Self-adaptive control method of space environment improvement equipment and robot

Abstract

The invention relates to the technical field of air purification, and discloses a self-adaptive control method of space environment improvement equipment and a robot, which improve the cleaning effect and the air quality management level of a hotel room by integrating real-time air quality monitoring, dynamic cleaning path optimization and intelligent control technologies. Compared with a traditional fixed cleaning route method, the technical scheme has the advantages that the cleaning strategy can be flexibly adjusted according to the actual air environment condition of the room, various air pollution sources such as mites, dust and bacteria can be effectively dealt with, the cleaning route can be optimized, interference to the surrounding check-in room can be reduced, and in addition, through application of an intelligent algorithm, the cleaning efficiency is improved. According to the system, accurate and efficient cleaning operation can be achieved, so that the comfort degree and the satisfaction degree of guests are improved, a healthier indoor environment is provided, and the method is scientific, data-driven and capable of being flexibly adapted to a complex environment, and all-directional air quality improvement of hotel rooms is achieved.

Description

Technical Field

[0001] The present invention relates to the field of air purification technology, and more specifically, to an adaptive control method and a robot for space environment improvement equipment. Background Art

[0002] In existing hotel rooms, due to the long-term lack of effective cleaning and maintenance, the indoor air environment is poor. At the same time, the accumulation of dust not only affects the cleanliness of the room, but also may carry bacteria and viruses, further deteriorating the air quality. Although relevant content about air environment cleaning has appeared in the prior art, there are still certain problems in its application in the hotel room environment.

[0003] For example, the Chinese patent application with publication number CN113757829A provides a control method, electronic device and computer-readable storage medium for an air purifier. The patent automatically pushes the moving route for the air purifier to execute, and can cruise and purify multiple indoor space areas. The Chinese patent application with publication number CN102563801A provides an air purifier and a method for controlling its edge purification. By designing an optimized walking route, the air in a predetermined area can be effectively purified, and the purification efficiency can be improved under limited energy supply.

[0004] Although the above patents are all capable of designing corresponding cleaning routes to improve the efficiency of air cleaning, hotel rooms are different from ordinary environments. During the cleaning process, the impact on surrounding rooms should be considered, and the above cleaning routes are all pre-set and not optimized according to actual conditions.

[0005] In view of this, the present invention proposes an adaptive control method and a robot for space environment improvement equipment to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an adaptive control method and a robot for space environment improvement equipment.

[0007] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an adaptive control method for a space environment improvement device includes: Obtain the check-in registration data and room layout diagram corresponding to the target room, predetermine M candidate cleaning paths according to the room layout diagram, and calculate the cleaning coverage corresponding to each candidate cleaning path, where M is an integer greater than 0; The method for calculating the cleaning coverage corresponding to each selected cleaning path includes: Obtain a preset unit cleaning width, calculate a target product between the length of the selected cleaning path and the unit cleaning width, use the target product as the cleaning area, and use the ratio of the cleaning area to the total area of ​​the target room as the cleaning coverage; Determine the cleaning impact based on the check-in data, and determine the target cleaning path from M candidate cleaning paths according to the cleaning impact, cleaning coverage and genetic algorithm; The method for determining the cleaning impact based on check-in data includes: Determine Q occupied rooms according to the check-in registration data, obtain the barrier materials corresponding to the occupied rooms according to the room layout diagram, determine the corresponding cleaning impact factors according to the barrier materials, and use the average value of the cleaning impact factors as the cleaning impact degree; Acquire air environment data corresponding to the target room, calculate an air hazard coefficient according to the air environment data, obtain a cleaning action sequence according to the air hazard coefficient and a target cleaning path, and clean the target room according to the cleaning action sequence, wherein the air environment data includes an allergen concentration value, a particulate matter concentration value, and a microbial concentration value; Methods for calculating the air hazard factor based on air environment data include: AHC= ; Where AHC is the air hazard coefficient, is the microbial concentration value, is the particle concentration value, is the allergen concentration value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, is a logarithmic function with base 2.

[0008] Furthermore, the method of predetermining M to-be-selected cleaning paths according to the room layout diagram includes: A real-time image of the target room is obtained, a real-time layout map is obtained according to the real-time image, and the similarity between the real-time layout map and the room layout map is calculated. When the similarity is greater than a preset similarity threshold, a first cleaning path corresponding to the room layout map is obtained, and the first cleaning path is used as a candidate cleaning path. When the similarity is less than or equal to the preset similarity threshold, the real-time layout map is input into a pre-built path planning model to obtain a second cleaning path, and the second cleaning path is used as a candidate cleaning path.

[0009] Furthermore, the method for obtaining a real-time layout diagram according to a real-time image includes: Based on the edge detection algorithm, edge information in the real-time image is extracted, the outline of the object in the target room is extracted according to the edge information, the object outline is identified and the corresponding position information is determined, and the position information is represented according to the coordinate system of the room layout diagram to obtain the real-time layout diagram.

[0010] Furthermore, the method for constructing the path planning model includes: A sample data set is obtained, wherein the sample data set includes a historical layout diagram and a historical cleaning path, the sample data set is divided into a sample training set and a sample test set, a regression network is constructed, the historical layout diagram in the sample training set is used as input data of the regression network, the historical cleaning path in the sample training set is used as output data of the regression network, the regression network is trained to obtain an initial regression network for predicting a real-time cleaning path, the initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a path planning model.

[0011] Furthermore, the method of determining the target cleaning path from the M candidate cleaning paths according to the cleaning influence, the cleaning coverage and the genetic algorithm includes: The difference between the cleaning impact and the cleaning coverage is taken as the fitness value, and based on a genetic algorithm, the optimal target cleaning path is determined from M candidate cleaning paths with the goal of minimizing the fitness value.

