Electronic cleaning equipment operation optimization method and system based on Internet of Things

Abstract

The invention discloses an electronic cleaning equipment operation optimization method and system based on the Internet of Things, and belongs to the field of control systems.The electronic cleaning equipment operation optimization method based on the Internet of Things comprises the following steps that ground stains are sensed in real time through a multi-mode sensor and an edge computing technology, and common stains and excrement stains are distinguished; after excrement stains are recognized, the electronic cleaning equipment is controlled to stop sweeping immediately, a rolling brush / dust collection module is closed, and stain diffusion is avoided; through cooperation of the Internet of Things and family environment data, a risk area is pre-judged, and cleaning logic is adjusted; compared with the prior art, the method has the beneficial effects that the dirt is classified, and when the dirt is judged to be excrement dirt, the electronic cleaning equipment is controlled to stop cleaning, so that the excrement dirt is prevented from being diffused; meanwhile, through cooperation of the Internet of Things and family environment data, the risk area is pre-judged, the cleaning logic is adjusted, the cleaning frequency and path of the electronic cleaning equipment are dynamically changed, and the stain diffusion risk is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of control systems, and particularly relates to a method and system for optimizing the operation of an electronic cleaning device based on the Internet of Things. Background Art

[0002] Electronic cleaning devices such as floor sweeping robots are commonly used in daily life. Floor sweeping robots scan and map the environment using lidar, navigate and plan paths using gyroscopes, gather garbage with side brushes, suck dust into the dust box with a rotating brush, and mop the floor with a pressurized mop. They are equipped with infrared / ultrasonic sensors to avoid obstacles, and intelligent algorithms to adjust the route in real time. After completing the task, they automatically return to the charging station to achieve autonomous cleaning of the entire house.

[0003] When there are children or pets at home, children and pets may have the problem of urinating and defecating anywhere. Usually, when the rotating brush and dust suction device of a floor sweeping robot come into contact with liquid or viscous substances, these stains may be spread, resulting in a larger area of pollution. Therefore, when a floor sweeping robot encounters excrement, cleaning will actually make the situation worse and needs to be improved. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and system for optimizing the operation of an electronic cleaning device based on the Internet of Things to address the above problems.

[0005] An embodiment of the present invention is implemented as follows. A method for optimizing the operation of an electronic cleaning device based on the Internet of Things includes the following steps:

[0006] Real-time perception of floor stains and differentiation between ordinary stains and excrement stains through multi-modal sensors (liquid detection, gas recognition, AI vision) and edge computing technology;

[0007] After identifying excrement stains, control the electronic cleaning device to immediately stop cleaning and turn off the rotating brush / dust suction module to prevent stain spread;

[0008] Collaborate with home environment data (such as pet activity periods, room humidity) through the Internet of Things to predict risk areas and adjust the cleaning logic.

[0009] In one embodiment, the present invention provides a method for optimizing the operation of an electronic cleaning device based on the Internet of Things. In the step of real-time perception of floor stains and differentiation between ordinary stains and excrement stains through multi-modal sensors (liquid detection, gas recognition, AI vision) and edge computing technology, it specifically includes:

[0010] Use a liquid detection sensor (such as a capacitive or infrared sensor) to continuously monitor changes in floor humidity; analyze the odor components in the air (such as ammonia and hydrogen sulfide released by excrement) through a gas sensor (such as an electrochemical ammonia sensor or a semiconductor VOC sensor);

[0011] Through the lightweight convolutional neural network (CNN) model deployed on the edge device, combined with the stain image features (such as color, diffusion form, texture, etc.) collected in real time by the intelligent camera integrated with the AI vision module, and compared and analyzed with the excrement feature database pre-trained in the cloud;

[0012] Cross-validate the three-way data through a sensor fusion algorithm (such as Kalman filtering or Bayesian network). If the preset confidence level is exceeded (such as humidity > 70%, ammonia concentration > 50 ppm, and visual matching degree > 90%), it is determined as excrement stain.

[0013] In one embodiment, the present invention provides an operation optimization method for an Internet of Things-based electronic cleaning device. After identifying the excrement stain, to control the electronic cleaning device to immediately stop cleaning and turn off the roller brush / vacuum module to avoid stain diffusion, specifically includes:

[0014] After identifying the excrement stain, immediately trigger a hardware-level interrupt signal, execute an emergency stop program, cut off the power drive circuits of the roller brush motor and the vacuum fan, quickly brake the mechanical components through the PID algorithm, and at the same time close the vacuum air flow channel to prevent the excrement stain from being inhaled;

[0015] Mark the pollution coordinates through the SLAM map, control the electronic cleaning device to automatically bypass during subsequent cleaning tasks, and at the same time push an alarm and a real-time picture through the App for the user to confirm;

[0016] If the electronic cleaning device has come into contact with the excrement stain, control the electronic cleaning device to automatically back off and start the self-cleaning program.

