Cooperative scheduling method and device for multiple types of unmanned equipment, and electronic equipment
By obtaining unmanned equipment files and park pictures for feature extraction, generating and decomposing environmental maintenance tasks, the problem of inefficient management of unmanned equipment in the park is solved, and efficient collaborative work and refined management of unmanned equipment are realized.
Patent Information
- Application Number
- CN202411121784.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-12-03
AI Technical Summary
In the prior art, the management of multiple unmanned equipment in the park is still mainly manual scheduling, resulting in inefficiency and difficulty in achieving overall coordinated work.
By obtaining unmanned equipment files and park pictures, feature extraction is generated, environmental maintenance tasks are broken down into sub-tasks, and appropriate equipment is allocated according to the equipment job type and efficiency, and automatic task issuance and collaborative work is realized.
It improves the speed and quality of tasks of unmanned equipment, reduces the workload of manual inspections, and realizes efficient maintenance and refined management of the park environment.
Smart Images

Figure CN119067377A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing, and specifically to a method, device and electronic equipment for collaborative scheduling of multiple types of unmanned equipment. Background Art
[0002] With the rapid development of smart parks, more and more parks have introduced various unmanned equipment to improve the automation and intelligence level of park operation and management. These unmanned equipment covers multiple park management areas such as environmental monitoring, greening maintenance, cleaning and sanitation, security patrol, etc., such as unmanned vehicles for tourist pick-ups, lawn mowing robots responsible for lawn mowing, sweepers for road cleaning, patrol robots for park safety inspections, and unmanned disinfection vehicles for regular disinfection of the park. Park managers need to coordinate and dispatch these heterogeneous equipment and coordinate various park affairs to maximize the efficiency of the equipment.
[0003] At present, the management of various unmanned equipment in the park is still mainly based on manual scheduling. Managers need to issue work instructions one by one, which makes it difficult to coordinate the overall situation and leads to low efficiency.
[0004] Therefore, there is an urgent need for a method, device and electronic equipment for collaborative scheduling of multiple types of unmanned equipment. Summary of the invention
[0005] The present application provides a method, device and electronic equipment for collaborative scheduling of multiple types of unmanned equipment. Through automatic task distribution, various unmanned equipment can work together to efficiently complete the environmental maintenance of the park.
[0006] In the first aspect of the present application, a method for collaborative scheduling of multiple types of unmanned equipment is provided, the method comprising: obtaining a preset unmanned equipment file, the preset unmanned equipment file including various types of unmanned equipment and the operation types and operation efficiencies corresponding to the unmanned equipment; obtaining multiple park pictures; performing feature extraction on the park pictures to obtain the green plant maintenance status and sanitary conditions of the park; generating multiple environmental maintenance tasks based on the green plant maintenance status and the sanitary conditions; decomposing the target environmental maintenance task to obtain multiple target subtasks, the target environmental maintenance task being any one of the multiple environmental maintenance tasks; assigning corresponding target unmanned equipment to each of the target subtasks based on the operation type and the operation efficiency; and sending each of the target subtasks to the corresponding target unmanned equipment so that each of the target unmanned equipment completes the corresponding target subtask.
[0007] By adopting the above technical solution and obtaining the preset unmanned equipment files, we can clearly understand the operation type and operation efficiency of various types of unmanned equipment, and provide a basis for subsequent task allocation. By using the acquired park pictures for feature extraction, we can accurately judge the green plant maintenance and sanitation conditions of the park, automatically generate targeted environmental maintenance tasks, and reduce the workload of manual inspections. By decomposing the generated environmental maintenance tasks, complex tasks can be divided into multiple simple subtasks to facilitate the execution of unmanned equipment. According to the operation type and efficiency of the unmanned equipment, the most suitable equipment can be assigned to each subtask to improve the speed and quality of task completion. Through task distribution, various unmanned equipment can work together to efficiently complete the environmental maintenance of the park and improve the park environment.
[0008] Optionally, the feature extraction of the park image to obtain the green plant maintenance status and sanitary condition of the park specifically includes: performing area extraction on the park image to identify the green plant area and road area of the park; for the green plant area, calculating the corresponding green plant coverage rate; comparing the green plant coverage rate with a preset health threshold to obtain the green plant maintenance status of the park; performing image recognition on the road area to obtain the corresponding health hazard targets and the health hazard target types and quantity distribution corresponding to the health hazard targets; determining the sanitary condition of the park according to the health hazard target types and the quantity distribution.
