CN114548246A - Control method and system of intelligent device and electronic device - Google Patents
Control method and system of intelligent device and electronic device Download PDFInfo
- Publication number
- CN114548246A CN114548246A CN202210129871.8A CN202210129871A CN114548246A CN 114548246 A CN114548246 A CN 114548246A CN 202210129871 A CN202210129871 A CN 202210129871A CN 114548246 A CN114548246 A CN 114548246A
- Authority
- CN
- China
- Prior art keywords
- gaussian
- sequence
- humidity
- temperature
- vectors
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G10/00—Treatment rooms or enclosures for medical purposes
- A61G10/02—Treatment rooms or enclosures for medical purposes with artificial climate; with means to maintain a desired pressure, e.g. for germ-free rooms
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Pulmonology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to the field of intelligent medical monitoring of animals, and particularly discloses a control method, a system and an electronic device of an intelligent device. Through the mode, whether the current temperature and humidity are reasonable or not can be judged more accurately, and further unreasonable temperature and humidity are adjusted, so that a suitable monitoring and recovery environment is provided for animals.
Description
Technical Field
The present application relates to the field of intelligent medical monitoring of animals, and more particularly, to a control method, system and electronic device for an intelligent device.
Background
The intelligent animal medical monitoring device is mainly used for rehabilitation and treatment of animals, and provides a suitable monitoring and recovery environment for weak and critical animals. The device mainly comprises a relatively closed monitoring chamber, a sensor, a controller and the like. The animal can obtain the proper temperature, humidity and oxygen concentration which can be set in the monitoring chamber, and meanwhile, the equipment can provide the functions of lighting, power-off protection, fault warning and the like.
The key and difficulty of the device in the research and development process lies in the temperature and humidity control of the monitoring chamber, the temperature change can affect the humidity, and the temperature change can also affect the temperature, which is called as the coupling effect between the temperature and the humidity. Because of the coupling effect between temperature and humidity, and the characteristics of nonlinearity and big hysteresis of temperature and humidity control, how to control temperature and humidity fast and accurately becomes a challenge.
Therefore, a control method of the smart device is desired.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. Embodiments of the present application provide a control method, a system, and an electronic device for an intelligent device, which use a converter-based encoder model to perform context coding on a plurality of temperature values and a plurality of humidity values to obtain global temperature-related information, humidity-related information, and temperature-humidity-related information, and further perform fusion of the temperature data and the humidity data through likelihood maximization of gaussian distribution to train the converter-based encoder model and the classifier. Through the mode, whether the current temperature and humidity are reasonable or not can be judged more accurately, and further unreasonable temperature and humidity are adjusted, so that a suitable monitoring and recovery environment is provided for animals.
According to an aspect of the present application, there is provided a control method of a smart device, including:
a training phase comprising:
acquiring training data, wherein the training data are temperature data and humidity data of a series of time points at a preset time interval;
context-coding the temperature data and the humidity data at the series of time points using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
constructing a sequence of Gaussian distributions of the sequence of the temperature characteristic vectors and the sequence of the humidity characteristic vectors, wherein the variance and the mean of each Gaussian distribution in the sequence of the Gaussian distributions are obtained by calculating the corresponding temperature characteristic vectors and humidity characteristic vectors based on a likelihood maximization calculation principle and by using Gaussian probability density values for adjusting data fusion;
discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors;
performing two-dimensional splicing on the plurality of Gaussian vectors to obtain a classification feature map;
passing the classification feature map through a classifier to obtain a classification loss function value;
calculating a gaussian density loss function value based on the gaussian probability density value; and
computing a weighted sum of the classification loss function value and the Gaussian density loss function value as a loss function value to train the converter-based encoder model and the classifier; and
an inference phase comprising:
acquiring temperature data and humidity data of a series of time points of a preset time interval;
context-coding the temperature data and the humidity data at the series of time points using the converter-based encoder model trained to be completed in the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
constructing a sequence of Gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors;
discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors, and performing two-dimensional splicing on the Gaussian vectors to obtain a classification feature map;
and passing the classification characteristic diagram through a classifier to obtain a classification result for indicating whether the current temperature and humidity are reasonable or not.
