Map updating method and apparatus, and computer-readable storage medium

Abstract

A map updating method, device and computer readable storage medium are used to improve the accuracy of the updated map. In the present application, the map updating device receives data of a first data type and data of a second data type from a plurality of data collection devices, obtains first information of a map element from the data of the first data type, and obtains second information of the map element from the data of the second data type. According to the first information and the second information of the map element, the target information of the map element on the map is determined. Since the data of two different data types can include more information than the data of one data type, the combination of the data of two data types can obtain more accurate information of the map element, and thus the accuracy of the updated map can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a map updating method, apparatus and computer-readable storage medium. Background Technology

[0002] High-definition maps (HD maps) are maps with high positioning accuracy and real-time data updates. They primarily serve autonomous vehicles, providing lane-level planning and vehicle positioning assistance within road segments.

[0003] One solution involves using specialized map-collecting vehicles to gather data and updating the map based on that data. However, these specialized map-collecting vehicles are expensive and few in number, and the amount of data they collect is insufficient to meet the needs of autonomous vehicles for hourly or even minute-level map updates.

[0004] With the continuous development of intelligent technology in the entire vehicle industry, more and more vehicles are equipped with various sensors. The data collected by these sensors can be transmitted to a cloud server via the network. Besides vehicles, an increasing number of devices also have data collection capabilities, such as roadside units (RSUs). The cloud server can create and update high-precision maps based on data collected from multiple data collection devices (e.g., multiple vehicles), and then distribute the updated high-precision maps to the vehicles. This method of creating and updating high-precision maps will become the mainstream approach in the future, and improving the accuracy of the created or updated high-precision maps is a pressing issue that needs to be addressed. Summary of the Invention

[0005] This application provides a map updating method, apparatus, and storage medium for determining information about map elements by combining data of multiple data types, thereby improving map accuracy.

[0006] In a first aspect, this application provides a map updating method, which includes: a map updating device receiving data of a first data type and data of a second data type from multiple data acquisition devices; obtaining first information of map elements from the first data type; obtaining second information of map elements from the second data type; and determining target information of map elements on a map based on the first and second information, wherein the target information includes at least one of location information, content information, or attribute information of the map elements. In one possible implementation, the first data type and the second data type are two data types selected from: raw data, feature-level data, or target-level data. The raw data is data acquired by a sensor. The feature-level data is data extracted from the raw data acquired by the sensor that can characterize the features of the detected object. The target-level data is data extracted from the raw data or the feature-level data that can characterize the attributes of the detected object.

[0007] As can be seen, the embodiments of this application can improve the accuracy of target information by comprehensively considering data of multiple data types. For example, feature-level data may filter out some key information because it filters the original data. Combining the original data and feature-level data to determine the target information of map elements can further improve the accuracy of the target information of map elements. As another example, target-level data may filter out some key information compared to the original data and feature-level data because it filters more information from the original data. Therefore, comprehensively considering target-level data and feature-level data, or target-level data and original data, to determine the target information of map elements can further improve the accuracy of the target information of map elements.

[0008] In one possible implementation, the multiple data acquisition devices include a first data acquisition device and a second data acquisition device. The map updating device can obtain first information about map elements from data of a first data type, including: obtaining third information about map elements from first data acquired by the first data acquisition device; the first data is data of the first data type. Fourth information about map elements is obtained from second data acquired by the second data acquisition device; the second data is data of the first data type. Based on the third and fourth information, the first information about map elements is obtained. Thus, the first information can be obtained from multiple data of the first data type, thereby improving the accuracy of the first information.

[0009] In one possible implementation, the map updating device can obtain first information about map elements based on third and fourth information, including: determining the first information based on at least one of the reliability of first data or the reliability of second data, as well as the third and fourth information. This can further improve the reliability of the first information.

[0010] In one possible implementation, the map updating device can determine a first weight based on at least one of the reliability of first data or the reliability of second data, as well as third and fourth information, including: determining a first weight based on the reliability of the first data or the reliability of the second data, wherein the first weight represents the degree of influence of the third information on the first information; determining a second weight based on the reliability of the first data or the reliability of the second data, wherein the second weight represents the degree of influence of the fourth information on the first information; and determining the first information based on the first weight, the second weight, the third information, and the fourth information. Since the information of map elements is weighted and fused based on the reliability of the data, the reliability of the first information can be further improved.

[0011] In one possible implementation, the reliability of the first data is related to at least one of the following: the historical map element recognition accuracy of the first data acquisition device; or, the confidence level of the first data. Thus, when the historical map element recognition accuracy of the first data acquisition device is considered, the hardware accuracy issues of the first data acquisition device itself may be taken into account, meaning the reliability of the first data can be inferred based on historical performance, thereby further improving the accuracy of the reliability. On the other hand, when the confidence level of the data is combined to determine the reliability of the data, the accuracy of the reliability can be further improved.

[0012] In one possible implementation, the reliability of the second data is related to at least one of the following: the historical map element recognition accuracy of the second data acquisition device; or, the confidence level of the second data. This can further improve the reliability of the first data. Thus, when the historical map element recognition accuracy of the second data acquisition device is considered, the hardware accuracy issues of the second data acquisition device itself may be taken into account, meaning the reliability of the second data can be inferred based on historical performance, thereby further improving the accuracy of the reliability. On the other hand, when the confidence level of the data is combined to determine the reliability of the data, the accuracy of the reliability can be further improved.

[0013] In one possible implementation, the confidence level of the first data is related to at least one of the parameters of the sensor device that acquired the first data, or the relative positional relationship between the sensor device that acquired the first data and map elements. Thus, the confidence level of the first data can more accurately reflect its reliability.

[0014] In one possible implementation, the confidence level of the second data is related to at least one of the following: the parameters of the sensor device acquiring the second data, or the relative positional relationship between the sensor device acquiring the second data and map elements. Thus, the confidence level of the second data can more accurately reflect its reliability.

[0015] In one possible implementation, the historical map element recognition accuracy of the first data acquisition device includes at least one of the following: within a preset time period, the percentage of data reported by the first data acquisition device with correctly identified map element information; within a preset time period, the percentage of data reported by the first data acquisition device of a first data type with correctly identified map element information; or, within a preset time period, the percentage of data reported by the first data acquisition device that includes map elements of the same type as the map elements with correctly identified map element information. It can be seen that the historical map element recognition accuracy of the data acquisition device can be maintained at different granularities, thereby allowing for a more accurate assessment of the data acquisition device's capabilities.

[0016] In one possible implementation, the historical map element recognition accuracy of the second data acquisition device is used to indicate at least one of the following: within a preset time period, the percentage of data reported by the second data acquisition device in which map element information is correctly recognized; within a preset time period, the percentage of data reported by the second data acquisition device in which map element information is correctly recognized among data of the first data type; or, within a preset time period, the percentage of data reported by the second data acquisition device in which map elements of the same type as the map elements are correctly recognized. It can be seen that the historical map element recognition accuracy of the data acquisition device can be maintained at different granularities, thereby allowing for a more accurate assessment of the data acquisition device's capabilities.

[0017] In one possible implementation, obtaining second information about a map element from data of a second data type includes: obtaining sixth information about the map element from third data acquired by a third data acquisition device; where the third data is data of a second data type. Obtaining seventh information about the map element from fourth data acquired by a fourth data acquisition device; where the fourth data is data of a second data type. The second information about the map element is obtained based on the sixth and seventh information. Thus, second information can be obtained from multiple data of the second data type, thereby improving the accuracy of the second information.

[0018] In one possible implementation, obtaining the second information of a map element based on the sixth and seventh information includes: determining the second information based on at least one of the reliability of the third or fourth data, as well as the sixth and seventh information. This can further improve the reliability of the second information.

[0019] In one possible implementation, the map updating device can determine a fifth weight based on at least one of the reliability of third or fourth data, along with sixth and seventh information, including: determining a fifth weight representing the degree of influence of the sixth information on the second information based on the reliability of the third or fourth data; determining a sixth weight representing the degree of influence of the seventh information on the second information based on the reliability of the third or fourth data; and determining the second information based on the fifth weight, sixth weight, sixth information, and seventh information. Since the information of map elements is weighted and fused according to the reliability of the data, the reliability of the second information can be further improved.

[0020] In one possible implementation, the reliability of the third data is related to at least one of the following: the historical map element recognition accuracy of the third data acquisition device; or, the confidence level of the third data. Thus, when the historical map element recognition accuracy of the third data acquisition device is considered, the hardware accuracy issues of the third data acquisition device itself may be taken into account, meaning the reliability of the third data can be inferred based on historical performance, thereby further improving the accuracy of the reliability. On the other hand, when the confidence level of the data is combined to determine the reliability of the data, the accuracy of the reliability can be further improved.

[0021] In one possible implementation, the reliability of the fourth data is related to at least one of the following: the historical map element recognition accuracy of the fourth data acquisition device; or, the confidence level of the fourth data. Thus, when the historical map element recognition accuracy of the fourth data acquisition device is considered, the hardware accuracy issues of the fourth data acquisition device itself may be taken into account, meaning the reliability of the fourth data can be inferred based on historical performance, thereby further improving the accuracy of the reliability. On the other hand, when the confidence level of the data is combined to determine the reliability of the data, the accuracy of the reliability can be further improved.

[0022] In one possible implementation, the confidence level of the third data is related to at least one of the following: the parameters of the sensor device acquiring the third data, or the relative positional relationship between the sensor device acquiring the third data and map elements. Thus, the confidence level of the third data can more accurately reflect its reliability.

[0023] In one possible implementation, the confidence level of the fourth data is related to at least one of the parameters of the sensor device acquiring the fourth data, or the relative positional relationship between the sensor device acquiring the fourth data and map elements. Thus, the confidence level of the fourth data can more accurately reflect its reliability.

[0024] In one possible implementation, the map updating device can send target information to a third data acquisition device. This target information enables the third data acquisition device to combine with the sixth information to determine its historical map element recognition accuracy. In this way, vertical fusion can be further performed based on the historical map element recognition accuracy of the data acquisition device, thereby further improving the accuracy of vertical fusion.

[0025] In one possible implementation, the map updating device can send target information to the fourth data acquisition device. This target information enables the fourth data acquisition device to combine with the seventh information to determine its historical map element recognition accuracy. Thus, vertical fusion can be further performed based on the historical map element recognition accuracy of the data acquisition device, thereby further improving the accuracy of the vertical fusion.

[0026] In one possible implementation, the map updating device can update the historical map element recognition accuracy of at least one of the multiple data acquisition devices based on data received from multiple data acquisition devices and target information. The at least one data acquisition device can be a device providing data of a first data type. Alternatively, the at least one data acquisition device can also be a device providing data of the first data type. For example, in one possible implementation, the map updating device can determine the historical map element recognition accuracy of a third data acquisition device based on the target information and a sixth piece of information; and send the historical map element recognition accuracy of the third data acquisition device to the third data acquisition device. Thus, vertical fusion can be further performed based on the historical map element recognition accuracy of the data acquisition devices, which can further improve the accuracy of vertical fusion.

[0027] In one possible implementation, the map updating device can determine the historical map element recognition accuracy of the fourth data acquisition device based on the target information and the seventh information; and send the historical map element recognition accuracy of the fourth data acquisition device to the fourth data acquisition device. In this way, vertical fusion can be further performed based on the historical map element recognition accuracy of the data acquisition device, which can further improve the accuracy of vertical fusion.

[0028] In one possible implementation, for at least one of a plurality of data acquisition devices, the historical map element recognition accuracy of the at least one data acquisition device includes at least one of the following:

[0029] Within a preset time period, the detection success rate of at least one data acquisition device; for example, the higher the detection success rate, the higher the accuracy of historical map element recognition.

[0030] Within a preset time period, at least one data acquisition device makes an effective contribution to cloud fusion a certain number of times; for example, the more effective contributions to cloud fusion there are, the higher the accuracy of historical map element recognition.

[0031] Within a preset time period, the credibility rating of at least one data acquisition device is determined by a star rating; for example, a maximum of 5 stars, with the first data acquisition device having a star rating of 3 (for example, the higher the credibility rating, the higher the accuracy of historical map element recognition).

