Control method, device, apparatus, air conditioner, medium and product of internet of things device

Abstract

The application provides a control method and device of an Internet of Things equipment, an equipment, an air conditioner, a medium and a product, the method comprising: emitting a wireless transmission signal to a preset equipment environment where the Internet of Things equipment is located, and receiving a wireless reflection signal returned from the equipment environment; determining user characteristic information corresponding to the equipment environment according to the wireless reflection signal; and adjusting an operation parameter of the Internet of Things equipment according to the user characteristic information. An embodiment of the application monitors the user characteristic information in the equipment environment by receiving the wireless reflection signal in real time, changes the operation parameter of the Internet of Things equipment according to the user characteristic information, matches the operation parameter with the user characteristic information, effectively utilizes the inherent wireless signal resource of the Internet of Things equipment, does not need to increase the hardware cost, avoids the problems that the computer vision technology is easy to involve the user privacy and the requirement for light intensity, and avoids the problem that the special sensor technology is high in cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of Internet of Things, and in particular to a control method and device of an Internet of Things equipment, a control equipment, an air conditioner, a medium and a product. Specifically, the present application relates to a control method and device of an Internet of Things equipment, a control equipment, an air conditioner, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the increasing demand for intelligent control and human-computer interaction, human behavior perception technology has become a popular research direction in the field of Internet of Things. If human behavior perception technology can be applied in the field of Internet of Things, it can greatly simplify the control method of the user to the equipment. For example, the user can start the Internet of Things equipment around him by waving his hand.

[0003] However, the human behavior perception technology in the related art cannot be applied to the field of Internet of Things. Because the existing human behavior perception technology is realized based on computer vision technology or special sensor technology. The computer vision technology is limited by user privacy and light conditions, and cannot be applied in the Internet of Things equipment. Moreover, the camera has a detection dead angle. Even if the computer vision technology is applied in the Internet of Things equipment, it can only realize human perception in a specific area within the visual range of the camera, which affects the user's use. Although the special sensor technology can realize fine-grained behavior perception, the cost of deploying special sensors is extremely high, and it is not convenient to install special sensors. Therefore, the special sensor technology is difficult to be widely applied. SUMMARY

[0004] The main purpose of the present application is to overcome the defects of the above-mentioned related art, and to provide a control method and device of an Internet of Things equipment, an equipment, an air conditioner, a medium and a product, to solve the problem that the human behavior perception technology in the related art cannot be applied to the field of Internet of Things.

[0005] In one aspect, the present application provides a control method of an Internet of Things equipment, comprising: emitting a wireless signal to a device environment where a preset Internet of Things equipment is located, and receiving a wireless reflection signal returned from the device environment; determining user feature information corresponding to the device environment according to the wireless reflection signal; and adjusting the operating parameters of the Internet of Things equipment according to the user feature information.

[0006] Optionally, the feature parameter in the user feature information comprises a user quantity; and the determining the user feature information corresponding to the device environment according to the wireless reflection signal comprises: for each wireless reflection signal, extracting signal receiving strength and channel state information in the wireless reflection signal; extracting a signal domain feature sequence from the signal receiving strength and the channel state information, respectively; and determining the user quantity in the device environment according to the signal domain feature sequence corresponding to each wireless reflection signal by using a pre-trained user quantity perception model.

[0007] Optionally, the feature parameter in the user feature information comprises a user position; and the determining the user feature information corresponding to the device environment according to the wireless reflection signal comprises: for each wireless reflection signal, extracting signal receiving strength and channel state information in the wireless reflection signal; for each wireless reflection signal, identifying a reference position corresponding to the signal receiving strength and the channel state information of the wireless reflection signal in a user signal fingerprint library corresponding to the Internet of Things device, and determining the reference position as the user position in the device environment; wherein the user signal fingerprint library corresponding to the Internet of Things device is used to pre-record wireless signal features corresponding to a plurality of reference positions in the device environment, wherein the wireless signal features at least comprise reference signal receiving strength and reference channel state information.

[0008] Optionally, the identifying the reference position corresponding to the signal receiving strength and the channel state information of the wireless reflection signal in the user signal fingerprint library corresponding to the Internet of Things device, and determining the reference position as the user position in the device environment comprises: splicing the signal receiving strength and the channel state information of the wireless reflection signal into a spliced signal information; wherein the reference signal receiving strength and the reference channel state information corresponding to a same reference position in the user signal fingerprint library are a spliced reference signal information; determining a preset number of reference signal information closest to the spliced signal information corresponding to the wireless reflection signal in the user signal fingerprint library; in a case where one reference signal information is determined, determining the reference position corresponding to the determined reference signal information as the user position; in a case where a plurality of reference signal information are determined, determining the reference position corresponding to the reference signal information closest to the spliced signal information as the user position; or, in a case where a plurality of reference positions corresponding to the plurality of reference signal information are determined, determining the reference position located at a center position as the user position.

[0009] Optionally, the feature parameter in the user feature information comprises: a user state; and the determining of the user feature information corresponding to the device environment according to the wireless reflection signal comprises: extracting channel state information in each wireless reflection signal and extracting dynamic state information in the channel state information; and determining the user state in the device environment according to the dynamic state information corresponding to each wireless reflection signal by using a pre-trained motion state perception model.

[0010] Optionally, the adjusting of the operation parameter of the Internet of Things device according to the user feature information comprises: identifying the changed feature parameter in the determined user feature information according to the previously determined user feature information; adjusting the working power parameter of the Internet of Things device according to the user quantity in the case that the changed feature parameter is the user quantity; adjusting the working direction parameter of the Internet of Things device according to the user position in the case that the changed feature parameter is the user position; and adjusting the working power parameter and / or the working mode parameter of the Internet of Things device according to the user state in the case that the changed feature parameter is the user state.