According to another aspect of the present application, there is provided a control system of a smart device, including:
a training module comprising:
the training data acquisition unit is used for acquiring training data, wherein the training data are temperature data and humidity data of a series of time points at a preset time interval;
an encoding unit configured to perform context encoding on the temperature data and the humidity data at the series of time points obtained by the training data obtaining unit using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
a gaussian distribution constructing unit configured to construct a sequence of gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors obtained by the encoding unit, wherein a variance and a mean of each gaussian distribution in the sequence of gaussian distributions are obtained by calculating corresponding temperature feature vectors and humidity feature vectors based on a likelihood maximization calculation principle and using gaussian probability density values for adjusting data fusion;
a gaussian discretization unit configured to discretize each gaussian distribution in the sequence of gaussian distributions obtained by the gaussian distribution constructing unit to obtain a plurality of gaussian vectors;
the two-dimensional splicing unit is used for performing two-dimensional splicing on the plurality of Gaussian vectors obtained by the Gaussian discretization unit to obtain a classification feature map;
the classifier processing unit is used for enabling the classification characteristic graph obtained by the two-dimensional splicing unit to pass through a classifier so as to obtain a classification loss function value;
a gaussian density loss function value calculation unit for calculating a gaussian density loss function value based on the gaussian probability density value; and
a training unit for calculating a weighted sum of the classification loss function value obtained by the classifier processing unit and the gaussian density loss function value obtained by the gaussian density loss function value calculation unit as a loss function value to train the converter-based encoder model and the classifier; and
an inference module comprising:
a data acquisition unit for acquiring temperature data and humidity data at a series of time points at predetermined time intervals;
a feature vector generation unit, configured to perform context coding on the temperature data and the humidity data at the series of time points obtained by the data acquisition unit using the converter-based encoder model trained in the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
a gaussian distribution sequence generating unit configured to construct a sequence of gaussian distributions of the sequence of temperature characteristic vectors and the sequence of humidity characteristic vectors obtained by the characteristic vector generating unit;
the classification characteristic map generation unit is used for carrying out discretization processing on each Gaussian distribution in the Gaussian distribution sequence obtained by the Gaussian distribution sequence generation unit to obtain a plurality of Gaussian vectors and carrying out two-dimensional splicing on the Gaussian vectors to obtain a classification characteristic map; and
and the classification unit is used for enabling the classification characteristic diagram obtained by the classification characteristic diagram generation unit to pass through a classifier so as to obtain a classification result which is used for indicating whether the current temperature and humidity are reasonable or not.
According to yet another aspect of the present application, there is provided an electronic device including: a processor; and a memory in which computer program instructions are stored, which, when executed by the processor, cause the processor to perform the control method of the smart device as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to execute the control method of the smart device as described above.
According to the control method, the control system and the electronic device of the intelligent device, a plurality of temperature values and a plurality of humidity values are context-coded by using a converter-based encoder model to obtain global temperature related information, humidity related information and temperature-humidity related information, and the temperature data and the humidity data are further fused by likelihood maximization of Gaussian distribution to train the converter-based encoder model and the classifier. Through the mode, whether the current temperature and humidity are reasonable or not can be judged more accurately, and further unreasonable temperature and humidity are adjusted, so that a suitable monitoring and recovery environment is provided for animals.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 is a scene schematic diagram of a control method of an intelligent device according to an embodiment of the present application.
Fig. 2A is a flowchart of a training phase in a control method of a smart device according to an embodiment of the present application.
Fig. 2B is a flowchart of an inference phase in a control method of a smart device according to an embodiment of the present application.
Fig. 3A is a schematic diagram of an architecture of a training phase in a control method of an intelligent device according to an embodiment of the present application.
Fig. 3B is a schematic diagram of an architecture of an inference phase in a control method of an intelligent device according to an embodiment of the present application.
Fig. 4 is a block diagram of a control system of a smart device according to an embodiment of the present application.
Fig. 5 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Overview of a scene
As mentioned above, the intelligent animal medical monitoring device is mainly aimed at the rehabilitation and treatment of animals, and provides a suitable monitoring and recovery environment for weak and sick animals. The device mainly comprises a relatively closed monitoring chamber, a sensor, a controller and the like. The animal can obtain the proper temperature, humidity and oxygen concentration which can be set in the monitoring chamber, and meanwhile, the equipment can provide the functions of lighting, power-off protection, fault warning and the like.
