Intelligent environment air cleaning method, system, terminal device and storage medium

Abstract

The application is suitable for the field of air purification technology, and provides an intelligent environmental air cleaning and purifying method, system, terminal device and storage medium. After being triggered and started, the global mobile cleaning path is planned according to space information, so that the spatial coverage integrity and action efficiency of the cleaning operation are ensured. Then, while moving along the path to perform basic cleaning, multi-source environmental state information is acquired and fused in real time, and the basic cleaning strategy is dynamically adjusted online accordingly, so that the system can actively adapt to the differentiated pollution conditions and dynamically changing environmental elements in different areas, thereby significantly improving the pertinence, overall efficiency and environmental adaptability of cleaning and purification without manual intervention.

Description

Technical Field

[0001] This application belongs to the field of air purification technology, and in particular relates to an intelligent environmental air cleaning and purification method, system, terminal equipment and storage medium. Background Technology

[0002] As living standards improve, people are paying increasing attention to the cleanliness and health of indoor air, especially in complex environments such as pet-owning homes and offices where air pollution sources are diverse (e.g., odors, bacteria, dust) and unevenly distributed. Current air cleaning devices, whether fixed purifiers or simple mobile robots, mostly rely on preset programs or threshold responses from single sensors for their cleaning strategies. For example, fixed devices have limited purification range and leave cleaning blind spots; while mobile devices often rely on random collisions or simple edge cleaning, lacking a global understanding and planning of the space, resulting in low cleaning efficiency and insufficient coverage. Therefore, existing air cleaning solutions struggle to achieve efficient, comprehensive, and intelligent purification effects when faced with real, complex indoor environments. Summary of the Invention

[0003] Therefore, embodiments of this application provide an intelligent ambient air cleaning and purification method, system, terminal device, and storage medium, which can solve the problem that existing technologies are unable to achieve efficient, comprehensive, and intelligent purification effects when facing real and complex indoor environments.

[0004] In a first aspect, embodiments of this application provide an intelligent ambient air cleaning and purification method, which is applied to an intelligent ambient air cleaning and purification system, and includes: The cleaning and purification task will be started when the conditions for starting the cleaning and purification task are met. Acquire spatial information of the space to be cleaned and purified, and plan the movement and cleaning path of the intelligent ambient air cleaning and purification system within the space based on the spatial information; Control the intelligent ambient air cleaning and purification system to move along the mobile cleaning and purification path, and execute basic cleaning and purification strategies during the movement; During the movement and cleaning process, multi-source environmental status information of the space to be cleaned is acquired, and the basic cleaning and purification strategy is dynamically adjusted based on the multi-source environmental status information. The cleaning and purification task ends when the preset completion task is met.

[0005] Secondly, embodiments of this application provide an intelligent ambient air cleaning and purification system, comprising: Drive the mobile module for movement within the space to be cleaned and purified; The air quality monitoring module is used to monitor air quality parameters in the space to be cleaned and purified. The cleaning and purification module is used to perform environmental cleaning and air purification operations; The sensing and interaction module is used to acquire spatial information and image data of the space to be cleaned and purified, and to realize human-computer interaction. The control module is communicatively connected to the drive movement module, air quality monitoring module, cleaning and purification module, and sensing and interaction module, and is used for: The cleaning and purification task will be started when the conditions for starting the cleaning and purification task are met. Acquire spatial information of the space to be cleaned and purified, and plan the movement and cleaning path of the intelligent ambient air cleaning and purification system within the space based on the spatial information; Control the intelligent ambient air cleaning and purification system to move along the mobile cleaning and purification path, and execute basic cleaning and purification strategies during the movement; During the movement and cleaning process, multi-source environmental status information of the space to be cleaned is acquired, and the basic cleaning and purification strategy is dynamically adjusted based on the multi-source environmental status information. The cleaning and purification task ends when the preset completion task is met.

[0006] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the above-described intelligent ambient air cleaning and purification method.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described intelligent ambient air cleaning and purification method.

[0008] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the aforementioned intelligent ambient air cleaning and purification method.

[0009] The beneficial effects of this application embodiment compared with the prior art are as follows: After triggering the start, this application embodiment first plans a global mobile cleaning path based on spatial information, ensuring the spatial coverage integrity and operational efficiency of the cleaning operation. Then, while performing basic cleaning along the path, it acquires and integrates multi-source environmental status information in real time, and dynamically adjusts the basic cleaning strategy online accordingly. This allows the system to proactively adapt to the differentiated pollution conditions and dynamically changing environmental factors in different areas, thereby significantly improving the targeting, overall efficiency, and environmental adaptability of cleaning and purification without human intervention. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram illustrating the implementation process of the intelligent ambient air cleaning and purification method provided in the embodiments of this application.

[0012] Figure 2 This is a schematic diagram of the structure of the intelligent ambient air cleaning and purification system provided in the embodiments of this application.

[0013] Figure 3 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application.

[0014] Figure label: 2. Intelligent ambient air cleaning and purification system; 21. Drive and movement module; 22. Air quality monitoring module; 23. Cleaning and purification module; 24. Sensing and interaction module; 25. Control module. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are protected by this application.

[0016] It should be noted that the terms "comprising," "including," and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application, are intended to cover non-exclusive inclusion. For example, a process, method, terminal, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Terms such as "first" and "second" in the claims, specification, and accompanying drawings of this application, as well as relational terms, are used merely to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such immediate relationship or order between these entities / operations / objects.

[0017] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0018] As living standards improve, people are paying increasing attention to the cleanliness and health of indoor air, especially in complex environments such as pet-owning homes and offices where air pollution sources are diverse (e.g., odors, bacteria, dust) and unevenly distributed. Current air cleaning devices, whether fixed purifiers or simple mobile robots, mostly rely on preset programs or threshold responses from single sensors for their cleaning strategies. For example, fixed devices have limited purification range and leave cleaning blind spots; while mobile devices often rely on random collisions or simple edge cleaning, lacking a global understanding and planning of the space, resulting in low cleaning efficiency and insufficient coverage. Therefore, existing air cleaning solutions struggle to achieve efficient, comprehensive, and intelligent purification effects when faced with real, complex indoor environments.

[0019] In view of this, this application provides an intelligent ambient air cleaning and purification method. After triggering the start, a global mobile cleaning path is first planned based on spatial information to ensure the spatial coverage integrity and operational efficiency of the cleaning operation. Then, while performing basic cleaning along the path, multi-source environmental status information is acquired and integrated in real time. Based on this, the basic cleaning strategy is dynamically adjusted online, enabling the system to proactively adapt to the differentiated pollution conditions and dynamically changing environmental factors in different areas. This significantly improves the targeting, overall efficiency, and environmental adaptability of the cleaning and purification without human intervention.

[0020] To illustrate the technical solution of this application, specific embodiments are described below.

[0021] Figure 1 This illustration shows a schematic diagram of the implementation process of an intelligent ambient air cleaning and purification method provided in an embodiment of this application. This method can be applied to, for example... Figure 2 The control module 25 of the intelligent ambient air cleaning and purification system 2 shown can be specifically applied to the intelligent ambient air cleaning and purification system 2. The intelligent ambient air cleaning and purification system 2 may also include a drive and movement module 21, an air quality monitoring module 22, a cleaning and purification module 23, and a sensing and interaction module 24.

[0022] Specifically, the above-mentioned intelligent ambient air cleaning and purification method may include the following steps S101 to S105.

[0023] Step S101: When the conditions for starting the cleaning and purification task are met, start the cleaning and purification task.

[0024] The cleaning and purification task initiation condition refers to the event or state that triggers the system to begin a complete cleaning process. This can include manual commands issued by the user through a mobile terminal application or voice, as well as the intelligent ambient air cleaning and purification system 2 automatically detecting that ambient air quality parameters (such as odor concentration and particulate matter concentration) exceed preset thresholds through built-in sensors.

[0025] In the embodiments of this application, the control module 25 can continuously monitor start signals from user interaction interfaces (such as mobile APP network commands, local voice recognition module commands), and simultaneously continuously collect environmental parameters through a local air quality sensor array. When a clear manual start command is received, or when the built-in algorithm determines that the sensor data exceeds a preset pollution threshold, the control module 25 can trigger a new cleaning task instance, initialize task parameters, and notify each functional module to enter a ready state, thereby activating the system from standby or hibernation state and entering an orderly task execution cycle. This ensures that the initiation of cleaning operations can originate from direct user control or be autonomously determined by the system based on environmental conditions, thus achieving intelligent task triggering.

