Household appliance control system and control method based on Internet of Things

Abstract

The invention relates to a household appliance control system and control method based on the Internet of Things, and belongs to the technical field of household appliance control. Real-time sensor data are acquired, the real-time sensor data are preprocessed, preprocessed sensor features are acquired, and then control analysis is performed according to the preprocessed sensor features; and obtaining an analysis result, thereby constructing a potential risk identification model in combination with the operation frequency of the household electrical appliance, the characteristics of the operation time period and the real-time household electrical appliance operation behavior data, and finally performing risk analysis on the analysis result and the current real-time household electrical appliance operation behavior data through the potential risk identification model. And controlling the household appliances according to the risk analysis result. According to the invention, the household electrical appliance which is started abnormally is found in time by combining the operation frequency of the household electrical appliance, the characteristics of the operation time period and the real-time household electrical appliance operation behavior data, so that fire caused by the high-power household electrical appliance which is started abnormally is avoided, and the control rationality of the household electrical appliance is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of home appliance control, and in particular to a home appliance control system and a control method based on the Internet of Things. Background Art

[0002] Smart devices have a certain degree of automation and can be easily programmed through an intuitive user interface. For example, a smart coffee machine can be programmed to make coffee at a certain time without connecting to the Internet during this period. Smart connected devices can also be remotely controlled or monitored through Bluetooth, LTE, Wi-Fi, wired network or other connection methods. Such as smart light bulbs, smart sockets, smart security cameras, smart refrigerators, etc. The application of smart technology can not only send, receive, and retrieve information normally, but also automatically turn on and off certain functions or devices. The application of communication technology can provide consumers with more interaction and control. Most of the smart technology here refers to smart devices - mobile phones, TVs, appliances, wearable devices, etc. Some consumers are keen to use smart technology to control everything from home security systems, electrical equipment to thermostats. The industry generally uses a terminal device to unify the association and management of devices in the home in the form of the Internet of Things, such as smartphones, smart TVs, smart speakers, etc., and uses interactive control methods such as voice to build a smart home appliance control system to realize the opening, closing and function adjustment of the unified interface of the device. At present, after household electrical appliances are plugged in, there will be a continuous flow of power even if they are not working, which means that there is usually a loss of 5% to 10% of the used power. When there is no one at home, it is best to unplug the electrical appliances. But if the user forgets to unplug the device, it is very inconvenient to unplug it when returning home temporarily. There are more and more types and functions of household appliances, and some functions are set more and more finely. The operating costs of users are constantly increasing. How to quickly and accurately realize the functions of the equipment has become one of the most concerned issues for users. In addition, many accidents, such as fires, are caused by unattended devices being plugged in. For example, the abnormal opening of medium and high-power equipment in the middle of the night cannot be identified in some existing technologies, which will lead to fires. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a home appliance control system and a control method based on the Internet of Things.

[0004] To achieve the above object, the technical solution adopted by the present invention is: The first aspect of the present invention provides a method for controlling household appliances based on the Internet of Things, comprising the following steps: Acquire real-time sensor data, and acquire preprocessed sensor features by preprocessing the real-time sensor data; Perform control analysis according to the preprocessed sensor characteristics to obtain analysis results; Build a potential risk identification model by combining the operation frequency of home appliances, the characteristics of the operation time period, and real-time home appliance operation behavior data; The potential risk identification model is used to perform risk analysis on the analysis results and the current real-time home appliance operation behavior data, and the home appliances are controlled according to the risk analysis results.

[0005] Furthermore, in this method, the real-time sensor data is preprocessed to obtain the preprocessed sensor features, specifically: Setting a sensor data noise characteristic range, and performing data filtering, denoising, and data enhancement processing on the real-time sensor data to obtain initialized sensor data; Performing noise classification on the initialized sensor data based on the sensor data noise characteristic range to obtain noise data in the real-time sensor data; The noise data is removed from the real-time sensor data to obtain preprocessed sensor features.

[0006] Furthermore, in this method, control analysis is performed according to the preprocessed sensor characteristics to obtain analysis results, specifically: Pre-synchronize the user's basic profile data to the IoT platform, introduce the Manhattan distance metric, and construct real-time user features based on the pre-processed sensor features; Calculate the Manhattan distance between the basic information data of the user and the real-time user features by using the Manhattan distance measurement method, and determine whether the Manhattan distance is greater than a preset Manhattan distance threshold; When the Manhattan distance is not greater than the preset Manhattan distance threshold, the corresponding real-time user feature is used as a user feature with control authority, and an analysis result with control authority is generated; When the Manhattan distance is greater than the preset Manhattan distance threshold, the corresponding real-time user feature is used as a user feature without control authority, and an analysis result of not having control authority is generated; When no user feature is identified within the preset time, an analysis result is generated that no user has entered the predetermined area.