[0012] Furthermore, the method for determining the optimal target cleaning path from the M candidate cleaning paths includes: S201: Taking M candidate cleaning paths as the initial population, and taking the difference between the cleaning influence and the cleaning coverage as the fitness function, calculating the fitness value of each individual in the population; S202: Adopt the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between the individuals, and select the individual with the smallest fitness value as the parent individual; S203: Repeat the selection process of S201-S202 until N parent individuals are selected, and then proceed to S204; S204: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals; S205: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population, ensuring that the size of the new population is still N; S206: The convergence threshold of the preset fitness value is CT. If the fitness value change of the optimal individual in the population of consecutive K generations is less than CT, the genetic algorithm terminates; S207: When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal cleaning path, which is used as the target cleaning path.

[0013] Furthermore, the method for obtaining the air environment data corresponding to the target room includes: Take any point of the target cleaning path as the coordinate origin, any sub-path of the target cleaning path as the X-axis, and the vertical direction of the arbitrary sub-path as the Y-axis to generate a detection coordinate system. In the detection coordinate system, generate R groups of detection environment data through the Markov random walk method, and use the R groups of detection environment data as air environment data.

[0014] Furthermore, the method for cleaning the target room according to the cleaning action sequence includes: The real-time location information of the space environment improvement equipment is obtained, and it is determined whether to stop moving according to the real-time location information. If so, the space environment improvement equipment deploys a corresponding cleaning robot, and the cleaning robot performs cleaning according to a preset cleaning route. The cleaning robot is arranged on one side of the space environment improvement equipment.

[0015] Furthermore, the method for cleaning the target room according to the cleaning action sequence also includes: When the target object needs to be cleaned, open the lock between the space environment improvement device and the cleaning robot, take out the corresponding cleaning robot from the space environment improvement device, then the space environment improvement device stops moving, aim the cleaning hole of the cleaning robot at the surface of the target object, and clean the target object.

[0016] Furthermore, an atmosphere light is provided on the top of the space environment improvement device, and the target image pre-stored in the database is projected onto the ceiling of the target room through the atmosphere light, and different target images can be switched by adjusting the atmosphere light.

[0017] In a second aspect, an adaptive control robot for a space environment improvement device is used to implement the adaptive control method for the space environment improvement device, comprising: Processing module: used to obtain the check-in registration data and room layout diagram corresponding to the target room, predetermine M candidate cleaning paths according to the room layout diagram, and calculate the cleaning coverage corresponding to each candidate cleaning path, where M is an integer greater than 0; The method for calculating the cleaning coverage corresponding to each selected cleaning path includes: Obtain a preset unit cleaning width, calculate a target product between the length of the selected cleaning path and the unit cleaning width, use the target product as the cleaning area, and use the ratio of the cleaning area to the total area of ​​the target room as the cleaning coverage; Optimization module: Determine the cleaning impact based on check-in data, and determine the target cleaning path from M candidate cleaning paths according to the cleaning impact, cleaning coverage and genetic algorithm; The method for determining the cleaning impact based on check-in data includes: Determine Q occupied rooms according to the check-in registration data, obtain the barrier materials corresponding to the occupied rooms according to the room layout diagram, determine the corresponding cleaning impact factors according to the barrier materials, and use the average value of the cleaning impact factors as the cleaning impact degree; Cleaning module: used to obtain the air environment data corresponding to the target room, calculate the air hazard coefficient according to the air environment data, obtain the cleaning action sequence according to the air hazard coefficient and the target cleaning path, and clean the target room according to the cleaning action sequence, wherein the air environment data includes allergen concentration values, particulate matter concentration values, and microbial concentration values; Methods for calculating the air hazard factor based on air environment data include: AHC= ; Where AHC is the air hazard coefficient, is the microbial concentration value, is the particle concentration value, is the allergen concentration value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, is a logarithmic function with base 2.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention improves the cleaning effect and air quality management level of hotel rooms by integrating real-time air quality monitoring, dynamic cleaning path optimization and intelligent control technology. Compared with the traditional fixed cleaning route method, the technical solution of the present invention can flexibly adjust the cleaning strategy according to the actual air environment conditions of the room. It can not only effectively deal with various air pollution sources such as mites, dust, bacteria, etc., but also optimize the cleaning path and reduce interference with surrounding occupied rooms. In addition, through the use of intelligent algorithms, accurate and efficient cleaning operations can be achieved, thereby improving the comfort and satisfaction of guests and providing a healthier indoor environment. This method is not only scientific and data-driven, but also can flexibly adapt to complex environments to achieve all-round air quality improvement in hotel rooms. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of an adaptive control method of a space environment improvement device in the present invention; Figure 2 A schematic diagram of the structure of an adaptive control robot for space environment improvement equipment in the present invention; Figure 3 A schematic diagram of a first candidate cleaning path for a target room of the present invention; Figure 4 A schematic diagram of a second candidate cleaning path for a target room of the present invention; Figure 5 A schematic diagram of constructing a detection coordinate system in the present invention; Figure 6 A schematic diagram of the space environment improvement device in the present invention moving along a target cleaning path; Figure 7 This is an overall schematic diagram of the space environment improvement device and the cleaning robot in the present invention; Figure 8 A side view of the space environment improvement device and the cleaning robot in the present invention; Fig. 9 is an overall schematic diagram of the cleaning robot of the present invention; Fig.10 is a side view of the cleaning robot of the present invention; Fig.11 It is a schematic diagram of the lock buckle of the present invention.