[0026] Step S102: Obtain spatial information of the space to be cleaned and purified, and plan the moving cleaning and purification path of the intelligent ambient air cleaning and purification system 2 in the space to be cleaned and purified based on the spatial information.

[0027] Spatial information refers to data describing the physical structure of the space to be cleaned and purified, including but not limited to room layout, obstacle locations, and the boundaries and dimensions of passable areas.

[0028] A mobile cleaning and purification path is one or more mobile trajectories planned by the intelligent ambient air cleaning and purification system 2 based on spatial information to complete the cleaning task.

[0029] In the embodiments of this application, the control module 25 can move itself within the initial area by driving the movement module 21, while simultaneously using onboard sensors such as LiDAR or depth cameras to scan the surrounding environment and acquire raw point cloud or depth data such as distance and contour. This data is fed into a simultaneous localization and mapping (SLAM) algorithm for processing, gradually constructing a passable environment map that includes the locations of obstacles such as walls and furniture. Subsequently, a path planning algorithm can use this map to calculate the optimal or near-optimal movement sequence that can efficiently cover most of the passable area. This sequence is the mobile cleaning and purification path, which can avoid repeated cleaning and missed areas caused by random movement.

[0030] Step S103: Control the intelligent ambient air cleaning and purification system 2 to move along the moving cleaning and purification path, and execute the basic cleaning and purification strategy during the movement.

[0031] Among them, the basic cleaning and purification strategy refers to a set of preset and fixed purification procedures that the system executes before obtaining or fully analyzing multi-source environmental status information. For example, the default working mode of medium wind speed, turning on ultraviolet germicidal lamps and negative ion generators.

[0032] In the embodiments of this application, the control module 25 can send speed and steering commands to the drive module 21 (such as a hub motor) according to the planned mobile cleaning and purification path, controlling itself to move along a predetermined trajectory. While moving, the control module 25 can send a start command to the cleaning and purification module 23 to activate core purification units such as electrostatic membrane adsorption units, filters, activated carbon adsorption units, ultraviolet germicidal lamp units, low-concentration ozone generating units, and negative oxygen ion generating units, and begin executing a preset environmental air purification program, i.e., a basic cleaning and purification strategy.

[0033] Step S104: During the movement and cleaning process, acquire multi-source environmental status information of the space to be cleaned and purified, and dynamically adjust the basic cleaning and purification strategy based on the multi-source environmental status information.

[0034] Multi-source environmental status information refers to a collection of various environmental perception data, including at least real-time air quality parameters collected by air quality sensors and real-time image data collected by visual sensors. It includes at least various air quality parameters reflecting the degree of air pollution (such as specific gas concentrations and particulate matter quantity), as well as image or video stream data acquired through visual sensors.

[0035] In the embodiments of this application, during the process of the device moving along the path and executing the basic strategy, the control module 25 can continuously collect real-time data through various onboard sensors, such as changes in odor concentration monitored by gas sensors, fluctuations in dust quantity monitored by particulate matter sensors, and real-time visual scenes captured by cameras. This multi-source environmental status information is transmitted to the control module 25 in real time. The intelligent algorithms built into or loaded into the control module 25 quickly process and fuse these information to generate control commands, which modify one or more parameters (such as fan speed, working mode of a specific purification unit) in the currently executed basic cleaning and purification strategy in real time. This allows the system to go beyond fixed programs and respond in real time according to changes in the environment in time and space, greatly enhancing the targeting and environmental adaptability of cleaning.

[0036] Step S105: When the preset task completion is met, the cleaning and purification task is terminated.

[0037] The preset task completion conditions refer to the criteria for determining the completion of a single cleaning and purification task. These include at least the system's determination that it has completed its planned movement to cover the passable area, and the system's monitoring that the overall air quality parameters within the space have improved and remained at a preset "good" level.

[0038] In the embodiments of this application, the control module 25 can continuously evaluate two key indicators during task execution: first, by comparing the location information with the planned path, it determines whether spatial coverage has been completed; second, by analyzing real-time monitored air quality parameters, it determines whether the overall environment has been purified to the required standard. When either the path coverage is completed or the air quality meets the required standard, the control module 25 can issue a stop command to the drive movement module 21 and the cleaning and purification module 23, ending the current task cycle, and the equipment can return to the standby point or charging dock. This ensures that the task will not be executed indefinitely, forming a complete closed loop from triggering, planning, execution, control to termination, guaranteeing the integrity of the cleaning operation and the energy efficiency of the system operation.

[0039] The beneficial effects of this application embodiment compared with the prior art are as follows: After triggering the start, this application embodiment first plans a global mobile cleaning path based on spatial information, ensuring the spatial coverage integrity and operational efficiency of the cleaning operation. Then, while performing basic cleaning along the path, it acquires and integrates multi-source environmental status information in real time, and dynamically adjusts the basic cleaning strategy online accordingly. This allows the system to proactively adapt to the differentiated pollution conditions and dynamically changing environmental factors in different areas, thereby significantly improving the targeting, overall efficiency, and environmental adaptability of cleaning and purification without human intervention.

[0040] It should be understood that the intelligent ambient air cleaning and purification system of this application can implement its core intelligent dynamic adjustment function through different software logics. Several main and optional implementation methods will be described below. Those skilled in the art should understand that these methods can be implemented individually or selected or combined according to product design needs.

[0041] In some specific embodiments of this application, the multi-source environmental status information includes real-time air quality parameters. The step of acquiring the multi-source environmental status information of the space to be cleaned and dynamically adjusting the basic cleaning and purification strategy based on the multi-source environmental status information may specifically include steps S401 to S403.

[0042] Step S401: During the process of moving along the mobile cleaning and purification path, the real-time air quality parameters in the multi-source environmental status information are continuously acquired.

[0043] The real-time air quality parameters include at least one of the following: sulfide concentration, ammonia concentration, volatile organic compound concentration, characteristic gas concentration related to sebum decomposition (such as nonenal), temperature and humidity, and ozone concentration. Real-time air quality parameters are electrical signals or digital readings reflecting the instantaneous concentration of specific pollutants in the air, continuously measured and output by an onboard gas sensor array during the cleaning process.

[0044] In the embodiments of this application, the intelligent ambient air cleaning and purification system 2 continuously operates its integrated air quality sensor array while moving along a planned path. Sulfide sensors, ammonia sensors, volatile organic compound (VOC) sensors, and a metal oxide semiconductor sensor specifically sensitive to the odor of human and pet sebum oxidation, each respond to corresponding characteristic gas molecules in the air, outputting analog voltages or digital signals proportional to their concentrations. Temperature and humidity sensors monitor environmental thermodynamic conditions, while an ozone sensor monitors the ozone content in the environment. These sensors sample at a fixed frequency (e.g., several times per second) and communicate via analog-to-digital conversion and bus, continuously transmitting real-time numerical streams representing sulfide concentration, ammonia concentration, VOC concentration, sebum odor concentration, temperature and humidity, and ozone concentration to the system's control module 25.

[0045] Step S402: Based on the continuously acquired real-time air quality parameters, dynamically determine the current air quality level of the current location of the intelligent ambient air cleaning and purification system 2.

[0046] The current air quality level is a qualitative rating assigned by the system to the current location of the equipment to summarize the degree of pollution, such as excellent, good, moderate, or poor.

[0047] In the embodiments of this application, the control module 25 can receive real-time parameters and can have a built-in hierarchical rule base, which defines concentration threshold ranges corresponding to different air quality levels (e.g., excellent, good, moderate, and poor) for each type of air quality parameter (e.g., sulfides, VOCs, etc. VOCs, short for Volatile Organic Compounds). The control module 25 can process the latest set of parameters in parallel, comparing the measured value of each parameter with the threshold in the rule base to determine its individual level. Then, a comprehensive decision-making logic (e.g., taking the worst level among the various parameters, or performing a weighted calculation) can be used to fuse the individual results, and finally output a single judgment result representing the overall air condition at the current location of the device, i.e., the current air quality level. This judgment process is repeated cyclically as the device moves and new data arrives, realizing dynamic updates of the level. Thus, the original multi-dimensional sensor readings are fused and transformed into a unified and semantically clear condition indicator, providing a decision-making basis for selecting targeted purification actions.

