Data processing method, device and storage medium

Abstract

The present application discloses a data processing method, device and storage medium. The method includes: receiving a first image set; wherein the first image set includes a plurality of first images in a reference area of ​​a paved area, a plurality of photovoltaic panels exist in the reference area, and the paved area includes the reference area and other areas. Based on the first image set, the first photovoltaic panel and the second photovoltaic panel to be cleaned in the reference area are determined. The first associated area of ​​the first photovoltaic panel is determined, and the second associated area of ​​the second photovoltaic panel is determined. The third photovoltaic panel associated with the first photovoltaic panel is determined from the first associated area, and the fourth photovoltaic panel associated with the second photovoltaic panel is determined from the second associated area. A first cleaning instruction is sent to the first drone, and a second cleaning instruction is sent to the second drone, to instruct the first drone to clean the first photovoltaic panel and the third photovoltaic panel, and the second drone to clean the second photovoltaic panel and the fourth photovoltaic panel, thereby improving the accuracy and cleaning efficiency of the drones cleaning the photovoltaic panels.

Description

Technical Field

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

[0002] Photovoltaic energy, as a renewable energy source, directly converts solar radiation into electrical energy. It is an important energy source at present and one of the ultimate energy sources for mankind in the future. Solar panels are designed to capture solar energy with maximum efficiency. Over time, due to the accumulation of pollutants on the surface of photovoltaic panels, the power generation efficiency of photovoltaic panels will decrease. The accumulation of tiny particles in the air will significantly reduce the efficiency of photovoltaic panels by 10%-30%.

[0003] At present, photovoltaic cleaning is mainly done by manual cleaning, supplemented by professional cleaning, and a large part of the work involves high-altitude operations. However, high-altitude operations are dangerous and labor-intensive, and most professional cleaning vehicles are row-mounted or self-propelled, which cannot work across panels. Often, one photovoltaic panel needs to be equipped with a cleaning vehicle, which greatly increases the cost burden. Summary of the invention

[0004] The embodiments of the present application provide a data processing method, device and storage medium, which can send photovoltaic panel cleaning instructions to different drones based on images of different photovoltaic panels, thereby improving the cleaning efficiency and accuracy of the photovoltaic panels.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, comprising: receiving a first image set; wherein the first image set includes a plurality of first images in a reference area of ​​a paved area, there are a plurality of photovoltaic panels in the reference area, and the paved area includes the reference area and other areas. Based on the first image set, determine the first photovoltaic panel and the second photovoltaic panel to be cleaned in the reference area. Determine the first associated area of ​​the first photovoltaic panel, and determine the second associated area of ​​the second photovoltaic panel. Determine the third photovoltaic panel associated with the first photovoltaic panel from the first associated area, and determine the fourth photovoltaic panel associated with the second photovoltaic panel from the second associated area. Send a first cleaning instruction to the first drone, and send a second cleaning instruction to the second drone; wherein the first cleaning instruction is used to instruct the cleaning of the first photovoltaic panel and the third photovoltaic panel, and the second cleaning instruction is used to instruct the cleaning of the second photovoltaic panel and the fourth photovoltaic panel.

[0006] In some feasible examples, determining a first photovoltaic panel and a second photovoltaic panel to be cleaned in a paved area based on the first image set includes:

[0007] Recognize each first image to obtain a second image set; wherein each second image in the second image set includes at least one dirt image of a photovoltaic panel;

[0008] Evaluate each dirt image in the second image set to obtain a cleaning difficulty score for each dirt image;

[0009] Classifying the second image set to obtain a first sub-image set and a second sub-image set; wherein the cleaning difficulty score of the dirt images in the first sub-image set is less than or equal to a first threshold, and the cleaning difficulty score of the dirt images in the second sub-image set is greater than the first threshold;

[0010] The photovoltaic panel corresponding to the dirt image in the first sub-image set is used as the first photovoltaic panel to be cleaned in the paved area, and the photovoltaic panel corresponding to the dirt image in the second sub-image set is used as the second photovoltaic panel to be cleaned in the paved area.

[0011] In some feasible examples, each dirt image in the second image set is evaluated to obtain a cleaning difficulty score of each dirt image, including:

[0012] determining an image size of each dirt image in the second image set;

[0013] determining a type of dirt in each dirt image in the second image set;

[0014] Based on the preset weights corresponding to the types of dirt, a cleaning difficulty score of the dirt image of the image size is determined.

[0015] In some feasible examples, determining a first associated area of ​​a first photovoltaic panel includes:

[0016] Obtaining property information of the first photovoltaic panel and a cleaning difficulty score of the second image set;

[0017] Determining a first associated area based on the property information of the first photovoltaic panel and the cleaning difficulty score of the second image set;

[0018] In some feasible examples, determining a second associated area of ​​a second photovoltaic panel includes:

[0019] obtaining property information of a second photovoltaic panel and a cleaning difficulty score of a second image set;

[0020] determining a second associated area based on the property information of the second photovoltaic panel and the cleaning difficulty score of the second image set;

[0021] In some feasible examples, determining a third photovoltaic panel associated with the first photovoltaic panel from the first associated area includes:

[0022] Get the wind direction and wind speed of the outside wind;

[0023] determining a preset radius of the first photovoltaic panel based on the wind direction and wind speed;

[0024] Taking the position of the first photovoltaic panel as the origin, the fan-shaped area corresponding to the preset radius and wind direction is the first sub-associated area;

[0025] Based on the first association area range, determine the area within the first association area except the first sub-association area as the second sub-association area;

[0026] The photovoltaic panel in the second sub-associated area is determined to be the third photovoltaic panel.