[0009] By adopting the above technical solutions, through regional extraction of park pictures, green plant areas and road areas can be accurately identified, providing a basis for subsequent analysis. By calculating the green plant coverage rate for the green plant area and comparing it with the preset health threshold, the health status of the green plants can be objectively evaluated, and the green plant areas that need maintenance can be discovered in time. Image recognition of road areas can accurately locate various health hazard targets, and count their types and quantity distribution to fully understand the health status of the park. Through the analysis of green plant maintenance and health conditions, the park environment can be intelligently diagnosed, potential problems can be discovered, and refined management of the park environment can be achieved.
[0010] Optionally, calculating the corresponding green plant coverage rate for the green plant area specifically includes: counting the number of green vegetation pixels in the green plant area; calculating the ratio of the number of green vegetation pixels to the total number of pixels in the green plant area, to obtain the green plant coverage rate.
[0011] By adopting the above technical solution, the actual coverage area of green plants can be accurately quantified by counting the number of green vegetation pixels in the green plant area. The green plant coverage rate is calculated by calculating the proportion of green vegetation pixels to the total pixels, which can objectively reflect the density of green plants. As a key indicator for measuring the health status of green plants, the green plant coverage rate can intuitively show the growth of green plants and provide a quantitative basis for green plant maintenance.
[0012] Optionally, the green plant maintenance condition includes healthy and unhealthy, and the green plant coverage rate is compared with a preset health threshold to obtain the green plant maintenance condition of the park, specifically including: if it is determined that the green plant coverage rate is greater than the preset health threshold, then the green plant maintenance condition of the park is determined to be healthy; if it is determined that the green plant coverage rate is less than or equal to the preset health threshold, then the green plant maintenance condition of the park is determined to be unhealthy.
[0013] By adopting the above technical solution, the health status of the green plants in the park can be automatically judged by comparing the calculated green plant coverage rate with the preset health threshold. If the green plant coverage rate is greater than the preset health threshold, it indicates that the green plants are growing well and are in a healthy state; if the green plant coverage rate is lower than or equal to the preset health threshold, it means that the green plants have growth problems and need timely maintenance. Using the threshold comparison method, large areas of green plants in the park can be quickly screened, areas in urgent need of maintenance can be found, and maintenance efficiency can be improved.
[0014] Optionally, determining the sanitary condition of the park according to the sanitary hazard target type and the quantity distribution specifically includes: determining, according to the sanitary hazard target type, a sanitary hazard level corresponding to the sanitary hazard target type in a preset sanitary hazard table, the preset sanitary hazard table including a correspondence between sanitary hazard target types and sanitary hazard levels; calculating the density value of the sanitary hazard target per square meter of road area, and determining the density level corresponding to the density value; determining the sanitary condition according to the sanitary hazard level and the density level.
[0015] By adopting the above technical solution, through the preset health hazard table, the identified health hazard target type can be quickly converted into the corresponding hazard level, reflecting the severity of the health hazard target. Using the density of hazard targets per square meter, the sanitary condition of the road area can be quantitatively evaluated. The greater the density, the worse the sanitary condition. Combining the hazard level and density level, the type and number of health hazard targets can be comprehensively considered to comprehensively judge the sanitary condition of the park and provide a basis for formulating cleaning and maintenance tasks. Through the hazard table and density level, the qualitative health assessment can be converted into a quantitative grade division, making the health condition assessment more standardized and intelligent, and reducing the interference of human factors.
[0016] Optionally, the target environment maintenance task is decomposed to obtain multiple target sub-tasks, specifically including: according to the task type of the target environment maintenance task, determining a decomposition rule corresponding to the task type in a preset task decomposition rule; according to the decomposition rule, decomposing the target environment maintenance task into multiple target sub-tasks; wherein the preset task decomposition rule includes a correspondence between the task type and the decomposition rule.
[0017] By adopting the above technical solution, different types of environmental maintenance tasks can be standardized and split into executable subtasks through preset task decomposition rules. By using the correspondence between task types and preset task decomposition rules, applicable rules can be quickly matched to improve the efficiency and accuracy of task decomposition. Breaking down the target maintenance task into multiple target subtasks can reduce the complexity of the task and facilitate the execution of unmanned equipment. The introduction of preset task decomposition rules makes task allocation more flexible and intelligent, and improves the automation level of environmental maintenance.
[0018] Optionally, assigning corresponding target unmanned equipment to each target subtask based on the job type and the job efficiency specifically includes: obtaining the target task type and job content of each target subtask; obtaining a historical execution task list of the target unmanned equipment; determining whether the target task type is in the historical execution task list; if it is determined that the target task type is in the historical execution task list, assigning the target unmanned equipment to the target subtask.