[0032] The number of times at least one data acquisition device makes a detection error within a preset time period; for example, the fewer the number of detection errors, the higher the accuracy of historical map element recognition.

[0033] Within a preset time period, the detection error of at least one data acquisition device; for example, the smaller the detection error, the higher the accuracy of historical map element recognition.

[0034] Within a preset time period, at least one data acquisition device will detect the accuracy of the results by a star rating; for example, the higher the star rating of the detection result accuracy, the higher the accuracy of historical map element recognition.

[0035] As can be seen from the above scheme, the specific manifestations of the accuracy of historical map element recognition by data acquisition equipment can be varied, thereby improving the flexibility of the scheme.

[0036] In one possible implementation, the historical map element recognition accuracy rate of at least one data acquisition device is: the historical map element recognition accuracy rate for a specific data type. For example, the historical map element recognition accuracy rate of a third data acquisition device can be calculated as: the percentage of correctly identified map element information among the data of a specific data type reported by the third data acquisition device within a preset time period. In this application, the data type can also be written as "level," in which case it can also be written as the historical map element recognition accuracy rate for a specific level. In this way, the data accuracy advantage of each data acquisition device under a specific data type can be utilized, ultimately improving the accuracy of the map information fused from multiple data acquisition devices.

[0037] In one possible implementation, the historical map element recognition accuracy rate of at least one data acquisition device is: the historical map element recognition accuracy rate for a specific map element type. For example, the historical map element recognition accuracy rate of a third data acquisition device can be calculated as: within a preset time period, the percentage of data reported by the third data acquisition device that correctly identifies map element information within the specified map element type. In this way, the data accuracy advantage of each data acquisition device for a specific map element type can be utilized to ultimately improve the accuracy of the map information fused from multiple data acquisition devices.

[0038] In one possible implementation, the historical map element recognition accuracy rate of at least one data acquisition device is: the historical map element recognition accuracy rate for a specific data acquisition environment. For example, the historical map element recognition accuracy rate of a third data acquisition device can be calculated as: within a preset time period, the percentage of data reported by the third data acquisition device that correctly identifies map element information within the specific data acquisition environment. In this way, the data accuracy advantage of each data acquisition device under a specific data acquisition environment can be utilized to ultimately improve the accuracy of the map information fused from multiple data acquisition devices.

[0039] In one possible implementation, the map updating device may instruct at least one data acquisition device to implement a data reporting strategy, which is determined based on the historical map element identification accuracy. In another possible implementation, the data reporting strategy instructing the at least one data acquisition device includes at least one of the following: the reporting cycle of the at least one data acquisition device; or, map element type information reported by the at least one data acquisition device.

[0040] In one possible implementation, the map updating device can instruct at least one data acquisition device, based on the historical map element identification accuracy of at least one data acquisition device for a specific data type, on the reporting cycle of that specific data type. This allows for a more rational formulation of information reporting strategies based on the performance of the data acquisition devices themselves.

[0041] In one possible implementation, the map updating device can instruct at least one data acquisition device, based on the historical map element identification accuracy of at least one data acquisition device for a specific map element type, on the data reporting cycle for map elements of that specific map element type. This allows for a more rational approach to developing information reporting strategies based on the performance of the data acquisition devices themselves.

[0042] In one possible implementation, the map updating device can instruct at least one data acquisition device, based on the historical map element recognition accuracy of at least one data acquisition device for a specific data acquisition environment, on the data reporting cycle for that specific data acquisition environment. This allows for a more rational formulation of information reporting strategies based on the performance of the data acquisition devices themselves.

[0043] In one possible implementation, the map updating device can determine target information of a map element on a map based on first and second information of the map element, including: determining the target information based on at least one of first parameter information or second parameter information, as well as the first and second information. The first parameter information represents the reliability of data in data of a first data type, and the second parameter information represents the reliability of data in data of a second data type. This can further improve the accuracy of the target information.

[0044] In one possible implementation, the map updating device can determine target information based on at least one of first parameter information or second parameter information, as well as first information and second information, including: determining a third weight based on at least one of the first parameter information or second parameter information, the third weight representing the degree of influence of the first information on the target information; determining a fourth weight based on at least one of the first parameter information or second parameter information, the fourth weight representing the degree of influence of the second information on the target information; and determining the target information based on the third weight, the fourth weight, the first information, and the second information. Since the first information and the second information are weighted and fused, and the calculation is based on parameter information used to characterize the reliability of the data, the accuracy of the target information can be further improved.

[0045] In one possible implementation, the map updating device can determine the target information based on the first parameter information and the second parameter information, choosing the one with higher credibility. Since the target information is determined by prioritizing the one with the highest credibility, the accuracy of the target information can be improved, thereby improving the accuracy of the updated map.

[0046] In one possible implementation, the first parameter information includes at least one of the following: a preset priority level of the first data type; the number of pieces of information that match the first information in the first information and the second information; the amount of data in the first data type; the confidence level of the data in the first data type; or, the historical map element recognition accuracy of the data acquisition device corresponding to the data in the first data type.

[0047] In one possible implementation, the second parameter information includes at least one of the following: a preset priority level of the second data type; the number of pieces of information in the first and second information that match the second information; the amount of data in the second data type; the confidence level of the data in the second data type; or, the historical map element recognition accuracy of the data acquisition device corresponding to the data in the second data type.

[0048] In one possible implementation, the content included in the first parameter information is determined sequentially based on the following priority parameters: the highest priority parameter is the preset priority level of the first data type; the second highest priority parameter is the number of map elements used to determine the target information that match the first information; and the next highest priority parameter is the amount of data in the first data type. By setting priorities for each parameter, the accuracy of horizontal fusion can be further improved.

[0049] In one possible implementation, the content included in the second parameter information is determined sequentially based on the following priority parameters: the highest priority parameter is the preset priority level of the second data type; the second highest priority parameter is the number of map elements used to determine the target information that match the second information; and the next highest priority parameter is the amount of data in the second data type. By setting priorities for each parameter, the accuracy of horizontal fusion can be further improved.

[0050] In one possible implementation, the confidence level of the data in the first data type is related to at least one of the following: the sensor device parameters of the data acquisition device corresponding to the data in the first data type; or, the relative positional relationship between the data acquisition device corresponding to the data in the first data type and the map elements. Thus, the confidence level can more accurately reflect the reliability of the data.

[0051] In one possible implementation, the confidence level of the data in the second data type is related to at least one of the following: the sensor device parameters of the data acquisition device corresponding to the data in the second data type; or, the relative positional relationship between the data acquisition device corresponding to the data in the second data type and the map elements. In this way, the confidence level can more accurately reflect the reliability of the data.

[0052] Corresponding to the method provided in the first aspect, this application also provides an apparatus. This apparatus can be a map updating device, a server-side device, or a chip. For example, the map updating device can be the aforementioned server-side map updating device or a communication chip that can be used in a server-side map updating device.

[0053] Thirdly, a map updating apparatus is provided, including a communication unit and a processing unit, to execute any embodiment of the map updating method described in the first aspect. The communication unit is used to perform functions related to sending and receiving. Optionally, the communication unit includes a receiving unit and a sending unit. In one design, the map updating apparatus is a communication chip, and the communication unit can be the input / output circuit or port of the communication chip.

[0054] In another design, the communication unit can be a transmitter and a receiver, or the communication unit can be a transmitter and a receiver.

[0055] Optionally, the map updating apparatus may further include modules that can be used to perform any of the embodiments of the map updating method of the first aspect described above.

[0056] Fourthly, a map updating apparatus is provided, which is the aforementioned server-side map updating apparatus. It includes a processor and a memory. Optionally, it also includes a transceiver. The memory stores computer programs or instructions, and the processor retrieves and executes the computer programs or instructions from the memory. When the processor executes the computer programs or instructions in the memory, the map updating apparatus performs any implementation of any of the map updating methods described in the first aspect.

[0057] Optionally, there may be one or more processors and one or more memories.

[0058] Optionally, the memory can be integrated with the processor, or the memory can be set up separately from the processor.

[0059] Optionally, the transceiver may include a transmitter and a receiver.

[0060] Fifthly, a map updating apparatus is provided, including a processor. The processor is coupled to a memory and can be used to execute any aspect of the first aspect and any possible implementation thereof. Optionally, the map updating apparatus further includes a memory. Optionally, the map updating apparatus further includes a communication interface, to which the processor is coupled.

[0061] In another implementation, the map updating device is a server-side map updating device. When the map updating device is a server-side map updating device, the communication interface can be a transceiver or an input / output interface. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0062] In another implementation, the map updating device is a chip or a chip system. When the map updating device is a chip or a chip system, the communication interface can be an input / output interface, interface circuit, output circuit, input circuit, pins, or related circuits on the chip or chip system. The processor can also be manifested as a processing circuit or logic circuit.

[0063] Sixthly, a system is provided, which includes the aforementioned data acquisition equipment and a map updating device on the server side.

[0064] Seventhly, a vehicle is provided that includes the aforementioned data acquisition device.

[0065] Eighthly, a computer program product is provided, comprising: a computer program (also referred to as code or instructions) that, when run, causes a map updating device to perform the method in any possible implementation of the first aspect, or causes the map updating device to perform the method in any implementation of the first aspect.

[0066] In a ninth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code or instructions) that, when executed on a processor, causes a map updating device to perform the method in any possible implementation of the first aspect, or causes the map updating device to perform the method in any implementation of the first aspect.

[0067] In a tenth aspect, a chip system is provided, which may include a processor. The processor is coupled to a memory and can be used to execute any of the methods in the first aspect, and any possible implementation of any of the first aspect. Optionally, the chip system also includes a memory. The memory is used to store a computer program (also referred to as code or instructions). The processor is used to call and run the computer program from the memory, causing a device on which the chip system is mounted to execute any of the methods in the first aspect, and any possible implementation of any of the first aspect.

[0068] In specific implementation, the aforementioned map updating device can be a chip, the input circuit can be an input pin, the output circuit can be an output pin, and the processing circuit can be a transistor, gate circuit, flip-flop, and various logic circuits. The input signal received by the input circuit can be received and input by, for example, but not limited to, a receiver, and the signal output by the output circuit can be, for example, but not limited to, output to a transmitter and transmitted by the transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, which is used as the input circuit and the output circuit at different times. This application does not limit the specific implementation of the processor and various circuits. Attached Figure Description

[0069] Figure 1 This is a schematic diagram illustrating a scenario to which an embodiment of this application applies;

[0070] Figure 2 A schematic flowchart illustrating a map updating method provided in an embodiment of this application;

[0071] Figure 3 A schematic flowchart illustrating a map updating method provided in an embodiment of this application;

[0072] Figure 4 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0073] Figure 5 This is a schematic diagram of another communication device provided in an embodiment of this application;

[0074] Figure 6 This is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0075] The embodiments of this application are further described below with reference to the accompanying drawings.

[0076] Figure 1 An exemplary diagram illustrates a scenario to which an embodiment of this application is applicable, such as... Figure 1 As shown, this scenario can include one or more data acquisition devices, which can be used to collect data via sensors. These data acquisition devices can be terminal devices. Figure 1 The example shown uses a vehicle as the terminal device. Figure 1 As shown, Figure 1 The diagram schematically shows three vehicles: vehicle 201, vehicle 202, and vehicle 203. The data acquisition device can also be a roadside unit 206. The application scenario of this application embodiment may also include a server 204 and a storage device 205. The server can be used to determine map element information based on the data collected by each data acquisition device, and then update the map based on the map element information. The storage device 205 can be used to store the map. The following describes these aspects respectively. Figure 1 The components involved and some terms used in the embodiments of this application will be introduced.

[0077] (1) Terminal equipment.

[0078] The terminal device in this application embodiment can be a vehicle or non-motorized vehicle with communication function, a portable device, a wearable device, or a mobile phone (or "cellular" phone), etc., or it can be a component or chip in these devices. The terminal device in this application can refer to a terminal device applied to the Internet of Vehicles (IoV), and can also be called an IoV terminal device, IoV terminal, IoV communication device, or vehicle-mounted terminal device, etc.