[0007] Furthermore, in this method, a potential risk identification model is constructed by combining the operation frequency of home appliances, the characteristics of the operation time period, and the home appliance operation behavior data, specifically: Collect the operation frequency and operation time characteristics of household appliances, set the potential risk operation frequency and operation time, and build a potential risk identification model based on the generative adversarial network; The operation behavior data of the home appliances are obtained from the device usage log, and several potential risk operation frequencies and operation time periods are extracted from the operation frequency and operation time period characteristics of the home appliances to construct constraint conditions; Extracting abnormal operation behavior data from the home appliance operation behavior data, constructing a training sample data set based on the abnormal operation behavior data, and inputting the abnormal operation behavior data under the constraint conditions into the potential risk identification model for training; Through training, a potential risk identification model that meets expectations is obtained.

[0008] Furthermore, in this method, the potential risk identification model is used to perform risk analysis on the analysis results and the current real-time home appliance operation behavior data, specifically: When the analysis result is that no user has entered the predetermined area, the operation frequency within the preset time, the characteristics of the operation time period, and the current real-time home appliance operation behavior data are collected; The operation frequency within the preset time, the characteristics of the operation period, and the current real-time home appliance operation behavior data are input into the risk identification model, and the generator generates an initial risk analysis result based on the previous real-time home appliance operation behavior data; The operation frequency within the preset time and the characteristics of the operation period are used as constraint conditions, and a judge is used to judge whether to accept the initial risk analysis result based on the constraint conditions; When the discriminator accepts the initial risk analysis result, the initial risk analysis result is output as the final prediction result. When the discriminator does not accept the initial risk analysis result, the next risk analysis result is generated until the discriminator accepts the risk analysis result.

[0009] Furthermore, in this method, the household appliances are controlled according to the risk analysis results, specifically: Setting a risk assessment index and determining whether the risk analysis result is greater than the risk assessment index; When the risk analysis result is greater than the risk assessment index, the corresponding home appliance will be powered off and an early warning prompt will be issued.

[0010] A second aspect of the present invention provides a home appliance control system based on the Internet of Things, including a memory and a processor, wherein the memory includes a home appliance control method program based on the Internet of Things, and when the home appliance control method program based on the Internet of Things is executed by the processor, the steps of any one of the home appliance control methods based on the Internet of Things are implemented.

[0011] The present invention solves the defects existing in the background technology and has the following beneficial effects: The present invention obtains real-time sensor data, pre-processes the real-time sensor data, obtains the pre-processed sensor features, and then performs control analysis based on the pre-processed sensor features to obtain analysis results, thereby combining the operating frequency of home appliances, the characteristics of the time period in which the operation is performed, and the real-time home appliance operation behavior data to build a potential risk identification model, and finally performs risk analysis on the analysis results and the current real-time home appliance operation behavior data through the potential risk identification model, and controls the home appliances according to the risk analysis results. The present invention timely discovers abnormally started home appliances by combining the operating frequency of home appliances, the characteristics of the time period in which the operation is performed, and the real-time home appliance operation behavior data, thereby avoiding fires caused by abnormally started high-power appliances and improving the rationality of home appliance control. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0013] Figure 1 The overall flow chart of the home appliance control method based on the Internet of Things is shown; Figure 2 A system block diagram of a home appliance control system based on the Internet of Things is shown. DETAILED DESCRIPTION

[0014] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0015] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0016] like Figure 1 As shown, the first aspect of the present invention provides a home appliance control method based on the Internet of Things, comprising the following steps: S102: acquiring real-time sensor data, and obtaining preprocessed sensor features by preprocessing the real-time sensor data; Exemplarily, the sensor data includes infrared sensor data, infrared thermal imaging sensor data, temperature sensor data, humidity sensor data, etc. S104: Perform control analysis according to the preprocessed sensor characteristics and obtain analysis results; S106: Building a potential risk identification model based on the operation frequency of the home appliance, the characteristics of the operation time period, and the real-time home appliance operation behavior data; S108: Perform risk analysis on the analysis results and the current real-time home appliance operation behavior data through a potential risk identification model, and control the home appliances according to the risk analysis results.