[0027] In some feasible examples, the method further includes receiving a third image set, the third image set including a plurality of third images in other areas of the paved area; the third images include a plurality of photovoltaic panels;

[0028] Based on the attribute information of the first photovoltaic panel and the third image set, searching for a fifth photovoltaic panel of the same type as the first photovoltaic panel in other regions;

[0029] When the cleaning interval date of the fifth photovoltaic panel is greater than the cleaning interval duration, the location of the fifth photovoltaic panel is determined as the third associated area.

[0030] In some feasible examples, determining the third photovoltaic panel associated with the first photovoltaic panel from the second sub-associated area and / or the third associated area includes:

[0031] The photovoltaic panels in the second sub-association area and the third association area are used as third photovoltaic panels.

[0032] In some feasible examples, determining a fourth photovoltaic panel associated with the second photovoltaic panel from the second associated area includes:

[0033] Get the wind direction and wind speed of the outside wind;

[0034] determining a preset radius of the second photovoltaic panel based on the wind direction and wind speed;

[0035] Taking the position of the second photovoltaic panel as the origin, the fan-shaped area corresponding to the preset radius and wind direction is the third sub-associated area;

[0036] Based on the range of the second association area, determining an area within the second association area except the third sub-association area as a fourth sub-association area;

[0037] The photovoltaic panel in the fourth sub-association area is determined to be a fourth photovoltaic panel.

[0038] In some feasible examples, the method further includes receiving a third image set, the third image set including a plurality of third images in other areas of the paved area; the third images include a plurality of photovoltaic panels;

[0039] Based on the attribute information of the second photovoltaic panel and the third image set, searching for a sixth photovoltaic panel of the same type as the second photovoltaic panel in other regions;

[0040] When the cleaning interval date of the sixth photovoltaic panel is greater than the cleaning interval duration, the location of the sixth photovoltaic panel is determined as the fourth associated area.

[0041] In some feasible examples, determining the fourth photovoltaic panel associated with the second photovoltaic panel from the fourth sub-associated area and / or the fourth associated area includes:

[0042] The fourth sub-association area and the photovoltaic panel in the fourth association area are used as the fourth photovoltaic panel.

[0043] In a second aspect, an embodiment of the present application provides a data processing device, including a processor and a memory, wherein the memory is used to store computer-readable instructions, and the processor is used to call the instructions stored in the memory to execute the method of the first aspect.

[0044] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the method of the first aspect.

[0045] Implementing the embodiments of the present application has the following beneficial effects:

[0046] After receiving the first image set, the first image set is analyzed to obtain the second image set, and the first photovoltaic panel and the second photovoltaic panel are distinguished according to the cleaning difficulty of the second image set, and then the third photovoltaic panel associated with the first photovoltaic panel and the fourth photovoltaic panel associated with the second photovoltaic panel are determined. According to the attribute information of the first photovoltaic panel and the third photovoltaic panel, a first cleaning instruction is sent to the first drone for cleaning the first photovoltaic panel and the third photovoltaic panel, and according to the attribute information of the second photovoltaic panel and the fourth photovoltaic panel, a second cleaning instruction is sent to the second drone for cleaning the second photovoltaic panel and the fourth photovoltaic panel. Cleaning instructions are sent to corresponding drones for different photovoltaic panels to perform cleaning operations. Different drones plan the optimal cleaning paths for different associated areas, reduce flight time and energy consumption, and ensure that the areas that need to be cleaned are covered, thereby improving the accuracy and cleaning efficiency of drones cleaning photovoltaic panels. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A schematic diagram of the architecture of a paving system provided in an embodiment of the present application;

[0049] Figure 2 An interactive schematic diagram of a data processing method provided in an embodiment of the present application;

[0050] Figure 3 A flowchart of a data processing method provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of an associated region in a data processing method provided in an embodiment of the present application;

[0052] Figure 5 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0053] Figure 6 A schematic diagram of the structure of another data processing device provided in an embodiment of the present application.

[0054] Figure Annotation

[0055] 10-paving equipment, 20-photovoltaic panel support, 30-photovoltaic panel, 41-first drone, 42-second drone, 43-reference area, 44-first associated area, 45-first sub-associated area, 46-third photovoltaic panel, 47-second sub-associated area, 48-first photovoltaic panel, 49-second associated area, 50-server, 51-third sub-associated area, 52-fourth sub-associated area, 54-second photovoltaic panel, 55-fourth photovoltaic panel, 56-paving area, 57-other areas;

[0056] 300 - data processing device, 301 - transceiver unit, 302 - processing unit, 401 - processor, 402 - communication interface, 403 - memory, 404 - bus. DETAILED DESCRIPTION

[0057] The terms "first" and "second" in the specification, claims and drawings of this application are only used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0058] "At least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three and more than three, and "and / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c".

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] See also Figure 1 , Figure 1 This is a schematic diagram of the architecture of a paving system provided in an embodiment of the present application. Figure 1 As shown, the paving system may include a paving device 10, a photovoltaic panel support 20, a photovoltaic panel 30, a first drone 41 and a second drone 42, and a server 50, etc. Among them, the server 50 can be used to control the operation of electronic equipment such as the paving device 10, the first drone 41 and the second drone 42. The server 50 can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The server may be implemented by a server cluster consisting of multiple servers.

