Configuration method, device and equipment for take-off and landing field of unmanned aerial vehicle and storage medium

Abstract

The invention provides an unmanned aerial vehicle take-off and landing field configuration method and device, equipment and a storage medium, and relates to the technical field of unmanned aerial vehicles. The configuration method for the take-off and landing field of the unmanned aerial vehicle comprises the following steps: constructing a user demand data set of the unmanned aerial vehicle; respectively generating a demand matrix and a supply matrix based on the user demand data set; matching the demand matrix with the supply matrix; and based on the matching result, configuring the take-off and landing field of the unmanned aerial vehicle according to a preset optimization rule. According to the embodiment of the invention, the configuration of the large-scale unmanned aerial vehicle take-off and landing field can be realized based on the real low-altitude traffic data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicles, in particular to a method and device for configuring an unmanned aerial vehicle landing site, and a storage medium. BACKGROUND

[0002] Low-altitude economy, as a new economic form, has been highly valued by the country in recent years and has shown broad prospects for development. The rapid development of low-altitude economy cannot be separated from the construction of infrastructure, and the unmanned aerial vehicle landing site is one of the important infrastructures of low-altitude economy, which can provide unmanned aerial vehicle landing, charging, storage and other services, improve the unmanned aerial vehicle operation area, and provide infrastructure support for low-altitude flight activities of various industries through sharing.

[0003] In the process of building an unmanned aerial vehicle landing site, site selection and planning is a key link to ensure the safe, efficient and sustainable development of low-altitude economy, and needs to consider many factors such as safety, efficiency, economy, environment, regulations, social acceptance and future expansion.

[0004] The site selection of the landing station can usually be realized by the operation optimization of a fine mathematical model combined with a deep learning method. However, the existing operation research method has two defects: firstly, the model is fine but the data size is too small, and usually only a few or ten sites are studied for planning. Secondly, real low-altitude traffic data is used, and the assumption of user demand is too simple. The existing deep learning method also has the problem of not being able to use a large number of completed planning maps as labeled data for training. SUMMARY

[0005] According to an aspect of the present application, a method for configuring an unmanned aerial vehicle landing site is provided, comprising: constructing a user demand data set of unmanned aerial vehicles; generating a demand matrix and a supply matrix based on the user demand data set, respectively; matching the demand matrix and the supply matrix; and configuring the landing site of the unmanned aerial vehicle based on the matching result and according to a preset optimization rule.

[0006] According to some embodiments, a single takeoff and landing of the unmanned aerial vehicle is set as a user demand; wherein the user demand data set of the unmanned aerial vehicle is constructed by: generating a plurality of data points corresponding to a plurality of user demands, wherein any data point in the plurality of data points represents a user demand, and any data point contains time information and spatial information of the corresponding user demand; and constructing the user demand data set based on the plurality of data points.

[0007] According to some embodiments, constructing the user demand data set of the unmanned aerial vehicle further comprises: performing data augmentation on the user demand data set in a preset data augmentation manner to increase the number of data points in the user demand data set, wherein the preset data augmentation manner includes time augmentation and / or spatial augmentation.

[0008] According to some embodiments, based on the user demand data set, a demand matrix and a supply matrix are respectively generated, including: based on the time information and the space information of the user demand, determining a first research area corresponding to the user demand data set that has undergone data enhancement; performing grid processing on the first research area based on a preset grid scale to obtain a plurality of spatio-temporal blocks; obtaining the number of data points in any spatio-temporal block in the plurality of spatio-temporal blocks to generate the demand matrix; and performing data smoothing processing on the demand matrix.

[0009] According to some embodiments, based on the user demand data set, a demand matrix and a supply matrix are respectively generated, including: based on the space information of the user demand, clustering a plurality of data points in the user demand data set to obtain a preset number of cluster clusters, wherein each cluster cluster includes a cluster center; filtering the preset number of cluster clusters according to the number of data points in the cluster cluster; and performing grid processing on the cluster center corresponding to the filtered cluster cluster to generate the supply matrix.

