Method, device and system for processing reported information

Abstract

The present application discloses a method, device and system for processing reported information, which is used to provide an efficient and accurate way to process multiple identification information reported for the same target. The method includes: a cloud server receives N identification information of a target object from N acquisition devices, N is a positive integer, and the identification information includes the identification result, confidence value and confidence type of the target object; the N received identification information is divided into M groups according to the confidence type, M is a positive integer not greater than N; the group identification information corresponding to each group in the M groups is determined, a group of identification information is selected, and the identification result in the selected identification information is determined as the final result of the target object. Through this method, the cloud server can select and compare the confidence value of the identification information according to the confidence type in the received identification information, so as to obtain a more accurate final result of the target object, effectively improving the accuracy of the result.

Description

Technical Field

[0001] The present invention relates to the technical field of information collection, and in particular to a method, device and system for processing reported information. Background Art

[0002] High-precision maps are often used during travel to help travelers and autonomous vehicles make more accurate decisions. Due to the increasing demand for high-precision map accuracy, frequent data collection and timely updates to high-precision maps are necessary.

[0003] At present, in the process of collecting data information for high-precision maps, the static part of the high-precision map is often drawn first using a centralized collection method, and then the drawn high-precision map is updated and improved using a crowdsourcing collection method.

[0004] However, in a crowdsourcing collection model, since it is necessary to collect identification information of target objects reported by numerous vehicles, and different vehicles have different recognition capabilities and accuracy, different vehicles may report different results for the same target, increasing the difficulty for the cloud server to accurately determine the target object. For example, suppose the target object is an 80km / h speed limit sign on the side of a highway. Among them, one vehicle may identify the target object as an 80km / h speed limit sign, while another vehicle may mistakenly identify the target object as a 60km / h speed limit sign. After receiving different recognition results for the same target object, the cloud server needs to determine which result to accept and update it to the map. If the selection is inappropriate, it may lead to errors, posing a hidden danger to traffic safety.

[0005] However, currently, cloud servers do not have an accurate and effective method for processing multiple pieces of identification information received from the same target object. Summary of the Invention

[0006] The present application provides a method, device and system for processing reported information, which are used to process reported information efficiently and accurately.

[0007] It should be understood that the method for processing reported information provided in the embodiments of the present application can be executed by a processing device and a processing system for reported information.

[0008] Among them, the processing system of the reported information includes a cloud server and a collection device.

[0009] Among them, the cloud server can be a server with processing functions, such as a central processing unit, or a processing chip in the server. The specific embodiments of the present application do not limit the cloud server.

[0010] It should be understood that there are various situations of the collection device provided in the embodiments of the present application. It can be a single device or a combination of at least two devices.

[0011] Exemplarily, the collection device may be at least one mobile collection device, at least one fixed collection device, or a combination of at least one mobile collection device and at least one fixed collection device.

[0012] In a possible implementation, the fixed data collection device is a road side unit (RSU).

[0013] Exemplarily, in the embodiment of the present application, the device for collecting target objects, determining identification information of target objects, and reporting the identification information of the target objects is executed by the RSU.

[0014] Preferably, the RSU integrates one or more sensors such as a camera, a radar, a GPS receiver, etc., and has acquisition function, processing function, and transceiver function.

[0015] In which, when the RSU executes the method for processing reported information, the target object is collected through the camera and / or sensor in the RSU, and the processor in the RSU determines the identification information of the target object based on the collected information. The identification information includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value, and then the identification information of the target object is sent to the cloud server through the transceiver in the RSU.

[0016] In a possible implementation, the fixed acquisition device is a combination of an RSU and at least one sensor and / or camera.

[0017] Exemplarily, in the embodiment of the present application, the device for collecting target objects, determining identification information of target objects, and reporting the identification information of the target objects is performed by the RSU in combination with the at least one sensor and / or camera.

[0018] In which, when the RSU combines with the at least one sensor and / or camera to execute the reported information processing method, the RSU collects the target object through at least one external camera and / or sensor, and obtains the information collected by the at least one camera and / or sensor. The RSU determines the identification information of the target object through its own processor based on the collected information. The identification information includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value. Then, the identification information of the target object is sent to the cloud server through the transceiver in the RSU.

[0019] In a possible implementation, the fixed data collection device is a combination of an RSU having data collection and transceiver functions and a central processing unit.

[0020] Exemplarily, in the embodiment of the present application, the device for collecting target objects, determining identification information of target objects, and reporting the identification information of the target objects is executed by the RSU in combination with the central processor.

[0021] When the RSU executes the method for processing reported information in conjunction with the central processor, the target object is captured by at least one camera and / or sensor in the RSU, and the information collected by the target object is sent to the central processor. The central processor determines the identification information of the target object based on the received collected information of the target object, and the identification information includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value. The central processor sends the identification information of the target object to the RSU, and the RSU sends the received identification information of the target object to the cloud server.

[0022] Preferably, the central processor stores information for determining the recognition capability and recognition accuracy of the RSU, so that the recognition information of the target object processed by the central processor based on the collected information of the target object sent by the RSU can better represent the result of the RSU.

[0023] In a possible implementation, the mobile data collection device is a vehicle.

[0024] Exemplarily, in the embodiment of the present application, the device for collecting target objects, determining identification information of target objects, and reporting the identification information of the target objects is executed by the vehicle.

[0025] Preferably, the vehicle is an intelligent vehicle comprising at least one camera, a memory, a transceiver, a processor and a sensor.

[0026] In which, when the vehicle executes the processing method for reporting information in the embodiment of the present application, the target object is collected through the camera and / or sensor in the vehicle, and the processor in the vehicle determines the identification information of the target object based on the collected information. The identification information includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value, and then the identification information of the target object is sent to the cloud server through the transceiver in the vehicle.

[0027] In a possible implementation, the mobile data collection device is a combination of a vehicle having data collection and transceiver functions and a central processing unit.

[0028] Exemplarily, in the embodiment of the present application, the device for collecting target objects, determining identification information of target objects, and reporting the identification information of the target objects is executed by the vehicle in combination with the central processor.

[0029] When the RSU executes the method for processing reported information in conjunction with the central processor, the target object is captured through at least one camera and / or sensor in the vehicle, and the information collected by the target object is sent to the central processor. The central processor determines the identification information of the target object based on the received collected information of the target object, and the identification information includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value. The central processor sends the identification information of the target object to the vehicle, and the vehicle sends the received identification information of the target object to the cloud server.

[0030] Preferably, the central processing unit stores information for determining the recognition capability and recognition accuracy of the vehicle, so that the recognition information of the target object processed by the central processing unit based on the collected information of the target object sent by the vehicle can better represent the result of the vehicle.

[0031] It should be noted that the RSU may also be replaced by other devices with similar functions to the RSU, and this application does not limit this.

[0032] In an optional implementation of the embodiments of the present application, the methods described in aspects 1 to 2 may be performed by an electronic device, wherein the electronic device may be a server (or cloud server), an integrated circuit in a server, or a chip in a server. The following will be performed using a cloud server as an example.

[0033] In an optional implementation of the embodiment of the present application, the methods described in aspects 3 to 4 may be performed by a collection device, which may be a vehicle, and is not specifically limited in the embodiment of the present application.

[0034] In a first aspect, an embodiment of the present application provides a method for processing reported information, including:

[0035] A cloud server receives N identification information of a target object from N acquisition devices, where N is a positive integer, and the identification information includes an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value; the cloud server divides the received N identification information into M groups according to the confidence type in the identification information, where M is a positive integer not greater than N; the cloud server determines the group identification information corresponding to each group in the M groups; the cloud server selects a group of identification information from the M groups of identification information, and determines the identification result in the selected identification information as the final result of the target object. Among them, optionally, when the above method is executed by the processing system of the reported information, the cloud server in the processing system of the reported information receives N identification information of the target object from N collection devices through the transceiver in the cloud server, and then processes the received N identification information through the processor in the cloud server. For example, the processor divides the received N identification information into M groups, determines the group identification information corresponding to each group in the M groups, selects one group of identification information from the M groups of identification information, and determines the identification result in the selected identification information as the final result of the target object.

[0036] Based on the above method, the cloud server can group and compare the received identification information of the target object according to the confidence type in the received identification information, so as to obtain a more accurate final result of the target object, effectively improving the accuracy of the result.

[0037] In a possible implementation, the N pieces of identification information are received by the cloud server within a first threshold time period.

[0038] Optionally, a timer may be set in the cloud server, and the timing duration of the timer is a threshold duration.

[0039] Exemplarily, the cloud server may start the timer after receiving the identification information of the target object sent by the first acquisition device, and stop receiving the identification information of the target object sent by the acquisition device after the timer ends.

[0040] Based on the above method, by setting a threshold time length, the time for the cloud server to receive the identification information of the target object sent by the collection device is limited, thereby effectively avoiding the cloud server waiting indefinitely for the identification information of the target object sent by the collection device and being unable to determine the final result of the target object in a timely manner.

[0041] In one possible implementation, before the cloud server receives the identification information of the target object sent by N collection devices, the cloud server sends a first indication message to the collection devices within a threshold range. The first indication message is used to instruct the collection devices to identify the target object and report the identification information of the target object.

[0042] When the above method is executed by the reporting information processing system, the cloud server in the reporting information processing system sends the first indication information to the collection device within the threshold range through the transceiver in the cloud server.

[0043] For example, because the cloud server needs to obtain the identification information of the target object, in order to effectively reduce unnecessary signaling overhead and to improve the effectiveness of the received identification information of the target object, a threshold range can be preset and a first indication information can be sent to the collection device within the threshold range.

[0044] Preferably, the cloud server can obtain the location information of the target object, and determine the area to which the indication information needs to be sent based on the location of the target object and the threshold range. Thus, the cloud server sends the first indication information to at least one collection device in the area.

[0045] Based on the above method, by setting the threshold range, unnecessary signaling overhead is effectively reduced, and the effectiveness of the received identification information of the target object is improved.

[0046] In a possible implementation, before the cloud server sends the first indication information to the collection devices within a threshold range, the cloud server receives identification information of the target object sent by less than a threshold number of collection devices.

[0047] When the above method is executed by the processing system of the reported information, the cloud server in the processing system of the reported information receives identification information of the target object sent by less than the threshold number of collection devices through the transceiver before sending the first indication information to the collection devices within the threshold range through the transceiver.

[0048] Exemplarily, one situation that triggers the cloud server to send the first indication information to the collection devices within the threshold range is that the cloud server receives identification information of the target objects sent by the collection devices less than the threshold number through the transceiver. Because the number of identification information of the target objects received by the cloud server is less than the threshold number, in order to ensure the validity of the final result of the cloud server determining the target object, the cloud server needs to obtain identification information of a certain number of target objects. To this end, the cloud server triggers the sending of the first indication information to the collection devices within the threshold range.

[0049] Based on the above method, after the cloud server determines that the number of identification information of the target object received is less than the threshold number, it triggers the sending of the first indication information to the collection device within the threshold range, so that the cloud server can obtain the identification information of a larger number of target objects, effectively improving the accuracy of the final result of the cloud server in determining the target object.

[0050] In a possible implementation, the first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0051] Exemplarily, in an embodiment of the present application, it is assumed that the cloud server pre-sets the confidence type for calculating the confidence value of the target object recognition result, for example, confidence type 1 and confidence type 2. The cloud server can send the set confidence type to the collection device through a first indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1 or confidence type 2.

[0052] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value, and can effectively avoid the cloud server being unable to parse the received confidence value due to the lack of the ability to determine the confidence value of other confidence types.

[0053] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0054] In one possible implementation, before the cloud server receives identification information of the target object sent by N acquisition devices, the cloud server sends second indication information to the acquisition devices within a threshold range, where the second indication information is used to indicate at least one confidence type for determining the confidence value of the target object identification result.

[0055] Exemplarily, in an embodiment of the present application, it is assumed that the cloud server pre-sets the confidence type for calculating the confidence value of the target object recognition result, for example, confidence type 1 and confidence type 2. The cloud server can send the set confidence type to the collection device through a second indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1 or confidence type 2.

[0056] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value, and can effectively avoid the cloud server being unable to parse the received confidence value due to the lack of the ability to determine the confidence value of other confidence types.

[0057] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0058] In a possible implementation, each set of identification information in the M groups includes the same confidence type.

[0059] Based on the above method, if the identification information confidence type of each group of target objects is the same after grouping, the confidence values ​​of multiple target objects in the same group can be directly compared, so as to determine the identification information of the target object with the highest accuracy in each group.

[0060] In a possible implementation, the cloud server determines the identification information containing the largest confidence value in each group as the group identification information.

[0061] Based on the above method, an embodiment of the present application provides a method for determining group identification information, that is, determining the identification information containing the largest confidence value in each group as the group identification information.

[0062] In a possible implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0063] Based on the above method, an embodiment of the present application provides a situation of a collection device, for example, the collection device is a mobile collection device and / or a fixed collection device, the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0064] In a possible implementation, the cloud server updates the map area where the target object is located according to the final result of the target object, and notifies at least one collection device of the updated map area.

[0065] When the above method is executed by the reported information processing system, the cloud server in the reported information processing system, when determining through the processor that the final result of the target object is different from the content of the target object in the map area, updates the map area where the target object is located, and notifies the at least one collection device of the updated map area through the transceiver. Or;

[0066] When the above method is executed by the processing system of the reported information, the cloud server in the processing system of the reported information directly updates the map area where the target object is located according to the final result of the target object through the processor, and notifies the at least one collection device of the updated map area through the transceiver.