The key and difficulty of the device in the research and development process lies in the temperature and humidity control of the monitoring chamber, the temperature change can affect the humidity, and the temperature change can also affect the temperature, which is called as the coupling effect between the temperature and the humidity. Because of the coupling effect between temperature and humidity, and the characteristics of nonlinearity and big hysteresis of temperature and humidity control, how to control temperature and humidity fast and accurately becomes a challenge. Therefore, a control method of the smart device is desired.
Specifically, in the technical scheme of the application, temperature data and humidity data of a series of time points at a preset time interval are obtained, a plurality of temperature values and a plurality of humidity values are context-coded by using a converter-based encoder model, that is, each temperature value is converted into a temperature input vector, each humidity value is converted into a humidity input vector, and then all the temperature input vectors and all the humidity input vectors are input into a converter to obtain a sequence of temperature characteristic vectors and a sequence of humidity characteristic vectors. Since the converter-based encoder model can encode the input vector based on the context, the obtained temperature and humidity feature vectors can obtain global temperature, humidity and temperature-humidity related information.
Then, in order to fuse the temperature feature vector and the humidity feature vector, data fusion is performed by likelihood maximization of the gaussian distribution, considering that both the temperature and the humidity substantially follow the gaussian distribution within a predetermined period of time, that is, the probability distributions of the population are the same or similar, but the feature scales of the respective data are different.
Specifically, the temperature characteristic is assumed to beThe sequence of amounts is denoted TiAnd the sequence of the humidity characteristic vector is recorded as HiThen, the mean and variance of the gaussian distribution calculated according to the likelihood maximization are respectively:
wherein 1 isN＝[1,1,…,1]I.e. a vector in which all positions are 1, and NiIs a Gaussian probability density value used for adjusting data fusion.
In this way, the number of time points, e.g. n Gaussian distributions, can be obtained
And then discretizing each Gaussian distribution to obtain n Gaussian vectors, and performing two-dimensional connection on the n Gaussian vectors to obtain a classification characteristic diagram.
When the classification feature map is subjected to a classifier to obtain a classification loss function, a gaussian density loss function is calculated based on a gaussian probability density value, which is expressed as:
to balance the differences between the individual gaussian probability densities.
Based on this, the present application proposes a control method of an intelligent device, which includes: a training phase and an inference phase. Wherein the training phase comprises the steps of: acquiring training data, wherein the training data are temperature data and humidity data of a series of time points at a preset time interval; context-coding the temperature data and the humidity data at the series of time points using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors; constructing a sequence of Gaussian distributions of the sequence of the temperature characteristic vectors and the sequence of the humidity characteristic vectors, wherein the variance and the mean of each Gaussian distribution in the sequence of the Gaussian distributions are obtained by calculating the corresponding temperature characteristic vectors and humidity characteristic vectors based on a likelihood maximization calculation principle and by using Gaussian probability density values for adjusting data fusion; discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors; performing two-dimensional stitching on the plurality of Gaussian vectors to obtain a classification feature map; passing the classification feature map through a classifier to obtain a classification loss function value; calculating a gaussian density loss function value based on the gaussian probability density value; and calculating a weighted sum of the classification loss function value and the gaussian density loss function value as a loss function value to train the converter-based encoder model and the classifier. Wherein the inference phase comprises the steps of: acquiring temperature data and humidity data of a series of time points of a preset time interval; context-coding the temperature data and the humidity data at the series of time points using the converter-based encoder model trained to be completed in the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors; constructing a sequence of Gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors; discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors, and performing two-dimensional splicing on the Gaussian vectors to obtain a classification feature map; and passing the classification characteristic diagram through a classifier to obtain a classification result for indicating whether the current temperature and humidity are reasonable or not.
Fig. 1 illustrates a scene diagram of a control method of a smart device according to an embodiment of the present application. As shown in fig. 1, in the training phase of the application scenario, first, training data, which are temperature data and humidity data at a series of time points of a predetermined time interval, are acquired by sensors deployed at fixed positions of a monitoring chamber (e.g., M as illustrated in fig. 1), wherein the sensors are a temperature sensor (e.g., T as illustrated in fig. 1) and a humidity sensor (e.g., H as illustrated in fig. 1). The obtained training data is then input into a server (e.g. server S as illustrated in fig. 1) where the control algorithm of the smart device is deployed, wherein the server is capable of training the converter-based encoder model and the classifier of the control of the smart device with the training data.