[0019] By adopting the above technical solution, the actual operating capabilities and experience of the equipment can be understood by obtaining the historical execution task list of the unmanned equipment. By matching the target task type of the subtask with the historical task list, the most suitable unmanned equipment can be selected to perform the task, thereby improving the quality and efficiency of task completion. The historical execution records reflect the actual performance of the unmanned equipment. The equipment selection based on the historical execution records can avoid the problem of mismatch between equipment capabilities and task requirements, reduce the risk of task execution failure, and ensure the stability and reliability of environmental maintenance work.
[0020] In the second aspect of the present application, a multi-type unmanned equipment collaborative scheduling device is provided, which includes: an acquisition module and a processing module, wherein: the acquisition module is used to acquire a preset unmanned equipment file, and the preset unmanned equipment file includes various types of unmanned equipment and the corresponding operation type and operation efficiency of the unmanned equipment; the acquisition module is also used to acquire multiple park pictures; the processing module is used to extract features from the park pictures to obtain the green plant maintenance status and sanitary status of the park; the processing module is also used to generate multiple environmental maintenance tasks based on the green plant maintenance status and the sanitary status; the processing module is also used to decompose the target environmental maintenance task to obtain multiple target subtasks, and the target environmental maintenance task is any one of the multiple environmental maintenance tasks; the processing module is also used to assign corresponding target unmanned equipment to each of the target subtasks according to the operation type and the operation efficiency; the processing module is also used to send each of the target subtasks to the corresponding target unmanned equipment, so that each of the target unmanned equipment completes the corresponding target subtask.
[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.
[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.
[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By obtaining the preset unmanned equipment files, you can clearly understand the operation type and efficiency of each type of unmanned equipment, providing a basis for subsequent task allocation. By using the acquired park pictures for feature extraction, you can accurately judge the green plant maintenance and sanitation conditions of the park, automatically generate targeted environmental maintenance tasks, and reduce the workload of manual inspections. By decomposing the generated environmental maintenance tasks, complex tasks can be split into multiple simple subtasks to facilitate the execution of unmanned equipment. According to the operation type and efficiency of the unmanned equipment, the most suitable equipment can be assigned to each subtask to improve the speed and quality of task completion. Through task distribution, various unmanned equipment can work together to efficiently complete the environmental maintenance of the park and improve the park environment.
[0024] 2. By extracting the area of the park image, the green plant area and road area can be accurately identified, providing a basis for subsequent analysis. By calculating the green plant coverage rate for the green plant area and comparing it with the preset health threshold, the health status of the green plants can be objectively evaluated and the green plant areas that need maintenance can be discovered in time. Image recognition of the road area can accurately locate various health hazard targets, count their types and quantity distribution, and fully grasp the health status of the park. Through the analysis of the maintenance and health status of green plants, the park environment can be intelligently diagnosed, potential problems can be discovered, and refined management of the park environment can be achieved.
[0025] 3. By presetting the health hazard table, the identified health hazard target type can be quickly converted into the corresponding hazard level, reflecting the severity of the health hazard target. Using the density of hazard targets per square meter, the sanitation condition of the road area can be quantitatively evaluated. The greater the density, the worse the sanitation condition. Combining the hazard level and density level, the type and number of health hazard targets can be comprehensively considered to comprehensively judge the sanitation condition of the park and provide a basis for formulating cleaning and maintenance tasks. Through the hazard table and density level, the qualitative health assessment can be converted into a quantitative grading, making the health condition assessment more standardized and intelligent, and reducing the interference of human factors. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a flowchart of a method for collaborative scheduling of multiple types of unmanned equipment disclosed in an embodiment of the present application; Figure 2 It is a module schematic diagram of a multi-type unmanned equipment collaborative scheduling device disclosed in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.
[0027] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION
[0028] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.
[0029] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.
[0030] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0031] This application provides a method for coordinating the dispatch of multiple types of unmanned equipment. Figure 1 , Figure 1 1 is a flow chart of a method for collaborative scheduling of multiple types of unmanned equipment provided in an embodiment of the present application. The method is applied to a server and includes steps S101 to S107, which are as follows: Step S101: Obtain a preset unmanned equipment file, which includes various types of unmanned equipment and the operation types and operation efficiencies corresponding to the unmanned equipment.
[0032] In step S101, the server establishes a connection with a preset equipment archive database. The preset equipment archive database stores detailed information of all unmanned equipment in the park. The server sends a query request to the preset equipment archive database to read the archive data of the unmanned equipment. The equipment archive is usually organized in a structured table form, with each row corresponding to an unmanned equipment and each column corresponding to an equipment attribute. The equipment attributes include equipment number, equipment type, operation type, and operation efficiency.
[0033] Step S102: Acquire multiple park pictures.
[0034] In step S102, various types of camera equipment are deployed in the park, including fixed surveillance cameras and drone aerial photography. These camera equipment are distributed in various areas of the park and collect park pictures from different perspectives. The server establishes a data transmission channel with these camera equipment to obtain multiple park pictures taken by them from different perspectives.