[0020] Reference numerals: 10. The first selected cleaning path; 20. The second selected cleaning path; 30. Space environment improvement equipment; 31. Negative ion outlet; 32. Atmosphere light; 33. Aromatherapy outlet; 34. Ultrasonic outlet; 40. Cleaning robot; 41. Lock. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Example 1

[0023] See also Figure 1 As shown, this embodiment discloses an adaptive control method for a space environment improvement device, including: S10: Obtain check-in registration data and a room layout diagram corresponding to the target room, predetermine M candidate cleaning paths according to the room layout diagram, and calculate the cleaning coverage corresponding to each candidate cleaning path, where M is an integer greater than 0; In this embodiment, the check-in registration data refers to the check-in registration information of the surrounding rooms of the target room. The surrounding rooms here can be rooms located on both sides of the target room, or rooms located above and below the target room. The check-in registration information is obtained from the hotel management system, and whether there are customers staying in the surrounding rooms is determined based on the check-in registration information. The room layout diagram refers to the floor plan or structural diagram of the target room. Taking the floor plan as an example, the floor plan can be a CAD diagram of the target room. The floor plan expresses the placement of the bed, sofa, TV cabinet, etc. in the target room. It can be understood that M to-be-selected cleaning paths can be determined in advance based on the room layout diagram and corresponding expert knowledge.

[0024] The method for predetermining M candidate cleaning paths according to the room layout diagram includes: A real-time image of the target room is obtained, a real-time layout map is obtained according to the real-time image, and the similarity between the real-time layout map and the room layout map is calculated. When the similarity is greater than a preset similarity threshold, a first cleaning path corresponding to the room layout map is obtained, and the first cleaning path is used as a candidate cleaning path. When the similarity is less than or equal to the preset similarity threshold, the real-time layout map is input into a pre-built path planning model to obtain a second cleaning path, and the second cleaning path is used as a candidate cleaning path.

[0025] It should be noted that real-time images can be obtained through space environment improvement equipment. The space environment improvement equipment in this embodiment is a multifunctional device that integrates spray and mosquito repellent functions. Similarly, the space environment improvement equipment has a camera function and can obtain real-time images of the target room.

[0026] The method for obtaining a real-time layout diagram according to a real-time image includes: Based on the edge detection algorithm, edge information in the real-time image is extracted, the outline of the object in the target room is extracted according to the edge information, the object outline is identified and the corresponding position information is determined, and the position information is represented according to the coordinate system of the room layout diagram to obtain the real-time layout diagram.

[0027] In this embodiment, the edge detection algorithm can be a Canny algorithm or a Sobel algorithm, and a contour tracking algorithm (such as the findContours function in OpenCV) can be used to process the edge information, extract and track the complete contour of the object, and use a shape descriptor (such as Hu moment, Fourier descriptor) to describe the extracted contour, so as to realize the recognition of the object contour. For each identified object contour, its center of mass (i.e., the geometric center of the contour) is calculated as the position information of the object. Calculating the center of mass is a prior art, and this embodiment will not go into details.

[0028] It should be added that the above calculation of the similarity between the real-time layout diagram and the room layout diagram can be: vectorizing the real-time layout diagram and the room layout diagram, and then calculating the cosine value between the real-time layout diagram and the room layout diagram. The above vectorization can be gridding the layout diagram, and each grid block can be a feature vector.

[0029] The construction method of the path planning model includes: A sample data set is obtained, wherein the sample data set includes a historical layout map and a historical cleaning path. The sample data set is divided into a sample training set and a sample test set. A regression network is constructed. The historical layout map in the sample training set is used as input data of the regression network, and the historical cleaning path in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time cleaning path. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a path planning model. The initial regression network is preferably a deep neural network model.

[0030] In this embodiment, by calculating the similarity between the real-time layout map and the room layout map, the cleaning path that best suits the current room status can be dynamically selected. This makes the planning of the cleaning path more accurate, and can adapt to changes in the placement of items or structure in the room, thereby improving the cleaning effect. When faced with complex changes in the room layout, it can respond flexibly without affecting the cleaning effect due to environmental changes.

[0031] The method for calculating the cleaning coverage corresponding to each candidate cleaning path includes: The preset unit cleaning width is obtained, the target product between the length of the selected cleaning path and the unit cleaning width is calculated, the target product is used as the cleaning area, and the ratio of the cleaning area to the total area of ​​the target room is used as the cleaning coverage.

[0032] It should be noted that the above-mentioned unit cleaning width refers to the width that can be covered per unit path length when the space environment improvement equipment performs a cleaning task. For example, the space environment improvement equipment has a spray function, and the unit cleaning width refers to the effective width of the spray diffusion. For example, when the space environment improvement equipment is moving forward, the maximum width that the sprayed liquid can evenly cover. From the above content, it can be seen that the greater the cleaning coverage corresponding to the selected cleaning path, the more likely it is that the selected cleaning path should be selected as the target cleaning path.

[0033] S20: determining the cleaning impact based on the check-in data, and determining a target cleaning path from M candidate cleaning paths according to the cleaning impact, the cleaning coverage, and a genetic algorithm; Methods for determining cleaning impact based on check-in data include: Q occupied rooms are determined according to the check-in registration data, barrier materials corresponding to the occupied rooms are obtained according to the room layout diagram, corresponding cleaning impact factors are determined according to the barrier materials, and the average value of the cleaning impact factors is used as the cleaning impact degree.

[0034] It should be noted that the occupied rooms mentioned above refer to the rooms around the target room that have been occupied by customers. The surrounding rooms here can be rooms on both sides of the target room, or rooms above and below the target room. Take the room on one side of the target room and the room above the target room as examples. When the occupied room is on one side of the target room, the corresponding barrier material is the wall. When the occupied room is above the target room, the corresponding barrier material is the floor. Usually, the wall can be a gypsum board, concrete wall, etc., and the material of the floor can be reinforced concrete or wooden structure. Therefore, when the barrier materials are different, the influence on the occupied room is also different. It can be understood that, for example, the sound insulation effect of reinforced concrete is better than that of gypsum board. Therefore, the cleaning impact factor corresponding to reinforced concrete is smaller than the cleaning impact factor corresponding to gypsum board. Figure 3 and Figure 4 As shown, Figure 3 A first candidate cleaning path 10 is shown, Figure 4 The second optional cleaning path 20 is shown. It can be understood that when the first optional cleaning path 10 is selected as the target cleaning path, it indicates that there are no guests staying in the rooms on both sides of the target room. When the second optional cleaning path 20 is selected as the target cleaning path, it indicates that there are guests staying in the rooms on one side of the target room. The above content is only an exemplary description.

