Indoor air quality control methods, devices, and equipment based on user preferences

Abstract

This invention relates to a method, apparatus, and device for adjusting indoor air quality based on user preferences. The method includes: acquiring the user's current state data and the current air quality data of the user's environment; inputting the current state data into a preset air quality preference model to obtain the user's corresponding required air quality data, and determining whether the current air quality data meets the required air quality data. The preset air quality preference model is learned using a random forest algorithm and a deep reinforcement learning algorithm based on multiple historical data points. If any parameter in the current air quality data does not meet the required air quality data, a target control device and its control parameters are determined based on the parameter that did not meet the required air quality data, and the target device is controlled according to the control parameters. Thus, by integrating hardware and multiple algorithms, user preference-based air quality decision control is achieved, realizing truly intelligent and personalized management, and meeting users' multiple needs for comfort, health, and energy conservation.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to a method, apparatus, and device for adjusting indoor air quality based on user preferences. Background Technology

[0002] With the continuous improvement of electronic information technology and control technology, and the gradual acceleration of social informatization, many smart home control systems have emerged in the home field. However, these traditional control systems have problems such as relying on human triggering and scene setting for control methods, insufficient precision in setting control conditions, difficulty in adapting to real environments with multiple factors and devices, and poor control effects that cannot meet the dual needs of comfort, health, and energy saving.

[0003] In related technologies, the air conditioning function of smart home control systems is usually adjusted and optimized based on user settings and environmental data collection in certain scenarios, so that the air conditioning function of smart home control systems is closer to the user's requirements.

[0004] However, the aforementioned technical methods rely too heavily on human intervention and system scenario settings, making them unsuitable for complex environments with multiple factors and devices. Furthermore, they fail to provide timely interaction and feedback to users, significantly diminishing the user experience and thus requiring urgent solutions. Summary of the Invention

[0005] This invention provides a method, device, and equipment for adjusting indoor air quality based on user preferences. It addresses the problems in related technologies where smart home control systems rely on human triggering and scene settings, and are unable to adapt to complex environments with multiple factors and devices. By integrating hardware and multiple algorithms, it improves the control effect on indoor air quality, achieves true intelligent and personalized management, meets multiple epidemic prevention requirements, and satisfies users' multiple needs for comfort, health, and energy conservation.

[0006] To achieve the above objectives, a first aspect of the present invention proposes a method for adjusting indoor air quality based on user preferences, comprising the following steps:

[0007] Obtain the user's current status data and the current air quality data of the user's environment;

[0008] The current state data is input into a preset air quality preference model to obtain the user's required air data, and it is determined whether the current air data meets the required air data. The preset air quality preference model is learned using random forest algorithm and deep reinforcement learning algorithm based on the user's historical state data and the air data corresponding to the historical data.

[0009] If any parameter in the current air data does not meet the required air data, then the target control device and the control parameters of the target device are determined based on the parameter that does not meet the required air data, and the target device is controlled according to the control parameters of the target device.

[0010] According to one embodiment of the present invention, before inputting the current state data into the preset air quality preference model, the method further includes:

[0011] Obtain the user's historical status data and the corresponding demand air data;

[0012] Based on a preset division ratio, the historical state data and the corresponding demand air data are divided into a training set and a test set. Each training set and the test set includes multiple sets of data, and each set of data consists of a state data and the corresponding demand air data.

[0013] Based on the random forest algorithm and the deep reinforcement learning algorithm, an initial air quality preference model is obtained by learning from the training set, and the initial air quality preference model is tested using the test set. If the test results meet the preset test conditions, the initial air quality preference model is used as the preset air quality preference model.

[0014] According to one embodiment of the present invention, after testing the initial air quality preference model using a test set, the method further includes:

[0015] If the test results do not meet the preset test conditions, the preset division ratio is adjusted, and a new air quality preference model is relearned based on the adjusted training set until the test results of the new initial air quality preference model meet the preset test conditions. The new initial air quality preference model is then used to obtain the preset air quality preference model.

[0016] According to one embodiment of the present invention, after controlling the target device according to the control parameters of the target device, the method further includes:

[0017] Determine whether the user's device adjustment command has been received;

[0018] The target control device is controlled based on the device adjustment command, and the control result and the current state data are stored in the target memory. The preset air quality preference model is updated according to the control result and the current state data.

