Smart Home Control System and Method Based on Floor Scrubber

Abstract

The present invention provides a smart home control system and method based on a floor scrubber, which collect the real-time obstacle distribution in the home environment and the activity trajectory data of family members; calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber based on the real-time obstacle distribution and activity trajectory data; use the fuzzy logic algorithm to evaluate the home environment requirements to generate suitable living conditions; based on the suitable living conditions, the living habits data of family members and the historical cleaning data, apply the clustering analysis method and decision tree algorithm to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan; implement the personalized cleaning plan to obtain the air quality index of the home environment, and generate a smart home control solution based on the air quality index; the technical solution provided by the present invention improves the intelligent level and user experience of the smart home system, making it more efficient, comfortable and environmentally friendly.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of smart home, and particularly to a smart home control system and method based on a floor mopping machine. Background Art

[0002] With the development of smart home technology, users' demand for intelligent management of the home environment is increasing day by day. In terms of daily cleaning, users hope that automated devices can complete cleaning tasks efficiently, safely and personalized.

[0003] Currently, the floor mopping machine solutions on the market already have basic obstacle avoidance functions and fixed cleaning path planning, but these solutions still have significant deficiencies. For example, traditional cleaning devices usually rely on simple sensors and preset paths to execute cleaning tasks, and are prone to jamming or collision problems in complex and changeable home environments, affecting cleaning efficiency and device life. Summary of the Invention

[0004] The embodiments of the present invention provide a smart home control system and method based on a floor mopping machine to solve the problems in the prior art that it cannot adapt to changes in the home environment, is prone to jamming or collision problems, and affects cleaning efficiency and device life.

[0005] In a first aspect, the embodiments of the present invention provide a smart home control method based on a floor mopping machine, including:

[0006] Collect real-time obstacle distribution in the home environment and activity trajectory data of family members;

[0007] Based on the real-time obstacle distribution and the activity trajectory data, calculate the obstacle avoidance and seamless coverage cleaning path of the floor mopping machine;

[0008] Based on the obstacle avoidance and seamless coverage cleaning path, use the fuzzy logic algorithm to evaluate the home environment requirements to generate suitable living conditions;

[0009] Based on the suitable living conditions, the living habits data of family members, and the historical cleaning data, apply the clustering analysis method and the decision tree algorithm to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan;

[0010] Implement the personalized cleaning plan to obtain the air quality index of the home environment, and based on the air quality index, dynamically adjust the suction intensity and water flow of the floor mopping machine to generate a smart home control solution.

[0011] Optionally, based on the obstacle avoidance and seamless coverage cleaning path, using the fuzzy logic algorithm to evaluate the home environment requirements to generate suitable living conditions, including:

[0012] Based on the obstacle avoidance and seamless coverage cleaning path, the working state of the floor mopping machine, and the home environment parameters, use the fuzzy logic algorithm to evaluate the demand status of the home environment and obtain the target home environment demand evaluation result;

[0013] Based on the target home environment demand evaluation result, adjust the working state of the target smart home device to generate the target working state;

[0014] Based on the target working state, introduce the adaptive control algorithm to dynamically adjust the operating parameters of each smart home device to generate a suitable living condition, and the operating parameters include the wind speed setting value and the humidity setting value.

[0015] Optionally, based on the obstacle avoidance and seamless coverage cleaning path, the working state of the floor mopping machine, and the home environment parameters, use the fuzzy logic algorithm to evaluate the demand status of the home environment and obtain the target home environment demand evaluation result, including:

[0016] Obtain home environment data from multiple sensors, and the home environment data includes home environment parameters;

[0017] Use the graph neural network to analyze the home layout and device distribution to optimize the application range and accuracy of the home environment data, generate a home environment state description, and use the reinforcement learning algorithm to train the graph neural network during the optimization process to make the graph neural network adapt to the changes in the home layout in real time;

[0018] Based on the obstacle avoidance and seamless coverage cleaning path, the working state of the floor mopping machine, and the home environment state description, use the fuzzy logic algorithm to evaluate the demand status of the home environment to obtain the preliminary home environment demand evaluation result, and use the convolutional neural network to analyze the historical environment data during the evaluation process using the fuzzy logic algorithm to extract potential environmental features to optimize the evaluation;

[0019] Introduce the support vector machine model to identify the best device configuration under different environmental conditions, and combine the preliminary home environment demand evaluation result to generate the target home environment demand evaluation result.

[0020] Optionally, based on the suitable living condition, the living habit data of family members, and the historical cleaning data, apply the clustering analysis method and the decision tree algorithm to formulate a preliminary cleaning plan and optimize the preliminary cleaning plan to generate a personalized cleaning plan, including:

[0021] Use the clustering analysis method to group the suitable living condition, the living habit data of family members, and the historical cleaning data to obtain the cleaning task classification;

[0022] Based on the above cleaning task classification, apply the decision tree algorithm to determine the optimal cleaning order and optimal cleaning frequency to generate a preliminary cleaning plan;

[0023] Obtain family member activity images, apply the object detection algorithm to analyze the family member activity images to calculate the stay time and activity frequency of family members in each room. Based on the stay time and activity frequency, use the bidirectional long short-term memory network to predict the long-term activity trend of family members to refine the preliminary cleaning plan and obtain a refined cleaning plan;

[0024] Use the reinforcement learning algorithm to simulate the application effects of different cleaning strategies in the refined cleaning plan to search for the combination of the best cleaning time and optimal cleaning frequency. Based on the combination of the best cleaning time and optimal cleaning frequency, use the Bayesian optimization algorithm to optimize the refined cleaning plan to obtain a personalized cleaning plan.

[0025] Optionally, obtain family member activity images, apply the object detection algorithm to analyze the family member activity images to calculate the stay time and activity frequency of family members in each room. Based on the stay time and activity frequency, use the bidirectional long short-term memory network to predict the long-term activity trend of family members to refine the preliminary cleaning plan and obtain a refined cleaning plan, including:

[0026] Obtain family member activity images, apply the object detection algorithm to identify the target objects in the family member activity images to obtain family member position information;

[0027] Based on the family member position information, calculate the stay time and activity frequency of family members in each room, use the spatio-temporal graph convolutional network to classify the stay time and activity frequency to obtain a classification result, and based on the classification result, identify the behavior patterns of family members;

[0028] Use the bidirectional long short-term memory network to analyze the stay time, the activity frequency, and the behavior patterns to obtain a behavior analysis result. Based on the behavior analysis result, predict the long-term activity trend of family members to generate a long-term activity trend prediction result;

[0029] Based on the long-term activity trend prediction result, adjust the cleaning frequency and cleaning time corresponding to each room to obtain the adjusted cleaning frequency and cleaning time. Use the adjusted cleaning frequency and cleaning time to refine the preliminary cleaning plan to obtain a refined cleaning plan.