[0048] Step S403: Based on the current air quality level, switch the corresponding cleaning and purification mode in real time, and adjust the working parameters of the purification unit corresponding to the cleaning and purification mode.

[0049] The operating parameters include at least one of the following: ultraviolet germicidal lamp power, ozone generation unit concentration, negative oxygen ion generation unit output, and fan speed.

[0050] Cleanliness and purification modes are predefined operating procedures for purification units designed to address specific air quality levels. Each mode clearly defines the combination of purification units involved and their target operating states.

[0051] The operating parameters of the purification unit are key physical quantity settings that control the working status of each specific execution component in the cleaning and purification module 23. Specifically, these may include the emission power of the ultraviolet germicidal lamp used for microbial inactivation, the target output concentration of the ozone generating unit used for strong oxidative disinfection, the ion release rate of the negative oxygen ion generating unit used for particulate matter agglomeration and partial gas decomposition, and the fan rotation speed that determines the air circulation volume, etc.

[0052] In the embodiments of this application, after obtaining the current air quality level, the control module 25 can query a preset mode mapping table. This mapping table defines the cleaning and purification modes to be activated for different air quality levels. For example, "Excellent" corresponds to a low-speed ventilation mode, "Good" corresponds to a standard filtration mode, "Medium" corresponds to an enhanced purification mode, and "Poor" corresponds to a deep disinfection mode. Once the target mode is determined, the control module 25 can generate control instructions for each purification unit that perfectly match that mode. These instructions include specific operating parameter settings. For example, in deep disinfection mode, the instructions might include adjusting the power of the ultraviolet germicidal lamp to 80% of its rated value, controlling the ozone generator concentration at a preset safety limit of 0.05 mg / m³, maximizing the output of the negative ion generator, and simultaneously setting the fan speed to the highest level to accelerate air circulation and disinfectant diffusion. The control module 25 sends these operating parameter instructions to the corresponding purification unit actuators in real time via a drive circuit or communication interface, thereby quickly and accurately switching the system's purification behavior to the state most compatible with the current pollution level. The assessment results of environmental conditions are directly transformed into specific, quantifiable, and executable equipment actions, achieving an adaptive match between purification intensity and pollution level.

[0053] This application's implementation establishes a closed-loop system, from continuously acquiring specific air quality parameters to dynamically determining pollution levels, and then switching and adjusting specific purification modes and parameters in real time based on the level. It utilizes a targeted sensor array to directly quantify environmental pollutants, especially odors and harmful gases closely related to daily life and pets. Intelligent algorithms fuse multi-dimensional data into intuitive air quality levels, solving the problem of incomplete judgments caused by traditional equipment relying on single or few parameters. Furthermore, through preset level mode mapping and refined unit parameter control, it ensures the accuracy and efficiency of the transition from assessment conclusions to actions, allowing the purification intensity to match the pollution level. This significantly improves the system's response accuracy and targeted treatment of ambient air pollution, especially complex odors and gaseous pollutants. While improving overall purification efficiency, it avoids energy waste or equipment damage caused by over-purification, achieving a balance between cleaning effectiveness and operational economy.

[0054] In some other specific embodiments of this application, the multi-source environmental status information includes real-time image data, and the step of acquiring the multi-source environmental status information of the space to be cleaned and dynamically adjusting the basic cleaning and purification strategy according to the multi-source environmental status information may specifically include steps S501 to S505.

[0055] Step S501: Obtain real-time image data from the multi-source environmental status information.

[0056] Among them, the real-time image data is a sequence of digital images or video streams that are continuously captured and output by the image acquisition device mounted on the intelligent ambient air cleaning and purification system 2 during the cleaning task, and is used for visual perception of the surrounding environment.

[0057] In the embodiments of this application, during the movement and cleaning process, the intelligent ambient air cleaning and purification system 2 continuously captures images of the surrounding environment from a forward or panoramic perspective using an integrated camera module. The camera captures optical images at a fixed frame rate, such as ten to thirty frames per second, and converts them into digital signals. These continuous image frames undergo preliminary format conversion and compression by an image processor to form a real-time image data stream, which is then transmitted in real-time to the system's control module 25 via an internal data bus for further processing.

[0058] Step S502: Perform graphic recognition analysis on the real-time image data to obtain the analysis results.

[0059] In the embodiments of this application, the control module 25 can receive real-time image data streams and load a pre-trained deep learning model for pet recognition, such as a target detection model based on a convolutional neural network. The model performs forward inference calculations on each frame of the input image or images sampled at certain intervals, extracts image features, and compares them with pet features learned by the model. After processing, the model outputs analysis results, including whether a pet was detected, the pet's confidence score, and the bounding box coordinates that identify the pet's position in the image coordinate system. This clearly determines whether there is a live target (i.e., a pet) that requires special attention within the current field of view.

[0060] Step S503: When the analysis result corresponds to the presence of a pet in the space to be cleaned and purified, determine the relative distance between the pet and the intelligent environmental air cleaning and purification system 2.

[0061] The relative distance refers to the straight-line spatial distance between the intelligent ambient air cleaning and purification system 2 and the identified pet.

[0062] In the embodiments of this application, when the analysis results confirm the detection of a pet and the confidence level is higher than a set threshold, the control module 25 can initiate the distance calculation process. Specifically, the control module 25 can use a binocular vision camera or a 3D camera with depth perception capabilities, combined with the pixel position of the pet in the image and the camera's intrinsic and extrinsic parameters, to calculate the physical straight-line distance from the optical center of the camera to the identified pet subject through triangulation or direct reading of the depth map. Furthermore, the control module 25 can also use a monocular camera, combined with the known approximate size of the pet (as prior knowledge) and its pixel size in the image, to estimate the relative distance through geometric relationships. The calculated distance value, i.e., the relative distance, is updated in real time and transmitted to the decision unit.

[0063] Step S504: When the relative distance is less than or equal to the first preset safety threshold, a safety avoidance strategy is executed, which includes suspending the disinfection operation in the cleaning and purification strategy.

[0064] The first preset safety threshold is a distance value pre-set and stored in the system. This value defines the boundary of the adjacent area where the system determines that a pet has entered and a safety response needs to be triggered. For example, it can be set to 0.5 meters to 1 meter based on the radiation range of the ozone generator or ultraviolet germicidal lamp. When the relative distance is less than or equal to this threshold, the pet is determined to have entered a harmful radiation area.

[0065] In this embodiment, the control module 25 continuously compares the relative distance with a first preset safety threshold, such as 0.5 meters, stored in memory in real time. Once the relative distance is detected to be less than or equal to this threshold, the control module 25 immediately determines that the pet has entered a harmful radiation zone. At this time, the control module 25 generates a high-priority emergency control command, which is directly sent to the drive controller of the cleaning and purification module 23, ordering it to immediately shut off the power to the ultraviolet germicidal lamp and stop the ozone generator from discharging. Simultaneously, the current disinfection status can be recorded. This embodiment of the application can take rapid and direct hard safety measures when a pet is detected to be too close. By immediately stopping all disinfection operations that could directly harm the pet, it effectively avoids the risk of health damage to the pet due to the equipment's operation, achieving proactive safety protection.

[0066] Step S505: When the relative distance is greater than the first preset safety threshold, restore or continue to execute the cleaning and purification strategy that matches the current multi-source environmental status information.

[0067] In the embodiments of this application, distance monitoring continues during the execution of the safety avoidance strategy. When the pet's activity causes the relative distance to exceed the first preset safety threshold again, the control module 25 can determine that the pet has left the high-risk adjacent area. At this time, the safety avoidance state can be automatically deactivated. The control module 25 can reassess the current complete multi-source environmental status information, including real-time air quality parameters and other sensor information. Based on the latest environmental assessment results, it re-invokes the normal strategy decision-making logic and calculates the optimal cleaning and purification strategy to be executed. Subsequently, the system resumes the execution of the strategy. If the new strategy includes disinfection operations and the environment is safe, the corresponding purification unit is reactivated. This ensures that intervention is only necessary (when the pet approaches), and once the risk is eliminated, it immediately resumes the intelligent operation mode aimed at cleaning efficiency and environmental adaptation, avoiding the overall decrease in cleaning efficiency caused by safety pauses and achieving an intelligent balance between safety and efficiency.

