Intelligent ecological environment optimization method and system based on machine learning

Through the intelligent ecological environment optimization method based on machine learning, users' behavior patterns and environmental preference requirements are identified, and indoor environment parameters are automatically adjusted, which solves the problem of insufficient optimization in traditional technologies and improves user experience and energy efficiency.

CN119063187AInactive Publication Date: 2024-12-03LIAONING INST OF SCI & TECH
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411242424.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The optimization of traditional indoor ecological environment depends on the linkage of user manual settings and smart devices, and lacks dynamic adaptability to user behavior and environmental changes, resulting in the optimization being not intelligent enough, difficult to meet personalized needs, and affecting user experience.

Method used

Using an intelligent ecological environment optimization method based on machine learning, by obtaining real-time environment and behavior data, identifying the user's target behavior patterns and environmental preference requirements, determining the parameters to be adjusted, and using preset energy efficiency optimization rules to formulate adjustment strategies, control the intelligent device to Optimize the indoor environment.

Benefits of technology

It realizes automatic adjustments based on user behavior patterns and environmental changes, accurately optimizes indoor environmental parameters, meets personalized needs, improves user comfort, and reduces energy consumption through energy efficiency optimization, achieving smarter and more energy-saving automated control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063187A_ABST
    Figure CN119063187A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent ecological environment optimization method and system based on machine learning, relates to the technical field of environment optimization, and mainly aims to intelligently optimize an indoor ecological environment, meet individual requirements of users and improve user experience. According to the main technical scheme, the method comprises the steps of obtaining indoor real-time environment data and real-time behavior data; inputting the real-time environment data and the real-time behavior data into a behavior preference recognition model to obtain a target behavior mode corresponding to the user and an environment preference requirement corresponding to the target behavior mode; determining to-be-adjusted parameters corresponding to the real-time environment data in the target behavior mode according to the environment preference requirements; determining an adjustment strategy corresponding to the to-be-adjusted parameter by using a preset energy efficiency optimization rule; and controlling related indoor intelligent equipment to execute corresponding operation according to the adjustment strategy so as to optimize the indoor ecological environment. The main purpose is to intelligently optimize the indoor ecological environment, meet the individual needs of users and improve the user experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of environmental optimization technology, and in particular to an intelligent ecological environment optimization method and system based on machine learning. Background Art

[0002] With the development of science and technology and the improvement of living standards, people have higher and higher requirements for living and working environments. In modern buildings and home environments, the application of intelligent technology is becoming more and more extensive, especially in environmental control. Intelligent environmental control systems can automatically adjust indoor temperature, humidity, lighting and other parameters to meet users' comfort needs by integrating a variety of intelligent devices (such as air conditioners, humidifiers, curtains, etc.).

[0003] At present, traditional indoor ecological environment optimization mostly relies on users manually setting preferred environmental parameters, coupled with linkage control between smart devices, that is, controlling smart devices according to preferred environmental parameters to optimize the indoor ecological environment. However, this preferred environmental parameters and device linkage are often fixed, lacking the ability to dynamically adapt to user behavior and environmental changes, resulting in insufficient intelligence in indoor ecological environment optimization, making it difficult to meet users' personalized needs and affecting user experience. Summary of the invention

[0004] In view of the above problems, the present application provides an intelligent ecological environment optimization method and system based on machine learning, the main purpose of which is to intelligently optimize the indoor ecological environment, meet the personalized needs of users, and improve user experience.

[0005] In order to solve the above technical problems, this application proposes the following solutions: In a first aspect, the present application provides a method for optimizing an intelligent ecological environment based on machine learning, the method comprising: Obtain real-time indoor environmental data and real-time behavioral data; Inputting the real-time environment data and the real-time behavior data into a behavior preference recognition model to obtain a target behavior pattern corresponding to the user and an environment preference requirement corresponding to the target behavior pattern; Determine, according to the environmental preference requirement, the parameter to be adjusted corresponding to the real-time environmental data in the target behavior mode; Determine the adjustment strategy corresponding to the parameter to be adjusted by using the preset energy efficiency optimization rule; According to the adjustment strategy, relevant smart devices in the room are controlled to perform corresponding operations to optimize the indoor ecological environment.

[0006] In a second aspect, the present application provides an intelligent ecological environment optimization device based on machine learning, the system comprising: A first acquisition unit, used to acquire indoor real-time environmental data and real-time behavior data; An identification unit, used to input the real-time environment data and the real-time behavior data into a behavior preference identification model to obtain a target behavior pattern corresponding to the user and an environment preference requirement corresponding to the target behavior pattern; A first determining unit, configured to determine, according to the environmental preference requirement, a parameter to be adjusted corresponding to the real-time environmental data in the target behavior mode; A second determining unit, used to determine an adjustment strategy corresponding to the parameter to be adjusted by using a preset energy efficiency optimization rule; The control unit is used to control the relevant smart devices in the room to perform corresponding operations according to the adjustment strategy to optimize the indoor ecological environment.

