An electric control scheduling method and system of a cleaning task whole-process monitoring system and a medium

Abstract

The application provides an electric control scheduling method and system of a cleaning task whole-process monitoring system and a medium, and belongs to the technical field of electric control scheduling; the method comprises the following steps: collecting multi-modal environment data of a cleaning area, and constructing a digital twin of the cleaning area; generating a dirt risk heat map according to dirt distribution data, and generating a candidate cleaning strategy; matching the cleaning task instruction information and the candidate cleaning strategy to obtain an optimal cleaning strategy, and generating electric control scheduling scheme information according to the optimal cleaning strategy; collecting the running state data of a cleaning device and the real-time environment data of the cleaning area in real time; performing real-time analysis on the running state data of the cleaning device and the real-time environment data of the cleaning area to obtain cleaning effect information, and adjusting the electric control scheduling scheme information according to the cleaning effect information; through real-time monitoring and dynamic adjustment, equipment abnormalities and cleaning effect substandard problems can be found in time, the scheduling scheme can be adjusted quickly, cleaning task delays can be avoided, and cleaning efficiency and quality can be improved.

Description

Technical Field

[0001] This application relates to the field of electrical control and scheduling technology, and more specifically, to an electrical control and scheduling method, system, and medium for a full-process monitoring system for cleaning tasks. Background Technology

[0002] With the intelligent development of the cleaning industry, cleaning tasks are becoming increasingly complex. Whether in commercial complexes, industrial parks, or public areas, higher demands are being placed on cleaning efficiency, quality, and scheduling rationality. Currently, existing electronic scheduling methods for cleaning tasks mostly employ fixed paths or manual scheduling, which have several shortcomings: Firstly, they cannot perceive real-time environmental changes in the cleaning area (such as dirt distribution and fluctuations in pedestrian density), resulting in a lack of dynamic adaptability in scheduling plans and easily leading to problems such as untimely cleaning, equipment idleness, or operational conflicts. Secondly, they lack effective monitoring of the entire cleaning process, making it impossible to accurately determine the operating status and cleaning effect of cleaning equipment, hindering real-time optimization of scheduling plans, and failing to effectively utilize the data from the entire cleaning process to provide reliable support for subsequent scheduling. Furthermore, existing scheduling methods often only consider cleaning efficiency, neglecting multiple objectives such as operating costs and personnel interference, resulting in low scheduling efficiency and failing to meet the full-process management needs of cleaning tasks in complex scenarios. Summary of the Invention

[0003] The purpose of this application is to provide an electronic control scheduling method, system, and medium for a full-process monitoring system for cleaning tasks. Through real-time monitoring and dynamic adjustment, it can promptly detect equipment abnormalities and substandard cleaning results, and quickly adjust the scheduling plan to avoid delays in cleaning tasks and improve cleaning efficiency and quality.

[0004] This application embodiment also provides an electronic control scheduling method for a full-process monitoring system for cleaning tasks, including: collecting multimodal environmental data of the cleaning area and constructing a digital twin of the cleaning area, wherein the multimodal environmental data includes environmental image data, dirt distribution data and human flow density data; A dirt risk heat map is generated based on dirt distribution data. The dirt risk heat map is then input into a digital twin to generate candidate cleaning strategies. The candidate cleaning strategies are then dynamically corrected based on the pedestrian density data to obtain the corrected candidate cleaning strategies. The cleaning task instruction information is obtained, and the cleaning task instruction information is matched with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy. The electronic control scheduling scheme information is generated based on the optimal cleaning strategy. The cleaning task instruction information includes cleaning area parameters, cleaning standard parameters, cleaning time limit parameters, and cleaning equipment configuration parameters. The system controls the cleaning equipment to perform cleaning tasks based on the electronic control scheduling scheme information, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area. The system performs real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information. It then determines whether the cleaning effect information meets the set conditions. If not, it adjusts the electronic control scheduling scheme. If it does, it generates a cleaning task scheduling report.

[0005] Optionally, in the electronic control scheduling method of the cleaning task end-to-end monitoring system described in this application embodiment, collecting multimodal environmental data of the cleaning area and constructing a digital twin of the cleaning area specifically includes: The system uses high-definition cameras within the cleaning area to capture panoramic and partial images of the area in real time. Image features are extracted from panoramic and local images. Based on these image features, information on the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls are captured to obtain environmental image data. Based on infrared sensing equipment, water quality sensors and image recognition algorithms, information on the location, type, degree of pollution and diffusion trend of dirt in the clean area is collected to obtain dirt distribution data. Based on infrared thermal imaging sensors and video frame analysis algorithms, real-time information on the number of people, flow direction, and degree of aggregation in different areas of the clean area is collected, and the trend of changes in people flow is dynamically captured to obtain people density data. Based on environmental image data, dirt distribution data, and pedestrian density data, a 3D model is generated to create a data twin of the clean area.

[0006] Optionally, in the electronically controlled scheduling method of the cleaning task full-process monitoring system described in this application embodiment, the dynamic correction of the candidate cleaning strategy based on the pedestrian density data specifically includes: Based on the analysis of the pedestrian density data, the flow direction information is analyzed. Based on the pedestrian flow direction information and obstacle distribution information, the trend of pedestrian gathering and traffic pressure changes in each area within the future time window are predicted, and dynamic pedestrian flow prediction information is generated. Based on the dynamic pedestrian flow prediction information, high-interference areas and low-interference time periods for cleaning operations are identified, and obstacle avoidance operation timing constraint information is generated. The candidate cleaning strategy is modified by using the obstacle avoidance operation timing constraint information, and the operation path planning and operation timing arrangement are adjusted to obtain the modified cleaning strategy.

[0007] Optionally, in the electronic control scheduling method of the cleaning task end-to-end monitoring system described in this application embodiment, a dirt risk heat map is generated based on dirt distribution data, and the dirt risk heat map is input into a digital twin to generate candidate cleaning strategies, specifically including: Obtain data on the distribution of dirt and grime, and establish a dirt and grime risk assessment system based on the data, classifying it into multiple risk levels; Based on the dirt and filth risk assessment system, a risk assessment is conducted on the dirt and filth distribution data to obtain risk assessment information, and the corresponding risk level is matched according to the risk assessment information. The dirt risk level is associated with the dirt location information of the clean area based on the visualization rendering algorithm, and dirt risk distribution information is generated based on the color gradient to obtain a dirt risk heat map. The soiling risk heatmap is converted to a standard format. Input a standard-format dirt risk heatmap into the digital twin to generate candidate cleaning strategies.

[0008] Optionally, in the electronic control scheduling method of the cleaning task full-process monitoring system described in this application embodiment, the following steps are taken: obtaining cleaning task instruction information, matching the cleaning task instruction information with candidate cleaning strategies to obtain the optimal cleaning strategy, and generating electronic control scheduling scheme information based on the optimal cleaning strategy. Specifically, this includes: Obtain cleaning task instruction information, perform structured parsing of the cleaning task instruction information, extract cleaning area parameters, cleaning standard parameters, cleaning time limit parameters and cleaning equipment configuration parameters to obtain core instruction information; The core instruction information is matched with the candidate cleaning strategies to obtain a matching score; Candidate cleaning strategies are filtered based on matching scores to obtain the optimal cleaning strategy; Configure the electronic control scheme according to the optimal cleaning strategy, perform feasibility verification on the electronic control scheme, and obtain matching degree information; Compare the matching information with the set condition information; If the matching degree information meets the set conditions, then the power control scheduling scheme information is generated; If the matching information does not meet the set conditions, the electronic control scheme will be adjusted.

[0009] Optionally, in the electrical control scheduling method of the cleaning task full-process monitoring system described in this application embodiment, the cleaning equipment is controlled to perform cleaning tasks according to the electrical control scheduling scheme information, and the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area are collected in real time, specifically including: Initial cleaning equipment parameters are obtained, and the initial parameters of the cleaning equipment are adjusted according to the electrical control scheduling scheme to obtain the operating parameters of the cleaning equipment. The operation of the cleaning equipment is controlled according to the operating parameters of the cleaning equipment to obtain operating status data and real-time environmental data of the cleaning area; The operational status data and real-time environmental data are preprocessed to remove abnormal noise data, correct data deviations, and convert the data into a standardized format to obtain standard operational status data and standard environmental data.