[0010] According to some embodiments, the cluster center corresponding to the filtered cluster cluster is subjected to grid processing to generate the supply matrix, including: determining a second research area based on the cluster center corresponding to the filtered cluster cluster; performing grid processing on the second research area based on a preset grid scale to obtain a plurality of spatial blocks; obtaining the number of data points in any spatial block in the plurality of spatial blocks; and generating the supply matrix according to the number of data points in any spatial block and a preset hyperparameter.

[0011] According to some embodiments, the demand matrix and the supply matrix are matched, including: obtaining a two-dimensional demand matrix corresponding to the demand matrix under a preset time dimension; performing data cancellation processing on the two-dimensional demand matrix and the supply matrix to obtain a first demand residual matrix and / or a first supply residual matrix; transferring the position of the first demand residual matrix to the position of the first supply residual matrix within a preset range to obtain a demand overflow matrix; performing secondary data cancellation processing on the demand overflow matrix and the first supply residual matrix within the preset range to obtain a second demand residual matrix and / or a second supply residual matrix; restoring the position of the second demand residual matrix to the position of the first demand residual matrix, and restoring the position of the second supply residual matrix to the position of the first supply residual matrix; and superimposing a plurality of second demand residual matrices and second supply residual matrices with restored positions under the preset time dimension.

[0012] According to some embodiments, based on the matching result, the landing field of the unmanned aerial vehicle is configured according to a preset optimization rule, including: setting a plurality of planning areas corresponding to the landing field; obtaining a second demand surplus matrix and a second supply surplus matrix corresponding to each of the plurality of planning areas, to obtain a surplus demand quantity and a surplus supply quantity of each of the plurality of planning areas; based on the surplus demand quantity and the surplus supply quantity of each of the plurality of planning areas, configuring the landing field according to the preset optimization rule; and updating the supply matrix according to the configuration result of the landing field.

[0013] According to some embodiments, the preset optimization rule includes: determining a planning area with the largest surplus demand quantity and a planning area with the largest surplus supply quantity in the plurality of planning areas; newly building a landing field in the planning area with the largest surplus demand quantity; and removing a landing field in the planning area with the largest surplus supply quantity; and maintaining the current number of landing fields in any planning area unchanged in a case where a newly built landing field is removed or a removed landing field is newly built in any planning area.

[0014] According to an aspect of the present application, a configuration device of a landing field of an unmanned aerial vehicle is provided, including: a data construction module configured to construct a user demand data set of the unmanned aerial vehicle; a matrix generation module configured to generate a demand matrix and a supply matrix based on the user demand data set; a matrix matching module configured to match the demand matrix with the supply matrix; and a configuration module configured to configure a landing field of the unmanned aerial vehicle based on a matching result and according to a preset optimization rule.

[0015] According to an aspect of the present application, an electronic device is provided, including: one or more processors; a storage device configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0016] According to an aspect of the present application, a computer readable storage medium is provided, which stores a computer program or instructions, and the computer program or instructions are executed by a processor to implement the method as described above.

[0017] According to the embodiments of the present application, the modeling of the landing field planning can be performed based on real user demand data, the data order of the model is expanded and the calculation process of the model is simplified, the fast solution of the maximum coverage problem of the landing field can be realized, and the operation efficiency of the model is improved.

[0018] It should be understood that the foregoing general description and the following detailed description are only exemplary and do not limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description only some embodiments of the present application.

[0020] Figure 1 A flow chart of a configuration method of a UAV landing site according to an example embodiment of the present application is shown.

[0021] Figure 2 A schematic diagram of data points corresponding to user demand according to an example embodiment of the present application is shown.

[0022] Figure 3 A schematic diagram of data set data enhancement of user demand according to an example embodiment of the present application is shown.

[0023] Figure 4 A schematic diagram of data point clustering in a user demand data set according to an example embodiment of the present application is shown.