[0061] Optionally, the electronic device may be a personal computer (PC), a laptop or a smart phone, or an all-in-one machine, a handheld computer, a tablet computer (pad), a smart TV player terminal, a vehicle-mounted terminal or a portable device. The operating system of the electronic device on the PC side, such as an all-in-one machine, may include but is not limited to Linux system, Unix system, Windows series system (such as Windows XP, Windows 7, etc.), Mac OS X system (Apple computer operating system) and other operating systems. The operating system of the electronic device on the mobile side, such as a smart phone, may include but is not limited to Android system, IOS (Apple mobile phone operating system), Window system and other operating systems.

[0062] The electronic device can install and run applications, and the server can be a server corresponding to the application installed in the electronic device, providing application services for the application. Among them, the application can be a separately integrated application software, or a small program embedded in other applications, or a system on a web page, etc., which is not limited here. In the embodiment of the present application, the application installed in the paving equipment 10 is used to pave the photovoltaic panel 30 on the photovoltaic panel bracket 20, or to grab the photovoltaic panel 30 from the photovoltaic panel bracket 20. The application installed in the first drone 41 or the second drone 42 is used to clean the photovoltaic panel 30, and to control the drone to fly in the reference area 43, etc.

[0063] The functions performed by the electronic device or server can be implemented by the processor inside it. The processor may include a control board or a control chip. Exemplarily, the processor may include a battery management system (BMS), a micro control unit (MCU), a central processing unit (CPU), other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a pulse width modulator (PWM) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.

[0064] The present application does not limit the type and number of the first drone 41 and the second drone 42, and the cleaning power of the first drone 41 is less than or equal to the cleaning power of the second drone 42. In other words, the second drone 42 can clean dirt that is more difficult to clean than the first drone 41.

[0065] The first drone 41 is an ion nozzle drone, and the second drone 42 is a high-pressure fine water mist drone. The realization principle of the ion nozzle drone is that electrostatic ions attached to the surface of the photovoltaic panel 30 can suppress dust, and the operation of the blades of the ion nozzle drone will generate a reactionary airflow, thereby achieving floating and sinking cleaning. The realization principle of the high-pressure fine water mist drone is to use high-pressure air to ensure the impact of water mist while reducing water consumption to achieve key cleaning of key polluted areas.

[0066] It should be noted that Figure 1 The structure and number of the devices or apparatuses of the system architecture shown are only examples, and the embodiments of the present application are not limited thereto. The figure may also include devices or components not shown. For example, a cleaning device may also be included to clean the photovoltaic panels 30 in the paved area. For the sake of simplicity, they are not described one by one in the drawings.

[0067] For another example, the paving system may further include a camera for collecting images, such as the first image set, etc. The present application does not limit the location of the camera, which may be located on the third drone or on the photovoltaic panel support 20 .

[0068] See also Figure 2 , Figure 2An interactive schematic diagram of a data processing method provided in an embodiment of the present application. The method can be executed by a data processing device, which can be a server, or can be a device or component in a server, or a computer program (including program code, program instructions), etc. The data processing device can be a server, or a device or component on a photovoltaic panel support 20, or a computer program, etc., or a device or component in a third drone. After the data processing device receives the first image set, the data processing device analyzes the multiple first images in the first image set to determine the first photovoltaic panel 48 and the second photovoltaic panel 54 to be cleaned in the reference area 43, and identifies the second image set from the first image set to determine the degree of cleanliness of the photovoltaic panel 30. The first photovoltaic panel and the second photovoltaic panel are determined according to the degree of cleanliness of the photovoltaic panel 30, the instruction for cleaning the first photovoltaic panel is the first cleaning instruction, and the instruction for cleaning the second photovoltaic panel is the second cleaning instruction, the data processing device sends the first cleaning instruction to the first drone 41, so that the first drone 41 starts cleaning the first photovoltaic panel, and the data processing device sends the second cleaning instruction to the second drone 42, so that the second drone 42 starts cleaning the second photovoltaic panel. The data processing device is also used to receive a third image set to identify the cleanliness of photovoltaic panels in other areas of the paved area.

[0069] See also Figure 2 and Figure 3 The method includes but is not limited to the following steps S201 to S205, wherein:

[0070] S201: Receive a first image set. Figure 4 , wherein the first image set includes a plurality of first images within a reference area 43 of a paved area 56 , a plurality of photovoltaic panels 30 exist within the reference area 43 , and the paved area 56 includes the reference area 43 and other areas 57 .

[0071] The reference area 43 of the paved area 56 is photographed to obtain a first image set, that is, an image of multiple photovoltaic panels 30 in the reference area 43. The present application does not limit the position of the camera. For example, it can be a camera on the photovoltaic panel bracket 20, which is used to detect the cleanliness of the photovoltaic panel 30 in real time; it can also be a camera on a third drone, which is used to detect the cleanliness of more photovoltaic panels 30. After obtaining the first image set, the image set is transmitted to a data processing device through a mobile network or a wireless network, and the data processing device analyzes the multiple first images in the first image set. The reference area 43 and other areas 57 in the paved area 56 are distinguished according to cleaning requirements. For example, the reference area 43 can be a key cleaning area, a non-sensitive area, or a suspended work area. By distinguishing the reference area 43 from other areas 57, the drone can focus on the areas that need to be cleaned, avoid wasting time in unnecessary areas, and thus improve the overall cleaning efficiency.