[0010] Optionally, in the electrical control scheduling method of the cleaning task full-process monitoring system described in this application embodiment, the real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area is performed to obtain cleaning effect information, specifically including: The operating status data of the cleaning equipment and the real-time environmental data of the cleaning area are preprocessed to remove noise data and abnormal fluctuation data generated during transmission. The missing key data is supplemented based on historical data from the same period and operating data of similar equipment in the same area. Match the device operating status data at the same time point with the real-time environmental data of the corresponding area; The system analyzes the operating status data of a single cleaning device with the real-time environmental data of the current work area to obtain real-time dirt data, and then analyzes the cleaning effect information based on the real-time dirt data.

[0011] Secondly, embodiments of this application provide an electronic control scheduling system for a full-process monitoring system for cleaning tasks. The system includes a memory and a processor. The memory includes a program for an electronic control scheduling method for a full-process monitoring system for cleaning tasks. When the program for the electronic control scheduling method for a full-process monitoring system for cleaning tasks is executed by the processor, it performs the following steps: collecting multimodal environmental data of the cleaning area and constructing a digital twin of the cleaning area. The multimodal environmental data includes environmental image data, dirt distribution data, and human flow density data. A dirt risk heat map is generated based on dirt distribution data. The dirt risk heat map is then input into a digital twin to generate candidate cleaning strategies. The candidate cleaning strategies are then dynamically corrected based on the pedestrian density data to obtain the corrected candidate cleaning strategies. The cleaning task instruction information is obtained, and the cleaning task instruction information is matched with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy. The electronic control scheduling scheme information is generated based on the optimal cleaning strategy. The cleaning task instruction information includes cleaning area parameters, cleaning standard parameters, cleaning time limit parameters, and cleaning equipment configuration parameters. The system controls the cleaning equipment to perform cleaning tasks based on the electronic control scheduling scheme information, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area. The system performs real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information. It then determines whether the cleaning effect information meets the set conditions. If not, it adjusts the electronic control scheduling scheme. If it does, it generates a cleaning task scheduling report.

[0012] Optionally, in the electronic control scheduling system of the cleaning task end-to-end monitoring system described in this application embodiment, multimodal environmental data of the cleaning area is collected to construct a digital twin of the cleaning area, specifically including: The system uses high-definition cameras within the cleaning area to capture panoramic and partial images of the area in real time. Image features are extracted from panoramic and local images. Based on these image features, information on the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls are captured to obtain environmental image data. Based on infrared sensing equipment, water quality sensors and image recognition algorithms, information on the location, type, degree of pollution and diffusion trend of dirt in the clean area is collected to obtain dirt distribution data. Based on infrared thermal imaging sensors and video frame analysis algorithms, real-time information on the number of people, flow direction, and degree of aggregation in different areas of the clean area is collected, and the trend of changes in people flow is dynamically captured to obtain people density data. Based on environmental image data, dirt distribution data, and pedestrian density data, a 3D model is generated to create a data twin of the clean area.

[0013] Thirdly, embodiments of this application also provide a computer-readable storage medium, which includes an electronic control scheduling method program for a full-process monitoring system for cleaning tasks. When the electronic control scheduling method program for a full-process monitoring system for cleaning tasks is executed by a processor, it implements the steps of the electronic control scheduling method for a full-process monitoring system for cleaning tasks as described in any of the above claims.

[0014] As can be seen from the above, the electronic control scheduling method, system, and medium of the full-process monitoring system for cleaning tasks provided in this application embodiment construct a digital twin of the cleaning area by collecting multimodal environmental data of the cleaning area; generate a dirt risk heat map based on dirt distribution data, input the dirt risk heat map into the digital twin to generate candidate cleaning strategies, dynamically correct the candidate cleaning strategies based on the pedestrian density data to obtain corrected candidate cleaning strategies; acquire cleaning task instruction information, match the cleaning task instruction information with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy, generate electronic control scheduling scheme information based on the optimal cleaning strategy; and generate electronic control scheduling scheme information based on the electronic control scheduling scheme. The system controls cleaning equipment to perform cleaning tasks and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area. It analyzes this data in real time to obtain cleaning effect information and determines whether the cleaning effect meets set conditions. If not, it adjusts the electronic control scheduling scheme; if it does, it generates a cleaning task scheduling report. Through real-time monitoring and dynamic adjustment, this invention can collect real-time operating status data of cleaning equipment and environmental data of the cleaning area, promptly detect equipment abnormalities and substandard cleaning effects, and quickly adjust the scheduling scheme to avoid cleaning task delays and improve cleaning efficiency and quality. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating the electronic control scheduling method of the cleaning task end-to-end monitoring system provided in this application embodiment; Figure 2 A flowchart illustrating the construction of a digital twin of the cleaning area for the electronic control scheduling method of the full-process monitoring system for cleaning tasks provided in this application embodiment; Figure 3 A flowchart illustrating the candidate cleaning strategy acquisition process of the electronic control scheduling method for the full-process monitoring system for cleaning tasks provided in this application embodiment. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0018] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an electrical control scheduling method for a cleaning task end-to-end monitoring system, as described in some embodiments of this application. This electrical control scheduling method for the cleaning task end-to-end monitoring system is used in a terminal device and includes the following steps: S101, Collect multimodal environmental data of the cleaning area and construct a digital twin of the cleaning area. The multimodal environmental data includes environmental image data, dirt distribution data and pedestrian density data. S102, Generate a dirt risk heat map based on dirt distribution data, input the dirt risk heat map into the digital twin, generate candidate cleaning strategies, dynamically correct the candidate cleaning strategies based on pedestrian density data, and obtain the corrected candidate cleaning strategies. S103, obtain cleaning task instruction information, match the cleaning task instruction information with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy, and generate electronic control scheduling scheme information based on the optimal cleaning strategy. The cleaning task instruction information includes cleaning area parameters, cleaning standard parameters, cleaning time limit parameters and cleaning equipment configuration parameters. S104, controls the cleaning equipment to perform cleaning tasks according to the electronic control scheduling scheme information, and collects the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area in real time; S105: Perform real-time analysis on the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information. Determine whether the cleaning effect information meets the set conditions. If not, adjust the electronic control scheduling scheme information. If it meets the conditions, generate a cleaning task scheduling report.

[0020] It should be noted that the candidate cleaning strategy is dynamically adjusted based on the pedestrian density data, specifically including: Based on the analysis of the pedestrian density data, the flow direction information is analyzed. Based on the pedestrian flow direction information and obstacle distribution information, the trend of pedestrian gathering and traffic pressure changes in each area within the future time window are predicted, and dynamic pedestrian flow prediction information is generated. Based on the dynamic pedestrian flow prediction information, high-interference areas and low-interference time periods for cleaning operations are identified, and obstacle avoidance operation timing constraint information is generated. The candidate cleaning strategy is modified by using the obstacle avoidance operation timing constraint information, and the operation path planning and operation timing arrangement are adjusted to obtain the modified cleaning strategy.

[0021] Specifically, pedestrian density data is injected into the constructed digital twin of the clean area. Combined with the obstacle distribution information and channel topology (such as corridor width, entrance and exit locations, corners, elevator entrances, etc.) in the digital twin, a time-series prediction algorithm (such as a short-term traffic prediction model based on LSTM) is used to predict the trend of pedestrian gathering and traffic pressure changes in each area within a preset time window (such as the next 5 minutes, 10 minutes, and 15 minutes), thereby generating dynamic pedestrian flow prediction information.

[0022] High-interference areas refer to areas where the expected pedestrian density will exceed a set threshold (e.g., more than 0.5 people per square meter) within a future time window, and where the main pedestrian flow direction passes through, or areas with high pedestrian traffic and complex flow patterns (e.g., entrances / exits, escalator entrances, and main passageway intersections). Cleaning operations in such areas are prone to work interruptions, reduced efficiency, or obstruction of pedestrian passage.

[0023] Low-interference periods refer to future time windows in which the population density in a certain area is expected to be lower than a set threshold (e.g., number of people per unit area < 0.1 people / m²), or the area is not within the coverage of the main direction of population flow, making it suitable for cleaning operations.