[0030] Optionally, based on the real-time obstacle distribution and the activity trajectory data, calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber, including:

[0031] Generate fused data based on the real-time obstacle distribution and the activity trajectory data;

[0032] Apply a convolutional neural network to extract features from the fused data to identify the position information of obstacles and the activity patterns of family members. Based on the position information of the obstacles and the activity patterns of family members, generate a preliminary home environment map, and use the simultaneous localization and mapping algorithm to perform real-time update processing on the preliminary home environment map to obtain an updated home environment map;

[0033] Based on the updated home environment map, use the A* algorithm and the plowing path planning algorithm to calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber.

[0034] Optionally, implement the personalized cleaning plan to obtain the air quality index of the home environment. Based on the air quality index, dynamically adjust the suction intensity and water flow rate of the floor scrubber to generate a smart home control scheme, including:

[0035] Implement the personalized cleaning plan and use multiple sensors to continuously monitor the air quality index of the home environment during the implementation of the personalized cleaning plan;

[0036] Based on the air quality index, use a long short-term memory network to predict the air quality change trend. According to the air quality change trend and the demand status of the home environment, use a fuzzy logic control system to dynamically adjust the suction intensity and water flow rate of the floor scrubber to obtain an adjusted cleaning operation result;

[0037] Based on the adjusted cleaning operation result, use the ant colony optimization algorithm to generate a smart home control scheme.

[0038] In a second aspect, an embodiment of the present invention provides a smart home control system based on a floor scrubber, including:

[0039] A collection module for collecting the real-time obstacle distribution in the home environment and the activity trajectory data of family members;

[0040] A calculation module for calculating the obstacle avoidance and seamless coverage cleaning path of the floor scrubber based on the real-time obstacle distribution and the activity trajectory data;

[0041] An evaluation module for using the fuzzy logic algorithm to evaluate the home environment demand for the obstacle avoidance and seamless coverage cleaning path to generate suitable living conditions;

[0042] An optimization module for formulating a preliminary cleaning plan based on the suitable living conditions, the living habit data of family members, and the historical cleaning data, and optimizing the preliminary cleaning plan to generate a personalized cleaning plan;

[0043] A generation module for implementing the personalized cleaning plan to obtain the air quality index of the home environment, and dynamically adjusting the suction intensity and water flow rate of the floor scrubber based on the air quality index to generate a smart home control solution.

[0044] In a third aspect, an embodiment of the present invention provides a computing device, including a processor and a memory. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the smart home control method based on the floor scrubber according to any one of the first aspects.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the smart home control method based on the floor scrubber according to any one of the first aspects is implemented.

[0046] In the embodiments of the present invention, the real-time obstacle distribution in the home environment and the activity trajectory data of family members are collected; based on the real-time obstacle distribution and the activity trajectory data, the obstacle avoidance and seamless coverage cleaning path of the floor scrubber are calculated; based on the obstacle avoidance and seamless coverage cleaning path, the fuzzy logic algorithm is used to evaluate the home environment requirements to generate suitable living conditions; based on the suitable living conditions, the living habits data of family members, and the historical cleaning data, the clustering analysis method and the decision tree algorithm are applied to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan; implement the personalized cleaning plan to obtain the air quality index of the home environment, and dynamically adjust the suction intensity and water flow rate of the floor scrubber based on the air quality index to generate a smart home control solution. The technical solution provided by the present invention ensures that the floor scrubber efficiently and safely completes the cleaning task through the obstacle avoidance and seamless coverage cleaning path, uses the fuzzy logic algorithm to evaluate the home environment requirements to generate suitable living conditions, and formulates a personalized cleaning plan in combination with the living habits data of family members and the historical cleaning data, which can adapt to the specific needs of different families and improve the user experience; dynamically adjusting the suction intensity and water flow rate of the floor scrubber improves the cleaning effect and reduces resource waste; the smart home control solution minimizes energy consumption and noise impact on the premise of ensuring the cleaning effect, thereby optimizing the operation efficiency and performance of the entire smart home system and realizing efficient, comfortable and environmentally friendly home environment management. Among them, based on the long-term activity trend prediction results, the system dynamically adjusts the cleaning frequency and cleaning time of each room, refines the preliminary cleaning plan, and generates a personalized cleaning plan to ensure the best cleaning effect and user experience; the system monitors and predicts the air quality change trend in real time and dynamically adjusts the operation parameters of the floor scrubber, improving the cleaning effect and reducing resource waste.

[0047] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0049] Figure 1 It is a flowchart of a smart home control method based on a floor scrubber provided by an embodiment of the present invention;

[0050] Figure 2 It is a schematic structural diagram of a smart home control system based on a floor scrubber provided by an embodiment of the present invention;

[0051] Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0053] In some processes described in the specification, claims and the above drawings of the present invention, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The operation numbers such as 101, 102, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are different types.

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0055] Figure 1 It is a flowchart of a smart home control method based on a floor scrubber provided by an embodiment of the present invention. As Figure 1 shown, the method includes:

[0056] With the continuous development of smart home technology, users have put forward higher requirements for the intelligent management of the home environment. In terms of daily cleaning, users expect that automated devices can not only complete cleaning tasks efficiently and safely, but also provide personalized cleaning solutions according to the living habits of family members and real-time environmental changes. In addition, real-time monitoring and improvement of indoor air quality are also important requirements for enhancing living comfort. However, existing floor mopping machine solutions still have many deficiencies in aspects such as intelligent obstacle avoidance and air quality control. Based on this, the present invention provides a smart home regulation method based on a floor mopping machine, such as Figure 1 , including:

[0057] Step 101: Collect the real-time obstacle distribution in the home environment and the activity trajectory data of family members;

[0058] In this step, the real-time obstacle distribution refers to the real-time position and shape information of all obstacles in the home environment obtained through sensors (such as lidar, ultrasonic sensors, etc.). The activity trajectory data of family members refers to the moving paths and staying times of family members in different rooms recorded by cameras or other sensors (such as infrared sensors) obtained through cameras or other sensors (such as infrared sensors).

[0059] This step collects the real-time obstacle distribution and the activity trajectory data of family members through sensors (such as lidar, ultrasonic sensors, cameras, etc.) installed in each room of the home. For example, in a typical home environment, there may be furniture such as sofas and coffee tables in the living room, and the positions and shapes of these obstacles will be accurately captured by lidar sensors. At the same time, the camera will record the activity trajectories of family members, such as children playing in the living room and adults cooking in the kitchen. These data are transmitted to the central control system for further processing.

[0060] Step 102: Based on the real-time obstacle distribution and the activity trajectory data, calculate the obstacle avoidance and seamless coverage cleaning path of the floor mopping machine;

[0061] In this step, the obstacle avoidance and seamless coverage cleaning path refers to the optimal cleaning path of the floor mopping machine calculated based on the real-time obstacle distribution and the activity trajectory of family members, ensuring efficient and complete coverage of the entire cleaning area.

[0062] In this step, after receiving the obstacle distribution and activity trajectory data, an advanced path planning algorithm is used to calculate the obstacle avoidance and seamless coverage cleaning path of the floor mopping machine in combination with these data. For example, in the above scenario, the system will plan a path to avoid the sofa and coffee table and ensure that the floor mopping machine can efficiently and completely cover the entire living room area. This kind of path planning not only improves the cleaning efficiency, but also avoids the situation of the floor mopping machine getting stuck or colliding.