[0079] A vehicle (such as any one of vehicle 201, vehicle 202, or vehicle 203) is a typical terminal device in the Internet of Vehicles (IoV). In the following embodiments of this application, a vehicle is used as an example for description. Any vehicle in the embodiments of this application can be an intelligent vehicle or a non-intelligent vehicle, and the comparison of the embodiments in this application is not limited. Those skilled in the art should understand that the embodiments of this application using a vehicle as an example can also be applied to other types of terminal devices. Specifically, the terminal device can execute IoV-related business processes through its internal functional units or devices. For example, when the terminal device is a vehicle, one or more of the following devices in the vehicle can be used to execute the terminal device-related method processes in the embodiments of this application: a telematics box (T-Box), a domain controller (DC), a multi-domain controller (MDC), an on-board unit (OBU), or an IoV chip, etc.

[0080] In this embodiment, the vehicle can communicate with other objects based on vehicle-to-everything (V2X) wireless communication technology. For example, communication between the vehicle and a cloud server can be achieved based on V2X. Communication between the vehicle and other objects can be based on wireless high-fidelity (e.g., wireless fidelity (Wi-Fi)) or 5G mobile communication technology. For example, communication between the vehicle and other devices (such as roadside unit 206 or server 204) can be achieved based on 5G.

[0081] In this embodiment, the terminal device can be used to collect surrounding environmental information, such as through sensors installed on the terminal device. In this embodiment, the vehicle may include a data acquisition device. The data acquisition device can collect data through sensors and transmit the raw data collected by the sensors to a server or roadside unit for map updates. The data acquisition device can also process the raw data to obtain processed data (such as feature-level data, target-level data, etc.) and transmit the processed data to a server or roadside unit for map updates. When the terminal device is a vehicle, in this embodiment, the data acquisition device in the vehicle can be a component inside the vehicle, the vehicle itself, or a mobile phone. This data acquisition device may include the data acquisition device of the vehicle's positioning system, the data acquisition device for intelligent driving, or any other device with computing capabilities.

[0082] In this embodiment, the terminal device (such as a vehicle) is equipped with a sensor for acquiring images of the vicinity of the vehicle. The sensor may include a camera, LiDAR, millimeter-wave radar, ultrasonic sensors, etc. Furthermore, each vehicle may be equipped with one or more sensors, and the number of each type of sensor may be one or more. The sensors may be installed on the top of the vehicle (e.g., in the middle of the roof), the front of the vehicle, etc. This embodiment does not limit the installation location or number of sensors in each vehicle.

[0083] (2) Roadside unit (RSU) 206.

[0084] like Figure 1 As shown, this application scenario may include the RSU206. The RSU206 can be used to send vehicle-to-everything (V2X) messages to terminal devices via direct communication (such as PC5) or dedicated short-range communications (DSRC) technology. V2X messages can carry dynamic information or other information that needs to be notified to the terminal device. The communication method between the roadside unit and the terminal device can also be referred to as vehicle-to-infrastructure (V2I) communication. It should be noted that... Figure 1 The diagram only shows that the roadside unit 206 has a communication path with the vehicle 201 and the server 204. In actual applications, the roadside unit 206 can also have a communication path with other vehicles, such as vehicle 202 and vehicle 203, which are not shown in the diagram.

[0085] This application does not specify the particular deployment form of the roadside unit, which can be a terminal device, a mobile or non-mobile terminal device, a server, or a chip, etc. The roadside unit can also be used to report dynamic information occurring within its jurisdiction to the vehicle network server, such as by reporting dynamic information through roadside information (RSI) messages.

[0086] The system architecture applicable to the embodiments of this application may or may not include roadside units; this application does not impose any limitations. In one possible implementation, the roadside unit can focus on sensing certain specified elements according to instructions issued by the server and report the sensing results. Alternatively, in another possible implementation, the roadside unit can also send instructions to the terminal device or issue an updated map.

[0087] The roadside unit in this embodiment may also be equipped with a data acquisition device. The data acquisition device can collect data via sensors and transmit the raw data collected by the sensors to a server or roadside unit for map updating. The data acquisition device can also process the raw data to obtain processed data (such as feature-level data, target-level data, etc.) and transmit the processed data to a server or roadside unit for map updating.

[0088] (3) Server 204.

[0089] like Figure 1 As shown, this application scenario may include server 204. Server 204 can be a vehicle-to-everything (V2X) platform or server that manages and provides services to terminal devices and / or roadside units, including application servers or map cloud servers that provide services for high-precision maps and navigation maps. In one possible implementation, server 204 can be used to update maps based on data reported by data collection devices, and to distribute updates to high-precision maps. The specific deployment form of the server is not limited in this application; for example, it can be deployed in the cloud, or it can be a standalone computer device or chip. When it is necessary to send V2X messages to terminal devices, the server can send the V2X messages to the roadside units, and the roadside units can then broadcast them to terminal devices within their coverage area. Of course, the server can also directly send V2X messages to the terminal devices.

[0090] (4) Storage device 205.

[0091] like Figure 1 As shown, in this application scenario, storage device 205 can be used to store data, such as maps.

[0092] (5) Data types include: raw data, feature-level data and target-level data.

[0093] In this embodiment, the data acquisition device (such as a vehicle) is equipped with sensors for acquiring images of the vicinity of the vehicle. These sensors may include cameras, lidar, millimeter-wave radar, ultrasonic sensors, etc. Furthermore, each vehicle may be equipped with one or more sensors, and the number of each type of sensor may be one or more. Sensors may be installed on the top of the vehicle (e.g., in the middle of the roof), the front of the vehicle, etc. This embodiment does not limit the installation location or number of sensors in each vehicle.

[0094] In this application embodiment, three types of data are defined: raw data, feature-level data, and target-level data. Specifically, the raw data collected by the sensor in this application embodiment is processed to obtain at least one of feature-level data or target-level data. These three data types are described below.

[0095] It should be noted that the three data types mentioned in the embodiments of this application are merely examples, and the data types applicable to the embodiments of this application are not limited to these three.

[0096] Raw data refers to the data collected by the sensor. For example, when the sensor is a LiDAR, the raw data is the LiDAR point cloud data; when the sensor is a camera, the raw data is pixel-level data. Raw data can be represented as Pi (i = 0, 1, 2…N), where Pi represents the information of a point in the environment detected by the sensor, and N represents the number of environmental points detected by the sensor. For example, for a 3D LiDAR point cloud, Pi represents the 3D coordinate information of a point in the environment; for a camera, Pi represents the pixel information of a point in the environment mapped to a 2D image.

[0097] Feature-level (Detection Level or Feature Level) data is extracted from the raw data acquired by the sensor, representing the characteristics of the object being detected. Features can be, for example, key points representing the shape and contour of an object, or local gradient features obtained from 3D laser point clouds or images in the environment. Feature-level data can be represented as Fi (i = 0, 1, 2…N), where Fi represents information about a specific feature of the object being detected in the environment, and N represents the number of features of the object being detected.

[0098] Object-level data is data extracted from raw data or feature-level data that characterizes the attributes of the detected object. Object-level data has significant semantic features, such as lane lines, traffic lights, or traffic signs. Object-level data can be represented as Oi (i = 0, 1, 2…N), where Oi represents the information of a specific object in the environment detected by the sensor, and N represents the number of objects detected by the sensor.

[0099] In this embodiment, the conversion between different data types can be achieved through feature extraction and target extraction. For example, feature extraction of the original data can yield feature-level data, target extraction of the original data can yield target-level data, and target extraction of the feature-level data can yield target-level data. This embodiment is not limited to the methods of feature extraction and target extraction.

[0100] (6) Map elements.

[0101] The map elements in this application embodiment refer to elements in a map, including but not limited to: roads, lane lines, signs, ground markings, traffic lights, and drivable area markings. Roads may include guardrails and curbs; signs include various types such as road signs, directional signs, and height restriction signs; and ground markings include traffic diversion signs, entrance / exit signs, speed limit signs, and time limit signs. In one possible implementation, this application embodiment can be applied to high-precision maps. High-precision maps, simply put, are electronic maps with higher accuracy and more data dimensions, containing more map elements. Higher accuracy is reflected, for example, in the fact that the element information contained in the map is accurate to the centimeter level.

[0102] Based on the above, Figure 2 This illustration shows a flowchart of a map update method provided in an embodiment of this application. This method can be executed by a map update device and a data acquisition device. The map update device can be located on the server side, for example, it can be a device on the server side, a module on the server, or a chip on the server. The data acquisition device mentioned in this embodiment can be located on the vehicle side, for example, it can be the vehicle itself, a module on the vehicle, or a chip on the vehicle. The data acquisition device can also be located on the RSU side, for example, it can be the RSU, a module on the RSU, or a chip on the RSU. Figure 2 As shown, the method includes:

[0103] Step 201: One or more data acquisition devices report data. The map update device receives data of N data types from multiple data acquisition devices, where N is an integer greater than 1.

[0104] In one possible implementation, the N data types can be multiple data types from raw data, feature-level data, or target-level data. It should be noted that the three data types mentioned in the embodiments of this application are merely examples, and the data types applicable to the embodiments of this application are not limited to these three. For a description of these three data types, please refer to the foregoing content, which will not be repeated here.

[0105] Step 202: The map updating device obtains N pieces of information about map elements from N types of data. Each of the N pieces of information corresponds one-to-one with one of the N data types.

[0106] Step 203: The map updating device determines the target information of the map element on the map based on N pieces of information. The target information includes at least one of the following: location information, content information, or attribute information of the map element.

[0107] For example, when the map element is a lane line, the target information can be at least one of the following: the position information of the lane line, the color of the lane line, or the specific shape of the lane line (solid line or dashed line, etc.).

[0108] For example, when the map element is a sign, such as a road sign, directional sign, or height restriction sign, the target information can be at least one of the following: the location information of the sign, the content of the sign, the shape of the sign, or the color of the sign.

[0109] For example, when the map element is a ground sign, such as a diversion sign, entrance / exit sign, speed limit sign, or time limit sign, the target information can be at least one of the following: the location information of the ground sign, the specific shape of the ground sign, or the color of the ground sign.

[0110] For example, when the map element is a traffic light, the target information can be at least one of the following: the location information of the traffic light, or the specific shape of the traffic light.

[0111] For example, when the map element is a drivable area marker line, the target information can be the location information of the drivable area marker line, or at least one of the specific contents of the drivable area marker line.

[0112] For example, when a map element is an obstacle (such as a traffic cone), the target information can be at least one of the obstacle's location information or its shape information.

[0113] When N is 2 Figure 2 One possible implementation includes: obtaining first information about map elements from data of a first data type; obtaining second information about map elements from data of a second data type; and determining target information of the map elements on the map based on the first and second information. When N is 3, Figure 2 One possible implementation includes: obtaining first information of a map element from data of a first data type; obtaining second information of a map element from data of a second data type; obtaining fifth information of a map element from at least one data of a third data type; and determining target information of the map element on the map based on the first, second, and fifth information. The following description, for the purpose of more clearly illustrating the embodiments of this application, uses the first data type as target-level data, the second data type as feature-level data, and the third data type as raw data as an example.

[0114] To explain more clearly Figure 2 The proposed scheme Figure 3 The illustration shows another possible scenario to which the embodiments of this application are applicable. The following is in conjunction with... Figure 3 The map updating method provided in the embodiments of this application will be described.

[0115] like Figure 3 As shown, the data acquisition device is a vehicle, which is used as an example for illustration. Figure 3 The vehicle V shown 11 Vehicle V 12 Vehicle V 21 Vehicle V 22 Vehicle V 31 and vehicle V 32 To clearly illustrate the embodiments of this application, the following description uses map elements as obstacles (such as traffic cones) as an example. The information of the map elements can be at least one of the location information or shape of the obstacle. The following description uses the location information of the obstacle as an example.