[0019] According to an embodiment of the present invention, the indoor air quality adjustment method based on user preferences further includes:

[0020] determining whether an external access request exists for the target memory;

[0021] verifying the external access request if the external access request exists for the target memory;

[0022] issuing a rejection access prompt and issuing a prompt message to a preset mobile terminal if the verification fails.

[0023] According to an embodiment of the present application, the indoor air quality adjustment method based on user preferences further comprises:

[0024] determining whether a data display request is received;

[0025] displaying the current state data and / or the current air data if the data display request is received.

[0026] According to the indoor air quality adjustment method based on user preferences provided by the embodiment of the present application, the air quality preference model is trained by the historical data of the user and the corresponding demand air data, the current state data and the current air data of the user are input into the trained air quality preference model to generate a personalized device control strategy, and the terminal device is controlled according to the generated control strategy to adjust the environmental air quality where the user is located. Therefore, by integrating hardware and various algorithms, the control effect on the indoor air quality is improved, truly intelligent and personalized management is realized, multiple epidemic prevention requirements are met, and multiple demands of the user for comfort, health and energy saving are met.

[0027] To achieve the above object, the second aspect embodiment of the present application provides an indoor air quality adjustment device based on user preferences, comprising:

[0028] an acquisition module configured to acquire current state data of a user and current air data of an environment where the user is located;

[0029] a prediction decision module configured to input the current state data into a preset air quality preference model to obtain demand air data corresponding to the user, and determine whether the current air data meets the demand air data, wherein the preset air quality preference model is learned by a random forest algorithm and a deep reinforcement learning algorithm based on historical state data of the user and air data corresponding to the historical data;

[0030] a control module configured to determine a target control device and a control parameter of the target device according to a parameter that does not meet the demand air data when any parameter in the current air data does not meet the demand air data, and control the target device according to the control parameter of the target device.

[0031] According to one embodiment of the present application, before the current state data is input into the preset air quality preference model, the prediction decision module is further configured to:

[0032] Obtain historical state data of the user and demand air data corresponding to the historical state data;

[0033] Divide the historical state data and the demand air data corresponding to the historical state data into a training set and a test set based on a preset division ratio, wherein the training set and the test set each include a plurality of groups of data, and each group of data is composed of one piece of state data and demand air data corresponding to the piece of state data;

[0034] Learn the training set based on the random forest algorithm and the deep reinforcement learning algorithm to obtain an initial air quality preference model, and test the initial air quality preference model using the test set, and if the test result meets a preset test condition, the initial air quality preference model is taken as the preset air quality preference model.

[0035] According to one embodiment of the present application, after the test set is used to test the initial air quality preference model, the prediction decision module is further configured to:

[0036] If the test result does not meet the preset test condition, the preset division ratio is adjusted, and a new air quality preference model is re-learned based on the adjusted training set until the test result of the new initial air quality preference model meets the preset test condition, and the new initial air quality preference model is taken as the preset air quality preference model.

[0037] According to one embodiment of the present application, after the target device is controlled according to the control parameter of the target device, the control module is further configured to:

[0038] Judge whether a device adjustment instruction of the user is received;

[0039] Control the target control device based on the device adjustment instruction, store the control result and the current state data into a target storage, and update the preset air quality preference model according to the control result and the current state data.

[0040] According to one embodiment of the present application, the indoor air quality adjustment device based on user preference is further configured to:

[0041] Judge whether there is an external access request for the target storage;

[0042] If there is the external access request for the target storage, the external access request is verified.

[0043] If the verification fails, a rejection access prompt is issued, and a prompt message is issued to a preset mobile terminal.

[0044] According to one embodiment of the present application, the indoor air quality adjustment device based on user preferences is further used for:

[0045] determining whether a data display request is received;

[0046] If the data display request is received, the current state data and / or the current air data are displayed.

[0047] According to the indoor air quality adjustment device based on user preferences provided by the embodiments of the present application, the air quality preference model is trained through the historical data of the user and the corresponding required air data, the current state data and the current air data of the user are input into the trained air quality preference model, a personalized device control strategy is generated, and the terminal device is controlled according to the generated control strategy, so as to adjust the environmental air quality where the user is located. Therefore, through the integration of hardware and various algorithms, the control effect on the indoor air quality is improved, the truly intelligent and personalized management is realized, the multiple epidemic prevention requirements are met, and the multiple requirements of the user for comfort, health and energy saving are met.