[0063] Step 103: Based on the obstacle avoidance and seamless coverage cleaning path, use the fuzzy logic algorithm to evaluate the household environment requirements to generate suitable living conditions;

[0064] In this step, after calculating the obstacle avoidance and seamless coverage cleaning path, the fuzzy logic algorithm is used to evaluate the household environment requirements to generate suitable living conditions. For example, if the humidity is high and there is an odor in the current household environment, the fuzzy logic algorithm may recommend increasing the running time and intensity of the air purifier, and at the same time adjusting the water flow rate of the floor scrubber to improve the cleaning effect. This method can flexibly respond to different environmental conditions and provide more comfortable living conditions.

[0065] Step 104: Based on the suitable living conditions, the living habits data of family members, and the historical cleaning data, apply the clustering analysis method and decision tree algorithm to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan;

[0066] In this step, combining the suitable living conditions, the living habits data of family members (such as children often playing in the living room and adults usually cleaning before going to bed at night), and the historical cleaning data, the clustering analysis method and decision tree algorithm are used to formulate a preliminary cleaning plan. For example, the system may classify family members into two categories: active during the day and active at night, and formulate corresponding cleaning plans according to their activity times. Then, further optimize the preliminary cleaning plan to generate a personalized cleaning plan. This can ensure that the cleaning tasks meet the specific needs of each family member and improve the overall cleaning efficiency.

[0067] Step 105: Implement the personalized cleaning plan, obtain the air quality index of the household environment, and based on the air quality index, dynamically adjust the suction intensity and water flow rate of the floor scrubber to generate a smart home control plan;

[0068] In this step, the air quality index refers to the air quality parameters in the household environment monitored in real time by various sensors (such as PM2.5 sensors, carbon dioxide sensors, humidity sensors, etc.), including particulate matter concentration, carbon dioxide concentration, humidity, and temperature, etc.

[0069] During this step in the implementation of the personalized cleaning plan, various sensors are used to continuously monitor the air quality indicators of the home environment. For example, a PM2.5 sensor may detect a relatively high concentration of particulate matter in the living room area. Based on these air quality indicators, a long short-term memory network is used to predict the future trend of air quality changes, and a fuzzy logic control system is utilized to dynamically adjust the suction intensity and water flow rate of the floor scrubber. Assuming that it is predicted that the particulate matter concentration will continue to rise, the system will increase the suction intensity and the water flow rate to more effectively remove dust and pollutants. Finally, based on the adjusted cleaning operation results, an ant colony optimization algorithm is used to generate a smart home regulation plan to ensure the best overall home environment management effect.

[0070] In the embodiment of the present invention, by collecting the obstacle distribution and the activity trajectory data of family members in real time, the system can calculate an efficient obstacle avoidance and seamless coverage cleaning path to ensure the safety and coverage rate of the cleaning process; use the fuzzy logic algorithm to evaluate the home environment requirements to generate suitable living conditions, improving the living comfort; combine the clustering analysis method and the decision tree algorithm to formulate and optimize the personalized cleaning plan, making the cleaning tasks more in line with the specific needs of each family member; by continuously monitoring the air quality and dynamically adjusting the operation parameters of the floor scrubber, the cleaning effect is further improved, and a comprehensive optimized smart home regulation plan is generated. This method not only improves the cleaning efficiency and user experience, but also significantly enhances the cleanliness, comfort and intelligent management level of the home environment. In addition, through intelligent management and optimization, the system can save energy to the greatest extent while ensuring the cleaning effect, achieving the goal of green environmental protection.

[0071] Traditional cleaning equipment usually relies on fixed parameter settings to perform cleaning tasks and cannot dynamically adjust its operation mode according to the complex home environment. To overcome this limitation, a specific embodiment of the present invention provides step 103, based on the obstacle avoidance and seamless coverage cleaning path, using the fuzzy logic algorithm to evaluate the home environment requirements to generate suitable living conditions, specifically including the following steps:

[0072] Step 301: Based on the obstacle avoidance and seamless coverage cleaning path, the working state of the floor scrubber, and the home environment parameters, use the fuzzy logic algorithm to evaluate the demand status of the home environment to obtain the target home environment demand evaluation result;

[0073] In this step, the working state of the floor scrubber refers to the current operation parameters and running state of the floor scrubber, such as suction intensity, water flow rate, battery power, etc. The home environment parameters refer to various environmental factors including temperature, humidity, air quality (such as PM2.5 concentration, carbon dioxide concentration), light intensity, etc.

[0074] This step collects the obstacle avoidance and seamless coverage cleaning path of the floor scrubber, the current working status (such as medium suction intensity and low water flow rate), and the home environment parameters (such as living room temperature of 22°C, humidity of 50%, and PM2.5 concentration of 30 µg / m³). Then, the fuzzy logic algorithm is used to comprehensively analyze these data to evaluate the demand status of the home environment. For example, in a family with children, if it is detected that the humidity in the bedroom is low and the PM2.5 concentration is high, the fuzzy logic algorithm may recommend increasing the humidity and raising the operating intensity of the air purifier. In this way, the evaluation result of the target home environment demand can be generated to guide the subsequent adjustment of smart home devices.

[0075] Step 302: Based on the evaluation result of the home environment demand, adjust the working status of the target smart home device to generate a target working status;

[0076] This step adjusts the working status of the target smart home device according to the evaluation result of the home environment demand. For example, the system will adjust the humidity setting value of the humidifier from 40% to 55%, and adjust the wind speed setting value of the air purifier from low gear to high gear. In addition, the system will also adjust the temperature setting value of the air conditioner from 24°C to 22°C to ensure a suitable indoor temperature. Through these adjustments, a target working status is generated, enabling each smart home device to work together to jointly improve the quality of the home environment.

[0077] Step 303: Based on the target working status, introduce an adaptive control algorithm to dynamically adjust the operating parameters of each smart home device to generate suitable living conditions, where the operating parameters include wind speed setting values and humidity setting values;

[0078] This step introduces an adaptive control algorithm after generating the target working status to dynamically adjust the operating parameters of each smart home device according to real-time feedback. For example, when the humidity sensor detects that the humidity in the bedroom has reached 55%, the system will automatically reduce the operating intensity of the humidifier; if the PM2.5 sensor detects that the particulate matter concentration is still high, the system will continue to maintain the high gear wind speed operation of the air purifier until the air quality meets the standard. Through this dynamic adjustment mechanism, the system can not only quickly respond to environmental changes but also ensure that each device operates in the best state, thereby generating more suitable living conditions. The specific operating parameters include wind speed setting values and humidity setting values, as well as other relevant parameters such as temperature setting values and lighting intensity.

[0079] In the embodiments of the present invention, by comprehensively analyzing the obstacle avoidance and seamless coverage cleaning path, the working state of the floor mopping machine, and the home environment parameters, and using the fuzzy logic algorithm to generate the evaluation result of the target home environment requirements, the comprehensiveness and accuracy of the evaluation are ensured; based on the evaluation result, the working state of the target smart home device is adjusted to generate the target working state, enabling each device to work collaboratively to jointly improve the home environment quality; by introducing the adaptive control algorithm to dynamically adjust the operating parameters of each smart home device, the system can quickly respond to environmental changes and ensure that the devices operate in the best state, thereby generating more suitable living conditions.