[0035] It should be added that the room layout diagram usually contains detailed information on the building structure, including the materials and construction methods of the walls and floor slabs between the rooms. This information is usually clearly marked in the architectural design and construction drawings. Therefore, the barrier materials corresponding to the occupied rooms can be directly obtained through the room layout diagram. The correspondence between the barrier materials and the cleaning influencing factors mentioned above can be determined experimentally by technicians in this field, or can be predetermined based on expert experience and relevant reference materials.

[0036] The method of determining the target cleaning path from M candidate cleaning paths according to the cleaning influence, the cleaning coverage and the genetic algorithm includes: The difference between the cleaning impact and the cleaning coverage is taken as the fitness value, and based on a genetic algorithm, the optimal target cleaning path is determined from M candidate cleaning paths with the goal of minimizing the fitness value.

[0037] The method for determining the optimal target cleaning path from M candidate cleaning paths includes: S201: Taking M candidate cleaning paths as the initial population, and taking the difference between the cleaning influence and the cleaning coverage as the fitness function, calculating the fitness value of each individual in the population; S202: Adopt the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between the individuals, and select the individual with the smallest fitness value as the parent individual; S203: Repeat the selection process of S201-S202 until N parent individuals are selected, and then proceed to S204; S204: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals; S205: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population, ensuring that the size of the new population is still N; S206: The convergence threshold of the preset fitness value is CT. If the fitness value change of the optimal individual in the population of consecutive K generations is less than CT, the genetic algorithm terminates; S207: When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal cleaning path, which is used as the target cleaning path.

[0038] It can be understood that the tournament selection strategy is a selection mechanism in a genetic algorithm, which is used to select sub-individuals from the current population as the parents of the next generation. The tournament selection strategy uses local competition to make individuals with better fitness values ​​have a greater probability of being selected, but will not completely exclude poorer individuals, thereby maintaining the diversity of the population. Single-point crossover is a crossover operation method in a genetic algorithm, which is used to generate the next generation of sub-individuals. Single-point crossover can effectively combine the characteristics of two parent individuals to generate new sub-individuals, thereby exploring new areas in space and increasing the diversity of the population.

[0039] This embodiment combines actual building structure information, and the algorithm can provide practical and effective solutions in specific applications, adapt to different types of hotel room layouts, reduce disturbances to surrounding guests through optimized cleaning paths, and improve customer satisfaction. The use of genetic algorithms and path planning models makes the entire cleaning path selection process more scientific and data-driven, avoiding the blindness and randomness of traditional methods.

[0040] S30: Acquire air environment data corresponding to the target room, calculate an air hazard coefficient according to the air environment data, obtain a cleaning action sequence according to the air hazard coefficient and the target cleaning path, and clean the target room according to the cleaning action sequence, wherein the air environment data includes an allergen concentration value, a particle concentration value, and a microorganism concentration value; Methods for obtaining air environment data corresponding to the target room include: Take any point of the target cleaning path as the coordinate origin, any sub-path of the target cleaning path as the X-axis, and the vertical direction of the arbitrary sub-path as the Y-axis to generate a detection coordinate system. In the detection coordinate system, generate R groups of detection environment data through the Markov random walk method, and use the R groups of detection environment data as air environment data.

[0041] like Figure 3 and Figure 5 As shown, Figure 5 A schematic diagram of constructing a detection coordinate system based on the first candidate cleaning path 10 is shown in the figure. The Markov random walk method refers to a random process model based on the Markov chain, which is used to simulate a randomly changing system or process. This method is often used in calculations to simulate random paths, predictions, and other uncertain system analyses. The basic idea of ​​the Markov random walk method is that the next state of the system only depends on the current state and has nothing to do with the previous state (i.e., it has "memorylessness"). The role of the Markov random walk method here is to generate randomly distributed detection points, obtain the air environment data of these points, and ensure that the air environment detection covers the entire target room while maintaining the randomness and comprehensiveness of the detection.

[0042] In this embodiment, the allergen concentration value may be a mite concentration value, the microorganism concentration value may be a bacteria concentration value, and the air environment data may also be obtained through space environment improvement equipment, which will not be elaborated in this embodiment.

[0043] Methods for calculating the air hazard factor based on air environment data include: AHC= ; Where AHC is the air hazard coefficient, is the microbial concentration value, is the particle concentration value, is the allergen concentration value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, is a logarithmic function with base 2.

[0044] In this embodiment, taking the allergen concentration value as an example, when the allergen concentration value is higher, it means that the air quality in the target room is worse. Similarly, it can be inferred that the higher the air hazard coefficient is, the lower the air quality in the target room is. Therefore, the greater the air hazard coefficient is, the more it is necessary to use space environment improvement equipment for enhanced treatment, including increasing the spraying amount of aromatherapy spray and performing negative oxygen ion sterilization and other operations to improve the air quality in the room.

[0045] The cleaning action sequence mentioned above represents a combination of cleaning actions performed in the process of the space environment improvement equipment moving along the target cleaning path. For example, it includes different cleaning actions such as spraying aromatherapy spray and negative oxygen ion sterilization. According to different air hazard coefficient values, the corresponding threshold interval is set so that the air hazard coefficient includes a low hazard coefficient, a medium hazard coefficient and a high hazard coefficient. When the air hazard coefficient is a low hazard coefficient, the cleaning action sequence can be a low-intensity aromatherapy spray. When the air hazard coefficient is a medium hazard coefficient, the cleaning action sequence can be a medium-intensity aromatherapy spray + mild negative oxygen ion sterilization. This embodiment will not go into too much detail.