[0011] Another aspect of the present application provides a control device of an Internet of Things device, comprising: a transceiving unit configured to send a wireless transmission signal to a device environment in which a preset Internet of Things device is located, and receive a wireless reflection signal returned from the device environment; a determining unit configured to determine user feature information corresponding to the device environment according to the wireless reflection signal; and a control unit configured to adjust an operation parameter of the Internet of Things device according to the user feature information.

[0012] Optionally, the feature parameter in the user feature information comprises: a user quantity; the determining of the user feature information corresponding to the device environment according to the wireless reflection signal comprises: extracting signal receiving strength and channel state information in each wireless reflection signal; and extracting a signal domain feature sequence in the signal receiving strength and the channel state information, respectively; and determining the user quantity in the device environment according to the signal domain feature sequence corresponding to each wireless reflection signal by using a pre-trained user quantity perception model.

[0013] Optionally, the feature parameter in the user feature information comprises a user position; the determining unit, which determines the user feature information corresponding to the device environment according to the wireless reflection signal, comprises: extracting signal receiving strength and channel state information in each wireless reflection signal; identifying a reference position corresponding to the signal receiving strength and channel state information of the wireless reflection signal in a user signal fingerprint library corresponding to the Internet of Things device, and determining the reference position as the user position in the device environment; wherein the user signal fingerprint library corresponding to the Internet of Things device is used to pre-record wireless signal features corresponding to multiple reference positions in the device environment; the wireless signal features at least comprise reference signal receiving strength and reference channel state information.

[0014] Optionally, the determining unit, which identifies the reference position corresponding to the signal receiving strength and channel state information of the wireless reflection signal in the user signal fingerprint library corresponding to the Internet of Things device and determines the reference position as the user position in the device environment, comprises: splicing the signal receiving strength and channel state information of the wireless reflection signal into a spliced signal information; wherein the reference signal receiving strength and reference channel state information corresponding to the same reference position in the user signal fingerprint library is a spliced reference signal information; determining a preset number of reference signal information closest to the spliced signal information corresponding to the wireless reflection signal in the user signal fingerprint library; in the case of determining one reference signal information, determining the reference position corresponding to the determined reference signal information as the user position; in the case of determining multiple reference signal information, determining the reference position corresponding to the reference signal information closest to the spliced signal information as the user position; or, in the case of determining multiple reference positions corresponding to the multiple reference signal information respectively, determining the reference position located at the center position as the user position.

[0015] Optionally, the feature parameter in the user feature information comprises a user state; the determining unit, which determines the user feature information corresponding to the device environment according to the wireless reflection signal, comprises: extracting channel state information and extracting dynamic state information in the channel state information in each wireless reflection signal; determining the user state in the device environment according to the dynamic state information corresponding to multiple wireless reflection signals respectively by using a pre-trained motion state perception model.

[0016] Optionally, the control unit adjusts the operating parameters of the Internet of Things device according to the user feature information, including: identifying the changed feature parameters in the determined user feature information this time according to the previously determined user feature information; in the case that the changed feature parameters are the number of users, adjusting the working power parameters of the Internet of Things device according to the number of users; in the case that the changed feature parameters are the user location, adjusting the working direction parameters of the Internet of Things device according to the user location; in the case that the changed feature parameters are the user state, adjusting the working power parameters and / or the working mode parameters of the Internet of Things device according to the user state.

[0017] In still another aspect of the present application, a control device of an Internet of Things device comprises: at least one communication interface; at least one bus connected with the at least one communication interface; at least one processor connected with the at least one bus; and at least one memory connected with the at least one bus, wherein the processor is configured to execute a control program of the Internet of Things device stored in the memory to implement the control method of the Internet of Things device as described in any one of the above aspects.

[0018] In still another aspect of the present application, an air conditioner is provided, which comprises the control device of the Internet of Things device as described above. The air conditioner is an air conditioner with a humidifying function.

[0019] In still another aspect of the present application, a computer readable storage medium is provided, which stores computer executable instructions, and the computer executable instructions are executed to implement the control method of the Internet of Things device as described in any one of the above aspects.

[0020] In still another aspect of the present application, a computer program product is provided, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the method as described in any one of the above aspects.

[0021] According to the technical solution of the present application, wireless transmission signals can be sent to the device environment where the preset Internet of Things device is located, and wireless reflection signals returned from the device environment are received; user feature information corresponding to the device environment is determined according to the wireless reflection signals; and the operating parameters of the Internet of Things device are adjusted according to the user feature information.

[0022] According to the technical solution of the present application, the user feature information in the device environment is monitored by receiving the wireless reflection signals in real time, and the operating parameters of the Internet of Things device are changed according to the user feature information, so that the operating parameters are matched with the user feature information, the inherent wireless signal resources of the Internet of Things device are effectively utilized, the hardware cost is not increased, the computer vision technology is avoided to involve the user privacy and the requirement for light intensity, and the problem of high cost of special sensor technology is also avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 Flowchart of a method for controlling an Internet of Things device according to an embodiment of the present invention;

[0025] Figure 2 A control schematic diagram of an Internet of Things device according to an embodiment of the present invention;

[0026] Figure 3 This is a structural block diagram of a control device for an Internet of Things device according to an embodiment of the present invention;

[0027] Figure 4 FIG. 4 is a structural block diagram of a control device for an Internet of Things device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and corresponding drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] An embodiment of the present invention provides a method for controlling an Internet of Things device. Figure 1 FIG. 1 is a flow chart of a method for controlling an Internet of Things device according to an embodiment of the present invention.