[0007] In order to achieve the above-mentioned purpose, according to the third aspect of the present application, a storage medium is provided, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the intelligent ecological environment optimization method based on machine learning of the above-mentioned first aspect.

[0008] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present application, a processor is provided, which is used to run a program, wherein the program executes the intelligent ecological environment optimization method based on machine learning of the above-mentioned first aspect when running.

[0009] Through the above-mentioned technical scheme, the present application provides an intelligent ecological environment optimization method and system based on machine learning. When the indoor ecological environment needs to be optimized, real-time environmental data and real-time behavior data in the room are obtained, and the real-time environmental data and real-time behavior data are input into the behavior preference recognition model to obtain the target behavior pattern corresponding to the user and the environmental preference requirements corresponding to the target behavior pattern. According to the environmental preference requirements, the parameters to be adjusted corresponding to the real-time environmental data under the target behavior pattern are determined, and the adjustment strategies corresponding to the parameters to be adjusted are determined using preset energy efficiency optimization rules. According to the adjustment strategies, the relevant intelligent devices in the room are controlled to perform corresponding operations to optimize the indoor ecological environment. Through the technical solution provided by the present application, the user's current behavior pattern and the user's environmental preference requirements under the behavior pattern can be identified based on real-time environmental data and behavioral data, and the parameters that need to be adjusted under the current behavior pattern, i.e., the parameters to be adjusted, can be obtained based on the environmental preference requirements and real-time environmental data, so that subsequent adjustments based on the parameters to be adjusted can meet the user's environmental preferences, that is, they can be automatically adjusted according to the user's behavior pattern and environmental changes, so as to more accurately adjust the indoor environmental parameters to meet the user's personalized needs and enhance the user's comfort. At the same time, by optimizing the energy efficiency of the parameters to be adjusted, an adjustment strategy is obtained, so that the adjustment strategy can control related smart devices in a more energy-saving way, which not only reduces energy consumption, but also realizes more intelligent automatic control, thereby ensuring that a comfortable indoor ecological environment is provided to users in a long-term and stable manner.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A flow chart of an intelligent ecological environment optimization method based on machine learning provided in an embodiment of the present application is shown; Figure 2 Another flow chart of an intelligent ecological environment optimization method based on machine learning provided in an embodiment of the present application is shown; Figure 3 A block diagram of a smart ecological environment optimization system based on machine learning provided in an embodiment of the present application is shown; Figure 4A block diagram showing the composition of another intelligent ecological environment optimization system based on machine learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0013] At present, traditional indoor ecological environment optimization mostly relies on users manually setting preferred environmental parameters, coupled with linkage control between smart devices, that is, controlling smart devices according to preferred environmental parameters to optimize the indoor ecological environment. However, such preferred environmental parameters and device linkage are often fixed, lacking the ability to dynamically adapt to user behavior and environmental changes, that is, unable to automatically adjust according to user behavior patterns and environmental changes, resulting in insufficient intelligence in indoor ecological environment optimization, making it difficult to meet users' personalized needs and affecting user experience.

[0014] To this end, the present application embodiment provides an intelligent ecological environment optimization method based on machine learning, through which the indoor ecological environment can be intelligently optimized to meet the personalized needs of users and improve user experience. The specific execution steps are as follows: Figure 1 As shown, including: 101. Obtain real-time indoor environmental data and real-time behavioral data.

[0015] In this step, a variety of environment-related sensors are deployed indoors in advance, such as temperature sensors, humidity sensors, light sensors, etc., based on which indoor environmental conditions can be monitored in real time. The above sensor data can be collected through a smart home system or an Internet of Things platform, and a reasonable collection frequency can be set for these sensors, such as collecting data every 5 minutes or every 10 minutes, to obtain real-time environmental data.

[0016] Behavioral data includes but is not limited to device interaction records, mobile device data, and user feedback. Device interaction records are used to record the user's interaction with smart devices, such as records of controlling devices through smart home applications or voice assistants. Mobile device data refers to location information, activity status, etc. collected using the user's mobile device (such as a smartphone or wearable device). User feedback can be obtained through questionnaires or direct user feedback to obtain the user's subjective evaluation of the environment. By collating the above data, real-time behavioral data can be obtained.

[0017] 102. Input the real-time environment data and the real-time behavior data into the behavior preference recognition model to obtain the target behavior pattern corresponding to the user and the environment preference requirement corresponding to the target behavior pattern.

[0018] In this step, historical environmental data and historical behavioral data of the indoor environment over a period of time in the past, such as a week or a month, can be collected in advance. Then, key features are extracted from the historical environmental data and historical behavioral data, such as time features (what time do you get up and go to bed every day), behavioral features (what devices are used and how often), environmental features (indoor and outdoor temperature and humidity changes), and user preference features (favorite temperature, humidity, etc.). Next, a suitable machine learning model is selected to train a behavioral preference recognition model, such as a random forest or deep neural network, and the extracted key features are preprocessed, such as normalization and standardization. Finally, the preprocessed key features are used to train the aforementioned selected behavioral preference recognition model to obtain a trained behavioral preference model. This behavioral preference model can not only identify different behavioral patterns corresponding to users, but also identify the predicted environmental preference requirements of users under different behavioral patterns.