[0017] It should be noted that the present invention combines the operating frequency of home appliances, the characteristics of the operating time period, and the real-time home appliance operating behavior data to timely detect abnormally started home appliances, thereby avoiding fires caused by abnormally started high-power appliances and improving the rationality of home appliance control.

[0018] Furthermore, in this method, the real-time sensor data is preprocessed to obtain the preprocessed sensor features, specifically: Set the sensor data noise characteristic range, and perform data filtering, denoising, and data enhancement processing on the real-time sensor data to obtain the initialized sensor data; Based on the noise characteristic range of the sensor data, the noise data after the initialization processing is classified to obtain the noise data in the real-time sensor data; Noise data is removed from real-time sensor data to obtain preprocessed sensor features.

[0019] It should be noted that the real-time sensor data is subjected to data filtering, denoising and data enhancement processing, wherein the processing means include Kalman filtering, mean filtering, stop filtering, singular value decomposition and other processing methods. Through this method, the sensor data can be processed to obtain sensor data with less noise, which is beneficial to subsequent recognition tasks.

[0020] Furthermore, in this method, control analysis is performed according to the preprocessed sensor characteristics to obtain analysis results, specifically: The user's basic profile data is synchronized to the IoT platform in advance, and the Manhattan distance metric is introduced to build real-time user features based on the pre-processed sensor features; It should be noted that the user's basic information data includes voiceprint data, facial image data, fingerprint data, user's name, user's health data and other data.

[0021] Calculate the Manhattan distance between the user's basic information data and the real-time user features by using the Manhattan distance measurement method, and determine whether the Manhattan distance is greater than a preset Manhattan distance threshold; When the Manhattan distance is not greater than the preset Manhattan distance threshold, the corresponding real-time user features are used as user features with control authority, and an analysis result with control authority is generated; It should be noted that the data collected by the sensor is authenticated through this method to obtain whether the user has control authority. Only when the user has authority can the user perform control.

[0022] When the Manhattan distance is greater than the preset Manhattan distance threshold, the corresponding real-time user feature is regarded as a user feature without control authority, and an analysis result of not having control authority is generated; When no user feature is identified within the preset time, an analysis result is generated that no user has entered the predetermined area.

[0023] Furthermore, in this method, a potential risk identification model is constructed by combining the operation frequency of home appliances, the characteristics of the operation time period, and the home appliance operation behavior data, specifically: Collect the operation frequency and operation time characteristics of household appliances, set the potential risk operation frequency and operation time, and build a potential risk identification model based on the generative adversarial network; The operation behavior data of home appliances are obtained from the device usage logs, and several potential risk operation frequencies and operation time periods are extracted from the operation frequency and operation time period characteristics of the home appliances to construct constraint conditions; Extract abnormal operation behavior data from the home appliance operation behavior data, build a training sample data set based on the abnormal operation behavior data, and input the abnormal operation behavior data under the constraint conditions into the potential risk identification model for training; Through training, a potential risk identification model that meets expectations is obtained.

[0024] It should be noted that the operating frequency and operating time characteristics of different home appliances may be different. For example, the operating frequency of home appliances is almost 0 and the operating time is late at night or when users do not often use them. By generating adversarial networks and combining abnormal operating behavior data under constraints (abnormal self-start, abnormal use, etc.), a potential risk identification model is constructed to identify potential risks.

[0025] Furthermore, in this method, a potential risk identification model is used to perform risk analysis on the analysis results and the current real-time home appliance operation behavior data, specifically: When the analysis result is that no user has entered the predetermined area, the operation frequency within the preset time, the characteristics of the operation time period, and the current real-time home appliance operation behavior data are collected; The operation frequency within a preset time, the characteristics of the operation period, and the current real-time home appliance operation behavior data are input into the risk identification model, and the generator generates an initial risk analysis result based on the previous real-time home appliance operation behavior data; The operation frequency within the preset time and the characteristics of the operation period are used as constraints, and the judgement device is used to determine whether to accept the initial risk analysis results based on the constraints; When the discriminator accepts the initial risk analysis result, the initial risk analysis result is output as the final prediction result. When the discriminator does not accept the initial risk analysis result, the next risk analysis result is generated until the discriminator accepts the risk analysis result.

[0026] It should be noted that, through this method, risk analysis results can be identified, wherein the risk analysis results include low risk, medium risk, high risk, etc., wherein descriptions such as low risk, medium risk, high risk, etc. can be used as outputs of the model.