[0031] Step S110, a wireless transmission signal is sent to a device environment where the preset Internet of Things device is located, and a wireless reflection signal returned from the device environment is received.

[0032] The types of Internet of Things devices include, but are not limited to, air conditioners, humidifiers, humidifying air conditioners, cool fans, and warm air heaters.

[0033] The device environment refers to the place where the Internet of Things device is set. For example, the device environment is the indoor environment where the Internet of Things device is located.

[0034] The wireless transmission signal refers to the wireless signal sent by the communication module built in the Internet of Things device. The types of communication modules include, but are not limited to, Wi-Fi modules. Correspondingly, the types of wireless transmission signals include, but are not limited to, Wi-Fi signals.

[0035] The wireless reflection signal refers to the wireless signal reflected by people or objects in the device environment. The types of wireless reflection signals are the same as those of the discovery transmission signals.

[0036] Step S120, according to the wireless reflection signal, the user feature information corresponding to the device environment is determined.

[0037] The user feature information is used to reflect the user behavior pattern and space use state in the device environment. For example, the user feature information includes the number of users, user location, and / or user state.

[0038] Specifically, the signal reception strength (Received Signal Strength Indication, RSSI for short) and channel state information (Channel State Information, CSI for short) can be extracted from the wireless reflection signal; the signal reception strength and the channel state information are preprocessed respectively; and the user feature information corresponding to the device environment is determined according to the preprocessed signal reception strength and channel state information.

[0039] The signal reception strength and the channel state information are wireless signal features of the wireless reflection signal. The signal reception strength and the channel state information can be regarded as two independent signals. The signal reception strength is a signal strength indicator, which is suitable for fast estimation of signal quality. The channel state information is used to provide detailed channel information, which is suitable for more detailed analysis. In the actual environment, the signal may be affected by various factors, such as obstacles, interference sources, etc. By combining the two kinds of data of signal reception strength and channel state information, the limitations of a single data source can be compensated for, thereby improving the robustness and accuracy of the system.

[0040] Step S130, according to the user feature information, the running parameters of the Internet of Things device are adjusted.

[0041] According to the user feature information, the current running parameter of the Internet of Things device is adjusted to a running parameter matched with the user feature information.

[0042] In an embodiment of the present application, a wireless transmission signal is sent to a preset device environment where the Internet of Things device is located, and a wireless reflection signal returned from the device environment is received; according to the wireless reflection signal, user feature information corresponding to the device environment is determined; and according to the user feature information, the running parameter of the Internet of Things device is adjusted. In an embodiment of the present application, the user feature information in the device environment is monitored by receiving the wireless reflection signal in real time, and the running parameter of the Internet of Things device is changed according to the user feature information, so that the running parameter is matched with the user feature information. The inherent wireless signal resource of the Internet of Things device is effectively utilized, without increasing the hardware cost, avoiding the problems that the computer vision technology is easy to involve the user privacy and the requirement for light intensity, and the special sensor technology is high in cost.

[0043] The control method of the Internet of Things device will be further described below in combination with the control schematic diagram of the Internet of Things device shown in Figure 2

[0044] In an embodiment of the present application, the Internet of Things device which needs to be controlled by using human behavior sensing can be deployed in a preset device environment; the Internet of Things device is internally provided with a wireless signal transceiver. For example, a humidifying air conditioner with a Wi-Fi module is deployed in an indoor environment. The control method of the Internet of Things device of an embodiment of the present application can be implemented on the Internet of Things device or the control method of the Internet of Things device of an embodiment of the present application can be implemented on a preset control device. The control device is connected to the Internet of Things device, and transmits a wireless transmission signal, receives a wireless reflection signal and reports information of the wireless reflection signal to the control device under the control of the control device. The control device is, for example, a home host device.

[0045] The wireless signal transceiver in the Internet of Things device transmits a wireless transmission signal to the device environment and receives a wireless reflection signal reflected from the device environment. After the wireless transmission signal is transmitted, it may touch static objects such as home, wall, etc. due to scattering, refraction and reflection, and may touch human body due to scattering, refraction and reflection. Therefore, multiple wireless reflection signals are reflected from the device environment in succession, which may be reflected from static objects in the device environment or from human body. Therefore, each received wireless reflection signal needs to be analyzed to determine the user feature information in the device environment.

[0046] ​The wireless signal features of each wireless reflection signal include signal reception strength and channel state information. The signal reception strength and channel state information can be extracted from each wireless reflection signal.

[0047] In order to more accurately analyze the user feature information, the signal reception strength and channel state information can be pre-processed respectively. The signal reception strength and channel state information can be regarded as two signals, and the pre-processing is used to remove outliers and noise in the signals.

[0048] The pre-processing includes but is not limited to outlier removal processing, interpolation processing, filtering processing and average processing.

[0049] The outlier removal processing includes using a preset Hampel detection algorithm to identify outliers in each wireless signal feature. The outliers refer to wireless signal features deviating from other wireless signal features. The outliers can be caused by environmental interference or other factors in the data collection process. Removing these outliers helps to improve the accuracy of subsequent analysis. For example, if the RSSI of a signal is much larger than that of other signals, it can be removed.

[0050] The interpolation processing includes that, during the process of receiving wireless reflection signals, the wireless reflection signals can be non-uniformly distributed in time due to delays or other factors. In order to solve this problem, linear interpolation can be performed on the wireless signal features to make the wireless signal features uniform in time interval, which helps to ensure the consistency and accuracy of subsequent analysis.