[0024] The timing constraints for obstacle avoidance operations specifically include: Prohibited work periods: Cleaning operations are prohibited in high-interference areas during peak pedestrian traffic hours; Recommended work window: During periods of low disruption, prioritize cleaning tasks in high-risk, dirty areas; Recommended operating direction: The operating direction of cleaning equipment should be consistent with the direction of pedestrian flow as much as possible, rather than going against it, in order to reduce conflicts and avoidance actions with pedestrian flow.

[0025] By making real-time adjustments to the aforementioned candidate cleaning strategies, cleaning equipment will not enter critical channels during periods of peak crowd density and flow. Instead, it will choose times when there is relatively little pedestrian traffic or when the flow direction is consistent with the work direction. This not only reduces the mutual interference between cleaning equipment and pedestrian traffic and decreases the frequency of equipment pauses to avoid crowds, but also improves cleaning efficiency.

[0026] like Figure 2 As shown in the embodiment of the present invention, collecting multimodal environmental data of a clean area and constructing a digital twin of the clean area specifically includes: The system uses high-definition cameras within the cleaning area to capture panoramic and partial images of the area in real time. Image features are extracted from panoramic and local images. Based on these image features, information on the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls are captured to obtain environmental image data. Based on infrared sensing equipment, water quality sensors and image recognition algorithms, information on the location, type, degree of pollution and diffusion trend of dirt in the clean area is collected to obtain dirt distribution data. Based on infrared thermal imaging sensors and video frame analysis algorithms, real-time information on the number of people, flow direction, and degree of aggregation in different areas of the clean area is collected, and the trend of changes in people flow is dynamically captured to obtain people density data. Based on environmental image data, dirt distribution data, and pedestrian density data, a 3D model is generated to create a data twin of the clean area.

[0027] It should be noted that the multimodal environmental data collected from the clean area includes: 1. Data Acquisition Trigger: After the electronic control dispatch terminal receives the cleaning task instruction, it synchronously starts the multimodal environmental data acquisition process. The acquisition range strictly matches the cleaning area parameters specified in the cleaning task instruction to ensure the relevance and effectiveness of the acquired data and avoid invalid data redundancy.

[0028] 2. Data Collection Content: The focus is on collecting three core multimodal data types to comprehensively cover key environmental information in cleaning scenarios, providing comprehensive data support for the construction of digital twins. (1) Environmental image data: High-definition cameras deployed in the cleaning area are used to collect panoramic and local images of the area in real time, focusing on capturing the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls, providing intuitive image data for subsequent dirt identification and path planning; (2) Dirt distribution data: By combining infrared sensing equipment, water quality sensors and image recognition algorithms, the specific location, type of dirt (such as dust, water stains, oil stains, etc.), degree of pollution and diffusion trend of dirt in the area are collected to form a standardized dirt data set; (3) Pedestrian density data: Through infrared thermal imaging sensors and video frame analysis technology, the number of people, flow direction and concentration in different areas of the cleaning area are collected in real time, and the trend of pedestrian flow changes is dynamically captured, providing data support for subsequent scheduling optimization and avoiding conflicts between operations and pedestrian flow.

[0029] 3. Data processing and transmission: Real-time preprocessing of the collected multimodal environmental data, removal of abnormal and noisy data, and standardization of data format conversion to ensure data consistency and accuracy; the preprocessed data is transmitted in real time to the electric control dispatch terminal and digital twin construction module via wireless communication (at least one of WiFi, Bluetooth, and LoRa) to achieve data synchronization and sharing.

[0030] Building a digital twin of a clean area includes: 1. Data preprocessing optimization: The multimodal environmental data transmitted to the digital twin construction module undergoes secondary fine processing, including data noise reduction, data fusion, and data completion. Environmental image data, dirt distribution data, and pedestrian density data are correlated and matched to form a standardized dataset that can be directly used for model building.

[0031] 2. Digital Twin Infrastructure Construction: Based on preprocessed multimodal environmental data, a virtual digital twin corresponding to the physical space of the cleaning area is constructed using 3D modeling technology. This virtual twin restores the core physical features of the area, such as building layout, obstacle location, passage distribution, and the area where cleaning equipment can operate, ensuring consistency between the virtual model and the actual cleaning area.

[0032] 3. Multimodal data injection: The processed dirt distribution data is transformed into a dirt risk heat map through visualization algorithms and accurately injected into the corresponding location of the digital twin to realize the visualization of dirt distribution and pollution level, making it easy to intuitively view the dirt status of the area; at the same time, real-time pedestrian density data is injected into the model to realize real-time synchronization of dynamic changes in pedestrian flow, so that the digital twin can dynamically reflect the actual environmental status of the clean area.

[0033] 4. Model Calibration and Debugging: After completing the basic setup and data injection, the parameters of the digital twin are calibrated. By comparing the environmental parameters, dirt distribution, and pedestrian flow status of the virtual model with those of the actual cleaning area, the model parameters are adjusted to ensure that the virtual model can accurately simulate the dynamic changes of the actual scene. At the same time, in combination with the multi-granularity simulation requirements, the response speed and simulation accuracy of the model are debugged to ensure that the digital twin can stably support the subsequent cleaning operation strategy effectiveness evaluation, path simulation and other operations.

[0034] 5. Model Update and Maintenance: Establish a dynamic update mechanism for the digital twin, receive the latest data transmitted by the multimodal environment acquisition module in real time, and update the distribution of dirt and grime, the status of people flow, etc. in the virtual model in real time to ensure the synchronization between the digital twin and the actual cleaning area, and provide continuous and reliable virtual scene support for the generation and adjustment of subsequent power control scheduling schemes.

[0035] like Figure 3 As shown, according to an embodiment of the present invention, a dirt risk heatmap is generated based on dirt distribution data. The dirt risk heatmap is then input into a digital twin to generate candidate cleaning strategies, specifically including: Obtain data on the distribution of dirt and grime, and establish a dirt and grime risk assessment system based on the data, classifying it into multiple risk levels; Based on the dirt and filth risk assessment system, a risk assessment is conducted on the dirt and filth distribution data to obtain risk assessment information, and the corresponding risk level is matched according to the risk assessment information. The dirt risk level is associated with the dirt location information of the clean area based on the visualization rendering algorithm, and dirt risk distribution information is generated based on the color gradient to obtain a dirt risk heat map. The soiling risk heatmap is converted to a standard format. Input a standard-format dirt risk heatmap into the digital twin to generate candidate cleaning strategies.

[0036] It should be noted that generating a soil contamination risk heatmap based on soil contamination distribution data includes: 1. Dirt Distribution Data Preprocessing: Standardized dirt distribution data is extracted from multimodal environmental data. The focus is on screening four core parameters: dirt location, dirt type, pollution level, and diffusion trend. Invalid and abnormally fluctuating data are removed, and missing dirt data is supplemented to ensure data integrity and accuracy. At the same time, different weight coefficients are assigned according to dirt type (dust, water stains, oil stains, etc.), with oil stains and stubborn stains, which are difficult to clean, having higher weights than dust and water stains, which are easy to clean.

[0037] 2. Classification of Contamination Risk Levels: Based on the pre-processed contamination distribution data, a contamination risk assessment system is established, classifying multiple risk levels (such as low risk, medium risk, high risk, and extremely high risk). The risk level is jointly determined by the degree of contamination, the diffusion trend, and the weighting coefficient: the more severe the contamination, the faster the diffusion trend, and the higher the weighting coefficient, the higher the contamination risk level. The threshold for classifying each risk level is clearly defined, forming standardized risk level determination rules to ensure the consistency of risk assessment.

[0038] 3. Heatmap Generation and Optimization: A visualization rendering algorithm is used to accurately correlate the level of dirt risk with the spatial location of the cleaned area, presenting the distribution of dirt risk using color gradients (e.g., blue = low risk, yellow = medium risk, orange = high risk, red = very high risk), generating a dirt risk heatmap. The heatmap is then optimized to clearly label the dirt risk level, dirt type, and core pollution parameters of each area, ensuring the intuitiveness and readability of the heatmap and facilitating the formulation of subsequent cleaning strategies.

[0039] Inputting the dirt risk heatmap into the digital twin includes: 1. Heatmap Format Adaptation: The generated dirt risk heatmap is converted into a standardized data format that can be recognized and adapted by the digital twin, ensuring that the spatial coordinates of the heatmap correspond accurately to the virtual spatial coordinates of the digital twin, and avoiding problems such as position offset and data misalignment.