[0067] It should be noted that the area range of the updated map in the embodiment of the present application can be determined according to actual conditions, and the embodiment of the present application does not limit the scope of determining the updated map area.

[0068] Based on the above method, the cloud server promptly updates the map area where the target object is located according to the final result of the determined target object, and notifies the collection device of the updated map area, so as to timely maintain the information in the map and ensure the validity and real-time nature of the map information.

[0069] In a second aspect, an embodiment of the present application provides a method for processing reported information, including:

[0070] The cloud server receives N identification information of a target object from N acquisition devices, where N is a positive integer, and the identification information includes an identification result of the target object and a confidence value of the identification result, wherein the confidence values ​​in the N identification information are determined by the same confidence type; the cloud server selects the identification information with the largest confidence value among the N identification information; the cloud server determines the identification result in the selected identification information as the final result of the target object.

[0071] Among them, optionally, when the above method is executed by the processing system of the reported information, the cloud server in the processing system of the reported information receives N identification information of the target object from N collection devices through the transceiver in the cloud server, and then processes the received N identification information through the processor in the cloud server. For example, the processor divides the received N identification information into M groups, determines the group identification information corresponding to each group in the M groups, selects one group of identification information from the M groups of identification information, and determines the identification result in the selected identification information as the final result of the target object.

[0072] Based on the above method, in an embodiment of the present application, the identification information of at least one target object received by the cloud server is determined by the same confidence type. The cloud server can directly compare the confidence values ​​in the received identification information, thereby determining the identification result in the identification information with the largest confidence value as the final result of the target object, effectively improving the accuracy of the results.

[0073] In a possible implementation, the N pieces of identification information are received by the cloud server within a threshold time period.

[0074] Optionally, a timer may be set in the cloud server, and the timing duration of the timer is a threshold duration.

[0075] Exemplarily, the cloud server may start the timer after receiving the identification information of the target object sent by the first acquisition device, and stop receiving the identification information of the target object sent by the acquisition device after the timer ends.

[0076] Based on the above method, by setting a threshold time length, the time for the cloud server to receive the identification information of the target object sent by the collection device is limited, thereby effectively avoiding the cloud server waiting indefinitely for the identification information of the target object sent by the collection device and being unable to determine the final result of the target object in a timely manner.

[0077] In one possible implementation, before the cloud server receives the identification information of the target object sent by N collection devices, the cloud server sends a first indication message to the collection devices within a threshold range. The first indication message is used to instruct the collection devices to identify the target object and report the identification information of the target object.

[0078] When the above method is executed by the reporting information processing system, the cloud server in the reporting information processing system sends the first indication information to the collection device within the threshold range through the transceiver in the cloud server.

[0079] For example, because the cloud server needs to obtain the identification information of the target object, in order to effectively reduce unnecessary signaling overhead and to improve the effectiveness of the received identification information of the target object, a threshold range can be preset and a first indication information can be sent to the collection device within the threshold range.

[0080] Preferably, the cloud server can obtain the location information of the target object, and determine the area to which the indication information needs to be sent based on the location of the target object and the threshold range. Thus, the cloud server sends the first indication information to at least one collection device in the area.

[0081] Based on the above method, by setting the threshold range, unnecessary signaling overhead is effectively reduced, and the effectiveness of the received identification information of the target object is improved.

[0082] In a possible implementation, before the cloud server sends the first indication information to the collection devices within a threshold range, the cloud server receives identification information of the target object sent by less than a threshold number of collection devices.

[0083] When the above method is executed by the processing system of the reported information, the cloud server in the processing system of the reported information receives identification information of the target object sent by less than the threshold number of collection devices through the transceiver before sending the first indication information to the collection devices within the threshold range through the transceiver.

[0084] Exemplarily, one situation that triggers the cloud server to send the first indication information to the collection devices within the threshold range is that the cloud server receives identification information of the target objects sent by the collection devices less than the threshold number through the transceiver. Because the number of identification information of the target objects received by the cloud server is less than the threshold number, in order to ensure the validity of the final result of the cloud server determining the target object, the cloud server needs to obtain identification information of a certain number of target objects. To this end, the cloud server triggers the sending of the first indication information to the collection devices within the threshold range.

[0085] Based on the above method, after the cloud server determines that the number of identification information of the target object received is less than the threshold number, it triggers the sending of the first indication information to the collection device within the threshold range, so that the cloud server can obtain the identification information of a larger number of target objects, effectively improving the accuracy of the final result of the cloud server in determining the target object.

[0086] In a possible implementation, the first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0087] Exemplarily, in an embodiment of the present application, it is assumed that the cloud server pre-sets the confidence type for calculating the confidence value of the target object recognition result, for example, confidence type 1 and confidence type 2. The cloud server can send the set confidence type to the collection device through a first indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1 or confidence type 2.

[0088] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value, and can effectively avoid the cloud server being unable to parse the received confidence value due to the lack of the ability to determine the confidence value of other confidence types.

[0089] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0090] In one possible implementation, before the cloud server receives identification information of the target object sent by N acquisition devices, the cloud server sends second indication information to the acquisition devices within a threshold range, where the second indication information is used to indicate at least one confidence type for determining the confidence value of the target object identification result.

[0091] Exemplarily, in an embodiment of the present application, it is assumed that the cloud server pre-sets the confidence type for calculating the confidence value of the target object recognition result, for example, confidence type 1 and confidence type 2. The cloud server can send the set confidence type to the collection device through a second indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1 or confidence type 2.

[0092] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value, and can effectively avoid the cloud server being unable to parse the received confidence value due to the lack of the ability to determine the confidence value of other confidence types.

[0093] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0094] In a possible implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0095] Based on the above method, an embodiment of the present application provides a situation of a collection device, for example, the collection device is a mobile collection device and / or a fixed collection device, the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0096] In a possible implementation, the cloud server updates the map area where the target object is located according to the final result of the target object, and notifies at least one collection device of the updated map area.

[0097] When the above method is executed by the reported information processing system, the cloud server in the reported information processing system, when determining through the processor that the final result of the target object is different from the content of the target object in the map area, updates the map area where the target object is located, and notifies the at least one collection device of the updated map area through the transceiver. Or;

[0098] When the above method is executed by the processing system of the reported information, the cloud server in the processing system of the reported information directly updates the map area where the target object is located according to the final result of the target object through the processor, and notifies the at least one collection device of the updated map area through the transceiver.

[0099] It should be noted that the area range of the updated map in the embodiment of the present application can be determined according to actual conditions, and the embodiment of the present application does not limit the scope of determining the updated map area.

[0100] Based on the above method, the cloud server promptly updates the map area where the target object is located according to the final result of the determined target object, and notifies the collection device of the updated map area, so as to timely maintain the information in the map and ensure the validity and real-time nature of the map information.

[0101] In a third aspect, an embodiment of the present application provides a method for processing reported information, including:

[0102] The acquisition device determines the identification information of the target object, wherein the identification information includes the recognition result of the target object, the confidence value of the recognition result, and the confidence type used to determine the confidence value; the acquisition device sends the identification information of the target object to the cloud server, so that the cloud server updates the map area where the target object is located.

[0103] Optionally, when the above method is performed by the reported information processing system, a collection device in the reported information processing system collects the target object using a camera and / or sensor in the collection device, and sends the collected information of the target object to a processor of the collection device. The collection device determines identification information of the target object based on the processor, and sends the identification information of the target object to a cloud server.

[0104] Based on the above method, in an embodiment of the present application, the identification information of the target object reported by the collection device to the cloud server includes a confidence type for determining the confidence value. The cloud server can then group and compare the received identification information of the target object according to the confidence type in the received identification information, thereby obtaining a more accurate final result of the target object, effectively improving the accuracy of the result.

[0105] In a possible implementation, before the acquisition device determines the identification information of the target object, the acquisition device receives first indication information from the cloud server, where the first indication information is used to instruct the acquisition device to identify the target object and report the identification information of the target object.

[0106] When the above method is executed by the processing system for reporting information, the collection device in the processing system for reporting information triggers the determination of the identification information of the target object after receiving the first indication information sent by the cloud server.

[0107] Based on the above method, an embodiment of the present application provides a method for triggering a collection device to determine the identification information of the target object.

[0108] In a possible implementation, before the acquisition device determines the identification information of the target object, the acquisition device determines that the identification result of the target object obtained is different from the content indicated by the area corresponding to the target object in the map used by the acquisition device.

[0109] When the above method is executed by the processing system of the reported information, the collection device in the processing system of the reported information triggers the determination of the identification information of the target object after determining that the obtained identification result of the target object is different from the content indicated by the corresponding area of ​​the target object in the map applied by the collection device.

[0110] Based on the above method, an embodiment of the present application provides another method for triggering a collection device to determine the identification information of the target object.

[0111] In a possible implementation, the first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0112] Exemplarily, in an embodiment of the present application, it is assumed that the cloud server pre-sets the confidence type for calculating the confidence value of the target object recognition result, for example, confidence type 1 and confidence type 2. The cloud server can send the set confidence type to the collection device through a first indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1 or confidence type 2.

[0113] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value, and can effectively avoid the cloud server being unable to parse the received confidence value due to the lack of the ability to determine the confidence value of other confidence types.

[0114] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0115] In one possible implementation, before the acquisition device determines the identification information of the target object, the acquisition device receives second indication information from the cloud server, where the second indication information is used to indicate at least one confidence type for determining a confidence value of a target object identification result.

[0116] Exemplarily, in an embodiment of the present application, it is assumed that the cloud server pre-sets the confidence type for calculating the confidence value of the target object recognition result, for example, confidence type 1 and confidence type 2. The cloud server can send the set confidence type to the collection device through a second indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1 or confidence type 2.

[0117] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value, and can effectively avoid the cloud server being unable to parse the received confidence value due to the lack of the ability to determine the confidence value of other confidence types.

[0118] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0119] In a possible implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0120] Based on the above method, an embodiment of the present application provides a situation of a collection device, for example, the collection device is a mobile collection device and / or a fixed collection device, the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0121] In a fourth aspect, an embodiment of the present application provides a method for processing reported information, including:

[0122] The acquisition device determines identification information of the target object, wherein the identification information includes an identification result of the target object and a confidence value of the identification result, wherein the confidence value of the identification result is determined by a preset confidence type; the acquisition device sends the identification information of the target object to a cloud server, so that the cloud server updates the map area where the target object is located.

[0123] Optionally, when the above method is performed by the reported information processing system, a collection device in the reported information processing system collects the target object using a camera and / or sensor in the collection device, and sends the collected information of the target object to a processor of the collection device. The collection device determines identification information of the target object based on the processor, and sends the identification information of the target object to a cloud server.

[0124] Based on the above method, in an embodiment of the present application, the identification information of the target object reported by the acquisition device to the cloud server contains an identification result whose confidence value is determined by a preset confidence type. The cloud server can directly compare the received identification information to obtain a more accurate final result of the target object, thereby effectively improving the accuracy of the result.

[0125] In a possible implementation, before the acquisition device determines the identification information of the target object, the acquisition device receives first indication information from the cloud server, where the first indication information is used to instruct the acquisition device to identify the target object and report the identification information of the target object.

[0126] When the above method is executed by the processing system for reporting information, the collection device in the processing system for reporting information triggers the determination of the identification information of the target object after receiving the first indication information sent by the cloud server.

[0127] Based on the above method, an embodiment of the present application provides a method for triggering a collection device to determine the identification information of the target object.

[0128] In a possible implementation, before the acquisition device determines the identification information of the target object, the acquisition device determines that the identification result of the target object obtained is different from the content indicated by the area corresponding to the target object in the map used by the acquisition device.

[0129] When the above method is executed by the processing system of the reported information, the collection device in the processing system of the reported information triggers the determination of the identification information of the target object after determining that the obtained identification result of the target object is different from the content indicated by the corresponding area of ​​the target object in the map applied by the collection device.

[0130] Based on the above method, an embodiment of the present application provides another method for triggering a collection device to determine the identification information of the target object.

[0131] In a possible implementation manner, the first indication information is further used to indicate that the preset confidence type is the first confidence type.

[0132] Exemplarily, in an embodiment of the present application, it is assumed that the confidence type pre-set by the cloud server for calculating the confidence value of the target object recognition result is the first confidence type, for example, the confidence type is confidence type 1, then the cloud server can send the set confidence type to the collection device by sending a first indication message to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1.

[0133] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value.

[0134] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the first indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0135] In a possible implementation, the collection device receives second indication information from the cloud server, where the second indication information is used to indicate that the preset confidence type is the first confidence type.

[0136] Exemplarily, in an embodiment of the present application, it is assumed that the confidence type pre-set by the cloud server for calculating the confidence value of the target object recognition result is the first confidence type, for example, confidence type 1. The cloud server can send the set confidence type to the collection device through a second indication message sent to the collection device, so that the collection device determines the confidence value of the target object recognition result based on confidence type 1.

[0137] Based on the above method, the cloud server can make the confidence values ​​obtained from the recognition results of the target objects reported by the cloud server more comparable by instructing the collection device in advance on the confidence type used to determine the confidence value.

[0138] It should be noted that if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may select a confidence type for determining the confidence value on its own and report the selected confidence value to the cloud server; or, if the confidence type for determining the confidence value indicated to the collection device by the cloud server through the second indication information is a confidence type that the collection device cannot execute, the collection device may apply to the cloud server for re-indication of another confidence type for determining the confidence value. The cloud server may send a notification of the new confidence type only to the collection device, or may re-send a notification of the new confidence type to all collection devices.