[0017] In one embodiment, the present invention provides an operation optimization method for an Internet of Things-based electronic cleaning device. In the step of predicting risk areas and adjusting the cleaning logic by collaborating with home environment data (such as pet activity periods, room humidity) through the Internet of Things, specifically includes:

[0018] Integrate multi-source home environment data through the Internet of Things, access intelligent devices (such as baby monitors, intelligent diaper sensors, children's bracelets) to obtain the activity trajectories and work and rest rules of infants and young children (such as nap periods, post-meal activity areas), and at the same time combine pet collar positioning, temperature and humidity sensors, and camera data to construct a whole-house dynamic risk map;

[0019] Use a spatio-temporal correlation analysis algorithm to identify high-risk scenarios through a machine learning model (such as a random forest); dynamically adjust the cleaning logic according to the high-risk scenarios, and change the cleaning frequency and path of the electronic cleaning device.

[0020] In one embodiment, the present invention provides an operation optimization method for an Internet of Things-based electronic cleaning device. The operation optimization method for the Internet of Things-based electronic cleaning device further includes:

[0021] After identifying the excrement stain, the contaminated area is accurately located through the SLAM map, and the coordinate information is transmitted to the home IoT hub (such as a smart gateway or cloud platform) through the Wi-Fi / Zigbee protocol;

[0022] Analyze the rooms to which the polluted area belongs, and link the smart air conditioner in the area to shut down the air supply function to prevent the odor from spreading to other spaces through the airflow;

[0023] If the contaminated area involves corridors or open spaces, the virtual electronic fence will be automatically activated (through voice prompts, red light warnings from smart lights, or automatic closing of pet activity doors) to restrict children or pets from entering the contaminated area and avoid secondary contact.

[0024] In one embodiment, the present invention provides an electronic cleaning equipment operation optimization system based on the Internet of Things, comprising:

[0025] The stain differentiation module is used to sense ground stains in real time and distinguish between common stains and excrement stains through multimodal sensors (liquid detection, gas recognition, AI vision) and edge computing technology;

[0026] The cleaning stop module is used to control the electronic cleaning device to immediately stop cleaning and turn off the roller brush / dust suction module after identifying excrement stains to prevent the stains from spreading;

[0027] The cleaning logic adjustment module is used to coordinate with the Internet of Things and home environment data (such as pet activity time and room humidity) to predict risk areas and adjust the cleaning logic.

[0028] In one embodiment, the present invention provides an operation optimization system for electronic cleaning equipment based on the Internet of Things, and the stain differentiation module includes:

[0029] Humidity and air detection unit, used to monitor the change of ground humidity in real time by using liquid detection sensor (such as capacitive or infrared sensor); analyze the odor components in the air (such as ammonia and hydrogen sulfide released by excrement) by using gas sensor (such as electrochemical ammonia sensor or semiconductor VOC sensor);

[0030] The image recognition unit is used to compare and analyze the stain image features (such as color, diffusion form, texture, etc.) collected in real time by the intelligent camera with an integrated AI vision module through a lightweight convolutional neural network (CNN) model deployed on the edge device, and with the pre-trained excrement feature database in the cloud;

[0031] A stain determination unit, which is used to cross-verify three-way data through a sensor fusion algorithm (such as Kalman filtering or Bayesian network). If the preset confidence level is exceeded (such as humidity > 70%, ammonia concentration > 50 ppm, and visual matching degree > 90%), it is determined as excrement stain.

[0032] In one embodiment, the present invention provides an operation optimization system for an Internet of Things-based electronic cleaning device. The cleaning stop module includes:

[0033] An emergency stop unit, which is used to immediately trigger a hardware-level interrupt signal after identifying excrement stain, execute an emergency stop program, cut off the power drive circuits of the roller brush motor and the dust suction fan, quickly brake mechanical components through a PID algorithm, and at the same time close the dust suction air flow channel to prevent excrement stain from being inhaled;

[0034] A pollution coordinate marking unit, which is used to mark pollution coordinates through a SLAM map, control the electronic cleaning device to automatically bypass during subsequent cleaning tasks, and at the same time push an alarm and real-time pictures through the App for the user to confirm;

[0035] A device self-processing unit, which is used to control the electronic cleaning device to automatically retreat and start a self-cleaning program if the electronic cleaning device has come into contact with excrement stain.

[0036] In one embodiment, the present invention provides an operation optimization system for an Internet of Things-based electronic cleaning device. The cleaning logic adjustment module includes:

[0037] A risk map construction unit, which is used to integrate multi-source home environment data through the Internet of Things, access intelligent devices (such as baby monitors, intelligent diaper sensors, children's bracelets) to obtain the activity trajectories and work and rest rules of infants and young children (such as nap time periods, post-meal activity areas), and at the same time combine pet collar positioning, temperature and humidity sensor, and camera data to construct a whole-house dynamic risk map;

[0038] A cleaning logic adjustment unit, which is used to use a spatio-temporal correlation analysis algorithm to identify high-risk scenarios through a machine learning model (such as a random forest) (for example, food debris is likely to remain in the area where infants and young children often crawl within 1 hour after a meal, or the excretion risk increases when the humidity > 80% in the space where pets and children coexist); dynamically adjust the cleaning logic according to the high-risk scenarios, and change the cleaning frequency and path of the electronic cleaning device.