[0068] This application's implementation constructs a complete chain from visual acquisition, pet recognition, distance calculation to hierarchical safety control based on precise distance thresholds, realizing an intelligent proactive protection mechanism for pet safety. It reliably senses the presence of pets using machine vision and categorizes safety risks through distance quantification. When a pet enters a preset danger threshold distance, the system can override any other cleaning optimization logic and forcibly suspend all disinfection operations, such as ultraviolet light and ozone, that might affect the living animal, thus establishing an absolute safety red line at the hardware execution level. Once the pet moves away, the system automatically resumes the intelligent cleaning strategy based on the environmental cleanliness requirements. Therefore, this solution fundamentally solves the core human-machine safety contradiction when mobile cleaning equipment operates in pet-owning environments, achieving a reliable balance between pursuing efficient disinfection and purification and ensuring the safety of live pets, greatly improving the product's safety, reliability, and user trust in specific application scenarios.

[0069] In some other specific embodiments of this application, the multi-source environmental status information includes real-time air quality parameters and real-time image data. The step of acquiring the multi-source environmental status information of the space to be cleaned and dynamically adjusting the basic cleaning and purification strategy based on the multi-source environmental status information may specifically include steps S601 to S605.

[0070] Step S601: During the process of moving along the mobile cleaning and purification path, real-time air quality parameters and real-time image data from the multi-source environmental status information are continuously acquired.

[0071] In the embodiments of this application, when the intelligent ambient air cleaning and purification system 2 performs a mobile cleaning task, its internal gas sensor array and vision sensor operate in parallel. The gas sensor array collects and outputs real-time air quality parameters reflecting the levels of various pollutants such as sulfide concentration and volatile organic compound concentration at a fixed frequency. Simultaneously, the system's onboard camera continuously captures images of the foreground and surrounding environment at a set frame rate, generating a real-time image data stream. Both types of sensor data can be synchronously transmitted to the control module 25 via the system's internal bus or interface.

[0072] Step S602: Dynamically determine the current first cleaning requirement level based on the real-time air quality parameters.

[0073] The first cleanliness requirement level is a classification based on the urgency of the current ambient air cleanliness requirement. This level reflects the level of purification required to remove pollutants, and can be divided into three levels: low requirement (concentration of all pollutants is below 50% of the national standard limit), medium requirement (concentration of any pollutant exceeds 50% but is below 100% of the national standard limit), and high requirement (concentration of any pollutant exceeds 100% of the national standard limit).

[0074] In the embodiments of this application, the control module 25 can continuously receive real-time air quality parameters. The control module 25 pre-stores concentration thresholds for different pollutant parameters, corresponding to different cleanliness requirement levels. It can comprehensively evaluate the latest set of parameters; for example, when the concentrations of all major pollutants are below the minimum threshold, it is determined to be a low-requirement level; when the concentration of any major pollutant exceeds the medium threshold, it is determined to be a medium-requirement level; when a specific harmful pollutant, such as high concentrations of VOCs or ammonia compounds, is detected, it is determined to be a high-requirement level. The first cleanliness requirement level can be dynamically refreshed as sensor data is updated.

[0075] Step S603: Perform continuous graphic recognition analysis on the real-time image data to determine whether there are pets in the space to be cleaned and purified, and determine the security status level related to the pet when a pet is identified.

[0076] The safety status level is a classification of the degree of safety risk posed by the current interaction between the pet and the system. This level is determined by a combination of factors, including the pet's relative distance and behavioral state (e.g., stationary, running, approaching). For example, it can be divided into three levels: safe (distance > 2 meters and pet stationary), alert (1 meter < distance < 2 meters, or pet moving slowly), and warning (distance < 1 meter, or pet approaching rapidly).

[0077] In the embodiments of this application, the control module 25 can run a pet detection and behavior analysis algorithm on continuously input real-time image data. When the algorithm identifies a pet target in the image, it can further calculate the pet's outline, motion vector, and pixel distance between the pet and the device, thereby estimating the physical relative distance. Simultaneously, it analyzes the pet's movement trajectory and posture to determine whether the pet is moving away, stationary, lingering, or actively approaching the device. Based on the calculated relative distance and the analyzed behavioral intent, and according to preset mapping rules, a safety status level is assigned to the current scene. For example, a pet stationary at a distance corresponds to a safety level, lingering at a medium distance corresponds to a attention level, and rapidly approaching or being within very close range corresponds to a warning level.

[0078] Step S604: Perform a collaborative judgment based on the first cleaning requirement level and the security status level to obtain a collaborative judgment result.

[0079] In the embodiments of this application, the control module 25 may have a built-in set of collaborative decision rules, which is essentially a query mapping table with cleaning demand level and security status level as joint input conditions. The control module 25 can use these two levels at the current moment as a combined index to query the mapping table, thereby directly obtaining a corresponding collaborative judgment result. For example, the mapping table may define that when the demand level is "high" and the status level is "warning", the collaborative judgment result is "execute the safety-first mild purification mode"; when the demand level is "high" and the status level is "safe", the collaborative judgment result is "execute the efficient disinfection mode".

[0080] Step S605: Based on the collaborative judgment result, dynamically adjust the basic cleaning and purification strategy to execute the target cleaning and purification mode corresponding to the collaborative judgment result.

[0081] In the embodiments of this application, each collaborative judgment result uniquely corresponds to a predefined target cleaning and purification mode. This mode specifies in detail the on / off states, power levels, or concentration settings of all controllable units such as ultraviolet lamps, ozone generators, negative ion generators, and fans. The control module 25 can generate a series of precise digital or analog control signals based on this target mode and send them to the execution components of each cleaning and purification module 23 via drive circuits. These instructions will override or correct the corresponding parameters in the currently running basic cleaning and purification strategy, thereby achieving real-time and precise adjustment of the strategy. For example, if the collaborative judgment result requires the execution of a "safety-first, gentle purification mode," the control signal will shut down the ozone and ultraviolet units, only activating the fan and HEPA (High Efficiency Particulate Air) filtration, and may reduce the movement speed.

[0082] This application's implementation process independently and in parallel processes air quality and visual information to derive two key decision factors: cleaning demand level and safety status level, ensuring the professionalism and real-time nature of the assessment. Furthermore, a pre-defined set of collaborative decision-making rules is used to fuse and judge these two potentially conflicting factors, thereby achieving a globally optimal dynamic trade-off between cleaning efficiency and pet safety. This enables the system to both activate powerful purification in highly polluted environments and intelligently suppress high-risk operations to ensure safety when pets approach, or maximize cleaning efficiency when pet safety is ensured.

[0083] In some specific embodiments of this application, controlling the intelligent ambient air cleaning and purification system 2 to move along the moving cleaning and purification path may specifically include steps S701 to S704.

[0084] Step S701: During the movement along the mobile cleaning and purification path, real-time detection data from multiple environmental sensing sensors is acquired.

[0085] The detection data includes at least two of the following: lidar point cloud data, 3D depth image data, infrared ranging data, collision sensing signals, and cliff sensing signals.

[0086] The environmental perception sensor is a sensing device installed on the intelligent environmental air cleaning and purification system 2 to detect the surrounding physical environment and objects. It may include a lidar that emits a laser beam and receives the reflection to measure distance and contour, a 3D depth camera that acquires a visual image with depth information, an infrared ranging sensor that emits invisible infrared light and measures the reflection time, a mechanical or capacitive collision sensing switch that is triggered when the device casing is physically squeezed, and a cliff sensor that emits a signal toward the ground to detect whether there is a danger of falling ahead.

[0087] In the embodiments of this application, the intelligent ambient air purification system 2 operates independently and continuously with its various environmental sensing sensors as it moves along a global path. A lidar sensor rotates and scans at several revolutions per second, continuously outputting a three-dimensional point cloud data stream describing the contours and distances of surrounding objects. A 3D depth camera captures the scene at a fixed frame rate, outputting an image sequence containing pixel depth information. Infrared ranging sensors positioned on the sides and in the forward direction of the fuselage continuously measure the distance to objects in specific directions and output digital signals. Collision sensors installed within the fuselage's collision skirt monitor physical contact events in real time. A cliff sensor facing the ground continuously detects whether the ground ahead suddenly disappears. The raw output signals or data packets from all these sensors are synchronously acquired and transmitted to the control module 25 in real time through their respective communication interfaces.