[0027] Furthermore, in this method, the household appliances are controlled according to the risk analysis results, specifically: Set risk assessment indicators and determine whether the risk analysis results are greater than the risk assessment indicators; When the risk analysis result is greater than the risk assessment index, the corresponding home appliances will be powered off and an early warning will be issued.

[0028] In addition, the method further comprises: Collect environmental characteristic data in the target area through sensors, extract the user's disease data information through the user's basic information data information, and retrieve the allergen characteristic data related to the current disease data information through big data based on the user's disease data information; By extracting features from the environmental feature data in the target area, material composition data information in the environmental feature data in the current target area is obtained, and a Mahalanobis distance measurement method is introduced; Calculate the Mahalanobis distance value between the allergen feature data related to the current disease data information and the material component data information in the environmental feature data in the current target area by using the Mahalanobis distance measurement method; When there is material composition data information whose Mahalanobis distance value is lower than the preset Mahalanobis distance threshold, the household appliances in the target area are controlled to be ventilated and disinfected until there is no material composition data information whose Mahalanobis distance value is lower than the preset Mahalanobis distance threshold.

[0029] It should be noted that since the user may have certain allergic diseases, by timely monitoring the environmental characteristic data within the target area, when there is material composition data information with a Mahalanobis distance value lower than the preset Mahalanobis distance threshold, the home appliances in the target area are controlled to be ventilated and disinfected until there is no material composition data information with a Mahalanobis distance value lower than the preset Mahalanobis distance threshold, which can further improve the rationality of home appliance control.

[0030] In addition, the method further comprises: Acquire a household floor plan in a target area, and initialize the number of home appliance controller devices, the type of home appliance controllers, and the installation location information of the home appliance controllers according to the household floor plan in the target area; Performing a control delay test based on the number of home appliance controller devices and the installation location information of the home appliance controller, obtaining control delay data of home appliances in each area of ​​the house, and determining whether the control delay data of home appliances in each area of ​​the house is higher than a control delay threshold; If so, reconfigure the number of home appliance controller devices and the installation location information of the home appliance controller until the control delay data of the home appliance devices in each area of ​​the house does not exceed the control delay threshold; A transmission attempt is made through the home appliance controller device, and a type of home appliance controller is randomly selected for control attempt. When the control delay of the current type of home appliance controller is higher than the control delay threshold, another type of home appliance controller is reselected for control attempt until the control delay of the current type of home appliance controller is no higher than the control delay threshold.

[0031] It should be noted that the types of home appliance controllers include Bluetooth data, wireless sensor information transmission equipment, wifi equipment, etc. Since the size of the house will affect the control of home appliances, the number of home appliance controller devices and the installation location information of the home appliance controller will cause the control delay data of the home appliances in various areas of the house to be higher than the control delay threshold. At this time, the control will be delayed and the expected control requirements cannot be met. This method can optimize the number of home appliance controller devices and the installation location information of the home appliance controller, as well as optimize the types of home appliance control devices for control, thereby reducing the control delay of home appliances, achieving rapid response, and improving user experience.

[0032] like Figure 2 As shown, the second aspect of the present invention provides a home appliance control system 4 based on the Internet of Things, including a memory 41 and a processor 42. The memory 41 includes a home appliance control method program based on the Internet of Things. When the home appliance control method program based on the Internet of Things is executed by the processor 42, it includes: Acquire real-time sensor data, and obtain preprocessed sensor features by preprocessing the real-time sensor data; Exemplarily, the sensor data includes infrared sensor data, infrared thermal imaging sensor data, temperature sensor data, humidity sensor data, etc. Perform control analysis based on the preprocessed sensor characteristics and obtain analysis results; Build a potential risk identification model by combining the operation frequency of home appliances, the characteristics of the operation time period, and real-time home appliance operation behavior data; The potential risk identification model is used to conduct risk analysis on the analysis results and the current real-time home appliance operation behavior data, and the home appliances are controlled based on the risk analysis results.

[0033] It should be noted that the present invention combines the operating frequency of home appliances, the characteristics of the operating time period, and the real-time home appliance operating behavior data to timely detect abnormally started home appliances, thereby avoiding fires caused by abnormally started high-power appliances and improving the rationality of home appliance control.