[0139] In a possible implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0140] Based on the above method, an embodiment of the present application provides a situation of a collection device, for example, the collection device is a mobile collection device and / or a fixed collection device, the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0141] In a fifth aspect, embodiments of the present application further provide a device for processing reported information, which can be used to perform the operations in any possible implementation of the first and fourth aspects described above. For example, the device may include modules or units for performing each of the operations in the first aspect or any possible implementation of the first aspect described above. For example, it may include a transceiver module and a processing module.

[0142] In the sixth aspect, an embodiment of the present application provides a chip system, including a processor and optionally a memory; wherein the memory is used to store computer programs, and the processor is used to call and run computer programs from the memory, so that a processing device for reporting information installed with the chip system executes any method in any possible implementation method of the above-mentioned first aspect or fourth aspect.

[0143] In a seventh aspect, an embodiment of the present application provides a vehicle, at least one camera, at least one memory, at least one transceiver, and at least one processor;

[0144] The camera is used to capture the target object and obtain at least one image of the target object;

[0145] The memory is used to store one or more programs and data information; wherein the one or more programs include instructions;

[0146] The processor is configured to determine identification information of the target object based on the at least one image, the identification information including a recognition result of the target object, a confidence value of the recognition result, and a type used to determine the confidence value;

[0147] The transceiver is used to send the identification information of the target object to the cloud server.

[0148] In a possible implementation, the vehicle further includes a display screen, a voice broadcast device, and at least one sensor;

[0149] The display screen is used to display the image of the target object;

[0150] The voice broadcasting device is used to broadcast the recognition result of the target object;

[0151] The sensor is used to detect and identify the position, distance and other representative information of the target object.

[0152] Among them, the camera described in the embodiment of the present application can be a camera of a driver monitoring system, a cockpit camera, an infrared camera, a driving recorder (i.e., a recording terminal), a reversing image camera, etc., and is not limited to the specific embodiment of the present application.

[0153] The camera's capture area can be the vehicle's external environment. For example, when the vehicle is moving forward, the capture area is the area in front of the vehicle; when the vehicle is reversing, the capture area is the area behind the vehicle's rear; if the camera is a 360-degree multi-angle camera, the capture area can be the 360-degree area around the vehicle, etc.

[0154] The sensors described in the embodiments of the present application may be one or more of a photoelectric / light-sensitive sensor, an ultrasonic / acoustic sensor, a ranging / distance sensor, a visual / image sensor, and the like.

[0155] In an eighth aspect, an embodiment of the present application provides a first system for processing reported information, the system comprising a cloud server and a collection device;

[0156] The acquisition device is configured to determine identification information of a target object, the identification information including an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value; and transmit the identification information of the target object to a cloud server, so that the cloud server updates a map area where the target object is located;

[0157] The cloud server is used to receive N identification information of a target object from N acquisition devices, where N is a positive integer, and the identification information includes an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value; divide the received N identification information into M groups according to the confidence type in the identification information, where M is a positive integer not greater than N; determine the group identification information corresponding to each group in the M groups; select a group of identification information from the M groups of identification information, and determine the identification result in the selected identification information as the final result of the target object.

[0158] In a ninth aspect, an embodiment of the present application provides a second system for processing reported information, the system comprising a cloud server and a collection device;

[0159] The acquisition device is configured to determine identification information of a target object, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value of the identification result is determined by a preset confidence type; and transmit the identification information of the target object to a cloud server, so that the cloud server updates a map area where the target object is located;

[0160] The cloud server is used to receive N identification information of a target object from N collection devices, where N is a positive integer, and the identification information includes an identification result of the target object and a confidence value of the identification result, wherein the confidence value in the N identification information is determined by a preset confidence type; select the identification information with the largest confidence value among the N identification information; and determine the identification result in the selected identification information as the final result of the target object.

[0161] In the tenth aspect, an embodiment of the present application provides a computer program product, which includes: computer program code, when the computer program code is executed by the communication module, processing module or transceiver, or processor of the information reporting processing device, the information reporting processing device executes any method in any possible implementation method of the first or fourth aspect above.

[0162] In the eleventh aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a program, and the program enables the processing device for reporting information to execute any method in any possible implementation method of the above-mentioned first aspect or fourth aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0163] Figure 1 Schematic diagram of the scene for existing acquisition devices to identify target objects;

[0164] Figure 2 A schematic diagram of the processing scenario of existing reported information;

[0165] Figure 3 A schematic diagram of a system for reporting information processing provided in an embodiment of the present application;

[0166] Figure 4 A schematic diagram of an autonomous driving scenario provided in an embodiment of the present application;

[0167] Figure 5 A schematic diagram of the first application scenario provided in the embodiment of the present application;

[0168] Figure 6 A schematic diagram of a vehicle provided for this application;

[0169] Figure 7 A schematic diagram of a second application scenario provided in an embodiment of the present application;

[0170] Figure 8 A schematic diagram of a first method for processing reported information provided in an embodiment of the present application;

[0171] Figure 9 A schematic diagram of a third application scenario provided in an embodiment of the present application;

[0172] Figure 10 A schematic diagram of a second method for processing reported information provided in an embodiment of the present application;

[0173] Figure 11 A schematic diagram of a fourth application scenario provided in an embodiment of the present application;

[0174] Figure 12 A schematic diagram of a third method for processing reported information provided in an embodiment of the present application;

[0175] Figure 13 A schematic diagram of a fourth method for processing reported information provided in an embodiment of the present application;

[0176] Figure 14 Schematic diagram of the first reporting information processing device provided in this application;

[0177] Figure 15 Schematic diagram of the second reporting information processing device provided in this application. DETAILED DESCRIPTION

[0178] High-precision maps are often used during travel to help travelers and autonomous vehicles make more accurate decisions. Therefore, the accuracy requirements for high-precision maps are becoming increasingly stringent. To ensure the accuracy of high-precision maps during application, they need to be updated promptly based on actual road conditions.

[0179] HD map data collection can be divided into two modes: centralized collection and crowdsourcing. To ensure data accuracy and reduce collection costs, a combination of these two modes is often employed. For example, a centralized collection mode is used to first create the static portion of a HD map, and then crowdsourcing is used to update and improve the resulting HD map.

[0180] However, in the crowdsourcing collection mode, since it is necessary to collect target recognition information reported by many vehicles, and the recognition capabilities and recognition accuracy of different vehicles are different, the recognition results reported by different vehicles for the same target object often differ, resulting in conflicts.

[0181] For example, suppose that Figure 1 As shown, the target object is a 60 km / h speed limit sign on the side of the road. One vehicle (for example, vehicle A) identifies the target object as a 60 km / h speed limit sign, while another vehicle (for example, vehicle B) may mistakenly identify the target object as an 80 km / h speed limit sign due to problems with recognition accuracy. After the cloud server receives different recognition results for the same target object, it needs to determine which result to accept and update it to the map. An inappropriate selection may lead to erroneous map updates, posing a hidden danger to traffic safety.

[0182] In order to solve the recognition conflict problem in crowdsourcing mapping, the industry has proposed a confidence-based processing method.

[0183] For example, when a vehicle identifies a target object, in addition to obtaining the target object's identification result, it also calculates a confidence value for the identification result. The identification information of the target object reported by the vehicle to the cloud server includes not only the target object's identification result but also the confidence value of the identification result.

[0184] When the cloud server receives identification information reported by different vehicles for the same target object, the cloud server can refer to the confidence value in the identification information reported by the vehicle to further determine which identification information to select as the final result of the display of the target object on the map.

[0185] For example, one processing method is to select the recognition result corresponding to the recognition information with the highest confidence value from the multiple received recognition information.

[0186] Among them, such as Figure 2 As shown, assuming that for the same target object, the content of the identification information reported by vehicle A for the target object includes: the recognition result of the target object is a speed limit sign, and the speed limit indication is 60km / h, and the confidence value of the recognition result is 60%; the content of the identification information reported by vehicle B for the target object includes: the recognition result of the target object is a speed limit sign, and the speed limit indication is 80km / h, and the confidence value of the recognition result is 70%; the content of the identification information reported by vehicle C for the target object includes: the recognition result of the target object is a billboard, and the confidence value of the recognition result is 80%.

[0187] Therefore, the cloud server may adopt the recognition result with the highest confidence value, that is, select the recognition result reported by vehicle C for the target object, determine the target object as a billboard, and update the map.

[0188] However, this method for processing reported information has a significant drawback: Each vehicle may use a different method to calculate the confidence level for its target object recognition results. Consequently, the confidence levels derived from these different methods can have significantly different meanings. Consequently, the confidence levels reported by different vehicles cannot be directly compared.

[0189] For example, assuming that for the same target object, vehicle A calculates the recognition result of the target object using method A and determines that the confidence value of the recognition result is 60%; vehicle B calculates the recognition result of the target object using method B and determines that the confidence value of the recognition result is 70%.

[0190] Among them, simply comparing the numerical values ​​of the confidence values ​​reported by the two vehicles may result in that the recognition result of the target object reported by vehicle B is more reliable.

[0191] However, if vehicle B uses the same confidence value calculation method as vehicle A to calculate the recognition result, the calculated confidence value of the recognition result may be 50%. In this way, combined with the confidence value of the recognition result obtained by vehicle A, it can be seen that the recognition result reported by vehicle A is more reliable. If the recognition result obtained by vehicle B is determined as the final result of the target object, there will be a misjudgment. If the map is updated based on this misjudged recognition result, the updated content will be incorrect, which can easily lead to safety risks.

[0192] In other words, the existing method of processing reported information often fails to truly reflect the degree of credibility because the reporting vehicles use different confidence value calculation methods for the same target object, which may bring the risk of misjudgment.

[0193] In summary, there is currently no accurate and effective method for processing multiple reported results of the same target identification information in the crowdsourcing collection mode.

[0194] To solve this problem, the embodiments of the present application provide a method and device for processing reported information, so as to provide an efficient and accurate processing of reported information and reduce misjudgments caused by improper processing of reported information.

[0195] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: long term evolution (LTE) system, worldwide interoperability for microwave access (WiMAX) communication system, future fifth generation (5G) system, such as new radio access technology (NR), and future communication systems such as 6G system.

[0196] Taking the 5G system (also known as the New Radio system) as an example, specifically, in the embodiment of the present application, a method for calculating the confidence value of the reported recognition results for the same target different vehicles in the reported information is mainly obtained during the reporting information processing process, so as to compare the confidence values ​​obtained using the same confidence calculation method.

[0197] To facilitate understanding of the embodiments of the present application, the embodiments of the present application provide a processing system for reporting information, such as Figure 3 As shown, the reporting information processing system includes a collection device 300 and a cloud server 310.

[0198] The collection device 300 is used to collect information about a target object and determine identification information of the target object.

[0199] In which, the identification information includes the identification result of the target object and the confidence value of the identification result determined according to a preset confidence type; or, the identification information includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value.

[0200] In the embodiment of this application, Figure 3 As shown in (a), the collection device 300 can be a mobile collection device, such as a vehicle.

[0201] As an optional method, the vehicle in the embodiment of the present application has the functions of collecting images, processing information and communicating.

[0202] For example, Figure 4 The figure shows a possible application scenario of an embodiment of the present application. The above application scenarios can be unmanned driving, automatic driving, intelligent driving, networked driving, etc. The target detection and tracking system can be installed in motor vehicles (such as unmanned vehicles, intelligent vehicles, electric vehicles, digital vehicles, etc.), drones, rail vehicles, bicycles, traffic lights, speed measuring devices or network equipment (such as base stations and terminal devices in various systems), etc.

[0203] In addition, if Figure 3 As shown in (b), the collection device 300 in the embodiment of the present application can also be a fixed collection device.

[0204] Among them, an optional fixed collection device in the embodiment of the present application can be a device with a camera function, at least one sensor and a communication function.

[0205] For example, the fixed collection device described in the embodiment of the present application is an RSU installed on the road.

[0206] Exemplarily, the fixed acquisition device in the embodiment of the present application is a system composed of a camera, at least one sensor and a communication device, that is, the three devices exist independently, and the three devices as a whole are referred to as a fixed acquisition device; alternatively, the fixed acquisition device in the embodiment of the present application can be a device that integrates a camera, at least one sensor and a communication device.

[0207] In addition, if Figure 3 As shown in (c), the collection device 300 in the embodiment of the present application can also be a combination of a mobile collection device and a fixed collection device.

[0208] For the sake of simplicity in the embodiments of the present application, a vehicle is selected as the collection device for introduction. For the sake of simplicity, when the collection device only includes a fixed collection device, or the collection device includes a fixed collection device and a mobile collection device, the content of the processing method for executing the reported information can be specifically referred to the content of the information reported by the collection device for the vehicle.

[0209] The cloud server 310 , also known as a receiving end, has the capability to analyze and process information and communicate with other devices.

[0210] In an optional manner of the embodiment of the present application, the cloud server is a central processing unit; or, the cloud server is a processing chip in the server.

[0211] Among them, the cloud server 310 is responsible for receiving the identification information of the target object sent by the collection device 300, determining whether the corresponding map content needs to be updated based on the identification information of the target object, and notifying the corresponding collection device of the updated map content after completing the update of the map content.

[0212] Among them, the system architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application.

[0213] For example, in subsequent developments, the acquisition device may be a combination of a mobile acquisition device and a fixed acquisition device.

[0214] For another example, in the subsequent development process, there may be intervention of third-party application devices.