[0035] Step S103: extract features from the park image to obtain the green plant maintenance and sanitation conditions of the park.
[0036] In step S103, regional extraction is performed on the park image to identify the green plant areas and road areas of the park; for the green plant areas, the corresponding green plant coverage rate is calculated; the green plant coverage rate is compared with the preset health threshold to obtain the green plant maintenance status of the park; image recognition is performed on the road area to obtain the corresponding health hazard targets and the health hazard target types and quantity distribution of the health hazard targets; the health status of the park is determined based on the type and quantity distribution.
[0037] Specifically, the server first inputs the acquired park image into the preset semantic segmentation model, which learns the multi-scale texture and color features of the image through a convolutional neural network and generates a corresponding semantic label map. The server extracts the connected areas marked as "green plants" and "roads" in the semantic label map, which correspond to the green plant area and road area in the park image, respectively. For the extracted green plant area, the server first counts the number of pixels marked as green plants, and then divides it by the total number of pixels in the green plant area to obtain the green plant coverage rate, which quantifies the density of green plants in the park. For the extracted road area, the server uses a sanitation hazard target detection model (such as Faster R-CNN) to locate and identify various types of garbage, stains and other hazard targets in the image. The sanitation hazard target detection model outputs the category label (such as discarded plastics, fruit peels and paper scraps) and the position of the bounding box of the sanitation hazard target. Based on this, the server counts the number of various types of sanitation hazard targets and estimates their spatial distribution density in the road area. On the one hand, the category of the sanitation hazard target is mapped to the preset sanitation hazard level (such as hazardous waste corresponds to level 2 hazard), reflecting the severity of the hazard. On the other hand, the density of sanitation hazard targets (such as the amount of garbage per square meter of road) directly reflects the cleanliness of the road. By comparing it with the preset density level threshold, the sanitation condition of the road can be judged. Finally, the server comprehensively considers the hazard level and density level to derive the overall sanitation condition of the road area, including excellent, good, and fair.
[0038] In a possible implementation, for a green plant area, the corresponding green plant coverage rate and vegetation index are calculated, specifically including: counting the number of green vegetation pixels in the green plant area; calculating the ratio of the number of green vegetation pixels to the total number of pixels in the green plant area to obtain the green plant coverage rate.
[0039] Specifically, the server performs a color space transformation on the mask image of the green plant area, converts the RGB image into an HSV image, and then sets the hue (H), saturation (S), and brightness (V) threshold ranges of the green vegetation to extract the pixels in the mask image that meet the "green" condition. The hue threshold can be set to [60, 180], that is, the range from yellow-green to cyan; the saturation threshold can be set to [0.2, 1.0] to exclude colors that are too gray or bright; the brightness threshold can be set to [0.2, 0.8] to exclude pixels that are too bright or too dark. The server counts the number of green pixels extracted and divides it by the total number of pixels in the green plant area to obtain the green plant coverage rate, which ranges from 0 to 1.
[0040] For example, the server extracts a 100*100 pixel green plant area, and after HSV color space conversion and threshold filtering, 8000 green vegetation pixels are obtained, so the green plant coverage rate is 8000 / 10000=0.8.
[0041] In one possible implementation, the green plant maintenance conditions include healthy and unhealthy. The green plant coverage rate and the preset health threshold are compared to obtain the green plant maintenance conditions of the park, specifically including: if it is determined that the green plant coverage rate is greater than the preset health threshold, then the green plant maintenance condition of the park is determined to be healthy; if it is determined that the green plant coverage rate is less than or equal to the preset health threshold, then the green plant maintenance condition of the park is determined to be unhealthy.
[0042] Specifically, the server first reads the preset health threshold from the configuration file or database. The preset health threshold is set by the landscaping expert or manager according to the actual situation of the park, and represents the minimum health standard for the green plant coverage rate. The server compares the preset health threshold with the green plant coverage rate calculated in the previous step. The server determines the relationship between the green plant coverage rate and the preset health threshold, and determines the maintenance status of the green plants in the park accordingly. If the green plant coverage rate is greater than the preset health threshold, the server determines that the maintenance status of the green plants in the park is healthy. On the contrary, if the green plant coverage rate is less than or equal to the preset health threshold, the server determines that the maintenance status of the green plants in the park is unhealthy. For example, for a certain park, the preset health threshold is set to 0.8, which means that the green plant coverage rate reaches more than 80%, and the maintenance status of the green plants in the park is healthy.
