Data processing method and related device

Abstract

The invention discloses a data processing method and a related device, and the method is applied to a first edge computing device, and comprises the steps: obtaining perception data reported by each perception device in a first communication coverage range of the first edge computing device; target reference data transmitted by at least one second edge computing device is obtained, an overlapping area exists between a second communication coverage area of the second edge computing device and the first communication coverage area, and the target reference data is fusion data determined by the second edge computing device; and performing data fusion processing on the sensing data reported by each sensing device and the target reference data transmitted by each second edge computing device to obtain target fusion data in the first communication coverage range.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method and related devices. Background Art

[0002] In the Internet of Things (IoV) and other IoTs involving object perception, edge computing devices can collect perception data uploaded by perception devices within their perception range and report them to the cloud platform. For example, in IoV, edge computing devices such as Multi-access Edge Computing (MEC) devices will collect perception data reported by perception devices such as Road Side Units (RSUs), vehicles or cameras and radars installed on the road, and report the collected perception data to the cloud platform.

[0003] Among them, after the cloud platform performs data fusion processing on the data reported by multiple edge computing devices, it will send the fused data to the smart terminal through the edge computing device. However, there will be data transmission delays between the edge computing device and the cloud platform, which may result in the inability to provide the required data to the smart terminals in the Internet of Things in a timely manner. Summary of the invention

[0004] On the one hand, the present application provides a data processing method, which is applied to a first edge computing device, including:

[0005] Obtaining perception data reported by each perception device within a first communication coverage range of the first edge computing device;

[0006] Obtain target reference data transmitted by at least one second edge computing device, where a second communication coverage range of the second edge computing device overlaps with the first communication coverage range, and the target reference data is fused data determined by the second edge computing device;

[0007] Data fusion processing is performed on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage range.

[0008] In a possible implementation manner, the target fusion data includes object fusion data of at least one target object within the first communication coverage area;

[0009] The data processing method further includes:

[0010] For each target object, if there are multiple object identifiers corresponding to the target object in the object fusion data of the target object, the object identifiers of the target object in the object fusion data of the target object are unified into a same object identifier.

[0011] In yet another possible implementation manner, unifying the object identifiers of the target objects in the object fusion data of the target objects into the same object identifier includes:

[0012] Determine the target object identifier with the earliest generation time among the multiple object identifiers;

[0013] The object identifiers of the target objects in the object fusion data of the target objects are uniformly set to the target object identifiers with the earliest generation time.

[0014] In yet another possible implementation, the target reference data includes: object fusion data of at least one first candidate object in an overlapping area between the second edge computing device and the first edge computing device, and historical fusion data of the first candidate object at at least one historical time point;

[0015] The performing data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device includes:

[0016] Performing data fusion processing on the sensing data reported by each sensing device to determine object fusion data of at least one target object within the first communication coverage area;

[0017] Determining a target object that matches the first candidate object based on the object fusion data of the first candidate object and the object fusion data of each target object;

[0018] The object fusion data of the first candidate object is fused into the object fusion data of the target object matched by the first candidate object, and the history fusion data of the first candidate object is fused into the history fusion data of the target object matched by the first candidate object.

[0019] In yet another possible implementation, the target fusion data includes object fusion data of at least one target object within the first communication coverage area;

[0020] The data processing method further includes:

[0021] Determine at least one second edge computing device having an overlapping area with the first communication coverage area and an overlapping area between the first edge computing device and the second edge computing device;

[0022] For each second edge computing device, based on the object fusion data of at least one target object, determine at least one second candidate object currently located in an overlapping area between the second edge computing device and the first edge computing device, where the second candidate object belongs to the at least one target object;

[0023] Determining current object fusion data of the second candidate object and historical fusion data at at least one historical time point;

[0024] The reference data of each of the at least one second candidate object is sent to the second edge computing device, where the reference data of the second candidate object includes: object fusion data and historical fusion data of the second candidate object.

[0025] In another possible implementation, the determining at least one second edge computing device having an overlapping area between the corresponding second communication coverage range and the first communication coverage range, and an overlapping area between the first edge computing device and the second edge computing device, includes:

[0026] Obtain information of each second edge computing device corresponding to the configured first edge computing device and an overlapping area between the second edge computing device and the first edge computing device;

[0027] or,

[0028] Detect the first communication coverage of the first edge computing device and obtain the second communication coverage of the other edge computing devices determined by other edge computing devices. Based on the first communication coverage of the first edge computing device and the second communication coverage of the other edge computing devices, determine at least one second edge computing device whose second communication coverage has an overlapping area with the first communication coverage of the first edge computing device and an overlapping area between the second edge computing device and the first edge computing device.