[0019] Among them, the behavior pattern refers to the user's behavioral tendencies and regularities during a specific time period or during certain activities. Such as rest mode, work mode, etc. The environmental preference requirements are the user's personal preferences for indoor environmental conditions, such as temperature of 22 degrees, humidity of 50%, light intensity of 300 lux, etc. These preferences may vary from person to person and may also change with the time of day. For example, the rest mode prefers a relatively high temperature (24 degrees), relatively low humidity (50%), and weak light intensity (200 lux), while the work mode prefers a lower temperature (22 degrees), lower humidity (40%), and stronger light intensity (500 lux).

[0020] By inputting the real-time environment data and the real-time behavior data into the behavior preference recognition model, the user's current corresponding target behavior pattern and its environment preference requirements can be output through the behavior preference recognition model.

[0021] 103. Determine the parameters to be adjusted corresponding to the real-time environmental data under the target behavior mode according to the environmental preference requirements.

[0022] The environmental preference requirements of the behavior preference recognition model in the aforementioned step 102 are mapped to specific environmental parameters, such as temperature, humidity, light intensity, etc., to obtain the target environmental parameters corresponding to the target behavior pattern. Then, the current environmental parameters are extracted from the real-time environmental data, and the differences between the current environmental parameters and the target environmental parameters are compared to find out the parts that need to be adjusted, and the parameters to be adjusted can be determined.

[0023] For example, assuming that the current environmental parameters are: temperature 26 degrees, humidity 40%, light intensity 350 lux, and the target environmental parameters are: temperature 22 degrees, humidity 45%, light intensity 350 lux. After comparison, the parameters to be adjusted are: temperature drops by 4 degrees and humidity rises by 5%.

[0024] 104. Determine an adjustment strategy corresponding to the parameter to be adjusted using a preset energy efficiency optimization rule.

[0025] In this step, the energy efficiency optimization rule is used to characterize the rule for minimizing the energy consumption of the adjustment process of the target adjustment parameter. Since the parameter to be adjusted may include multiple environmental parameters, and the change of an environmental parameter may involve multiple related smart devices, such as temperature changes can be related to air conditioners, electric curtains, etc., and humidity changes can be related to humidifiers, smart windows, etc. Therefore, each environmental parameter can be associated with the smart device that can affect its change in advance, and the corresponding correlation degree can be assigned according to the degree of influence. Taking 0-1 as an example, if the air conditioner has a greater impact on the temperature change, the correlation between the two can be set to 0.9, and the opening and closing of the electric curtain can also have an impact on the temperature change, but the impact is small, and the correlation between the two can be set to 0.3, etc. At the same time, determine the energy efficiency of each related smart device when adjusting according to the parameter to be adjusted, such as the power consumption of the air conditioner in energy-saving mode. Combine the correlation and energy efficiency to calculate the adjustment contribution of each smart device, which is used to characterize the role of a smart device relative to other smart devices when adjusting environmental parameters. Since the greater the correlation and the higher the energy efficiency, the higher the corresponding adjustment contribution. Therefore, the adjustment strategy corresponding to the parameter to be adjusted can be determined according to the adjustment contribution. For example, the priority order of related smart devices can be set according to the adjustment contribution, and a single control or linkage control strategy can be formulated according to the priority order, that is, corresponding control parameters can be set for related smart devices to ensure that the subsequent related smart devices can control the parameters to work and optimize the indoor ecological environment.

[0026] It should be noted that multiple objectives are considered when formulating strategies, such as minimizing energy consumption while ensuring user comfort, and allowing strategies to be dynamically adjusted according to environmental changes to adapt to changing conditions.

[0027] 105. Control relevant smart devices in the room to perform corresponding operations according to the adjustment strategy to optimize the indoor ecological environment.

[0028] As can be seen from step 104, the adjustment strategy includes relevant smart devices and control parameters corresponding to the relevant smart devices. Therefore, in this step, by analyzing the adjustment strategy, it is possible to determine which smart devices need to be controlled and how they work. For example, the temperature of the air conditioner is set to 22 degrees, the humidity of the humidifier is set to 50%, etc. The control instructions corresponding to each relevant smart device are generated according to the control parameters, and the control instructions are sent to the corresponding relevant smart devices by the smart home system or the Internet of Things platform through wireless communication protocols (such as Wi-Fi, Bluetooth, etc.). Thereby, the relevant smart devices perform corresponding operations to optimize the indoor ecological environment.