[0024] Figure 5 A schematic diagram of data offset of a two-dimensional demand matrix and a supply matrix according to an example embodiment of the present application is shown.

[0025] Figure 6 A schematic diagram of secondary data offset of a demand overflow matrix and a first supply surplus matrix according to an example embodiment of the present application is shown.

[0026] Figure 7 A schematic diagram of position recovery of a second demand surplus matrix according to an example embodiment of the present application is shown.

[0027] Figure 8 A schematic diagram of a configuration device of a UAV landing site according to an example embodiment of the present application is shown.

[0028] Figure 9 A block diagram of an electronic device according to an example embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments may, however, be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the figures.

[0030] The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of these specific details, or other methods, components, materials, apparatus, or operations may be employed. In these cases, well-known structures, methods, apparatuses, implementations, materials, or operations will not be shown or described in detail.

[0031] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0032] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0033] This application provides a method, apparatus, device, and storage medium for configuring unmanned aerial vehicle (UAV) take-off and landing sites, which enables the configuration of large-scale UAV take-off and landing sites.

[0034] The following will describe in detail, with reference to the accompanying drawings, a method, apparatus, device, and storage medium for configuring an unmanned aerial vehicle (UAV) take-off and landing site according to embodiments of this application.

[0035] Figure 1 A flowchart illustrating a method for configuring a drone take-off and landing field according to an example embodiment of this application is shown.

[0036] like Figure 1 As shown, in step S100, a user demand dataset for drones is constructed.

[0037] For example, in step S100, the configuration device generates multiple data points corresponding to multiple user needs, and constructs a user needs dataset accordingly.

[0038] The configuration device acquires the drone's flight dynamics data and determines the user's needs within the flight dynamics data.

[0039] According to some embodiments, the flight dynamics data of the UAV includes the UAV's takeoff and landing records, including time information and spatial information (e.g., planar spatial coordinates) corresponding to each takeoff and landing of the UAV.

[0040] According to some embodiments, the configuration device sets a single takeoff and landing of the drone as a user requirement, and each user requirement includes corresponding time and space information.

[0041] The configuration device generates multiple data points corresponding to multiple user requirements, and constructs a user requirement dataset based on these data points.

[0042] According to some embodiments, any one of the multiple data points generated by the configuration device represents a user requirement, such as... Figure 2 As shown. Furthermore, each of the multiple data points contains both temporal and spatial information relevant to the user's needs.

[0043] According to some embodiments, the configuration device can also perform data augmentation on the user demand dataset according to a preset data augmentation method based on the actual scenario, so as to increase the number of data points in the user demand dataset.

[0044] like Figure 3 As shown, when the number of original data points in the user requirement dataset is small, the configuration device can augment the user requirement dataset through temporal and / or spatial augmentation. That is, for an isolated data point in the user requirement dataset, the configuration device adds data points to its vicinity according to temporal periodicity or spatial proximity to increase the number of data points in the user requirement dataset. Figure 3 The three dimensions shown are a time axis and two spatial axes.

[0045] In step S200, a demand matrix and a supply matrix are generated based on the user demand dataset.

[0046] For example, in step S200, the configuration device generates a demand matrix based on the data-enhanced user demand dataset and generates a supply matrix based on the initial user demand dataset without data enhancement.

[0047] Based on the temporal and spatial information of user needs, the configuration device determines the first study area corresponding to the data-enhanced user needs dataset.

[0048] Furthermore, the configuration device performs rasterization processing on the first study area based on a preset raster scale to obtain multiple spatiotemporal blocks within the first study area.

[0049] For example, the configuration device determines the first research region, whose spatiotemporal coordinates are [(X min ,Y minT min ),(X max ,Y max ,T max )], where X, Y are spatial axis coordinates, and T is time axis coordinate. Assuming that the preset grid scale is dx, dy, dt, the configuration device performs grid processing on the first study area, and any one of the plurality of spatio-temporal blocks [(X min +a*dx,Y min +b*dy,T min +c*dt),(X min +(a+1)*dx,Y min +(b+1)*dy,T min +(c+1)*dt)] in the first study area can be obtained.