[0051] The filtering processing includes that a preset noise reduction filter can be used to perform noise reduction processing on the wireless signal features. Of course, in the device environment, not only static objects and human bodies, but also wireless reflection signals reflected by static objects and human bodies have different frequency ranges, such as the frequency range of walking is 20-80 Hz, and the frequency range of breathing is 0.1-0.5 Hz. The frequency range corresponding to the human body can be obtained through existing research or testing. After obtaining the frequency range corresponding to the human body, a filter can be used to filter the wireless signal features within the frequency range corresponding to the human body.

[0052] The average processing includes that if there is a lot of noise in the wireless signal features of the wireless reflection signals, the influence of the noise can be reduced by performing average processing on the wireless signal features of the wireless reflection signals.

[0053] After the pre-processing, each wireless signal feature can be analyzed to form user feature information. Among them, the feature parameters in the user feature information include the number of users, the location of the user and / or the state of the user.

[0054] The number of users refers to the number of users within the working range of the Internet of Things device.

[0055] The user position refers to a user position within a working range of the Internet of Things device.

[0056] The user state refers to a user state within a working range of the Internet of Things device. For example, the user is walking fast or walking slowly; the user is sleeping or walking.

[0057] The working range of the Internet of Things device refers to a coverage range of a communication module of the Internet of Things device. The coverage range can be set according to requirements.

[0058] In an embodiment of the present application, the signal receiving strength and channel state information can be extracted in the wireless signal features, the features for determining the number of users, the features for determining the user position and the features for determining the user state are extracted in the preprocessed signal receiving strength and channel state information, the features for determining the number of users, the features for determining the user position and the features for determining the user state are input into a pre-trained deep learning model (deep learning algorithm); wherein the deep learning model determines the number of users, the user position and the user state in the device environment according to the features for determining the number of users, the features for determining the user position and the features for determining the user state; and the number of users, the user position and the user state output by the deep learning model are obtained.

[0059] In another embodiment of the present application, the signal receiving strength and channel state information can be extracted in the wireless signal features, the features for determining the number of users, the features for determining the user position and the features for determining the user state are extracted in the preprocessed signal receiving strength and channel state information, and the number of users, the user position and the user state are determined using different determination methods. Of course, the pre-trained model can also be used to complete the steps of determining the number of users, the user position and the user state using different determination methods. That is, different determination methods are performed by different layers in the model.

[0060] The process of determining the number of users, the user position and the user state using different determination methods will be described below.

[0061] In determining the number of users in the device environment according to the wireless reflection signals, for each wireless reflection signal, signal reception strength and channel state information can be extracted from the wireless reflection signal; and from the signal reception strength and the channel state information, signal domain feature sequences are respectively extracted to obtain signal domain feature sequences corresponding to the wireless reflection signal (i.e., signal domain features corresponding to the combined signal reception strength and channel state information); and a pre-trained user number perception model is used to determine the number of users in the device environment according to the signal domain feature sequences corresponding to the plurality of wireless reflection signals. Alternatively, for each wireless reflection signal, signal reception strength and channel state information can be extracted from the wireless reflection signal; and from the signal reception strength and the channel state information, signal domain feature sequences are respectively extracted to obtain signal domain feature sequences corresponding to the wireless reflection signal; and a signal domain fusion feature sequence is obtained by fusing the signal domain feature sequences corresponding to the plurality of wireless reflection signals; and a pre-trained user number perception model is used to determine the number of users in the device environment according to the signal domain fusion feature sequence.

[0062] The wireless reflection signal refers to a signal captured from the device environment, which contains the influence of user activities in the device environment on the wireless signal.

[0063] The signal domain feature sequence is used to reflect the changes of the signal in different dimensions, thereby helping to identify the influence of different numbers of users on the signal.

[0064] The signal domain feature sequence includes a plurality of types of signal domain features arranged in a predetermined order.

[0065] The types of signal domain features include but are not limited to time domain features, subcarrier domain features, frequency domain features, and time-frequency domain features. The time domain features are, for example, mean, variance, and standard deviation. The subcarrier domain features are, for example, amplitude and phase of the subcarrier. The frequency domain features are, for example, spectral density and spectral peak. The time-frequency domain features are, for example, short-time Fourier transform (STFT) features and Discrete Wavelet Transform (DWT) features.

[0066] Further, for each wireless reflection signal, signal reception strength and channel state information are extracted from the wireless reflection signal; and the signal reception strength and the channel state information are respectively preprocessed, and from the preprocessed signal reception strength and channel state information, signal domain feature sequences are respectively extracted.

[0067] Further, the signal domain fusion feature sequence can be an average value of the same signal domain features of the multiple wireless reflection signals. That is, the signal domain fusion feature sequence also includes multiple types of signal domain features arranged in a predetermined order, and each signal domain feature is the average value of the corresponding signal domain features of the multiple wireless reflection signals. A single signal domain feature sequence can be affected by noise, interference, and other factors. After fusing multiple signal domain feature sequences, the multiple signal domain feature sequences can complement each other, improving the accuracy and reliability of feature extraction.

[0068] Further, the user quantity perception model is a pre-trained lightweight model. The lightweight model is trained to have the ability to determine the number of users in the device environment according to the signal domain fusion feature sequence. The types of the lightweight model include but are not limited to Mobile Net model. Using a lightweight model can reduce the amount of computation and the number of parameters, so that the control method of the Internet of Things device of the present application can be deployed on a hardware platform with limited computing resources.

[0069] Further, when training the user quantity perception model, wireless reflection signals under different user quantities can be pre-collected, pre-processed, and used for signal domain feature sequence extraction and user quantity determination. The real user quantity is used as the true value, and the signal domain feature sequence is used as the input data of the user quantity perception model for training the model and verifying the performance of the user quantity perception model. Gradient descent method can be used to train the user quantity perception model until the user quantity perception model converges.