[0029] In yet another possible implementation, the method further includes:

[0030] For each of the first candidate objects, if there is no target object matching the first candidate object, the object fusion data and each history fusion data of the first candidate object are deleted.

[0031] On the other hand, the present application also provides a data processing device, applied to a first edge computing device, including:

[0032] A first obtaining unit, configured to obtain perception data reported by each perception device within a first communication coverage range of the first edge computing device;

[0033] A second obtaining unit is used to obtain target reference data transmitted by at least one second edge computing device, where a second communication coverage range of the second edge computing device overlaps with the first communication coverage range, and the target reference data is fused data determined by the second edge computing device;

[0034] A fusion processing unit is used to perform data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage range.

[0035] In another aspect, the present application also provides an electronic device, including a processor and a memory;

[0036] The processor is used to execute the data processing method as described in any one of the above;

[0037] The memory is used to store programs required for the processor to perform operations.

[0038] On the other hand, the present application also provides a computer program product, including computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement any of the data processing methods described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0040] Figure 1 A flow chart of a data processing method provided in this application;

[0041] Figure 2 A schematic diagram of another flow chart of the data processing method provided in this application;

[0042] Figure 3 A schematic diagram of an implementation process of sending reference data from a first edge computing device to a second edge computing device in this application;

[0043] Figure 4 An example diagram of the communication coverage and overlapping areas of different edge computing devices in this application;

[0044] Figure 5 A schematic diagram of a composition architecture of a vehicle-road cooperative system provided by this application;

[0045] Figure 6 This is a schematic diagram showing the principle of data fusion performed by MEC devices in this application;

[0046] Figure 7 A schematic diagram of another flow chart of the data processing method provided in this application;

[0047] Figure 8 A schematic diagram of the structure of a data processing device provided by the present application;

[0048] Fig. 9 A schematic diagram of the composition architecture of an electronic device provided in this application. DETAILED DESCRIPTION

[0049] The solution of the present application is applicable to any Internet of Things with edge computing devices deployed. The Internet of Things includes a cloud platform, the cloud platform has at least one edge computing device connected to the cloud platform, and each edge computing device is connected to at least one sensing device and at least one terminal device through wireless communication or the like.

[0050] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation mode of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. It is known to those skilled in the art that with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0051] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0052] like Figure 1 , shows a flow chart of a data processing method provided by an embodiment of the present application. The method of this embodiment is applied to a first edge computing device, which can be any edge computing device in the Internet of Things. It is referred to as the first edge computing device only for the sake of distinction. For example, the first edge computing device can be a multi-access edge computing (MEC) device in a vehicle-road cooperative system such as the Internet of Vehicles.

[0053] The method of this embodiment may include:

[0054] S101, obtaining perception data reported by each perception device within a first communication coverage range of a first edge computing device.

[0055] Among them, the first communication coverage range of the first edge computing device refers to the communication range in which the first edge computing device can establish a communication connection with the sensing device or other communication devices.

[0056] The sensing device is a communication device that can sense the external environment and obtain the sensed data. For example, the sensing device includes at least various types of sensors, such as cameras, radars, or infrared sensors. The sensing device may also include a monitoring device for speed collection or other information monitoring.

[0057] The data obtained by the perception device is the perception data. For example, if the perception device is a camera, the perception data is the perceived image; if the perception device is a radar, the perception data is the radar data of the object.

[0058] For example, in the case of a vehicle-road cooperative system, the sensing equipment may include but is not limited to the road side unit (RSU) equipment, as well as speed sensors, image sensors and radars on the vehicle. Among them, the road side unit equipment may include road cameras, millimeter wave radars, laser radars and various intelligent monitoring equipment.

[0059] S102, obtaining target reference data transmitted by at least one second edge computing device.

[0060] Among them, there is an overlapping area between the second communication coverage range of the second edge computing device and the first communication coverage range.

[0061] In the present application, the target reference data is the fused data determined by the second edge computing device. For example, the fused data determined by the second edge computing device is at least part of the data obtained by the second edge computing device fusing the sensed data of each sensed device within the second communication coverage area and the fused data sent by other edge computing devices.

[0062] It can be understood that for any edge computing device, data fusion of the perception data reported by the perception devices within its communication coverage at least means merging and processing various types of data of the same perception object collected from different perception devices to obtain more comprehensive and accurate data information of the perception object.