[0043] In a possible implementation, the sanitary condition of the park is determined based on the type and quantity distribution of the sanitary hazard targets, specifically including: determining the sanitary hazard level corresponding to the sanitary hazard target type in a preset sanitary hazard table according to the type, the preset sanitary hazard table including the correspondence between the sanitary hazard target type and the sanitary hazard level; calculating the density value of the sanitary hazard target in each square meter of the road area, and determining the density level corresponding to the density value; determining the sanitary condition based on the sanitary hazard level and the density level.
[0044] Specifically, the server first determines the health hazard level corresponding to each type of health hazard target detected based on the preset health hazard table. The preset health hazard table is summarized by park management experts or sanitation workers based on years of experience. The table lists the types and degree of harm of various common health hazard targets, and divides them into several health hazard levels accordingly. For example, the preset health hazard table classifies "sewage accumulation" as a level 3 hazard (highest risk), "discarded masks" as a level 2 hazard (higher risk), and "waste paper balls" as a level 1 hazard (general risk). The server matches the hazard detection results with the preset health hazard table to quickly obtain the health hazard levels of various health hazard targets. The health hazard levels include three levels (level 1 hazards, level 2 hazards, and level 3 hazards).
[0045] The server calculates the average density of health hazard targets per unit road area. Usually, the statistical unit is one square meter of road area. The server first extracts the spatial position coordinates and bounding box size of each health hazard target based on the health hazard target detection results, and maps them to the corresponding position of the park road plan. Then, the server evenly divides the plan into several grids, each grid representing a one-square-meter road area. Next, the server counts the number of various health hazard targets in each grid, and calculates the ratio of the total number to the grid area to obtain the health hazard target density in units of "pieces / square meter". Finally, the server averages the health hazard target density of all grids to obtain the health hazard target density of the entire park road.
[0046] The density value of the sanitation hazard target needs to be further mapped to a density level, and together with the sanitation hazard level, the sanitary condition of the park is finally determined. The server refers to the preset density level classification standard, and the server divides the density of the hazard target into several levels and represents it with numbers. For example, the server corresponds the density values [0, 0.2), [0.2, 0.5), and [0.5, +∞) to density levels 1 (excellent), 2 (good), and 3 (general) respectively. The larger the density level number, the denser the distribution of the hazard targets and the worse the road sanitation condition.
[0047] The server combines the sanitation hazard level and density level to judge the sanitary condition of the park roads. The principle of taking the higher rather than the lower level is usually adopted, that is, taking the maximum value of the sanitation hazard level and the density level as the sanitation level of the park. For example, if the highest level of the hazard target in the park is level 2 (such as discarded masks), the average density is 0.3 / square meter corresponding to density level 2, then the sanitation level of the park is max(2,2)=2, which is at a "good" level. This evaluation method takes into account the harmfulness of the sanitation hazard target itself, and also reflects the wide distribution of the sanitation hazard target, which can more comprehensively and accurately evaluate the sanitation status of the park. The overall sanitation status of the road area includes excellent, good, and general.
[0048] Step S104: Generate multiple environmental maintenance tasks based on the green plant maintenance and sanitary conditions.
[0049] In step S104, the server automatically generates a series of environmental maintenance tasks based on the green plant maintenance and sanitation conditions obtained in the previous step. The server uses a rule-based and policy-based task generation method to determine the task type, quantity, and priority of the required environmental maintenance tasks by judging the green plant maintenance and sanitation levels and matching the predefined task generation rules.
[0050] The server compares the maintenance and sanitation conditions of green plants with the preset task generation rule base. The task generation rule base is a summary and refinement of park management experts based on years of environmental maintenance experience, and contains the correspondence between various environmental conditions and maintenance tasks. A typical task generation rule is like "If the maintenance condition of green plants = unhealthy, then generate a patrol maintenance task with a high priority." The server matches the parameters such as the maintenance condition and sanitation condition of green plants with the conditional part in the preset task generation rule base, finds all rules that meet the conditions, and extracts their conclusion part as the basis for task generation.
[0051] In terms of green plant maintenance, the server determines the comparison result of the green plant coverage rate and the preset health threshold. If the green plant coverage rate is less than or equal to the preset health threshold, it means that the growth of vegetation in the park is worrying and measures need to be taken to improve it. At this time, the server generates a series of green plant inspection and maintenance tasks based on the "unhealthy" green plant maintenance situation. The tasks may include pest control, water and fertilizer management, and vegetation pruning. Since poor green plant maintenance will directly affect the park's landscape effect and visitor experience, the server marks such maintenance tasks as high priority so that they can be handled as soon as possible. On the contrary, if the server finds that the green plant coverage rate is greater than the preset health threshold, it can be judged that the vegetation in the park is growing well, and routine inspection and maintenance tasks can be generated, and the task priority is also low.