[0029] Based on the above Figure 1 It can be seen from the implementation method that the present application provides an intelligent ecological environment optimization method based on machine learning, which is to obtain real-time indoor environmental data and real-time behavior data when the indoor ecological environment needs to be optimized, and input the real-time environmental data and real-time behavior data into the behavior preference recognition model to obtain the target behavior pattern corresponding to the user and the environmental preference requirements corresponding to the target behavior pattern, determine the parameters to be adjusted corresponding to the real-time environmental data under the target behavior pattern according to the environmental preference requirements, determine the adjustment strategy corresponding to the parameters to be adjusted using the preset energy efficiency optimization rules, and control the relevant indoor smart devices to perform corresponding operations according to the adjustment strategy to optimize the indoor ecological environment. Through the technical solution provided by the present application, the user's current behavior pattern and the user's environmental preference requirements under the behavior pattern can be identified based on real-time environmental data and behavioral data, and the parameters that need to be adjusted under the current behavior pattern, i.e., the parameters to be adjusted, can be obtained based on the environmental preference requirements and real-time environmental data, so that subsequent adjustments based on the parameters to be adjusted can meet the user's environmental preferences, that is, they can be automatically adjusted according to the user's behavior pattern and environmental changes, so as to more accurately adjust the indoor environmental parameters to meet the user's personalized needs and enhance the user's comfort. At the same time, by optimizing the energy efficiency of the parameters to be adjusted, an adjustment strategy is obtained, so that the adjustment strategy can control related smart devices in a more energy-saving way, which not only reduces energy consumption, but also realizes more intelligent automatic control, thereby ensuring that a comfortable indoor ecological environment is provided to users in a long-term and stable manner.

[0030] Further, the preferred embodiment of the present application is in the above Figure 1 Based on this, a detailed description of the process of intelligent ecological environment optimization based on machine learning is given. The specific steps are as follows Figure 2 As shown, including: 201. Obtain real-time indoor environmental data and real-time behavior data.

[0031] This step is combined with the description of step 101 in the above method, and the same contents will not be repeated here.

[0032] 202. Input the real-time environment data and the real-time behavior data into the behavior preference recognition model to obtain the target behavior pattern corresponding to the user and the environment preference requirement corresponding to the target behavior pattern.

[0033] This step is combined with the description of step 102 in the above method, and the same contents are not repeated here.

[0034] It should be noted that the specific execution process for constructing the behavioral preference model is: obtaining historical environmental data and historical behavioral data within a preset period; extracting target features from the historical environmental data and historical behavioral data; and using the target features to train the machine learning model to obtain a behavioral preference recognition model.

[0035] Among them, the target features include time features, behavior features, environment features and user preference features. The behavior preference recognition model is used to identify different behavior patterns corresponding to users and the environment preference requirements corresponding to different behavior patterns.

[0036] In this step, historical environmental data and historical behavioral data within a preset period are first collected from the smart home system or IoT platform. The preset period can be a week, a month, or a longer period of time. Historical environmental data includes temperature, humidity, light intensity, etc., which are usually provided by various sensors installed indoors. Historical behavioral data includes device interaction records, mobile device data, and user feedback, which are usually provided by smart home applications or voice assistants, users' mobile devices (such as smartphones or wearable devices), and user feedback questionnaires or subjective evaluation information.

[0037] After obtaining historical environmental data and historical behavioral data, the most useful features for identification, namely target features, can be selected through correlation analysis, principal component analysis (PCA) and other methods. That is, time features, behavioral features, environmental features and user preference features can be extracted respectively. For time features, the historical behavioral data can be timestamped and parsed into easy-to-use formats, such as hours, minutes, days of the week, months, etc., and then periodic features can be extracted from them, such as behavioral patterns in the same time period every day, behavioral habits at fixed times every week, etc. For behavioral features, the type of each behavior can be identified first, such as turning on the lights, turning off the air conditioner, etc., and then the frequency of each behavior can be counted to analyze the user's behavioral patterns, and the duration of each behavior can be recorded at the same time, such as the duration of turning on the lights, etc., so that the behavioral features at least include the behavior type, behavior frequency and behavior duration. For environmental features, key environmental parameters in historical environmental data can be extracted, such as temperature, humidity, light intensity, etc., and then the trend of environmental parameters can be analyzed, such as the temperature change curve over time. For user preference features, we can record the user's manual adjustment records of environmental parameters, that is, the user's preference settings, such as manually set temperature, humidity, etc., and collect user feedback information on environmental settings, that is, user preference feedback, such as satisfaction scores, etc.

[0038] After the target features are extracted, you can choose a suitable machine learning model, such as random forest, support vector machine (SVM) or deep neural network (DNN), etc. And preprocess the extracted features, such as missing value filling, outlier processing, data normalization, etc. to form a feature data set for the extracted features, and divide it into training set, validation set and test set. Use the training set data to train the behavior preference model, and adjust the parameters through the validation set to optimize the model performance. Finally, use the test set data to evaluate the prediction performance of the model, such as accuracy, recall rate, etc.

[0039] Apply the trained model to new real-time environmental data and real-time historical data to identify the user's current behavior pattern, that is, the target behavior pattern, and at the same time identify the user's environmental preference requirements under the target behavior pattern. For example, when the target behavior pattern is the working mode, the user's preferred temperature in the working mode is 22 degrees and the humidity is 50%.

[0040] 203. Determine the target environmental parameters corresponding to the target behavior pattern according to the environmental preference requirements.