[0063] It can be understood that, since the target reference data includes the fused data determined by the second edge computing device that overlaps with the communication coverage of the first edge computing device, the target reference data at least includes the fused data of the objects in the overlapping area within the second communication coverage of the second edge computing device. Based on this, the first edge computing device can determine the status data of each object that enters the first communication coverage through each overlapping area within the communication coverage of other edge computing devices based on the target reference data transmitted by each second edge computing device, and can also know the status data of these objects before entering the first communication coverage.

[0064] In one possible implementation, the target reference data may include fused data determined by the second edge computing device at the current moment and at least one historical moment.

[0065] It can be understood that for any two edge computing devices with overlapping communication coverage, the purpose of continuously monitoring the state changes of the perceived objects can be achieved based on the perceived objects appearing in the overlapping area and based on data changes such as the trajectory of the perceived objects within the communication coverage areas corresponding to the two edge computing devices.

[0066] Correspondingly, for the first edge computing device, it only needs to care about the fusion data of the perceived objects existing in the overlapping area corresponding to the second edge computing device. Based on this, the target reference data may only include the object fusion data of at least one first candidate object in the overlapping area between the second edge computing device and the first edge computing device, as well as the historical fusion data of each first candidate object at at least one historical time point.

[0067] The first candidate object is a sensed object determined by the second edge computing device and located in the overlapping area corresponding to the first edge computing device and the second edge computing device. For example, the first candidate object may be a sensed vehicle, pedestrian, or animal. Depending on the Internet of Things used in this case, the possible object types of the first candidate object may also be different, and there is no restriction on this.

[0068] S103: Perform data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage area.

[0069] Among them, by performing data fusion processing on the perception data of each perception device and the target reference data, it is possible to classify the data belonging to the same object together, thereby fusing the object fusion data of each object appearing in the first communication coverage area.

[0070] Among them, the target fusion data may include the fusion data of each target object within the first communication coverage. It is understandable that since the fusion data of the target object is not only obtained based on the perception data of the perception device within the first communication coverage, but also integrates the fusion data determined by other edge computing devices, the fusion data of the target object not only includes the data change information of the target object within the first communication coverage, but also includes the data change information within the second communication coverage corresponding to other edge computing devices, so that the first edge computing device can provide the fusion data of the target object to the vehicle terminal or other intelligent terminal, so that the vehicle terminal and other intelligent terminals can obtain relevant information such as their own speed and position in a timely manner.

[0071] In the present application, there is no limitation on the specific implementation of data fusion processing of each perception data and the target reference data.

[0072] From the above content, it can be seen that in this application, the first edge computing device will obtain the target reference data transmitted by other edge computing devices that have overlapping areas with its communication coverage. Since the target reference data includes the fused data determined by the second edge computing device, the target reference data will inevitably include the fused data of the objects in the overlapping area between the second edge computing device and the first edge computing device and the data of these objects within the communication coverage corresponding to the second edge computing device. Based on this, the first edge computing device can determine the data state changes of the objects within the communication coverage corresponding to the first edge computing device and its adjacent edge computing devices by fusing the perception data of each perception device within the first communication coverage and the target reference data transmitted by each second edge computing device, so that the first edge computing device does not need to report the perception data collected by the perception device to the cloud platform, and can also determine the data state changes of each object perceived by it within different communication coverage, reducing the situation where the required data cannot be provided to the terminal device in time due to the delay in data transmission between the edge computing device and the cloud platform.

[0073] In the present application, there are many possibilities for the specific implementation of data fusion processing of perception data and target reference data. The following is an explanation using one implementation method as an example.

[0074] like Figure 2 , shows another flow chart of the data processing method provided by the present application. The method of this embodiment is applied to a first edge computing device. The method of this embodiment may include:

[0075] S201, obtaining perception data reported by each perception device within a first communication coverage range of a first edge computing device.

[0076] S202: Obtain target reference data transmitted by at least one second edge computing device.

[0077] Among them, there is an overlapping area between the second communication coverage range of the second edge computing device and the first communication coverage range.

[0078] The target reference data is fused data determined by the second edge computing device.

[0079] In this embodiment, the target reference data includes: object fusion data of at least one first candidate object in the overlapping area between the second edge computing device and the first edge computing device, and historical fusion data of each first candidate object at at least one historical time point.

[0080] The first candidate object is an object determined by the second edge computing device and located in an overlapping area between the second edge computing device and the first edge computing device.

[0081] The object fusion data of the first candidate object is the data obtained by the second edge computing device for the first candidate object. Based on this, the object fusion data of the first candidate object includes multiple data of the first candidate object at the current moment. For example, the object fusion data of the first candidate object may include image data, radar data, speed, position and other data of the first candidate object at the current moment.