[0052] In terms of sanitation conditions, the server analyzes the hazard level and density level of sanitation hazard targets. The hazard level reflects the degree of harm of a single sanitation hazard target, and the density level reflects the widespread distribution of sanitation hazard targets. The higher the two indicators, the worse the sanitation condition of the park, and the more sanitation forces are needed. For example, when the server finds that the sanitation condition is assessed as "general", it triggers the preset task generation rules and generates multiple sanitation cleaning tasks. The server marks the cleaning tasks in the area where the level 3 hazard targets are located as high priority based on the spatial location and density distribution information of the sanitation hazard targets. At the same time, the server will also generate corresponding sanitation inspection tasks to comprehensively check for possible hidden dangers and provide pre-guarantee for the cleaning tasks.
[0053] Step S105: Decompose the target environment maintenance task to obtain multiple target subtasks, where the target environment maintenance task is any one of the multiple environment maintenance tasks.
[0054] In step S105, according to the task type of the target environment maintenance task, a decomposition rule corresponding to the task type is determined in the preset task decomposition rule; according to the decomposition rule, the target environment maintenance task is decomposed into multiple target subtasks; wherein the preset task decomposition rule includes the correspondence between the task type and the decomposition rule.
[0055] Specifically, the target environmental maintenance task is any one of multiple environmental maintenance tasks. The server will take all environmental maintenance tasks for decomposition. The server first reads the key attribute information of the target environmental maintenance task, including task type and operation efficiency. Task type is the primary basis for task decomposition. Different types of environmental maintenance tasks have significant differences in decomposition rules and sub-task composition. For example, green plant maintenance tasks may need to be decomposed into sub-tasks such as watering, fertilizing, pruning, and pest control, while sanitation cleaning tasks may need to be decomposed into sub-tasks such as garbage collection, stain cleaning, and disinfection and sterilization.
[0056] The server accesses the preset task decomposition rule library, which contains various common environmental maintenance task types and their corresponding decomposition rules. The decomposition rule defines how to convert a large task goal into multiple small task steps. The server uses data structures such as decision tree and AND-OR tree to describe it. The server matches the task type of the target environmental maintenance task with the decomposition rules in the preset task decomposition rule library, finds the applicable rules, and then automatically disassembles the original task and generates subtasks in strict accordance with the conditional logic and task templates in the rules. Taking the green plant maintenance task as an example, the server substitutes the conditional judgment into the decomposition rule to determine which subtasks need to be generated. The server generated a watering subtask and a fertilizing subtask after decomposition.
[0057] After the task decomposition is completed, the server will perform necessary redundancy elimination and logic optimization on the generated subtasks to improve the efficiency of task execution. On the one hand, the server merges and compares the coverage of subtasks, identifies completely overlapping or highly similar subtasks, and merges them to avoid unnecessary duplication of work; on the other hand, the server analyzes the execution sequence and dependency of subtasks, constructs a task priority graph, and ensures that subtasks can be carried out in a reasonable order. For example, for a tree pruning task, the server will mark a group of subtasks such as "straightening branches-fixing branches-pruning branches" as sequential dependencies so that they can be executed strictly in sequence.
[0058] Step S106: assign corresponding target unmanned equipment to each target subtask according to the operation type and operation efficiency.
[0059] In step S106, the target task type and job content of each target subtask are obtained; the historical execution task list of the target unmanned equipment is obtained; it is determined whether the target task type is in the historical execution task list; if it is determined that the target task type is in the historical execution task list, the target unmanned equipment is assigned to the target subtask.
[0060] Specifically, the server obtains the target task type and operation content of the target subtask: the server extracts the task type (such as greening maintenance, cleaning, etc.) and specific operation content (such as pruning bushes, cleaning garbage, etc.) of each target subtask from the results of the target environment maintenance task decomposition to form structured task attribute data. Obtain the historical task data of the target unmanned equipment: the server accesses the unmanned equipment archive to extract the historical execution task list of each candidate equipment, including key information such as the task type, operation content, and completion quality of the equipment. The server matches the task type of the target subtask with the historical task list of the target unmanned equipment to determine whether the task type is in the execution experience of the target unmanned equipment. This process can be achieved through keyword matching. If it is determined that the target task type is in the historical execution task list, the server automatically generates a control instruction and sends the operation instruction of each target subtask to the corresponding target unmanned equipment.
[0061] Step S107: Send each target subtask to the corresponding target unmanned equipment, so that each target unmanned equipment can complete the corresponding target subtask.
[0062] In step S107, a stable data transmission channel is established between the server and the unmanned device through a wireless communication network (such as 5G, Wi-Fi, etc.). The server packages the task execution script and other data corresponding to the target subtask to form a structured task data packet, which is sent to the target unmanned device through a communication link. After receiving the task data packet, the target unmanned device parses and verifies it through the task management module, extracts key job information, and sends the task request to the job scheduling module of the target unmanned device to complete the corresponding target subtask.