[0116] In this application embodiment, the data type reported by any vehicle can be one or more, such as one or more of raw data, feature-level data or target-level data. In this application embodiment, there is no restriction on the types of data that a vehicle can report. Figure 3 This is merely an example, such as Figure 3 As shown, vehicle V 11 (First data acquisition device) and vehicle V 12 The data reported by the (second data acquisition device) is of target-level data type (first data type). For example, vehicle V 11 or vehicle V 12 At least one of the reported data may include: the obstacle is a traffic cone, and the location information of the traffic cone.

[0117] like Figure 3 As shown, vehicle V 21 (Third data acquisition device) or vehicle V 22 The data reported by the fourth data acquisition device is feature-level data (second data type). For example, vehicle V 21 or vehicle V 22 At least one of the reported data may include: key point information about the shape and outline of the obstacle.

[0118] like Figure 3 As shown, vehicle V 31 (Fifth data acquisition device) and vehicle V 32 The data reported by the sixth data acquisition device is raw data (third data type). For example, vehicle V 31 or vehicle V 32 At least one of the reported data may include: lidar point cloud data of obstacles.

[0119] In this embodiment, after receiving this data, the cloud server 204 can first perform vertical fusion on the data of various data types. Vertical fusion mentioned in this embodiment refers to the fusion of data of the same data type. For example, the map update device performs fusion on vehicle V... 11 Reported target-level data (first data) and vehicle V 12 The reported target-level data (second data) is fused to obtain the location information of the obstacles corresponding to the fused target-level data (first information of the map elements). In one possible implementation, this can be achieved from vehicle V... 11 The reported target-level data yields obstacle location information (third information), which is obtained from vehicle V. 12 The obstacle's location information (fourth information) is obtained from the reported target-level data. The two location information of the obstacle are fused together to obtain the obstacle's location information (first information of the map element) corresponding to the fused target-level data.

[0120] For example, map update devices update vehicle V 21 Reported feature-level data (third data) and vehicle V 22 The reported feature-level data (fourth data) is fused to obtain the location information of the obstacles corresponding to the fused feature-level data (second information of map elements). In one possible implementation, this can be obtained from vehicle V... 21 The location information of the obstacle (sixth information) is obtained from the reported feature-level data, from vehicle V. 22 The obstacle's other location information (seventh information) is obtained from the reported feature-level data. The two location information of the obstacle are fused to obtain the obstacle's location information (second information of the map element) corresponding to the fused feature-level data.

[0121] For example, map update devices update vehicle V 31 The reported raw data (fifth data) and vehicle V 32 The reported raw data (sixth data) is fused to obtain the location information of the obstacles corresponding to the fused raw data (fifth information of the map elements). In one possible implementation, this can be obtained from vehicle V... 31 The location information of the obstacle (eighth information) is obtained from the reported raw data, from vehicle V. 32 The obstacle's location information (ninth information) is obtained from the reported raw data. The two location information of the obstacle are fused to obtain the obstacle's location information (fifth information of the map element) corresponding to the fused raw data.

[0122] Furthermore, the information of map elements corresponding to the various data types is fused together. This fusion can be understood as horizontal fusion, thereby obtaining the target information of the map elements. The target information of the map elements is the information of the map elements on the updated map. For example, the location information of obstacles corresponding to the fused target-level data (the first information of the map element), the location information of obstacles corresponding to the fused feature-level data (the second information of the map element), and the location information of obstacles corresponding to the fused original data (the fifth information of the map element) are fused together to obtain the location information of the obstacles, which is the target information of the map elements.

[0123] For example, the location information of obstacles corresponding to the fused target-level data might be designated as Location Information 1, the location information of obstacles corresponding to the fused feature-level data as Location Information 2, and the location information of obstacles corresponding to the fused original data as Location Information 3. Considering that feature-level data may have filtered the original data, potentially removing some key information, while target-level data may have removed even more information, one possible priority order for data types is: original data has the highest priority, feature-level data has the second highest priority, and target-level data has the lowest priority. Based on this, after horizontal fusion, the location information of obstacles (target information of map elements) can be determined as: Location Information 3.

[0124] Furthermore, in this embodiment, the server-side map updating device can also update the historical map element recognition accuracy of at least one of the multiple data acquisition devices based on data received from multiple data acquisition devices and target information. At least one data acquisition device can be a device providing data of a first data type. At least one data acquisition device can also be a device providing data of a second data type. For example, the server-side map updating device can calculate or update the historical map element recognition accuracy of the vehicle-side data acquisition device based on target information, and then send the historical map element recognition accuracy of the data acquisition device to the data acquisition device. In another possible implementation, the server-side map updating device can also send target information to each vehicle-side data acquisition device so that each maintains its own historical map element recognition accuracy. The historical map element recognition accuracy will be described in detail later and will not be elaborated upon here.

[0125] As can be seen from the above, the embodiments of this application can achieve closed-loop fusion of horizontal and vertical data. Specifically, based on the data reported by each data acquisition device, vertical fusion is performed on data of the same type to obtain fused data corresponding to each data type. Further, horizontal fusion is performed again on the fused data corresponding to each data type, and the final result is used as the target information for map elements to update the map. Furthermore, the obtained target information for map elements is fed back to each data acquisition device to enable each data acquisition device to maintain its historical map element recognition accuracy.

[0126] As can be seen from the above, the embodiments of this application can improve the accuracy of target information by comprehensively considering data of multiple data types. For example, feature-level data may filter out some key information because it filters the original data. Combining the original data and feature-level data to determine the target information of map elements can further improve the accuracy of the target information of map elements. As another example, target-level data may filter out some key information compared to the original data and feature-level data because it filters more information. Therefore, combining target-level data and feature-level data, or target-level data and original data, to determine the target information of map elements can further improve the accuracy of the target information of map elements.

[0127] For vertical fusion, one possible implementation is to fuse the data based on the credibility of the data across multiple datasets. For example, the first information can be determined based on at least one of the credibility of the first data or the credibility of the second data, as well as third and fourth information. The higher the credibility of the data, the greater the influence of the map element information in that data on the first information.

[0128] In one possible implementation, the information of the map element corresponding to the data with the highest credibility can be used as the first information. For example, vehicle V 11 The reported target-level data (first data) is more reliable. The obstacle location information determined based on the first data is location information 4, while the location information based on vehicle V is... 12 The obstacle's location information, determined by the reported target-level data (second data), is location information 5. In this case, location information 4 can be used as the obstacle's first information.

[0129] In another possible implementation, when there are many data acquisition devices, more than two sets of data of the same data type can be obtained for the same map element. The information of the map element supported by the larger number of data acquisition devices can be used as the information of that map element in the vertical fusion result corresponding to that data type. For example, consider three vehicles that report target-level data. The obstacle location information determined based on the data reported by these three vehicles is location information 6, location information 7, and location information 7. In this case, since location information 7 accounts for a large proportion of the total, it can be determined that the obstacle location information in the vertical fusion result for the target-level data is location information 7.

[0130] In another possible implementation, a first weight is determined based on at least one of the credibility of the first data or the credibility of the second data, the first weight representing the degree of influence of the third information on the first information. A second weight is determined based on at least one of the credibility of the first data or the credibility of the second data, the second weight representing the degree of influence of the fourth information on the first information. The first information is determined based on the first weight, the second weight, the third information, and the fourth information.

[0131] In this embodiment of the application, target-level data (e.g.) is used. Figure 3 The example of fusing the first and second data in the data is introduced as an example.

[0132] In one possible implementation, the first data and the second data can be fused using formula (1):

[0133] y = f(result1, result2) = ...Formula (1)

[0134] In formula (1):

[0135] y represents the data fusion result;

[0136] result1 is the first data;

[0137] result2 is the second data;

[0138] w1 represents the reliability of the first data, which can be determined based on the parameters of the first sensor device that acquired the first data; w1 can be one-dimensional or multi-dimensional data, for example, w1 = (w11, w12, ... w1...). i …, w1 M1 M1 represents the number of targets included in the first set of data, and w1 represents the number of targets included in the first set of data. i Let be the confidence level of target i in the first set of data, where i is a natural number less than M1;

[0139] w2 represents the reliability of the second data, which can be determined based on the parameters of the second sensor device that acquired the second data. w2 can be one-dimensional or multi-dimensional data, for example, w2 = (w21, w22, ..., w2...). j …, w2 M2 M2 represents the number of targets included in the second set of data, and w2 represents the number of targets included in the second set of data. j Let J be the confidence level of target j in the second data, where j is a natural number less than M2;

[0140] This can be understood as the first weight;

[0141] This can be understood as the second weight.

[0142] In another possible implementation, result1 can be understood as the third information of the map element determined from the first data, result2 as the fourth information of the map element determined from the first data, and y as the first information obtained from the fused data after fusing the first data and the second data.

[0143] It's understandable that the credibility of a data point can be finely divided so that different map elements within the data correspond to different credibility levels. It's easy to see that the higher the proportion of the credibility of the first data point in the sum of the credibility values ​​of the first and second data points, the greater the weight of the first data point in the fusion result. Alternatively, it can be understood that the sensor with the higher credibility value will have a larger proportion of its detected data in the fusion result.

[0144] The above description uses target-level data fusion as an example. The fusion scheme for raw data and feature-level data is similar. For instance, the second information can be determined based on at least one of the credibility of the third or fourth data, along with the sixth and seventh information. The fifth weight is determined based on at least one of the credibility of the third or fourth data, representing the degree of influence of the sixth information on the second information. The sixth weight is also determined based on at least one of the credibility of the third or fourth data, representing the degree of influence of the seventh information on the second information. The second information is then determined based on the fifth weight, sixth weight, sixth information, and seventh information. The method for determining the second information is similar to that for the first information and will not be repeated here.

[0145] Based on the above, it can be seen that vertical fusion can be performed based on the credibility of the data collected by the data acquisition device. In one possible implementation, the credibility of the data collected by a data acquisition device may include at least one of the following: the confidence level of the data, or the historical map element recognition accuracy of the data acquisition device. These parameters are described below using parameter a1 and parameter a2.

[0146] Parameter a1: Confidence level corresponding to the first data.

[0147] In one possible implementation, the confidence level of the first data is related to at least one of the parameters of the sensor device that acquired the first data, or the relative positional relationship between the sensor device that acquired the first data and the map element.

[0148] The confidence level can be determined based on one or more of the following: the sensor parameters that collected the first data, the sensing distance of the map element, and the sensing angle of the map element.

[0149] Among them, the parameters of the sensing device are related to the initial accuracy of the sensing device itself, the installation space angle, and the installation coordinates.

[0150] The perception distance of a map element is the distance between the map element and the sensing device in the perception coordinate system.

[0151] The perception angle of a map element is the angle formed by the map element and the sensing device in the perception coordinate system.

[0152] It should be noted that when a sensor device includes multiple sensors, the confidence level of the sensor device can be obtained by weighting or averaging the confidence levels of the multiple sensors included in the sensor device.

[0153] It's easy to understand that the higher the accuracy of the sensor parameters, the greater the confidence level; conversely, the lower the accuracy, the smaller the confidence level. Similarly, the smaller the sensing distance, the greater the confidence level; and vice versa. Likewise, the smaller the sensing angle, the greater the confidence level; and vice versa.

[0154] Confidence is used to measure the reliability of identification results. Currently, there are several methods in the industry for calculating confidence, including at least the following:

[0155] Posterior probabilities obtained directly from Bayesian classification methods, estimates of posterior probabilities obtained from neural networks or other methods, randomness measures obtained from algorithmic randomness theory, membership values ​​obtained from fuzzy mathematics, and accuracy rates obtained through multiple test experiments, etc.

[0156] It should be noted that the confidence level calculation method in the embodiments of this application is not limited to the above-mentioned methods. Any calculation method that can be used to determine the confidence level can be applied to the embodiments of this application and is within the protection scope of the embodiments of this application.

[0157] Parameter a2: Historical map element recognition accuracy of the first data acquisition device.

[0158] In this embodiment, the historical map element recognition accuracy of the first data acquisition device can be maintained based on historical data. Specifically, it may include one or more of the following parameters a2-1, a2-2, and a2-3.