[0039] In one embodiment, the present invention provides an operation optimization system for an Internet of Things-based electronic cleaning device. The operation optimization system for the Internet of Things-based electronic cleaning device further includes:

[0040] The stain coordinate positioning module is used to identify excrement stains, accurately locate the contaminated area through the SLAM map, and transmit the coordinate information to the home IoT hub (such as a smart gateway or cloud platform) through the Wi-Fi / Zigbee protocol;

[0041] The odor prevention module is used to analyze the rooms to which the polluted area belongs, and link the smart air conditioner in the area to shut down the air supply function to prevent the odor from spreading to other spaces through the airflow;

[0042] The module for avoiding secondary contact is used to automatically activate the virtual electronic fence (through voice prompts, red light warnings with smart lights, or automatic closing of pet activity doors) if the contaminated area involves corridors or open spaces, restricting children or pets from entering the contaminated area to avoid secondary contact.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention classifies the stains, and when it is determined to be excrement stains, it will control the electronic cleaning equipment to stop cleaning, so as to avoid the spread of excrement stains; at the same time, it will coordinate with the Internet of Things and home environment data to predict risk areas and adjust the cleaning logic, dynamically change the cleaning frequency and path of the electronic cleaning equipment, and reduce the risk of stain spread. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the first part of the flow chart of an operation optimization method for electronic cleaning equipment based on the Internet of Things provided in an embodiment of the present invention.

[0045] Figure 2 A schematic diagram of a process for distinguishing common stains from excrement stains provided in an embodiment of the present invention.

[0046] Figure 3 A schematic diagram of a process for preventing stains from spreading provided by an embodiment of the present invention.

[0047] Figure 4 A schematic diagram of a flow chart for adjusting the cleaning logic provided in an embodiment of the present invention.

[0048] Figure 5 A schematic diagram of the second part of the flow chart of an operation optimization method for electronic cleaning equipment based on the Internet of Things provided in an embodiment of the present invention.

[0049] Figure 6 A schematic diagram of the first part of an Internet of Things-based electronic cleaning equipment operation optimization system provided by an embodiment of the present invention.

[0050] Figure 7 A schematic diagram of a stain distinguishing module provided in an embodiment of the present invention.

[0051] Figure 8 A schematic diagram of a cleaning stop module provided in an embodiment of the present invention.

[0052] Figure 9 Schematic diagram of the cleaning logic adjustment module provided by the embodiment of the present invention.

[0053] Figure 10 Schematic diagram of the second part of an Internet of Things-based electronic cleaning device operation optimization system provided by the embodiment of the present invention. Detailed implementation manners

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] In one embodiment, as Figure 1 shown, an Internet of Things-based electronic cleaning device operation optimization method includes the following steps:

[0056] Step S1: Through multimodal sensors (liquid detection, gas recognition, AI vision) and edge computing technology, the ground stains are sensed in real time, and ordinary stains and excrement stains are distinguished;

[0057] Step S2: After identifying excrement stains, control the electronic cleaning device to immediately stop cleaning and turn off the roller brush / vacuum module to prevent the stains from spreading;

[0058] Step S3: Through the cooperation of the Internet of Things and home environment data (such as pet activity periods, room humidity), predict risk areas and adjust the cleaning logic.

[0059] Step S1 adopts a combination of multi-modal sensor fusion and edge computing, aiming to break through the technical limitations of single sensors in traditional cleaning devices. The liquid detection sensor captures sudden changes in ground humidity (such as urine infiltration) through capacitance / infrared technology. The gas sensor conducts chemical fingerprint recognition on specific VOC components such as ammonia and hydrogen sulfide in excrement. AI vision performs pixel-level analysis on the morphological features of stains (such as the irregular edge diffusion of feces) through a lightweight CNN model. The three-way data is cross-validated through Kalman filtering to complete millisecond-level decision-making at the edge, ensuring both the accuracy of excrement recognition and avoiding the latency risk of cloud transmission, providing a reliable judgment basis for the subsequent action chain. The emergency braking mechanism in Step S2 constructs a physical safety defense line. It directly cuts off the power of the rotary brush through a hardware-level interrupt signal, uses the PID algorithm to achieve reverse braking of the motor torque, compresses the stopping time of mechanical components within 300 ms, and at the same time closes the dust suction air flow channel to form negative pressure isolation. The response time is sub-second, effectively preventing secondary pollution caused by the rotation of the rotary brush with excrement. Step S3 realizes the dimensionality increase of risk prediction through Internet of Things data fusion, integrates the humidity alarm of intelligent diapers, the positioning trajectory of pet collars, and the data stream of temperature and humidity sensors, and uses the random forest model to construct a dynamic risk map. For example, when the pet's activity hot zone overlaps with the one-hour period after a meal, the cleaning priority of this area is automatically decreased and the bow-shaped path is switched to the boundary cruise mode. This spatio-temporal correlation analysis enables the device to shift from passive response to active avoidance, reducing the probability of contact with excrement.