[0080] To formulate a more accurate and personalized cleaning strategy, it is necessary to more accurately evaluate the demand status of the home environment. Based on this, the present invention provides a specific embodiment. In step 301, based on the obstacle avoidance and seamless coverage cleaning path, the working state of the floor mopping machine, and the home environment parameters, the fuzzy logic algorithm is used to evaluate the demand status of the home environment, and the target home environment demand evaluation result is obtained, which specifically includes the following steps:

[0081] Step 311: Obtain home environment data from multiple sensors, where the home environment data includes home environment parameters;

[0082] In this step, the home environment data refers to the home environment parameters obtained from multiple sensors (such as temperature sensors, humidity sensors, PM2.5 sensors, etc.), including temperature, humidity, air quality, etc.

[0083] In this step, home environment data is obtained from multiple sensors (such as temperature sensors, humidity sensors, PM2.5 sensors, etc.) installed in each room. For example, in a typical home environment, the living room may be equipped with temperature sensors, humidity sensors, and PM2.5 sensors, which will monitor and transmit data to the central control system in real time. Suppose the current temperature in the living room is 22 °C, the humidity is 50%, and the PM2.5 concentration is 30 µg / m³. These data form the basis of the home environment parameters for subsequent steps.

[0084] Step 312: Use the graph neural network to analyze the home layout and device distribution to optimize the application range and accuracy of the home environment data, generate a home environment state description, and use the reinforcement learning algorithm to train the graph neural network during the optimization process to enable the graph neural network to adapt to changes in the home layout in real time;

[0085] In this step, the home environment state description refers to the overall description of the home environment generated based on the analysis result of the graph neural network, including room layout, device location, and its operating state, etc.

[0086] This step uses a graph neural network to analyze the home layout and device distribution. For example, the system generates a graphical structure data model based on the positions of sensors and device distribution, where nodes represent rooms or devices, and edges represent the connection relationships between them. Then, a reinforcement learning algorithm is used to train the graph neural network to enable it to adapt to changes in the home layout in real time. For example, when family members move furniture or add new devices, the graph neural network automatically adjusts its model to ensure the accuracy of the description of the home environment state. The finally generated home environment state description includes the layout of each room, the device positions, and their operating states, providing a comprehensive view of the home environment.

[0087] Step 313: Based on the obstacle avoidance and seamless coverage cleaning path, the working state of the floor scrubber, and the home environment state description, use a fuzzy logic algorithm to evaluate the demand status of the home environment, obtaining a preliminary home environment demand evaluation result. During the evaluation using the fuzzy logic algorithm, a convolutional neural network is used to analyze historical environment data to extract potential environment features for optimizing the evaluation;

[0088] This step combines the obstacle avoidance and seamless coverage cleaning path, the working state of the floor scrubber (such as medium suction intensity and low water flow rate), and the home environment state description, and uses a fuzzy logic algorithm to evaluate the demand status of the home environment. For example, in the above scenario, if it is detected that the humidity in the bedroom is low and the PM2.5 concentration is high, the fuzzy logic algorithm may recommend increasing the humidity and raising the operating intensity of the air purifier. To optimize the evaluation result, the system also uses a convolutional neural network to analyze historical environment data to extract potential environment features. For example, the convolutional neural network can analyze the humidity change trend in the bedroom in the past week to help the system more accurately predict future humidity requirements. Through this comprehensive evaluation, the system generates a preliminary home environment demand evaluation result.

[0089] To accurately evaluate the demand status of the home environment and optimize the operating parameters of smart home devices accordingly. Embodiments of the present invention also provide a calculation formula for the preliminary home environment demand evaluation result. This formula takes into account the multiple influences of current home environment parameters, historical environment data, family member activity patterns, and smart home device states, and uses advanced algorithms such as graph neural networks, fuzzy logic algorithms, and long short-term memory networks to dynamically adjust the cleaning strategy to achieve more intelligent and precise home environment management. The specific calculation formula is as follows:

[0090] ;

[0091] represents the preliminary home environment demand evaluation result; represents the weighted average of home environment parameters The weight coefficient of; Represents the weighted average of historical environmental data as the weight coefficient; Represents the weighted impact of family member activity patterns as the weight coefficient; Represents a function based on the description of the home environment status as the weight coefficient; Represents a function based on the working status of the floor scrubber as the weight coefficient; as the weight coefficient; Represents the weight coefficient of the function based on the working status of the floor scrubber

[0092] Through the application of the above-mentioned formula for the preliminary home environment demand assessment results, the system can significantly improve the accuracy and intelligence level of home environment assessment. Specifically, this formula comprehensively considers the current environmental parameters, historical data, family member activity patterns, and device status, making the preliminary home environment demand assessment results more comprehensive and accurate, and being able to better reflect the actual needs of the home environment; through this formula, the system can dynamically adjust the cleaning strategy according to the real-time changing home environment to ensure the best cleaning effect and living experience; through reasonable weight setting and dynamic adjustment, the system can save energy to the greatest extent on the premise of ensuring the cleaning effect and achieve the goal of green environmental protection; through this formula, the system can intelligently arrange cleaning tasks according to the habits and activity patterns of family members, avoid disturbing the normal life of family members, and improve the overall living comfort.

[0093] Step 314: Introduce a support vector machine model to identify the best device configuration under different environmental conditions, and combine with the preliminary home environment demand assessment results to generate the target home environment demand assessment results;

[0094] After generating the preliminary home environment demand assessment results in this step, a support vector machine model is introduced to identify the best device configuration under different environmental conditions. For example, the support vector machine model can recommend the most suitable settings for humidifiers, air conditioners, and air purifiers according to the current humidity, temperature, and air quality indicators. Combining with the preliminary home environment demand assessment results, the system generates the target home environment demand assessment results. For example, the system may adjust the humidity setting value of the humidifier from 40% to 55% and adjust the wind speed setting value of the air purifier from low gear to high gear. Through this comprehensive analysis and optimization, the system can generate more accurate target home environment demand assessment results, ensure that each smart home device can operate in the best state, and improve the overall home environment quality.

[0095] The embodiments of the present invention obtain home environment data from multiple sensors, analyze the home layout and device distribution using graph neural networks, and generate a description of the home environment state, ensuring the scope and accuracy of data application; by analyzing historical environment data through a fuzzy logic algorithm combined with a convolutional neural network, the system can more accurately evaluate the demand situation of the home environment and generate a preliminary home environment demand assessment result; introducing a support vector machine model to identify the optimal device configuration under different environmental conditions, and combining the preliminary assessment result to generate a target home environment demand assessment result, enabling each smart home device to operate in the best state and improving the overall quality of the home environment.