[0050] The configuration device obtains the number of data points in any one of the plurality of spatio-temporal blocks to generate a demand matrix.

[0051] For example, the configuration device obtains the number of data points (i.e., the number of user demands occurring in the spatio-temporal block) in the spatio-temporal block [(X min +a*dx,Y min +b*dy,T min +c*dt),(X min +(a+1)*dx,Y min +(b+1)*dy,T min +(c+1)*dt)], denoted as D[a, b, c], and uses it as the demand matrix corresponding to the first study area.

[0052] According to some embodiments, the configuration device can perform data smoothing processing on the demand matrix through a preset nonlinear function to simplify the operation process.

[0053] In addition, based on the spatial information of the user demand, the configuration device clusters a plurality of data points in the user demand data set that has not been subjected to data enhancement to obtain a preset number of clustering clusters.

[0054] According to some embodiments, the configuration device ignores the time information of the data points in the initial user demand data set that has not been subjected to data enhancement, and only clusters a plurality of data points based on the spatial information of the data points to obtain a preset number of clustering clusters. Wherein, the configuration device can divide a plurality of data points in the user demand data set into a preset number (for example, 3) of clustering clusters through a K-means clustering algorithm, and the cluster center of each clustering cluster is a clustering center, which can be used as the site selection of the initialized unmanned aerial vehicle landing site, as shown in Figure 4 .

[0055] According to some embodiments, the number of clustering clusters is slightly more than the upper limit of the number of planned drone landing sites. For example, if the number of planned drone landing sites is 2000, the configuration device needs to determine 2500 clustering clusters based on the data points in the user demand data set.

[0056] Further, the configuration device screens the determined clustering clusters according to the number of data points in the clustering clusters, to remove clustering clusters with fewer data points and obtain clustering centers corresponding to the screened clustering clusters.

[0057] According to some embodiments, the configuration device can obtain a clustering cluster with fewer data points in a preset number of clustering clusters, and allocate the data points in the clustering cluster to other clustering clusters as needed. After the data points are allocated, the configuration device deletes the clustering cluster and determines whether the number of remaining clustering clusters meets the actual demand.

[0058] The configuration device determines a second research area based on the clustering centers corresponding to the screened clustering clusters.

[0059] Further, the configuration device rasterizes the second research area based on a preset grid scale to obtain a plurality of spatial blocks in the second research area.

[0060] For example, the configuration device determines a second research area with a spatial coordinate of [(X min ,Y min ), (X max ,Y max )], where X and Y are spatial axis coordinates. Assuming that the preset grid scale is dx and dy, the configuration device rasterizes the second research area to obtain any spatial block [(X min +a*dx, Y min +b*dy), (X min +(a+1)*dx, Y min +(b+1)*dy)] in the plurality of spatial blocks in the second research area.

[0061] The configuration device obtains the number of data points in any spatial block in the plurality of spatial blocks, and generates a supply matrix in combination with a preset hyperparameter.

[0062] For example, the configuration device obtains the number of data points (i.e., the number of drone landing sites) in the spatial block [(X min +a*dx, Y min +b*dy), (X min +(a+1)*dx, Y min +(b+1)*dy)], and multiplies it by the preset hyperparameter p to obtain a supply matrix S[a, b] corresponding to the second research area. The hyperparameter p represents that a unit landing site can be used p times in a unit time.

[0063] In step S300, the demand matrix is ​​matched with the supply matrix.

[0064] For example, in step S300, the configuration device matches the demand matrix with the supply matrix to update the supply matrix.

[0065] The configuration device obtains the corresponding two-dimensional demand matrix in the demand matrix under the preset time dimension.

[0066] According to some embodiments, the demand matrix is ​​a three-dimensional matrix containing time information. Given a specific time dimension, the demand matrix can be transformed into a two-dimensional demand matrix for the current time dimension, which can then be used to match a two-dimensional supply matrix.