[0088] Step S702: The acquired multiple detection data are fused to generate environmental obstacle information.

[0089] The environmental obstacle information includes at least the type, location, and distance of the obstacle.

[0090] In the embodiments of this application, the control module 25 can receive asynchronous and heterogeneous detection data streams from different sensors. First, time synchronization and coordinate system unification are performed, transforming all data into the same body coordinate system. Then, data from different sources are correlated and complemented. For example, the precise distance information of the LiDAR point cloud is used to calibrate the scale of the depth image, infrared data is used to supplement the LiDAR's detection blind spots on specific materials, and all detected object contours are compared with a pre-established obstacle feature library for classification. For example, large, continuous point clouds are classified as walls, isolated, regularly shaped objects as furniture, and small moving contours as pedestrians or pets. The fusion processing ultimately outputs a structured list of environmental obstacles, where each obstacle entry includes its inferred type, its precise position in the fused coordinate system, and its real-time distance relative to the cleaning equipment body.

[0091] Step S703: Based on the environmental obstacle information, determine whether there is any obstacle risk on the current movement path.

[0092] In the embodiments of this application, the control module 25 can compare the latest list of environmental obstacles with the global mobile cleaning and purification path currently being tracked by the system. The system's overall outline is projected forward to form a dynamic safe passage area along the planned path. Simultaneously, the position and movement trend (if calculable) of each obstacle in the environmental obstacle list are analyzed in relation to the spatiotemporal relationship with the system's planned path. Using computational geometry methods, it is determined whether the system's safe passage area will intersect with the area occupied by any obstacle in the near future. If a possibility of intersection is detected, it is determined that there is an obstacle risk on the current movement path, and the risky obstacle and its attributes are marked.

[0093] Step S704: When it is determined that there is a risk of obstacle, a local path adjustment command or an emergency braking command is generated and executed according to the type and location of the obstacle to achieve obstacle avoidance.

[0094] The local path adjustment instruction is an alternative local motion trajectory calculated in real time by the path planning algorithm to avoid this risk. This instruction can include a series of target point coordinates, speed and turning angle.

[0095] The emergency braking command is the highest priority control command issued by the system to the drive movement module 21 when a high risk or sudden obstacle is detected, requiring it to immediately stop all motor power output.

[0096] In the embodiments of this application, once an obstacle risk is detected, the control module 25 immediately initiates the obstacle avoidance response routine. This routine selects the optimal obstacle avoidance strategy based on the type and specific location of the obstacle. For static obstacles such as table or chair legs, or slowly moving obstacles, a smooth local detour path is calculated in real time based on their shape and position, generating a local path adjustment command containing a series of waypoints, and sending it to the drive control unit for execution, so that the device can bypass the obstacle and rejoin the original global path. For suddenly appearing, high-speed approaching dynamic obstacles such as a running pet, or when the device is very close to the edge and there is a risk of falling, the system will generate a high-priority emergency braking command, which will instantly cut off the power to the drive motor, causing the device to stop urgently. After all commands are executed, the system continues to monitor the environment until the obstacle risk is eliminated.

[0097] This application's implementation utilizes multiple sensors with different principles working collaboratively. Through information fusion technology, it significantly improves the accuracy, completeness, and robustness of environmental perception, overcoming the limitations of a single sensor in specific scenarios. Based on this, by dynamically analyzing the spatiotemporal correlation between the environmental situation and the planned path, it achieves proactive prediction rather than passive response to collision and fall risks. This fundamentally enhances the safety and smoothness of the cleaning and purification system when autonomously moving in complex, dynamic, and uncertain home environments, effectively avoiding accidents such as collisions, getting stuck, or falls, and ensuring the continuous execution of cleaning tasks and the safety of the equipment itself.

[0098] In some specific embodiments of this application, after the cleaning and purification task is ended when the preset end task is met, the above method may further include steps S801 to S804.

[0099] Step S801: Collect multi-dimensional process data related to this cleaning and purification task and upload it to the cloud server.

[0100] The multi-dimensional process data includes at least the multi-source environmental status information obtained during this cleaning and purification task and the records of the cleaning and purification strategies executed.

[0101] In the embodiments of this application, when a single cleaning and purification task terminates due to the fulfillment of termination conditions, the control module 25 of the intelligent ambient air cleaning and purification system 2 can first check the network connection status. If the network is available, the data archiving program is immediately started and uploaded. This program extracts the time-series data records of the entire task cycle from the system's circular data buffer or storage unit. These collected data include at least two parts: first, multi-source environmental state information collected and cached at a fixed frequency during the task, such as the concentration values ​​of various gases at different time points, particulate matter values, and synchronous image recognition result summaries; second, the execution records of the cleaning and purification strategies strictly corresponding to these time points, including the executed mode name, specific controlled parameter values ​​such as fan speed level, ozone concentration setpoint, and ultraviolet lamp on / off status. The system packages these data together with task metadata such as task ID, timestamp, and device number, and sends them to a designated cloud server for storage via the device's wireless communication module using a secure transmission protocol. If the network is unavailable, the multi-dimensional process data of this task is stored in local non-volatile memory and retransmitted after the next network connection is established.

[0102] In step S802, the cloud server uses a machine learning model to train and analyze the accumulated multi-dimensional process data from multiple cleaning and purification tasks to generate an optimized cleaning and purification strategy model.

[0103] In the embodiments of this application, the cloud server can receive and store multi-dimensional process data uploaded from multiple cleaning tasks from the same device or a group of similar devices. Once the data accumulates to a certain scale, the cloud-based data analysis engine is activated. This engine uses multi-source environmental state information from historical data as input features, and subsequent environmental quality change data or evaluated cleaning effects as optimization targets to train a pre-set machine learning model. For example, the model may learn which combination of purification parameters can reduce odors to a safe level in the shortest time and with low energy consumption under specific odor concentration and pet distance conditions. The training process adjusts the model's internal parameters through iterative optimization algorithms, making its output decision recommendations increasingly closer to the ideal effect. After training, the model is solidified, generating an optimized cleaning and purification strategy model.

[0104] Specifically, the cloud server can use a deep Q-network model, taking the environmental state from multi-dimensional process data as the state input, the purification strategy parameters as the action output, and the degree of improvement in air quality after purification as the reward value. Through iterative training, the model learns the optimal strategy mapping.

[0105] Step S803: The optimized cleaning and purification strategy model is sent from the cloud server to the intelligent ambient air cleaning and purification system 2.

[0106] In the embodiments of this application, after the cloud server completes the generation and testing of the newly optimized cleaning and purification strategy model, it will send a model distribution command to the target device or device group through the management backend. The new model file or parameter package is pushed to the cloud management module of the target device via a mobile network or the Internet. After confirming the model version update, the device firmware downloads and verifies the integrity and compatibility of the model file during safe idle periods, such as overnight charging, and then stores it in local non-volatile memory, replacing or updating the old strategy model. The device control system will load this latest model upon the next startup.

[0107] Step S804: In the subsequent cleaning and purification tasks, the basic cleaning and purification strategy is dynamically adjusted based on the issued optimized cleaning and purification strategy model and the real-time acquired multi-source environmental status information.

[0108] In the embodiments of this application, when performing a new cleaning and purification task, the control module 25 not only makes decisions based on built-in fixed rules, but can also load and use an optimized cleaning and purification strategy model downloaded from the cloud. When the device moves and acquires new multi-source environmental status information in real time, it inputs this real-time information into the loaded optimized model. This model, as a highly efficient decision function, quickly calculates the optimal strategy recommendation for the current specific situation based on the complex patterns it has learned, and outputs it in the form of a target purification mode and parameters. The control module 25 can generate corresponding control commands based on this output to dynamically adjust the relevant parameters in the running basic cleaning and purification strategy. For example, for a stubborn odor scenario that has been difficult to remove in the past, the optimized model may suggest a different, time-series combination strategy of activated carbon adsorption and negative ion generation.

[0109] This application's implementation method provides real-world fuel for cloud analytics by accumulating multi-dimensional process data. Leveraging its powerful computing capabilities and global data perspective, the cloud employs machine learning to extract more efficient cleaning decision-making patterns from massive amounts of operational experience and encapsulates these patterns into deployable strategy models. Ultimately, front-end devices apply this optimized model, enabling their ability to dynamically adjust strategies to continuously evolve, significantly improving the adaptability of cleaning results and user satisfaction.