[0041] In this step, since the environmental preference requirements are the user's personal preferences for indoor environmental conditions. They usually include the user's expected indoor temperature range, humidity range, light intensity, noise level, air quality, etc. Therefore, by analyzing the environmental preference requirements, the target environmental parameters corresponding to the target behavior pattern can be obtained. Among them, the target environmental parameters are the user's expected environmental parameters for indoor environmental conditions, which can be a single environmental parameter or a set of multiple environmental parameters. This embodiment does not limit this. It should be noted that if the user has clear preference settings, they can be read and used directly.

[0042] 204. Extract current environmental parameters from the real-time environmental data.

[0043] In this step, since the real-time environmental data is the most recent environmental data acquired by various sensors deployed indoors according to the acquisition frequency, the real-time environmental data includes the environmental parameters that can be currently acquired, and the current environmental parameters of the room can be obtained by extraction. The current environmental parameters can be extracted according to the type of indoor sensors related to the environment, or according to the environmental parameters included in the target environmental parameters, which is not limited in this embodiment.

[0044] 205. Determine the parameters to be adjusted based on the comparison result between the target environmental parameters and the current environmental parameters.

[0045] In this step, the target environmental parameters are compared and analyzed with the current environmental parameters, that is, whether the current environmental parameters are within the target environmental parameter range, so as to determine the environmental parameter items that need to be adjusted, and through difference calculation, the specific environmental parameter values ​​that need to be adjusted can also be obtained, and the adjusted environmental parameter items and their specific environmental parameter values ​​are used as parameters to be adjusted.

[0046] 206. Determine the related smart devices corresponding to the parameter to be adjusted according to the parameter-device association relationship, and obtain the association degree corresponding to each related smart device.

[0047] Among them, one environmental parameter corresponds to at least one related smart device.

[0048] In this step, a correlation table between an environmental parameter and related smart devices can be established in advance based on which smart devices affect the change of a specific environmental parameter. Each environmental parameter can correspond to one related smart device, but it can also correspond to multiple related smart devices. For example, the related smart devices for temperature can be smart air conditioners, smart heaters, smart curtains, etc., the related smart devices for humidity can be smart humidifiers, smart dehumidifiers, etc., and the related smart devices for light intensity can be smart curtains, smart lights, etc. At the same time, a score is assigned for the correlation between each related smart device and its corresponding specific environmental parameter, and the correlation is used to characterize the influence of the related smart device on the specific environmental parameter. The higher the correlation, the stronger the ability of the related smart device to adjust the environmental parameter. The value of the assigned score can be evaluated by using historical data to evaluate the performance of the related smart device when adjusting the specific environmental parameter, and determined based on the evaluation results.

[0049] For example, as shown in Table 1: Table 1 Specific environmental parameters Related smart devices Relevance temperature air conditioner 0.9 Heater 0.7 curtain 0.3 humidity humidifier 0.8 Dehumidifier 0.9 illumination Lighting 0.8 curtain 0.6 noise Sound absorbing equipment 0.7 Audio equipment 0.5 Air Quality Air Purifier 0.8 In order to ensure that the relevant smart devices can respond in time in the future and ensure the effectiveness of indoor ecological environment optimization, it is necessary to ensure that the relevant smart devices in the association table are available and can be controlled. Specifically, before determining the relevant smart devices corresponding to the parameters to be adjusted according to the parameter-device association relationship, the method also includes: monitoring the operating status corresponding to each smart device in the room; and updating the parameter-device association relationship according to the operating status.

[0050] In this step, all smart devices are equipped with sensors that can upload their status information in real time in advance. The device status information fed back by these sensors is collected through the smart home system or the Internet of Things platform, such as the working status of the device (such as on, off, fault, etc.), real-time energy consumption or health status (such as whether the sensor is working properly) and other indicators. The corresponding operating status can be determined through the device status information. According to the operating status of the smart device, it can be judged whether it is valid, that is, whether it is available and controllable. If it is determined that a smart device has a fault or works abnormally, it needs to be temporarily removed from the parameter-device association relationship, and the parameter-device association relationship is updated so that the smart devices in the parameter-device association relationship are always fault-free and working properly, ensuring the effectiveness of the subsequent indoor ecological environment optimization.

[0051] 207. Calculate the energy efficiency of each relevant smart device.

[0052] In this step, the energy consumption data of the relevant smart device can be determined from the device specifications recorded in the device manual, such as through the power, energy efficiency level and other information contained in the device specifications, or can be determined by the energy consumption data recorded in the status information of the relevant smart device deployed on the relevant smart device in step 206 for feedback. After the energy consumption data of each relevant smart device is obtained, the energy consumption of each associated smart device when adjusting a certain environmental parameter in the adjustment parameter is evaluated according to the energy consumption data. The adjustment of the parameter to be adjusted can be regarded as a task to be completed, and the energy efficiency of each related smart device when completing the task is calculated. The energy efficiency is used to measure the energy consumed by each related smart device when completing the task. The higher the energy efficiency, the less energy the related smart device consumes when completing the same task. Specifically, it can be calculated using the following formula: Energy efficiency = effect of device completing the task / energy consumed by the device. Exemplarily, the smart air conditioner consumes 1.5 kWh of electricity for every 1°C reduction, and the smart curtain has no energy consumption. The target adjustment parameter is regarded as a task to be completed, and the energy efficiency ratio of each associated smart device when completing the task is calculated. For example, a smart air conditioner consumes 1.5 kWh of energy for every degree of temperature reduction, and its energy efficiency ratio is 1 / 1.5 ≈ 0.67, while the energy efficiency of smart curtains is infinite (because there is no energy consumption).