[0082] The historical fusion data of the first candidate object is the object fusion data of the first candidate object at a historical time point.

[0083] The historical time point is a time point before the current moment. The number of historical time points and specific historical moments can be set as needed. For example, for each first candidate object, the historical fusion data of the first candidate object determined five times before the current moment can be obtained, and the historical fusion data of the first candidate object at the five most recent historical time points can be obtained.

[0084] S203: Perform data fusion processing on the perception data reported by each perception device to determine object fusion data of at least one target object within the first communication coverage area.

[0085] It can be understood that the perception data reported by each perception device are independent data, and by performing data fusion processing on the perception data reported by each perception device, it is possible to determine the target objects that can be perceived within the first communication coverage range, and merge the perception data belonging to the same target object to obtain object fusion data for each target object.

[0086] S204: For each first candidate object, determine a target object that matches the first candidate object based on the object fusion data of the first candidate object and the object fusion data of each target object.

[0087] It can be understood that the data of the same object determined by different edge computing devices at the same time point are at least partially the same. Based on this, the target object and the first candidate object belonging to the same object can be identified.

[0088] For example, objects at the same position at the same time point are actually the same object. Based on this, if the object fusion data of the first candidate object shows that the first candidate object is at position 1 at a certain time 1, and the object fusion data of a target object shows that the target object is also at position 1 at time 1, then it means that the first candidate object and the target object are the same object, and therefore, the target object is the object matched by the first candidate object.

[0089] Of course, this is just to facilitate understanding of the target object that matches the first candidate object, and to use a simple example to illustrate that in actual applications, it may be necessary to analyze multiple dimensions of data of the first candidate object and the target object in order to accurately determine the first candidate object and the target object that match each other, without specific restrictions.

[0090] S205 , fusing the object fusion data of the first candidate object into the object fusion data of the target object matching the first candidate object, and fusing the history fusion data of the first candidate object into the history fusion data of the target object matching the first candidate object.

[0091] It should be noted that this embodiment is described by first fusing the perception data of each perception device to determine the target objects that may exist within the current first communication coverage, and then determining the first candidate objects that match the target objects. In practical applications, it is also possible to simultaneously perform data fusion on the perception data and the object fusion data of each first candidate object, and determine the target objects and first candidate objects that match each other. Then, the historical fusion data of the first candidate object is fused into the historical fusion data of the corresponding target object.

[0092] It is understandable that due to differences in the perception capabilities of the perception devices under the edge computing devices or deviations in the perception data, some first candidate objects may not be matched to the target object. For the first candidate objects that cannot be matched to the target object, the object fusion data and historical fusion data of the first candidate objects are useless data. Based on this, for each first candidate object, if it does not exist in the target object matched by the first candidate object, the object fusion data and historical fusion data of the first candidate object are deleted.

[0093] It can be understood that in any of the above embodiments, after determining the target fusion data, the first edge computing device will also send the fusion data determined by the first edge computing device to the second edge computing device with which the communication coverage overlaps.

[0094] The following takes the target fusion data including the object fusion data of at least one target object within the first communication range as an example to introduce the process of the first edge computing device sending reference data to the second edge computing device. Figure 3 , shows a schematic diagram of an implementation process of a first edge computing device sending reference data to a second edge computing device, which is applied to the first edge computing device. This embodiment may include:

[0095] S301, determining at least one second edge computing device whose corresponding second communication coverage area overlaps with the first communication coverage area of ​​the first edge computing device, and an overlapping area between the first edge computing device and the second edge computing device.

[0096] like Figure 4 An example diagram showing the relationship between the communication coverage areas of multiple edge computing devices.

[0097] exist Figure 4 In the example, the communication coverage of each edge computing device is a circle area, and different edge computing devices have different corresponding communication coverage areas. Figure 4 It can be seen that the communication coverage of edge computing device 1 overlaps with that of edge computing device 2 and edge computing device 3. There is an overlapping area 401 between the communication coverage of edge computing device 1 and the communication coverage of edge computing device 2; and there is an overlapping area 402 between the communication coverage of edge computing device 1 and the communication coverage of edge computing device 3.

[0098] For edge computing device 1 , edge computing device 2 and edge computing device 3 both belong to the second edge computing device of edge computing device 1 .

[0099] In the present application, there may be multiple possible implementations for determining the second edge computing device and the overlapping area between the second edge computing device and the first edge computing device.