[0096] Traditional cleaning devices usually rely on fixed parameter settings to perform cleaning tasks and cannot dynamically adjust their operation modes according to the unique needs of each family. Based on this, in order to better adapt to the specific needs of different families, the present invention provides a specific embodiment. Step 104: Based on the suitable living conditions, the living habit data of family members, and the historical cleaning data, apply the clustering analysis method and decision tree algorithm to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan, which specifically includes the following steps:

[0097] Step 401: Use the clustering analysis method to group the suitable living conditions, the living habit data of family members, and the historical cleaning data to obtain cleaning task classifications;

[0098] In this step, the living habit data of family members refers to the time and location information recording the daily activities of family members. For example, a certain family member usually activities in the kitchen between 7 am and 8 am. The historical cleaning data refers to the records of cleaning tasks in the past period, including cleaning time, frequency, and effect, etc.

[0099] This step uses the clustering analysis method to group the suitable living conditions, the living habit data of family members, and the historical cleaning data. For example, in a family of four, the system may divide a day into several time periods according to the habits of family members (such as 7 am to 8 am is breakfast time, and 6 pm to 8 pm is dinner time), and combine the suitable living conditions (such as the bedroom needs to maintain a relatively high humidity and a relatively low PM2.5 concentration) and historical cleaning data (such as a comprehensive cleaning is carried out at 9 am every Saturday). Through clustering analysis, the system groups these data to generate different cleaning task classifications, such as morning cleaning, evening cleaning, and weekend general cleaning.

[0100] Step 402: Based on the cleaning task classifications, apply the decision tree algorithm to determine the optimal cleaning order and optimal cleaning frequency to generate a preliminary cleaning plan;

[0101] After generating the cleaning task classification, this step applies a decision tree algorithm to determine the optimal cleaning order and optimal cleaning frequency for each classification. For example, for tasks to be cleaned in the morning, the system may suggest cleaning the kitchen first (because family members are active there frequently in the morning), and then the living room; for tasks of weekend thorough cleaning, it is recommended to start from the bedroom and gradually expand to other rooms. In this way, the system generates a preliminary cleaning plan. Suppose the decision tree algorithm analyzes that the best cleaning order is to clean high-frequency activity areas first and then low-frequency activity areas, and the best cleaning frequency is to clean high-frequency activity areas once every morning and conduct a comprehensive cleaning once a week. This can ensure that the cleaning tasks are both efficient and meet the actual needs of family members.

[0102] Step 403: Obtain family member activity images, apply an object detection algorithm to analyze the family member activity images to calculate the stay time and activity frequency of family members in each room, and based on the stay time and activity frequency, use a bidirectional long short-term memory network to predict the long-term activity trend of family members to refine the preliminary cleaning plan and obtain a refined cleaning plan;

[0103] This step obtains the activity images of family members through a camera or other sensors, and applies an object detection algorithm to analyze these images to calculate the stay time and activity frequency of family members in each room. For example, the system finds that a certain family member often stays in the study for two hours on weekday evenings, and is more active in the living room on weekends. Then, the system uses a bidirectional long short-term memory network to analyze these stay times and activity frequencies to predict the long-term activity trend of family members. Suppose the bidirectional long short-term memory network predicts that the activity time of this family member in the study will gradually decrease and the activity time in the living room will increase in the next few weeks. Based on these prediction results, the system refines the preliminary cleaning plan, adjusts the cleaning frequency and key areas, and generates a refined cleaning plan. For example, the system may suggest reducing the cleaning frequency of the study and increasing the number of cleaning times in the living room.

[0104] Step 404: Use a reinforcement learning algorithm to simulate the application effects of different cleaning strategies in the refined cleaning plan to search for the combination of the best cleaning time and optimal cleaning frequency, and based on the combination of the best cleaning time and optimal cleaning frequency, use a Bayesian optimization algorithm to optimize the refined cleaning plan to obtain a personalized cleaning plan;

[0105] After generating the refined cleaning plan, this step uses a reinforcement learning algorithm to simulate the application effects of different cleaning strategies to search for the optimal combination of cleaning time and frequency. For example, the system will simulate the cleaning effects at different time periods (such as 7 am, 12 noon, 8 pm), and record the changes in environmental quality and family member feedback after each cleaning. Through this simulation, the system finds the optimal combination of cleaning time and frequency. Suppose the reinforcement learning algorithm discovers that cleaning at 7 am can significantly improve the air quality during the day, while cleaning at 8 pm is more conducive to night-time rest. Finally, the system uses the Bayesian optimization algorithm to further optimize the refined cleaning plan to ensure the best overall cleaning effect. For example, the Bayesian optimization algorithm may suggest focusing the morning cleaning on high-frequency activity areas, while concentrating on the bedroom at night, ultimately generating a personalized cleaning plan.

[0106] The embodiments of the present invention use a clustering analysis method to group the data of suitable living conditions, family members' living habits, and historical cleaning data to generate cleaning task classifications, ensuring the effectiveness and practicality of the data; applying a decision tree algorithm to determine the optimal cleaning order and frequency to generate a preliminary cleaning plan, making the cleaning tasks more efficient and meeting the actual needs; by obtaining family member activity images and applying object detection algorithms and bidirectional long short-term memory networks, the system can accurately calculate the stay time and activity frequency of family members and predict their long-term activity trends, thereby refining the cleaning plan and improving the accuracy of the plan; by simulating the application effects of different cleaning strategies using a reinforcement learning algorithm and optimizing the cleaning plan using the Bayesian optimization algorithm, the system can generate a personalized cleaning solution to ensure the best cleaning effect and user experience.

[0107] Traditional cleaning equipment cannot dynamically adjust its operation mode according to the specific activity patterns of each family member. To better adapt to the unique living habits of different family members, based on this, the present invention provides a specific embodiment, step 403, obtaining family member activity images, applying an object detection algorithm to analyze the family member activity images to calculate the stay time and activity frequency of family members in each room, and based on the stay time and activity frequency, using a bidirectional long short-term memory network to predict the long-term activity trends of family members to refine the preliminary cleaning plan to obtain a refined cleaning plan, specifically including the following steps:

[0108] Step 411: Obtain family member activity images, and apply an object detection algorithm to identify the target objects in the family member activity images to obtain family member position information;

[0109] In this step, the family member activity images refer to the activity videos or images of family members in different rooms obtained through cameras or other sensors.

[0110] This step obtains the activity images of family members through cameras installed in each room. For example, in a family of four, the system can capture the movement of a certain family member between the living room, bedroom, and kitchen. Then, target detection algorithms are applied to analyze these images to identify the specific locations of family members. Suppose the system detects that a certain family member appears in the kitchen at 7 am and then enters the living room at 8 am. In this way, the system can obtain the location information of this family member in each room.

[0111] Step 412: Based on the location information of family members, calculate the residence time and activity frequency of family members in each room, use a spatio-temporal graph convolutional network to classify the residence time and activity frequency, obtain a classification result, and based on the classification result, identify the behavior patterns of family members;

[0112] In this step, the location information of family members refers to the specific locations of family members in each room identified based on target detection algorithms. The residence time and activity frequency refer to the length of time and the frequency of family members staying in each room. The behavior pattern refers to the behavioral characteristics identified based on the residence time and activity frequency of family members, such as being active in the kitchen in the morning and resting in the living room at night.