[0048] To achieve the above object, the third aspect of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the indoor air quality adjustment method based on user preferences as described in the above embodiments.

[0049] To achieve the above object, the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the indoor air quality adjustment method based on user preferences as described in the above embodiments.

[0050] To achieve the above object, the fifth aspect of the present application provides a computer program product, comprising a computer program, which is executed by a processor to implement the indoor air quality adjustment method based on user preferences as described in the above embodiments.

[0051] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0052] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description, taken in conjunction with the accompanying drawings, in which:

[0053] Figure 1 A flowchart illustrating an indoor air quality adjustment method based on user preferences, provided as an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of the system structure of a user preference-based indoor air quality control method according to a specific embodiment of the present invention;

[0055] Figure 3 A flowchart illustrating a user preference-based indoor air quality adjustment method according to a specific embodiment of the present invention;

[0056] Figure 4 A flowchart illustrating the specific implementation steps of an indoor air quality regulation method based on user preferences for intelligent control according to a specific embodiment of the present invention;

[0057] Figure 5 A block diagram of a user-preference-based indoor air quality control device according to an embodiment of the present invention;

[0058] Figure 6 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present invention.

[0059] Figure label:

[0060] 10- User-preference-based indoor air quality control device, 100- Acquisition module, 200- Prediction and decision-making module, 300- Control module, 601- Memory, 602- Processor, 603- Communication interface. Detailed Implementation

[0061] Embodiments of the present invention are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0062] The following description, with reference to the accompanying drawings, describes a user-preference-based indoor air quality control method, apparatus, and device according to embodiments of the present invention. First, the user-preference-based indoor air quality control method according to embodiments of the present invention will be described with reference to the accompanying drawings.

[0063] Figure 1 This is a flowchart of an indoor air quality adjustment method based on user preferences provided in one embodiment of the present invention.

[0064] like Figure 1 As shown, this user-preference-based indoor air quality control method includes the following steps:

[0065] In step S101, the user's current status data and the current air quality data of the user's environment are obtained.

[0066] The user's current status data includes the user's current physical health status, and the current air data of the user's environment includes ultrafine particle data, fine particle data, total suspended particulate matter data, formaldehyde concentration data, carbon dioxide concentration data, temperature and humidity data, and energy consumption data.

[0067] Specifically, embodiments of the present invention can acquire the user's current state data and the current air quality data of the user's environment by embedding a sensing module in a wearable device. The sensing module includes a sensor module for sensing various parameters and data in the environment (such as ultrafine particulate matter concentration, fine particulate matter concentration, total suspended particulate matter concentration, formaldehyde concentration, carbon dioxide concentration, temperature and humidity, energy consumption, etc.) and a wearable device module for sensing the user's physical health status (such as the user's respiratory rate, heart rate, allergy information, etc.), enabling real-time monitoring of the real environment and the user's state. The wearable device includes environmental monitoring sensors (ultrafine particulate matter monitoring sensors, fine particulate matter monitoring sensors, total suspended particulate matter monitoring sensors, formaldehyde monitoring sensors, carbon dioxide monitoring sensors, temperature and humidity monitoring sensors, energy consumption monitoring sensors), physiological monitoring sensors (such as heart rate sensors, respiratory rate sensors, blood oxygen sensors, skin conductance sensors), a data processing unit, a wireless communication module, and a user feedback module.

[0068] For example, users can wear wearable devices (such as wristbands) with built-in sensors to monitor air pollution and health data around them. Ultrafine particulate matter sensors monitor viral aerosol concentrations, fine particulate matter sensors monitor pollution from activities like cooking and smoking, total suspended particulate matter sensors monitor pollen pollution, formaldehyde sensors monitor indoor air pollution, and carbon dioxide sensors monitor overall ventilation. Heart rate sensors use photoplethysmography (PPG) technology to measure heart rate fluctuations in real time, especially detecting abnormally high heart rates when the user is experiencing allergies or unstable health. Respiratory rate sensors monitor respiratory rate by analyzing minute vibrations in the chest or wrist to identify changes in breathing patterns; this method can be used to determine if breathing is restricted or accelerated when air pollution or allergen concentrations are high. Blood oxygen sensors measure blood oxygen saturation levels using optical sensors, monitoring for decreased blood oxygen levels when respiratory function is impaired, such as when particulate matter concentrations are high. Skin conductance sensors detect skin conductivity, reflecting the user's stress level or physical workload. This data helps assess the potential impact of air pollution on users' health.