[0215] For example, Figure 5 As shown, assuming that the collection device is a vehicle and the third-party application device is a virtual reality VR display device for a map scene, the cloud server can determine that the map content needs to be updated and after completing the map update, it can also send the updated map information to the third-party application device, so that the user can obtain more accurate and real information when using the third-party device for a virtual experience.

[0216] Among them, the embodiment of the present application provides an internal structure of a vehicle, such as Figure 6 As shown, the specific content is not limited to the following.

[0217] The vehicle 600 includes a camera 610 , a sensor 620 , a memory 630 , a processor 640 , and a transceiver 650 .

[0218] The camera 610 is used to acquire an image of a target object.

[0219] The camera in the embodiment of the present application may be a camera of a driver monitoring system, a cockpit camera, an infrared camera, a driving recorder (i.e., a recording terminal), a reversing camera, etc., and the specific embodiment of the present application is not limited thereto. The shooting area of ​​the camera may be the external environment of the vehicle.

[0220] The sensor 620 is used to obtain the representation information of the target object, thereby assisting the processor in determining the recognition result of the target object.

[0221] The representation information of the target object is mainly used to represent the external features of the target object, as well as location information, etc. For example, the representation information of the target object includes the size, color, shape, placement, etc. of the target object.

[0222] For example, the sensors described in the embodiments of the present application may include one or more of a photoelectric / light-sensitive sensor, an ultrasonic / acoustic sensor, a ranging / distance sensor, a visual / image sensor, a gyroscope sensor, and the like.

[0223] It should be noted that in the embodiment of the present application, the camera and the sensor can be used in combination to collect information on the target object. The specific combination method and / or collection method are not limited in this application. Any collection method for the target object that can be applied in the embodiment of the present application is applicable to the embodiment of the present application.

[0224] The memory 630 is used to store one or more programs and data information; wherein the one or more programs include instructions.

[0225] Among them, the data information described in the embodiment of the present application may include algorithm information for determining the confidence value of the recognition result, etc.

[0226] The processor 640 is used to obtain the collection information of the target object and determine the identification information of the target object based on the collection information of the target object, wherein the identification information includes the recognition result of the target object and the confidence value of the recognition result determined by the processor 640 according to a preset confidence type; or, the identification information includes the recognition result of the target object, the confidence value of the recognition result determined by the processor 640, and the confidence type used to determine the confidence value.

[0227] Exemplarily, the processor 640 in the embodiment of the present application obtains the acquisition information of the target object from the camera 610 and / or the sensor 620 according to the transceiver 650; or, the processor 640 in the embodiment of the present application obtains the acquisition information of the target object according to the communication interface connected to the camera 610 and / or the sensor 620.

[0228] The transceiver 650 is used to transmit information with a cloud server and to transmit information with other communication devices such as vehicles.

[0229] In one optional embodiment of the present application, the transceiver is used to report the identification information of the target object determined by the vehicle to a cloud server.

[0230] The system architecture and business scenarios described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Furthermore, it is known to those skilled in the art that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems. It should be understood that Figures 3 to 6 This is a simplified schematic diagram for ease of understanding only. The system architecture may further include other devices or other unit modules.

[0231] Some of the terms used in the embodiments of the present application are explained below for easier understanding.

[0232] 1) Confidence value: This is an optional condition in the embodiment of the present application. The confidence value is used to measure the credibility of the recognition result.

[0233] There are currently many methods for calculating confidence values ​​in the industry, including at least the following:

[0234] The posterior probability directly obtained based on the Bayesian classification method, the estimation of the posterior probability based on neural networks or other methods, the randomness measurement value obtained based on algorithmic randomness theory, the membership value obtained based on fuzzy mathematics, the accuracy rate obtained through statistics of multiple test experiments, etc.

[0235] It should be noted that the confidence calculation methods described in the embodiments of the present application are not limited to the above-mentioned ones. Any calculation method that can be used to determine the confidence value can be applied to the embodiments of the present application and falls within the protection scope of the embodiments of the present application.

[0236] 2) Same type fusion, an optional method in the embodiment of the present application, the same type fusion refers to comparing and fusing the confidence values ​​of the target object recognition results obtained by the same confidence type.

[0237] For example, when performing similar fusion in the embodiment of the present application, the result of similar fusion can be obtained by directly referring to the confidence value.

[0238] For example, the recognition result of vehicle A for the target object has a confidence value of 60% calculated using confidence type 1; the recognition result of vehicle B for the target object has a confidence value of 70% calculated using confidence type 1; and the recognition result of vehicle C for the target object has a confidence value of 75% calculated using confidence type 1.

[0239] Since the recognition results of the target object by vehicles A, B, and C all use confidence type 1 to calculate the confidence value, vehicles A, B, and C can perform similar fusion when comparing their confidence values.

[0240] That is, after receiving the identification information of the target object reported by vehicles A, B, and C, the cloud server can directly compare the confidence values ​​of vehicles A, B, and C. From the received identification information of the target object, the recognition result corresponding to the identification information with the highest confidence value is selected as the final result of the target object determined by vehicles A, B, and C. That is, when the cloud server determines the final result of the target object based on the identification information of the target object reported by vehicles A, B, and C, it determines the recognition result in the identification information reported by vehicle C as the final result of the target object.

[0241] 3) Heterogeneous fusion, an optional method in the embodiment of the present application, the same type of fusion refers to comparing and fusing the confidence values ​​of the target object recognition results obtained by different confidence types.

[0242] In an application scenario in an embodiment of the present application, it is assumed that the recognition result of the target object by vehicle A is calculated by confidence type 1, and the confidence value is 60%; the recognition result of the target object by vehicle B is calculated by confidence type 2, and the confidence value is 70%; the recognition result of the target object by vehicle C is calculated by confidence type 3, and the confidence value is 75%.

[0243] In this scenario, the confidence values ​​reported by the three vehicles received by the cloud server are calculated using different confidence types. Therefore, the cloud server directly performs heterogeneous fusion on the confidence values ​​reported by the three vehicles.

[0244] In another application scenario in the embodiment of the present application, it is assumed that the recognition result of the target object by vehicle A is calculated by confidence type 1, and the confidence value is 60%; the recognition result of the target object by vehicle B is calculated by confidence type 1, and the confidence value is 70%; the recognition result of the target object by vehicle C is calculated by confidence type 2, and the confidence value is 75%; the recognition result of the target object by vehicle D is calculated by confidence type 2, and the confidence value is 65%.

[0245] In this scenario, among the confidence values ​​reported by the four vehicles received by the cloud server, the confidence values ​​reported by vehicles A and B are calculated based on the same confidence type, and the confidence values ​​reported by vehicles C and D are calculated based on the same confidence type.

[0246] Therefore, the cloud server needs to first perform similar fusion, that is, first determine the fusion results of vehicles A and B, and the fusion results of vehicles C and D based on the similar fusion method. This can be understood as grouping the identification information of target objects reported by different vehicles. Specifically, the identification information of target objects reported by vehicles A and B is grouped together according to the confidence type, and the identification information of target objects reported by vehicles C and D is grouped together.

[0247] Among them, according to the introduction of the above-mentioned similar fusion, the cloud server has the largest confidence value of vehicle B among vehicles A and B, so the identification information reported by vehicle B is selected as the result of the similar fusion of the group. It can be understood that the identification information reported by vehicle B is used as the group identification information of the group; the cloud server has the largest confidence value of vehicle C among vehicles C and D, so the identification information reported by vehicle C is selected as the result of the similar fusion of the group. It can be understood that the identification information reported by vehicle C is used as the group identification information of the group.

[0248] Then, the cloud server continues to perform heterogeneous fusion on vehicle B and vehicle C. It can be understood that the cloud server continues to perform heterogeneous fusion on the two similar fusion results (i.e., two sets of corresponding group identification information) obtained by similar fusion.

[0249] In addition, in actual situations, cloud servers can combine other information for fusion when performing heterogeneous fusion.

[0250] The other information in the embodiment of the present application may include historical statistical information and other vehicle-related parameters, etc., which are not specifically limited.

[0251] In an optional manner of an embodiment of the present application, the cloud server performs analysis based on the accuracy of historical vehicle reports. The cloud server may perform a weighted summation of the confidence value reported by the vehicle and the historical accuracy rate reported to obtain a judgment value, thereby determining the final recognition result reported by the vehicle to be adopted based on the judgment value corresponding to each vehicle when performing heterogeneous fusion.

[0252] For example, assuming that the confidence value of the recognition result reported by vehicle A for the target object is 80%, the cloud server queries the historical reporting accuracy of vehicle A and obtains that the historical reporting accuracy of vehicle A is 90%. Then, through the set weighted summation algorithm, the evaluation value of vehicle A can be obtained as 85%.

[0253] 4) Confidence type: The confidence type described in the embodiments of the present application can be understood as a calculation method for calculating a confidence value.

[0254] Among them, there are many ways to express the confidence type contained in the identification information of the target object in the embodiment of the present application, which are not limited to the following ones.

[0255] Representation method 1: The identification information of the target object includes an identifier corresponding to the confidence type, which indicates the confidence type used to calculate the confidence value.

[0256] There are multiple identifiers corresponding to the confidence level types, which are not limited to the following:

[0257] a. Use the name corresponding to the confidence type as the identifier of the confidence type.

[0258] For example, the vehicle directly uses the method name used to calculate the confidence value of the target recognition result as the confidence type.

[0259] For example, assuming that vehicle A uses the Bayesian classification method to calculate the confidence value of the target object recognition result, the recognition information reported by vehicle A contains the Bayesian classification method expressed in text, thereby indicating that the confidence type of the Bayesian classification method is used to determine the confidence value.

[0260] b. The keyword corresponding to the confidence type serves as the identifier of the confidence type.

[0261] Exemplarily, it is assumed that the corresponding relationship between the confidence type and the keyword is set as shown in Table 1.

[0262]

[0263] Table 1 Correspondence between confidence value calculation method and keywords

[0264] For example, assuming that the confidence value of the target object recognition result of vehicle A is directly calculated through the Bayesian learning method, the recognition information reported by vehicle A contains the posterior probability of the text expression, thereby indicating that the confidence value is determined by the confidence type of the Bayesian classification method.

[0265] c. The serial number corresponding to the confidence type serves as the identifier of the confidence type.

[0266] Exemplarily, it is assumed that the corresponding relationship between the confidence type and the sequence number is set as shown in Table 2.

[0267]

[0268] Table 2 Correspondence between confidence value calculation method and serial number

[0269] For example, assuming that the confidence value of the target object recognition result of vehicle A is directly calculated by the Bayesian learning method, the recognition information reported by vehicle A contains the serial number 1 expressed in text, or 1 in binary representation.

[0270] Among them, the confidence value in the embodiment of the present application can be obtained using a mainstream calculation method that is not included in the first five categories, and may be some customized methods. There is no specific limitation. Any method that can be used to calculate the confidence value of the recognition result in the embodiment of the present application falls within the scope of protection of this application.

[0271] In order to more clearly demonstrate the technical solution provided by this application, the reporting information processing method provided by this application is described below in multiple embodiments.

[0272] It should be noted that the following introduction is only an enumeration of the technical solutions provided in this application and does not constitute a limitation of the technical solutions provided in this application. Any combination and variation of the following embodiments to obtain a method for solving the technical problems of this application falls within the scope of protection of this application.

[0273] In the first embodiment, the identification information of the target object reported by the vehicle to the cloud server includes the identification result of the target object, the confidence value of the identification result, and the confidence type used to determine the confidence value.

[0274] The following is an exemplary introduction based on the method of embodiment 1, which is not limited to the following scenarios:

[0275] Scenario 1: The collection device actively identifies and reports the target object.

[0276] Assume that the current reporting information processing scenario is as follows Figure 7 As shown in FIG, the target object is a newly installed speed limit sign on the road. There are three vehicles collecting information about the target object, namely vehicle A, vehicle B, and vehicle C.

[0277] After actively completing the information collection of the target object, the vehicles A, B and C report the identification information of the target object to the cloud server, wherein the identification information includes the identification result, the confidence value and the confidence type.

[0278] For example, when vehicles A, B, and C respectively drive onto the road section, they recognize that a new object, i.e., the target object, has appeared on the left side of the road through their own sensing devices and / or camera acquisition devices. Vehicles A, B, and C discover that the target object does not exist at this location in the original map.

[0279] Therefore, the vehicles A, B, and C actively collect information about the target object, determine the identification information of the target object, and report the identification information of the target object to the cloud server.

[0280] Among them, after receiving the identification information of the target object reported by vehicles A, B and C, the cloud server analyzes the identification information reported by vehicles A, B and C to determine the final result of the target object.

[0281] Preferably, in an embodiment of the present application, the cloud server analyzes the identification information of the target object received within a threshold time period to determine the final result of the target object.

[0282] There are multiple ways to set the threshold duration in the embodiment of the present application, which are not limited to the following:

[0283] Method 1 for setting the threshold duration: In the embodiment of the present application, when the cloud server needs to obtain identification information of the target object, it selects a duration from at least one preset duration as the threshold duration.

[0284] Method 2 for setting the threshold duration: In the embodiment of the present application, the cloud server selects a duration from the duration of at least one vehicle notification received as the threshold duration.

[0285] For example, the cloud server determines the duration of the first vehicle report received as the threshold duration.

[0286] As an optional method, the vehicle can carry the reporting duration in the identification information of the target object reported to the cloud server.

[0287] Exemplarily, upon receiving the first identification information reported for the target object, the cloud server starts a timer and continues to receive identification information for the target object reported by other vehicles. When the timer reaches the threshold duration, the cloud server stops receiving identification information reported for the target object. The cloud server analyzes the identification information of the target object received within the threshold duration to determine the final result of the target object.