[0046] In this embodiment, by integrating real-time air quality monitoring, dynamic cleaning path optimization and intelligent control technology, the cleaning effect and air quality management level of the hotel room are greatly improved. Compared with the traditional fixed cleaning route method, this solution can flexibly adjust the cleaning strategy according to the actual air environment conditions of the room. It can not only effectively deal with various air pollution sources such as mites, dust, bacteria, etc., but also optimize the cleaning path and reduce interference with surrounding occupied rooms. In addition, through the use of intelligent algorithms, the system can achieve accurate and efficient cleaning operations, thereby significantly improving the comfort and satisfaction of guests and providing a healthier indoor environment. This method is not only scientific and data-driven, but also can flexibly adapt to complex environments to achieve all-round air quality improvement in hotel rooms.

[0047] Example 2

[0048] This embodiment provides an adaptive control method for a space environment improvement device based on Embodiment 1; Methods for cleaning a target room according to a cleaning action sequence include: The real-time location information of the space environment improvement equipment is obtained, and it is determined whether to stop moving according to the real-time location information. If so, the space environment improvement equipment deploys a corresponding cleaning robot, and the cleaning robot performs cleaning according to a preset cleaning route. The cleaning robot is arranged on one side of the space environment improvement equipment.

[0049] It should be noted that if Figure 6 and Figure 7 As shown, Figure 6It shows that the space environment improvement device 30 is moving along the target cleaning path. Figure 7 A cleaning robot 40, a negative ion outlet 31, an atmosphere light 32, an aromatherapy outlet 33, and an ultrasonic outlet 34 are shown. The cleaning robot 40 is arranged in the middle of one side of the space environment improvement device 30, and an atmosphere light 32 is arranged at the top of the space environment improvement device 30. A plurality of negative ion outlet holes 31 are opened at the top of one side of the space environment improvement device 30, a plurality of aromatherapy outlet holes 33 are opened at one end of the space environment improvement device 30, and a plurality of ultrasonic outlet holes 34 are opened at the bottom of one side of the space environment improvement device 30. It can be understood that in this embodiment, when the space environment improvement device 30 moves near the bed, the cleaning robot 40 will move onto the bed, and the mite removal unit in the cleaning robot 40 will clean the surface of the bed, and the preset cleaning route refers to the cleaning route pre-set in the cleaning robot 40, for example, it can be cleaned back and forth along the length direction of the bed.

[0050] Among them, during the cleaning process of the cleaning robot 40, the space environment improvement device 30 will release the gas of the aromatherapy agent through the aromatherapy outlet 33. These aromas can cover the odor in the room and make the air fresher and more pleasant. The aromatherapy agent contains antibacterial or antiviral ingredients, which can help reduce bacteria and viruses in the air and improve the air quality. The space environment improvement device 30 will also release negative ions (i.e., negatively charged oxygen molecules) through the negative ion outlet 31. Negative ions can neutralize positive ions in the air, which often come from electronic devices or other pollution sources. Negative ions can combine with tiny particles such as dust, pollen, and smoke in the air to make them heavier and settle to the ground, thereby reducing pollutants and allergens in the air.

[0051] It should be added that Figure 8 , Fig. 9 and Fig.10 As shown, the cleaning robot 40 is placed on one side of the space environment improvement equipment 30. When the cleaning robot 40 is needed to perform mite removal work, the cleaning robot 40 can move through the crawler structure at the bottom. The crawler structure can help the robot move stably on various surfaces, including beds or other areas that need to be cleaned. After reaching the target position, the cleaning robot 40 will start the mite removal unit or other cleaning functions and start cleaning the bed or other surfaces. After the cleaning task is completed, the cleaning robot 40 will continue to move to the next target position or return to the initial position, ready for the next operation or standby. The mite removal unit mentioned above can be a HEPA filter, an ultraviolet lamp activated carbon filter or an activated carbon filter, etc.

[0052] Among them, the cleaning robot 40 can clean the bed, and can also clean the surface of the table, the surface of the sofa, the surface of the carpet, etc. in the target room.

[0053] Methods for determining whether to stop moving based on real-time location information include: The real-time relative distance between the real-time location information and the preset target location information is calculated, and when the real-time relative distance is less than the preset relative distance threshold, the movement is stopped.

[0054] It can be understood that the above-mentioned target position information can be the position information of the bed. In this embodiment, the position information of the bed can be determined in advance according to the room layout diagram. Based on the real-time relative distance between the space environment improvement device 30 and the bed, it is determined whether to stop moving and put the cleaning robot 40 on the bed. When the cleaning robot 40 completes the cleaning task and returns to the space environment improvement device 30, the space environment improvement device 30 continues to move along the target cleaning path.

[0055] In this embodiment, by acquiring the position information of the space environment improvement device 30 in real time and calculating the relative distance between the device and the preset target position information (such as a bed), it is possible to accurately determine whether it is necessary to stop moving and deploy the cleaning robot 40. This automated cleaning process can ensure that the cleaning robot 40 fully cleans the area that needs to be cleaned (such as a bed), thereby improving the cleaning effect and efficiency. The space environment improvement device 30 can continue to move along the preset cleaning path while the cleaning robot 40 is cleaning. This design maximizes the efficiency of the equipment, avoids the equipment from stagnation during the cleaning process, and ensures comprehensive cleaning of the entire room.

[0056] The method for cleaning the target room according to the cleaning action sequence also includes: When the target object needs to be cleaned, the lock 41 between the space environment improvement device 30 and the cleaning robot 40 is opened, and the corresponding cleaning robot 40 is taken out from the space environment improvement device 30. At this time, the space environment improvement device 30 stops moving, and the cleaning hole of the cleaning robot 40 is aligned with the surface of the target object to clean the target object.