[0069] In step S102, the current state data is input into the preset air quality preference model to obtain the user's corresponding air quality data, and it is determined whether the current air quality data meets the air quality requirements. The preset air quality preference model is learned using random forest algorithm and deep reinforcement learning algorithm based on the user's historical state data and the corresponding air quality data.

[0070] It should be noted that before inputting the current state data into the preset air quality preference model, the embodiments of the present invention can also perform preliminary analysis on the current state data and filter the collected data to remove noise interference.

[0071] Specifically, the preset air quality preference model can analyze the user's preference for indoor air quality in different situations and the user's air quality needs in different health states (such as allergy season or during a cold) based on the user's historical state data and the corresponding air data. It can also extract features from the user's operation behavior through deep reinforcement learning to build the user's air quality preference model. After the current state data is input into the preset air quality preference model, the model can predict the user's required air data in the future time period based on the random forest algorithm and deep reinforcement learning algorithm, and determine whether the current air data meets the required air data.

[0072] For example, embodiments of the present invention continuously collect user preference data on indoor air quality in different contexts. This data includes, but is not limited to, user preferences for air humidity, temperature, and air freshness in different seasons and time periods, as well as user air quality needs under different health conditions (e.g., allergy season or during a cold). Machine learning algorithms are used to extract features from user behavior to construct an air quality preference model. Deep learning algorithms are used to analyze user behavior patterns to accurately capture trends in user air quality preferences. Random forest and deep reinforcement learning algorithms are used to predict user air quality needs in future time periods. For example, as the allergy season approaches, the system can predict in advance that users may need more efficient air purification and automatically adjust the device's operating mode to reduce allergens in the air, comparing the required air quality data with the current air quality data.

[0073] In step S103, if any parameter in the current air data does not meet the required air data, the target control device and the control parameters of the target device are determined based on the parameter that does not meet the required air data, and the target device is controlled according to the control parameters of the target device.

[0074] Specifically, if any parameter in the current air data does not meet the required air quality, it means that the current ambient air quality does not meet the user's required ambient air quality. Based on the parameters of the required air data, the target device to be controlled and the control parameters of the target device can be determined. After obtaining the control parameters of the target device, the target device is controlled according to the control parameters.

[0075] For example, based on the control parameters of the target device, the system adjusts the air purifier's fan speed and filtration level, controls the opening and closing of window openers, and automatically adjusts the temperature and humidity settings of the air conditioning system. For instance, when the system detects that a user is in a high-risk allergy period or has an abnormal health condition, it issues an early warning based on this information and executes corresponding adjustment strategies. These include automatically increasing the air purifier's filtration efficiency, adjusting the air conditioning system's temperature and humidity settings to reduce allergens in the air, and closing windows in advance to prevent harmful substances from outdoor air from entering the room.

[0076] Optionally, in some embodiments, after controlling the target device according to the control parameters of the target device, the method further includes: determining whether a user's device adjustment command has been received; controlling the target control device based on the device adjustment command, storing the control result and current state data in the target memory, and updating the preset air quality preference model according to the control result and current state data.

[0077] Specifically, when the system controls the target device according to its control parameters, if the user is not satisfied with the air quality adjustment, they initiate a device adjustment command. Upon receiving this command, the system controls the target device accordingly, simultaneously storing the control results and current state data in the target's memory and continuously updating the preset air quality preference model. By recording environmental changes and user satisfaction after each user intervention, the system continuously refines its control strategy through reinforcement learning, making the control process more precise and efficient.

[0078] For example, when a user manually adjusts the air purifier's fan speed multiple times in similar situations, the system will automatically learn this user's operating preference and apply that preference setting automatically under similar environmental conditions, reducing the user's operational burden.

[0079] In addition, the effectiveness of each control parameter is evaluated through deep reinforcement learning algorithms, and multi-dimensional evaluation criteria (such as air quality improvement effect, energy consumption, changes in user health status, etc.) are set to optimize the strategy.