[0040] 2. Precise Heat Map Injection: Through the digital twin and simulation module, the adapted dirt risk heat map is precisely injected into the completed digital twin of the clean area, achieving deep integration between the heat map and the virtual scene of the digital twin. During the injection process, it is ensured that the heat map can be updated in real time with the dirt distribution data. That is, when the multimodal environment acquisition module obtains new dirt distribution data and regenerates the heat map, the heat map in the digital twin can be updated synchronously to maintain consistency with the actual dirt situation.

[0041] 3. Injection Verification and Adjustment: After completing the heatmap injection, the injection effect is verified. The heatmap in the digital twin is compared with the actual dirt distribution in the clean area to check the coordinate matching degree and the accuracy of risk level presentation. If there is a deviation, the injection parameters and spatial coordinates of the heatmap are adjusted to ensure that the dirt risk heatmap can truly and accurately reflect the dirt distribution and risk level of the clean area, providing reliable support for subsequent cleaning strategy simulation evaluation.

[0042] Candidate cleaning strategies based on digital twins and heatmaps include: 1. Preparations for strategy generation: Utilize the multi-granularity simulation function of the digital twin and simulation module, using the dirt risk heat map as the core basis, and combine it with cleaning task instructions (cleaning standards, cleaning time limits, equipment configuration), pedestrian density data, and virtual scene parameters of the digital twin to clarify the core indicators of simulation evaluation (cleaning efficiency, cleaning effect, operating cost, and degree of pedestrian interference).

[0043] 2. Initial Cleaning Strategy Generation: Based on the risk level distribution of the dirt risk heat map, multiple initial cleaning strategies are generated, with the core principle of "prioritizing high-risk areas, coordinating the allocation of resources in areas of similar risk, and avoiding densely populated areas": For extremely high-risk and high-risk areas, priority is given to allocating equipment with strong cleaning capabilities and high efficiency, and the shortest operation path is planned; for medium-risk and low-risk areas, equipment resources are reasonably allocated, taking into account both operational efficiency and cost; and by combining pedestrian density data, operation times in areas with high pedestrian traffic are avoided to reduce conflicts between operations and pedestrian flow.

[0044] 3. Multi-granularity simulation evaluation: Input multiple initial cleaning strategies into the digital twin and start strategy-level simulation and task-level simulation: The strategy-level simulation comprehensively evaluates the overall effectiveness (cleaning effect achievement rate, operating cost, and human flow interference coefficient) of each initial strategy and selects candidate strategies with higher effectiveness evaluation scores; the task-level simulation performs fine-grained simulation of the candidate strategies, simulating the operation path, execution time, energy consumption, and cleaning effect of the cleaning equipment, and outputs detailed simulation result data, including the advantages and disadvantages of each strategy.

[0045] 4. Candidate Strategy Screening and Optimization: Based on simulation results, compare the core indicators of each candidate strategy, such as cleaning effect, operating cost, and degree of human interference. Eliminate strategies with low efficiency or obvious defects (such as path conflicts or failure to meet cleaning standards). Optimize and adjust the remaining candidate strategies, such as optimizing the operation sequence in high-risk areas, adjusting equipment allocation schemes, and optimizing operation paths. Finally, form 2-3 sets of candidate cleaning strategies with optimal efficiency and adapted to the actual cleaning scenario, providing core references for the generation of subsequent dynamic electronic control scheduling schemes.

[0046] According to an embodiment of the present invention, cleaning task instruction information is obtained, and the cleaning task instruction information is matched with candidate cleaning strategies to obtain the optimal cleaning strategy. Then, an electronic control scheduling scheme is generated based on the optimal cleaning strategy. Specifically, this includes: Obtain cleaning task instruction information, perform structured parsing of the cleaning task instruction information, extract cleaning area parameters, cleaning standard parameters, cleaning time limit parameters and cleaning equipment configuration parameters to obtain core instruction information; The core instruction information is matched with the candidate cleaning strategies to obtain a matching score; Candidate cleaning strategies are filtered based on matching scores to obtain the optimal cleaning strategy; Configure the electronic control scheme according to the optimal cleaning strategy, perform feasibility verification on the electronic control scheme, and obtain matching degree information; Compare the matching information with the set condition information; If the matching degree information meets the set conditions, then the power control scheduling scheme information is generated; If the matching information does not meet the set conditions, the electronic control scheme will be adjusted.

[0047] It should be noted that obtaining cleaning task instruction information includes: 1. Command Acquisition Trigger: The electronic control dispatch terminal receives cleaning task commands issued by the upper-level system, or the staff manually enters cleaning task commands through the terminal, triggering the command parsing and information extraction process to ensure the timeliness and accuracy of command acquisition.

[0048] 2. Core Information Extraction: The cleaning task instructions are structured and parsed to extract four core instruction information points, clarifying the core requirements of the cleaning task and providing a clear basis for subsequent strategy matching and scheduling scheme generation. Specifically, this includes: (1) Cleaning area parameters: Extract parameters such as the specific range of the cleaning area, area type (e.g., commercial complex, industrial park, public corridor, etc.), distribution of obstacles in the area, and boundaries of the workable area to clarify the spatial constraints of the cleaning operation; (2) Cleaning standard parameters: Extract the cleaning standards for each area, including the dirt residue threshold, cleaning coverage, and cleaning precision (such as the floor stain removal rate and wall cleanliness), and clarify the core criteria for judging the cleaning effect; (3) Cleaning time limit parameters: Extract the total completion time limit of the cleaning task and the segmented completion time limit of each area, clarify the time constraints, and ensure that the cleaning task is completed within the specified time; (4) Cleaning equipment configuration parameters: Extract the types, quantities, performance parameters (such as cleaning efficiency, energy consumption, cleaning mode, and operating range) of the adjustable cleaning equipment, and the current status of the equipment (idle, under maintenance, or in operation) to clarify the equipment resource constraints.

[0049] 3. Command Information Verification and Standardization: Verify the extracted cleaning task command information, check the completeness and accuracy of the information, remove invalid information and correct erroneous parameters; convert the verified command information into a standardized format to be consistent with the format of candidate cleaning strategies and digital twin parameters to ensure a smooth subsequent matching process.

[0050] The optimal cleaning strategy is obtained by matching the cleaning task instruction information with the candidate cleaning strategies, including: 1. Matching index determination: Based on the four core parameters of the cleaning task instruction as constraints and combined with the simulation results data of candidate cleaning strategies, the core indicators for matching evaluation are determined, including the matching degree of cleaning effect achievement, time adaptability, equipment resource adaptability, operation cost adaptability, and pedestrian interference adaptability. Each indicator is assigned a corresponding weight according to its importance (the matching degree of cleaning effect achievement has the highest weight, followed by time adaptability).

[0051] 2. Generate matching scores one by one: Match each group of candidate cleaning strategies with the cleaning task instruction information one by one, and calculate the comprehensive matching score for each group of strategies: (1) Cleaning effect matching degree: Compare the simulated cleaning effect of the candidate strategy (such as dirt removal rate, cleaning coverage rate) with the cleaning standard parameters in the instruction, calculate the matching percentage, the higher the percentage, the higher the score; (2) Time fit: Compare the simulation execution time of the candidate strategy with the cleaning time limit parameter in the instruction to ensure that the execution time does not exceed the specified time limit, and the closer the time is to the optimal time limit, the higher the score; (3) Equipment resource adaptability: Compare the equipment type and quantity required by the candidate strategy with the cleaning equipment configuration parameters in the instruction to check whether the equipment resources are sufficient and whether the equipment performance meets the strategy requirements. The higher the adaptability, the higher the score. (4) Cost adaptation: Combine the cost control requirements implied in the instructions (such as energy consumption limit and water consumption limit), compare the simulated cost of the candidate strategies. The lower the cost and the higher the limit, the higher the score. (5) Adaptability to pedestrian interference: Compare the operation sequence, path and instructions of the candidate strategies with the pedestrian-related requirements of the clean area (such as avoiding peak pedestrian hours). The lower the degree of interference, the higher the score.