[0288] Among them, by setting the threshold time, it is possible to effectively avoid the cloud server being unable to determine the amount of identification information that needs to be analyzed for the target object, thereby timely and effectively determining the final result of the target object, resulting in the problem of untimely map updates.

[0289] like Figure 8 As shown, the embodiment of the present application provides a first method for processing reported information based on the above scenario 1, and the specific process includes:

[0290] S800 : Vehicle A recognizes target object 1 and obtains a recognition result of target object 1 .

[0291] S801 : Vehicle B identifies target object 1 and obtains a recognition result of target object 1 .

[0292] S802 : Vehicle C recognizes target object 1 and obtains a recognition result of target object 1 .

[0293] There is no order in the above S800 to S802.

[0294] S803: Vehicle A determines the confidence type of the application.

[0295] S804: Vehicle B determines the confidence type of the application.

[0296] S805 , vehicle C determines the confidence type of the application.

[0297] There is no order in the above S803 to S805.

[0298] In one optional manner, the vehicle may pre-set an application confidence type, that is, the vehicle may subsequently apply the confidence type to determine corresponding confidence values ​​for all target object recognition results.

[0299] Alternatively, after obtaining the recognition result of the target object, the vehicle may determine a confidence type for calculating the confidence value for the recognition result. That is, the vehicle may determine the confidence type to be used based on the recognition results of different target objects according to actual circumstances.

[0300] S806: Vehicle A calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0301] S807: Vehicle B calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0302] S808: The vehicle C calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0303] S809, the vehicle A reports the obtained identification information of the target object 1 to the cloud server, where the identification information includes the identification result, the confidence value and the confidence type.

[0304] For example, in an embodiment of the present application, when the vehicle reports the recognition result, confidence value and corresponding confidence type to the cloud server, the recognition result, confidence value and confidence type of the target object can be encapsulated in the reported message content and sent to the cloud server together.

[0305] Assume that the identification information reported by vehicle A for target object 1 is as follows:

[0306] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 1; Confidence value: 70%.

[0307] S810, the vehicle B reports the obtained identification information of the target object 1 to the cloud server.

[0308] Assume that the identification information reported by vehicle B for target object 1 is as follows:

[0309] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 1; Confidence value: 60%.

[0310] S811, the vehicle C reports the obtained identification information of the target object 1 to the cloud server.

[0311] Assume that vehicle C reports the following information for target object 1:

[0312] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 2; Confidence value: 80%.

[0313] S812: The cloud server receives identification information of the target object reported by at least one vehicle.

[0314] For example, the cloud server receives identification information of the same target object reported by three vehicles.

[0315] Preferably, in order to avoid the cloud server from waiting indefinitely for the identification information reported by the vehicle for the target object, which affects the timeliness of the map update, the cloud server only analyzes and processes the messages reported by the vehicle received within a threshold time.

[0316] For example, after receiving the message reported by the first vehicle to target object 1, the cloud server starts the timer. If it receives the messages reported by the second and third vehicles to target object 1 within the preset time, the cloud server only analyzes the messages reported by the first three vehicles.

[0317] S813: The cloud server classifies the received identification information of at least one target object according to the confidence type.

[0318] Specifically, the cloud server classifies N recognition messages of the same target object received according to the confidence type into M categories, where M is less than or equal to N.

[0319] That is to say, if the confidence types included in the N recognition messages of the same target object received by the cloud server are all different, each recognition message needs to be classified into one category, and a total of N categories need to be divided.

[0320] If there are at least two recognition messages among the N recognition messages of the same target object received by the cloud server that use the same confidence type, the recognition messages containing the same confidence type need to be classified into one category. Therefore, the number of categories is less than N.

[0321] S814. The cloud server performs homogeneous fusion and / or heterogeneous fusion on the received recognition messages to obtain the final result of the target object.

[0322] Among them, if the N recognition messages received by the cloud server are classified into M categories, and at this time M is 1, that is, the N recognition messages received all contain the same confidence type. Then the cloud server performs homogeneous fusion on the received recognition messages to obtain the final result of the target object.

[0323] If the N recognition messages received by the cloud server are classified into M categories, and at this time, M = N, that is, the N recognition messages received all contain different confidence types, then the cloud server performs heterogeneous fusion on the received recognition messages to obtain the final result of the target object.

[0324] If the N recognition messages received by the cloud server are classified into M categories, and at this time M < N, that is, there are recognition messages with the same confidence type among the N recognition messages received, then the cloud server needs to first perform homogeneous fusion on the classified recognition messages in the same group to obtain the homogeneous fusion result of this group of recognition messages (that is, the group recognition message), and then perform heterogeneous fusion on the group recognition messages obtained for each group to obtain the final final result of the target object.

[0325] S815. The cloud server compares the final result of the target object with the original result of the target object in the original map.

[0326] S816. After the cloud server determines that the final result of the target object is different from the original result, it updates the map according to the final result of the target object.

[0327] Among them, the situation where the target object does not exist in the original map is also included in S816, and this situation can be understood as the final result of the target object being different from the original result.

[0328] S817: The cloud server sends the updated map to the corresponding vehicle.

[0329] It should be noted that the examples in this application Figure 8 The steps shown can be adjusted and deleted in order according to actual conditions, and the specific embodiments of this application are not limited. For example, S815 to S816 can be integrated into one step, that is, no comparison is required, and the corresponding map area is directly updated according to the final result of the target object.

[0330] Scenario 2: The cloud server instructs the collection device to identify and report the target object.

[0331] Assume that the current reporting information processing scenario is as follows Figure 9 As shown, the target object is a new speed limit sign on the road.

[0332] The cloud server regularly checks and updates the stored maps. During the checking and updating process, the cloud server finds that there is missing data of the target object in area A of the map. In order to ensure the integrity and accuracy of the map, the cloud server needs to re-identify the target object.

[0333] Therefore, the cloud server can send a first instruction message to vehicles within the target object threshold range, instructing the receiving vehicle to identify the target object and report the identification information of the target object. The identification information of the target object includes the identification result of the target object, the confidence value, and the confidence type.

[0334] There are many ways to set the threshold range in the embodiment of the present application, which are not limited to the following:

[0335] Method 1 for setting the threshold range: In the embodiment of the present application, the cloud server determines its own jurisdiction as the threshold range.

[0336] Method 2 for setting the threshold duration: In the embodiment of the present application, the cloud server determines the location of the target object, determines the location of the target object as the center of the circle, obtains a center area according to a preset radius, and determines the center area as the threshold range.

[0337] Method 3 for setting the threshold duration: In the embodiment of the present application, the threshold range of the cloud server is a pre-configured fixed value.

[0338] For example, assume that vehicles A, B, and C receive the first instruction information sent by the cloud server. Consequently, vehicles A, B, and C collect information about the target object according to the first instruction information and obtain identification information about the target object. This identification information includes the target object's identification result, confidence value, and confidence type. Vehicles A, B, and C then report the target object's identification information to the cloud server.

[0339] Among them, after receiving the identification information of the target object reported by vehicles A, B and C, the cloud server analyzes the identification information reported by vehicles A, B and C to determine the final result of the target object.

[0340] Preferably, in an embodiment of the present application, the cloud server analyzes the identification information of the target object received within a threshold time period to determine the identification result of the target object.

[0341] Exemplarily, upon receiving the first identification information reported for the target object, the cloud server starts a timer and continues to receive identification information for the target object reported by other vehicles. When the timer reaches the threshold duration, the cloud server stops receiving identification information reported for the target object. The cloud server analyzes the identification information of the target object received within the threshold duration to determine the final result of the target object.

[0342] By setting the threshold time, it is possible to effectively avoid the cloud server being unable to determine the identification information that needs to be analyzed for the target object, thereby timely and effectively determining the identification result of the target object, resulting in the problem of untimely map updates.

[0343] like Figure 10 As shown, the embodiment of the present application provides a method for processing reported information based on the above scenario 2, and the specific process includes:

[0344] S1000, the cloud server determines the target object to be collected;

[0345] S1001, the cloud server sends a first indication message to a vehicle within a threshold range of the target object, wherein the first indication message instructs the vehicle to collect the target object and report identification information of the target object.

[0346] S1002: Vehicle A receives the first instruction information, identifies the target object 1, and obtains the recognition result of the target.

[0347] S1003: Vehicle B receives the first instruction information, identifies the target object 1, and obtains a recognition result of the target.

[0348] S1004: Vehicle C receives the first instruction information, identifies the target object 1, and obtains a recognition result of the target.

[0349] There is no order in the above S1002 to S1004.

[0350] S1005 , vehicle A determines the confidence type of the application.

[0351] S1006 , vehicle B determines the confidence type of the application.

[0352] S1007 , vehicle C determines the confidence type of the application.

[0353] Among them, there is no order of precedence in the above S1005 to S1007.

[0354] In one optional manner, the vehicle may pre-set an application confidence type, that is, the vehicle may subsequently apply this confidence type to determine confidence values ​​for all target object recognition results.

[0355] Alternatively, after obtaining the target recognition result, the vehicle may determine a confidence type for calculating the confidence value for the recognition result. That is, the vehicle may determine the confidence type to be used based on the recognition results of different targets according to actual circumstances.

[0356] S1008: Vehicle A calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0357] S1009: Vehicle B calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0358] S1010: The vehicle C calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0359] S1011, the vehicle A reports the obtained identification information of the target object 1 to the cloud server.

[0360] Assume that vehicle A reports the following information for target object 1:

[0361] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 1; Confidence value: 70%.

[0362] S1012, the vehicle B reports the obtained identification information of the target object 1 to the cloud server.

[0363] Assume that vehicle B reports the following information for target object 1:

[0364] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 1; Confidence value: 60%.

[0365] S1013, the vehicle C reports the obtained recognition result, confidence value and confidence type of the target object 1 to the cloud server.

[0366] Assume that vehicle C reports the following information for target object 1:

[0367] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 2; Confidence value: 80%.

[0368] Among them, in an embodiment of the present application, when the vehicle reports the recognition result, confidence value and corresponding confidence type to the cloud server, the recognition result, confidence value and confidence type of the target object can be encapsulated in the reported message content and sent to the cloud server together.

[0369] S1014: The cloud server receives a message reported by at least one vehicle.

[0370] For example, the cloud server receives identification information of the same target reported by three vehicles.

[0371] Preferably, in order to avoid the cloud server from waiting indefinitely for the vehicle's report on the target object, which affects the timeliness of the map update, the cloud server only analyzes and processes the identification information reported by the vehicle received within a threshold time.

[0372] For example, after receiving the message reported by the first vehicle to target object 1, the cloud server starts the timer. If it receives the messages reported by the second and third vehicles to target object 1 within the preset time, the cloud server only analyzes the messages reported by the first three vehicles.

[0373] S1015: The cloud server classifies the received at least one piece of identification information according to the confidence type.

[0374] Specifically, the cloud server classifies N received messages of the same target object into M categories according to the confidence type, where M is less than or equal to N.

[0375] For details, please refer to the above S810, which will not be elaborated here for the sake of brevity.

[0376] S1016: The cloud server performs similar fusion and / or heterogeneous fusion on the received messages to obtain the identification result of the target object.

[0377] For the specific content, please refer to the above S811. For the sake of brevity, it will not be repeated here.

[0378] S1017: The cloud server compares the final result of the target object with the original result of the target object in the original map.

[0379] S1018: After determining that the final result of the target object is different from the original result, the cloud server updates the map according to the final result of the target object.

[0380] The S1018 also includes a case where the target object does not exist in the original map. This case can be understood as the final result of the target object being different from the original result.

[0381] S1019, the cloud server sends the updated map to the corresponding vehicles.

[0382] It should be noted that the examples in this application Figure 10 The steps shown can be adjusted in order and deleted according to actual conditions, and are not limited to the specific embodiments of the present application.

[0383] Scenario 3: After receiving identification information reported by a vehicle regarding the target object, the cloud server instructs other vehicles to identify and report the target object.

[0384] Assume that the current reporting information processing scenario is as follows Figure 11 As shown, the target object is a new speed limit sign on the road.

[0385] When vehicle A reaches this road section, it uses its own sensors and / or camera to identify a new object, the target object, on the left side of the road. However, vehicle A discovers that the target object does not exist at this location in the original map. Therefore, vehicle A proactively collects information about the target object, determines its identification information, and reports it to the cloud server.

[0386] After receiving the identification information of the target object reported by vehicle A, the cloud server sends a first instruction message to other vehicles within the area where the target object is located to avoid misjudgment caused by receiving the identification information of the target object reported by only one vehicle. The first instruction message instructs the receiving vehicle to identify the target object and report the identification information of the target object. The identification information of the target object includes the identification result, confidence value, and confidence type of the target object.

[0387] Assume that vehicles B and C receive the first instruction information sent by the cloud server. Therefore, vehicles B and C collect information about the target object according to the first instruction information and obtain identification information about the target object. The identification information includes the identification result, confidence value, and confidence type of the target object. Vehicles B and C then report the identification information of the target object to the cloud server.

[0388] Among them, after receiving the identification information of the target object reported by vehicles B and C, the cloud server analyzes it in combination with the identification information reported by vehicle A previously received to determine the identification result of the target object; or, after receiving the identification information of the target object reported by vehicles B and C, the cloud server analyzes the identification information of the target object reported by vehicles B and C to determine the identification result of the target object.