[0080] Optionally, in some embodiments, the indoor air quality adjustment method based on user preferences further includes: determining whether there is an external access request for the target storage; if there is an external access request for the target storage, verifying the external access request; if the verification fails, issuing an access denial reminder and sending a reminder message to a preset mobile terminal.

[0081] Specifically, when a user requests access to the target storage device to modify historical and preference data stored therein, this embodiment of the invention requires verification of the access request. For example, it may use a facial recognition device or a voiceprint / fingerprint authentication device to verify the identity of the requester. If verification fails, the access request is rejected, an access denial alert is issued, and the alert information is sent to a preset mobile terminal via a communication connection to remind the user of potential security threats.

[0082] Optionally, in some embodiments, the indoor air quality adjustment method based on user preferences further includes: determining whether a data display request has been received; if a data display request has been received, then displaying the current status data and / or the current air data.

[0083] Specifically, the embodiments of the present invention are equipped with a visual interface module. When a user needs to obtain current air data, he / she can send a data display request through a preset mobile terminal. When the system receives the data display request, it displays the current status data and current air data on the preset mobile terminal or display terminal according to the data display request.

[0084] For example, users can view current environmental data through a visual interface and receive real-time feedback on the improvement in air quality via the health bracelet. The smart health bracelet seamlessly integrates with the residential air pollution intelligent control system, ensuring that the system not only senses environmental data but also captures the user's health status in real time. Through this data, the system can predict and manage air quality, adjust control strategies, prevent allergic reactions, reduce indoor air pollution, and prevent the spread of viruses through the air, further optimizing indoor air quality management.

[0085] Therefore, the air quality preference model is trained by using users' historical data and corresponding demand air data. The user's current state data and current air data are then input into the trained air quality preference model to generate personalized equipment control strategies. The terminal equipment is then controlled according to the generated control strategies. Based on user feedback and satisfaction, the preference model is continuously adjusted and optimized to make the air quality preference model more in line with the user's actual needs.

[0086] Optionally, in some embodiments, before inputting the current state data into the preset air quality preference model, the method further includes: acquiring the user's historical state data and the corresponding air demand data; dividing the historical state data and the corresponding air demand data into a training set and a test set based on a preset division ratio, wherein both the training set and the test set include multiple sets of data, each set of data consisting of a state data and the corresponding air demand data; learning an initial air quality preference model from the training set based on a random forest algorithm and a deep reinforcement learning algorithm, and testing the initial air quality preference model using the test set; if the test results meet preset test conditions, then using the initial air quality preference model as the preset air quality preference model.

[0087] Specifically, the training process for the air quality preference model includes: acquiring the user's historical status data and the corresponding demand air data. For example, when a user is experiencing an allergic reaction, the corresponding demand air data is that the total suspended particulate matter in indoor air is below 0.3 mg / m³. After acquiring the user's historical status data and the corresponding demand air data, the historical data and the corresponding demand air data are grouped. Each group consists of one status data point and the corresponding demand air data point. Then, according to a preset division ratio, multiple data groups are divided into training and testing sets, each containing multiple data points. The training set is then trained using random forest and deep reinforcement learning algorithms to extract user preferences and construct an initial air quality preference model. This initial air quality preference model is then tested using the testing set. After testing, if the test results meet the preset test conditions, the initial air quality preference model is adopted as the preset air quality preference model.

[0088] Optionally, in some embodiments, after testing the initial air quality preference model using the test set, the method further includes: if the test results do not meet the preset test conditions, adjusting the preset division ratio, and relearning a new air quality preference model based on the adjusted training set, until the test results of the new initial air quality preference model meet the preset test conditions, and obtaining the preset air quality preference model from the new initial air quality preference model.

[0089] Specifically, the initial air quality preference model is tested based on the test set. When the test results do not meet the preset test conditions, the ratio of the training set and the test set is adjusted, the data groups are re-divided to obtain a new training set and a new test set, and the initial air quality preference model is reconstructed based on the adjusted training set. The initial air quality preference model is then tested based on the test set. The above operation is repeated until the test results meet the preset test conditions, and the initial air quality preference model is used as the preset air quality preference model.

[0090] To enable those skilled in the art to further understand the user preference-based indoor air quality adjustment method of the present invention, the following detailed description is provided in conjunction with specific embodiments.