[0052] 3. Optimal Cleaning Strategy Selection: Based on the comprehensive matching score of each group of candidate strategies, the strategy with the highest score is selected as the optimal cleaning strategy. If multiple strategies have the same score, the core indicators are further compared (prioritizing the matching degree of cleaning effect and time adaptability) to determine the unique optimal cleaning strategy. At the same time, the optimal cleaning strategy is finally verified by combining the virtual simulation results of the digital twin to ensure that it has no path conflicts, reasonable equipment scheduling, and can be directly used for the generation of subsequent power control scheduling schemes.

[0053] The information generated based on the optimal cleaning strategy includes: 1. Scheduling scheme framework construction: Taking the optimal cleaning strategy as the core, and combining cleaning task instruction information, multimodal environmental data (human flow density, dirt distribution) and cleaning equipment configuration parameters, the core framework of the electronic control scheduling scheme is built, clarifying the core content of the scheme, and ensuring the integrity and executability of the scheme.

[0054] 2. Core Scheduling Information Generation: Based on the optimal cleaning strategy, specific information for the electronic control scheduling scheme is generated, focusing on four core components: (1) Equipment allocation information: Clearly define the specific working area and tasks of each cleaning equipment, and allocate corresponding cleaning tasks based on the equipment performance parameters (e.g., allocate equipment with strong cleaning capabilities to high-risk dirty areas) to ensure the rational use of equipment resources and avoid idleness or overload. (2) Operation path information: Based on the virtual scene of the digital twin, optimize the operation path in the optimal cleaning strategy, plan the optimal operation path of each device, avoid obstacles and densely populated areas, shorten the operation distance, and improve cleaning efficiency; clarify the starting point, passing point, ending point and operation sequence of the path to ensure that there are no conflicts in the path; (3) Cleaning mode and parameter information: Based on the type and degree of dirt in the cleaning area (in conjunction with the dirt risk heat map), set the corresponding cleaning mode (such as high pressure cleaning, vacuuming, mopping, etc.) and cleaning parameters (such as cleaning pressure, vacuuming power, mopping speed) for each device to ensure that the cleaning effect meets the requirements of the instructions; (4) Collaborative operation sequence information: Clarify the start and end times of each cleaning equipment, plan the collaborative operation process, avoid path conflicts caused by multiple equipment operating in the same area at the same time, take into account the trend of changes in pedestrian flow, and reasonably arrange the operation sequence to reduce interference with personnel activities.

[0055] 3. Feasibility Verification of the Scheme: The feasibility verification function of the power control scheduling scheme generation module is invoked to perform a comprehensive verification of the generated power control scheduling scheme, including power constraint verification (ensuring that the equipment power meets the operation requirements), spatial constraint verification (ensuring that there are no obstacles blocking the operation path), conflict verification (ensuring that there are no path or timing conflicts in equipment operation), and capacity constraint verification (ensuring that the equipment load is within a reasonable range). If the verification fails, the scheduling scheme is adjusted accordingly (such as adjusting equipment allocation, optimizing operation paths, and adjusting operation timing) until the verification is passed.

[0056] 4. Standardized output of scheduling scheme: The electrical control scheduling scheme that has passed the feasibility verification will be transformed into a standardized instruction format that can be recognized by the electrical control execution unit of the cleaning equipment. The execution priority and parameter threshold of each instruction will be clearly defined. At the same time, a scheme description document will be generated, which will mark the core parameters, execution requirements and emergency adjustment rules of the scheme, providing support for subsequent scheme issuance, execution monitoring and dynamic adjustment.

[0057] According to an embodiment of the present invention, the cleaning equipment is controlled to perform cleaning tasks based on the electronic control scheduling scheme information, and the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area are collected in real time, specifically including: Initial cleaning equipment parameters are obtained, and the initial parameters of the cleaning equipment are adjusted according to the electrical control scheduling scheme to obtain the operating parameters of the cleaning equipment. The operation of the cleaning equipment is controlled according to the operating parameters of the cleaning equipment to obtain operating status data and real-time environmental data of the cleaning area; The operational status data and real-time environmental data are preprocessed to remove abnormal noise data, correct data deviations, and convert the data into a standardized format to obtain standard operational status data and standard environmental data.

[0058] It should be noted that the issuance of the power control dispatch plan and equipment start-up control include: Preparation for plan issuance: The scheduling execution and monitoring module extracts the standardized electronic control scheduling plan that has passed the feasibility verification, sorts and organizes the instructions according to the type of cleaning equipment and the work area, and clarifies the corresponding work instructions (work path, cleaning mode, parameters, and timing) for each piece of equipment to ensure the compatibility of the instructions with the equipment's electronic control execution unit. Wireless command delivery: The classified scheduling commands are synchronously delivered to the electronic control execution units of each cleaning device via at least one wireless communication method, such as WiFi, Bluetooth, or LoRa. The delivery status is fed back in real time during the delivery process to ensure that each device successfully receives the command. For devices that fail to receive the command, the command is re-delivered and communication faults are investigated to avoid command omissions. Equipment Start-up and Initialization: After receiving the instruction, the electrical control execution unit of each cleaning equipment automatically starts the equipment initialization process, checks its own equipment parameters against the scheduling instruction requirements (such as cleaning mode and parameter thresholds), and completes the equipment self-check (checking power and cleaning component status). After the self-check passes, the equipment starts at the start time set by the instruction and enters the standby state. If the self-check fails (such as insufficient power or component failure), the abnormal information is immediately reported to the scheduling execution and monitoring module, triggering the subsequent adjustment process. Job start control: The scheduling execution and monitoring module synchronously links with the digital twin to synchronize the start status of each device in real time. By comparing the collaborative operation sequence with the electrical control scheduling plan, it controls each device to start cleaning operations in a preset order and path, ensuring that there are no conflicts in the collaborative operation of multiple devices and strictly following the requirements of the scheduling plan. Real-time control of cleaning equipment operation includes: Real-time path and mode control: The scheduling execution and monitoring module compares the actual working path of the equipment with the preset path of the scheduling plan in real time. If a path deviation occurs (such as avoiding sudden obstacles), a path adjustment command is immediately issued to ensure that the equipment returns to the preset path. At the same time, the cleaning mode and parameter execution status are monitored in real time. Based on the real-time environmental changes in the cleaning area (such as the degree of dirt exceeding expectations), the cleaning parameters are fine-tuned (such as increasing the cleaning pressure) to ensure that the cleaning effect meets the standards. Collaborative operation management: Real-time monitoring of the operation sequence and area of ​​multiple devices. If problems such as overlapping operations or path conflicts occur, the operation sequence or path of the relevant devices will be adjusted immediately to avoid affecting operation efficiency. Real-time data on pedestrian density will be synchronized. If pedestrian flow suddenly gathers in a certain area, instructions to suspend operations or adjust the operation sequence will be issued to reduce interference with personnel activities. Emergency control and handling: In response to emergencies during operation (such as equipment failure or sudden dirt and grime), the scheduling execution and monitoring module responds immediately, suspends the operation of relevant equipment, issues emergency handling instructions (such as activating backup equipment or adjusting the operation scope), and simultaneously updates the equipment status and environmental status in the digital twin to ensure the orderly progress of the operation. Real-time data collection of cleaning equipment operating status includes: Clearly defined data collection parameters: Clearly define the core operating status data to be collected, covering key indicators of the entire equipment operation process, including: equipment operating status (normal, fault, paused), remaining power and consumption rate, wear status of cleaning components (such as brush head wear), cleaning mode and real-time parameters, operation progress (completed area, remaining area), energy consumption and water consumption, and equipment operation fault codes (if any). Data collection method and frequency: The cleaning equipment collects real-time operating status data through built-in sensors (power sensor, energy consumption sensor, wear sensor, etc.) and electronic control execution unit. The collection frequency is synchronized with the equipment's operating rhythm (collected once every 30 seconds during normal operation and once every 5 seconds during fault conditions) to ensure the real-time and continuous nature of the data. Data preprocessing and transmission: The collected operational status data is preprocessed in real time to remove abnormal noise data, correct data deviations, and convert the data into a standardized format; it is transmitted in real time to the scheduling execution and monitoring module via wireless communication, and simultaneously backed up to the data archiving and analysis module to ensure that the data is not lost; for data that fails to be transmitted, it is automatically retransmitted and the transmission error log is recorded. Real-time environmental data collection in the clean area includes: Collection Scope and Parameters: The collection scope is consistent with the cleaning task area. The focus is on collecting three types of core real-time environmental data to evaluate the cleaning effect and environmental changes: First, real-time dirt data (the location and degree of remaining dirt in the cleaned area); second, real-time pedestrian flow data (the number of people in each area and their flow trend); and third, environmental disturbance data (such as sudden water stains, dust diffusion, etc.). Data collection equipment linkage: High-definition cameras, infrared sensors, water quality sensors, etc. deployed in the cleaning area are linked to collect real-time environmental data simultaneously; among them, real-time dirt data is obtained by combining image recognition algorithms with sensor data, and real-time pedestrian flow data is collected by video frame analysis and infrared thermal imaging technology to ensure data accuracy. Data association and transmission: The collected real-time environmental data is associated with the corresponding cleaning equipment's operational data (e.g., real-time dirt data of a certain equipment's operating area is associated with the equipment's cleaning parameters). After preprocessing, the data is transmitted in real-time to the scheduling execution and monitoring module, and simultaneously injected into a digital twin to achieve synchronous updates between the virtual scene and the actual environment. The data is also transmitted to the dynamic adjustment module to provide data support for subsequent adjustments to the scheduling scheme. Real-time data monitoring and feedback include: Real-time data monitoring: The scheduling and monitoring module builds a data monitoring panel to display the real-time operating status data of each cleaning equipment and the real-time environmental data of the cleaning area, and to mark abnormal data (such as equipment power being lower than the threshold or a certain area not meeting the dirt standard), so that staff can keep track of the operation status in real time. Anomaly feedback trigger: If the collected data exceeds the preset threshold (such as equipment failure, excessive dirt residue in the cleaning area, or crowd gathering exceeding the safe range), the anomaly feedback mechanism will be triggered immediately to send early warning information to the electronic control terminal and staff, and synchronously link with the dynamic adjustment module to provide accurate data basis for real-time adjustment of the scheduling plan, ensuring that the cleaning task is carried out in an orderly manner and the cleaning effect meets the standards.