[0063] Reference Figure 2The present application also provides a multi-type unmanned equipment collaborative scheduling device, which is a server, and the server includes: an acquisition module 201 and a processing module 202, wherein: the acquisition module 201 is used to obtain a preset unmanned equipment file, which includes various types of unmanned equipment and the corresponding operation types and operation efficiencies of the unmanned equipment; the acquisition module 201 is also used to obtain multiple park pictures; the processing module 202 is used to extract features from the park pictures to obtain the green plant maintenance and sanitation conditions of the park; the processing module 202 is also used to generate multiple environmental maintenance tasks based on the green plant maintenance and sanitation conditions; the processing module 202 is also used to decompose the target environmental maintenance task to obtain multiple target subtasks, and the target environmental maintenance task is any one of the multiple environmental maintenance tasks; the processing module 202 is also used to assign corresponding target unmanned equipment to each target subtask according to the operation type and operation efficiency; the processing module 202 is also used to send each target subtask to the corresponding target unmanned equipment, so that each target unmanned equipment can complete the corresponding target subtask.
[0064] In one possible implementation, the processing module 202 performs feature extraction on the park image to obtain the green plant maintenance status and sanitary status of the park, specifically including: the processing module 202 performs region extraction on the park image to identify the green plant area and road area of the park; the processing module 202 calculates the corresponding green plant coverage rate for the green plant area; the processing module 202 compares the green plant coverage rate with a preset health threshold to obtain the green plant maintenance status of the park; the processing module 202 performs image recognition on the road area to obtain the corresponding health hazard target and the health hazard target type and quantity distribution corresponding to the health hazard target; the processing module 202 determines the sanitary status of the park according to the health hazard target type and quantity distribution.
[0065] In a possible implementation, the processing module 202 calculates the corresponding green plant coverage rate for the green plant area, specifically including: the processing module 202 counts the number of green vegetation pixels in the green plant area; the processing module 202 calculates the ratio of the number of green vegetation pixels to the total number of pixels in the green plant area to obtain the green plant coverage rate.
[0066] In one possible implementation, the green plant maintenance conditions include healthy and unhealthy. The processing module 202 compares the green plant coverage rate with a preset health threshold to obtain the green plant maintenance conditions of the park, specifically including: if the processing module 202 determines that the green plant coverage rate is greater than the preset health threshold, then the green plant maintenance condition of the park is determined to be healthy; if the processing module 202 determines that the green plant coverage rate is less than or equal to the preset health threshold, then the green plant maintenance condition of the park is determined to be unhealthy.
[0067] In a possible implementation, the processing module 202 determines the sanitary condition of the park according to the type and quantity distribution of the sanitary hazard target, specifically including: the processing module 202 determines the sanitary hazard level corresponding to the sanitary hazard target type in a preset sanitary hazard table according to the sanitary hazard target type, and the preset sanitary hazard table includes the correspondence between the sanitary hazard target type and the sanitary hazard level; the processing module 202 calculates the density value of the sanitary hazard target in each square meter of the road area, and determines the density level corresponding to the density value; the processing module 202 determines the sanitary condition according to the sanitary hazard level and the density level.
[0068] In a possible implementation, the processing module 202 decomposes the target environment maintenance task to obtain multiple target sub-tasks, specifically including: the processing module 202 determines a decomposition rule corresponding to the task type in the preset task decomposition rule according to the task type of the target environment maintenance task; the processing module 202 decomposes the target environment maintenance task into multiple target sub-tasks according to the decomposition rule; wherein the preset task decomposition rule includes the correspondence between the task type and the decomposition rule.
[0069] In one possible implementation, the processing module 202 assigns corresponding target unmanned equipment to each target subtask based on the job type and job efficiency, specifically including: the acquisition module 201 acquires the target task type and job content of each target subtask; the acquisition module 201 acquires the historical execution task list of the target unmanned equipment; the processing module 202 determines whether the target task type is in the historical execution task list; if the processing module 202 determines that the target task type is in the historical execution task list, the target unmanned equipment is assigned to the target subtask.
[0070] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0071] The present application also provides an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .
[0072] The communication bus 302 is used to realize the connection and communication between these components.
[0073] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.
[0074] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0075] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.
[0076] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a method for collaborative scheduling of multiple types of unmanned equipment.
[0077] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing a multi-type unmanned equipment collaborative scheduling method in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to 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 know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0078] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments.
[0079] 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.
[0080] In the several embodiments provided in this 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 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0081] The units described as separate components may or may not be physically separated, and the components shown 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 solution of this embodiment.