[0057] It is understandable that if Fig.11 As shown, Fig.11A lock 41 is shown, and the space environment improvement device 30 and the cleaning robot 40 are fixedly connected by the lock 41. The fixedly connected lock 41 can ensure that the cleaning robot 40 is safely locked on the space environment improvement device 30 when not in operation, preventing the cleaning robot 40 from accidentally falling or being damaged during movement or transportation, which also reduces mistakes or accidents during operation. The lock 41 can ensure that the cleaning robot 40 is safely charged on a fixed base, avoiding charging failure or instability due to poor contact or position displacement. In addition, it can provide feedback on whether the space environment improvement device 30 is in a locked state, facilitating remote management and control of the space environment improvement device 30. The fixedly connected lock system can ensure accurate docking between the cleaning robot 40 and the space environment improvement device 30, facilitating the coordinated work of functions, such as the synchronous start-up of functions such as aromatherapy spray and negative ion release. The lock system not only ensures physical connection, but also may support power supply.

[0058] The above-mentioned target objects can be clothes, lamps, decorations, curtains, etc. in the target room. It can be understood that, for example, curtains, decorations, etc. cannot be cleaned automatically, and the cleaning robot 40 needs to be picked up manually, and the cleaning hole of the cleaning robot 40 is aimed at the surface of the target object, and the cleaning robot 40 is moved back and forth on the surface of the target object for cleaning. This operation mode can not only cope with areas that are difficult for automated equipment to reach, but also ensure the comprehensiveness of cleaning. It is particularly suitable for target objects with complex shapes and higher positions. By manually moving the cleaning robot 40 back and forth, it can be more effectively ensured that all surfaces are fully cleaned.

[0059] An atmosphere light 32 is disposed on the top of the space environment improvement device 30 , and the target image pre-stored in the database is projected onto the ceiling of the target room through the atmosphere light 32 . Different target images can be switched by adjusting the atmosphere light 32 .

[0060] The target image refers to an image used to help sleep, such as a starry sky image, a forest landscape, etc. The atmosphere light 32 is usually integrated with an intelligent control system. By connecting to a database in the device, the system can automatically adjust the projected image according to the mode selected by the user (such as a sleep-aid mode, a relaxation mode, etc.).

[0061] Example 3

[0062] like Figure 2 As shown, this embodiment provides an adaptive control robot for space environment improvement equipment based on the embodiment 1, including: Processing module: used to obtain the check-in registration data and room layout diagram corresponding to the target room, predetermine M candidate cleaning paths according to the room layout diagram, and calculate the cleaning coverage corresponding to each candidate cleaning path, where M is an integer greater than 0; In this embodiment, the check-in registration data refers to the check-in registration information of the surrounding rooms of the target room. The surrounding rooms here can be rooms located on both sides of the target room, or rooms located above and below the target room. The check-in registration information is obtained from the hotel management system, and whether there are customers staying in the surrounding rooms is determined based on the check-in registration information. The room layout diagram refers to the floor plan or structural diagram of the target room. Taking the floor plan as an example, the floor plan can be a CAD diagram of the target room. The floor plan expresses the placement of the bed, sofa, TV cabinet, etc. in the target room. It can be understood that M to-be-selected cleaning paths can be determined in advance based on the room layout diagram and corresponding expert knowledge.

[0063] The method for predetermining M candidate cleaning paths according to the room layout diagram includes: A real-time image of the target room is obtained, a real-time layout map is obtained according to the real-time image, and the similarity between the real-time layout map and the room layout map is calculated. When the similarity is greater than a preset similarity threshold, a first cleaning path corresponding to the room layout map is obtained, and the first cleaning path is used as a candidate cleaning path. When the similarity is less than or equal to the preset similarity threshold, the real-time layout map is input into a pre-built path planning model to obtain a second cleaning path, and the second cleaning path is used as a candidate cleaning path.

[0064] It should be noted that real-time images can be obtained through space environment improvement equipment. The space environment improvement equipment in this embodiment is a multifunctional device that integrates spray and mosquito repellent functions. Similarly, the space environment improvement equipment has a camera function and can obtain real-time images of the target room.

[0065] The method for obtaining a real-time layout diagram according to a real-time image includes: Based on the edge detection algorithm, edge information in the real-time image is extracted, the outline of the object in the target room is extracted according to the edge information, the object outline is identified and the corresponding position information is determined, and the position information is represented according to the coordinate system of the room layout diagram to obtain the real-time layout diagram.

[0066] The construction method of the path planning model includes: A sample data set is obtained, wherein the sample data set includes a historical layout map and a historical cleaning path. The sample data set is divided into a sample training set and a sample test set. A regression network is constructed. The historical layout map in the sample training set is used as input data of the regression network, and the historical cleaning path in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time cleaning path. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a path planning model. The initial regression network is preferably a deep neural network model.

[0067] In this embodiment, by calculating the similarity between the real-time layout map and the room layout map, the cleaning path that best suits the current room status can be dynamically selected. This makes the planning of the cleaning path more accurate, and can adapt to changes in the placement of items or structure in the room, thereby improving the cleaning effect. When faced with complex changes in the room layout, it can respond flexibly without affecting the cleaning effect due to environmental changes.

[0068] The method for calculating the cleaning coverage corresponding to each candidate cleaning path includes: The preset unit cleaning width is obtained, the target product between the length of the selected cleaning path and the unit cleaning width is calculated, the target product is used as the cleaning area, and the ratio of the cleaning area to the total area of ​​the target room is used as the cleaning coverage.

[0069] Optimization module: Determine the cleaning impact based on check-in data, and determine the target cleaning path from M candidate cleaning paths according to the cleaning impact, cleaning coverage and genetic algorithm; Methods for determining cleaning impact based on check-in data include: Q occupied rooms are determined according to the check-in registration data, barrier materials corresponding to the occupied rooms are obtained according to the room layout diagram, corresponding cleaning impact factors are determined according to the barrier materials, and the average value of the cleaning impact factors is used as the cleaning impact degree.