[0113] After obtaining the location information of family members in this step, calculate their residence time and activity frequency in each room. For example, the system finds that a certain family member is active in the kitchen from 7 am to 8 am every morning and in the living room from 5 pm to 7 pm. Then, the system uses a spatio-temporal graph convolutional network to classify these residence times and activity frequencies to generate a classification result. Suppose the spatio-temporal graph convolutional network classifies the above behaviors as being active in the kitchen in the morning and in the living room in the afternoon. Based on these classification results, the system further identifies the behavior patterns of family members, such as preparing breakfast in the kitchen in the morning and relaxing in the living room in the afternoon.

[0114] Step 413: Use a bidirectional long short-term memory network to analyze the residence time, the activity frequency, and the behavior patterns to obtain a behavior analysis result, and based on the behavior analysis result, predict the long-term activity trend of family members to generate a long-term activity trend prediction result;

[0115] This step uses a bidirectional long short-term memory network to comprehensively analyze the residence time, activity frequency, and behavior patterns, generating behavior analysis results. For example, the bidirectional long short-term memory network may find that a certain family member has a significantly higher activity frequency on weekends than on weekdays and spends more time in the living room and study. Based on these behavior analysis results, the system further predicts the long-term activity trends of family members. Suppose the bidirectional long short-term memory network predicts that this family member will be more active in the living room and study on weekends in the next few weeks, while mainly concentrating in the kitchen and bedroom on weekdays. In this way, the system generates the long-term activity trend prediction results, providing a prediction of future family member activities.

[0116] Step 414: Based on the long-term activity trend prediction results, adjust the cleaning frequency and cleaning time corresponding to each room to obtain the adjusted cleaning frequency and cleaning time, and use the adjusted cleaning frequency and cleaning time to refine the preliminary cleaning plan to obtain the refined cleaning plan;

[0117] After generating the long-term activity trend prediction results in this step, the system dynamically adjusts the cleaning frequency and cleaning time of each room according to these prediction results. For example, if the prediction results show that a certain family member will be more active in the living room and study on weekends in the next few weeks, the system will correspondingly increase the cleaning frequency of these two rooms and may adjust the cleaning time to a certain period before the weekend. Suppose the system decides to increase the cleaning frequency of the living room from once a week to once every three days and the cleaning frequency of the study from twice a week to once every two days. In this way, the system refines the preliminary cleaning plan, generating a more accurate refined cleaning plan to ensure that the cleaning tasks of each room are both efficient and meet the actual needs.

[0118] In the embodiments of the present invention, by acquiring family member activity images and applying object detection algorithms, the system can accurately identify the specific locations of family members, ensuring the accuracy of data; based on the location information of family members, the system calculates their residence time and activity frequency in each room and uses a spatio-temporal graph convolutional network for classification to identify the behavior patterns of family members, enhancing the depth and breadth of data analysis; by analyzing the residence time, activity frequency, and behavior patterns through a bidirectional long short-term memory network, the system can predict the long-term activity trends of family members, providing the ability to predict future activities; based on the long-term activity trend prediction results, the system dynamically adjusts the cleaning frequency and cleaning time of each room, refines the preliminary cleaning plan, and generates a personalized cleaning plan to ensure the best cleaning effect and user experience.

[0119] Traditional cleaning devices usually rely on simple sensors and preset paths to perform cleaning tasks, which makes them inadequate when facing a dynamically changing home environment. To overcome this limitation, based on this, the present invention provides a specific embodiment. Step 102: Based on the real-time obstacle distribution and the activity trajectory data, calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber, specifically including the following steps:

[0120] Step 201: Based on the real-time obstacle distribution and the activity trajectory data, generate fused data;

[0121] In this step, the system fuses the real-time obstacle distribution and the activity trajectory data together to generate fused data, which serves as the basis for subsequent analysis.

[0122] Step 202: Apply a convolutional neural network to extract features from the fused data to identify the position information of obstacles and the activity patterns of family members. Based on the position information of the obstacles and the activity patterns of family members, generate a preliminary home environment map, and use the simultaneous localization and mapping algorithm to perform real-time update processing on the preliminary home environment map to obtain an updated home environment map;

[0123] In this step, after generating the fused data, a convolutional neural network is applied to extract features from these data to identify the position information of obstacles and the activity patterns of family members. For example, the convolutional neural network can identify the specific positions of obstacles such as sofas and coffee tables in the living room and determine the time periods and frequencies of family members' activities in the living room. Based on these features, the system generates a preliminary home environment map. To ensure the accuracy and real-time nature of the map, the system uses the simultaneous localization and mapping algorithm to perform real-time update processing on the preliminary home environment map. Suppose a family member moves a piece of furniture or changes their activity pattern, the simultaneous localization and mapping algorithm will automatically adjust the map to ensure that it always remains up-to-date, and finally generate an updated home environment map.

[0124] Step 203: Based on the updated home environment map, use the A* algorithm and the ploughing path planning algorithm to calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber;

[0125] After generating the updated home environment map, the system uses the A* algorithm and the plowing path planning algorithm to calculate the obstacle avoidance and seamless coverage cleaning path for the floor scrubber. For example, based on the distribution of obstacles in the updated home environment map, the system uses the A* algorithm to calculate the optimal path from the starting point to the ending point, ensuring avoidance of all obstacles. At the same time, the system uses the plowing path planning algorithm to ensure seamless coverage of the cleaning area, avoiding omission or repeated cleaning. Suppose the system calculates a cleaning path that starts from the living room entrance, bypasses the sofa and coffee table, and finally covers the entire living room. This path planning not only improves the cleaning efficiency but also ensures the cleaning quality.

[0126] In the embodiment of the present invention, by integrating the real-time obstacle distribution and activity trajectory data, the system generates the integrated data, providing a comprehensive basis for subsequent analysis; applying a convolutional neural network to extract features from the integrated data, identifying the position information of obstacles and the activity patterns of family members, generating a preliminary home environment map, and updating the map in real time through the simultaneous localization and mapping algorithm, ensuring the accuracy and real-time nature of the map; based on the updated home environment map, the system uses the A* algorithm and the plowing path planning algorithm to calculate the obstacle avoidance and seamless coverage cleaning path for the floor scrubber, ensuring that the cleaning task is both efficient and without omission.

[0127] Traditional cleaning devices usually rely on fixed suction intensity and water flow rate settings to perform cleaning tasks and cannot be dynamically adjusted according to changes in real-time air quality. To overcome this limitation, based on this, the present invention provides a specific embodiment, step 105, implementing the personalized cleaning plan to obtain the air quality index of the home environment, and based on the air quality index, dynamically adjusting the suction intensity and water flow rate of the floor scrubber to generate a smart home control solution, specifically including the following steps:

[0128] Step 501: Implement the personalized cleaning plan and use multiple sensors to monitor the air quality index of the home environment in real time during the implementation of the personalized cleaning plan.

[0129] When starting the personalized cleaning plan, the floor scrubber starts to perform the cleaning task according to the pre-set path and operation parameters. At the same time, the system uses multiple sensors installed in the room (such as PM2.5 sensors, carbon dioxide sensors, humidity sensors, etc.) to monitor the air quality index in real time. For example, in a family with children and pets, the sensors may detect a relatively high PM2.5 concentration in the living room area and a relatively high humidity in the bedroom area. These real-time data will be transmitted to the central control system for further analysis and processing.