[0060] In one embodiment, as Figure 2 shown, a method for optimizing the operation of an Internet of Things-based electronic cleaning device, in the step S1, in the step of real-time sensing of ground stains and distinguishing ordinary stains from excrement stains through multi-modal sensors (liquid detection, gas recognition, AI vision) and edge computing technology, specifically includes:

[0061] Step S11, using a liquid detection sensor (such as a capacitive or infrared sensor) to continuously monitor changes in ground humidity; analyzing the odor components in the air (such as ammonia and hydrogen sulfide released by excrement) through a gas sensor (such as an electrochemical ammonia sensor or a semiconductor VOC sensor);

[0062] Step S12, through a lightweight convolutional neural network (CNN) model deployed on an edge device, combining the stain image features (such as color, diffusion form, texture, etc.) continuously collected by an intelligent camera integrated with an AI vision module, and comparing and analyzing them with the excrement feature database pre-trained in the cloud;

[0063] Step S13, cross-verify the three-way data through a sensor fusion algorithm (such as Kalman filtering or Bayesian network). If the preset confidence level is exceeded (such as humidity > 70%, ammonia concentration > 50 ppm, and visual matching degree > 90%), it is determined as excrement stain.

[0064] In step S11, a capacitance / infrared sensor is used to detect sudden changes in ground humidity (such as changes in dielectric constant caused by urine infiltration). At the same time, an electrochemical gas sensor is deployed to capture chemical fingerprints unique to excrement, such as ammonia (NH3) and hydrogen sulfide (H2S), to form a physical-chemical two-dimensional perception baseline. In step S12, a lightweight CNN model is introduced for real-time image analysis at the edge. Through transfer learning, a pre-trained excrement feature library in the cloud is reused (such as the brown-yellow HSV color gamut of feces and the fractal-like texture of urine diffusion) to avoid model inaccuracy caused by differences in the home environment. In step S13, a Bayesian network is used for probabilistic decision-making. Dynamic weight allocation is performed on the humidity threshold (> 70%), gas concentration (NH3 > 50 ppm), and visual confidence level (> 90%). For example, when 80% humidity is detected during the pet activity period but the visual match is only 70%, the false positive rate is reduced through conditional probability calculation. The three-way data is fused at the edge in milliseconds, avoiding cloud latency and reducing the missed detection rate through redundant perception.

[0065] In one embodiment, as Figure 3 shown, a method for optimizing the operation of an Internet of Things-based electronic cleaning device. In step S2, after identifying the excrement stain, the electronic cleaning device is controlled to immediately stop cleaning and turn off the roller brush / vacuum module. In the step of avoiding stain spread, it specifically includes:

[0066] In step S21, after identifying the excrement stain, immediately trigger a hardware-level interrupt signal, execute an emergency stop program, cut off the power drive circuits of the roller brush motor and the vacuum fan, quickly brake the mechanical components through a PID algorithm, and at the same time close the vacuum air flow channel to prevent the excrement stain from being sucked in;

[0067] In step S22, mark the pollution coordinates through a SLAM (a technology in which a robot or device constructs an environmental map in real time through sensor data and synchronously determines its own position when operating in an unknown environment) map, control the electronic cleaning device to automatically bypass during subsequent cleaning tasks, and at the same time push an alarm and real-time video through the App for the user to confirm;

[0068] In step S23, if the electronic cleaning device has come into contact with the excrement stain, control the electronic cleaning device to automatically retreat and start the self-cleaning program.

[0069] Step S21 directly cuts off the motor power supply through a hardware-level interrupt signal (instead of relying on the software protocol stack), and dynamically adjusts the reverse braking torque in combination with the PID algorithm, which can achieve the stop of the roller brush within 300 ms (traditional soft braking takes more than 1.5 seconds). At the same time, the dust suction channel is closed to form a negative pressure barrier, physically blocking the hidden danger of pollutants being inhaled into the internal air duct and causing secondary pollution. Step S22 relies on SLAM high-precision positioning (error < 2 cm) to generate a digital twin model of the polluted area, which not only enables the device to avoid obstacles autonomously (automatically expanding a 15-cm safety boundary during path planning), but also transmits the pollution coordinates and image evidence chain, so that the App alarm information includes multi-dimensional data such as spatial position, timestamp, and visual features, improving the user's disposal efficiency. The self-cleaning mechanism of Step S23 can adopt a spiral paradoxical logic. When the device retreats, it simultaneously starts a double-pulse water flow to wash the roller brush (to avoid dragging pollutants), and activates the UV-C ultraviolet sterilization module (radiation dose > 80 mJ / cm²).