[0389] Preferably, in an optional manner of an embodiment of the present application, the cloud server analyzes the identification information of the target object received within a threshold time period after sending the first indication information and the identification information of the target object received before sending the first indication information to determine the identification result of the target object.

[0390] Preferably, in another optional manner of the embodiment of the present application, the cloud server analyzes the identification information of the target object received within a threshold time period after sending the first indication information, and determines the identification result of the target object.

[0391] Exemplarily, after receiving identification information reported for a target object, the cloud server sends a first indication message to other vehicles within the area where the target object is located to avoid misjudgment due to receiving identification information of the target object reported by only one vehicle. After sending the first indication message, the cloud server starts a timer. The timer runs for a threshold duration. During the timer, the cloud server receives identification information reported for the target object by other vehicles. When the timer reaches the threshold duration, the cloud server stops receiving identification information reported for the target object.

[0392] The cloud server analyzes the identification information of the target object received within a threshold time period to determine the identification result of the target object; or, the cloud server analyzes the identification information of the target object received within a threshold time period and the identification information reported for the target object received before sending the first indication information to determine the identification result of the target object.

[0393] By setting the threshold time, it is possible to effectively avoid the cloud server being unable to determine the identification information that needs to be analyzed for the target object, thereby timely and effectively determining the identification result of the target object, resulting in the problem of untimely map updates.

[0394] like Figure 12 As shown, the embodiment of the present application provides a method for processing reported information based on the above scenario three, and the specific process includes:

[0395] S1200: Vehicle A identifies target object 1 and obtains a recognition result of the target.

[0396] S1201: Vehicle A determines the confidence type of the application.

[0397] In one optional manner, the vehicle may pre-set an application confidence type, that is, the vehicle's subsequent recognition results for all targets may be determined using this confidence type.

[0398] Alternatively, after obtaining the target recognition result, the vehicle may determine a confidence type for calculating the confidence value for the recognition result. That is, the vehicle may determine the confidence type to be used based on the recognition results of different targets according to actual circumstances.

[0399] S1202: Vehicle A calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0400] S1203, the vehicle A reports the obtained identification information of the target object 1 to the cloud server.

[0401] Assume that the identification information reported by vehicle A for target object 1 is as follows:

[0402] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 1; Confidence value: 70%.

[0403] S1204, the cloud server receives the identification information reported by vehicle A.

[0404] S1205, the cloud server sends a first indication message to vehicles within the target object threshold range reported by vehicle A, wherein the first indication message instructs the vehicle to collect the target object and report identification information of the target object.

[0405] S1206: Vehicle B receives the first instruction information, identifies the target object 1, and obtains a recognition result of the target.

[0406] S1207: Vehicle C receives the first instruction information, identifies the target object 1, and obtains a recognition result of the target.

[0407] Among them, there is no order of precedence in the above S1206 to S1207.

[0408] S1208 , vehicle B determines the confidence type of the application.

[0409] S1209 , vehicle C determines the confidence type of the application.

[0410] Among them, there is no order of precedence in the above S1208 to S1209.

[0411] In one optional manner, the vehicle may pre-set an application confidence type, that is, the vehicle may apply this confidence type to determine confidence values ​​for subsequent recognition results of all targets.

[0412] Alternatively, after obtaining the target recognition result, the vehicle may determine a confidence type for calculating the confidence value for the recognition result. That is, the vehicle may determine the confidence type to be used based on the recognition results of different targets according to actual circumstances.

[0413] S1210: Vehicle B calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0414] S1211: The vehicle C calculates the recognition result according to the confidence type determined for application to obtain a confidence value.

[0415] S1212, the vehicle B reports the obtained identification information of the target object 1 to the cloud server.

[0416] Assume that the identification information reported by vehicle B for target object 1 is as follows:

[0417] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 1; Confidence value: 60%.

[0418] S1213, the vehicle C reports the obtained identification information of the target object 1 to the cloud server.

[0419] Assume that vehicle C reports the following information for target object 1:

[0420] Recognition result: Vehicle forward direction indication; Confidence type: Confidence type 2; Confidence value: 80%.

[0421] Among them, in an embodiment of the present application, when the vehicle reports the recognition result, confidence value and corresponding confidence type to the cloud server, the recognition result, confidence value and confidence type of the target object can be encapsulated in the reported message content and sent to the cloud server together.

[0422] S1214: The cloud server receives a message reported by at least one vehicle.

[0423] For example, the cloud server receives identification information for the same target reported by vehicle B and vehicle C.

[0424] Preferably, in order to avoid the cloud server from waiting indefinitely for the identification information reported by the vehicle for the target object, which affects the timeliness of the map update, the cloud server only analyzes and processes the identification information reported by the vehicle received within a threshold time period.

[0425] For example, after sending the first indication message, the cloud server starts the timer. If it receives vehicle C and the identification information reported by vehicle C to the target object 1 within the preset time period, the cloud server only analyzes the identification information reported by vehicle B, vehicle C and vehicle A received before sending the first indication message.

[0426] S1215: The cloud server classifies the received at least one piece of identification information according to the confidence type.

[0427] For details, please refer to the above S810, which will not be elaborated here for the sake of brevity.

[0428] S1216, the cloud server performs similar fusion and / or heterogeneous fusion on the received identification information to obtain the final result of the target object.

[0429] For the specific content, please refer to the above S811. For the sake of brevity, it will not be repeated here.

[0430] S1217: The cloud server compares the final result of the target object with the original result of the target object in the original map.

[0431] S1218: After determining that the final result of the target object is different from the original result, the cloud server updates the map according to the final result of the target object.

[0432] The S1218 also includes a case where the target object does not exist in the original map. This case can be understood as the final result of the target object being different from the original result.

[0433] S1219, the cloud server sends the updated map to the corresponding vehicles.

[0434] Embodiment 2: The confidence types used by vehicles to calculate confidence values ​​are pre-standardized so that the confidence values ​​received by the cloud server can be directly compared.

[0435] Among them, in the embodiment of the present application, there are many ways to pre-unify the confidence types used by vehicles to calculate confidence values, which are not limited to the following ones.

[0436] Unified method 1: The cloud server determines the confidence type used to calculate the confidence value, and notifies the collection device of the determined confidence type.

[0437] Among them, the cloud server in the embodiment of the present application can send a second indication message to the collection device to instruct the collection device that has received the second indication message to use the confidence type indicated by the second indication message to calculate the confidence value of the recognition result when determining the confidence value of the target object recognition result.

[0438] It should be noted that, in the embodiment of the present application, the timing at which the cloud server sends the second indication information to the collection device is not limited.

[0439] For example, in the first optional method, the cloud server sends the second indication information to all vehicles involved in the scope of its jurisdiction during the initialization phase, so that the vehicles within the scope of the cloud server determine the confidence value of the target object recognition result according to the confidence type indicated by the cloud server.

[0440] Therefore, after receiving the recognition result and corresponding confidence value of the target object reported by the vehicle, the cloud server can directly compare at least one confidence value received for the same target object to determine the final result of the target object.

[0441] Furthermore, if a vehicle later drives into the jurisdiction of the cloud server and has not received the second indication information sent by the cloud server in advance; or, when the cloud server sends the second indication information to vehicles within the jurisdiction, some vehicles fail to successfully receive the second indication information, then the vehicles that have not received the second indication information can refer to the three scenarios in the above-mentioned embodiment one to report the identification information of the target object.

[0442] For example, in a second optional approach, the cloud server periodically sends the second indication information to all vehicles within its jurisdiction, enabling vehicles within the cloud server's jurisdiction to determine the confidence value of the target object recognition result based on the confidence type indicated by the cloud server. Thus, upon receiving the target object recognition result and corresponding confidence value reported by a vehicle, the cloud server can directly compare at least one received confidence value for the same target object to determine the final result for the target object.

[0443] For example, in a third optional manner, when the cloud server determines that it is necessary to obtain the identification information of the target object, the cloud server sends the second indication information to the vehicle used to obtain the identification information of the target object.

[0444] For example, in combination with scenario 2 in embodiment 1 above, assuming that the cloud server finds that there is missing data of the target object in area A of the map, the cloud server can send a second indication message to vehicles within the target object threshold range, instructing the receiving vehicle to use confidence type 1 to calculate the confidence value of the target object recognition result.

[0445] In addition, the cloud server sends a first indication message to vehicles within the target object threshold range, instructing the receiving vehicle to identify the target object and report the identification result and confidence value of the target object. In this embodiment of the application, the order in which the first indication message and the second indication message are sent is not limited.

[0446] Preferably, in conjunction with Scenario 2 in the above-mentioned Example 1, assuming that the cloud server discovers that there is missing data for a target object in Area A of the map, the cloud server can send a first indication message to vehicles within the target object threshold range, instructing the receiving vehicles to identify the target object, calculate the confidence value of the target object identification result using Confidence Type 1, and report the identification result and confidence value of the target object. In other words, in this embodiment of the application, the first indication message also serves as the second indication message, that is, the first indication message and the second indication message are the same indication message, thereby saving signaling overhead.

[0447] like Figure 13 As shown, the embodiment of the present application provides a first method for processing reported information based on the content of the above-mentioned embodiment 2, and the specific process includes:

[0448] S1300, the cloud server sends first indication information to at least one collection device, where the first indication information is used to instruct the collection device to use a first confidence type to calculate the confidence value of the target recognition result.

[0449] It should be noted that step 1300 is sent by the cloud server to the vehicle periodically; or, step 1300 is sent by the cloud server when it needs to obtain the identification information of the target object; or, step 1300 is sent by the cloud server to the vehicle during initialization.

[0450] In step 1300 described in the embodiment of the present application, the vehicle to which the cloud server sends the first indication information may be a vehicle within the jurisdiction of the cloud server, or a vehicle within the area indicated by the cloud server.

[0451] It is assumed that vehicle A, vehicle B, and vehicle C receive the first indication information sent by the cloud server.

[0452] It should be noted that the information in S1300 used to instruct the collection device to use the first confidence type to calculate the confidence value may also be the second instruction information.

[0453] S1301: Vehicle A identifies target object 1 and obtains a recognition result of the target.

[0454] S1302: Vehicle B identifies target object 1 and obtains a recognition result of the target.

[0455] S1303: Vehicle C identifies target object 1 and obtains a recognition result of the target.

[0456] There is no order in the above S1301 to S1303.

[0457] S1304: Vehicle A calculates the recognition result using the first confidence type indicated by the application cloud server to obtain a confidence value.

[0458] S1305: Vehicle B calculates the recognition result using the first confidence type indicated by the application cloud server to obtain a confidence value.

[0459] S1306: The vehicle C calculates the recognition result using the first confidence type indicated by the application cloud server to obtain a confidence value.

[0460] There is no order in the above S1304 to S1306.

[0461] S1307, the vehicle A reports the obtained identification information of the target object 1 to the cloud server.

[0462] The recognition information includes the recognition result of the target object 1 and the confidence value of the recognition result.

[0463] S1308, the vehicle B reports the obtained recognition result and confidence value of the target object 1 to the cloud server.

[0464] S1309, the vehicle C reports the obtained recognition result and confidence value of the target object 1 to the cloud server.

[0465] S1310, the cloud server receives identification information reported by at least one vehicle.

[0466] For example, the cloud server receives recognition results for the same target reported by three vehicles, as well as corresponding confidence values ​​calculated using the same confidence type.

[0467] Preferably, in order to avoid the cloud server from waiting indefinitely for the vehicle's reported message for the target object, which affects the timeliness of the map update, the cloud server only analyzes and processes the vehicle's reported message received within a threshold time.

[0468] For example, after receiving the message reported by the first vehicle for target object 1, the cloud server starts the timer. If it receives the messages reported by the second and third vehicles for target object 1 within the threshold time, the cloud server only analyzes the messages reported by the first three vehicles.

[0469] S1311, the cloud server analyzes the multiple identification information reported for the same target object and obtains the final result of the target object.

[0470] S1312: The cloud server compares the final result of the target object with the original result of the target object in the original map.

[0471] S1313: After determining that the final result of the target object is different from the original result, the cloud server updates the map according to the final result of the target object.

[0472] The S1313 also includes a case where the target object does not exist in the original map. This case can be understood as the final result of the target object being different from the original result.

[0473] S1314, the cloud server sends the updated map to the corresponding vehicles.

[0474] Furthermore, the following situations may occur in actual applications:

[0475] Case 1: The cloud server determines that the confidence type used to calculate the confidence value is one, and notifies the collection device of the determined confidence type.

[0476] However, some vehicles that receive the notification may not have the capability to calculate the confidence value according to the confidence type indicated by the cloud server.

[0477] At this time, these vehicles may use other confidence types to calculate the confidence value of the target object, and when reporting the identification information of the target object, carry the adopted confidence type in the identification information.

[0478] Case 2: The cloud server determines that the confidence type used to calculate the confidence value is one, and notifies the reporting end of the determined confidence type.

[0479] However, some vehicles that receive the notification may not have the capability to calculate the confidence value according to the confidence type indicated by the cloud server.

[0480] At this time, the part of vehicles may send a request message to the cloud server, where the request message is used to request the cloud server to re-change the confidence type used to determine the confidence value.

[0481] Among them, after receiving the instruction request information reported by the vehicle, the cloud server can re-instruct the confidence type of the part of vehicles for determining the confidence value according to the request information of the vehicle.

[0482] In addition, the cloud server records the confidence type indicated to the part of vehicles, so that after receiving the confidence value of the target object recognition result reported by the part of vehicles, the cloud server knows the classification of the confidence value.