[0070] When determining the user position corresponding to the device environment according to the wireless reflection signal, the signal reception strength and channel state information can be extracted from each received wireless reflection signal. For each wireless reflection signal, the signal reception strength and channel state information of the wireless reflection signal are identified in the user signal fingerprint library corresponding to the Internet of Things device to determine the reference position corresponding to the signal reception strength and channel state information of the wireless reflection signal as the user position in the device environment. The user signal fingerprint library corresponding to the Internet of Things device pre-records the reference positions corresponding to multiple reference users in the device environment and the reference signal reception strength and reference channel state information extracted from the wireless reflection signal returned by each reference user.

[0071] The user information fingerprint library is a pre-constructed database that can record wireless signal characteristics corresponding to each reference position. The wireless signal characteristics at least include signal reception strength and channel state information. The user signal fingerprint library corresponding to the Internet of Things device pre-records reference positions corresponding to a plurality of reference users in the device environment and reference signal reception strength and reference channel state information extracted from wireless reflection signals returned by each reference user. Further, for each Internet of Things device, a coordinate system corresponding to the device environment can be set, and each coordinate position in the coordinate system is a reference position. The reference user can walk or rest in the device environment, and then the reference signal reception strength and the reference channel state information corresponding to different coordinate positions can be collected after the device environment emits wireless transmission signals. The reference signal reception strength and the reference channel state information corresponding to different coordinate positions can be pre-processed respectively, and the pre-processed reference signal reception strength and the reference channel state information are stored in the corresponding coordinate positions to form the user signal fingerprint library.

[0072] Further, in each received wireless reflection signal, the signal reception strength and the channel state information are extracted, and for each wireless reflection signal, the signal reception strength and the channel state information corresponding to the wireless reflection signal are pre-processed respectively. In the user signal fingerprint library, the reference position corresponding to the pre-processed signal reception strength and channel state information is identified, and the reference position is determined as the user position in the device environment.

[0073] Further, identifying the reference position corresponding to the signal reception strength and the channel state information of the wireless reflection signal includes: splicing the signal reception strength and the channel state information of the wireless reflection signal into a spliced signal information; wherein in the user signal fingerprint library, the reference signal reception strength and the reference channel state information corresponding to the same reference position are a spliced reference signal information; in the user signal fingerprint library, a preset number of reference signal information closest to the spliced signal information corresponding to the wireless reflection signal is determined; in the case where one reference signal information is determined, the reference position corresponding to the determined reference signal information is determined as the user position; in the case where a plurality of reference signal information is determined, the reference position corresponding to the reference signal information closest to the spliced signal information is determined as the user position; or, in the case where a plurality of reference positions corresponding to a plurality of reference signal information are determined, the reference position located at the center position is determined as the user position.

[0074] Further, splicing the signal reception strength and the channel state information of the wireless reflection signal into a spliced signal information can be to form a sequence by arranging the signal reception strength and the channel state information of the wireless reflection signal in a predetermined order, and forming a spliced signal information.

[0075] Further, the reference signal receiving strength and the reference channel state information corresponding to the same reference position are spliced into one reference signal information.

[0076] Further, a preset K-Nearest Neighbor (KNN) algorithm can be used to determine a preset number of reference signal information closest to the spliced signal information corresponding to the wireless reflection signal in the user signal fingerprint library. The preset number can be an empirical value or a value obtained through experiments. The distance measurement methods include, but are not limited to, Euclidean distance, Manhattan distance, or cosine similarity.

[0077] Further, in the plurality of reference positions corresponding to the plurality of reference signal information, the reference position located at the center position is determined as the user position. The plurality of reference positions can be arranged in a circle that can accommodate the plurality of reference positions and has the smallest area. The reference position closest to the center of the circle is determined as the reference position at the center position, and the parameter position at the center position is determined as the user position.

[0078] In determining the user state in the device environment according to the wireless reflection signal, channel state information can be extracted from each wireless reflection signal, and dynamic state information can be extracted from the channel state information. A pre-trained motion state perception model can be used to determine the user state in the device environment according to the dynamic state information corresponding to the plurality of wireless reflection signals.

[0079] The dynamic state information refers to a signal segment corresponding to a human action in the channel state information.

[0080] The user state is used to reflect the behavior state of the user in the device environment. The user state includes, but is not limited to, motion speed and activity type. The motion speed is used to reflect the speed of the user movement. The activity type is used to reflect the type of user activity, such as resting, running, jumping, etc.

[0081] The motion state perception model is trained to determine the user state in the device environment according to the channel state information corresponding to the plurality of wireless reflection signals.

[0082] Further, in each wireless reflection signal, channel state information is extracted, and the channel state information is preprocessed. The dynamic state information is extracted from the preprocessed channel state information, and the dynamic state information corresponding to the wireless reflection signal is obtained.

[0083] Further, in order to improve the accuracy of the control method of the Internet of Things device, the channel state information can be processed by signal segmentation after preprocessing, and the signal segment corresponding to the action is retained. Further, in the device environment, not only static objects and human bodies, but also human bodies have actions and no actions, and the frequency ranges corresponding to actions and no actions are different. Since the wireless reflection signal may contain a large amount of data points, not all parts contain useful action information, and therefore the channel state information can be divided into smaller segments. When the human body moves, the adjacent subcarriers in the channel state information may become correlated. This correlation may be due to the change in signal characteristics caused by the action, thereby causing some correlation between different frequency components. By wavelet transform, the channel state information can be decomposed into sub-signals of different frequency bands, including low-frequency and high-frequency parts, and the high-frequency signal can be used as the signal segment with action.