[0070] In one embodiment, as Figure 4 shown, a method for optimizing the operation of an Internet of Things-based electronic cleaning device, in the step S3, through the coordination of the Internet of Things and home environment data (such as pet activity periods, room humidity), predicting risk areas and adjusting the cleaning logic steps specifically include:

[0071] Step S31, through the Internet of Things, integrates multi-source home environment data, accesses intelligent devices (such as baby monitors, smart diaper sensors, children's bracelets) to obtain the activity trajectories and daily routines of infants and young children (such as nap periods, post-meal activity areas), and at the same time combines pet collar positioning, temperature and humidity sensor, and camera data to construct a whole-house dynamic risk map;

[0072] Step S32, using a spatio-temporal correlation analysis algorithm, identifies high-risk scenarios through a machine learning model (such as a random forest); dynamically adjusts the cleaning logic according to the high-risk scenarios, changing the cleaning frequency and path of the electronic cleaning device.

[0073] Step S31 integrates multi-dimensional data sources through the Internet of Things (such as the UWB positioning accuracy of baby bracelets up to ±10cm, the activity heat map of pet collars, and the threshold alarm of diaper humidity sensors) to build a dynamic risk map for the whole house. For example, the temporal and spatial correlation between the infant nap period (13:00-15:00) and the activity hot zone 30 minutes after a meal (living room carpet area) is combined to predict the high-incidence area of ​​excretion. Step S32 uses a random forest model to perform feature engineering on historical events (such as the temperature and humidity change gradient 30 minutes before the excretion occurs, and abnormal behavior with a pet movement acceleration threshold of >3g), selects key factors through the Gini coefficient (such as the weight of the 1-hour period after a meal accounts for 47%), and dynamically adjusts the cleaning logic: in high-risk periods (such as after pet feeding), the corridor area cleaning mode is switched from full coverage to border cruising (path spacing is extended from 15cm to 50cm), and the cleaning frequency is automatically increased to 2 times / hour in low-risk periods (such as early morning). The collaboration of the two modules improves the prediction accuracy of risk areas and reduces the probability of accidentally entering polluted areas.

[0074] In one embodiment, Figure 5 As shown, an operation optimization method of electronic cleaning equipment based on the Internet of Things, the operation optimization method of electronic cleaning equipment based on the Internet of Things also includes:

[0075] Step S4, after identifying the excrement stain, accurately locate the contaminated area through the SLAM map, and transmit the coordinate information to the home IoT hub (such as a smart gateway or cloud platform) through the Wi-Fi / Zigbee protocol;

[0076] Step S5, analyzing the rooms to which the polluted area belongs, and linking the smart air conditioner in the area to turn off the air supply function to prevent the odor from spreading to other spaces through the airflow;

[0077] Step S6: If the contaminated area involves a corridor or open space, the virtual electronic fence is automatically activated (through voice prompts, red light warnings from smart lights, or automatic closing of pet activity doors) to restrict children or pets from entering the contaminated area to avoid secondary contact.

[0078] Step S4 uses SLAM technology to achieve centimeter-level pollution positioning (error <2cm), and uses Wi-Fi / Zigbee low-latency protocol (transmission delay <10ms) to upload the pollution coordinates to the home IoT hub to provide a spatial reference for subsequent linkage control. For example, when pet feces contaminates wooden floors, SLAM not only marks the specific coordinates, but also associates the room topology data (such as bedrooms or corridors) to avoid the ambiguity of traditional cleaning equipment that only records relative positions. Step S5 dynamically controls environmental equipment based on the spatial attributes of the polluted area (such as closed bedrooms or open living rooms): If the pollution is located in a bedroom covered by air conditioning, immediately turn off the fan and start the damper (response time <1 second) to reduce the spread of odor; if the polluted area involves multiple rooms, multiple air conditioners are synchronously controlled through the MQTT protocol (a communication protocol) to form an airflow isolation zone. Step S6 adopts multimodal interactive warning to address the pollution risk of open spaces: the smart light strip uses red light wavelengths (620-750nm) to define virtual boundaries (human eye sensitivity is increased by 3 times), and at the same time links with smart door locks to physically close related areas (such as the power-off adsorption of the electromagnetic lock of the pet activity door), combined with voice prompts (broadcast delay <200ms) to form an audio-visual coordinated warning, reducing the rate of children entering by mistake.

[0079] In one embodiment, Figure 6 As shown, an electronic cleaning equipment operation optimization system based on the Internet of Things includes:

[0080] Stain differentiation module 1 is used to sense ground stains in real time and distinguish between common stains and excrement stains through multimodal sensors (liquid detection, gas recognition, AI vision) and edge computing technology;

[0081] Cleaning stop module 2, which is used to control the electronic cleaning device to immediately stop cleaning and turn off the roller brush / dust suction module after identifying the excrement stains to prevent the stains from spreading;

[0082] The cleaning logic adjustment module 3 is used to coordinate with the home environment data (such as pet activity time and room humidity) through the Internet of Things to predict risk areas and adjust the cleaning logic.