[0053] 208. Determine an adjustment strategy corresponding to the parameter to be adjusted based on the correlation and energy efficiency.

[0054] The adjustment strategy includes relevant smart devices and control parameters of the relevant smart devices.

[0055] In this step, based on the two indicators of correlation and energy efficiency, the applicability and economy of each relevant smart device when adjusting specific environmental parameters can be comprehensively evaluated. According to the comprehensive evaluation results, the relevant smart devices are prioritized, and the optimal device adjustment strategy is formulated based on the priority ranking. The specific implementation process of determining the adjustment strategy corresponding to the parameter to be adjusted based on correlation and energy efficiency is as follows: calculate the adjustment contribution of each relevant smart device based on the correlation and energy efficiency; set the control parameters of each relevant smart device based on the adjustment contribution; use the relevant smart devices and the control parameters of the relevant smart devices as the adjustment strategy corresponding to the parameter to be adjusted.

[0056] It should be noted that the adjustment contribution represents the comprehensive performance of the relevant smart devices when adjusting specific environmental parameters, which combines the relevance and energy efficiency of the devices. Specifically, weight coefficients can be set for the relevance and energy efficiency according to the importance of relevance and energy efficiency in different application scenarios, and weighted sum calculations can be performed by combining the weight coefficients and the actual values ​​of relevance and energy efficiency to obtain the comprehensive performance of each relevant smart device when adjusting specific environmental parameters, that is, the adjustment contribution. The weighted summation method is as follows: Adjusted contribution = w1 × correlation + w2 × energy efficiency Among them, w1 and w2 are weight coefficients, which can be adjusted according to the actual application scenario.

[0057] By comparing the adjustment contribution, each related smart device can be prioritized, and the related smart device with the highest priority can be selected to generate an adjustment strategy, that is, a single control strategy, or an adjustment strategy in which each related smart device participates can be generated according to the priority, that is, a linkage control strategy. As an implementation method: Starting from the device with the highest correlation, energy efficiency can be considered in turn, so as to select an optimal related smart device, that is, select a related smart device with a high correlation and good energy efficiency as the first choice of the specific environmental parameters in the parameters to be adjusted, and at the same time determine the specific control parameters that need to be adjusted for the optimal related smart device, and use the related smart devices and the control parameters of the related smart devices as part of the adjustment strategy. For example, the parameters to be adjusted are: the temperature is reduced by 2-3 degrees, and the light intensity is increased by 50 lux. Combined with the above Table 1, it can be determined that the air conditioner has the highest correlation with temperature, and its energy efficiency is very high. Therefore, the air conditioner can be selected as the optimal related smart device for temperature adjustment, and the air conditioner temperature can be set to 22 degrees. As for light intensity, curtains have the highest energy efficiency, but the correlation is low, while lamps have a high correlation and acceptable energy efficiency, so more lamps can be turned on to increase the light intensity by 50 lux.

[0058] As another implementation: When a specific adjustment parameter has multiple related smart devices, the corresponding device adjustment logic can be set by linking multiple related smart devices according to the priority sorting. Specifically, the level of intervention adjustment can be set for the related smart devices according to the priority sorting, and the intervention timing of the related smart devices at different levels can be set according to the difference in adjustment contribution. If the difference in adjustment contribution is small, the intervention can be carried out at the same time to achieve the effect as quickly as possible. If the difference in adjustment contribution is large, the intervention time corresponding to the different gaps can be set, and linkage assistance can also be achieved. According to the intervention timing and intervention level, the corresponding control parameters are set for each related smart device, and used as part of the adjustment strategy. Taking temperature as an example, assuming that the related smart device at the first level is an air conditioner, and the related smart device at the second level can be a curtain or a heater, if the adjustment contribution of the air conditioner is 0.84 and the adjustment contribution of the heater is 0.68, if the adjustment contribution difference threshold of the linkage judgment is 0.1, if it is less than or equal to 0.1, the two are linked, and the intervention time can be 5 minutes. If it is greater than 0.1, the two have different intervention times, that is, they intervene in sequence, and the air conditioner can intervene for 10 minutes first, and then the heater intervenes for 5 minutes. This linkage method can not only achieve fine-grained adjustments, but also achieve multiple safeguards. That is, if a single device has a problem, other devices can also intervene to ensure that environmental parameters are maintained within the ideal range. Moreover, by having multiple related smart devices work together, it can avoid excessive work of a single related smart device, thereby reducing energy consumption.

[0059] 209. Control relevant smart devices in the room to perform corresponding operations according to the adjustment strategy to optimize the indoor ecological environment.