[0072] S202 : Based on the first image set, determine the first photovoltaic panel 48 and the second photovoltaic panel 54 to be cleaned in the reference area 43 .

[0073] The first image set includes multiple photovoltaic panels 30, and the degree of dirtiness of each photovoltaic panel 30 is different, and the cleaning drones required are also different. The data processing device identifies each first image in the first image set to obtain a second image set. Each second image in the second image set includes a dirt image of at least one photovoltaic panel. The degree of dirtiness of the photovoltaic panel 30 is identified by the second image to determine the type of photovoltaic panel 30 to be cleaned in the reference area 43.

[0074] Each dirt image in the second image set is evaluated to obtain a cleaning difficulty score of each dirt image. The specific steps are as follows:

[0075] (1) Determine the image size of each dirt image in the second image set. Determine the coverage area, coverage shape and deposition thickness of the dirt on the photovoltaic panel 30 through the dirt image, and then determine the percentage of the dirt coverage area relative to the photovoltaic panel 30.

[0076] (2) Determine the type of dirt in each dirt image in the second image set. The dirt on the photovoltaic panel 30 is composed of a variety of substances, including but not limited to dust, bird droppings, leaves, pollen, mineral deposits in rainwater, industrial pollution, bird feathers, etc. Dust and particulate matter are very fine particles, ranging in size from a few microns to tens of microns. The size of bird droppings ranges from a few millimeters to a few centimeters, depending on the type of bird and the amount of droppings. Leaves and branches are fragments of only a few millimeters in size or whole leaves of several centimeters in size. The size of pollen particles is between 10 and 100 microns. The size and shape of industrial pollutants such as oil stains and chemicals depend on the source of the pollution. Mineral deposits in rainwater form a thin layer with a thickness of only a few microns and cover a large area.

[0077] (3) Based on the preset weights corresponding to the types of dirt, determine the cleaning difficulty score of the dirt image of the image size. The data processing device sets preset weights for the common types of dirt on the photovoltaic panel 30. For example, the weight of dust is 1, which has a small impact and is easy to clean; the weight of bird droppings is 3, which has a large impact and is medium difficult to clean; the weight of oil stains is 4, which has a large impact and is difficult to clean; the weight of leaves is 2, which has a medium impact and is easy to clean. The cleaning difficulty score of the dirt image can be calculated by the following formula:

[0078] F=∑Q i ×S i

[0079] Where: F is the cleaning difficulty score, Q i is the weight of the corresponding dirt on the photovoltaic panel 30, S iis the coverage area of ​​the corresponding dirt on the photovoltaic panel 30. For example, if there is dust on the photovoltaic panel 30, the coverage area is 20%, and the weight is 1; bird droppings, the coverage area is 5%, and the weight is 3; oil stains, the coverage area is 2%, and the weight is 4; leaves, the coverage area is 10%, and the weight is 2. The dirt cleaning difficulty score is calculated as follows:

[0080] F=(1×20%)+(3×5%)+(4×2%)+(2×10%)=0.63

[0081] The higher the cleaning difficulty score, the stronger the necessity of cleaning. The second image set is classified according to the cleaning difficulty score to obtain a first sub-image set and a second sub-image set. Among them, the cleaning difficulty score of the dirt image in the first sub-image set is less than or equal to the first threshold, and the cleaning difficulty score of the dirt image in the second sub-image set is greater than the first threshold. For example, the first sub-image set has a cleaning difficulty score less than or equal to 0.5, and the second sub-image set has a cleaning difficulty score greater than 0.5.

[0082] The photovoltaic panel 30 corresponding to the dirt image in the first sub-image set is used as the first photovoltaic panel 48 to be cleaned in the paved area 56 , and the photovoltaic panel 30 corresponding to the dirt image in the second sub-image set is used as the second photovoltaic panel 54 to be cleaned in the paved area 56 .

[0083] S203 : Determine the first associated area 44 of the first photovoltaic panel 48 and the second associated area 49 of the second photovoltaic panel 54 .

[0084] The property information of the first photovoltaic panel 48, the cleaning difficulty score of the second image set, the property information of the second photovoltaic panel 54, and the cleaning difficulty score of the second image set are obtained. The property information of the first photovoltaic panel 48 is the cleaning difficulty score of the first photovoltaic panel 48 obtained by analyzing the second image set, and the property information of the second photovoltaic panel 54 is the cleaning difficulty score of the second photovoltaic panel 54 obtained by analyzing the second image set.

[0085] Based on the attribute information of the first photovoltaic panel 48 and the cleaning difficulty score of the second image set, the first associated region 44 is determined. For example, a photovoltaic panel 30 with a cleaning difficulty score less than or equal to 0.5 is determined as the first photovoltaic panel 48, and within the reference region 43, the region containing the first photovoltaic panel 48 is divided into the first associated region 44.

[0086] Based on the attribute information of the second photovoltaic panel 54 and the cleaning difficulty score of the second image set, the second associated area 49 is determined. For example, a photovoltaic panel 30 with a cleaning difficulty score greater than 0.5 is determined as the second photovoltaic panel 54, and within the reference area 43, the area containing the second photovoltaic panel 54 is divided into the second associated area 49. By dividing the first associated area 44 into the second associated area 49, different drones plan the optimal cleaning paths corresponding to different associated areas, reducing flight time and energy consumption, while ensuring that all areas that need to be cleaned are covered.