[0083] The online learning module can also be used to monitor the sensor baseline value in real time (such as the reading drift of the infrared liquid sensor affected by the reflectivity of the floor tiles), and establish a compensation model based on environmental parameters (light intensity, room temperature): when the AI ​​vision causes a sudden change in color temperature due to the opening and closing of the curtains, the HSV and LAB color space weights are automatically switched; the gas sensor is equipped with an automatic zeroing circuit, and the baseline value is refreshed every 30 minutes with a clean air sample (for example, to correct the false alarm of the ammonia sensor due to the interference of the fermented pet food odor).

[0084] In one embodiment, Figure 7As shown in the figure, an operation optimization system for an electronic cleaning device based on the Internet of Things. The stain differentiation module 1 includes:

[0085] A humidity and air detection unit 11, which is used to use a liquid detection sensor (such as a capacitive or infrared sensor) to monitor the change of ground humidity in real time; and analyze the odor components in the air (such as ammonia and hydrogen sulfide released by excrement) through a gas sensor (such as an electrochemical ammonia sensor or a semiconductor VOC sensor);

[0086] An image recognition unit 12, which is used to collect the stain image features (such as color, diffusion form, texture, etc.) in real time through a lightweight convolutional neural network (CNN) model deployed on an edge device and an intelligent camera integrated with an AI vision module, and compare and analyze them with the excrement feature database pre-trained in the cloud;

[0087] A stain determination unit 13, which is used to cross-verify the three-way data through a sensor fusion algorithm (such as Kalman filtering or Bayesian network). If the preset confidence level is exceeded (such as humidity > 70%, ammonia concentration > 50 ppm, and visual matching degree > 90%), it is determined as excrement stain.

[0088] It is also possible to integrate biological data at a deeper level, analyze the excrement image features (such as abnormal fecal form / color), compare them with the health database, and judge whether the excretor (pet, child) is healthy; for example, for a pet, when watery stool is detected (H value of the HSV color gamut > 30° and texture entropy < 2.5), the intelligent feeder is linked to suspend feeding and push the pet hospital reservation interface.

[0089] In one embodiment, as Figure 8 shown, an operation optimization system for an electronic cleaning device based on the Internet of Things. The cleaning stop module 2 includes:

[0090] An emergency stop unit 21, which is used to immediately trigger a hardware-level interrupt signal after identifying an excrement stain, execute an emergency stop program, cut off the power drive circuits of the roller brush motor and the dust suction fan, quickly brake the mechanical components through a PID algorithm, and at the same time close the dust suction air flow channel to prevent the excrement stain from being inhaled;

[0091] A pollution coordinate marking unit 22, which is used to mark the pollution coordinates through a SLAM map, control the electronic cleaning device to automatically bypass during subsequent cleaning tasks, and at the same time push an alarm and a real-time picture through the App for the user to confirm;

[0092] A device self-processing unit 23, which is used to control the electronic cleaning device to automatically retreat and start a self-cleaning program if the electronic cleaning device has come into contact with an excrement stain.

[0093] In the device self - processing unit 23, if there is still an odor after cleaning, relevant cleaning agents can be recommended. In addition, instead of making the electronic cleaning device automatically retreat and start the self - cleaning program, the movement of the electronic cleaning device can be controlled to stop to prevent the spread of stains.

[0094] In one embodiment, as Figure 9 shown, an operation optimization system for an Internet - of - Things - based electronic cleaning device, the cleaning logic adjustment module 3 includes:

[0095] A risk map construction unit 31, which is used to integrate multi - source home environment data through the Internet of Things, access intelligent devices (such as baby monitors, smart diaper sensors, children's bracelets) to obtain the activity trajectories and daily routines of infants and young children (such as napping periods, post - meal activity areas), and at the same time combine pet collar positioning, temperature and humidity sensor, and camera data to construct a whole - house dynamic risk map;

[0096] A cleaning logic adjustment unit 32, which is used to use spatio - temporal correlation analysis algorithms and machine learning models (such as random forests) to identify high - risk scenarios (for example, food debris is likely to remain in areas where infants and young children often crawl within 1 hour after meals, or the excretion risk increases when the humidity > 80% in the space where pets and children coexist); dynamically adjust the cleaning logic according to high - risk scenarios, and change the cleaning frequency and path of the electronic cleaning device.

[0097] Changing the cleaning frequency and path of the electronic cleaning device can specifically be, for example, automatically avoiding the periphery of the play mat during peak activity periods of infants and young children and switching to silent standby; for example, the excretion probability of the living room carpet increases 1 hour after feeding the pet, so the cleaning frequency of the living room carpet is reduced.