[0483] Alternatively, after receiving the instruction request information reported by the vehicle, the cloud server may re-instruct all vehicles of a new confidence type for determining the confidence value according to the request information of the vehicle.

[0484] Case 3: The cloud server determines that there are multiple confidence types for calculating the confidence value, and notifies the collection device of the determined confidence types.

[0485] However, since there are multiple indicated confidence types, the vehicle receiving the notification may randomly select a confidence value for calculating the recognition result from the indicated confidence types.

[0486] In this case, the confidence values ​​sent by the collection device to the cloud server may not be the same because the confidence types used may not be the same, and may still not be directly comparable.

[0487] At this time, the reporting vehicle may combine the contents of scenarios one to three of the above embodiment one and add a confidence type for calculating a confidence value into the identification information of the reported target object.

[0488] The confidence type included in the identification information is one of a plurality of confidence types indicated by the cloud server for calculating the confidence value.

[0489] It should be noted that if there are vehicles that do not have the ability to calculate the confidence value using the confidence type indicated by the cloud server, these vehicles can use other confidence types to calculate the confidence value of the target object, and when reporting the identification information of the target object, carry the adopted confidence type in the identification information.

[0490] Unified method 2: The cloud server and the vehicle are pre-configured to determine the confidence type used to calculate the confidence value.

[0491] Among them, in the embodiment of the present application, the confidence type used by the cloud server and the vehicle to calculate the confidence value can be manually configured in advance.

[0492] For example, the user determines that the confidence type used to calculate the confidence value is confidence type 1. Therefore, when determining the confidence value of the target object recognition result, the vehicle directly uses the pre-configured confidence type. After receiving the target object recognition result and confidence value reported by the vehicle, the cloud server can directly compare the at least one received confidence value.

[0493] Among them, the term "at least one" in the embodiments of the present application refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. The following at least one item (items) or similar expressions refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one item (items) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0494] Unless otherwise specified, ordinal numbers such as "first" and "second" in the embodiments of the present application are used to distinguish multiple objects and are not used to limit the order, timing, priority, or importance of multiple objects. In addition, the terms "including" and "having" in the embodiments of the present application, the claims, and the drawings are not exclusive. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules and may also include steps or modules that are not listed.

[0495] Through the above introduction to the scheme of the present application, it can be understood that, in order to realize the above functions, the above-mentioned implementation devices include hardware structures and / or software units corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0496] like Figure 14 As shown, an embodiment of the present invention provides a device for processing reported information, the device for processing reported information includes a processor 1400, a memory 1401, and a transceiver 1402;

[0497] The processor 1400 is responsible for managing the bus architecture and general processing, and the memory 1401 can store data used by the processor 1400 when performing operations. The transceiver 1402 is used to receive and send data under the control of the processor 1400 to communicate data with the memory 1401.

[0498] The bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits such as one or more processors represented by processor 1400 and memory represented by memory 1401. The bus architecture can also link various other circuits such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and are not further described herein. The bus interface provides an interface. Processor 1400 is responsible for managing the bus architecture and general processing, while memory 1401 can store data used by processor 1400 when performing operations.

[0499] The processes disclosed in the embodiments of the present invention can be applied to or implemented by processor 1400. During implementation, each step of the safe driving monitoring process can be completed by hardware integrated logic circuits or software instructions within processor 1400. Processor 1400 can be a general-purpose processor, digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present invention can be directly implemented and executed by a hardware processor, or by a combination of hardware and software modules within the processor. The software modules can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory 1401. Processor 1400 reads information from memory 1401 and, in conjunction with its hardware, completes the steps of the signal processing process.

[0500] In an optional manner of the present application, the device for reporting information processing is a cloud server, and the processor 1400 is used to read the program in the memory 1401 and execute the following Figure 8 The method flow of the cloud server in S800-S814 shown in FIG. 1 ; or executing the method flow of the cloud server ... Figure 10The method flow of the cloud server in S1000-S1019 shown in FIG. 10 is as follows: Figure 12 The method flow of the cloud server in S1200-S1219 shown in FIG. 1 is as follows: Figure 13 The method flow of the cloud server in S1300-S1314 is shown.

[0501] In another optional embodiment of the present invention, the device for reporting information processing is a collection device, such as a vehicle, and the processor 1400 is used to read the program in the memory 1401 and execute the following program: Figure 8 The method flow of the acquisition device in S800-S814 shown in FIG. 1 ; or executing the method flow of the acquisition device ... Figure 10 The method flow of the acquisition device in S1000-S1019 shown in FIG. 10 is as follows: Figure 12 The method flow of the acquisition device in S1200-S1219 shown in FIG. 1 is as follows: Figure 13 The method flow of the collection device in S1300-S1314 is shown.

[0502] like Figure 15 As shown, the present invention provides a device for processing reported information, which includes a transceiver module 1500 and a processing module 1501.

[0503] In an optional embodiment of the present application, when the device for processing the reported information is a cloud server, the device includes a transceiver module 1500 and a processing module 1501, and executes the following:

[0504] The transceiver module 1500 is configured to receive N identification information of a target object from N acquisition devices, where N is a positive integer, and the identification information includes a recognition result of the target object, a confidence value of the recognition result, and a confidence type used to determine the confidence value;

[0505] Processing module 1501 is used to divide the received N identification information into M groups according to the confidence type in the identification information, where M is a positive integer not greater than N; determine the group identification information corresponding to each group in the M groups; select a group of identification information from the M groups of identification information, and determine the identification result in the selected identification information as the final result of the target object.

[0506] In one implementation, the N pieces of identification information are received by the cloud server within a threshold time period.

[0507] In one implementation, the transceiver module 1500 is further configured to:

[0508] First indication information is sent to a collection device within a second threshold range, where the first indication information is used to instruct the collection device to identify a target object and report identification information of the target object.

[0509] In one implementation, the transceiver module 1500 is further configured to:

[0510] Receive identification information of target objects from fewer than a threshold number of acquisition devices.

[0511] In one implementation, the first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0512] In one implementation, the transceiver module 1500 is further configured to:

[0513] Second indication information is sent to the acquisition device within the threshold range, where the second indication information is used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0514] In one implementation, each set of identification information in the M groups includes the same confidence type.

[0515] In one implementation, the processing module 1501 is specifically configured to:

[0516] The identification information containing the largest confidence value in each group is determined as the group identification information.

[0517] In one implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0518] In one implementation, the processing module 1501 is further configured to:

[0519] According to the final result of the target object, the map area where the target object is located is updated, and the updated map area is notified to at least one collection device.

[0520] In an optional embodiment of the present application, when the device for processing the reported information is a cloud server, the device includes a transceiver module 1500 and a processing module 1501, and executes the following:

[0521] The transceiver module 1500 is configured to receive N pieces of identification information of a target object from N collection devices, where N is a positive integer, and the identification information includes an identification result of the target object and a confidence value of the identification result, wherein the confidence values ​​in the N pieces of identification information are determined by the same confidence type;

[0522] The processing module 1501 is configured to select the identification information having the largest confidence value from the N identification information; and determine the identification result in the selected identification information as the final result of the target object.

[0523] In one implementation, the N pieces of identification information are received by the cloud server within a threshold time period.

[0524] In one implementation, the transceiver module 1500 is further configured to:

[0525] First indication information is sent to a collection device within a second threshold range, where the first indication information is used to instruct the collection device to identify a target object and report identification information of the target object.

[0526] In one implementation, the transceiver module 1500 is further configured to:

[0527] Receive identification information of target objects from fewer than a threshold number of acquisition devices.

[0528] In one implementation, the first indication information is further used to indicate that the preset confidence type is the first confidence type.

[0529] In one implementation, the transceiver module 1500 is further configured to:

[0530] The cloud server sends second indication information to the collection device within the threshold range, where the second indication information is used to indicate that the preset confidence type is the first confidence type.

[0531] In one implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0532] In one implementation, the processing module 1501 is further configured to:

[0533] According to the final result of the target object, the map area where the target object is located is updated, and the updated map area is notified to at least one collection device.

[0534] In an optional manner of the embodiment of the present application, when the device for processing the reported information is a collection device, the device includes a transceiver module 1500 and a processing module 1501, and executes the following:

[0535] Processing module 1501 is used to determine identification information of a target object, where the identification information includes a recognition result of the target object, a confidence value of the recognition result, and a confidence type used to determine the confidence value;

[0536] The transceiver module 1500 is used to send the identification information of the target object to the cloud server, so that the cloud server can update the map area where the target object is located.

[0537] In one implementation, the transceiver module 1500 is further configured to:

[0538] Receive first indication information from the cloud server, where the first indication information is used to instruct the acquisition device to identify the target object and report the identification information of the target object.

[0539] In one implementation, the transceiver module 1500 is further configured to:

[0540] Receive identification information of target objects from fewer than a threshold number of acquisition devices.

[0541] In one implementation, the first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0542] In one implementation, the transceiver module 1500 is further configured to:

[0543] Second indication information is received from the cloud server, where the second indication information is used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

[0544] In one implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0545] In an optional manner of the embodiment of the present application, when the device for processing the reported information is a collection device, the device includes a transceiver module 1500 and a processing module 1501, and executes the following:

[0546] Processing module 1501 is used to determine identification information of a target object, where the identification information includes a recognition result of the target object and a confidence value of the recognition result, wherein the confidence value of the recognition result is determined by a preset confidence type;

[0547] The transceiver module 1500 is used to send the identification information of the target object to the cloud server, so that the cloud server can update the map area where the target object is located.

[0548] In one implementation, the transceiver module 1500 is further configured to:

[0549] Receive first indication information from the cloud server, where the first indication information is used to instruct the acquisition device to identify the target object and report the identification information of the target object.

[0550] In one implementation, the transceiver module 1500 is further configured to:

[0551] Receive identification information of target objects from fewer than a threshold number of acquisition devices.

[0552] In one implementation, the first indication information is further used to indicate that the preset confidence type is the first confidence type.

[0553] In one implementation, the transceiver module 1500 is further configured to:

[0554] Second indication information is received from the cloud server, where the second indication information is used to indicate that the preset confidence type is the first confidence type.

[0555] In one implementation, the collection device is a mobile collection device and / or a fixed collection device; the mobile collection device includes a vehicle, and the fixed collection device includes a roadside unit RSU.

[0556] above Figure 15 The functions of the transceiver module 1500 and the processing module 1501 shown may be performed by the processor 1400 running a program in the memory 1401 , or performed by the processor 1400 alone.

[0557] In some possible implementations, various aspects of the method for reporting information processing provided by the embodiments of the present invention can also be implemented in the form of a program product, which includes program code. When the program code is run on a computer device, the program code is used to enable the computer device to execute the steps of the method for reporting information processing according to various exemplary embodiments of the present invention described in this specification.

[0558] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0559] The program product for reporting information processing according to an embodiment of the present invention may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a server device. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in conjunction with a communication transmission, device, or apparatus.

[0560] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with a periodic network action system, apparatus, or device.

[0561] Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0562] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device.

[0563] The present embodiment of the present application also provides a computing device-readable storage medium for the method of processing reported information, i.e., the content is not lost after a power outage. The storage medium stores a software program, including program code. When the program code is executed on a computing device, the software program, when read and executed by one or more processors, can implement any of the above-mentioned information processing solutions in the embodiments of the present application.

[0564] The present application is described above with reference to block diagrams and / or flow charts illustrating methods, apparatus (systems) and / or computer program products according to embodiments of the present application. It should be understood that a block of a block diagram and / or flow chart, as well as a combination of blocks of a block diagram and / or flow chart, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer and / or other programmable data processing device to produce a machine such that instructions executed by the computer processor and / or other programmable data processing device create a method for implementing the functions / actions specified in the block diagram and / or flow chart block.

[0565] Accordingly, the present application may also be implemented using hardware and / or software (including firmware, resident software, microcode, etc.). Furthermore, the present application may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in conjunction with an instruction execution system. In the context of the present application, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, transmit, or convey a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0566] This application describes multiple embodiments in detail with reference to multiple flowcharts. However, it should be understood that these flowcharts and the descriptions of their corresponding embodiments are provided for ease of understanding only and should not constitute any limitation on this application. Not every step in each flowchart is necessarily required; for example, some steps can be skipped. Furthermore, the order in which the steps are executed is not fixed and is not limited to that shown in the figures. The order in which the steps are executed should be determined by their functions and inherent logic.

[0567] The multiple embodiments described in this application can be arbitrarily combined or the steps can be executed in an interleaved manner. The execution order of each embodiment and the execution order between the steps of each embodiment are not fixed and are not limited to those shown in the figures. The execution order of each embodiment and the interleaved execution order of each step of each embodiment should be determined by their functions and internal logic.

[0568] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, the present application is intended to include such modifications and variations if they fall within the scope of the claims of the present application and their equivalents.

Claims

1. A method for processing reported information, characterized in that: The method comprises: Receive N identification information of a target object from N acquisition devices, where N is a positive integer, the identification information including an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value, wherein the confidence type includes a calculation method used to calculate the confidence value; Divide the received N identification information into M groups according to the confidence type in the identification information, where M is a positive integer not greater than N; Determining group identification information corresponding to each group in the M groups; A set of identification information is selected from the M sets of identification information, and a recognition result in the selected identification information is determined as a final result of the target object.

2. The method according to claim 1, characterized in that The N pieces of identification information are received within a threshold time period.

3. The method according to claim 2, characterized in that Before receiving the identification information of the target object sent by N collection devices, the method further includes: First indication information is sent to a collection device within a threshold range, where the first indication information is used to instruct the collection device to identify a target object and report identification information of the target object.