After training is completed, in the inference phase, first, temperature data and humidity data at a series of time points of a predetermined time interval are acquired by a temperature sensor (e.g., T as illustrated in fig. 1) and a humidity sensor (e.g., H as illustrated in fig. 1) disposed at fixed positions of a monitoring chamber (e.g., M as illustrated in fig. 1). Then, the acquired temperature data and humidity data at the series of time points are input into a server (for example, a server S as illustrated in fig. 1) in which a control algorithm of the smart device is deployed, wherein the server can process the temperature data and humidity data at the series of time points by the control algorithm of the smart device to generate a classification result indicating whether the current temperature and humidity are reasonable or not. Further, the unreasonable temperature and humidity may be adjusted by a controller (e.g., C as illustrated in fig. 1) to provide an appropriate monitoring and recovery environment for the animal.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 2A illustrates a flowchart of a training phase in a control method of a smart device according to an embodiment of the present application. As shown in fig. 2A, a method for controlling an intelligent device according to an embodiment of the present application includes: a training phase comprising the steps of: s110, acquiring training data, wherein the training data are temperature data and humidity data of a series of time points at preset time intervals; s120, context coding is carried out on the temperature data and the humidity data of the series of time points by using a converter-based encoder model so as to obtain a sequence of temperature characteristic vectors and a sequence of humidity characteristic vectors; s130, constructing a sequence of Gaussian distributions of the sequence of the temperature characteristic vectors and the sequence of the humidity characteristic vectors, wherein the variance and the mean of each Gaussian distribution in the sequence of the Gaussian distributions are obtained by calculating the corresponding temperature characteristic vectors and humidity characteristic vectors based on a likelihood maximization calculation principle and by using Gaussian probability density values for adjusting data fusion; s140, performing discretization processing on each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors; s150, performing two-dimensional splicing on the multiple Gaussian vectors to obtain a classification characteristic map; s160, passing the classification characteristic map through a classifier to obtain a classification loss function value; s170, calculating a Gaussian density loss function value based on the Gaussian probability density value; and, S180, calculating a weighted sum of the classification loss function value and the gaussian density loss function value as a loss function value to train the converter-based encoder model and the classifier.
Fig. 2B illustrates a flow chart of an inference phase in a control method of a smart device according to an embodiment of the application. As shown in fig. 2B, the method for controlling an intelligent device according to the embodiment of the present application further includes: an inference phase comprising the steps of: s210, acquiring temperature data and humidity data of a series of time points at preset time intervals; s220, context coding is carried out on the temperature data and the humidity data of the series of time points by using the converter-based encoder model trained in the training stage to obtain a sequence of temperature characteristic vectors and a sequence of humidity characteristic vectors; s230, constructing a Gaussian distribution sequence of the temperature characteristic vector sequence and the humidity characteristic vector sequence; s240, performing discretization processing on each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors, and performing two-dimensional splicing on the Gaussian vectors to obtain a classification characteristic map; and S250, passing the classification characteristic diagram through a classifier to obtain a classification result for indicating whether the current temperature and humidity are reasonable or not.
Fig. 3A illustrates an architecture diagram of a training phase in a control method of a smart device according to an embodiment of the present application. As shown in fig. 3A, in the training phase, first, the obtained temperature data (e.g., P1 as illustrated in fig. 3A) and humidity data (e.g., P2 as illustrated in fig. 3A) at the series of time points are context-encoded using a converter-based encoder model (e.g., E1 as illustrated in fig. 3A) to obtain a sequence of temperature eigenvectors (e.g., VF1 as illustrated in fig. 3A) and a sequence of humidity eigenvectors (e.g., VF2 as illustrated in fig. 3A); next, constructing a sequence of gaussian distributions of the sequence of temperature and humidity eigenvectors (e.g., GD1 as illustrated in fig. 3A), wherein variances and means of respective gaussian distributions in the sequence of gaussian distributions are obtained by calculating corresponding temperature and humidity eigenvectors based on a likelihood maximization calculation principle and using a gaussian probability density value (e.g., GP1 as illustrated in fig. 3A) for adjusting data fusion; then, discretizing each gaussian distribution in the sequence of gaussian distributions to obtain a plurality of gaussian vectors (e.g., VG1 as illustrated in fig. 3A); then, the plurality of gaussian vectors are two-dimensionally stitched to obtain a classification feature map (e.g., F1 as illustrated in fig. 3A); then, passing the classification signature through a classifier (e.g., a classifier as illustrated in fig. 3A) to obtain a classification loss function value (e.g., a CLV as illustrated in fig. 3A); then, calculating a gaussian density loss function value (e.g., GDV as illustrated in fig. 3A) based on the gaussian probability density value (e.g., GP1 as illustrated in fig. 3A); and finally, computing a weighted sum of the classification loss function value and the gaussian density loss function value as a loss function value to train the converter-based encoder model and the classifier.