[0091] Specifically, such as Figure 2 As shown, Figure 2 A schematic diagram of a system for a user-preference-based indoor air quality control method according to a specific embodiment of the present invention is provided, wherein the system applicable to the user-preference-based indoor air quality control method includes:

[0092] 1. Perception Module

[0093] It includes sensor modules for sensing various parameters and data in the environment (such as ultrafine particulate matter concentration, fine particulate matter concentration, total suspended particulate matter concentration, formaldehyde concentration, carbon dioxide concentration, temperature and humidity, energy consumption, etc.) and wearable device modules for sensing the user's physical health status (such as the user's respiratory rate, heart rate, allergy information, etc.), which can realize real-time monitoring of the real environment and the user's status.

[0094] 2. Storage module

[0095] It includes a database for storing parameters and data obtained by the perception module from the real environment for the control module to read, storing the decisions made by the control module, storing the prediction data of the personnel preference prediction model, and storing the user's operation behavior in the interaction module.

[0096] 3. Control Module

[0097] It includes a deep reinforcement learning neural network module for implementing action strategies and a reward function module that measures the effectiveness of action strategies from multiple aspects, such as particulate matter concentration control, energy consumption, consumables, and human health benefits, thus enabling a trade-off between indoor air quality and energy consumption.

[0098] 4. Communication Module

[0099] This includes a transmission protocol module for specifying the transmission protocol used by the communication module, a local area network module for connecting the control module with various smart home devices in the real environment, and a communication interface module for connecting the sensing module with other external devices.

[0100] 5. Prediction Module

[0101] It includes a random forest algorithm module for analyzing user health data, integrating user characteristics, and predicting user preferences. The predictive model built by the algorithm module can predict the changing trend of air quality in advance and take measures in advance when needed. At the same time, it can also continuously optimize the control module, realize the steady learning of the system, and create a more intelligent and personalized indoor environment experience for users.

[0102] 6. Privacy Protection Module

[0103] It includes an access feature parameter module for identifying access points and extracting features from their historical access records, and a risk control module for analyzing and controlling the risks of access segments, enabling the control system to identify abnormal access trajectories, promptly detect potential security threats, and take corresponding measures to protect user privacy.

[0104] 7. Interactive Module

[0105] It includes an interface design module for designing the appearance and interaction of the user interface, a visualization interface module for displaying various parameters of the indoor air environment and energy consumption, a user input module for acquiring user data information, and a user feedback module for providing feedback to users so that they know whether their operations have been performed.

[0106] Furthermore, such as Figure 3 As shown, Figure 3 A flowchart illustrating a user-preference-based indoor air quality control method according to a specific embodiment of the present invention includes the following steps:

[0107] S301, Data Acquisition and Transmission

[0108] The sensing module collects environmental and user health data and uploads it to the storage module via the communication module.

[0109] S302, Data Storage and Processing

[0110] The storage module stores data and shares it with the control and prediction modules.

[0111] S303, Forecasting and Decision Making

[0112] The prediction module uses historical and current data to predict user preferences and air quality changes, and provides optimization suggestions to the control module.

[0113] S304, Equipment Control

[0114] The control module generates control commands based on prediction results and real-time data, and directs smart home devices to perform corresponding operations through the communication module.

[0115] S305, User Interaction and Feedback

[0116] The interactive module provides users with data visualization and control options, and the privacy protection module ensures the security of user data.

[0117] S306, Data Learning and Optimization

[0118] The system continuously collects user operation and environmental change data, constantly updates the experience pool, and optimizes prediction models and control strategies.

[0119] Furthermore, such as Figure 4 As shown, Figure 4 A flowchart illustrating the specific implementation steps of an indoor air quality regulation method based on user preferences for intelligent control according to a specific embodiment of the present invention includes the following steps:

[0120] S401, User Preference Data Collection and Modeling

[0121] The system continuously collects user preferences for indoor air quality in different contexts through the sensing and interaction modules.

[0122] S402, Prediction and Decision Making Based on Personnel Preferences

[0123] The prediction module periodically calls user preference data and real-time environmental data from the storage module, and uses random forest and deep reinforcement learning algorithms to predict users' air quality needs in the future.

[0124] S403, Generation of Personalized Control Strategies

[0125] The control module generates personalized equipment control strategies based on prediction results and user preference models.