[0084] Further, when training the motion state perception model, wireless reflection signals under different user states can be collected in advance, channel state information can be extracted from different wireless reflection signals, and dynamic state information can be extracted from the channel state information; the user state is taken as the true value, and the dynamic state information corresponding to the user state is taken as the input information of the motion state perception model, and the performance of the user state predicted by the motion state perception model is trained and verified. Wherein, the gradient descent method can be used to train the motion state perception model until the motion state perception model converges.

[0085] Further, the motion state perception model includes a speed perception sub-model and an activity perception sub-model. The speed perception sub-model and the activity perception sub-model can be jointly trained. After joint training, the speed perception sub-model can determine the motion speed of the human body by quantitatively analyzing the change of the time sequence of the channel state information. After joint training, the activity perception sub-model can perform spectral analysis on the channel state information and decompose it into low-frequency components and high-frequency components. Among them, the low-frequency component usually reflects slow posture changes, while the high-frequency component reflects fast actions. The types of activity perception sub-models include but are not limited to Hidden Markov Model (HMM).

[0086] For example, the carrier is in the frequency band of 5.825 GHz, according to the relationship between the frequency and the wavelength of electromagnetic wave, the wavelength is about 5.15 cm. If in the spectrum graph of walking activity, it is observed that there is a high-energy frequency band near the frequency of 35-40 Hz, then the Doppler effect formula can be used to calculate the speed, the moving speed v = Δf * λ / 2. If the frequency is 35 Hz, then v = 35 * 0.0515 / 2 = 0.901 m / s; if the frequency is 40 Hz, then v = 40 * 0.0515 / 2 = 1.03 m / s; through the above calculation, the walking speed range represented by the frequency component of 35-40 Hz in the spectrum graph of walking activity is about 0.9-1.03 m / s.

[0087] After transmitting the wireless transmission signal to the device environment, the received multipath wireless reflection signal is divided into static components and dynamic components. The static components mainly include direct signals and reflection signals caused by fixed obstacles such as walls, which are relatively stable when the device environment does not change. However, the dynamic components are reflection signals caused by human body movement, which will change with the movement of the human body. An embodiment of the present application determines the number of users and the location of users in the device environment through the corresponding wireless reflection signal of the human body, and identifies the movement speed and activity type of the human body according to the signal segment when the human body is in motion.

[0088] After determining the user feature information (user number, user location and user state), the operating parameters of the Internet of Things device can be adjusted according to the user feature information.

[0089] The operating parameters include but are not limited to: operating power parameters, operating direction parameters and operating mode parameters of the Internet of Things device. The types of operating power parameters, operating direction parameters and operating mode parameters can be determined according to the type of the Internet of Things device.

[0090] The operating power parameters include but are not limited to: compressor power, fan power.

[0091] The operating direction parameters are used to adjust the action area of the Internet of Things device. For example: the air outlet direction parameter of the humidifying air conditioner.

[0092] The operating mode parameters include but are not limited to: normal mode, silent mode, sleep mode.

[0093] Specifically, according to the previously determined user feature information, a changed feature parameter in the current determined user feature information is identified; in the case that the changed feature parameter is the number of users, the working power parameter of the Internet of Things device is adjusted according to the number of users; in the case that the changed feature parameter is the user position, the working direction parameter of the Internet of Things device is adjusted according to the user position; in the case that the changed feature parameter is the user state, the working power parameter and / or the working mode parameter of the Internet of Things device is adjusted according to the user state.

[0094] Further, adjusting the working power parameter of the Internet of Things device according to the number of users comprises adjusting the working power parameter of the Internet of Things device to the working power parameter corresponding to the number of users. Wherein, a plurality of user number ranges are pre-set and a working power parameter corresponding to each user number range is set, after determining the number of users in the device environment, the Internet of Things device is adjusted to the working power parameter corresponding to the user number range to which the number of users belongs. For example, in the case that the number of users increases, the air speed of the humidifying air conditioner can be increased to accelerate the convection and exchange of air, thereby improving the overall comfort; when it is detected that there is no one in the room, the humidifying air conditioner can be turned off or the operating power is reduced to reduce energy consumption.

[0095] Further, adjusting the working direction parameter of the Internet of Things device according to the user position comprises adjusting the working direction of the Internet of Things device to the direction facing the user position by adjusting the working direction parameter of the Internet of Things device. In the case that the user position is one, the working direction of the Internet of Things device is adjusted to the direction facing the user position; in the case that the user position is multiple, it is determined whether the coverage range of the working direction of the Internet of Things device can cover all user positions, if it can completely cover, the working direction of the Internet of Things device is adjusted to the direction facing (i.e. covering) all user positions; if it cannot completely cover, the working direction of the Internet of Things device is adjusted to the direction facing the most user positions. For example, when there are many people gathered in a corner of the room, the humidifying air conditioner can change the air outlet direction to locally adjust the temperature and humidity, so as to preferentially ensure that the temperature and humidity in the area are within the comfortable range.

[0096] Further, the user state comprises a user motion speed and a user activity type; adjusting the working power parameter and / or the working mode parameter of the Internet of Things device according to the user state comprises: in the case that the changed user running state is the user motion speed, adjusting the working power parameter of the Internet of Things device according to the user motion speed; in the case that the changed user running state is the user activity type, adjusting the working mode parameter of the Internet of Things device according to the user activity type.