[0100] For example, in one possible implementation, the cloud platform or the user can configure the second edge computing device corresponding to the edge computing device and the corresponding overlapping area information in each edge computing device in advance. Based on this, the present application can obtain the information of each second edge computing device corresponding to the configured first edge computing device and the overlapping area between each second edge computing device and the first edge computing device.

[0101] The information of the second edge computing device may include a device identifier of the second edge computing device, and may also include an IP address or other communication address of the second edge computing device, etc., without limitation.

[0102] In another possible implementation, the second edge computing device corresponding to the first edge computing device and the corresponding overlapping area can also be detected in real time. Specifically, the first communication coverage of the first edge computing device can be detected, and the second communication coverage of the other edge computing devices determined by other edge computing devices can be obtained. On this basis, based on the first communication coverage of the first edge computing device and the second communication coverage of the other edge computing devices, at least one second edge computing device whose second communication coverage has an overlapping area with the first communication coverage of the first edge computing device and the overlapping area between each second edge computing device and the first edge computing device are determined.

[0103] S302: For each second edge computing device, determine at least one second candidate object currently located in an overlapping area between the second edge computing device and the first edge computing device based on the object fusion data of at least one target object determined by the first edge computing device.

[0104] The second candidate object belongs to at least one target object. Just for the sake of distinction, the target object located in the overlapping area between the second edge computing area and the first edge computing area is called the second candidate object.

[0105] For example, based on the object fusion data of each target object, the location information of each target object is determined. Based on the location information of each target object, at least one second candidate object located in the overlapping area between the second edge computing device and the first edge computing device is determined.

[0106] S303: For each second candidate object, determine current object fusion data of the second candidate object and historical fusion data at at least one historical time point.

[0107] For example, the object fusion data determined for the second candidate object at 10 historical time points before the current moment is obtained, and the historical fusion data of each of the second candidate object at the 10 historical time points is obtained.

[0108] S304: Send reference data of at least one second candidate object to the second edge computing device.

[0109] The reference data of the second candidate object includes: object fusion data and historical fusion data of the second candidate object.

[0110] For the second edge computing device, it uses the reference data sent by the first edge computing device as the target reference data and follows the above Figure 1 Data fusion is performed in the manner of the embodiment without any specific limitation.

[0111] Combination Figure 4 To illustrate the benefits of this application:

[0112] Depend on Figure 4 It can be seen that while edge computing device 1 obtains the perception data reported by each perception device within its own communication coverage, it can also obtain the object fusion data of each candidate object in the overlapping area 401 currently determined by edge computing device 2 at the current moment and the historical fusion data at multiple historical time points. It can also obtain the object fusion data of each candidate object in the overlapping area 402 currently determined by edge computing device 3 at the current moment and the historical fusion data at multiple historical time points.

[0113] On this basis, the edge computing device 1 can perform data fusion on the perception data of each perception device within its communication coverage, overlap the object fusion data and historical fusion data of each candidate object in the remaining 401 and the overlapping area 402, so as to obtain the object fusion data of each object within the communication coverage corresponding to the edge computing device 1 at the current moment, and also obtain the historical position of each object within the communication coverage corresponding to the edge computing devices 1, 2 and 3 and other data information, so as to obtain the continuous state change information of each object over a period of time.

[0114] In order to facilitate understanding of the solution of this application, an application scenario is described below, taking the application of this application to a vehicle-road cooperative system such as the Internet of Vehicles as an example.

[0115] like Figure 5 , showing a schematic diagram of the composition architecture of a vehicle-road cooperative system.

[0116] Depend on Figure 5 It can be seen that the vehicle-road cooperative system can include: a cloud platform located in the cloud, and at least one multi-access edge computing (MEC) device located on the roadside. Each MEC device can have a communication connection with at least one roadside unit (RSU), camera, radar sensor and other perception devices.

[0117] The camera includes a camera arranged on the road and a camera arranged on the vehicle. Similarly, the radar sensor may include a radar sensor arranged on the road and on the vehicle.

[0118] For example, each MEC device can also have a communication connection with at least one on-board unit (OBU). The vehicle where the on-board unit is located can be equipped with sensors such as cameras and radars connected to the on-board unit. The data collected by the sensors connected to the on-board unit can be reported to the MEC device through the on-board unit.

[0119] In vehicle-road collaborative systems such as the Internet of Vehicles, through communication between the vehicle's on-board unit and road infrastructure such as MEC, the vehicle can obtain real-time road condition information such as traffic congestion and accident alerts, thereby helping drivers make more informed decisions and reduce the risk of traffic accidents.