[0159] Parameter a2-1: Within a preset time period, the percentage of data reported by the first data acquisition device that correctly identifies map element information.

[0160] In this embodiment of the application, the percentage of data in which map element information is correctly identified can also be understood as the accuracy rate of map element information identification.

[0161] For example, within a preset time period, the first data acquisition device reports information on K0 map elements, of which K1 map element information satisfies a first preset condition. Meeting the first preset condition means that the map element information is considered correctly detected data. In this case, the ratio of K1 to K0 can be used as the historical map element recognition accuracy of the first data acquisition device. K0 is a positive integer, and K1 is an integer not greater than K0.

[0162] In one possible implementation, the information of a map element satisfying a first preset condition may include the following:

[0163] When the information of the map element is location information, then: if the distance between the location indicated by the location information of the map element included in the data and the location indicated by the location information of the finally determined map element is less than a preset distance threshold, then the data can be said to satisfy the first preset condition.

[0164] When the information of the map element is the location information of the obstacle, then: if the information of the map element included in the data is the same as the information of the finally determined map element, then the data can be said to satisfy the first preset condition.

[0165] In one possible implementation, the historical map element recognition accuracy of the first data acquisition device can also be used to indicate one or more of the following:

[0166] Within a preset time period, the detection success rate of the first data acquisition device (for example, the higher the detection success rate, the higher the accuracy of historical map element recognition).

[0167] Within a preset time period, the number of times the first data acquisition device makes an effective contribution to cloud fusion (for example, the more times it makes an effective contribution to cloud fusion, the higher the accuracy of historical map element recognition).

[0168] Within a preset time period, the credibility rating of the first data acquisition device is determined by a star rating, such as a maximum of 5 stars, where the first data acquisition device has a star rating of 3 (for example, the higher the credibility rating, the higher the accuracy of historical map element recognition).

[0169] The number of times the first data acquisition device makes a detection error within a preset time period (for example, the fewer the number of detection errors, the higher the accuracy of historical map element recognition).

[0170] Within a preset time period, the first data acquisition device detects the magnitude of the error (for example, the smaller the detection error, the higher the accuracy of historical map element recognition).

[0171] Within a preset time period, the accuracy rating of the detection results from the first data acquisition device is determined by a star rating (for example, the higher the star rating of the detection result accuracy, the higher the accuracy of historical map element recognition).

[0172] Parameter a2-2: Within a preset time period, the percentage of data with correctly identified map element information in the first data type reported by the first data acquisition device.

[0173] In this embodiment of the application, the percentage of data in which map element information is correctly identified can also be understood as the accuracy rate of map element information identification.

[0174] For example, within a preset time period, the first data acquisition device reports information on K0 map elements. Among these K0 map element information, there are K2 map element information items, which are carried by the first data acquisition device through data of the first data type. Furthermore, among these K2 map element information items, there are K3 map element information items that satisfy the first preset condition. In this case, the ratio of K3 to K2 is the historical map element recognition accuracy rate in the first data type data reported by the first data acquisition device. The ratio of K3 to K2 can be used as the historical map element recognition accuracy rate of the first data acquisition device. K2 is an integer not greater than K0, and K3 is an integer not greater than K2. In this way, the map element information recognition accuracy rate of the data acquisition device can be maintained based on the granularity of the data type.

[0175] In one possible implementation, the historical map element recognition accuracy of the first data acquisition device can also be used to indicate one or more of the following:

[0176] The success rate of the first data acquisition device in detecting data of the first data type within a preset time period;

[0177] Within a preset time period, the number of times the first data acquisition device effectively contributes to cloud fusion based on data of the first data type;

[0178] Within a preset time period, the credibility rating of the first data acquisition device on the data of the first data type is given by a star rating, for example, a maximum of 5 stars, and the first data acquisition device has a star rating of 3.

[0179] The number of times the first data acquisition device makes a detection error on the first type of data within a preset time period;

[0180] Within a preset time period, the first data acquisition device detects the magnitude of error on the data of the first data type;

[0181] Within a preset time period, the first data acquisition device measures the accuracy of the results on the data of the first data type, assigning a star rating.

[0182] Parameter a2-3: Within a preset time period, the percentage of data reported by the first data acquisition device that includes map elements of the same type as the map element and whose map element information is correctly identified.

[0183] In this embodiment of the application, the percentage of data in which map element information is correctly identified can also be understood as the accuracy rate of map element information identification.

[0184] This application's embodiments involve type information for map elements. Map elements can be categorized, and each category can be identified by a type identifier. The type information mentioned herein can be a type identifier. The categorization rules are not limited; for example, signs can be categorized into one type, or ground markings can be categorized into another, and so on.

[0185] For example, within a preset time period, the first data acquisition device reports information on K0 map elements. Among these K0 map element information, there are K4 map element information. The type of each of these K4 map element information is the same as the type of map element mentioned in step 227 above, such as sign content recognition. For ease of reference, the type of map element mentioned in step 227 is referred to as the first type. Thus, the type of each map element in the K4 map element information is of the first type. Further, among these K4 map element information, there are K5 map element information, and the information of these K5 map element information satisfies the first preset condition. In this case, the ratio of K5 to K4 is the map element information recognition accuracy rate of the data reported by the first data acquisition device that includes map elements of the same type as the first map element. The ratio of K5 to K4 can be used as the map element information recognition accuracy rate of the first data acquisition device. K4 is an integer not greater than K0, and K5 is an integer not greater than K4. Thus, the map element information recognition accuracy rate of the data acquisition device can be maintained based on the granularity of the map elements.

[0186] In one possible implementation, the map element recognition accuracy of the first data acquisition device can also be used to indicate one or more of the following:

[0187] Within a preset time period, the detection success rate of the first data acquisition device on the first type of map elements;

[0188] Within a preset time period, the number of times the first data acquisition device effectively contributes to cloud fusion on the first type of map elements;

[0189] Within a preset time period, the credibility rating of the first data acquisition device on the first type of map element is determined by a star rating, for example, a maximum of 5 stars, and the first data acquisition device has a star rating of 3.

[0190] The number of times the first data acquisition device makes a detection error on the first type of map element within a preset time period;

[0191] Within a preset time period, the first data acquisition device detects the magnitude of the error on the first type of map elements;

[0192] Within a preset time period, the first data acquisition device measures the accuracy of the detection results on the first type of map elements, assigning a star rating.

[0193] In another possible implementation, parameters a2-1, a2-2, and a2-3 can be combined. For example, within a preset time period, the first data acquisition device reports information on K0 map elements. Among these K0 map elements, K4 map elements are of the same type as those mentioned in step 227, such as sign content recognition. Furthermore, among these K4 map elements, K5 map elements satisfy the first preset condition. And K6 of these K5 map elements are carried by data of the first data acquisition device reported using the first data type. In this case, the ratio of K6 to K4 can be used as the historical map element recognition accuracy of the first data acquisition device. K6 is an integer not greater than K5. Thus, the map element information recognition accuracy of the data acquisition device can be maintained based on the granularity of map elements and data types.

[0194] It should be noted that the information of multiple map elements among the aforementioned K0 map elements can be sent to the map update device through a single data report or through multiple data report processes. In other words, there is no limit to the number of map elements included in the single data report submitted by the data acquisition device; it can contain one or more map elements.

[0195] The above content describes the historical map element recognition accuracy through parameter a2. In one possible implementation, after step 203, the server in this embodiment can further send the target information to each data acquisition device so that each device can maintain its own historical map element recognition accuracy. Alternatively, the server can calculate or update the historical map element recognition accuracy of the data acquisition devices based on the target information, and then send it to the data acquisition devices.

[0196] In one possible implementation, the map updating device sends target information to a first data acquisition device, which, in conjunction with third information, enables the first data acquisition device to determine its historical map element recognition accuracy. In another possible implementation, the map updating device sends target information to a second data acquisition device, which, in conjunction with fourth information, enables the second data acquisition device to determine its historical map element recognition accuracy. In yet another possible implementation, the map updating device determines the historical map element recognition accuracy of the first data acquisition device based on the target information and the third information, and then sends this accuracy to the first data acquisition device. In yet another possible implementation, the map updating device determines the historical map element recognition accuracy of the second data acquisition device based on the target information and the fourth information, and then sends this accuracy to the second data acquisition device.

[0197] Similarly, the reliability of the second data is related to one or more of the following: the historical map element recognition accuracy of the second data acquisition device, and the confidence level of the second data. Specifically, the confidence level of the second data is related to at least one of the following: the parameters of the sensor device acquiring the second data, or the relative positional relationship between the sensor device acquiring the second data and the map elements. The reliability of the third data is related to at least one of the following: the historical map element recognition accuracy of the third data acquisition device, or the confidence level of the third data. The reliability of the fourth data is related to at least one of the following: the historical map element recognition accuracy of the fourth data acquisition device, or the confidence level of the fourth data. The confidence level of the third data is related to at least one of the following: the parameters of the sensor device acquiring the third data, or the relative positional relationship between the sensor device acquiring the third data and the map elements. The confidence level of the fourth data is related to at least one of the following: the parameters of the sensor device acquiring the fourth data, or the relative positional relationship between the sensor device acquiring the fourth data and the map elements. For related information, please refer to the aforementioned description of the reliability of the first data; it will not be repeated here.

[0198] As can be seen from the above, the map update device in this embodiment can, for received data of the same type, combine the map element recognition accuracy of the data acquisition device and / or the confidence level of the data to perform more accurate information fusion and remove defective data. This improves the accuracy of the fused data, thereby increasing the accuracy of map updates, and removes redundant interference data, thus reducing processing complexity. It should be understood that there are various algorithms for implementing fusion and data removal based on data confidence level, and no specific limitations are made here.

[0199] Furthermore, when data of the same type is fused (also known as vertical fusion), the fused data can also be assigned a level of credibility. Methods for calculating credibility can include Bayesian estimation, fuzzy mathematics, K-means, stochastic vector machines, or other classic neural network calculation methods, and are not specifically limited here.

[0200] For example, the reliability of the merged data can be derived from the reliability of the data being merged. For instance, the reliability of each data point can be averaged, and this average value can be used as the reliability of the merged data. For example, map element i in data D... V11 Credibility W V11 And map element i in data D V12 Credibility W V12 Calculate the average value and use it as the confidence level for the first type of data. In another possible implementation, W can be... V11 and W V12 The weighted sum is used as the confidence level for the first type of data.

[0201] The vertical fusion in this embodiment can be performed on the data acquisition device side or on a cloud server. When performed on the data acquisition device side, the data acquisition device can perform vertical fusion on multiple data of the same data type acquired by itself. When performed on a cloud server, this embodiment can also perform vertical fusion on data of the same data type reported by multiple vehicles.

[0202] On the other hand, when fusing data of the same type in this application embodiment, data from sensors of the same type can be fused, or data from sensors of different types can be fused. When fusing data from different sensors, the advantages of multiple sensors can be taken into account. For example, target-level data from cameras and millimeter-wave radar can be fused.

[0203] The system acquires the location information of a first target point and a second target point. The first target point represents the target object detected by the millimeter-wave radar sensor, and the second target point represents the target object detected by the camera. When the distance between the first and second target points is determined to be less than a first preset threshold (the size of the first preset threshold can be set according to the size of the target object, for example, 1 / 5 to 1 / 2 of the target object's size), the first and second target points are considered to be the same target. Furthermore, the distance and velocity of the target detected by the millimeter-wave radar, the category and lateral position of the target detected by the camera, are combined to form the target-level data information of the target. This method fuses the target-level data from the camera and the millimeter-wave radar, thereby leveraging both the target resolution and angle resolution capabilities of the camera and the ranging and velocity measurement capabilities of the millimeter-wave radar.