[0130] Step 502: Based on the air quality index, use a long short-term memory network to predict the trend of air quality change. According to the air quality change trend and the demand status of the home environment, use a fuzzy logic control system to dynamically adjust the suction intensity and water flow rate of the floor scrubber to obtain an adjusted cleaning operation result;

[0131] In this step, after receiving the air quality index, a long short-term memory network is used to analyze this data to predict the future trend of air quality change. For example, if the long short-term memory network predicts that the PM2.5 concentration in the living room area will increase significantly within the next hour, the system will, based on this trend and the current home environment needs (such as children playing in the living room), use a fuzzy logic control system to dynamically adjust the suction intensity and water flow rate of the floor scrubber. Assuming the current PM2.5 concentration is 80 µg / m³, the system may increase the suction intensity from the default value to the maximum and increase the water flow rate to enhance the cleaning effect. This dynamic adjustment mechanism ensures that when the air quality deteriorates, the floor scrubber can more effectively remove dust and pollutants.

[0132] Step 503: Based on the adjusted cleaning operation result, use the ant colony optimization algorithm to generate a smart home regulation plan;

[0133] For example, after each cleaning task is completed, the system records the actual operation parameters of the floor scrubber (such as suction intensity, water flow rate, cleaning time, and path, etc.) and compares them with the predicted air quality change trend to evaluate the cleaning effect. For example, if it is found that the adjustment of the suction intensity and water flow rate effectively reduces the PM2.5 concentration, the system will use these data as the basis for optimization. Then, using the ant colony optimization algorithm, the system generates an optimized smart home regulation plan. This plan not only considers the cleaning effect but also minimizes energy consumption and noise impact. For example, the system may recommend reducing unnecessary device operations during specific time periods or adjusting the working modes of the air conditioner and air purifier to achieve the best overall home environment management effect.

[0134] The embodiment of the present invention ensures the pertinence and effectiveness of the cleaning task by formulating a personalized cleaning plan; real-time monitors and predicts the trend of air quality change, and dynamically adjusts the operation parameters of the floor scrubber, improving the cleaning effect and reducing resource waste; the smart home regulation plan generated using the ant colony optimization algorithm further optimizes the operation efficiency and performance of the entire system. This method not only improves the cleanliness and comfort of the home environment but also significantly enhances the user's living experience and quality of life.

[0135] Figure 2 The following is a schematic structural diagram of the smart home regulation system based on the floor scrubber provided by the embodiment of the present invention. As Figure 2 shown, the system includes:

[0136] A collection module 21 for collecting the real-time obstacle distribution in the home environment and the activity trajectory data of family members;

[0137] A calculation module 22 for calculating an obstacle avoidance and seamless coverage cleaning path of the floor scrubber based on the real-time obstacle distribution and the activity trajectory data;

[0138] An evaluation module 23 for evaluating the home environment requirements by using a fuzzy logic algorithm for the obstacle avoidance and seamless coverage cleaning path to generate suitable living conditions;

[0139] An optimization module 24 for formulating a preliminary cleaning plan by applying a clustering analysis method and a decision tree algorithm based on the suitable living conditions, the living habits data of family members, and the historical cleaning data, and optimizing the preliminary cleaning plan to generate a personalized cleaning plan;

[0140] A generation module 25 for implementing the personalized cleaning plan to obtain an air quality index of the home environment, and dynamically adjusting the suction intensity and water flow rate of the floor scrubber based on the air quality index to generate a smart home control solution.

[0141] Figure 2 The smart home control system based on the floor scrubber can execute Figure 1 The smart home control method based on the floor scrubber shown in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For the smart home control system based on the floor scrubber in the above embodiment, the specific ways for each module and unit to perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0142] In a possible design, Figure 2 The smart home control system based on the floor scrubber shown in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0143] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0144] The processing component 32 is used for: collecting the real-time obstacle distribution in the home environment and the activity trajectory data of family members; calculating the obstacle avoidance and seamless coverage cleaning path of the floor scrubber based on the real-time obstacle distribution and the activity trajectory data; evaluating the home environment requirements by using the fuzzy logic algorithm based on the obstacle avoidance and seamless coverage cleaning path to generate suitable living conditions; formulating a preliminary cleaning plan by applying the clustering analysis method and the decision tree algorithm based on the suitable living conditions, the living habits data of family members and the historical cleaning data, optimizing the preliminary cleaning plan to generate a personalized cleaning plan; implementing the personalized cleaning plan to obtain the air quality index of the home environment, and dynamically adjusting the suction intensity and water flow rate of the floor scrubber based on the air quality index to generate a smart home control solution.

[0145] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0146] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0147] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0148] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0149] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0150] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0151] An embodiment of the present invention also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, the above-mentioned Figure 1 smart home control method based on a floor scrubber shown in the embodiment can be implemented.

[0152] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0153] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0154] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements 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 the present invention.

Claims

1. A smart home control method based on a floor cleaning machine, characterized in that: include: Collect real-time obstacle distribution in the home environment and activity trajectory data of family members; Based on the real-time obstacle distribution and the activity trajectory data, calculating the obstacle avoidance and seamless coverage cleaning path of the floor scrubber; Based on the obstacle avoidance and seamless coverage cleaning path, a fuzzy logic algorithm is used to evaluate the home environment requirements to generate suitable living conditions; Based on the suitable living conditions, the living habits data of the family members and the historical cleaning data, a cluster analysis method and a decision tree algorithm are applied to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan; Implement the personalized cleaning plan to obtain the air quality index of the home environment, and dynamically adjust the suction strength and water flow of the floor scrubber based on the air quality index to generate a smart home control plan; Based on the obstacle avoidance and seamless coverage cleaning path, a fuzzy logic algorithm is used to evaluate the home environment requirements to generate suitable living conditions, including: Based on the obstacle avoidance and seamless coverage cleaning path, the working status of the mopping machine and the home environment parameters, a fuzzy logic algorithm is used to evaluate the demand status of the home environment to obtain a target home environment demand evaluation result; Based on the home environment demand assessment result, adjusting the working state of the target smart home device to generate a target working state; Based on the target working state, an adaptive control algorithm is introduced to dynamically adjust the operating parameters of each smart home device to generate suitable living conditions, wherein the operating parameters include a wind speed set value and a humidity set value; Based on the obstacle avoidance and seamless coverage cleaning path, the working status of the mopping machine and the home environment parameters, the fuzzy logic algorithm is used to evaluate the demand status of the home environment, and the target home environment demand evaluation results are obtained, including: Acquire home environment data from a plurality of sensors, wherein the home environment data includes home environment parameters; Analyze the home layout and device distribution using a graph neural network to optimize the application scope and accuracy of the home environment data and generate a home environment status description. During the optimization process, use a reinforcement learning algorithm to train the graph neural network so that the graph neural network can adapt to changes in the home layout in real time. Based on the obstacle avoidance and seamless coverage cleaning path, the working status of the mopping machine and the home environment status description, a fuzzy logic algorithm is used to evaluate the demand status of the home environment to obtain a preliminary home environment demand evaluation result. In the process of using the fuzzy logic algorithm for evaluation, a convolutional neural network is used to analyze historical environmental data to extract potential environmental features to optimize the evaluation; A support vector machine model is introduced to identify the optimal equipment configuration under different environmental conditions, and combined with the preliminary home environment demand assessment results, a target home environment demand assessment result is generated.