[0060] This step is combined with the description of step 105 in the above method, and the same contents are not repeated here.

[0061] It should be noted that the specific execution process of controlling the relevant smart devices in the room to perform corresponding operations according to the adjustment strategy is: determining the relevant smart devices and control parameters of the relevant smart devices according to the adjustment strategy; generating corresponding control instructions based on the control parameters, and sending the control instructions to the relevant smart devices to optimize the indoor ecological environment.

[0062] Since step 208 takes the relevant smart devices and the control parameters of the relevant smart devices as part of the adjustment strategy, the relevant smart devices and their corresponding control parameters can be obtained by parsing the adjustment strategy. Based on the control parameters, corresponding control instructions can be generated to control the corresponding relevant smart devices. The control instructions are sent to the relevant smart devices through the smart home system or the Internet of Things platform. After receiving the instructions, the relevant smart devices perform corresponding operations according to the instructions.

[0063] Furthermore, as a response to the above Figure 1-2The implementation of the method embodiment shown in the figure, the embodiment of the present application provides an intelligent ecological environment optimization device based on machine learning, which is used to intelligently optimize the indoor ecological environment, meet the personalized needs of users, and improve user experience. The embodiment of this system corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. Specifically, Figure 3 As shown, the system includes: A first acquisition unit 31 is used to acquire indoor real-time environment data and real-time behavior data; The recognition unit 32 is used to input the real-time environment data and the real-time behavior data into a behavior preference recognition model to obtain a target behavior pattern corresponding to the user and an environment preference requirement corresponding to the target behavior pattern; A first determining unit 33 is used to determine the to-be-adjusted parameter corresponding to the real-time environmental data in the target behavior mode according to the environmental preference requirement; A second determining unit 34 is used to determine an adjustment strategy corresponding to the parameter to be adjusted by using a preset energy efficiency optimization rule; The control unit 35 is used to control the relevant smart devices in the room to perform corresponding operations according to the adjustment strategy to optimize the indoor ecological environment.

[0064] Further, such as Figure 4 As shown, the system also includes: A second acquisition unit 36 ​​is used to acquire historical environment data and historical behavior data within a preset period before inputting the real-time environment data and the real-time behavior data into the behavior preference recognition model to obtain the target behavior pattern corresponding to the indoor user and the environment preference requirement corresponding to the target behavior pattern; An extraction unit 37, configured to extract target features from the historical environment data and the historical behavior data, wherein the target features include time features, behavior features, environment features, and user preference features; The construction unit 38 is used to train the machine learning model using the target features to obtain the behavior preference model, and the behavior preference model is used to identify different behavior patterns corresponding to the user and the environmental preference requirements corresponding to the different behavior patterns.

[0065] Further, such as Figure 4 As shown, the first determining unit 33 includes: A first determination module 331 is used to determine the target environment parameter corresponding to the target behavior mode according to the environment preference requirement; An extraction module 332 is used to extract current environmental parameters from the real-time environmental data; The second determination module 333 is used to determine the parameter to be adjusted based on the comparison result between the target environmental parameter and the current environmental parameter.

[0066] Further, such as Figure 4 As shown, the second determining unit 34 includes: The third determination module 341 is used to determine the relevant smart device corresponding to the parameter to be adjusted according to the parameter-device association relationship, and obtain the association degree corresponding to each of the relevant smart devices. One environmental parameter corresponds to at least one relevant smart device; A calculation module 342, used to calculate the energy efficiency corresponding to each of the related smart devices; The fourth determination module 343 is used to determine an adjustment strategy corresponding to the parameter to be adjusted based on the correlation degree and the energy efficiency, where the adjustment strategy includes related smart devices and control parameters of the related smart devices.

[0067] Further, such as Figure 4 As shown, the system also includes: The monitoring module 344 is used to monitor the operation status of each indoor smart device before determining the related smart device corresponding to the parameter to be adjusted according to the parameter-device association relationship; The updating module 345 is used to update the parameter-device association relationship according to the operating status.

[0068] Further, such as Figure 4 As shown, the fourth determination module 343 is specifically used to: Calculating the adjustment contribution of each of the related smart devices according to the correlation degree and the energy efficiency; Setting a control parameter of each of the related smart devices based on the adjustment contribution; The related smart devices and the control parameters of the related smart devices are used as adjustment strategies corresponding to the parameters to be adjusted.

[0069] Further, such as Figure 4 As shown, the control unit 35 includes: A fifth determination module 351, configured to determine relevant smart devices and control parameters of the relevant smart devices according to the adjustment strategy; The control module 352 is used to generate corresponding control instructions based on the control parameters and send the control instructions to the relevant smart devices to optimize the indoor ecological environment.

[0070] Furthermore, an embodiment of the present application further provides a storage medium, wherein the storage medium is used to store a computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the above Figure 1-2The intelligent ecological environment optimization method based on machine learning described in.

[0071] Furthermore, the embodiment of the present application also provides a processor, the processor is used to run a program, wherein the program executes the above Figure 1-2 The intelligent ecological environment optimization method based on machine learning described in.