[0120] In the existing technical solution, MEC devices collect perception data reported by perception devices such as RSU, vehicles or cameras and radar sensors installed on the road, and report the collected perception data to the cloud platform. After the cloud platform performs data fusion processing on the data reported by multiple MEC devices, the fused data is sent to RSU or vehicle-mounted units through MEC devices.

[0121] In this application, if Figure 6 As shown, in order to reduce the data transmission delay between the MEC device and the cloud platform and improve the efficiency of determining the fusion data of each vehicle or other traffic participant under the MEC device, the present application adds a data forwarding function in the MEC device. Each MEC device will forward the fusion data of each candidate object determined to be located in the overlapping area between it and the adjacent MEC device to the adjacent MEC device.

[0122] On this basis, if Figure 6 As shown, each MEC device can perform data fusion based on the perception data reported by the perception device and the data transmitted by the adjacent MEC devices, so as to more comprehensively and completely analyze the status data such as the position and speed of objects such as vehicles at different time points.

[0123] For example, after receiving the fused data transmitted by other MEC devices, the MEC device can combine the Intersection Over Union (IOU) algorithm in the Bird's Eye View (BEV) space to perform data fusion processing on the fused data transmitted by other MEC devices and the perception data transmitted by each perception device within the communication coverage of the MEC device.

[0124] In particular, during the data fusion process, interference data or noise data such as unclear images taken by the camera or misidentified data can also be shielded, and the specific implementation is not restricted.

[0125] It is understandable that the edge computing device will assign an object ID to the object in order to distinguish different objects. However, after the same object moves from the communication coverage of one edge computing device to the communication coverage of another edge computing device, different edge computing devices will assign different object IDs to the object. On this basis, after the edge computing device performs data fusion, the same object in the fused data may correspond to two or more different object IDs.

[0126] For example, the target reference data transmitted by the second edge computing device may include: object fusion data corresponding to the object identifier of each first candidate object and historical fusion data at at least one time point. Although the object fusion data of the first candidate object is added to the object fusion data of the target object matched by the first candidate object in the target fusion data determined by the first edge computing device, the object identifier of the first candidate object is still retained. Then, the object fusion data of the target object may contain the object identifier assigned to the target object by the first edge computing device and the object identifier assigned to the first candidate object by the second edge computing device.

[0127] If multiple object identifiers are included in the object fusion data of the same target object, it will inevitably be detrimental to the cloud platform or other terminal devices such as vehicle-mounted units to reasonably distinguish different objects.

[0128] In order to solve this problem, after determining the target fusion data including object fusion data of at least one target object, the present application, for each target object, if there are multiple object identifiers corresponding to the target object in the object fusion data of the target object, unifies the object identifier of the target object in the object fusion data of the target object into the same object identifier.

[0129] There are many possibilities for the specific implementation of unifying the object identifiers of the same target object into the same object identifier, which are not specifically limited.

[0130] In a possible implementation, in order to ensure that the object identifiers of the same object in different edge computing devices are the same, for each target object, the object identifier of the target object can also be unified as the object identifier generated earliest for the target object in all edge computing devices. Figure 7 Provide explanation.

[0131] like Figure 7 Another flow chart of the data processing method provided by the present application is shown, and this embodiment is applied to a first edge computing device. The method of this embodiment may include:

[0132] S701, obtaining perception data reported by each perception device within a first communication coverage range of the first edge computing device.

[0133] S702: Obtain target reference data transmitted by at least one second edge computing device.

[0134] Among them, the second communication coverage range of the second edge computing device has an overlapping area with the first communication coverage range.

[0135] The target reference data is the fusion data determined by the second edge computing device. For example, the target reference data includes: object fusion data of at least one first candidate object in the overlapping area between the second edge computing device and the first edge computing device, and historical fusion data of each first candidate object at at least one historical time point.

[0136] S703: Perform data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage area.

[0137] The target fusion data includes object fusion data of at least one target object within the first communication coverage area.

[0138] The specific implementation of the above steps can refer to the relevant introduction of the previous embodiment, which will not be repeated here.

[0139] S704: For each target object, if there are multiple object identifiers corresponding to the target object in the object fusion data of the target object, determine the target object identifier with the earliest generation time among the multiple object identifiers.

[0140] For the sake of distinction, the object identifier with the earliest generation time is called the target object identifier.

[0141] As can be seen from the previous introduction, every time an object enters the communication coverage range of an edge computing device, the edge computing device will assign an object identifier to the object. Therefore, the object identifier with the earliest generation time corresponding to the object is the object identifier assigned to the object by the edge computing device corresponding to the communication coverage range that the object entered earliest.