[0097] Wherein, a plurality of motion speed ranges can be set in advance and a working power parameter is set for each motion speed range; the IoT device is adjusted to the working power parameter corresponding to the motion speed range to which the user motion speed belongs; wherein, if the working power parameter corresponding to the user number and the working power parameter corresponding to the user motion speed are different, the priority of the user number and the priority of the user motion speed are compared, and the IoT device is adjusted to the working power parameter corresponding to the highest priority feature parameter.

[0098] Wherein, a working mode parameter is set for each user activity type, and the IoT device is adjusted to the working mode parameter corresponding to the user activity type. For example, when a person is in a resting state, the air conditioner is adjusted to use a silent mode or a sleep mode, the noise and the wind speed are reduced, and the temperature is maintained in a more suitable range, helping the user to sleep and rest better; when the person is in an active state, the air conditioner is controlled to increase the air conditioner wind speed to keep the air circulating.

[0099] An embodiment of the present application further provides a control device of an IoT device. Figure 3 As shown in the figure, it is a structural diagram of the control device of the IoT device according to an embodiment of the present application.

[0100] The control device of the IoT device comprises a transceiving unit 310, a determination unit 320 and a control unit 330.

[0101] The transceiving unit 310 is used for emitting a wireless signal to a device environment where a preset IoT device is located, and receiving a wireless reflection signal returned from the device environment.

[0102] The determination unit 320 is used for determining user feature information corresponding to the device environment according to the wireless reflection signal.

[0103] The control unit 330 is used for adjusting the running parameter of the IoT device according to the user feature information.

[0104] The function of the device according to the embodiment of the present application has been described in the above-mentioned method embodiment, so the description of the present embodiment is not detailed, and the relevant description in the foregoing embodiment can be referred to, which will not be repeated here.

[0105] An embodiment of the present application further provides a control device of an IoT device. Figure 4 As shown in the figure, it is a structural block diagram of the control device of the IoT device according to an embodiment of the present application.

[0106] The control device of the Internet of Things device comprises a processor 410, a communication interface 420, a memory 430 and a communication bus 440. The processor 410, the communication interface 420 and the memory 430 complete mutual communication through the communication bus 440.

[0107] The memory 430 is used for storing a computer program.

[0108] In an embodiment of the present application, the processor 410 is used for executing the program stored in the memory 430 to implement the control method of the Internet of Things device provided by any one of the foregoing method embodiments, comprising: emitting a wireless signal to a preset device environment where an Internet of Things device is located, and receiving a wireless reflection signal returned from the device environment; determining user feature information corresponding to the device environment according to the wireless reflection signal; and adjusting an operating parameter of the Internet of Things device according to the user feature information.

[0109] The feature parameters in the user feature information comprise a user quantity, the determination of the user feature information corresponding to the device environment according to the wireless reflection signal comprises: for each wireless reflection signal, extracting signal receiving strength and channel state information in the wireless reflection signal; extracting signal domain feature sequences from the signal receiving strength and the channel state information respectively; and determining the user quantity in the device environment according to the signal domain feature sequences respectively corresponding to multiple wireless reflection signals by using a pre-trained user quantity perception model.

[0110] The feature parameters in the user feature information comprise a user position, the determination of the user feature information corresponding to the device environment according to the wireless reflection signal comprises: extracting signal receiving strength and channel state information in each wireless reflection signal; for each wireless reflection signal, identifying a reference position corresponding to the signal receiving strength and the channel state information of the wireless reflection signal in a user signal fingerprint library corresponding to the Internet of Things device, and determining the reference position as a user position in the device environment; wherein the user signal fingerprint library corresponding to the Internet of Things device is used for pre-recording wireless signal features corresponding to multiple reference positions in the device environment, and the wireless signal features at least comprise reference signal receiving strength and reference channel state information.

[0111] The reference position corresponding to the signal receiving strength and the channel state information of the wireless reflection signal is determined as the user position in the device environment, including: splicing the signal receiving strength and the channel state information of the wireless reflection signal into a spliced signal information; wherein the reference signal receiving strength and the reference channel state information corresponding to the same reference position in the user signal fingerprint library are a spliced reference signal information; in the user signal fingerprint library, a preset number of reference signal information closest to the spliced signal information corresponding to the wireless reflection signal is determined; in the case of determining one reference signal information, the reference position corresponding to the determined reference signal information is determined as the user position; in the case of determining multiple reference signal information, the reference position corresponding to the reference signal information closest to the spliced signal information is determined as the user position; or, in the case of determining multiple reference signal information corresponding to the reference position respectively, the reference position located at the center position is determined as the user position.

[0112] The feature parameters in the user feature information include: user state; the user feature information corresponding to the device environment is determined according to the wireless reflection signal, including: extracting channel state information in each wireless reflection signal and extracting dynamic state information in the channel state information; the user state in the device environment is determined according to the dynamic state information corresponding to multiple wireless reflection signals respectively by using a pre-trained motion state perception model.

[0113] The running parameters of the Internet of Things device are adjusted according to the user feature information, including: identifying the changed feature parameters in the determined user feature information according to the previously determined user feature information; in the case that the changed feature parameter is the user quantity, the working power parameter of the Internet of Things device is adjusted according to the user quantity; in the case that the changed feature parameter is the user position, the working direction parameter of the Internet of Things device is adjusted according to the user position; in the case that the changed feature parameter is the user state, the working power parameter and / or the working mode parameter of the Internet of Things device are adjusted according to the user state.

[0114] An embodiment of the present application provides an air conditioner, specifically a humidifying air conditioner, that is provided with a control device of the Internet of Things device, so as to automatically perceive the user quantity, the user position and the user state in the environment through the wireless reflection signal, automatically adjust the temperature and the wind speed of the humidifying air conditioner, and achieve the effects of energy saving and comfort.