[0072] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0073] It is understandable that the related features in the above methods and systems can be referenced to each other. In addition, the "first", "second" and the like in the above embodiments are used to distinguish the embodiments, and do not represent the advantages and disadvantages of the embodiments.

[0074] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0075] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the application is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the application described herein, and the description of the specific language above is for the purpose of disclosing the best mode of implementation of the application.

[0076] In addition, the memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0077] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0078] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0081] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0082] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0083] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0084] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0086] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An intelligent ecological environment optimization method based on machine learning, characterized in that: The method comprises: Obtain real-time indoor environmental data and real-time behavioral data; Inputting the real-time environmental data and the real-time behavioral data into a behavior preference recognition model to obtain a target behavior pattern corresponding to the user and an environmental preference requirement corresponding to the target behavior pattern; Determining, according to the environmental preference requirement, parameters to be adjusted corresponding to the real-time environmental data in the target behavior mode; Determining an adjustment strategy corresponding to the parameter to be adjusted using a preset energy efficiency optimization rule; According to the adjustment strategy, relevant smart devices in the room are controlled to perform corresponding operations to optimize the indoor ecological environment.

2. The method according to claim 1, characterized in that Before inputting the real-time environmental data and the real-time behavioral data into a behavior preference recognition model to obtain a target behavior pattern corresponding to the indoor user and an environmental preference requirement corresponding to the target behavior pattern, the method further includes: Obtain historical environmental data and historical behavior data within a preset period; Extracting target features from the historical environment data and the historical behavior data, wherein the target features include time features, behavior features, environment features, and user preference features; The target features are used to train the machine learning model to obtain the behavior preference model, which is used to identify different behavior patterns corresponding to users and the environmental preference requirements corresponding to different behavior patterns.

3. The method according to claim 1, characterized in that Determining the parameters to be adjusted corresponding to the real-time environmental data in the target behavior mode according to the environmental preference requirement includes: Determining target environmental parameters corresponding to the target behavior pattern according to the environmental preference requirements; Extracting current environmental parameters from the real-time environmental data; The parameter to be adjusted is determined based on a comparison result between the target environmental parameter and the current environmental parameter.

4. The method according to claim 1, wherein Determining the adjustment strategy corresponding to the parameter to be adjusted by using the preset energy efficiency optimization rule includes: Determine the related smart devices corresponding to the parameter to be adjusted according to the parameter-device association relationship, and obtain the association degree corresponding to each of the related smart devices, where one environmental parameter corresponds to at least one related smart device; Calculating the energy efficiency of each of the related smart devices; An adjustment strategy corresponding to the parameter to be adjusted is determined based on the correlation degree and the energy efficiency, where the adjustment strategy includes relevant smart devices and control parameters of the relevant smart devices.

5. The method according to claim 4, characterized in that Before determining the relevant smart device corresponding to the parameter to be adjusted according to the parameter-device association relationship, the method further includes: Monitor the operating status of each smart device in the room; The parameter-device association relationship is updated according to the operating status.

6. The method according to claim 4, characterized in that Determining an adjustment strategy corresponding to the parameter to be adjusted based on the correlation and the energy efficiency includes: Calculating the adjustment contribution of each of the related smart devices according to the correlation degree and the energy efficiency; Setting a control parameter of each of the related smart devices based on the adjustment contribution; The relevant smart devices and their control parameters are used as adjustment strategies corresponding to the parameters to be adjusted.

7. The method according to any one of claims 1 to 6, characterized in that According to the adjustment strategy, relevant smart devices in the room are controlled to perform corresponding operations to optimize the indoor ecological environment, including: determining relevant smart devices and control parameters of the relevant smart devices according to the adjustment strategy; Generate corresponding control instructions based on the control parameters, and send the control instructions to the relevant smart devices to optimize the indoor ecological environment.

8. An intelligent ecological environment optimization device based on machine learning, characterized in that: The system comprises: A first acquisition unit is used to acquire indoor real-time environmental data and real-time behavior data; an identification unit, configured to input the real-time environmental data and the real-time behavioral data into a behavior preference identification model to obtain a target behavior pattern corresponding to the user and an environmental preference requirement corresponding to the target behavior pattern; A first determining unit is configured to determine, according to the environmental preference requirement, a parameter to be adjusted corresponding to the real-time environmental data in the target behavior mode; A second determining unit, configured to determine an adjustment strategy corresponding to the parameter to be adjusted by using a preset energy efficiency optimization rule; The control unit is used to control the relevant smart devices in the room to perform corresponding operations according to the adjustment strategy to optimize the indoor ecological environment.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein, when the program is running, the device where the storage medium is located is controlled to execute the intelligent ecological environment optimization method based on machine learning as described in any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the intelligent ecological environment optimization method based on machine learning as described in any one of claims 1 to 7.

Citation Information

Cited By

  • Intelligent light curtain linkage control system and method based on environmental perception

    CN119247865A

  • Intelligent environment purification and humidification integrated linkage regulation and control method and system

    CN119617602A

  • Control method, system and device and storage medium

    CN119861591A