[0142] S705: uniformly set the object identifier of the target object in the object fusion data of the target object to be the target object identifier with the earliest generation time.

[0143] It can be understood that for each target object, each edge computing device sets the object identifier of the target object to the target object identifier with the earliest generation time. Then, the object identifier corresponding to the target object in each edge computing device is the same, which is conducive to more convenient and reliable distinction between objects.

[0144] Corresponding to a data processing method of the present application, the present application also provides a data processing device.

[0145] like Figure 8 , showing a schematic diagram of a composition structure of a data processing method provided by the present application, the apparatus of this embodiment can be applied to a first edge computing device, including:

[0146] A first obtaining unit 801 is used to obtain perception data reported by each perception device within a first communication coverage range of the first edge computing device;

[0147] A second obtaining unit 802 is used to obtain target reference data transmitted by at least one second edge computing device, where a second communication coverage range of the second edge computing device overlaps with the first communication coverage range, and the target reference data is fused data determined by the second edge computing device;

[0148] The fusion processing unit 803 is used to perform data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage range.

[0149] In a possible implementation manner, the target fusion data determined by the fusion processing unit includes object fusion data of at least one target object within the first communication coverage area;

[0150] The data processing device further comprises:

[0151] The identification unification unit is used for unifying the object identification of each target object in the object fusion data of the target object into a same object identification if there are multiple object identifications corresponding to the target object in the object fusion data of the target object.

[0152] In yet another possible implementation, the identification unification unit includes:

[0153] An identifier determination subunit, used to determine a target object identifier with the earliest generation time among the multiple object identifiers;

[0154] The identifier unification subunit is used to uniformly set the object identifiers of the target objects in the object fusion data of the target objects to the identifiers of the target objects with the earliest generation time.

[0155] In yet another possible implementation, the target reference data includes: object fusion data of at least one first candidate object in an overlapping area between the second edge computing device and the first edge computing device, and historical fusion data of the first candidate object at at least one historical time point;

[0156] The fusion processing unit includes:

[0157] A first fusion subunit is used to perform data fusion processing on the sensing data reported by each sensing device to determine object fusion data of at least one target object within the first communication coverage area;

[0158] An object matching unit, configured to determine a target object that matches the first candidate object based on the object fusion data of the first candidate object and the object fusion data of each target object;

[0159] The second fusion subunit is used to fuse the object fusion data of the first candidate object into the object fusion data of the target object matched by the first candidate object, and fuse the history fusion data of the first candidate object into the history fusion data of the target object matched by the first candidate object.

[0160] In yet another possible implementation manner, the target fusion data includes object fusion data of at least one target object within the first communication coverage area;

[0161] The data processing device further comprises:

[0162] a range determination unit, configured to determine at least one second edge computing device having an overlapping area with the first communication coverage area and an overlapping area between the first edge computing device and the second edge computing device;

[0163] an object determination unit, configured to determine, for each second edge computing device, at least one second candidate object currently located in an overlapping area between the second edge computing device and the first edge computing device based on object fusion data of at least one target object, wherein the second candidate object belongs to the at least one target object;

[0164] a data determination unit, configured to determine current object fusion data of the second candidate object and historical fusion data at at least one historical time point;

[0165] A data sending unit is used to send the reference data of each of the at least one second candidate object to the second edge computing device, where the reference data of the second candidate object includes: object fusion data and historical fusion data of the second candidate object.

[0166] In yet another possible implementation, the range determination unit includes:

[0167] A first range determination subunit, configured to obtain information of each second edge computing device corresponding to the configured first edge computing device and an overlapping area between the second edge computing device and the first edge computing device;

[0168] or,

[0169] The second range determination subunit is used to detect the first communication coverage range of the first edge computing device and obtain the second communication coverage range of the other edge computing devices determined by other edge computing devices, and based on the first communication coverage range of the first edge computing device and the second communication coverage range of the other edge computing devices, determine at least one second edge computing device whose second communication coverage range has an overlapping area with the first communication coverage range of the first edge computing device and an overlapping area between the second edge computing device and the first edge computing device.

[0170] In yet another possible implementation, the device further includes:

[0171] The data deleting unit is used to delete the object fusion data and each history fusion data of each first candidate object if the first candidate object does not exist in the target object matched by the first candidate object.

[0172] The present application also provides an electronic device. Fig. 9 , which shows a schematic diagram of a composition structure of the electronic device, and the electronic device at least includes a processor 901 and a memory 902;

[0173] The processor 901 is used to execute the data processing method described in any one of the above embodiments;

[0174] The memory 902 is used to store programs required for the processor to perform operations.