[0098] Taking an actual example, when the smart feeder records that the pet eats at 19:00, the Internet of Things central control synchronously monitors that the temperature and humidity in the living room area rise rapidly (from 25℃ / 50% to 28℃ / 70% within 30 minutes), and the pet collar IMU sensor detects continuous rolling movements (angular velocity > 200° / s). The random forest model determines that the living room is a high - risk area and triggers the following adjustments:

[0099] Path change: Switch the original planned bow - shaped full - coverage path (spacing 15 cm) to a wall - following boundary cruise mode (spacing extended to 50 cm), and bypass the dynamic restricted area with a radius of 1 m centered on the real - time coordinates of the pet through the A* algorithm (an algorithm);

[0100] Frequency control: Pause the cleaning of the living room until the risk is lifted, and at the same time increase the cleaning frequency of the adjacent dining area to 2 times per hour (dynamically mapping the risk of tableware dropping through lidar);

[0101] Device coordination: Link the air purifier to form a downward air current (wind speed 0.3 m / s) in the living room to inhibit the spread of excrement stain odor.

[0102] In one embodiment, Figure 10 As shown, an electronic cleaning equipment operation optimization system based on the Internet of Things, the electronic cleaning equipment operation optimization system based on the Internet of Things also includes:

[0103] The stain coordinate positioning module 4 is used to accurately locate the contaminated area through the SLAM map after identifying the excrement stain, and transmit the coordinate information to the home IoT hub (such as a smart gateway or cloud platform) through the Wi-Fi / Zigbee protocol;

[0104] The odor diffusion prevention module 5 is used to analyze the rooms to which the polluted area belongs, and link the intelligent air conditioner in the area to shut down the air supply function to prevent the odor from spreading to other spaces through the air flow;

[0105] The secondary contact avoidance module 6 is used to automatically activate the virtual electronic fence (through voice prompts, red light warnings with smart lights or automatic closing of pet activity doors) if the contaminated area involves corridors or open spaces, restricting children or pets from entering the contaminated area to avoid secondary contact.

[0106] In addition, scenarios can be expanded based on user habits. For example, if pollution occurs at night, the smart curtains can be closed to block external sight, or soothing sounds can be played through smart speakers to relieve pet anxiety. All linkage commands rely on edge computing to achieve millisecond-level responses, and users can customize rules through the App (such as "only turn off the air conditioner, do not enable the fence") to ensure freedom of life while efficiently controlling pollution. Instructions can also be sent to the air purifiers in the whole house to prioritize the purification intensity of polluted areas (such as switching to "rapid mode"), and accelerate the decomposition of odor molecules through high-efficiency filters and negative ion release.

[0107] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0108] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0109] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0110] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0111] In addition, it should be understood that although this specification is described according to implementation manners, not every implementation manner only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other implementation manners understandable by those skilled in the art.

Claims

1. An operation optimization method for electronic cleaning equipment based on the Internet of Things, characterized in that: The method for optimizing the operation of electronic cleaning equipment based on the Internet of Things includes the following steps: Through multimodal sensors and edge computing technology, ground stains can be sensed in real time to distinguish between common stains and excrement stains; After identifying the excrement stain, the electronic cleaning device is controlled to immediately stop cleaning and turn off the roller brush / vacuum module to prevent the stain from spreading; By coordinating the IoT with home environment data, risk areas can be predicted and cleaning logic can be adjusted.

2. The method for optimizing the operation of electronic cleaning equipment based on the Internet of Things according to claim 1, characterized in that: The step of sensing ground stains in real time and distinguishing common stains from excrement stains by using multimodal sensors and edge computing technology specifically includes: Use liquid detection sensors to monitor ground humidity changes in real time; use gas sensors to analyze odor components in the air; Through the lightweight convolutional neural network model deployed on the edge device, the stain image features collected in real time by the smart camera with integrated AI vision module are compared and analyzed with the excrement feature database pre-trained in the cloud; The three-way data is cross-validated through the sensor fusion algorithm. If it exceeds the preset confidence level, it is determined to be excrement stain.

3. The method for optimizing the operation of electronic cleaning equipment based on the Internet of Things according to claim 1, characterized in that: After the excrement stains are identified, the electronic cleaning device is controlled to immediately stop cleaning and close the roller brush / dust suction module to prevent the stains from spreading, specifically including: After identifying excrement stains, the hardware-level interrupt signal is immediately triggered to execute the emergency stop procedure, cut off the power drive circuit of the roller brush motor and the dust suction fan, quickly brake the mechanical parts through the PID algorithm, and at the same time close the dust suction airflow channel to prevent excrement stains from being sucked in; The contaminated coordinates are marked on the SLAM map, and the electronic cleaning equipment is controlled to automatically detour during subsequent cleaning tasks. At the same time, the App pushes alarms and real-time images for users to confirm. If the electronic cleaning device has come into contact with excrement stains, the electronic cleaning device is controlled to automatically retreat and start a self-cleaning program.