[0059] According to an embodiment of the present invention, real-time analysis is performed on the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information, specifically including: The operating status data of the cleaning equipment and the real-time environmental data of the cleaning area are preprocessed to remove noise data and abnormal fluctuation data generated during transmission. The missing key data is supplemented based on historical data from the same period and operating data of similar equipment in the same area. Match the device operating status data at the same time point with the real-time environmental data of the corresponding area; The system analyzes the operating status data of a single cleaning device with the real-time environmental data of the current work area to obtain real-time dirt data, and then analyzes the cleaning effect information based on the real-time dirt data.

[0060] It should be noted that data preprocessing and association alignment include: Secondary data verification and noise reduction: Retrieve real-time data on the operating status of cleaning equipment and real-time environmental data of the cleaning area, and perform secondary fine preprocessing to remove noise data and abnormal fluctuation data generated during transmission (such as false alarm data from sensors and incomplete data caused by communication interruptions); for missing key data, combine historical data from the same period and operating data of similar equipment in the same area to complete the data, ensuring the integrity and accuracy of both types of data.

[0061] Data association and alignment: Using "time + space" as the dual core dimensions, the two types of data are accurately associated and aligned. In the time dimension, it ensures that the equipment operation status data at the same time point matches the real-time environmental data of the corresponding area one by one. In the spatial dimension, the operation status data of a single cleaning device (such as cleaning parameters and work progress) is bound to the real-time environmental data of the current working area of ​​the device (such as remaining dirt and area range), clarifying the correspondence between the equipment operation status and the area cleaning effect, laying the foundation for subsequent analysis.

[0062] 3. Data standardization and unification: The two types of data after association are converted into a unified standardized format, and the data units and threshold ranges are clearly defined (such as energy consumption units are unified to kWh, and the degree of pollution is unified to a 0-100 scale). This ensures that the data can be directly compared and calculated during the analysis process, and avoids analysis deviations caused by format differences.

[0063] Analyzing the effectiveness of equipment operations based on equipment operating status data includes: 1. Core Operating Parameter Analysis: This section focuses on analyzing the key operating parameters of the cleaning equipment to determine whether the equipment is operating normally and whether it has achieved its preset cleaning capacity, providing equipment-level support for evaluating cleaning effectiveness. (1) Cleaning mode and parameter compliance: Compare the actual cleaning mode and cleaning parameters (such as cleaning pressure and dust collection power) of the equipment with the preset values ​​of the electronic control scheduling scheme to determine whether the parameters meet the standards and whether they are dynamically adjusted according to the type of dirt. If the parameters deviate from the preset range, mark them as "abnormal equipment operation parameters" and preliminarily determine that the cleaning effect of the area may not meet the standards.

[0064] (2) Equipment operation stability analysis: Analyze the equipment operation status (normal / fault / pause), power consumption rate, and cleaning component wear status. If the equipment experiences frequent faults, insufficient power leading to operation interruption, or severe wear of cleaning components (such as excessive wear of brush head), it is determined that the equipment operation is not effective enough, and the cleaning effect of the corresponding area may be affected.

[0065] (3) Operation progress matching analysis: Combine the equipment operation progress data (completed area, remaining area) with the cleaning time limit parameters to determine whether the equipment operation efficiency meets the requirements; if the operation progress is behind the preset time sequence and it is not caused by human traffic interference or sudden failure, it is necessary to further analyze whether the cleaning effect meets the standard in combination with environmental data.

[0066] 2. Equipment Operation Effectiveness Rating: Based on the above analysis results, the operational effectiveness of each cleaning device will be rated (Excellent / Good / Average / Poor). Excellent indicates that the equipment is operating normally, parameters are matched, and the schedule is met; Poor indicates that the equipment frequently malfunctions, parameters deviate, and the schedule is seriously delayed. This rating will serve as an important reference for the comprehensive evaluation of cleaning effectiveness.

[0067] Based on real-time environmental data of the cleaned areas, the analysis of the area's cleanliness compliance includes: Real-time dirt data core analysis: Based on the cleaning standard parameters (dirt residue threshold, cleaning coverage, cleaning precision) in the cleaning task instructions, compare real-time dirt data to accurately determine the cleaning effect of each area. Dirt Residue Analysis: Extract real-time dirt location and pollution level data for each area and compare them with preset dirt residue thresholds. If the pollution level of a certain area is lower than the threshold, it is determined that the dirt residue in that area meets the standard; if it is higher than the threshold, it is marked as "dirt residue exceeds the standard", and the location, degree of exceedance, and type of dirt are clearly identified.

[0068] Cleaning coverage analysis: Combine the data on the scope of the cleaned area with the data on the equipment operation progress to calculate the actual cleaning coverage (area of ​​cleaned area / total area of ​​cleaned area), compare it with the preset cleaning coverage standard to determine whether the requirements are met; if the coverage does not meet the standard, analyze the reasons for the uncleaned areas (equipment not in place, interference from people, etc.), and check the corresponding equipment operation data to find the problem.

[0069] Cleaning precision analysis: For different types of dirt, the cleaning effect (such as the removal rate of floor stains and the cleanliness of walls) is analyzed by image recognition algorithm and compared with the preset cleaning precision standard. The analysis focuses on the removal effect of difficult-to-clean types such as oil stains and stubborn stains to determine whether the cleaning standard has been met.

[0070] Correction for environmental interference factors: Analyze the pedestrian flow data and environmental interference data (sudden water stains, dust diffusion) in the real-time environmental data to determine whether such factors affect the cleaning effect. If a certain area is shut down due to a sudden gathering of people, or if it is contaminated again after cleaning due to sudden dirt (such as water stains caused by pipe leaks), the cleaning standard of that area needs to be corrected. Distinguish between "inadequate equipment operation" and "sudden environmental interference" that lead to substandard cleaning effect to ensure accurate analysis results.

[0071] Regional cleaning effectiveness rating: Based on the analysis results of dirt residue, cleaning coverage, and cleaning accuracy, and combined with environmental interference correction, the cleaning effectiveness of each cleaning area is rated (meets standards / basically meets standards / does not meet standards), and the core shortcomings of the cleaning effectiveness of each area are identified (such as excessive dirt residue or insufficient coverage).