[0175] It can be understood that the electronic device may further include a display unit 903 and an input unit 904 .

[0176] Of course, the electronic device may also have Fig. 9 There may be more or fewer components, without limitation.

[0177] A computer program product is also provided in an embodiment of the present application, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any data processing method provided in the embodiment of the present application.

[0178] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any data processing method provided in the embodiment of the present application.

[0179] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0180] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0181] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0182] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A data processing method, applied to a first edge computing device, comprising: Obtaining perception data reported by each perception device within a first communication coverage range of the first edge computing device; Obtain target reference data transmitted by at least one second edge computing device, where a second communication coverage range of the second edge computing device overlaps with the first communication coverage range, and the target reference data is fused data determined by the second edge computing device; Data fusion processing is performed on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage range.

2. The data processing method according to claim 1, wherein the target fusion data comprises object fusion data of at least one target object within the first communication coverage area; The data processing method further includes: For each target object, if there are multiple object identifiers corresponding to the target object in the object fusion data of the target object, the object identifiers of the target object in the object fusion data of the target object are unified into a same object identifier.

3. The data processing method according to claim 2, wherein the step of unifying the object identifiers of the target objects in the object fusion data of the target objects into the same object identifier comprises: Determine the target object identifier with the earliest generation time among the multiple object identifiers; The object identifiers of the target objects in the object fusion data of the target objects are uniformly set to the target object identifiers with the earliest generation time.

4. The data processing method according to claim 1, wherein the target reference data comprises: object fusion data of at least one first candidate object in an overlapping area between the second edge computing device and the first edge computing device, and historical fusion data of the first candidate object at at least one historical time point; The performing data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device includes: Performing data fusion processing on the sensing data reported by each sensing device to determine object fusion data of at least one target object within the first communication coverage area; Determining a target object that matches the first candidate object based on the object fusion data of the first candidate object and the object fusion data of each target object; The object fusion data of the first candidate object is fused into the object fusion data of the target object matched by the first candidate object, and the history fusion data of the first candidate object is fused into the history fusion data of the target object matched by the first candidate object.

5. The data processing method according to claim 1 or 4, wherein the target fusion data comprises object fusion data of at least one target object within the first communication coverage area; The data processing method further includes: Determine at least one second edge computing device having an overlapping area with the first communication coverage area and an overlapping area between the first edge computing device and the second edge computing device; For each second edge computing device, based on the object fusion data of at least one target object, determine at least one second candidate object currently located in an overlapping area between the second edge computing device and the first edge computing device, where the second candidate object belongs to the at least one target object; Determining current object fusion data of the second candidate object and historical fusion data at at least one historical time point; The reference data of each of the at least one second candidate object is sent to the second edge computing device, where the reference data of the second candidate object includes: object fusion data and historical fusion data of the second candidate object.

6. The data processing method according to claim 5, wherein the determining of at least one second edge computing device having an overlapping area between the corresponding second communication coverage range and the first communication coverage range, and an overlapping area between the first edge computing device and the second edge computing device comprises: Obtain information of each second edge computing device corresponding to the configured first edge computing device and an overlapping area between the second edge computing device and the first edge computing device; or, Detect the first communication coverage of the first edge computing device and obtain the second communication coverage of the other edge computing devices determined by other edge computing devices. Based on the first communication coverage of the first edge computing device and the second communication coverage of the other edge computing devices, determine at least one second edge computing device whose second communication coverage has an overlapping area with the first communication coverage of the first edge computing device and an overlapping area between the second edge computing device and the first edge computing device.

7. The data processing method according to claim 4, further comprising: For each of the first candidate objects, if there is no target object matching the first candidate object, the object fusion data and each history fusion data of the first candidate object are deleted.

8. A data processing device, applied to a first edge computing device, comprising: A first obtaining unit, configured to obtain perception data reported by each perception device within a first communication coverage range of the first edge computing device; A second obtaining unit is used to obtain target reference data transmitted by at least one second edge computing device, where a second communication coverage range of the second edge computing device overlaps with the first communication coverage range, and the target reference data is fused data determined by the second edge computing device; A fusion processing unit is used to perform data fusion processing on the perception data reported by each perception device and the target reference data transmitted by each second edge computing device to obtain target fusion data within the first communication coverage range.

9. An electronic device comprising a processor and a memory; The processor is used to execute the data processing method according to any one of claims 1 to 7 above; The memory is used to store programs required for the processor to perform operations.

10. A computer program product, comprising computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the data processing method according to any one of claims 1 to 7.

Images