4. The method according to claim 3, characterized in that Before sending the first indication information to the collection device within the threshold range, the method further includes: Receive identification information of target objects from fewer than a threshold number of acquisition devices.

5. The method according to claim 3 or 4, characterized in that The first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

6. The method according to any one of claims 1 to 3, characterized in that Before receiving the identification information of the target object sent by N collection devices, the method further includes: Second indication information is sent to the acquisition device within the threshold range, where the second indication information is used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

7. The method according to any one of claims 1 to 4, characterized in that Each set of identification information in the M groups includes the same confidence type.

8. The method according to claim 7, characterized in that Determining group identification information corresponding to each of the M groups includes: The identification information containing the largest confidence value in each group is determined as the group identification information.

9. The method according to any one of claims 1 to 4, characterized in that The collection device is a mobile collection device and / or a fixed collection device; The mobile data collection device includes a vehicle, and the fixed data collection device includes a roadside unit (RSU).

10. The method according to any one of claims 1 to 4, characterized in that The method further comprises: According to the final result of the target object, the map area where the target object is located is updated, and the updated map area is notified to at least one collection device.

11. A method for processing reported information, characterized in that: The method comprises: Receive N pieces of identification information of a target object from N acquisition devices, where N is a positive integer, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value in the N pieces of identification information is determined by a preset confidence type, and the confidence type includes a calculation method for calculating the confidence value; Select the identification information with the largest confidence value among the N identification information; Determining the recognition result in the selected recognition information as the final result of the target object; The method further comprises: Instructing the N collection devices that the preset confidence type to be applied is the first confidence type; When it is determined that some of the N collection devices are unable to execute the first confidence type, the preset confidence type to be applied is indicated to some of the N collection devices as the second confidence type.

12. The method according to claim 11, characterized in that The N pieces of identification information are received within a threshold time period.

13. The method according to claim 12, characterized in that Before receiving the identification information of the target object sent by N collection devices, the method further includes: First indication information is sent to a collection device within a threshold range, where the first indication information is used to instruct the collection device to identify a target object and report identification information of the target object.

14. The method according to claim 13, characterized in that Before sending the first indication information to the collection device within the threshold range, the method includes: Receive identification information of target objects from fewer than a threshold number of acquisition devices.

15. The method according to claim 13 or 14, characterized in that The first indication information is further used to indicate that the preset confidence type is the first confidence type.

16. The method according to any one of claims 11 to 13, characterized in that: Before receiving the identification information of the target object sent by N collection devices, the method further includes: Second indication information is sent to the collection device within the threshold range, where the second indication information is used to indicate that the preset confidence type is the first confidence type.

17. The method according to any one of claims 11 to 14, characterized in that: The collection device is a mobile collection device and / or a fixed collection device; The mobile data collection device includes a vehicle, and the fixed data collection device includes a roadside unit (RSU).

18. The method according to any one of claims 11 to 14, characterized in that: The method further comprises: According to the final result of the target object, the map area where the target object is located is updated, and the updated map area is notified to at least one collection device.

19. A method for processing reported information, characterized in that: The method comprises: The acquisition device determines identification information of the target object, the identification information including an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value, the confidence type including a calculation method used to calculate the confidence value; The acquisition device sends the identification information of the target object to the cloud server, and the cloud server obtains a final result of the target object after grouping the identification information of the N target objects received from the N acquisition devices based on the confidence type, and when it determines that the final result of the target object is different from the content of the target object in the map area, updates the map area where the target object is located based on the final result of the target object.

20. The method according to claim 19, characterized in that Before the acquisition device determines the identification information of the target object, the method further includes: The collection device receives first indication information from the cloud server, where the first indication information is used to instruct the collection device to identify a target object and report identification information of the target object.

21. The method according to claim 20, characterized in that The first indication information is further used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

22. The method according to claim 19 or 20, characterized in that Before the acquisition device determines the identification information of the target object, the method further includes: The acquisition device receives second indication information from the cloud server, where the second indication information is used to indicate at least one confidence type for determining a confidence value of a target object recognition result.

23. The method according to any one of claims 19 to 21, characterized in that The collection device is a mobile collection device and / or a fixed collection device.

24. The method according to claim 23, wherein The mobile data collection device includes a vehicle, and the fixed data collection device includes a roadside unit (RSU).

25. A method for processing reported information, characterized in that: The method comprises: The acquisition device determines identification information of the target object, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value of the identification result is determined by a preset confidence type, and the confidence type includes a calculation method for calculating the confidence value; The acquisition device sends the identification information of the target object to the cloud server, so that the cloud server, after performing grouping processing based on the confidence type on the N identification information of the target objects received from the N acquisition devices, obtains a final result of the target object, and when it is determined that the final result of the target object is different from the content of the target object in the map area, updates the map area where the target object is located based on the final result of the target object; The method further comprises: When the collection device determines that the preset confidence type of the application indicated by the cloud server cannot be executed and is the first confidence type, the collection device selects the confidence type used to determine the confidence value and reports the selected confidence type to the cloud server; or, when the collection device determines that the preset confidence type of the application indicated by the cloud server cannot be executed and is the first confidence type, the collection device applies to the cloud server for re-indicating the preset confidence type of the application.

26. The method according to claim 25, characterized in that Before the acquisition device determines the identification information of the target object, the method further includes: The collection device receives first indication information from the cloud server, where the first indication information is used to instruct the collection device to identify a target object and report identification information of the target object.

27. The method according to claim 26, characterized in that The first indication information is further used to indicate that the preset confidence type is the first confidence type.

28. The method according to claim 25 or 26, characterized in that Before the acquisition device determines the identification information of the target object, the method further includes: The collection device receives second indication information from the cloud server, where the second indication information is used to indicate that the preset confidence type is the first confidence type.

29. The method according to any one of claims 25 to 27, characterized in that The collection device is a mobile collection device and / or a fixed collection device.

30. The method according to claim 29, wherein The mobile data collection device includes a vehicle, and the fixed data collection device includes a roadside unit (RSU).

31. A device for processing reported information, characterized in that: include: a transceiver module, configured to receive N identification information of a target object from N acquisition devices, where N is a positive integer, the identification information including an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value, wherein the confidence type includes a calculation method used to calculate the confidence value; a processing module, configured to divide the received N identification information into M groups according to the confidence type in the identification information, where M is a positive integer not greater than N; Determining group identification information corresponding to each group in the M groups; A set of identification information is selected from the M sets of identification information, and a recognition result in the selected identification information is determined as a final result of the target object.

32. A device for processing reported information, characterized in that: include: a transceiver module, configured to receive N identification information of a target object from N acquisition devices, where N is a positive integer, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value in the N identification information is determined by a preset confidence type, and the confidence type includes a calculation method for calculating the confidence value; A processing module is used to select the identification information having the largest confidence value among the N identification information; and determine the identification result in the selected identification information as the final result of the target object; The processing module is further configured to: Instructing the N collection devices that the preset confidence type to be applied is the first confidence type; When it is determined that some of the N collection devices are unable to execute the first confidence type, the preset confidence type to be applied is indicated to some of the N collection devices as the second confidence type.

33. A device for processing reported information, characterized in that: include: a processing module, configured to determine identification information of a target object, the identification information including an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value, the confidence type including a calculation method used to calculate the confidence value; A transceiver module is used to send the identification information of the target object to a cloud server, and when the cloud server obtains a final result of the target object after grouping the identification information of the N target objects received from N acquisition devices based on the confidence type, and determines that the final result of the target object is different from the content of the target object in the map area, the cloud server updates the map area where the target object is located based on the final result of the target object.

34. A device for processing reported information, characterized in that: include: a processing module, configured to determine identification information of a target object, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value of the identification result is determined by a preset confidence type, and the confidence type includes a calculation method for calculating the confidence value; a transceiver module, configured to transmit the identification information of the target object to a cloud server, and configured to update the map area where the target object is located based on the final result of the target object obtained by grouping the identification information of the N target objects received from the N acquisition devices based on the confidence type, when the cloud server determines that the final result of the target object is different from the content of the target object in the map area; The processing module is further configured to: When it is determined that the preset confidence type of the application indicated by the cloud server cannot be executed and is the first confidence type, a confidence type for determining the confidence value is selected, and the selected confidence type is reported to the cloud server; or, when it is determined that the preset confidence type of the application indicated by the cloud server cannot be executed and is the first confidence type, an application is made to the cloud server to re-indicate the preset confidence type of the application.

35. A device for processing reported information, characterized in that: include: one or more processors; Memory; transceiver; The memory is used to store one or more programs and data information; wherein the one or more programs include instructions; The processor is configured to execute the method according to any one of claims 1 to 10; or the method according to any one of claims 11 to 18; or the method according to any one of claims 19 to 24; or the method according to any one of claims 25 to 30 according to at least one or more programs in the memory.

36. A vehicle, characterized in that: include: at least one camera, at least one memory, at least one transceiver, and at least one processor; The camera is used to capture the target object and obtain at least one image of the target object; The memory is used to store one or more programs and data information; wherein the one or more programs include instructions; The processor is configured to determine identification information of the target object based on the at least one image, the identification information including a recognition result of the target object, a confidence value of the recognition result, and a confidence type used to determine the confidence value, the confidence type including a calculation method used to calculate the confidence value; The transceiver is used to send the identification information of the target object to the cloud server, so that the cloud server obtains the final result of the target object after grouping the identification information of the N target objects sent by the N acquisition devices based on the confidence type, and when it determines that the final result of the target object is different from the content of the target object in the map area, the cloud server updates the map area where the target object is located based on the final result of the target object.

37. A vehicle, characterized in that: include: at least one camera, at least one memory, at least one transceiver, and at least one processor; The camera is used to capture the target object and obtain at least one image of the target object; The memory is used to store one or more programs and data information; wherein the one or more programs include instructions; The processor is configured to determine identification information of the target object based on the at least one image, the identification information including an identification result of the target object and a confidence value of the identification result, the confidence value being determined by a preset confidence type, the confidence type including a calculation method for calculating the confidence value, so that the cloud server, upon determining that a final result of the target object obtained after grouping N pieces of identification information of the target objects received from N acquisition devices based on the confidence type is different from content of the target object in a map area, updates the map area where the target object is located based on the final result of the target object; The transceiver is used to send the identification information of the target object to the cloud server; The processor is further configured to: When it is determined that the preset confidence type of the application indicated by the cloud server cannot be executed and is the first confidence type, a confidence type for determining the confidence value is selected, and the selected confidence type is reported to the cloud server; or, when it is determined that the preset confidence type of the application indicated by the cloud server cannot be executed and is the first confidence type, an application is made to the cloud server to re-indicate the preset confidence type of the application.

38. A system for processing reported information, characterized in that: include: At least one collection device and a cloud server; The acquisition device is used to determine identification information of the target object, the identification information including an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value, the confidence type including a calculation method used to calculate the confidence value; The identification information of the target object is sent to a cloud server, so that when the cloud server obtains a final result of the target object after grouping the identification information of the N target objects sent by the N acquisition devices based on the confidence type and determines that the final result of the target object is different from the content of the target object in the map area, the cloud server updates the map area where the target object is located based on the final result of the target object; The cloud server is configured to receive N identification information of target objects from N acquisition devices, where N is a positive integer, and the identification information includes an identification result of the target object, a confidence value of the identification result, and a confidence type used to determine the confidence value; Divide the received N identification information into M groups according to the confidence type in the identification information, where M is a positive integer not greater than N; Determining group identification information corresponding to each group in the M groups; A set of identification information is selected from the M sets of identification information, and a recognition result in the selected identification information is determined as a final result of the target object.

39. A system for processing reported information, characterized in that: include: At least one collection device and a cloud server; The acquisition device is configured to determine identification information of a target object, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value of the identification result is determined by a preset confidence type, and the confidence type includes a calculation method for calculating the confidence value; send the identification information of the target object to a cloud server, so that the cloud server, upon determining that a final result of the target object obtained by grouping N pieces of identification information of the target objects received from the N acquisition devices based on the confidence type is different from the content of the target object in the map area, updates the map area where the target object is located based on the final result of the target object; The cloud server is configured to receive N identification information of a target object from N acquisition devices, where N is a positive integer, the identification information including an identification result of the target object and a confidence value of the identification result, wherein the confidence value of the N identification information is determined by a preset confidence type; select the identification information having the largest confidence value among the N identification information; and determine the identification result of the selected identification information as the final result of the target object; The cloud server is further configured to indicate to the collection device that the preset confidence type applied is the first confidence type and / or the second confidence type; The collection device is also used to, when it is determined that the preset confidence type of the application indicated by the cloud server cannot be executed is the first confidence type, select a confidence type for determining the confidence value and report the selected confidence type to the cloud server; or, when it is determined that the preset confidence type of the application indicated by the cloud server cannot be executed is the first confidence type, apply to the cloud server for re-indicating the preset confidence type of the application.

40. The system for processing reported information according to claim 38 or 39, characterized in that: The collection device is a mobile collection device and / or a fixed collection device; The mobile data collection device includes a vehicle, and the fixed data collection device includes a roadside unit (RSU).

41. A computer-readable storage medium, characterized in that The method comprises computer instructions, which, when executed on a device for processing reported information, cause the device for processing reported information to execute the method according to any one of claims 1 to 10; or execute the method according to any one of claims 11 to 18; or execute the method according to any one of claims 19 to 24; or execute the method according to any one of claims 25 to 30.

Images