[0067] The configuration device performs data cancellation processing on the two-dimensional demand matrix and supply matrix corresponding to the demand matrix under the preset time dimension to obtain a first demand surplus matrix and / or a first supply surplus matrix.

[0068] For example, such as Figure 5 As shown, the two-dimensional demand matrix is ​​located at position (2,2), and the number of data points it contains corresponds to the user demand. The supply matrix is ​​located at positions (0,1), (2,2), and (2,4), and the number of data points it contains corresponds to the supply obtained by multiplying the number of UAV take-off and landing sites by a preset hyperparameter.

[0069] like Figure 5 As shown, the configuration device matches and cancels the data of the two-dimensional demand matrix and supply matrix at the corresponding positions to obtain a first demand surplus matrix and a first supply surplus matrix. Among them, after the user demand and supply at position (2,2) are canceled out, the first demand surplus matrix still has some uncancelled user demand, and the first supply surplus matrix still has uncancelled supply at positions (0,1) and (2,4).

[0070] The configuration device transfers the position of the first demand surplus matrix to the position of the first supply surplus matrix within a preset range to obtain a demand overflow matrix.

[0071] Then, the configuration device performs secondary data cancellation processing on the demand overflow matrix and the first supply surplus matrix within a preset range to obtain a second demand surplus matrix and / or a second supply surplus matrix.

[0072] For example, such as Figure 6 As shown, the configuration device transfers the first demand surplus matrix located at position (2,2) to positions (0,1) and (2,4) where the first supply surplus matrix is ​​located, and converts the first demand surplus matrix that has been transferred to positions (0,1) and (2,4) into a demand overflow matrix.

[0073] As shown in Figure 6 , the configuration device matches and offsets the demand surplus matrix in the corresponding position with the first supply surplus matrix again to obtain a second demand surplus matrix. Wherein, after the user demand in positions (0, 1) and (2, 4) and the supply are offset, the second demand surplus matrix still has part of the user demand that cannot be offset, and the second supply surplus matrix has no supply that can be used for offset.

[0074] The configuration device restores the positions of the second demand surplus matrix to the positions of the first demand surplus matrix, and restores the positions of the second supply surplus matrix to the positions of the first supply surplus matrix.

[0075] For example, as shown in Figure 7 , the configuration device restores the second demand surplus matrix in positions (0, 1) and (2, 4) to the corresponding position (2, 2) of the first demand surplus matrix.

[0076] Since the supply in the second supply surplus matrix has been completely offset and has not overflowed, the second supply surplus matrix does not need to be restored to the corresponding position of the first supply surplus matrix.

[0077] As shown in the second demand surplus matrix Figure 7 , it represents the user demand that cannot be matched. Similarly, if the supply in the second supply surplus matrix still remains, the second supply surplus matrix represents the final remaining supply capacity that the unmanned landing site can provide.

[0078] The configuration device obtains a plurality of second demand surplus matrices and second supply surplus matrices that have been subjected to data offset processing and position restoration in a preset time dimension, and superimposes the plurality of second demand surplus matrices and second supply surplus matrices respectively to obtain a second demand surplus matrix and a second supply surplus matrix in the preset time dimension.

[0079] In step S400, based on the matching result, the configuration device configures the landing site of the unmanned aerial vehicle according to the preset optimization rule.

[0080] For example, in step S400, the configuration device obtains the second demand surplus matrix and the second supply surplus matrix obtained through matching, and configures the landing site of the unmanned aerial vehicle according to the preset optimization rule.

[0081] According to the actual demand, the configuration device sets a plurality of planning areas corresponding to the unmanned aerial vehicle landing site.

[0082] Further, the configuration device obtains the second demand surplus matrix and the second supply surplus matrix corresponding to each planning area in the plurality of planning areas, and obtains the remaining demand quantity and the remaining supply quantity of each planning area.

[0083] Based on the remaining demand quantity and the remaining supply quantity of each planning area, the configuration device configures the take-off and landing field of the unmanned aerial vehicle according to a preset optimization rule.