[0204] Regarding the horizontal fusion in step 203 above, one possible implementation is that when at least two pieces of information among the N pieces of information are inconsistent, horizontal fusion can be performed based on the parameter information of each of the N data types. For example, when there is a first piece of information and a second piece of information among the N pieces of information, the target information can be determined based on at least one of the first parameter information or the second parameter information, as well as the first and second information. The first parameter information represents the reliability of the data in the first data type, and the second parameter information represents the reliability of the data in the second data type. One possible implementation is to use the information of the map element corresponding to the data type with the highest reliability as the target information. Another possible implementation is to use the information of the map element with the largest proportion among the N pieces of information as the target information. Many other possible implementations exist, and they will not be exhaustively listed.

[0205] In another possible implementation, a third weight is determined based on at least one of the first or second parameter information, the third weight representing the degree of influence of the first information on the target information. A fourth weight is determined based on at least one of the first or second parameter information, the fourth weight representing the degree of influence of the second information on the target information. The target information is determined based on the third weight, the fourth weight, the first information, and the second information.

[0206] The parameter information of a data type may include at least one of the following: the preset priority level of the data type, the number of map elements in the information used to determine the target information that match the information of the map elements corresponding to the data type, the data volume of the data type, the confidence level of the data of the data type, or the historical map element recognition accuracy of the data acquisition device corresponding to the data of the data type.

[0207] To make the explanation clearer, we will take the first data type as an example and use the following information b1, information b2, information b3, and information b4 to introduce the parameter information (first parameter information) of the first data type:

[0208] Information b1: The default priority level of the first data type.

[0209] One possible implementation is to prioritize data types. For example, considering that feature-level data may filter out some key information from the original data, while target-level data may filter out even more information, one possible ordering of data type priorities is: original data has the highest priority, followed by feature-level data, and target-level data has the lowest priority. The higher the priority of a data type, the greater the weight of the map element information corresponding to that data type can be.

[0210] In one possible implementation, if the map element is the content on a sign (such as the aforementioned maximum speed limit sign), and if the map element information corresponding to different data types is different, then the information of the map element in the original data can be selected as the target information.

[0211] Information b2: The amount of data in the first data type.

[0212] In one possible implementation, the map updating device receives data of a first data type from multiple data acquisition devices. It can further fuse this data to obtain fused data, and then extract the first information of map elements from the fused first data type. Information b2 refers to the sample data size of the fused first data type. In one possible implementation, the larger the sample data size, the more accurate the fused first data type, and the more accurate the first information of the map elements; the greater the weight of the first information of the map elements can be.

[0213] For example, the data of the first data type in information b2 is D. V11 and D V12 As can be seen, the data size of the first data type in this example is 2. Similarly, for example, the data size of the second data type could be 3.

[0214] Information b3: The reliability of data of the first data type.

[0215] The credibility of data of the first data type can be considered as the credibility of the first piece of information. This can be determined based on the credibility W. V11 And credibility W V12 We obtain the following: The credibility W. V11 It can include DV11 The confidence level, and / or, vehicle V 11 The accuracy of historical map element recognition. Credibility W V12 It can include D V12 The confidence level, and / or, vehicle V 12 The accuracy of historical map element recognition. Among them, the reliability W V11 For map element i in data D V11 Credibility, Credibility W V12 For map element i in data D V12 The credibility of data D. V11 For vehicle V 11 The reported data includes map element i. Data D V12 For vehicle V 12 The reported data includes map element i.

[0216] Information b4: The number of information items that match the first information item among N information items.

[0217] When the information of a map element is its location information, if one of the N pieces of information, such as the second piece of information, is within a preset distance threshold between the location indicated by the second piece of information and the location indicated by the first piece of information, then the first piece of information can be said to match the second piece of information. The location indicated by the second piece of information and the location indicated by the first piece of information can be the same or different.

[0218] When the information of a map element is the content of a sign, the first and second pieces of information are said to match if they are the same. If they are different, they are said to not match.

[0219] The above example uses the first data type. Similarly, the parameter information for the second data type may include at least one of the following: the preset priority level of the second data type, the data volume of the second data type, the reliability of the second data type, or the number of information items that match the second information out of N information items. For a detailed description of these details, please refer to information b1 to b4 above; they will not be repeated here.

[0220] In another possible implementation, the content included in the first parameter information can be determined sequentially according to the priority of the following parameter items: The parameter item with the highest priority is: the preset priority level of the first data type. The parameter item with the second highest priority is: the number of pieces of information in the map element information used to determine the target information that match the first information. The parameter item with the next highest priority is: the amount of data in the first data type. In another possible implementation, the content included in the second parameter information can be determined sequentially according to the priority of the following parameter items: The parameter item with the highest priority is: the preset priority level of the second data type. The parameter item with the second highest priority is: the number of pieces of information in the map element information used to determine the target information that match the second information. The parameter item with the next highest priority is: the amount of data in the second data type.

[0221] For example, in step 203 above, the N pieces of information include first information, second information, and fifth information. The first information is obtained from target-level data, the second information is obtained from feature-level data, and the fifth information is obtained from the original data. In one possible implementation, the target information of the map element can be determined based on a preset priority level of the data type. For example, if the priority of the original data is set to the highest, and the priority of the feature-level data and the target-level data are the same, then the fifth information can be determined as the target information. In another possible implementation, if the N pieces of information do not include information obtained from the original data, for example, only information obtained from feature-level data and information obtained from target-level data, then the target information can be determined based on the number of consistent information among the N pieces of information. That is, the information with the highest number of consistent information among the N pieces of information is taken as the target information. If there are M1 consistent information 1s and M1 consistent information 2s among the N pieces of information, and the number of other consistent informations is less than M1, then should information 1 or information 2 be selected? One possible implementation is to take the information with the largest number of sample points among the N pieces of information as the target information. In another possible implementation, the number of all sample points corresponding to information 1 can be determined, the number of all sample points corresponding to information 2 can be determined, and then the information with a larger number of sample points can be used as the target information.

[0222] In another possible implementation, the third weight of the first information can be determined based on one of the information b1 to information b4. In yet another possible implementation, the third weight of the first information can be determined based on multiple items of the information b1 to information b4. For example, a weight can be assigned to each item of the information b1 to information b4, and scores can be assigned to each item of the information b1 to information b4 to obtain a score for each item. Then, these four scores are weighted and summed to obtain the total score for the first information.

[0223] Similarly, we can obtain the total score for each of the N pieces of information, and then determine the weight of each piece of information based on the proportional relationship between the total scores of the N pieces of information. For example, if the N pieces of information only include the first and second pieces of information, the proportional relationship between the total score of the first and second pieces of information can be used as the ratio between the third and fourth weights.

[0224] In one possible implementation, the weight of a data type in this application embodiment can be set according to specific circumstances, specifically, it can be set according to the information of map elements.

[0225] For example, if the information of a map element is location information, then the weight value corresponding to one of the N pieces of information mentioned above can be 0 or 1, or a value other than 0 and 1. For example, the first piece of information includes the first location information of the map element, such as the coordinates of the map element in the Earth coordinate system. The second piece of information includes the second location information of the map element. In this case, the third and fourth weights can be set to 0 and 1, respectively, so that the second piece of information can be selected as the target information from the first and second pieces of information. In another possible implementation, the third and fourth weights can also be set to other parameters, such as 20% and 80%, etc. In this case, the coordinate values ​​in the first and second pieces of information can be weighted and summed, and the average value can be obtained to obtain the target information.

[0226] For another example, when the information of a map element is the content of a sign, the weight value corresponding to one of the N pieces of information mentioned above can only be 0 or 1, and cannot be any other value. For example, if the map element is a maximum speed limit sign, the first information includes the first identification content of the map element (the first identification content shows that the identified maximum speed limit sign is 80 kilometers per hour (km / h)). The second information includes the second identification content of the map element (the second identification content shows that the identified maximum speed limit sign is 60 km / h). In this case, the values ​​of the third and fourth weights can only be set to 0 and 1. For example, if the third weight is 0 and the fourth weight is 1, it means that the second information (60 km / h) is selected as the target information. That is, only one can be selected from the first and second information as the target information. When the N pieces of information include more than two pieces of information, when the map element is a maximum speed limit sign, and the N pieces of information include the specific value of the maximum speed limit sign, the map updating device needs to select one of the multiple specific values ​​as the target information.

[0227] In this embodiment, information about multiple map elements can be obtained based on data of various data types, which can also be understood as performing horizontal mutual verification of information about multiple map elements. For example, for the same map element, when the map update device has raw data, feature-level data, and target-level data simultaneously, the cloud can calibrate the feature data and target-level data based on the raw data. Optionally, when there are inconsistencies or conflicts in the results of the three types of data, the map update device can correct the results of detection data of other data types with relatively low confidence based on the detection data results with higher confidence (e.g., higher confidence level). For example, when the map element is location information, such as the first information, second information, and third information all including the location information of the map element, the information in the first information, second information, and third information that is inconsistent with the target information content can be corrected based on the location information in the finally determined target information. Furthermore, the information of the map element collected by the data acquisition device that is inconsistent with the target information can be corrected based on the target information. For example, a correction coefficient can be determined to correct the location information of the map element subsequently collected by the data acquisition device.

[0228] Following step 203 above, in one possible implementation, the map update device located in the cloud can instruct the reporting strategy of the data acquisition device located on the vehicle based on the target information and the data collected by the data acquisition device.

[0229] For example, the map updating device can generate a first message based on at least one of the target information or the data collected by the first data acquisition device, and send the first message to the first data acquisition device. The first message is used to indicate the data reporting cycle of the first data acquisition device, or at least one of the map element type information reported by the first data acquisition device. As another example, the map updating device can generate a second message based on at least one of the target information or the data collected by the second data acquisition device, and send the second message to the second data acquisition device. The second message is used to indicate the data reporting cycle of the second data acquisition device, or at least one of the map element type information reported by the second data acquisition device.

[0230] In practical applications, the map update device can instruct the data acquisition device to report certain information, such as its identification information (when the data acquisition device is a vehicle, this could be the vehicle's license plate number, identification number, or vehicle type information, etc.). In one possible implementation, the map update device can determine the data reporting strategy for a data acquisition device based on the historical map element recognition accuracy of that data acquisition device.

[0231] For example, the data reporting cycle of a data acquisition device can be determined based on its historical map element recognition accuracy. A higher historical map element recognition accuracy allows for a shorter data reporting cycle, while a lower accuracy allows for a longer reporting cycle, or even prevents the device from reporting data altogether.

[0232] For example, based on the historical map element recognition accuracy of the maintained data acquisition equipment, the system can instruct the data acquisition equipment to report the type of map elements. If the data acquisition equipment has a high recognition accuracy for one or several types of map elements, it can be instructed to report only the information of these types of map elements, or to shorten the reporting cycle of the information of these types of map elements.

[0233] For example, the accuracy of historical map element recognition can be statistically analyzed based on different data collection environments (e.g., day or night, sunny or rainy, snowing, suburban or urban, highway or city road, rugged or flat road, congestion, etc.). Based on the historical map element recognition accuracy under the subdivided data collection environment classification, the system can instruct the data collection devices on data reporting strategies related to the data collection environment in which the data collection devices are located. This will comprehensively utilize the data accuracy advantages of each data collection device under specific data collection environments, ultimately improving the accuracy of the map information after the fusion of multiple data collection devices.

[0234] In this application's embodiments, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0235] Furthermore, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority, or importance of multiple objects. For example, "first data type" and "second data type" are only used to distinguish different data types, and do not indicate a difference in priority or importance between the two data types.

[0236] It should be noted that the names of the above messages are merely examples. As communication technology evolves, the names of any of the above messages may change. However, regardless of how the names change, as long as their meaning is the same as that of the messages in this application, they all fall within the protection scope of this application.

[0237] The above mainly describes the solution provided in this application from the perspective of interaction between various network elements. It is understood that, in order to achieve the above functions, each network element includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0238] According to the aforementioned method, Figure 4 Provides executable implementations for embodiments of this application. Figure 2 A schematic diagram of the map updating device for the map updating method shown is provided. Figure 4 As shown, the map update device can be a server-side map update device. It can also be a chip or circuit, such as a chip or circuit that can be installed within a server-side map update device.

[0239] Furthermore, the map updating device 1301 may further include a bus system, wherein the processor 1302, memory 1304, and transceiver 1303 can be connected through the bus system.

