normal area.

13. A data processing system for mobile control, characterized in that: The system comprises: a feature acquisition module, used to acquire road features related to a target area, wherein the target area includes a target normal area and a target auxiliary area, and the road complexity of the target normal area is lower than the road complexity of the target auxiliary area; a model acquisition module, used to acquire a road information generation model, wherein the road information generation model is a machine learning model; An information generation module is used to generate target auxiliary information corresponding to the target auxiliary area according to the road information generation model and the road characteristics; a road element set generation module is used to obtain the first road element set corresponding to the target auxiliary area based on the target auxiliary information, the first road element set is used to assist the second road element set corresponding to the target auxiliary area so that the terminal performs a first mobile control operation corresponding to the target auxiliary area, and the accuracy of the first road element set is greater than the accuracy of the second road element set.

14. A data processing device for mobile control, characterized in that: The device comprises: at least one storage medium storing computer instructions; At least one processor executes the computer instructions to implement the data processing method for mobile control according to any one of claims 1 to 10. 15 . A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions, the computer executes the data processing method for mobile control according to claim 1 .

Images