[0084] According to some embodiments, based on the remaining demand quantity and the remaining supply quantity of each planning area, the configuration device determines, among the plurality of planning areas, a planning area with the largest remaining demand quantity and a planning area with the largest remaining supply quantity.

[0085] According to some embodiments, the configuration device can newly build a take-off and landing field in the planning area with the largest remaining demand quantity, and correspondingly remove a take-off and landing field in the planning area with the largest remaining supply quantity, so as to keep the number of planned take-off and landing fields unchanged.

[0086] Similarly, the configuration device can also remove a take-off and landing field in the planning area with the largest remaining supply quantity, and correspondingly newly build a take-off and landing field in the planning area with the largest remaining demand quantity.

[0087] According to some embodiments, in the case of removal after new building of a take-off and landing field in a planning area, or new building after removal of a take-off and landing field in a planning area, the configuration device maintains the current number of take-off and landing fields in the planning area unchanged, and adds the planning area to a blacklist, and no longer performs optimization.

[0088] The configuration device updates the supply matrix according to the configuration result of the take-off and landing field, for iterative matching with the demand matrix and iterative configuration optimization of the take-off and landing field.

[0089] According to the embodiments of the present application, the planning of the take-off and landing field of the unmanned aerial vehicle can be performed based on real user demand, the data order of the model is expanded and the calculation process of the model is simplified, and the maximum coverage of the take-off and landing field is realized, thereby improving the operation efficiency of the model.

[0090] Figure 8 A schematic diagram of a configuration device of a take-off and landing field of an unmanned aerial vehicle according to an example embodiment of the present application is shown.

[0091] As shown in Figure 8 The configuration device 100 includes a data construction module 110, a matrix generation module 120, a matrix matching module 130, and a configuration module 140.

[0092] The data construction module 110 obtains flight dynamic data of the unmanned aerial vehicle, and determines user demand in the flight dynamic data.

[0093] The data construction module 110 generates a plurality of data points corresponding to a plurality of user demands, and constructs a user demand data set therefrom.

[0094] The data construction module 110 can perform data augmentation on the user demand dataset according to the actual scene and in a preset data augmentation manner, so as to increase the number of data points in the user demand dataset.

[0095] Based on the time information and the space information of the user demand, the matrix generation module 120 determines a first research area corresponding to the user demand dataset that has been subjected to data augmentation.

[0096] The matrix generation module 120 performs gridding processing on the first research area based on a preset grid scale, so as to obtain a plurality of spatio-temporal blocks in the first research area.

[0097] The matrix generation module 120 obtains the number of data points in any spatio-temporal block of the plurality of spatio-temporal blocks, so as to generate a demand matrix.

[0098] Based on the space information of the user demand, the matrix generation module 120 clusters a plurality of data points in the user demand dataset that has not been subjected to data augmentation, so as to obtain a preset number of clustering clusters.

[0099] The matrix generation module 120 filters the determined clustering clusters according to the number of data points in the clustering clusters, so as to remove clustering clusters with fewer data points and obtain clustering centers corresponding to the filtered clustering clusters.

[0100] The matrix generation module 120 determines a second research area based on the clustering centers corresponding to the filtered clustering clusters.

[0101] The matrix generation module 120 performs gridding processing on the second research area based on a preset grid scale, so as to obtain a plurality of spatial blocks in the second research area.

[0102] The matrix generation module 120 obtains the number of data points in any spatial block of the plurality of spatial blocks, and generates a supply matrix in combination with a preset hyperparameter.

[0103] The matrix matching module 130 obtains a two-dimensional demand matrix corresponding to the demand matrix in a preset time dimension.

[0104] The matrix matching module 130 performs data cancellation processing on the two-dimensional demand matrix corresponding to the demand matrix in the preset time dimension and the supply matrix, so as to obtain a first demand residual matrix and / or a first supply residual matrix.

[0105] The matrix matching module 130 transfers the position of the first demand residual matrix to the position of the first supply residual matrix within a preset range, so as to obtain a demand overflow matrix.