[0110] In some more specific embodiments of this application, the step of dynamically adjusting the basic cleaning and purification strategy based on the optimized cleaning and purification strategy model issued and the multi-source environmental status information acquired in real time during the subsequent cleaning and purification task may specifically include steps S901 to S904.

[0111] Step S901: In subsequent cleaning and purification tasks, obtain the optimized cleaning and purification strategy model issued from the cloud server, and obtain the multi-source environmental status information in real time.

[0112] In the embodiments of this application, when initiating a new cleaning and purification task, the control module 25 can first load the optimized cleaning and purification strategy model previously successfully downloaded and stored from the cloud server from the device's non-volatile memory. This model may exist in the form of a data structure, configuration file, or lightweight inference engine. Simultaneously, all relevant sensors, including gas sensor arrays, particulate matter sensors, cameras, etc., are activated and begin continuously collecting environmental data at a fixed frequency. This real-time multi-source environmental state information, such as current odor concentration values, visual image frames, temperature and humidity readings, together with the loaded optimized model, constitutes the basic input for the dynamic decision-making of this task.

[0113] Step S902: Based on the real-time acquired multi-source environmental status information, identify the current cleaning scenario of the intelligent ambient air cleaning and purification system 2.

[0114] Among them, the cleaning scenario represents a specific combination of environmental states in which the device is currently located, such as "slight odor in the central area of ​​the living room", "heavy hair and odor near the pet bed", and "quiet and deserted bedroom at night".

[0115] In the embodiments of this application, the control module 25 can quickly analyze and fuse continuously flowing real-time multi-source environmental status information. By running a lightweight model, for example, analyzing image data to determine whether specific objects such as pets and pet beds are identified, and simultaneously reading the values ​​of the odor sensor to determine the pollution level, and then combining the device's own positioning information (from the SLAM system. SLAM stands for Simultaneous Localization and Mapping) to determine the room area. These discrete information points are combined according to a preset logic and finally mapped to a predefined cleaning scene label. For example, the predefined cleaning scene labels include "light pollution" and "heavy pollution in pet active area". The identification logic is as follows: when the positioning information shows that the device is located in the "living room" area marked on the map, the image recognition algorithm identifies the "pet bed" target with a confidence level of more than 80%, and the sebum odor sensor reading exceeds the preset threshold T1, then the current cleaning scene is determined to be "active odor near the pet bed".

[0116] Step S903: Match the identified cleaning scenario with the issued optimized cleaning and purification strategy model, and query and obtain the optimized control parameter group corresponding to the cleaning scenario from the optimized cleaning and purification strategy model.

[0117] The optimized control parameter group is a set of preset optimal control commands that are strictly bound to a specific cleaning scenario. This parameter group directly defines the actions to be performed, and includes specific equipment control command values ​​such as "fan speed: high", "negative ion intensity: medium", "UV lamp: off", and "movement speed: low".

[0118] In the embodiments of this application, after obtaining the current cleaning scene label, the control module 25 immediately uses it as a query key to search within the loaded optimized cleaning and purification strategy model. This optimized model can essentially be viewed as a high-level lookup table or decision dictionary, internally storing mapping relationships from various possible cleaning scenes to the optimal set of operating parameters. The control module 25 finds the entry in the model's index that perfectly matches or is most similar to the current cleaning scene, and then reads the complete set of optimized control parameters bound to that scenario. This parameter set is a structured dataset that explicitly lists the specific operating states that each purification unit should be set to in that scenario. For example, for the scenario of "active odors near the living room pet's bed," the retrieved optimized control parameter set might include "activate activated carbon fan high-speed mode," "set negative ion generator intensity to 70%," "turn off ultraviolet lamp," and "reduce movement speed by 30%."

[0119] Step S904: Replace or modify the control parameters currently in use in the basic cleaning and purification strategy according to the optimized control parameter group to achieve dynamic adjustment of the basic cleaning and purification strategy.

[0120] In the embodiments of this application, after obtaining the optimized control parameter set, the control module 25 can compare it with the corresponding control parameters in the currently executed basic cleaning and purification strategy. For each control command defined in the parameter set, the system generates a corresponding underlying control signal. For example, if the optimized parameter set requires the fan speed to be "high," while the current basic strategy requires "medium," then the control module 25 will send a new pulse width modulation signal to the fan drive circuit to increase the speed. If the negative ion generator is not enabled in the basic strategy, but the optimized parameter set requires it to be enabled, then the control module 25 will send an activation command to the negative ion generator circuit. These parameter replacements or modifications are completed in real time, overriding or correcting the original basic strategy's response in this scenario, ensuring that the device's immediate behavior strictly follows the best practices recommended by the optimization model.

[0121] This application's implementation transforms the abstract optimization strategy model distributed from the cloud into concrete, operable intelligent behaviors on the device side. It aggregates complex and ever-changing multi-source environmental information into meaningful scene tags, greatly simplifying the query and matching process of the optimization model and reducing the requirements for local device computing power. By directly querying the model to obtain optimization control parameter sets precisely bound to the context, and immediately applying them to the adjustment of the current strategy, a rapid closed loop of decision-making and execution is achieved. This enables the front-end device to execute the optimal purification strategy based on the real-time environment in every cleaning task, significantly improving the accuracy, timeliness, and overall cleaning efficiency of dynamic adjustments.

[0122] Figure 2 This illustration shows a structural diagram of an intelligent ambient air cleaning and purification system 2 provided in an embodiment of this application. The intelligent ambient air cleaning and purification system 2 can be configured on a terminal device. Specifically, the intelligent ambient air cleaning and purification system 2 includes: Drive the moving module 21 for moving within the space to be cleaned and purified; Air quality monitoring module 22 is used to monitor air quality parameters in the space to be cleaned and purified; Cleaning and purification module 23 is used to perform environmental cleaning and air purification operations; The sensing and interaction module 24 is used to acquire spatial information and image data of the space to be cleaned and purified, and to realize human-computer interaction; Control module 25, which is communicatively connected to drive movement module 21, air quality monitoring module 22, cleaning and purification module 23, and sensing and interaction module 24, is used for: The cleaning and purification task will be started when the conditions for starting the cleaning and purification task are met. The system acquires spatial information of the space to be cleaned and purified, and plans the movement cleaning and purification path of the intelligent ambient air cleaning and purification system 2 within the space to be cleaned and purified based on the spatial information. The intelligent ambient air cleaning and purification system 2 is controlled to move along the moving cleaning and purification path, and a basic cleaning and purification strategy is executed during the movement. During the movement and cleaning process, multi-source environmental status information of the space to be cleaned is acquired, and the basic cleaning strategy is dynamically adjusted based on the multi-source environmental status information. The cleaning and purification task ends when the preset completion task is met.

[0123] Specifically, the intelligent ambient air cleaning and purification system 2 can be implemented as an autonomously moving robotic device, which can be shaped like a pet.

[0124] The drive module 21 is embodied in four motor-driven wheels symmetrically arranged at the bottom of the device. Each wheel is driven by an independent motor and controls the device's straight movement, turning and rotation in place through differential speed. Its function is to provide the device with all the power and flexibility to move within the space to be cleaned and purified, which is the physical basis for achieving full coverage.

[0125] The air quality monitoring module 22 consists of multiple dedicated gas sensors. Specifically, it may include a sulfide and ammonia detection module and an ozone and negative oxygen ion detection module, which are integrated into the device in the form of a circuit board. However, their gas sampling probes are exposed near the device's air inlet or in a separate sampling chamber to ensure direct contact with the air to be measured. Their function is to accurately monitor the concentration of characteristic odor gases (sulfides, ammonia) produced by pets, decaying matter, etc., in the environment, as well as the concentration of ozone and negative oxygen ions generated by the device itself or the environment.

[0126] The cleaning and purification module 23 is a composite system integrating multiple purification methods. Specifically, it may include a turbine fan, a dust collection and lint extraction unit (for physically intercepting hair and large particles, which may include a pre-filter and brushes), an ultrasonic disinfection and sterilization unit, an ozone generator, and a negative ion generator. The turbine fan, as the core aerodynamic component, is installed at the end of the internal air duct to generate a directional airflow that enters from the bottom or side of the device, is filtered and purified, and then exits from the top or rear. The dust collection and lint extraction unit is arranged in the air intake duct. An ozone generator and a negative ion generator are integrated inside or at the rear of the air duct to generate ozone for disinfection and negative ions for purification. In addition, the ultrasonic disinfection and sterilization unit is also integrated inside the device, using ultrasonic waves to assist in disinfection.