[0115] An embodiment of the present application also provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of the control method of the Internet of Things device according to any one of the preceding method embodiments. Since the control method of the Internet of Things device has been described in detail above, the description of the present embodiment will not be elaborated on the related descriptions in the preceding embodiments.

[0116] An embodiment of the present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the control method of the Internet of Things device according to any one of the preceding method embodiments. Since the control method of the Internet of Things device has been described in detail above, the description of the present embodiment will not be elaborated on the related descriptions in the preceding embodiments.

[0117] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored on or transferred over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions can also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations. Also, as technology evolves, the underlying functions and logic can be implemented by equivalent hardware and / or software elements without departing from the scope and spirit of the disclosure.

[0118] In several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0119] The units described as separate components can or can not be physically separate, and the components of the control device can or can not be physical units, i.e. can be located in one place, or can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0120] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that make contributions to the related art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0121] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A control method of an Internet of Things device, the method comprising: The method comprises the following steps: sending a wireless transmission signal to a device environment where a preset Internet of Things device is located, and receiving a wireless reflection signal returned from the device environment; determining user feature information corresponding to the device environment according to the wireless reflection signal; adjusting an operation parameter of the Internet of Things device according to the user feature information; the feature parameter in the user feature information comprises a user quantity; the step of determining the user feature information corresponding to the device environment according to the wireless reflection signal comprises: for each wireless reflection signal, extracting signal receiving strength and channel state information in the wireless reflection signal; and extracting a signal domain feature sequence from the signal receiving strength and the channel state information, respectively; determining the user quantity in the device environment according to the signal domain feature sequence corresponding to each wireless reflection signal by using a pre-trained user quantity perception model.

2. The method of claim 1, wherein: the feature parameter in the user feature information comprises a user position; the step of determining the user feature information corresponding to the device environment according to the wireless reflection signal comprises: extracting signal receiving strength and channel state information in each wireless reflection signal; for each wireless reflection signal, identifying a reference position corresponding to the signal receiving strength and the channel state information of the wireless reflection signal in a user signal fingerprint library corresponding to the Internet of Things device, and determining the reference position as a user position in the device environment; wherein the user signal fingerprint library corresponding to the Internet of Things device is used to pre-record wireless signal features corresponding to a plurality of reference positions in the device environment; the wireless signal features at least comprise reference signal receiving strength and reference channel state information.

3. The method of claim 2, wherein, the step of identifying the reference position corresponding to the signal receiving strength and the channel state information of the wireless reflection signal in the user signal fingerprint library corresponding to the Internet of Things device, and determining the reference position as the user position in the device environment, comprises: splicing the signal receiving strength and the channel state information of the wireless reflection signal into a spliced signal information; wherein the reference signal receiving strength and the reference channel state information corresponding to the same reference position in the user signal fingerprint library are a spliced reference signal information; determining a preset number of reference signal information closest to the spliced signal information corresponding to the wireless reflection signal in the user signal fingerprint library; in the case of determining one reference signal information, determining the reference position corresponding to the determined reference signal information as the user position; in the case of determining a plurality of reference signal information, determining the reference position corresponding to the reference signal information closest to the spliced signal information as the user position; or, in the case of determining a plurality of reference positions corresponding to the plurality of reference signal information, determining the reference position located at the center position as the user position.

4. The method of claim 1, wherein: the feature parameter in the user feature information comprises a user state; The user feature information corresponding to the device environment is determined according to the wireless reflection signals, and the method comprises the steps of: In each wireless reflection signal, channel state information is extracted, and dynamic state information is extracted from the channel state information; A motion state perception model is trained in advance, and the user state in the device environment is determined according to the dynamic state information corresponding to each wireless reflection signal.

5. The method of claim 1, wherein, The running parameters of the Internet of Things device are adjusted according to the user feature information, and the method comprises the steps of: According to the user feature information determined last time, the feature parameters changed in the user feature information determined this time are identified; In the case that the changed feature parameter is the number of users, the working power parameter of the Internet of Things device is adjusted according to the number of users; In the case that the changed feature parameter is the user position, the working direction parameter of the Internet of Things device is adjusted according to the user position; In the case that the changed feature parameter is the user state, the working power parameter and / or the working mode parameter of the Internet of Things device are adjusted according to the user state.

6. A control device of an Internet of Things device, characterized in that, Comprise: The transceiver unit is used to send wireless transmission signals to the device environment where the preset Internet of Things device is located, and receive wireless reflection signals returned from the device environment; The determination unit is used to determine the user feature information corresponding to the device environment according to the wireless reflection signals; The control unit is used to adjust the running parameters of the Internet of Things device according to the user feature information; The feature parameters in the user feature information include the number of users; the determination unit, which determines the user feature information corresponding to the device environment according to the wireless reflection signals, comprises the following steps: for each wireless reflection signal, signal reception strength and channel state information are extracted from the wireless reflection signal; and signal domain feature sequences are respectively extracted from the signal reception strength and the channel state information; a user number perception model is trained in advance, and the number of users in the device environment is determined according to the signal domain feature sequences corresponding to each wireless reflection signal.

7. A control device of an Internet of Things device, characterized by, Comprise: At least one communication interface; At least one bus connected to the at least one communication interface; At least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to execute the control program of the Internet of Things device stored in the memory to realize the control method of the Internet of Things device in any one of claims 1-5.

8. An air conditioner characterized by comprising: The air conditioner comprises the control device of the Internet of Things device in claim 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions, and the computer executable instructions are executed to realize the control method of the Internet of Things device in any one of claims 1-5.

10. A computer program product, characterised in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1-5. The computer program is executed by the processor to realize the steps of the method in any one of claims 1-5.

Images