[0070] It should be added that the room layout diagram usually contains detailed information on the building structure, including the materials and construction methods of the walls and floor slabs between the rooms. This information is usually clearly marked in the architectural design and construction drawings. Therefore, the barrier materials corresponding to the occupied rooms can be directly obtained through the room layout diagram. The correspondence between the barrier materials and the cleaning influencing factors mentioned above can be determined experimentally by technicians in this field, or can be predetermined based on expert experience and relevant reference materials.

[0071] The method of determining the target cleaning path from M candidate cleaning paths according to the cleaning influence, the cleaning coverage and the genetic algorithm includes: The difference between the cleaning impact and the cleaning coverage is taken as the fitness value, and based on a genetic algorithm, the optimal target cleaning path is determined from M candidate cleaning paths with the goal of minimizing the fitness value.

[0072] The optimization modules include: Initialization unit: used to take M candidate cleaning paths as the initial population, and the difference between the cleaning influence and the cleaning coverage as the fitness function, and calculate the fitness value of each individual in the population; Selection unit: Adopt the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between individuals, and select the individual with the smallest fitness value as the parent individual; Cycle unit: used to repeat the above selection process until N parent individuals are selected, and then transfer to the crossover unit; Crossover unit: used to select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals; Reconstruction unit: used to randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population from all the child individuals, and replace the original population to ensure that the size of the new population is still N; Convergence unit: The convergence threshold for the preset fitness value is CT. If the fitness value of the best individual in the population of consecutive K generations changes less than CT, the genetic algorithm terminates; Processing unit: When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal cleaning path, which is used as the target cleaning path.

[0073] This embodiment combines actual building structure information, and the algorithm can provide practical and effective solutions in specific applications, adapt to different types of hotel room layouts, reduce disturbances to surrounding guests through optimized cleaning paths, and improve customer satisfaction. The use of genetic algorithms and path planning models makes the entire cleaning path selection process more scientific and data-driven, avoiding the blindness and randomness of traditional methods.

[0074] Cleaning module: used to obtain the air environment data corresponding to the target room, calculate the air hazard coefficient according to the air environment data, obtain the cleaning action sequence according to the air hazard coefficient and the target cleaning path, and clean the target room according to the cleaning action sequence, wherein the air environment data includes allergen concentration values, particulate matter concentration values, and microbial concentration values; Methods for obtaining air environment data corresponding to the target room include: Take any point of the target cleaning path as the coordinate origin, any sub-path of the target cleaning path as the X-axis, and the vertical direction of the arbitrary sub-path as the Y-axis to generate a detection coordinate system. In the detection coordinate system, generate R groups of detection environment data through the Markov random walk method, and use the R groups of detection environment data as air environment data.

[0075] In this embodiment, the allergen concentration value may be a mite concentration value, the microorganism concentration value may be a bacteria concentration value, and the air environment data may also be obtained through space environment improvement equipment, which will not be elaborated in this embodiment.

[0076] Methods for calculating the air hazard factor based on air environment data include: AHC= ; Where AHC is the air hazard coefficient, is the microbial concentration value, is the particle concentration value, is the allergen concentration value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, is a logarithmic function with base 2.

[0077] In this embodiment, taking the allergen concentration value as an example, when the allergen concentration value is higher, it means that the air quality in the target room is worse. Similarly, it can be inferred that the higher the air hazard coefficient is, the lower the air quality in the target room is. Therefore, the greater the air hazard coefficient is, the more it is necessary to use space environment improvement equipment for enhanced treatment, including increasing the spraying amount of aromatherapy spray and performing negative oxygen ion sterilization and other operations to improve the air quality in the room.

[0078] Example 4 The present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the adaptive control method of the space environment improvement device described above is implemented.

[0079] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0080] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0081] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0083] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0086] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0087] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An adaptive control method for a space environment improvement device, characterized in that: include: Obtain the check-in registration data and room layout diagram corresponding to the target room, predetermine M candidate cleaning paths according to the room layout diagram, and calculate the cleaning coverage corresponding to each candidate cleaning path, where M is an integer greater than 0; The method for calculating the cleaning coverage corresponding to each selected cleaning path includes: Obtain a preset unit cleaning width, calculate a target product between the length of the selected cleaning path and the unit cleaning width, use the target product as the cleaning area, and use the ratio of the cleaning area to the total area of ​​the target room as the cleaning coverage; Determine the cleaning impact based on the check-in data, and determine the target cleaning path from M candidate cleaning paths according to the cleaning impact, cleaning coverage and genetic algorithm; The method for determining the cleaning impact based on check-in data includes: Determine Q occupied rooms according to the check-in registration data, obtain the barrier materials corresponding to the occupied rooms according to the room layout diagram, determine the corresponding cleaning impact factors according to the barrier materials, and use the average value of the cleaning impact factors as the cleaning impact degree; Acquire air environment data corresponding to the target room, calculate an air hazard coefficient according to the air environment data, obtain a cleaning action sequence according to the air hazard coefficient and a target cleaning path, and clean the target room according to the cleaning action sequence, wherein the air environment data includes an allergen concentration value, a particulate matter concentration value, and a microbial concentration value; Methods for calculating the air hazard factor based on air environment data include: AHC= ; Where AHC is the air hazard coefficient, is the microbial concentration value, is the particle concentration value, is the allergen concentration value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, is a logarithmic function with base 2.

2. The adaptive control method of a space environment improvement device according to claim 1, characterized in that: The method for predetermining M cleaning paths to be selected according to the room layout diagram includes: A real-time image of the target room is obtained, a real-time layout map is obtained according to the real-time image, and the similarity between the real-time layout map and the room layout map is calculated. When the similarity is greater than a preset similarity threshold, a first cleaning path corresponding to the room layout map is obtained, and the first cleaning path is used as a candidate cleaning path. When the similarity is less than or equal to the preset similarity threshold, the real-time layout map is input into a pre-built path planning model to obtain a second cleaning path, and the second cleaning path is used as a candidate cleaning path.