[0127] The sensing and interaction module 24 integrates multiple sensing devices. A lidar unit can be mounted at the top center of the device for horizontal rotation scanning, acquiring distance information about the surrounding environment to build a map and determine location. An infrared camera module can be mounted at the front or top of the device to capture infrared images in low-light environments, aiding visual recognition. Infrared sensing modules can be distributed on the sides of the device for near-field obstacle detection or human / pet sensing. These sensors work together to acquire high-precision spatial information, image data, and achieve liveness detection. A display screen, serving as the human-machine interface, is mounted on the front or top of the device casing to display information such as operating status and air quality.

[0128] The control module 25 is the system's computing and control hub, physically comprised of a main circuit control board and a cooperating SOPC plus driver module (i.e., a programmable system-on-a-chip and driver integration module). The main circuit control board, as the core, integrates a high-performance microprocessor, memory, storage units, and various communication interfaces, responsible for running all advanced intelligent algorithms such as mapping, path planning, image recognition, multi-sensor fusion, and strategy decision-making. The SOPC plus driver module handles specific low-level real-time tasks such as motor drive control and sensor data acquisition and preprocessing. The charging module and battery pack provide power to the entire system. The control module is tightly connected via internal bus and cables to the motor driver of the drive movement module 21, the controllers of each unit in the cleaning and purification module 23, the data interfaces of all sensors, and various probes of the perception and interaction module 24. Its core function is to coordinate and schedule all hardware resources: receiving multi-source environmental status information from the air quality monitoring module 22 and the perception and interaction module 24; processing the information and generating decisions; sending movement commands to the drive movement module to control its movement along the planned path; and sending precise commands to the cleaning and purification module 23 to dynamically adjust the purification strategy.

[0129] The beneficial effects of this application embodiment compared with the prior art are as follows: After triggering the start, this application embodiment first plans a global mobile cleaning path based on spatial information, ensuring the spatial coverage integrity and operational efficiency of the cleaning operation. Then, while performing basic cleaning along the path, it acquires and integrates multi-source environmental status information in real time, and dynamically adjusts the basic cleaning strategy online accordingly. This allows the system to proactively adapt to the differentiated pollution conditions and dynamically changing environmental factors in different areas, thereby significantly improving the targeting, overall efficiency, and environmental adaptability of cleaning and purification without human intervention.

[0130] In some embodiments of this application, the multi-source environmental state information includes real-time air quality parameters, and the control module 25 is further used for: During the movement along the mobile cleaning and purification path, real-time air quality parameters from the multi-source environmental status information are continuously acquired. The real-time air quality parameters include at least one of the following: sulfide concentration, ammonia concentration, volatile organic compound concentration, sebum odor concentration, temperature and humidity, and ozone concentration. Based on the continuously acquired real-time air quality parameters, the current air quality level of the current location of the intelligent environmental air cleaning and purification system 2 is dynamically determined; Based on the current air quality level, the corresponding cleaning and purification mode is switched in real time, and the working parameters of the purification unit corresponding to the cleaning and purification mode are adjusted. The working parameters include at least one of the following: ultraviolet germicidal lamp power, ozone generation unit concentration, negative oxygen ion generation unit output, and fan speed.

[0131] In some embodiments of this application, the multi-source environmental state information includes real-time image data, and the control module 25 is further configured to: Acquire real-time image data from the multi-source environmental state information; The real-time image data is subjected to image recognition analysis to obtain the analysis results; When the analysis results correspond to the presence of a pet in the space to be cleaned and purified, the relative distance between the pet and the intelligent environmental air cleaning and purification system 2 is determined; When the relative distance is less than or equal to a first preset safety threshold, a safety avoidance strategy is executed, which includes suspending the disinfection operation in the cleaning and purification strategy. When the relative distance is greater than the first preset safety threshold, the cleaning and purification strategy that matches the current multi-source environmental status information is restored or continued.

[0132] In some embodiments of this application, the multi-source environmental state information includes real-time air quality parameters and real-time image data, and the control module 25 is further used for: During the process of moving along the mobile cleaning and purification path, real-time air quality parameters and real-time image data from the multi-source environmental status information are continuously acquired; Based on the real-time air quality parameters, the current first level of air quality requirement is dynamically determined; Continuous image recognition analysis is performed on the real-time image data to determine whether there are pets in the space to be cleaned and purified, and when a pet is identified, the security status level related to the pet is determined; A collaborative judgment result is obtained by combining the first cleaning requirement level and the security status level. Based on the collaborative judgment result, the basic cleaning and purification strategy is dynamically adjusted to execute the target cleaning and purification mode corresponding to the collaborative judgment result.

[0133] In some embodiments of this application, the control module 25 is further configured to: During the movement along the mobile cleaning and purification path, detection data from multiple environmental sensing sensors are acquired in real time. The detection data includes at least two of the following: lidar point cloud data, 3D depth image data, infrared ranging data, collision sensing signals, and cliff sensing signals. The acquired multiple detection data are fused to generate environmental obstacle information, which includes at least the type, location, and distance of the obstacle. Based on the environmental obstacle information, determine whether there are any obstacle risks on the current movement path; When an obstacle risk is detected, a local path adjustment command or an emergency braking command is generated and executed based on the type and location of the obstacle to achieve obstacle avoidance.

[0134] In some embodiments of this application, the control module 25 is further configured to: Collect multi-dimensional process data related to this cleaning and purification task and upload it to the cloud server. The multi-dimensional process data includes at least the multi-source environmental status information obtained in this cleaning and purification task and the records of the cleaning and purification strategies executed. The cloud server uses multi-dimensional process data accumulated from multiple cleaning and purification tasks to train and analyze a machine learning model to generate an optimized cleaning and purification strategy model. The optimized cleaning and purification strategy model is sent from the cloud server to the intelligent ambient air cleaning and purification system 2; In subsequent cleaning and purification tasks, the basic cleaning and purification strategy is dynamically adjusted based on the optimized cleaning and purification strategy model and the multi-source environmental status information acquired in real time.

[0135] In some embodiments of this application, the control module 25 is further configured to: In subsequent cleaning and purification tasks, the optimized cleaning and purification strategy model issued from the cloud server is obtained, and the multi-source environmental status information is obtained in real time. Based on the real-time acquired multi-source environmental status information, the current cleaning scenario of the intelligent environmental air cleaning and purification system 2 is identified; The identified cleaning scenario is matched with the issued optimized cleaning and purification strategy model, and the optimized control parameter group corresponding to the cleaning scenario is queried and obtained from the optimized cleaning and purification strategy model. By replacing or modifying the control parameters currently in use in the basic cleaning and purification strategy according to the optimized control parameter group, the basic cleaning and purification strategy can be dynamically adjusted.

[0136] like Figure 3 The diagram shown is a schematic of a terminal device provided in an embodiment of this application. The terminal device 3 may include: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301, such as an intelligent ambient air cleaning and purification program. When the processor 301 executes the computer program 303, it implements the steps in the various intelligent ambient air cleaning and purification embodiments described above, for example... Figure 1 Steps S101 to S105 are shown.

[0137] The terminal device may be, but is not limited to, smartphones, tablets, personal digital assistants, laptops, desktop computers, smartwatches, smart home control screens, and other portable or fixed electronic devices with data processing and wireless communication capabilities. When the processor executes the computer program, the terminal device can establish a communication connection with the aforementioned intelligent ambient air cleaning and purification system (e.g., via Wi-Fi, Bluetooth, mobile network, etc.), and send control commands such as cleaning task initiation and mode selection to it, or receive status information and environmental data uploaded by it, thereby realizing remote monitoring and intelligent management of the cleaning and purification process. In other words, the terminal device, as the remote control and interaction terminal of the intelligent ambient air cleaning and purification system, completes the above-mentioned steps related to user command reception, status information presentation, and remote decision-making by executing the corresponding computer program.