[0240] It should be understood that the processor 1302 described above can be a chip. For example, the processor 1302 can be a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0241] In implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware in the processor 1302 or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly implemented by the hardware processor, or by a combination of hardware and software modules in the processor 1302. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 1304, and the processor 1302 reads the information in memory 1304 and, in conjunction with its hardware, completes the steps of the above method.

[0242] It should be noted that the processor 1302 in this application embodiment can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in this application embodiment. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in this application embodiment can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0243] It is understood that the memory 1304 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0244] The map updating device may include a processor 1302, a transceiver 1303, and a memory 1304. The memory 1304 stores instructions, and the processor 1302 executes the instructions stored in the memory 1304 to achieve the above. Figures 1 to 3 The relevant scheme of the map updating device in any one or more of the methods shown.

[0245] In one possible implementation, transceiver 1303 is used to receive data of a first data type and data of a second data type from multiple data acquisition devices. Processor 1302 is used to obtain first information of map elements from the first data type data; obtain second information of map elements from the second data type data; and determine target information of map elements on the map based on the first and second information, wherein the target information includes at least one of location information, content information, or attribute information of the map elements. The first and second data types are two types of data: raw data, feature-level data, or target-level data; raw data is data acquired by sensors; feature-level data is data extracted from the raw data acquired by sensors that can characterize the characteristics of the detected object; target-level data is data extracted from the raw data or feature-level data that can characterize the attributes of the detected object.

[0246] As can be seen, the embodiments of this application can improve the accuracy of target information by comprehensively considering data of multiple data types. For example, feature-level data may filter out some key information because it filters the original data. Combining the original data and feature-level data to determine the target information of map elements can further improve the accuracy of the target information of map elements. As another example, target-level data may filter out some key information compared to the original data and feature-level data because it filters more information from the original data. Therefore, comprehensively considering target-level data and feature-level data, or target-level data and original data, to determine the target information of map elements can further improve the accuracy of the target information of map elements.

[0247] In one possible implementation, the multiple data acquisition devices include a first data acquisition device and a second data acquisition device. The processor 1302 is specifically configured to: obtain third information about map elements from first data acquired by the first data acquisition device; the first data is data of a first data type; obtain fourth information about map elements from second data acquired by the second data acquisition device; the second data is data of a first data type; and obtain first information about map elements based on the third and fourth information.

[0248] In one possible implementation, the processor 1302 is specifically configured to: determine the first information based on at least one of the credibility of the first data or the credibility of the second data, as well as the third information and the fourth information.

[0249] In one possible implementation, the processor 1302 is specifically configured to: determine a first weight based on at least one of the credibility of first data or the credibility of second data, the first weight being used to represent the degree of influence of third information on first information; determine a second weight based on at least one of the credibility of first data or the credibility of second data, the second weight being used to represent the degree of influence of fourth information on first information; and determine first information based on the first weight, the second weight, the third information, and the fourth information.

[0250] In one possible implementation, the reliability of the first data is related to at least one of the following: the historical map element recognition accuracy of the first data acquisition device; or, the confidence level of the first data. Thus, when the historical map element recognition accuracy of the first data acquisition device is considered, the hardware accuracy issues of the first data acquisition device itself may be taken into account, meaning the reliability of the first data can be inferred based on historical performance, thereby further improving the accuracy of the reliability. On the other hand, when the confidence level of the data is combined to determine the reliability of the data, the accuracy of the reliability can be further improved.

[0251] In one possible implementation, the reliability of the second data is related to at least one of the following: the historical map element recognition accuracy of the second data acquisition device; or, the confidence level of the second data. This can further improve the reliability of the first data. Thus, when the historical map element recognition accuracy of the second data acquisition device is considered, the hardware accuracy issues of the second data acquisition device itself may be taken into account, meaning the reliability of the second data can be inferred based on historical performance, thereby further improving the accuracy of the reliability. On the other hand, when the confidence level of the data is combined to determine the reliability of the data, the accuracy of the reliability can be further improved.

[0252] In one possible implementation, the confidence level of the first data is related to at least one of the parameters of the sensor device that acquired the first data, or the relative positional relationship between the sensor device that acquired the first data and map elements. Thus, the confidence level of the first data can more accurately reflect its reliability.

[0253] In one possible implementation, the confidence level of the second data is related to at least one of the parameters of the sensor device acquiring the second data, or the relative positional relationship between the sensor device acquiring the second data and map elements. Thus, the confidence level of the second data can more accurately reflect its reliability.

[0254] In one possible implementation, the processor 1302 is specifically configured to: determine target information based on at least one of first parameter information or second parameter information, and the first information and the second information; wherein the first parameter information is used to represent the reliability of data in data of a first data type, and the second parameter information is used to represent the reliability of data in data of a second data type.

[0255] In one possible implementation, the processor 1302 is specifically configured to: determine a third weight based on at least one of the first parameter information or the second parameter information, wherein the third weight is used to represent the degree of influence of the first information on the target information; determine a fourth weight based on at least one of the first parameter information or the second parameter information, wherein the fourth weight is used to represent the degree of influence of the second information on the target information; and determine the target information based on the third weight, the fourth weight, the first information, and the second information.

[0256] In one possible implementation, the processor 1302 is specifically configured to: determine the information with a higher degree of credibility between the first information and the second information as the target information based on the first parameter information and the second parameter information.

[0257] In one possible implementation, the processor 1302 is further configured to: send target information to the first data acquisition device via transceiver 1303, wherein the target information is used to enable the first data acquisition device to determine the historical map element recognition accuracy of the first data acquisition device in conjunction with the third information.

[0258] In one possible implementation, the processor 1302 is further configured to: send target information to the second data acquisition device via transceiver 1303, wherein the target information is used to enable the second data acquisition device to determine the historical map element recognition accuracy of the second data acquisition device in conjunction with the fourth information.

[0259] In one possible implementation, the processor 1302 is further configured to: determine the historical map element recognition accuracy of the first data acquisition device based on the target information and the third information; and send the historical map element recognition accuracy of the first data acquisition device to the first data acquisition device via the transceiver 1303.

[0260] In one possible implementation, the processor 1302 is further configured to: determine the historical map element recognition accuracy of the second data acquisition device based on the target information and the fourth information; and send the historical map element recognition accuracy of the second data acquisition device to the second data acquisition device via the transceiver 1303.

[0261] In one possible implementation, the processor 1302 is further configured to: update the historical map element recognition accuracy of at least one of the multiple data acquisition devices based on data received from multiple data acquisition devices and target information, wherein at least one data acquisition device is a device that provides data of a first data type.

[0262] In one possible implementation, transceiver 1303 is further configured to: instruct at least one data acquisition device on a data reporting strategy, the data reporting strategy being determined based on the historical map element identification accuracy.

[0263] In one possible implementation, transceiver 1303 is specifically configured to: instruct at least one data acquisition device, based on the historical map element identification accuracy of at least one data acquisition device for a specific data type, the reporting cycle of data of a specific data type.

[0264] In one possible implementation, transceiver 1303 is specifically configured to: instruct at least one data acquisition device, based on the historical map element identification accuracy of at least one data acquisition device for a specific map element type, the reporting cycle of map element data for that specific map element type.

[0265] In one possible implementation, transceiver 1303 is specifically configured to: instruct at least one data acquisition device, based on the historical map element identification accuracy of at least one data acquisition device for a specific data acquisition environment, on the data reporting cycle of the specific data acquisition environment.

[0266] Other related descriptions can be found in the foregoing method embodiments, and will not be repeated here. For the concepts, explanations, detailed descriptions, and other steps related to the technical solutions provided in this application embodiment involving the map updating device, please refer to the descriptions of these contents in the foregoing methods or other embodiments, and will not be repeated here.

[0267] According to the aforementioned method, Figure 5 This is a schematic diagram of the structure of the map updating device provided in the embodiments of this application, such as... Figure 5 As shown, the map updating device 1401 may include a communication interface 1403, a processor 1402, and a memory 1404. The communication interface 1403 is used for inputting and / or outputting information; the processor 1402 is used to execute computer programs or instructions, causing the map updating device 1401 to perform the aforementioned functions. Figures 1 to 3 In the relevant scheme, the map updating device 1401 achieves the above. Figures 1 to 3 The method on the map updating device side in the relevant solutions. In this embodiment, the communication interface 1403 can implement the above. Figure 4 The transceiver 1303 implements the above-mentioned solution, and the processor 1402 can implement it. Figure 4 The processor 1302 implements the above-mentioned scheme, and the memory 1404 can implement the above-mentioned scheme. Figure 4 The solution implemented by memory 1304 will not be described in detail here.

[0268] Based on the above embodiments and the same concept, Figure 6 The embodiments provided in this application can achieve, as Figure 2 A schematic diagram of the map updating device for the map updating method shown is as follows: Figure 6 As shown, the map update device 1501 can be a map update device on the server side, or it can be a chip or circuit, such as a chip or circuit that can be set in a map update device on the server side.

[0269] The communication unit 1503 is used to receive data of a first data type and data of a second data type from multiple data acquisition devices. The processing unit 1502 is used to obtain first information of a map element from the first data type data, obtain second information of a map element from the second data type data, and determine the target information of the map element on the map based on the first information and the second information, wherein the target information includes at least one of location information or road markings.

[0270] In one possible implementation, the first data type and the second data type are two of the following: raw data, feature-level data, or target-level data; the raw data is the data collected by the sensor; the feature-level data is the data extracted from the raw data collected by the sensor that can characterize the features of the object being detected; and the target-level data is the data extracted from the raw data or the feature-level data that can characterize the attributes of the object being detected.

[0271] As can be seen, the embodiments of this application can improve the accuracy of target information by comprehensively considering data of multiple data types. For example, feature-level data may filter out some key information because it filters the original data. Combining the original data and feature-level data to determine the target information of map elements can further improve the accuracy of the target information of map elements. As another example, target-level data may filter out some key information compared to the original data and feature-level data because it filters more information from the original data. Therefore, comprehensively considering target-level data and feature-level data, or target-level data and original data, to determine the target information of map elements can further improve the accuracy of the target information of map elements.

[0272] In the case where the map updating device 1501 corresponds to the server-side map updating device in the above method, the communication unit 1503 is used to receive a first message. The processing unit 1502 is used to parse the first message to obtain first data and update the map based on the first data. The first data is obtained based on data collected by at least one sensor of the vehicle, and the first message includes the first data. The first message includes at least one of first indication information, second indication information, and third indication information.

[0273] For the concepts, explanations, detailed descriptions, and other steps related to the technical solutions provided in the embodiments of this application involved in the map updating device, please refer to the descriptions of these contents in the foregoing methods or other embodiments, which will not be repeated here.

[0274] It is understood that the functions of each unit in the map update device 1501 described above can be referred to the implementation of the corresponding method embodiments, and will not be repeated here.

[0275] It should be understood that the above division of the map update device units is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. In this embodiment, the communication unit 1503 can be composed of the above-mentioned... Figure 4 The transceiver 1303 is implemented, and the processing unit 1502 can be implemented by the above. Figure 4 The processor 1302 is implemented.

[0276] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code or instructions, which, when executed on a computer, cause the computer to perform... Figures 1 to 3 The method of any one of the embodiments shown.

[0277] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when executed on a computer, causes the computer to perform... Figures 1 to 3 The method of any one of the embodiments shown.

[0278] According to the method provided in the embodiments of this application, this application also provides a chip system, which may include a processor. The processor is coupled to a memory and can be used to execute... Figures 1 to 3 The method of any one of the embodiments shown. Optionally, the chip system further includes a memory. The memory is used to store computer programs (also referred to as code or instructions). The processor is used to call and run the computer programs from the memory, causing the device on which the chip system is installed to perform... Figures 1 to 3 The method of any one of the embodiments shown.

[0279] According to the method provided in the embodiments of this application, this application also provides a system, which includes one or more vehicles as described above and a map updating device on the server side, wherein the data acquisition device described above is installed in the vehicle.