3. The adaptive control method of a space environment improvement device according to claim 2, characterized in that: The method for obtaining a real-time layout diagram according to a real-time image comprises: Based on the edge detection algorithm, edge information in the real-time image is extracted, the outline of the object in the target room is extracted according to the edge information, the object outline is identified and the corresponding position information is determined, and the position information is represented according to the coordinate system of the room layout diagram to obtain the real-time layout diagram.

4. The adaptive control method of a space environment improvement device according to claim 2, characterized in that: The method for constructing the path planning model includes: A sample data set is obtained, wherein the sample data set includes a historical layout diagram and a historical cleaning path, the sample data set is divided into a sample training set and a sample test set, a regression network is constructed, the historical layout diagram in the sample training set is used as input data of the regression network, the historical cleaning path in the sample training set is used as output data of the regression network, the regression network is trained to obtain an initial regression network for predicting a real-time cleaning path, the initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a path planning model.

5. The adaptive control method of a space environment improvement device according to claim 1, characterized in that: The method for determining a target cleaning path from M candidate cleaning paths according to the cleaning influence, the cleaning coverage and the genetic algorithm includes: The difference between the cleaning impact and the cleaning coverage is taken as the fitness value, and based on a genetic algorithm, the optimal target cleaning path is determined from M candidate cleaning paths with the goal of minimizing the fitness value.

6. The adaptive control method of a space environment improvement device according to claim 5, characterized in that: The method for determining the optimal target cleaning path from M candidate cleaning paths includes: S201: Taking M candidate cleaning paths as the initial population, and taking the difference between the cleaning influence and the cleaning coverage as the fitness function, calculating the fitness value of each individual in the population; S202: Adopt the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between the individuals, and select the individual with the smallest fitness value as the parent individual; S203: Repeat the selection process of S201-S202 until N parent individuals are selected, and then proceed to S204; S204: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals; S205: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population to ensure that the size of the new population is still N; S206: The convergence threshold of the preset fitness value is CT. If the fitness value change of the optimal individual in the population of consecutive K generations is less than CT, the genetic algorithm terminates; S207: When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal cleaning path, which is used as the target cleaning path.

7. The adaptive control method of a space environment improvement device according to claim 6, characterized in that: The method for obtaining the air environment data corresponding to the target room includes: Take any point of the target cleaning path as the coordinate origin, any sub-path of the target cleaning path as the X-axis, and the vertical direction of the arbitrary sub-path as the Y-axis to generate a detection coordinate system. In the detection coordinate system, generate R groups of detection environment data through the Markov random walk method, and use the R groups of detection environment data as air environment data.

8. The adaptive control method of a space environment improvement device according to claim 7, characterized in that: The method for cleaning the target room according to the cleaning action sequence comprises: The real-time location information of the space environment improvement equipment is obtained, and it is determined whether to stop moving according to the real-time location information. If so, the space environment improvement equipment deploys a corresponding cleaning robot, and the cleaning robot performs cleaning according to a preset cleaning route. The cleaning robot is arranged on one side of the space environment improvement equipment.

9. The adaptive control method of a space environment improvement device according to claim 8, characterized in that: The method for cleaning the target room according to the cleaning action sequence also includes: When the target object needs to be cleaned, open the lock between the space environment improvement device and the cleaning robot, take out the corresponding cleaning robot from the space environment improvement device, then the space environment improvement device stops moving, aim the cleaning hole of the cleaning robot at the surface of the target object, and clean the target object.

10. The adaptive control method of a space environment improvement device according to claim 9, characterized in that: An atmosphere light is arranged on the top of the space environment improvement device, and the target image pre-stored in the database is projected onto the ceiling of the target room through the atmosphere light, and different target images are switched by adjusting the atmosphere light.

11. An adaptive control robot for space environment improvement equipment, used to implement an adaptive control method for space environment improvement equipment according to any one of claims 1 to 10, characterized in that: include: Processing module: used to obtain the check-in registration data and room layout diagram corresponding to the target room, predetermine M candidate cleaning paths according to the room layout diagram, and calculate the cleaning coverage corresponding to each candidate cleaning path, where M is an integer greater than 0; The method for calculating the cleaning coverage corresponding to each selected cleaning path includes: Obtain a preset unit cleaning width, calculate a target product between the length of the selected cleaning path and the unit cleaning width, use the target product as the cleaning area, and use the ratio of the cleaning area to the total area of ​​the target room as the cleaning coverage; Optimization module: Determine the cleaning impact based on check-in data, and determine the target cleaning path from M candidate cleaning paths according to the cleaning impact, cleaning coverage and genetic algorithm; The method for determining the cleaning impact based on check-in data includes: Determine Q occupied rooms according to the check-in registration data, obtain the barrier materials corresponding to the occupied rooms according to the room layout diagram, determine the corresponding cleaning impact factors according to the barrier materials, and use the average value of the cleaning impact factors as the cleaning impact degree; Cleaning module: used to obtain the air environment data corresponding to the target room, calculate the air hazard coefficient according to the air environment data, obtain the cleaning action sequence according to the air hazard coefficient and the target cleaning path, and clean the target room according to the cleaning action sequence, wherein the air environment data includes allergen concentration values, particulate matter concentration values, and microbial concentration values; Methods for calculating the air hazard factor based on air environment data include: AHC= ; Where AHC is the air hazard coefficient, is the microbial concentration value, is the particle concentration value, is the allergen concentration value, is the inverse tangent function, is the inverse cotangent function, is the inverse sine function, is a logarithmic function with base 2.

Images