Fig. 3B illustrates an architecture diagram of an inference phase in a control method of a smart device according to an embodiment of the present application. As shown in fig. 3B, in the inference stage, first, context-coding the acquired temperature data (e.g., Q1 as illustrated in fig. 3B) and humidity data (e.g., Q2 as illustrated in fig. 3B) at the series of time points using the converter-based encoder model (e.g., E2 as illustrated in fig. 3B) trained by the training stage to obtain a sequence of temperature eigenvectors (e.g., FV1 as illustrated in fig. 3B) and a sequence of humidity eigenvectors (e.g., FV2 as illustrated in fig. 3B); next, a sequence of gaussian distributions of the sequence of temperature and humidity feature vectors is constructed (e.g., GD2 as illustrated in fig. 3B); then, discretizing each gaussian distribution in the sequence of gaussian distributions to obtain a plurality of gaussian vectors (e.g., VG2 as illustrated in fig. 3B) and two-dimensionally stitching the plurality of gaussian vectors to obtain a classification feature map (e.g., F2 as illustrated in fig. 3B); and, finally, passing the classification feature map through a classifier (e.g., a classifier as illustrated in fig. 3B) to obtain a classification result indicating whether the current temperature and humidity are reasonable.
More specifically, in the training phase, in step S110 and step S120, training data, which is temperature data and humidity data at a series of time points of a predetermined time interval, is acquired, and the temperature data and the humidity data at the series of time points are context-encoded using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors. As mentioned above, due to the coupling effect between the temperature and the humidity, that is, the change of the temperature will affect the humidity, and the change of the humidity will also affect the temperature, and the control of the temperature and the humidity has the characteristics of nonlinearity and large hysteresis. Therefore, in the technical scheme of the application, whether the current temperature and humidity are reasonable or not is expected to be judged rapidly and accurately so as to rapidly and accurately control the temperature and the humidity, thereby providing a proper monitoring and recovery environment for animals.
That is, in one particular example, first, training data, which are temperature data and humidity data at a series of time points at predetermined time intervals, are acquired by a temperature sensor and a humidity sensor deployed at fixed locations of a monitoring chamber. Then, context coding is carried out on the temperature data and the humidity data of the series of time points by using a converter-based encoder model so as to mine the global temperature related information, humidity related information and temperature-humidity related information, thereby obtaining a sequence of temperature characteristic vectors and a sequence of humidity characteristic vectors.
Specifically, in the embodiment of the present application, the process of context-coding the temperature data and the humidity data at the series of time points using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors includes: firstly, each temperature data is converted into a temperature input vector and each humidity data is converted into a humidity input vector through an embedding unit of the encoder model, so that the subsequent extraction of the implicit correlation information is facilitated. Then, all of the temperature input vectors and all of the humidity input vectors are input to a converter of the encoder model to obtain the sequence of temperature feature vectors and the sequence of humidity feature vectors. It should be understood that, since the converter-based encoder model can encode the input vector based on context, the obtained temperature feature vector and the humidity feature vector can obtain global temperature-related information, humidity-related information, and temperature-humidity-related information.