[0082] 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-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0083] If the integrated unit is implemented in the form of a software functional unit 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 execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.
[0084] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.
[0085] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. A method for collaborative scheduling of multiple types of unmanned equipment, characterized in that: The method comprises: Obtaining a preset unmanned equipment file, wherein the preset unmanned equipment file includes various types of unmanned equipment and the operation type and operation efficiency corresponding to the unmanned equipment; Get multiple park pictures; Extract features from the park image to obtain the green plant maintenance and sanitation conditions of the park; Generate multiple environmental maintenance tasks according to the green plant maintenance conditions and the sanitary conditions; Decomposing the target environment maintenance task to obtain a plurality of target subtasks, wherein the target environment maintenance task is any one of the plurality of environment maintenance tasks; According to the operation type and the operation efficiency, assigning corresponding target unmanned equipment to each of the target subtasks; Each of the target subtasks is sent to the corresponding target unmanned equipment so that each of the target unmanned equipment can complete the corresponding target subtask.
2. The method according to claim 1, characterized in that The feature extraction of the park image to obtain the green plant maintenance and sanitary conditions of the park specifically includes: Performing region extraction on the park image to identify the green plant area and road area of the park; For the green plant area, calculate the corresponding green plant coverage rate; Compare the green plant coverage rate with a preset health threshold to obtain the green plant maintenance status of the park; Performing image recognition on the road area to obtain corresponding health hazard targets and health hazard target types and quantity distribution corresponding to the health hazard targets; The sanitary condition of the park is determined according to the target type of sanitary hazard and the quantity distribution.
3. The method according to claim 2, characterized in that The calculating of the corresponding green plant coverage rate for the green plant area specifically includes: Counting the number of green vegetation pixels in the green plant area; The ratio of the number of green vegetation pixels to the total number of pixels in the green plant area is calculated to obtain the green plant coverage rate.
4. The method according to claim 2, characterized in that: The green plant maintenance conditions include healthy and unhealthy. The green plant coverage rate is compared with a preset health threshold to obtain the green plant maintenance conditions of the park, which specifically includes: If it is determined that the green plant coverage rate is greater than the preset health threshold, then the green plant maintenance condition of the park is determined to be healthy; If it is determined that the green plant coverage rate is less than or equal to the preset health threshold, then the green plant maintenance condition of the park is determined to be unhealthy.
5. The method according to claim 2, characterized in that: Determining the sanitary condition of the park according to the sanitary hazard target type and the quantity distribution specifically includes: According to the health hazard target type, determining the health hazard level corresponding to the health hazard target type in a preset health hazard table, wherein the preset health hazard table includes a correspondence between the health hazard target type and the health hazard level; Calculate the density value of the sanitary hazard target in each square meter of the road area, and determine the density level corresponding to the density value; The sanitary condition is determined according to the sanitary hazard level and the density level.
6. The method according to claim 1, characterized in that The target environment maintenance task is decomposed to obtain multiple target subtasks, including: According to the task type of the target environment maintenance task, determining a decomposition rule corresponding to the task type in the preset task decomposition rules; According to the decomposition rule, the target environment maintenance task is decomposed into a plurality of target subtasks; wherein the preset task decomposition rule includes a correspondence between task types and decomposition rules.
7. The method according to claim 1, characterized in that The allocating corresponding target unmanned equipment to each target subtask according to the operation type and the operation efficiency specifically includes: Obtain the target task type and job content of each target subtask; Obtain a historical execution task list of the target unmanned equipment; Determine whether the target task type is in the historical execution task list; If it is determined that the target task type is in the historical execution task list, the target unmanned equipment is allocated to the target subtask.
8. A multi-type unmanned equipment collaborative scheduling device, characterized in that: The device comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire a preset unmanned equipment file, wherein the preset unmanned equipment file includes various types of unmanned equipment and the operation type and operation efficiency corresponding to the unmanned equipment; The acquisition module (201) is also used to acquire multiple park pictures; The processing module (202) is used to extract features from the park image to obtain the maintenance and sanitation conditions of the green plants in the park; The processing module (202) is further used to generate a plurality of environmental maintenance tasks according to the green plant maintenance conditions and the sanitary conditions; The processing module (202) is further used to decompose the target environment maintenance task to obtain a plurality of target subtasks, wherein the target environment maintenance task is any one of the plurality of environment maintenance tasks; The processing module (202) is further used to allocate a corresponding target unmanned equipment to each target subtask according to the operation type and the operation efficiency; The processing module (202) is further used to send each of the target subtasks to the corresponding target unmanned equipment, so that each of the target unmanned equipment completes the corresponding target subtask.
9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.