[0087] S204 : determining the third photovoltaic panel 46 associated with the first photovoltaic panel 48 from the first associated region 44 , and determining the fourth photovoltaic panel 55 associated with the second photovoltaic panel 54 from the second associated region 49 .

[0088] The drones sort the photovoltaic panels 30 to be cleaned according to the priority during the cleaning operation. For example, the first drone 41 determines the first photovoltaic panel 48 and the third photovoltaic panel 46 in the first associated area 44, and the cleaning order of the first photovoltaic panel 48 is higher than the third photovoltaic panel 46. The second drone 42 determines the fourth photovoltaic panel 55 in the second associated area 49, and the cleaning order of the second photovoltaic panel 54 is higher than the fourth photovoltaic panel 55. In the present application, the priority of cleaning the photovoltaic panels 30 is determined according to the downwind movement direction and working radius of the drone, and the working steps include but are not limited to the following:

[0089] (1) Obtaining the wind direction and wind speed of the external wind. For example, the wind direction and wind speed of the external wind in the environment where the drone is located are measured by a wind direction sensor, and the wind direction and wind speed are transmitted to a data processing device via a mobile network or a wireless network.

[0090] (2) Determine the preset radius of the first photovoltaic panel 48 based on the wind direction and wind speed. After receiving the wind direction and wind speed of the external wind, the drone determines the direction of the preset radius based on the wind direction, and determines the size of the preset radius based on the wind speed. The preset radius is the fan-shaped radius of the third sub-association area 51 determined by the drone.

[0091] (3) With the position of the first photovoltaic panel 48 as the origin, the fan-shaped area corresponding to the preset radius and wind direction is the first sub-associated area 45. For example, if the position of the first drone 41 is point O, and the external wind blows from the northeast direction of the first drone 41 to the first drone 41, then the corresponding fan-shaped area is located in the southwest direction of the first drone 41, and the starting angle of the fan-shaped area is 0 degrees, and the ending angle range is 0 degrees to 180 degrees. The fan-shaped radius is determined according to the percentage of the external wind speed to the movement speed of the first drone 41, the drone's own radius and the reference area 43 radius. For example, if the wind speed of the external wind exceeds 10% of the drone's movement speed, the radius of the fan-shaped area exceeds 10% of the drone's own radius, and the maximum radius of the fan-shaped area does not exceed the radius of the reference area 43.

[0092] (4) Based on the range of the first associated area 44, the area in the first associated area 44 other than the first sub-associated area 45 is determined as the second sub-associated area 47. After the first sub-associated area 45 is determined based on the fan-shaped area and the first associated area 44, the area outside the fan-shaped area in the first associated area 44 is determined as the second sub-associated area 47. When the first drone 41 performs the cleaning operation, the photovoltaic panel 30 in the first sub-associated area 45 is cleaned first.

[0093] (5) The photovoltaic panel 30 in the second sub-associated area 47 is determined to be the third photovoltaic panel 46. After the first drone 41 finishes cleaning the photovoltaic panel 30 in the first sub-associated area 45, it determines the position of the third photovoltaic panel 46 and enters the second sub-associated area 47 to clean the third photovoltaic panel 46. The photovoltaic panels 30 in the reference area 43 are cleaned in different areas, which improves the working efficiency of the drone. At the same time, the first sub-associated area 45 is planned according to the downwind direction, which can save the energy of the first drone 41 to a certain extent and extend the working time of the first drone 41.

[0094] It is worth noting that if the external wind changes are not obvious, the first drone 41 takes the first photovoltaic panel 48 closest to itself as the fan origin, the direction in which the first photovoltaic panel 48 occupies a larger area as the opening direction of the fan, and the distance from the fan origin to the boundary of the reference area 43 as the fan radius, and determines the fan area to determine the first sub-associated area 45 and the second sub-associated area 47, and then determines the third photovoltaic panel 46.

[0095] In addition to the third photovoltaic panel 46 in the reference area 43, the third photovoltaic panel 46 also exists in other areas 57. The step of determining the third photovoltaic panel 46 in other areas 57 includes receiving a third image set, the third image set includes a plurality of third images in other areas 57 of the paved area 56, and the third image contains a plurality of photovoltaic panels 30. Based on the attribute information of the first photovoltaic panel 48 and the third image set, the fifth photovoltaic panel of the same type as the first photovoltaic panel 48 is searched from other areas 57. For example, the photovoltaic panel 30 with a cleaning difficulty score less than or equal to 0.5 in other areas 57 is the fifth photovoltaic panel. When the cleaning interval date of the fifth photovoltaic panel is greater than the cleaning interval duration, the location of the fifth photovoltaic panel is determined to be the third associated area. For example, the original cleaning area of ​​the photovoltaic panel 30 is cleaned every three days. It is recognized that the cleaning interval of the fifth photovoltaic panel has exceeded three days and needs to be cleaned again, then the fifth photovoltaic panel of this type is classified into the third associated area. The photovoltaic panel in the third associated area is the third photovoltaic panel 46 in the other area 57. When the first drone 41 receives the first cleaning instruction, it cleans the first photovoltaic panel 48 and the third photovoltaic panel 46. Differentiating the area and determining the third photovoltaic panel 46 in the other area 57 according to the cleaning interval length helps to collect data on the state comparison before and after cleaning of the photovoltaic panel 30 and the cleaning efficiency of the drone, providing a basis for subsequent optimization of the cleaning of the photovoltaic panel 30.