More specifically, in the training phase, in step S130, a sequence of gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors is constructed, wherein the variance and mean of each gaussian distribution in the sequence of gaussian distributions is obtained by calculating the corresponding temperature feature vector and humidity feature vector based on the likelihood maximization calculation principle and using the gaussian probability density value for adjusting the data fusion. It will be appreciated that in order to fuse the temperature and humidity eigenvectors, it is contemplated that both temperature and humidity substantially follow a gaussian distribution over a predetermined period of time, i.e., the probability distributions of their populations are the same or similar, while the characteristic dimensions of the respective data are different. Therefore, in the technical solution of the present application, the fusion of data is performed by the likelihood maximization of the gaussian distribution. That is, in one specific example, assume that the sequence of temperature eigenvectors is denoted as TiThe sequence of the humidity characteristic vector is marked as HiThen constructing a sequence T of said temperature eigenvectorsiAnd a humidity feature vectorSequence H ofiWherein the variance and the mean of each gaussian in the sequence of gaussian distributions are obtained by calculating corresponding temperature eigenvectors and humidity eigenvectors based on a likelihood maximization calculation principle and using gaussian probability density values for adjusting data fusion.
Specifically, in the embodiment of the present application, a sequence of gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors is constructed, wherein a process in which a variance and a mean of each gaussian distribution in the sequence of gaussian distributions is obtained by calculating corresponding temperature feature vectors and humidity feature vectors based on a likelihood maximization calculation principle and using gaussian probability density values for adjusting data fusion includes: calculating the mean and variance of each Gaussian distribution in the sequence of Gaussian distributions according to the following formula;
wherein 1N＝[1,1,…,1]I.e. a vector in which all positions are 1, and NiIs a Gaussian probability density value used for adjusting data fusion.
More specifically, in the training phase, in steps S140 and S150, discretization processing is performed on each gaussian distribution in the sequence of gaussian distributions to obtain a plurality of gaussian vectors, and the plurality of gaussian vectors are two-dimensionally stitched to obtain a classification feature map. That is, in the technical solution of the present application, in the above manner, the number of time points, for example, n gaussian distributions, can be obtained
Then, discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain n Gaussian vectors, and further performing interpolation on the n Gaussian vectorsAnd connecting lines in two dimensions to obtain a classification feature map so as to facilitate the subsequent training of the encoder model and the classifier by calculating a classification loss function value. It should be understood that the accuracy of classification is improved by discretizing each gaussian distribution in the sequence of gaussian distributions so as not to generate information loss during fusion.
More specifically, in the training phase, in step S160, the classification feature map is passed through a classifier to obtain a classification loss function value. That is, in one particular example, the classification feature map is first fully-connected encoded using a plurality of fully-connected layers of the classifier to obtain a classification feature vector. Then, the classification feature vector is input into a Softmax classification function of the classifier to obtain a classification result. Specifically, the classification feature vector is input into a Softmax classification function of the classifier to obtain a first probability that the classification feature vector is reasonable for the current temperature and humidity and a second probability that the classification feature vector is unreasonable for the current temperature and humidity, and a classification result is generated based on a comparison of the first probability and the second probability. Then, a cross entropy value between the classification result and a real value is calculated as the classification loss function value.
More specifically, in the training phase, gaussian density loss function values are calculated based on the gaussian probability density values, and a weighted sum of the classification loss function values and the gaussian density loss function values is calculated as loss function values to train the converter-based encoder model and the classifier in steps S170 and S180. That is, in the technical solution of the present application, when the classification feature map is obtained through the classifier to obtain the classification loss function, it is further necessary to calculate a gaussian density loss function value based on the gaussian probability density values to balance the difference between the gaussian probability densities of the individuals. Further re-calculating a weighted sum of the classification loss function value and the gaussian density loss function value as a loss function value to train the converter-based encoder model and the classifier. Accordingly, in one particular example, in each iteration, the parameters of the encoder model are updated by back-propagation of the gradient descent with the loss function values; the parameters of the classifier are then updated with the loss function values by back propagation of the gradient descent.
Specifically, in this embodiment of the present application, the process of calculating the gaussian density loss function value based on the gaussian probability density value includes: calculating the Gaussian density loss function value based on the Gaussian probability density value according to the following formula;
wherein the formula is:
after training is completed, the inference phase is entered. That is, after the converter-based encoder model and the classifier are trained using a control algorithm of a smart device, the trained converter-based encoder model and the classifier are used in an actual inference scenario.