2. The method according to claim 1, characterized in that Based on the suitable living conditions, the living habits data of the family members and the historical cleaning data, a cluster analysis method and a decision tree algorithm are applied to formulate a preliminary cleaning plan, optimize the preliminary cleaning plan, and generate a personalized cleaning plan, including: Using a cluster analysis method to group the suitable living conditions, family members' living habits data, and historical cleaning data to obtain a cleaning task classification; Based on the cleaning task classification, a decision tree algorithm is applied to determine an optimal cleaning sequence and an optimal cleaning frequency to generate a preliminary cleaning plan; Acquire activity images of family members, apply a target detection algorithm to analyze the activity images of family members to calculate the residence time and activity frequency of family members in each room, and use a bidirectional long short-term memory network to predict the long-term activity trend of family members based on the residence time and activity frequency, so as to refine the preliminary cleaning plan and obtain a refined cleaning plan; A reinforcement learning algorithm is used to simulate the application effects of different cleaning strategies in the refined cleaning plan to search for a combination of an optimal cleaning time and an optimal cleaning frequency. Based on the combination of the optimal cleaning time and the optimal cleaning frequency, a Bayesian optimization algorithm is used to optimize the refined cleaning plan to obtain a personalized cleaning plan.

3. The method according to claim 2, characterized in that Acquire family member activity images, apply target detection algorithm to analyze the family member activity images to calculate the residence time and activity frequency of family members in each room, and use bidirectional long short-term memory network to predict the long-term activity trend of family members based on the residence time and activity frequency, so as to refine the preliminary cleaning plan and obtain a refined cleaning plan, including: Acquire family member activity images, and use a target detection algorithm to identify target objects in the family member activity images to obtain family member location information; Based on the location information of the family members, the residence time and activity frequency of the family members in each room are calculated, the residence time and activity frequency are classified by using a spatiotemporal graph convolutional network to obtain classification results, and based on the classification results, the behavior patterns of the family members are identified; Analyze the residence time, the activity frequency, and the behavior pattern using a bidirectional long short-term memory network to obtain a behavior analysis result, and predict the long-term activity trend of the family members based on the behavior analysis result to generate a long-term activity trend prediction result; Based on the long-term activity trend prediction results, the cleaning frequency and cleaning time corresponding to each room are adjusted to obtain the adjusted cleaning frequency and cleaning time. The preliminary cleaning plan is refined using the adjusted cleaning frequency and cleaning time to obtain a refined cleaning plan.

4. The method according to claim 1, characterized in that: Based on the real-time obstacle distribution and the activity trajectory data, the obstacle avoidance and seamless coverage cleaning path of the floor scrubber are calculated, including: Based on the real-time obstacle distribution and the activity trajectory data, generating fused data; Applying a convolutional neural network to perform feature extraction on the fused data to identify location information of obstacles and activity patterns of family members, generating a preliminary home environment map based on the location information of obstacles and activity patterns of family members, and using a synchronous positioning and map building algorithm to perform real-time updating processing on the preliminary home environment map to obtain an updated home environment map; Based on the updated home environment map, the A* algorithm and the plowing path planning algorithm are used to calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber.

5. The method according to claim 1, characterized in that Implement the personalized cleaning plan to obtain the air quality index of the home environment, and dynamically adjust the suction strength and water flow of the floor scrubber based on the air quality index to generate a smart home control solution, including: Implementing the personalized cleaning plan, and using a variety of sensors to monitor in real time the air quality indicators of the home environment during the implementation of the personalized cleaning plan; Based on the air quality index, a long short-term memory network is used to predict the air quality change trend, and according to the air quality change trend and the demand conditions of the home environment, a fuzzy logic control system is used to dynamically adjust the suction strength and water flow of the floor scrubber to obtain an adjusted cleaning operation result; Based on the adjusted cleaning operation results, an ant colony optimization algorithm is used to generate a smart home control solution.

6. The intelligent home control system based on the floor cleaning machine is characterized by: include: A collection module is used to collect real-time obstacle distribution in the home environment and activity trajectory data of family members; A calculation module, used to calculate the obstacle avoidance and seamless coverage cleaning path of the floor scrubber based on the real-time obstacle distribution and the activity trajectory data; An evaluation module for the obstacle avoidance and seamless coverage cleaning path, using a fuzzy logic algorithm to evaluate home environment requirements to generate suitable living conditions; An optimization module, for formulating a preliminary cleaning plan based on the suitable living conditions, the living habits data of family members and the historical cleaning data, applying a cluster analysis method and a decision tree algorithm, optimizing the preliminary cleaning plan, and generating a personalized cleaning plan; A generation module, used to implement the personalized cleaning plan, obtain the air quality index of the home environment, and dynamically adjust the suction strength and water flow of the floor scrubber based on the air quality index to generate a smart home control plan; Based on the obstacle avoidance and seamless coverage cleaning path, a fuzzy logic algorithm is used to evaluate the home environment requirements to generate suitable living conditions, including: Based on the obstacle avoidance and seamless coverage cleaning path, the working status of the mopping machine and the home environment parameters, a fuzzy logic algorithm is used to evaluate the demand status of the home environment to obtain a target home environment demand evaluation result; Based on the home environment demand assessment result, adjusting the working state of the target smart home device to generate a target working state; Based on the target working state, an adaptive control algorithm is introduced to dynamically adjust the operating parameters of each smart home device to generate suitable living conditions, wherein the operating parameters include a wind speed set value and a humidity set value; Based on the obstacle avoidance and seamless coverage cleaning path, the working status of the mopping machine and the home environment parameters, the fuzzy logic algorithm is used to evaluate the demand status of the home environment, and the target home environment demand evaluation results are obtained, including: Acquire home environment data from a plurality of sensors, wherein the home environment data includes home environment parameters; Analyze the home layout and device distribution using a graph neural network to optimize the application scope and accuracy of the home environment data and generate a home environment status description. During the optimization process, use a reinforcement learning algorithm to train the graph neural network so that the graph neural network can adapt to changes in the home layout in real time. Based on the obstacle avoidance and seamless coverage cleaning path, the working status of the mopping machine and the home environment status description, a fuzzy logic algorithm is used to evaluate the demand status of the home environment to obtain a preliminary home environment demand evaluation result. In the process of using the fuzzy logic algorithm for evaluation, a convolutional neural network is used to analyze historical environmental data to extract potential environmental features to optimize the evaluation; A support vector machine model is introduced to identify the optimal equipment configuration under different environmental conditions, and combined with the preliminary home environment demand assessment results, a target home environment demand assessment result is generated.

7. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the smart home control method based on the floor cleaning machine as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the smart home control method based on the floor cleaning machine as described in any one of claims 1 to 5 is implemented.

Images