[0096] The fourth photovoltaic panel 55 associated with the second photovoltaic panel 54 is determined from the second associated area 49. The working steps include but are not limited to the following:

[0097] (1) Obtaining the wind direction and wind speed of the external wind. For example, the wind direction and wind speed of the external wind in the environment where the drone is located are measured by a wind direction sensor, and the wind direction and wind speed are transmitted to a data processing device via a mobile network or a wireless network.

[0098] (2) Determine the preset radius of the second photovoltaic panel 54 based on the wind direction and wind speed. After receiving the wind direction and wind speed of the external wind, the data processing device determines the direction of the preset radius based on the wind direction and determines the size of the preset radius based on the wind speed. The preset radius is the fan-shaped radius of the third sub-association area 51 determined by the drone.

[0099] (3) With the position of the second photovoltaic panel 54 as the origin, the fan-shaped area corresponding to the preset radius and wind direction is the third sub-associated area 51. For example, if the position of the second drone 42 is point O, and the external wind blows from the northeast direction of the second drone 42 to the second drone 42, then the corresponding fan-shaped area is located in the southwest direction of the second drone 42, and the starting angle of the fan-shaped area is 0 degrees, and the ending angle range is 0 degrees to 180 degrees. The fan-shaped radius is determined according to the percentage of the external wind speed to the movement speed of the second drone 42, the drone's own radius and the reference area 43 radius. For example, if the wind speed of the external wind exceeds 10% of the drone's movement speed, then the radius of the fan-shaped area is 10% of the radius of the drone itself, and the maximum radius of the fan-shaped area does not exceed the radius of the reference area 43.

[0100] (4) Based on the range of the second associated area 49, the area in the second associated area 49 except the third sub-associated area 51 is determined as the fourth sub-associated area 52. After the third sub-associated area 51 is determined based on the fan-shaped area and the second associated area 49, the area outside the fan-shaped area in the second associated area 49 is determined as the fourth sub-associated area 52. When the first drone 41 performs the cleaning operation, the photovoltaic panel 30 in the third sub-associated area 51 is cleaned first.

[0101] (5) The photovoltaic panel 30 in the fourth sub-associated area 52 is determined to be the fourth photovoltaic panel 55. After the second drone 42 finishes cleaning the photovoltaic panel 30 in the third sub-associated area 51, it determines the position of the fourth photovoltaic panel 55 and enters the fourth sub-associated area 52 to clean the fourth photovoltaic panel 55. The photovoltaic panels 30 in the reference area 43 are cleaned in different areas, which improves the working efficiency of the drone. At the same time, the third sub-associated area 51 is planned according to the downwind direction, which can save the energy of the second drone 42 to a certain extent and extend the working time of the second drone 42.

[0102] It is worth noting that if the external wind changes are not obvious, the second drone 42 takes the second photovoltaic panel 54 closest to itself as the fan origin, the direction in which the second photovoltaic panel 54 occupies a larger area as the opening direction of the fan, and the distance from the fan origin to the boundary of the reference area 43 as the fan radius, and determines the fan area to determine the third sub-associated area 51 and the fourth sub-associated area 52, and then determines the fourth photovoltaic panel 55.

[0103] In addition to the fourth photovoltaic panel 55 in the reference area 43, the fourth photovoltaic panel 55 also exists in the other area 57. The step of determining the fourth photovoltaic panel 55 in the other area 57 includes receiving a third image set, the third image set includes a plurality of third images in the other area 57 of the paved area 56, and the third image contains a plurality of photovoltaic panels 30. Based on the attribute information of the second photovoltaic panel 54 and the third image set, the sixth photovoltaic panel of the same type as the second photovoltaic panel 54 is searched from the other area 57. For example, the photovoltaic panel 30 with a cleaning difficulty score greater than 0.5 in the other area 57 is the sixth photovoltaic panel. When the cleaning interval date of the sixth photovoltaic panel is greater than the cleaning interval duration, the location of the sixth photovoltaic panel is determined to be the fourth associated area. For example, the original cleaning area of ​​the photovoltaic panel 30 is cleaned once every three days. It is recognized that the cleaning interval of the sixth photovoltaic panel has exceeded three days and needs to be cleaned again, then the sixth photovoltaic panel of this type is classified into the third associated area. The photovoltaic panel 30 in the third associated area is the fourth photovoltaic panel 55 in the other area 57. When the second drone 42 receives the second cleaning instruction, it cleans the second photovoltaic panel 54 and the fourth photovoltaic panel 55. Differentiating the area and determining the third photovoltaic panel 46 in the other area 57 according to the cleaning interval length helps to collect data on the state comparison of the photovoltaic panel 30 before and after cleaning and the cleaning efficiency of the drone, providing a basis for the subsequent optimization of the cleaning of the photovoltaic panel 30.

[0104] S205: Send a first cleaning instruction to the first drone 41 and a second cleaning instruction to the second drone 42; wherein the first cleaning instruction is used to instruct the cleaning of the first photovoltaic panel 48 and the third photovoltaic panel 46, and the second cleaning instruction is used to instruct the cleaning of the second photovoltaic panel 54 and the fourth photovoltaic panel 55.