[0072] Comprehensive analysis generates complete cleaning effect information, including: 1. Two-dimensional comprehensive comparison: The equipment operation effectiveness rating and the regional cleaning effect rating are comprehensively compared to establish the correlation between "equipment operation - cleaning effect" - if the equipment operation effectiveness is excellent but the regional cleaning effect is not up to standard, the focus is on investigating environmental interference factors; if the equipment operation effectiveness is poor and the regional cleaning effect is not up to standard, it is determined to be caused by equipment operation problems, and the equipment or scheduling plan should be adjusted first.

[0073] 2. Core Information Extraction of Cleaning Effectiveness: Integrating all the above analysis results, standardized cleaning effectiveness information is generated, focusing on four core elements: (1) Overview of overall cleaning effect: Clarify the overall compliance rate of cleaning tasks (number of compliant areas / total number of areas), the distribution of non-compliant areas and the core reasons; (2) Details of cleaning effect by area: Mark the cleaning effect rating, dirt residue, cleaning coverage and cleaning accuracy of each area, and identify the shortcomings of each area; (3) Equipment impact analysis: Clarify the impact of the operating status of each cleaning equipment on the cleaning effect, and mark the equipment with poor operation effectiveness and the corresponding affected areas; (4) Optimization suggestions: Based on the analysis results, provide targeted optimization suggestions (such as adjusting the cleaning parameters of a certain equipment, performing secondary cleaning on areas that do not meet the standards, and handling equipment malfunctions).

[0074] 3. Data Synchronization and Feedback: The generated cleaning effect information is synchronized in real time to the scheduling execution and monitoring module, the dynamic adjustment module, and the electronic control terminal, and simultaneously injected into the digital twin to achieve a visual presentation of the cleaning effect; at the same time, areas that do not meet the standards and abnormal equipment are marked, providing accurate data support for the real-time adjustment of the subsequent electronic control scheduling plan and the advancement of cleaning tasks.

[0075] Secondly, embodiments of this application provide an electronic control scheduling system for a full-process monitoring system for cleaning tasks. The system includes: a memory and a processor. The memory includes a program for an electronic control scheduling method for a full-process monitoring system for cleaning tasks. When the program for the electronic control scheduling method for a full-process monitoring system for cleaning tasks is executed by the processor, it performs the following steps: collecting multimodal environmental data of the cleaning area and constructing a digital twin of the cleaning area. The multimodal environmental data includes environmental image data, dirt distribution data, and human flow density data. A dirt risk heat map is generated based on dirt distribution data. The dirt risk heat map is then input into a digital twin to generate candidate cleaning strategies. The candidate cleaning strategies are then dynamically corrected based on the pedestrian density data to obtain the corrected candidate cleaning strategies. Obtain cleaning task instruction information, match the cleaning task instruction information with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy, and generate electronic control scheduling scheme information based on the optimal cleaning strategy. The cleaning task instruction information includes cleaning area parameters, cleaning standard parameters, cleaning time limit parameters, and cleaning equipment configuration parameters. The system controls the cleaning equipment to perform cleaning tasks based on the electronic control scheduling scheme information, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area. The system performs real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information. It then determines whether the cleaning effect information meets the set conditions. If not, it adjusts the electronic control scheduling scheme. If it does, it generates a cleaning task scheduling report.

[0076] According to an embodiment of the present invention, multimodal environmental data of a clean area is collected to construct a digital twin of the clean area, specifically including: The system uses high-definition cameras within the cleaning area to capture panoramic and partial images of the area in real time. Image features are extracted from panoramic and local images. Based on these image features, information on the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls are captured to obtain environmental image data. Based on infrared sensing equipment, water quality sensors and image recognition algorithms, information on the location, type, degree of pollution and diffusion trend of dirt in the clean area is collected to obtain dirt distribution data. Based on infrared thermal imaging sensors and video frame analysis algorithms, real-time information on the number of people, flow direction, and degree of aggregation in different areas of the clean area is collected, and the trend of changes in people flow is dynamically captured to obtain people density data. Based on environmental image data, dirt distribution data, and pedestrian density data, a 3D model is generated to create a data twin of the clean area.

[0077] In summary, the present invention has the following beneficial effects: 1. Achieve closed-loop management and control of the entire cleaning task process, from task instruction acquisition and environmental data collection to scheduling plan generation, execution monitoring, dynamic adjustment, and data archiving and analysis, forming a complete electronic control scheduling link. This effectively solves the problems of fragmented cleaning scheduling and incomplete monitoring in existing technologies, and improves the control and management accuracy of cleaning tasks.

[0078] 2. By introducing digital twins and multi-granularity simulation technology, and combining multimodal environmental data to construct a virtual model of the clean area, the effectiveness of cleaning operation strategies can be evaluated in advance, avoiding blind scheduling. At the same time, the dirt risk heat map is injected into the virtual model to realize the visual control of dirt distribution, thereby improving the scientificity and rationality of the scheduling plan.

[0079] 3. A multi-objective dynamic programming optimization method is adopted to generate a dynamic electric control scheduling scheme, which takes into account multiple objectives such as net cleaning benefits, operating costs, and personnel interference. Compared with single-objective scheduling, it is more in line with the actual cleaning scenario requirements and can reduce operating costs and minimize the impact on personnel activities while ensuring cleaning effect.

[0080] 4. It has real-time monitoring and dynamic adjustment capabilities, and can collect real-time data on the operating status of cleaning equipment and the environmental data of the cleaning area. It can promptly detect equipment abnormalities and problems with substandard cleaning results, and quickly adjust the scheduling plan to avoid delays in cleaning tasks and improve cleaning efficiency and quality.

[0081] 5. By archiving and analyzing the data of the entire cleaning process, a scheduling report is generated to provide data support for the electronic scheduling of subsequent cleaning tasks, realize the iterative optimization of scheduling strategies, gradually improve the intelligence level of cleaning scheduling, and adapt to the cleaning task needs in different scenarios.

[0082] 6. The system modules have clear division of labor and work together efficiently. It uses wireless communication to realize the real-time transmission of scheduling instructions and data, adapts to the collaborative operation of multiple cleaning devices, and can be flexibly applied to various cleaning scenarios. It is highly practical and has good scalability.

[0083] A third aspect of the present invention provides a computer-readable storage medium including a program for an electrical control scheduling method of a cleaning task full-process monitoring system. When the program for the electrical control scheduling method of the cleaning task full-process monitoring system is executed by a processor, it implements the steps of the electrical control scheduling method of the cleaning task full-process monitoring system as described above.

[0084] This invention discloses an electronic control scheduling method, system, and medium for a full-process monitoring system for cleaning tasks. It constructs a digital twin of the cleaning area by collecting multimodal environmental data; generates a dirt risk heat map based on dirt distribution data, inputs the heat map into the digital twin, and generates candidate cleaning strategies; acquires cleaning task instruction information, matches the instruction information with the candidate strategies to obtain the optimal cleaning strategy, and generates an electronic control scheduling scheme based on the optimal strategy; controls cleaning equipment to execute cleaning tasks according to the scheduling scheme, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area; analyzes the operating status data and environmental data in real-time to obtain cleaning effect information, and determines whether the cleaning effect meets set conditions. If not, the scheduling scheme is adjusted; if it does, a cleaning task scheduling report is generated. This invention, through real-time monitoring and dynamic adjustment, can collect real-time operating status data of cleaning equipment and environmental data of the cleaning area, promptly detect equipment abnormalities and substandard cleaning effects, and quickly adjust the scheduling scheme to avoid cleaning task delays and improve cleaning efficiency and quality.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0086] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0087] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0088] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0089] Alternatively, if the integrated units of the present invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. An electronic control scheduling method for a full-process monitoring system for cleaning tasks, characterized in that, include: Collect multimodal environmental data of the clean area and construct a digital twin of the clean area. The multimodal environmental data includes environmental image data, dirt distribution data and pedestrian density data. A dirt risk heat map is generated based on dirt distribution data. The dirt risk heat map is then input into a digital twin to generate candidate cleaning strategies. The candidate cleaning strategies are then dynamically corrected based on the pedestrian density data to obtain the corrected candidate cleaning strategies. The cleaning task instruction information is obtained, and the cleaning task instruction information is matched with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy. The electronic control scheduling scheme information is generated based on the optimal cleaning strategy. The cleaning task instruction information includes cleaning area parameters, cleaning standard parameters, cleaning time limit parameters, and cleaning equipment configuration parameters. The system controls the cleaning equipment to perform cleaning tasks based on the electronic control scheduling scheme information, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area. The system performs real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information. It then determines whether the cleaning effect information meets the set conditions. If not, it adjusts the electronic control scheduling scheme. If it does, it generates a cleaning task scheduling report.