[0106] The matrix matching module 130 performs secondary data cancellation processing on the demand overflow matrix and the first supply residual matrix within the preset range, so as to obtain a second demand residual matrix and / or a second supply residual matrix.

[0107] The matrix matching module 130 restores the positions of the second demand residual matrices to the positions of the first demand residual matrices, and restores the positions of the second supply residual matrices to the positions of the first supply residual matrices.

[0108] The matrix matching module 130 obtains a plurality of second demand residual matrices and second supply residual matrices that have been subjected to data offset processing and have their positions restored in a preset time dimension, and superimposes the plurality of second demand residual matrices and second supply residual matrices respectively.

[0109] The configuration module 140 sets a plurality of planning areas corresponding to the unmanned aerial vehicle landing sites.

[0110] The configuration module 140 obtains the second demand residual matrices and the second supply residual matrices corresponding to each planning area in the plurality of planning areas respectively, and obtains the residual demand quantity and the residual supply quantity of each planning area therefrom.

[0111] Based on the residual demand quantity and the residual supply quantity of each planning area, the configuration module 140 configures the landing sites of the unmanned aerial vehicles according to a preset optimization rule.

[0112] The configuration module 140 updates the supply matrix according to the configuration result of the landing sites.

[0113] Figure 9 A block diagram of an electronic device according to an example embodiment of the present application is shown.

[0114] As Figure 9 shown, the electronic device 600 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0115] As Figure 9 shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 can include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc. The storage unit stores program code that can be executed by the processing unit 610, so that the processing unit 610 performs the methods according to various example embodiments of the present application described in the present specification. For example, the processing unit 610 can perform the method as shown in Figure 1 .

[0116] The storage unit 620 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 6201 and / or a cache memory unit 6202, and can further include a read-only memory (ROM) 6203.

[0117] The storage unit 620 can also include a number of program modules 6205 that are stored in the memory 6204, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or a combination of which can include implementation of a network environment.

[0118] The bus 630 can represent one or more of several types of bus structures, including a storage unit bus or bus for storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit bus, or a local bus using any of a variety of bus architectures.

[0119] The electronic device 600 can also communicate with one or more external devices 700 such as a keyboard, a pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with the electronic device 600; and / or one or more devices that enable the electronic device 600 to communicate with one or more other computing devices. Such communication can occur via the input / output (I / O) interface 650. Still yet, the electronic device 600 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 660. The network adapter 660 can communicate with the other components of the electronic device 600 through the bus 630. It should be appreciated that the electronic device 600 can be a part of a larger system, including but not limited to a server system, a cloud computing system, etc. It should also be appreciated that the electronic device 600 can be connected to one or more devices that enable it to function as described herein.

[0120] From the above description of embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. The technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the methods according to the embodiments of the present application.

[0121] The software product can employ any combination of one or more computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0122] The computer readable storage medium can include a computer-readable medium in the form of a data signal embodied in a carrier wave, wherein the data signal modulates an electromagnetic wave, a magnetic field, or other transport mechanism. The computer readable storage medium can also include any computer-readable medium excluding propagated signals per se.

[0123] The program code can be executed by using one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, microcontrollers, programmable logic devices, application specific integrated circuits (ASICs), or the like. More generally, the program code can be executed by any one or combination of: a microprocessor, a controller, a microcontroller, a programmable logic device (PLD), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), or the like. The program code can be written in any form of programming language, including compiled or interpreted languages, and executed by using any one of the above-mentioned processors or a combination thereof.

[0124] The above-mentioned computer readable medium stores one or more programs, and when the one or more programs are executed by the device, the computer readable medium realizes the above-mentioned functions.

[0125] Those skilled in the art can understand that the above modules can be distributed in the device as described in the embodiment, and can also be changed in one or more devices different from the embodiment. The modules of the above embodiment can be combined into one module, or further split into multiple sub-modules.