[0126] S404, Dynamic Learning and Adaptive Adjustment

[0127] The system continuously updates the preference model based on changes in user behavior.

[0128] The user-preference-based indoor air quality regulation method proposed in this embodiment trains an air quality preference model using historical user data and corresponding demand air data. The model then inputs the user's current state data and current air data into the trained model to generate personalized device control strategies. These strategies are then used to control terminal devices, thereby regulating the ambient air quality. By integrating hardware and multiple algorithms, this method improves indoor air quality control, achieving true intelligent and personalized management, meeting multiple epidemic prevention requirements, and satisfying users' diverse needs for comfort, health, and energy conservation.

[0129] Next, with reference to the accompanying drawings, an indoor air quality conditioning device based on user preferences according to an embodiment of the present invention is described.

[0130] Figure 5 This is a block diagram of an indoor air quality conditioning device based on user preferences according to an embodiment of the present invention.

[0131] like Figure 5 As shown, the user preference-based indoor air quality control device 10 includes: an acquisition module 100, a prediction and decision module 200, and a control module 300.

[0132] The acquisition module 100 is used to acquire the user's current status data and the current air quality data of the user's environment.

[0133] The prediction and decision module 200 is used to input the current state data into the preset air quality preference model to obtain the user's corresponding air demand data and determine whether the current air data meets the air demand data. The preset air quality preference model is learned by using the random forest algorithm and deep reinforcement learning algorithm based on the user's historical state data and the air data corresponding to the historical data.

[0134] The control module 300 is used to determine the target control device and the control parameters of the target device based on the parameter that does not meet the required air data when any parameter in the current air data does not meet the required air data, and to control the target device based on the control parameters of the target device.

[0135] According to an embodiment of the present invention, before inputting the current state data into the preset air quality preference model, the prediction decision module 200 is further configured to: acquire the user's historical state data and the corresponding air demand data; divide the historical state data and the corresponding air demand data into a training set and a test set based on a preset division ratio, wherein both the training set and the test set include multiple sets of data, each set of data consisting of a state data and the corresponding air demand data; learn an initial air quality preference model from the training set based on the random forest algorithm and the deep reinforcement learning algorithm, and test the initial air quality preference model using the test set; if the test result meets the preset test conditions, the initial air quality preference model is used as the preset air quality preference model.

[0136] According to an embodiment of the present invention, after testing the initial air quality preference model using a test set, the prediction decision module 200 is further configured to: if the test results do not meet the preset test conditions, adjust the preset division ratio, and relearn a new air quality preference model based on the adjusted training set, until the test results of the new initial air quality preference model meet the preset test conditions, and obtain the preset air quality preference model from the new initial air quality preference model.

[0137] According to an embodiment of the present invention, after controlling the target device according to the control parameters of the target device, the control module 300 is further configured to: determine whether a user's device adjustment command has been received; control the target control device based on the device adjustment command, and store the control result and current state data in the target memory, and update the preset air quality preference model according to the control result and current state data.

[0138] According to one embodiment of the present invention, the indoor air quality adjustment device 10 based on user preferences is further configured to: determine whether there is an external access request for the target memory; if there is an external access request for the target memory, verify the external access request; if the verification fails, issue an access denial reminder and send a reminder message to a preset mobile terminal.

[0139] According to one embodiment of the present invention, the indoor air quality adjustment device 10 based on user preferences is further configured to: determine whether a data display request has been received; if a data display request has been received, then display the current status data and / or the current air data.

[0140] The user-preference-based indoor air quality control device proposed in this embodiment trains an air quality preference model using historical user data and corresponding demand air data. The user's current state data and current air data are then input into the trained model to generate a personalized device control strategy. This strategy is then used to control the terminal device, thereby adjusting the ambient air quality. By integrating hardware and multiple algorithms, the device improves indoor air quality control, achieving true intelligent and personalized management, meeting multiple epidemic prevention requirements, and satisfying users' diverse needs for comfort, health, and energy conservation.

[0141] Figure 6 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. The electronic device may include:

[0142] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0143] When the processor 602 executes the program, it implements the user preference-based indoor air quality adjustment method provided in the above embodiments.

[0144] Furthermore, electronic devices also include:

[0145] Communication interface 603 is used for communication between memory 601 and processor 602.

[0146] The memory 601 is used to store computer programs that can run on the processor 602.