[0138] A computer program can be divided into one or more modules / units. One or more modules / units are stored in memory 302 and executed by processor 301 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0139] The terminal device may include, but is not limited to, processor 301 and memory 302. Those skilled in the art will understand that... Figure 3 This is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, a terminal device may also include input / output devices, network access devices, buses, etc.

[0140] The processor 301 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0141] The memory 302 can be an internal storage unit of the terminal device, such as the hard drive or RAM of the terminal device. The memory 302 can also be an external storage device of the terminal device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 302 can include both internal and external storage units of the terminal device. The memory 302 is used to store computer programs and other programs and data required by the terminal device. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0142] It should be noted that, for the sake of convenience and brevity, the structure of the terminal device described above can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0143] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0144] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described intelligent ambient air cleaning and purification method.

[0145] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps in the above-described intelligent ambient air cleaning and purification method.

[0146] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0147] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for various specific applications, but such implementations should not be considered beyond the scope of this application.

[0148] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of systems or units may be electrical, mechanical, or other forms.

[0149] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0150] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0151] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0152] The embodiments described above are merely illustrative of the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for intelligent environmental air cleaning and purification, characterized in that, The method is applied to an intelligent ambient air cleaning and purification system, and the method includes: The cleaning and purification task will be started when the conditions for starting the cleaning and purification task are met. Acquire spatial information of the space to be cleaned and purified, and plan the movement cleaning and purification path of the intelligent ambient air cleaning and purification system within the space to be cleaned and purified based on the spatial information; Control the intelligent ambient air cleaning and purification system to move along the moving cleaning and purification path, and execute basic cleaning and purification strategies during the movement; During the movement and cleaning process, multi-source environmental status information of the space to be cleaned is acquired, and the basic cleaning strategy is dynamically adjusted based on the multi-source environmental status information. The cleaning and purification task ends when the preset completion task is met.

2. The intelligent ambient air cleaning and purification method as described in claim 1, characterized in that, The multi-source environmental status information includes real-time air quality parameters. The process of acquiring the multi-source environmental status information of the space to be cleaned and dynamically adjusting the basic cleaning and purification strategy based on the multi-source environmental status information includes: During the movement along the mobile cleaning and purification path, real-time air quality parameters from the multi-source environmental status information are continuously acquired. The real-time air quality parameters include at least one of the following: sulfide concentration, ammonia concentration, volatile organic compound concentration, sebum odor concentration, temperature and humidity, and ozone concentration. Based on the continuously acquired real-time air quality parameters, the current air quality level of the current location of the intelligent environmental air cleaning and purification system is dynamically determined; Based on the current air quality level, the corresponding cleaning and purification mode is switched in real time, and the working parameters of the purification unit corresponding to the cleaning and purification mode are adjusted. The working parameters include at least one of the following: ultraviolet germicidal lamp power, ozone generation unit concentration, negative oxygen ion generation unit output, and fan speed.

3. The intelligent ambient air cleaning and purification method as described in claim 1, characterized in that, The multi-source environmental status information includes real-time image data. The process of acquiring the multi-source environmental status information of the space to be cleaned and dynamically adjusting the basic cleaning and purification strategy based on the multi-source environmental status information includes: Acquire real-time image data from the multi-source environmental state information; The real-time image data is subjected to image recognition analysis to obtain the analysis results; When the analysis results correspond to the presence of a pet in the space to be cleaned and purified, the relative distance between the pet and the intelligent environmental air cleaning and purification system is determined; When the relative distance is less than or equal to a first preset safety threshold, a safety avoidance strategy is executed, which includes suspending the disinfection operation in the cleaning and purification strategy. When the relative distance is greater than the first preset safety threshold, the cleaning and purification strategy that matches the current multi-source environmental status information is restored or continued.

4. The intelligent ambient air cleaning and purification method as described in claim 1, characterized in that, The multi-source environmental status information includes real-time air quality parameters and real-time image data. The process of acquiring the multi-source environmental status information of the space to be cleaned and dynamically adjusting the basic cleaning and purification strategy based on the multi-source environmental status information includes: During the process of moving along the mobile cleaning and purification path, real-time air quality parameters and real-time image data from the multi-source environmental status information are continuously acquired; Based on the real-time air quality parameters, the current first level of air quality requirement is dynamically determined; Continuous image recognition analysis is performed on the real-time image data to determine whether there are pets in the space to be cleaned and purified, and when a pet is identified, the security status level related to the pet is determined; A collaborative judgment result is obtained by combining the first cleaning requirement level and the security status level. Based on the collaborative judgment result, the basic cleaning and purification strategy is dynamically adjusted to execute the target cleaning and purification mode corresponding to the collaborative judgment result.

5. The intelligent ambient air cleaning and purification method as described in claim 1, characterized in that, Controlling the intelligent ambient air cleaning and purification system to move along the moving cleaning and purification path includes: During the movement along the mobile cleaning and purification path, detection data from multiple environmental sensing sensors are acquired in real time. The detection data includes at least two of the following: lidar point cloud data, 3D depth image data, infrared ranging data, collision sensing signals, and cliff sensing signals. The acquired multiple detection data are fused to generate environmental obstacle information, which includes at least the type, location, and distance of the obstacle. Based on the environmental obstacle information, determine whether there are any obstacle risks on the current movement path; When an obstacle risk is detected, a local path adjustment command or an emergency braking command is generated and executed based on the type and location of the obstacle to achieve obstacle avoidance.

6. The intelligent ambient air cleaning and purification method as described in claim 1, characterized in that, After the cleaning and purification task is terminated when the preset termination task is met, the method further includes: Collect multi-dimensional process data related to this cleaning and purification task and upload it to the cloud server. The multi-dimensional process data includes at least the multi-source environmental status information obtained in this cleaning and purification task and the records of the cleaning and purification strategies executed. The cloud server uses multi-dimensional process data accumulated from multiple cleaning and purification tasks to train and analyze a machine learning model to generate an optimized cleaning and purification strategy model. The optimized cleaning and purification strategy model is sent from the cloud server to the intelligent ambient air cleaning and purification system; In subsequent cleaning and purification tasks, the basic cleaning and purification strategy is dynamically adjusted based on the optimized cleaning and purification strategy model and the multi-source environmental status information acquired in real time.

7. The intelligent ambient air cleaning and purification method as described in claim 6, characterized in that, In subsequent cleaning and purification tasks, the basic cleaning and purification strategy is dynamically adjusted based on the optimized cleaning and purification strategy model and the real-time acquired multi-source environmental status information, including: In subsequent cleaning and purification tasks, the optimized cleaning and purification strategy model issued from the cloud server is obtained, and the multi-source environmental status information is obtained in real time. Based on the real-time acquired multi-source environmental status information, the current cleaning scenario of the intelligent environmental air cleaning and purification system is identified; The identified cleaning scenario is matched with the issued optimized cleaning and purification strategy model, and the optimized control parameter group corresponding to the cleaning scenario is queried and obtained from the optimized cleaning and purification strategy model. By replacing or modifying the control parameters currently in use in the basic cleaning and purification strategy according to the optimized control parameter group, the basic cleaning and purification strategy can be dynamically adjusted.

8. An intelligent ambient air cleaning and purification system, characterized in that, The system includes: Drive the mobile module for movement within the space to be cleaned and purified; An air quality monitoring module is used to monitor the air quality parameters in the space to be cleaned and purified. The cleaning and purification module is used to perform environmental cleaning and air purification operations; The sensing and interaction module is used to acquire spatial information and image data of the space to be cleaned and purified, and to realize human-computer interaction; The control module is communicatively connected to the drive movement module, the air quality monitoring module, the cleaning and purification module, and the sensing and interaction module, and is used for: The cleaning and purification task will be started when the conditions for starting the cleaning and purification task are met. Acquire spatial information of the space to be cleaned and purified, and plan the movement cleaning and purification path of the intelligent ambient air cleaning and purification system within the space to be cleaned and purified based on the spatial information; Control the intelligent ambient air cleaning and purification system to move along the moving cleaning and purification path, and execute basic cleaning and purification strategies during the movement; During the movement and cleaning process, multi-source environmental status information of the space to be cleaned is acquired, and the basic cleaning strategy is dynamically adjusted based on the multi-source environmental status information. The cleaning and purification task ends when the preset completion task is met.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the intelligent ambient air cleaning and purification method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent ambient air cleaning and purification method as described in any one of claims 1 to 7.

Images