[0280] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0281] It should be noted that a portion of this patent application contains copyrighted material. The copyright holder retains all rights except for making copies of the contents of patent documents or records from the patent office.

[0282] The map update devices in the above-described device embodiments correspond to those in the method embodiments, with corresponding modules or units executing the respective steps. For example, the communication unit (transceiver) executes the receiving or sending steps in the method embodiments, while other steps besides sending and receiving can be executed by the processing unit (processor). The specific functions of each unit can be found in the corresponding method embodiments. There can be one or more processors.

[0283] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0284] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0285] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0286] In addition, the functional units in the various embodiments of this application can be integrated into one unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0287] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A map updating method, characterized in that, include: Receive data of a first data type and data of a second data type from multiple data acquisition devices; Obtain the first information of the map element from the data of the first data type; The second information of the map element is obtained from the data of the second data type; Based on the first information and the second information, the target information of the map element on the map is determined, wherein the target information includes at least one of the location information, content information or attribute information of the map element; Wherein, the first data type and the second data type are two data types among raw data, feature-level data, or target-level data; the first data type and the second data type are different; The raw data is the data collected by the sensor; The feature-level data refers to the data extracted from the raw data collected by the sensor that can characterize the features of the object being detected. The target-level data is data extracted from the raw data or feature-level data that can characterize the properties of the object being detected; The step of determining the target information of the map element on the map based on the first information and the second information of the map element includes: The target information is determined based on at least one of the first parameter information or the second parameter information, as well as the first information and the second information; wherein the first parameter information is used to indicate the credibility of the data of the first data type, and the second parameter information is used to indicate the credibility of the data of the second data type. The first parameter information includes at least one of the following: The preset priority level of the first data type; The amount of data in the first data type; The confidence level of the data of the first data type; or, The historical map element recognition accuracy of the data acquisition device corresponding to the data of the first data type; The second parameter information includes at least one of the following: The preset priority level of the second data type; The amount of data in the second data type; The confidence level of the data in the second data type; or, The accuracy rate of historical map element recognition of the data acquisition device corresponding to the data of the second data type.

2. The method as described in claim 1, characterized in that, The plurality of data acquisition devices includes a first data acquisition device and a second data acquisition device, wherein obtaining the first information of map elements from data of the first data type includes: The third information of the map element is obtained from the first data acquired by the first data acquisition device, wherein the first data is data of the first data type; The fourth information of the map element is obtained from the second data acquired by the second data acquisition device, wherein the second data is data of the first data type; Based on the third and fourth information, the first information of the map element is obtained.

3. The method as described in claim 2, characterized in that, The step of obtaining the first information of the map element based on the third information and the fourth information includes: The first information is determined based on at least one of the credibility of the first data or the credibility of the second data, as well as the third information and the fourth information.

4. The method as described in claim 3, characterized in that, The method of basing decisions on at least one of the credibility of the first data or the credibility of the second data, along with the third information and the fourth information, includes: A first weight is determined based on at least one of the credibility of the first data or the credibility of the second data, wherein the first weight is used to represent the degree of influence of the third information on the first information; A second weight is determined based on at least one of the credibility of the first data or the credibility of the second data, and the second weight is used to represent the degree of influence of the fourth information on the first information; The first information is determined based on the first weight, the second weight, the third information, and the fourth information.

5. The method as described in claim 3 or 4, characterized in that, The reliability of the first data is related to at least one of the following: The historical map element recognition accuracy of the first data acquisition device; or... Confidence level of the first data; The reliability of the second data is related to at least one of the following: The historical map element recognition accuracy of the second data acquisition device; or, The confidence level of the second data.

6. The method according to any one of claims 1-4, characterized in that, Determining the target information based on at least one of the first parameter information or the second parameter information, and the first information and the second information, includes: A third weight is determined based on at least one of the first parameter information or the second parameter information, wherein the third weight is used to represent the degree of influence of the first information on the target information; A fourth weight is determined based on at least one of the first parameter information or the second parameter information, wherein the fourth weight is used to represent the degree of influence of the second information on the target information; The target information is determined based on the third weight, the fourth weight, the first information, and the second information.

7. The method according to any one of claims 1-4, characterized in that, Determining the target information based on at least one of the first parameter information or the second parameter information, and the first information and the second information, includes: Based on the first parameter information and the second parameter information, the information with a higher degree of credibility between the first information and the second information is determined as the target information.

8. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the data received from the plurality of data acquisition devices and the target information, the historical map element recognition accuracy of at least one of the plurality of data acquisition devices is updated, wherein the at least one data acquisition device is a device that provides data of the first data type or the second data type; Instruct the at least one data acquisition device on a data reporting strategy, the data reporting strategy being determined based on the historical map element identification accuracy.

9. The method as described in claim 8, characterized in that, The historical map element recognition accuracy of the at least one data acquisition device includes at least one of the following: The detection success rate of the at least one data acquisition device within a preset time period; Within a preset time period, the number of times the at least one data acquisition device makes an effective contribution to cloud fusion; Within a preset time period, the reliability rating of the at least one data acquisition device is determined by a star rating. The number of times the at least one data acquisition device makes a detection error within a preset time period; Within a preset time period, the detection error of the at least one data acquisition device; or Within a preset time period, the accuracy of the detection results of the at least one data acquisition device is rated in stars.

10. The method as described in claim 8, characterized in that, The historical map element recognition accuracy of the at least one data acquisition device is: Accuracy of identifying historical map elements for specific data types; Accuracy of historical map element recognition for a specific map element type, or Accuracy of historical map element recognition for specific data collection environments.

11. The method as described in claim 8, characterized in that, The instruction of the data reporting strategy to the at least one data acquisition device includes at least one of the following: Based on the historical map element recognition accuracy of the at least one data acquisition device for a specific data type, the at least one data acquisition device is instructed on the reporting cycle of the data for the specific data type. Based on the historical map element identification accuracy of the at least one data acquisition device for a specific map element type, instruct the at least one data acquisition device of: the reporting cycle for the data of map elements of the specific map element type; or, Based on the historical map element recognition accuracy of the at least one data acquisition device for a specific data acquisition environment, the at least one data acquisition device is instructed on the data reporting cycle for the specific data acquisition environment.

12. A map updating device, characterized in that, include: A communication unit is used to receive data of a first data type and data of a second data type from multiple data acquisition devices; A processing unit is configured to obtain first information about map elements from data of the first data type; Second information of the map element is obtained from the data of the second data type; based on the first information and the second information, target information of the map element on the map is determined, wherein the target information includes at least one of the location information, content information or attribute information of the map element; Wherein, the first data type and the second data type are two data types among raw data, feature-level data, or target-level data; the first data type and the second data type are different; The raw data is the data collected by the sensor; The feature-level data refers to the data extracted from the raw data collected by the sensor that can characterize the features of the object being detected. The target-level data is data extracted from the raw data or feature-level data that can characterize the properties of the object being detected; The step of determining the target information of the map element on the map based on the first information and the second information of the map element includes: The target information is determined based on at least one of the first parameter information or the second parameter information, as well as the first information and the second information; wherein the first parameter information is used to indicate the credibility of the data of the first data type, and the second parameter information is used to indicate the credibility of the data of the second data type. The first parameter information includes at least one of the following: The preset priority level of the first data type; The amount of data in the first data type; The confidence level of the data of the first data type; or, The historical map element recognition accuracy of the data acquisition device corresponding to the data of the first data type; The second parameter information includes at least one of the following: The preset priority level of the second data type; The amount of data in the second data type; The confidence level of the data in the second data type; or, The accuracy rate of historical map element recognition of the data acquisition device corresponding to the data of the second data type.

13. The map updating device as described in claim 12, characterized in that, The processing unit is specifically used for: The third information of the map element is obtained from the first data acquired by the first data acquisition device, wherein the first data is data of the first data type; The fourth information of the map element is obtained from the second data acquired by the second data acquisition device, wherein the second data is data of the first data type; Based on the third and fourth information, the first information of the map element is obtained.

14. The map updating apparatus as described in claim 13, characterized in that, The processing unit is specifically used for: The first information is determined based on at least one of the credibility of the first data or the credibility of the second data, as well as the third information and the fourth information.

15. The map updating apparatus as described in claim 14, characterized in that, The processing unit is specifically used for: A first weight is determined based on at least one of the credibility of the first data or the credibility of the second data, wherein the first weight is used to represent the degree of influence of the third information on the first information; A second weight is determined based on at least one of the credibility of the first data or the credibility of the second data, and the second weight is used to represent the degree of influence of the fourth information on the first information; The first information is determined based on the first weight, the second weight, the third information, and the fourth information.

16. The map updating apparatus as described in claim 14 or 15, characterized in that, The reliability of the first data is related to at least one of the following: The historical map element recognition accuracy of the first data acquisition device; or... Confidence level of the first data; The reliability of the second data is related to at least one of the following: The historical map element recognition accuracy of the second data acquisition device; or, The confidence level of the second data.

17. The map updating apparatus according to any one of claims 12-15, characterized in that, The processing unit is specifically used for: A third weight is determined based on at least one of the first parameter information or the second parameter information, wherein the third weight is used to represent the degree of influence of the first information on the target information; A fourth weight is determined based on at least one of the first parameter information or the second parameter information, wherein the fourth weight is used to represent the degree of influence of the second information on the target information; The target information is determined based on the third weight, the fourth weight, the first information, and the second information.

18. The map updating apparatus as described in claim 17, characterized in that, The processing unit is specifically used for: Based on the first parameter information and the second parameter information, the information with a higher degree of credibility between the first information and the second information is determined as the target information.

19. The map updating apparatus according to any one of claims 12-15, characterized in that, The processing unit is further configured to: Based on data received from the plurality of data acquisition devices and the target information, the historical map element recognition accuracy of at least one of the plurality of data acquisition devices is updated, wherein the at least one data acquisition device is a device that provides data of the first data type or the second data type; or... The communication unit is further used for: Instruct the at least one data acquisition device on a data reporting strategy, the data reporting strategy being determined based on the historical map element identification accuracy.

20. The map updating apparatus as described in claim 19, characterized in that, The historical map element recognition accuracy of the at least one data acquisition device includes at least one of the following: The detection success rate of the at least one data acquisition device within a preset time period; Within a preset time period, the number of times the at least one data acquisition device makes an effective contribution to cloud fusion; Within a preset time period, the reliability rating of the at least one data acquisition device is determined by a star rating. The number of times the at least one data acquisition device makes a detection error within a preset time period; The detection error of the at least one data acquisition device within a preset time period; Within a preset time period, the accuracy of the detection results of the at least one data acquisition device is rated in stars.

21. The map updating apparatus as described in claim 19, characterized in that, The historical map element recognition accuracy of the at least one data acquisition device is at least one of the following: Accuracy of identifying historical map elements for specific data types; Accuracy of historical map element recognition for a specific map element type, or Accuracy of historical map element recognition for specific data collection environments.

22. The map updating apparatus as described in claim 19, characterized in that, The communication unit is specifically used for: Based on the historical map element recognition accuracy of the at least one data acquisition device for a specific data type, the at least one data acquisition device is instructed on the reporting cycle of the data for the specific data type. Based on the historical map element identification accuracy of the at least one data acquisition device for a specific map element type, instruct the at least one data acquisition device of: the reporting cycle for the data of map elements of the specific map element type; or, Based on the historical map element recognition accuracy of the at least one data acquisition device for a specific data acquisition environment, the at least one data acquisition device is instructed on the data reporting cycle for the specific data acquisition environment.

23. A map updating device, characterized in that, It includes a processor and a memory, the memory being used to store computer-executable instructions, the processor executing the computer-executable instructions in the memory to cause the map updating device to perform the method of any one of claims 1-11.

24. A map updating device, characterized in that, Including processor and communication interface, The communication interface is used for inputting and / or outputting information; The processor is configured to execute a computer program that causes the method of any one of claims 1-11 to be performed.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer-executable program, which, when executed by a processor, causes the method of any one of claims 1-11 to be performed.

26. A computer program product, characterized in that, When the computer program product is run on a processor, the method of any one of claims 1-11 is performed.

Images