[0105] After analyzing the first image set and the second image set, the data processing device determines the first photovoltaic panel 48, the second photovoltaic panel 54, the third photovoltaic panel 46 and the fourth photovoltaic panel 55, plans the working path of the drone according to the cleaning sequence of the first photovoltaic panel 48 and the third photovoltaic panel 46, generates a first cleaning instruction and sends it to the first drone 41 through a mobile network or a wireless network, so that the first drone 41 cleans the first photovoltaic panel 48 and the third photovoltaic panel 46. Plan the working path of the drone according to the cleaning sequence of the second photovoltaic panel 54 and the fourth photovoltaic panel 55, generate a second cleaning instruction and send it to the second drone 42 through a mobile network or a wireless network, so that the second drone 42 cleans the second photovoltaic panel 54 and the fourth photovoltaic panel 55. The photovoltaic panel 30 is divided into regions according to different degrees of dirtiness, and different cleaning instructions are generated and sent to the corresponding drones to ensure that the corresponding drones clean the corresponding photovoltaic panels 30, thereby improving the accuracy and work efficiency of the drones cleaning the photovoltaic panels 30.

[0106] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is described below.

[0107] See also Figure 5 , Figure 5 The following is a schematic diagram of a data processing device provided in an embodiment of the present application. The data processing device may be a server, or may be a device or component in a server, or may be executed by a computer program, etc. The data processing device may be a paving device 10, or a device or component in the paving device 10, or may be executed by a computer program, etc. The following is an example using a server 50 and a paving device 10. Figure 5 As shown, the data processing device includes a processor 401, a communication interface 402 and a memory 403. The processor 401, the communication interface 402 and the memory 403 may be connected to each other via a bus 404, or may be connected in other ways.

[0108] The processor 401 includes one or more processors, for example, one or more central processing units. When the processor 401 is a central processing unit (CPU), the CPU may be a single-core CPU or a multi-core CPU. In the embodiment of the present application, the processor 401 is used to control the data processing device to implement Figure 2 The embodiment shown.

[0109] The memory 403 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or portable read-only memory (CD-ROM), and is used to store relevant instructions and data.

[0110] The communication interface 402 is used to implement communication with other devices. For example, the communication interface of the server is used to implement communication with the paving device 10, and the communication interface of the paving device 10 is used to implement communication with the server. In the embodiment of the present application, the memory 403 stores computer-readable instructions 405, and the processor 401 is used to call the instructions stored in the memory 403. When the data processing device is a server, the above instructions are used to perform the following steps:

[0111] (1) Receive a first image set, wherein the first image set includes a plurality of first images in a reference area 43 of a paved area 56 , wherein the reference area 43 contains a plurality of photovoltaic panels 30 , and the paved area 56 includes the reference area 43 and other areas 57 .

[0112] (2) Based on the first image set, the first photovoltaic panel 48 and the second photovoltaic panel 54 to be cleaned in the reference area 43 are determined.

[0113] (3) Determine the first associated region 44 of the first photovoltaic panel 48 and determine the second associated region 49 of the second photovoltaic panel 54 .

[0114] (4) The third photovoltaic panel 46 associated with the first photovoltaic panel 48 is determined from the first associated region 44 , and the fourth photovoltaic panel 55 associated with the second photovoltaic panel 54 is determined from the second associated region 49 .

[0115] (5) Sending a first cleaning instruction to the first drone 41 and a second cleaning instruction to the second drone 42; wherein the first cleaning instruction is used to instruct the cleaning of the first photovoltaic panel 48 and the third photovoltaic panel 46, and the second cleaning instruction is used to instruct the cleaning of the second photovoltaic panel 54 and the fourth photovoltaic panel 55.

[0116] See also Figure 6 , Figure 6 A schematic diagram of the structure of another data processing device provided in an embodiment of the present application. The data processing device may be a server, or may be a device or component in a server, or may be executed by a computer program, etc. The data processing device may be a paving device 10, or a device or component in the paving device 10, or may be executed by a computer program, etc. The following takes the paving device 10 and the server as an example. When the data processing device 300 is a server, it includes:

[0117] The transceiver unit 301 is used to receive the first image set and the third image set, provide image information of the photovoltaic panel 30, and provide a reference for distinguishing dirt on the photovoltaic panel 30. It is also used to receive the wind direction and wind speed of the outside wind to determine the first sub-association area 45 and the second sub-association area 47 in the first association area 44, and the third sub-association area 51 and the fourth sub-association area 52 in the second association area 49. Figure 6 The transceiver unit 301 shown may be implemented via one or more communication interfaces 402 .

[0118] The processing unit 302 is used to process the received first image set and second image set, acquire and analyze the second image set, obtain the cleaning difficulty score of each photovoltaic panel 30, and thereby divide the photovoltaic panels 30 in the paved area 56 into a first photovoltaic panel 48, a second photovoltaic panel 54, a third photovoltaic panel 46 and a fourth photovoltaic panel 55, and generate a first cleaning instruction and a second cleaning instruction according to different types of photovoltaic panels. Figure 6 The related functions implemented by the processing unit 302 shown may be implemented by one or more processors 401 .

[0119] The transceiver unit 301 is also used to send a first cleaning instruction to the first drone 41 and a second cleaning instruction to the second drone 42, so that the first drone 41 cleans the first photovoltaic panel 48 and the third photovoltaic panel 46, and the second drone 42 cleans the second photovoltaic panel 54 and the fourth photovoltaic panel 55; and is used to receive the execution results of the cleaning instructions of the first drone and the second drone, and after determining that the cleaning operation of the first drone and the second drone is completed, send instructions to the first drone and the second drone, so that the first drone and the second drone fly to the take-off point.