[0034] Furthermore, in this system, by preprocessing the real-time sensor data, the preprocessed sensor features are obtained, specifically: Set the sensor data noise characteristic range, and perform data filtering, denoising, and data enhancement processing on the real-time sensor data to obtain the initialized sensor data; Based on the noise characteristic range of the sensor data, the noise data after the initialization processing is classified to obtain the noise data in the real-time sensor data; Noise data is removed from real-time sensor data to obtain preprocessed sensor features.

[0035] It should be noted that the real-time sensor data is subjected to data filtering, denoising and data enhancement processing, wherein the processing means include Kalman filtering, mean filtering, stop filtering, singular value decomposition and other processing methods. Through this method, the sensor data can be processed to obtain sensor data with less noise, which is beneficial to subsequent recognition tasks.

[0036] Furthermore, in this system, control analysis is performed based on the preprocessed sensor characteristics to obtain analysis results, specifically: The user's basic profile data is synchronized to the IoT platform in advance, and the Manhattan distance metric is introduced to build real-time user features based on the pre-processed sensor features; It should be noted that the user's basic information data includes voiceprint data, facial image data, fingerprint data, user's name, user's health data and other data.

[0037] Calculate the Manhattan distance between the user's basic information data and the real-time user features by using the Manhattan distance measurement method, and determine whether the Manhattan distance is greater than a preset Manhattan distance threshold; When the Manhattan distance is not greater than the preset Manhattan distance threshold, the corresponding real-time user features are used as user features with control authority, and an analysis result with control authority is generated; It should be noted that this method performs authentication processing on the data collected by the sensor to obtain whether the user has control authority.

[0038] When the Manhattan distance is greater than the preset Manhattan distance threshold, the corresponding real-time user feature is regarded as a user feature without control authority, and an analysis result of not having control authority is generated; When no user feature is identified within the preset time, an analysis result is generated that no user has entered the predetermined area.

[0039] Furthermore, in this system, a potential risk identification model is constructed by combining the operation frequency of home appliances, the characteristics of the operation time period, and the operation behavior data of home appliances, specifically: Collect the operation frequency and operation time characteristics of household appliances, set the potential risk operation frequency and operation time, and build a potential risk identification model based on the generative adversarial network; The operation behavior data of home appliances are obtained from the device usage logs, and several potential risk operation frequencies and operation time periods are extracted from the operation frequency and operation time period characteristics of the home appliances to construct constraint conditions; Extract abnormal operation behavior data from the home appliance operation behavior data, build a training sample data set based on the abnormal operation behavior data, and input the abnormal operation behavior data under the constraint conditions into the potential risk identification model for training; Through training, a potential risk identification model that meets expectations is obtained.

[0040] It should be noted that the operating frequency and operating time characteristics of different home appliances may be different. For example, the operating frequency of home appliances is almost 0 and the operating time is late at night or when users do not often use them. By generating adversarial networks and combining abnormal operating behavior data under constraints (abnormal self-start, abnormal use, etc.), a potential risk identification model is constructed to identify potential risks.

[0041] Furthermore, in this system, a potential risk identification model is used to perform risk analysis on the analysis results and the current real-time home appliance operation behavior data, specifically: When the analysis result is that no user has entered the predetermined area, the operation frequency within the preset time, the characteristics of the operation time period, and the current real-time home appliance operation behavior data are collected; The operation frequency within a preset time, the characteristics of the operation period, and the current real-time home appliance operation behavior data are input into the risk identification model, and the generator generates an initial risk analysis result based on the previous real-time home appliance operation behavior data; The operation frequency within the preset time and the characteristics of the operation period are used as constraints, and the judgement device is used to determine whether to accept the initial risk analysis results based on the constraints; When the discriminator accepts the initial risk analysis result, the initial risk analysis result is output as the final prediction result. When the discriminator does not accept the initial risk analysis result, the next risk analysis result is generated until the discriminator accepts the risk analysis result.

[0042] It should be noted that, through this method, risk analysis results can be identified, wherein the risk analysis results include low risk, medium risk, high risk, etc., wherein descriptions such as low risk, medium risk, high risk, etc. can be used as outputs of the model.

[0043] Furthermore, in this system, the home appliances are controlled according to the risk analysis results, specifically: Set risk assessment indicators and determine whether the risk analysis results are greater than the risk assessment indicators; When the risk analysis result is greater than the risk assessment index, the corresponding home appliances will be powered off and an early warning will be issued.