[0147] The memory 601 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0148] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0149] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0150] The processor 602 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.

[0151] This invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described user-preference-based indoor air quality adjustment method.

[0152] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described user-preference-based indoor air quality adjustment method.

[0153] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0154] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0155] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for adjusting indoor air quality based on user preferences, characterized by, The method comprises the following steps: obtaining current state data of a user and current air data of an environment in which the user is located, the current state data of the user comprising a current physical health state of the user; inputting the current state data into a preset air quality preference model to obtain corresponding required air data of the user, and determining whether the current air data meets the required air data, wherein the preset air quality preference model is learned based on historical state data of the user and corresponding required air data of the historical state data by using a random forest algorithm and a deep reinforcement learning algorithm; if any parameter in the current air data does not meet the required air data, determining a target device and a control parameter of the target device according to the parameter that does not meet the required air data, and controlling the target device according to the control parameter of the target device.

2. The method of claim 1, wherein, Before the current state data is input into the preset air quality preference model, the method further comprises the following steps: obtaining historical state data of the user and corresponding required air data of the historical state data; dividing the historical state data and the corresponding required air data of the historical state data into a training set and a test set based on a preset division ratio, wherein the training set and the test set each comprise a plurality of groups of data, and each group of data comprises one piece of state data and corresponding required air data of the piece of state data; learning the training set based on the random forest algorithm and the deep reinforcement learning algorithm to obtain an initial air quality preference model, and testing the initial air quality preference model by using the test set, and if the test result meets a preset test condition, taking the initial air quality preference model as the preset air quality preference model.

3. The method of claim 2, wherein, After testing the initial air quality preference model by using the test set, the method further comprises the following steps: if the test result does not meet the preset test condition, adjusting the preset division ratio, and re-learning a new air quality preference model based on the adjusted training set until the test result of the new initial air quality preference model meets the preset test condition, and taking the new initial air quality preference model as the preset air quality preference model.

4. The method of claim 1, wherein, After controlling the target device according to the control parameter of the target device, the method further comprises the following steps: determining whether a device adjustment instruction of the user is received; controlling the target device based on the device adjustment instruction, storing a control result and the current state data into a target storage, and updating the preset air quality preference model according to the control result and the current state data.

5. The method of claim 1, wherein, The method further comprises the following steps: determining whether there is an external access request for the target storage; if there is the external access request for the target storage, verifying the external access request; if the verification fails, issuing a rejection access reminder, and issuing a reminder information to a preset mobile terminal.

6. The method of claim 1, wherein, The method further comprises the following steps: determining whether a data display request is received; if the data display request is received, displaying the current state data and / or the current air data.

7. An indoor air quality conditioning device based on user preferences, characterized by, The method comprises the following steps: The acquisition module is configured to acquire current state data of a user and current air data of an environment in which the user is located, the current state data of the user including a current physical health state of the user. The prediction decision module is configured to input the current state data into a preset air quality preference model to obtain corresponding required air data of the user, and to determine whether the current air data meets the required air data, wherein the preset air quality preference model is learned based on historical state data of the user and corresponding required air data of the historical state data by using a random forest algorithm and a deep reinforcement learning algorithm. The control module is configured to determine a target device and a control parameter of the target device according to a parameter that does not meet the required air data when any parameter in the current air data does not meet the required air data, and to control the target device according to the control parameter of the target device.

8. The apparatus of claim 7, wherein, Before the current state data is input into the preset air quality preference model, the prediction decision module is further configured to: acquire historical state data of the user and corresponding required air data of the historical state data; divide the historical state data and the corresponding required air data of the historical state data into a training set and a test set based on a preset division ratio, wherein the training set and the test set each include multiple groups of data, and each group of data is composed of one piece of state data and corresponding required air data of the piece of state data; learn the training set based on the random forest algorithm and the deep reinforcement learning algorithm to obtain an initial air quality preference model, and test the initial air quality preference model by using the test set, and if a test result meets a preset test condition, the initial air quality preference model is taken as the preset air quality preference model.

9. An electronic device, comprising: The computer program is executed by the processor to implement the indoor air quality adjustment method based on user preference. The computer program is executed by the processor to implement the indoor air quality adjustment method based on user preference.

10. A computer storage medium having stored thereon a computer program, characterized in that ​

Images