2. The electronic control scheduling method of the cleaning task full-process monitoring system according to claim 1, characterized in that, Collect multimodal environmental data of the clean area and construct a digital twin of the clean area, specifically including: The system uses high-definition cameras within the cleaning area to capture panoramic and partial images of the area in real time. Image features are extracted from panoramic and local images. Based on these image features, information on the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls are captured to obtain environmental image data. Based on infrared sensing equipment, water quality sensors and image recognition algorithms, information on the location, type, degree of pollution and diffusion trend of dirt in the clean area is collected to obtain dirt distribution data. Based on infrared thermal imaging sensors and video frame analysis algorithms, real-time information on the number of people, flow direction, and degree of aggregation in different areas of the clean area is collected, and the trend of changes in people flow is dynamically captured to obtain people density data. Based on environmental image data, dirt distribution data, and pedestrian density data, a 3D model is generated to create a data twin of the clean area.

3. The electronic control scheduling method of the cleaning task full-process monitoring system according to claim 2, characterized in that, The candidate cleaning strategy is dynamically adjusted based on the pedestrian density data, specifically including: Based on the analysis of the pedestrian density data, the flow direction information is analyzed. Based on the pedestrian flow direction information and obstacle distribution information, the trend of pedestrian gathering and traffic pressure changes in each area within the future time window are predicted, and dynamic pedestrian flow prediction information is generated. Based on the dynamic pedestrian flow prediction information, high-interference areas and low-interference time periods for cleaning operations are identified, and obstacle avoidance operation timing constraint information is generated. The candidate cleaning strategy is modified by using the obstacle avoidance operation timing constraint information, and the operation path planning and operation timing arrangement are adjusted to obtain the modified cleaning strategy.

4. The electrical control scheduling method of the cleaning task full-process monitoring system according to claim 3, characterized in that, A dirt risk heatmap is generated based on dirt distribution data. This heatmap is then input into a digital twin to generate candidate cleaning strategies, including: Obtain data on the distribution of dirt and grime, and establish a dirt and grime risk assessment system based on the data, classifying it into multiple risk levels; Based on the dirt and filth risk assessment system, a risk assessment is conducted on the dirt and filth distribution data to obtain risk assessment information, and the corresponding risk level is matched according to the risk assessment information. The dirt risk level is associated with the dirt location information of the clean area based on the visualization rendering algorithm, and dirt risk distribution information is generated based on the color gradient to obtain a dirt risk heat map. The soiling risk heatmap is converted to a standard format. Input a standard-format dirt risk heatmap into the digital twin to generate candidate cleaning strategies.

5. The electrical control scheduling method of the cleaning task full-process monitoring system according to claim 4, characterized in that, The process involves acquiring cleaning task instruction information, matching it with candidate cleaning strategies to obtain the optimal cleaning strategy, and generating an electronic control scheduling scheme based on the optimal cleaning strategy. This includes: Obtain cleaning task instruction information, perform structured parsing of the cleaning task instruction information, extract cleaning area parameters, cleaning standard parameters, cleaning time limit parameters and cleaning equipment configuration parameters to obtain core instruction information; The core instruction information is matched with the candidate cleaning strategies to obtain a matching score; Candidate cleaning strategies are filtered based on matching scores to obtain the optimal cleaning strategy; Configure the electronic control scheme according to the optimal cleaning strategy, perform feasibility verification on the electronic control scheme, and obtain matching degree information; Compare the matching information with the set condition information; If the matching degree information meets the set conditions, then the power control scheduling scheme information is generated; If the matching information does not meet the set conditions, the electronic control scheme will be adjusted.

6. The electrical control scheduling method of the cleaning task full-process monitoring system according to claim 5, characterized in that, The system controls the cleaning equipment to perform cleaning tasks based on the electronic control scheduling scheme information, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area, specifically including: Initial cleaning equipment parameters are obtained, and the initial parameters of the cleaning equipment are adjusted according to the electrical control scheduling scheme to obtain the operating parameters of the cleaning equipment. The operation of the cleaning equipment is controlled according to the operating parameters of the cleaning equipment to obtain operating status data and real-time environmental data of the cleaning area; The operational status data and real-time environmental data are preprocessed to remove abnormal noise data, correct data deviations, and convert the data into a standardized format to obtain standard operational status data and standard environmental data.

7. The electrical control scheduling method of the cleaning task full-process monitoring system according to claim 6, characterized in that, Real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area yields cleaning effect information, specifically including: The operating status data of the cleaning equipment and the real-time environmental data of the cleaning area are preprocessed to remove noise data and abnormal fluctuation data generated during transmission. The missing key data is supplemented based on historical data from the same period and operating data of similar equipment in the same area. Match the device operating status data at the same time point with the real-time environmental data of the corresponding area; The system analyzes the operating status data of a single cleaning device with the real-time environmental data of the current work area to obtain real-time dirt data, and then analyzes the cleaning effect information based on the real-time dirt data.

8. An electronic control and scheduling system for a full-process monitoring system of a cleaning task, characterized in that, The system includes a memory and a processor. The memory contains a program for an electronic control scheduling method for a full-process monitoring system of cleaning tasks. When the program for the electronic control scheduling method of the full-process monitoring system of cleaning tasks is executed by the processor, it performs the following steps: Collect multimodal environmental data of the clean area and construct a digital twin of the clean area. The multimodal environmental data includes environmental image data, dirt distribution data and pedestrian density data. A dirt risk heat map is generated based on dirt distribution data. The dirt risk heat map is then input into a digital twin to generate candidate cleaning strategies. The candidate cleaning strategies are then dynamically corrected based on the pedestrian density data to obtain the corrected candidate cleaning strategies. The cleaning task instruction information is obtained, and the cleaning task instruction information is matched with the corrected candidate cleaning strategies to obtain the optimal cleaning strategy. The electronic control scheduling scheme information is generated based on the optimal cleaning strategy. The cleaning task instruction information includes cleaning area parameters, cleaning standard parameters, cleaning time limit parameters, and cleaning equipment configuration parameters. The system controls the cleaning equipment to perform cleaning tasks based on the electronic control scheduling scheme information, and collects real-time operating status data of the cleaning equipment and real-time environmental data of the cleaning area. The system performs real-time analysis of the operating status data of the cleaning equipment and the real-time environmental data of the cleaning area to obtain cleaning effect information. It then determines whether the cleaning effect information meets the set conditions. If not, it adjusts the electronic control scheduling scheme. If it does, it generates a cleaning task scheduling report.

9. The electrical control and dispatching system of the full-process monitoring system for cleaning tasks according to claim 8, characterized in that, Collect multimodal environmental data of the clean area and construct a digital twin of the clean area, specifically including: The system uses high-definition cameras within the cleaning area to capture panoramic and partial images of the area in real time. Image features are extracted from panoramic and local images. Based on these image features, information on the physical layout of the area, the distribution of obstacles, and the surface condition of the ground and walls are captured to obtain environmental image data. Based on infrared sensing equipment, water quality sensors and image recognition algorithms, information on the location, type, degree of pollution and diffusion trend of dirt in the clean area is collected to obtain dirt distribution data. Based on infrared thermal imaging sensors and video frame analysis algorithms, real-time information on the number of people, flow direction, and degree of aggregation in different areas of the clean area is collected, and the trend of changes in people flow is dynamically captured to obtain people density data. Based on environmental image data, dirt distribution data, and pedestrian density data, a 3D model is generated to create a data twin of the clean area.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an electrical control scheduling method program for a full-process monitoring system for cleaning tasks. When the electrical control scheduling method program for a full-process monitoring system for cleaning tasks is executed by a processor, it implements the steps of the electrical control scheduling method for a full-process monitoring system for cleaning tasks as described in any one of claims 1 to 7.

Images