[0044] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0045] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0046] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0047] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0048] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0049] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A home appliance control method based on the Internet of Things, characterized in that: The following steps are involved: Acquire real-time sensor data, and acquire preprocessed sensor features by preprocessing the real-time sensor data; Perform control analysis according to the preprocessed sensor characteristics to obtain analysis results; Build a potential risk identification model by combining the operation frequency of home appliances, the characteristics of the operation time period, and real-time home appliance operation behavior data; The potential risk identification model is used to perform risk analysis on the analysis results and the current real-time home appliance operation behavior data, and the home appliances are controlled according to the risk analysis results.

2. The method for controlling home appliances based on the Internet of Things according to claim 1, characterized in that: The real-time sensor data is preprocessed to obtain the preprocessed sensor features, specifically: Setting a sensor data noise characteristic range, and performing data filtering, denoising, and data enhancement processing on the real-time sensor data to obtain initialized sensor data; Performing noise classification on the initialized sensor data based on the sensor data noise characteristic range to obtain noise data in the real-time sensor data; The noise data is removed from the real-time sensor data to obtain preprocessed sensor features.

3. The method for controlling household appliances based on the Internet of Things according to claim 1, characterized in that: Perform control analysis according to the preprocessed sensor characteristics to obtain analysis results, specifically: Pre-synchronize the user's basic profile data to the IoT platform, introduce the Manhattan distance metric, and construct real-time user features based on the pre-processed sensor features; Calculate the Manhattan distance between the basic information data of the user and the real-time user features by using the Manhattan distance measurement method, and determine whether the Manhattan distance is greater than a preset Manhattan distance threshold; When the Manhattan distance is not greater than the preset Manhattan distance threshold, the corresponding real-time user feature is used as a user feature with control authority, and an analysis result with control authority is generated; When the Manhattan distance is greater than the preset Manhattan distance threshold, the corresponding real-time user feature is used as a user feature without control authority, and an analysis result of not having control authority is generated; When no user feature is identified within the preset time, an analysis result is generated that no user has entered the predetermined area.

4. The method for controlling home appliances based on the Internet of Things according to claim 1, characterized in that: A potential risk identification model is constructed by combining the operation frequency of home appliances, the characteristics of the operation time period, and the operation behavior data of home appliances. Specifically: Collect the operation frequency and operation time characteristics of household appliances, set the potential risk operation frequency and operation time, and build a potential risk identification model based on the generative adversarial network; The operation behavior data of the home appliances are obtained from the device usage log, and several potential risk operation frequencies and operation time periods are extracted from the operation frequency and operation time period characteristics of the home appliances to construct constraint conditions; Extracting abnormal operation behavior data from the home appliance operation behavior data, constructing a training sample data set based on the abnormal operation behavior data, and inputting the abnormal operation behavior data under the constraint conditions into the potential risk identification model for training; Through training, a potential risk identification model that meets expectations is obtained.

5. The method for controlling home appliances based on the Internet of Things according to claim 1, characterized in that: The potential risk identification model is used to perform risk analysis on the analysis results and the current real-time home appliance operation behavior data, specifically: When the analysis result is that no user has entered the predetermined area, the operation frequency within the preset time, the characteristics of the operation time period, and the current real-time home appliance operation behavior data are collected; The operation frequency within the preset time, the characteristics of the operation period, and the current real-time home appliance operation behavior data are input into the risk identification model, and the generator generates an initial risk analysis result based on the previous real-time home appliance operation behavior data; The operation frequency and the characteristics of the operation period within the preset time are used as constraint conditions, and a judge is used to judge whether to accept the initial risk analysis result based on the constraint conditions; When the discriminator accepts the initial risk analysis result, the initial risk analysis result is output as the final prediction result. When the discriminator does not accept the initial risk analysis result, the next risk analysis result is generated until the discriminator accepts the risk analysis result.

6. The method for controlling household appliances based on the Internet of Things according to claim 1, characterized in that: Control household appliances based on the risk analysis results, specifically: Setting a risk assessment index and determining whether the risk analysis result is greater than the risk assessment index; When the risk analysis result is greater than the risk assessment index, the corresponding home appliances will be powered off and an early warning prompt will be issued.

7. The home appliance control system based on the Internet of Things is characterized by: It comprises a memory and a processor, wherein the memory comprises a home appliance control method program based on the Internet of Things, and when the home appliance control method program based on the Internet of Things is executed by the processor, the steps of the home appliance control method based on the Internet of Things as described in any one of claims 1-6 are implemented.

Images