[0126] The above describes the embodiments of the present application in detail, and the above embodiment is only used to help understand the method and the core idea thereof. Meanwhile, the changes or deformations made by the person skilled in the art according to the idea of the present application, based on the specific implementation and the application range of the present application, all belong to the protection range of the present application. In summary, the content of the specification should not be understood as the limitation of the present application.

Claims

1. A method for configuring a drone take-off and landing field, characterized in that, include: Build a user demand dataset for drones; Based on the user demand dataset, a demand matrix and a supply matrix are generated respectively; Match the demand matrix with the supply matrix; Based on the matching results, the take-off and landing sites of the UAV are configured according to preset optimization rules.

2. The method according to claim 1, characterized in that, Set the single takeoff and landing of the drone as a user requirement; The construction of a user demand dataset for drones includes: Generate multiple data points corresponding to multiple user needs, wherein any one of the multiple data points represents a user need, and any one data point contains the time information and spatial information of the corresponding user need; The user demand dataset is constructed based on the multiple data points.

3. The method according to claim 2, characterized in that, Building a user demand dataset for drones also includes: The user demand dataset is augmented according to a preset data augmentation method to increase the number of data points in the user demand dataset, wherein the preset data augmentation method includes temporal augmentation and / or spatial augmentation.

4. The method according to claim 3, characterized in that, Based on the user demand dataset, a demand matrix and a supply matrix are generated, including: Based on the temporal and spatial information of the user needs, the first research area corresponding to the data-enhanced user needs dataset is determined. Based on a preset grid scale, the first study area is rasterized to obtain multiple spatiotemporal blocks; The number of data points within any spatiotemporal block among the plurality of spatiotemporal blocks is obtained to generate the demand matrix; The demand matrix is ​​then smoothed.

5. The method according to claim 2, characterized in that, Based on the user demand dataset, a demand matrix and a supply matrix are generated, including: Based on the spatial information of the user's needs, multiple data points in the user's needs dataset are clustered to obtain a preset number of clusters, wherein each cluster contains a cluster center. Based on the number of data points in the clusters, the preset number of clusters are filtered; The cluster centers corresponding to the selected clusters are rasterized to generate the supply matrix.

6. The method according to claim 5, characterized in that, The cluster centers corresponding to the selected clusters are rasterized to generate the supply matrix, including: Based on the cluster centers corresponding to the selected clusters, a second study area is determined; Based on a preset grid scale, the second study area is rasterized to obtain multiple spatial blocks; Obtain the number of data points within any spatial block among the plurality of spatial blocks; The supply matrix is ​​generated based on the number of data points within any spatial block and preset hyperparameters.

7. The method according to claim 1, characterized in that, Matching the demand matrix with the supply matrix includes: Obtain the two-dimensional demand matrix corresponding to the demand matrix under the preset time dimension; The two-dimensional demand matrix and the supply matrix are subjected to data cancellation processing to obtain a first demand surplus matrix and / or a first supply surplus matrix; The position of the first demand surplus matrix is ​​transferred to the position of the first supply surplus matrix within a preset range to obtain the demand overflow matrix; The demand overflow matrix is ​​subjected to secondary data cancellation processing with the first supply surplus matrix within the preset range to obtain a second demand surplus matrix and / or a second supply surplus matrix. The position of the second demand surplus matrix is ​​restored to the position of the first demand surplus matrix, and the position of the second supply surplus matrix is ​​restored to the position of the first supply surplus matrix; The multiple second demand surplus matrices and second supply surplus matrices of the recovered positions under the preset time dimension are superimposed.

8. A configuration device for a drone take-off and landing site, characterized in that, include: The data building module is used to build a user requirement dataset for drones; The matrix generation module is used to generate a demand matrix and a supply matrix based on the user demand dataset, respectively. A matrix matching module is used to match the demand matrix with the supply matrix; The configuration module is used to configure the take-off and landing site of the UAV based on the matching results and according to preset optimization rules.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the method as described in any one of claims 1-7.

Images