[0120] It should be noted that the data processing device may also be a third drone, such as an inspection drone, which first analyzes the paved area 56 and then sends the first cleaning instruction and the second cleaning instruction to the first drone 41 and the second drone 42.

[0121] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by the processor, the processor executes part or all of the steps of any data processing method recorded in the above method embodiments.

[0122] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0123] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] In the several embodiments disclosed in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0125] 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 distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0126] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0127] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, RAM, ROM, mobile hard disks, magnetic disks or optical disks.

[0128] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A data processing method, characterized in that: include: Receive a first image set; wherein the first image set includes a plurality of first images in a reference area of ​​a paved area, a plurality of photovoltaic panels exist in the reference area, and the paved area includes the reference area and other areas; determining a first photovoltaic panel and a second photovoltaic panel to be cleaned in the reference area based on the first image set; Determine a first associated area of ​​the first photovoltaic panel, and determine a second associated area of ​​the second photovoltaic panel; Determine a third photovoltaic panel associated with the first photovoltaic panel from the first associated region, and determine a fourth photovoltaic panel associated with the second photovoltaic panel from the second associated region; A first cleaning instruction is sent to the first drone, and a second cleaning instruction is sent to the second drone; wherein the first cleaning instruction is used to instruct the cleaning of the first photovoltaic panel and the third photovoltaic panel, and the second cleaning instruction is used to instruct the cleaning of the second photovoltaic panel and the fourth photovoltaic panel.

2. The method according to claim 1, characterized in that Determining a first photovoltaic panel and a second photovoltaic panel to be cleaned in the paving area based on the first image set includes: Recognize each of the first images to obtain a second image set; wherein each second image in the second image set includes at least one dirt image of the photovoltaic panel; Evaluate each dirt image in the second image set to obtain a cleaning difficulty score of each dirt image; Classifying the second image set to obtain a first sub-image set and a second sub-image set; wherein the cleaning difficulty score of the dirt images in the first sub-image set is less than or equal to a first threshold, and the cleaning difficulty score of the dirt images in the second sub-image set is greater than the first threshold; The photovoltaic panel corresponding to the dirt image in the first sub-image set is used as the first photovoltaic panel to be cleaned in the paved area, and the photovoltaic panel corresponding to the dirt image in the second sub-image set is used as the second photovoltaic panel to be cleaned in the paved area.

3. The method according to claim 2, characterized in that Evaluating each dirt image in the second image set to obtain a cleaning difficulty score for each dirt image includes: determining an image size of each dirt image in the second image set; determining a type of dirt in each dirt image in the second image set; Based on the preset weights corresponding to the types of the dirt, a cleaning difficulty score of the dirt image of the image size is determined.

4. The method according to claim 2, characterized in that: Determining the first associated area and the second associated area includes: Acquire property information of the first photovoltaic panel and a cleaning difficulty score of the second image set; determining the first associated area based on the property information of the first photovoltaic panel and the cleaning difficulty score of the second image set; Acquire property information of the second photovoltaic panel and a cleaning difficulty score of the second image set; The second associated area is determined based on the property information of the second photovoltaic panel and the cleaning difficulty score of the second image set.

5. The method according to claim 4, characterized in that Determining a third photovoltaic panel associated with the first photovoltaic panel from the first associated area includes: Get the wind direction and wind speed of the outside wind; determining a preset radius of the first photovoltaic panel based on the wind direction and wind speed; Taking the position of the first photovoltaic panel as the origin, the fan-shaped area corresponding to the preset radius and the wind direction is the first sub-associated area; Based on the first association area range, determining an area within the first association area other than the first sub-association area as a second sub-association area; The photovoltaic panel in the second sub-association area is determined to be a third photovoltaic panel.

6. The method according to claim 5, characterized in that The method further includes receiving a third image set, wherein the third image set includes a plurality of third images of other areas of the paved area; and a plurality of the photovoltaic panels are included in the third images; Based on the attribute information of the first photovoltaic panel and the third image set, searching for a fifth photovoltaic panel of the same type as the first photovoltaic panel in the other regions; When the cleaning interval date of the fifth photovoltaic panel is greater than the cleaning interval duration, the location of the fifth photovoltaic panel is determined as the third associated area.

7. The method according to claim 4, characterized in that Determining a fourth photovoltaic panel associated with the second photovoltaic panel from the second associated area includes: Get the wind direction and wind speed of the outside wind; determining a preset radius of the second photovoltaic panel based on the wind direction and wind speed; Taking the position of the second photovoltaic panel as the origin, the fan-shaped area corresponding to the preset radius and the wind direction is the third sub-associated area; Based on the range of the second association area, determining an area within the second association area except the third sub-association area as a fourth sub-association area; The photovoltaic panel in the fourth sub-association area is determined to be a fourth photovoltaic panel.

8. The method according to claim 7, characterized in that The method further includes receiving a third image set, wherein the third image set includes a plurality of third images of other areas of the paved area; and a plurality of the photovoltaic panels are included in the third images; Based on the attribute information of the second photovoltaic panel and the third image set, searching for a sixth photovoltaic panel of the same type as the second photovoltaic panel in the other regions; When the cleaning interval date of the sixth photovoltaic panel is greater than the cleaning interval duration, the location of the sixth photovoltaic panel is determined as the fourth associated area.

9. A data processing device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store computer-readable instructions, and the processor is used to call the instructions stored in the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 8.

Images