4. The method for optimizing the operation of electronic cleaning equipment based on the Internet of Things according to claim 1, characterized in that: The steps of predicting risk areas and adjusting cleaning logic by coordinating the IoT with home environment data specifically include: Through the Internet of Things, multi-source home environment data is integrated, and smart devices are connected to obtain the activity trajectory and daily routine of infants and young children. At the same time, a dynamic risk map of the whole house is constructed by combining pet collar positioning, temperature and humidity sensors and camera data; Utilize the spatiotemporal correlation analysis algorithm and the machine learning model to identify high-risk scenarios. Dynamically adjust the cleaning logic according to the high-risk scenarios and change the cleaning frequency and path of the electronic cleaning equipment.

5. The method for optimizing the operation of electronic cleaning equipment based on the Internet of Things according to any one of claims 1 to 4, characterized in that: The method for optimizing the operation of electronic cleaning equipment based on the Internet of Things also includes: After identifying the excrement stains, the contaminated area is accurately located through the SLAM map, and the coordinate information is transmitted to the home IoT hub via the Wi-Fi / Zigbee protocol; Analyze the rooms where the pollution area belongs, and link the smart air conditioner in the area to shut down the air supply function to prevent the odor from spreading to other spaces through the airflow; If the contaminated area involves corridors or open spaces, a virtual electronic fence will be automatically activated to restrict children or pets from entering the contaminated area to avoid secondary contact.

6. An electronic cleaning equipment operation optimization system based on the Internet of Things, characterized in that: include: The stain differentiation module is used to sense ground stains in real time and distinguish between common stains and excrement stains through multimodal sensors and edge computing technology; The cleaning stop module is used to control the electronic cleaning device to immediately stop cleaning and turn off the roller brush / dust suction module after identifying excrement stains to prevent the stains from spreading; The cleaning logic adjustment module is used to coordinate with home environment data through the Internet of Things to predict risk areas and adjust the cleaning logic.

7. The electronic cleaning equipment operation optimization system based on the Internet of Things according to claim 6 is characterized in that: The stain differentiation module includes: Humidity and air detection unit, used to monitor the change of ground humidity in real time using liquid detection sensor; analyze the odor components in the air through gas sensor; The image recognition unit is used to compare and analyze the stain image features collected in real time by the lightweight convolutional neural network model deployed on the edge device and the smart camera with the integrated AI vision module with the excrement feature database pre-trained in the cloud; The stain determination unit is used to cross-validate the three-way data through the sensor fusion algorithm. If it exceeds the preset confidence level, it is determined to be excrement stain.

8. The electronic cleaning equipment operation optimization system based on the Internet of Things according to claim 6 is characterized in that: The cleaning stop module includes: The emergency stop unit is used to immediately trigger a hardware-level interrupt signal after identifying excrement stains, execute the emergency stop procedure, cut off the power drive circuit of the roller brush motor and the dust suction fan, quickly brake the mechanical parts through the PID algorithm, and close the dust suction airflow channel to prevent excrement stains from being sucked in; The pollution coordinate marking unit is used to mark the pollution coordinates through the SLAM map, control the electronic cleaning equipment to automatically detour during subsequent cleaning tasks, and push alarms and real-time images through the App for user confirmation; The device self-processing unit is used to control the electronic cleaning device to automatically retreat and start a self-cleaning program if the electronic cleaning device has come into contact with excrement stains.

9. The electronic cleaning equipment operation optimization system based on the Internet of Things according to claim 6, characterized in that: The cleaning logic adjustment module includes: The risk map construction unit is used to integrate multi-source home environment data through the Internet of Things, access smart devices to obtain infant activity trajectories and daily routines, and combine pet collar positioning, temperature and humidity sensors, and camera data to build a dynamic risk map for the entire house; The cleaning logic adjustment unit is used to use the spatiotemporal correlation analysis algorithm to identify high-risk scenarios through a machine learning model; dynamically adjust the cleaning logic according to high-risk scenarios to change the cleaning frequency and path of the electronic cleaning equipment.

10. The electronic cleaning equipment operation optimization system based on the Internet of Things according to any one of claims 6 to 9, characterized in that: The electronic cleaning equipment operation optimization system based on the Internet of Things also includes: The stain coordinate positioning module is used to identify excrement stains, accurately locate the contaminated area through the SLAM map, and transmit the coordinate information to the home IoT hub through the Wi-Fi / Zigbee protocol; The odor prevention module is used to analyze the rooms to which the polluted area belongs, and link the smart air conditioner in the area to shut down the air supply function to prevent the odor from spreading to other spaces through the airflow; The module for avoiding secondary contact is used to automatically activate a virtual electronic fence if the contaminated area involves corridors or open spaces to restrict children or pets from entering the contaminated area to avoid secondary contact.

Images