More specifically, in the inference phase, in steps S210 and S220, temperature data and humidity data at a series of time points of a predetermined time interval are acquired, and the temperature data and humidity data at the series of time points are context-coded using the converter-based encoder model trained through the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors. That is, likewise, temperature data and humidity data are first acquired at a series of time points over a predetermined time interval by temperature and humidity sensors deployed at fixed locations in the monitoring chamber. Then, the temperature data and the humidity data of the series of time points are context-coded by using the converter-based encoder model trained in the training phase to extract the global temperature correlation information, humidity correlation information and temperature-humidity correlation information, so as to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors.
More specifically, in the inference phase, in step S230 and step S240And constructing a sequence of Gaussian distributions of the sequence of the temperature characteristic vectors and the sequence of the humidity characteristic vectors, discretizing each Gaussian distribution in the sequence of the Gaussian distributions to obtain a plurality of Gaussian vectors, and performing two-dimensional splicing on the Gaussian vectors to obtain a classification characteristic map. That is, similarly, first, the sequence T of the temperature feature vectors is constructediAnd a sequence H of humidity eigenvectorsiWherein the variance and the mean of each gaussian in the sequence of gaussian distributions are obtained by calculating corresponding temperature eigenvectors and humidity eigenvectors based on a likelihood maximization calculation principle and using gaussian probability density values for adjusting data fusion. Then, each Gaussian distribution in the sequence of Gaussian distributions is subjected to discretization processing so as not to generate information loss during fusion, and therefore the classification accuracy is improved to obtain a plurality of Gaussian vectors. Then, the Gaussian vectors are subjected to two-dimensional splicing to obtain a classification feature map.
More specifically, in the inference phase, in step S250, the classification feature map is passed through a classifier to obtain a classification result indicating whether the current temperature and humidity are reasonable. That is, in one particular example, the classification feature map is first fully-connected encoded using a plurality of fully-connected layers of the classifier to obtain a classification feature vector. Then, the classification feature vector is input into a Softmax classification function of the classifier to obtain a first probability that the classification feature vector is due to current temperature and humidity being reasonable and a second probability that the classification feature vector is due to current temperature and humidity being unreasonable. Then, a classification result is generated further based on the comparison of the first probability and the second probability. Specifically, when the first probability is greater than the second probability, the classification result is that the current temperature and humidity are reasonable; and when the second probability is greater than the first probability, the classification result is that the current temperature and humidity are unreasonable. Furthermore, when the current temperature and the current humidity are unreasonable, the unreasonable temperature and humidity can be adjusted through the controller, so that a proper monitoring and recovery environment is provided for the animals.
In summary, a control method of a smart device according to an embodiment of the present application is illustrated, which uses a converter-based encoder model to perform context coding on a plurality of temperature values and a plurality of humidity values to obtain global temperature-related information, humidity-related information, and temperature-humidity-related information, and further performs fusion of the temperature data and the humidity data through likelihood maximization of gaussian distribution to train the converter-based encoder model and the classifier. Through the mode, whether the current temperature and humidity are reasonable or not can be judged more accurately, and further unreasonable temperature and humidity are adjusted, so that a suitable monitoring and recovery environment is provided for animals.
Exemplary System
Fig. 4 illustrates a block diagram of a control system of a smart device according to an embodiment of the application. As shown in fig. 4, a control system 400 of a smart device according to an embodiment of the present application includes: a training module 410 and an inference module 420.
As shown in fig. 4, the training module 410 includes: a training data obtaining unit 411, configured to obtain training data, where the training data are temperature data and humidity data at a series of time points at a predetermined time interval; an encoding unit 412, configured to perform context encoding on the temperature data and the humidity data at the series of time points obtained by the training data obtaining unit 411 by using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors; a gaussian distribution constructing unit 413 for constructing a sequence of gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors obtained by the encoding unit 412, wherein the variance and mean of each gaussian distribution in the sequence of gaussian distributions is obtained by calculating the corresponding temperature feature vector and humidity feature vector based on a likelihood maximization calculation principle and using a gaussian probability density value for adjusting data fusion; a gaussian discretization unit 414 for discretizing each gaussian distribution in the sequence of gaussian distributions obtained by the gaussian distribution constructing unit 413 to obtain a plurality of gaussian vectors; a two-dimensional stitching unit 415, configured to perform two-dimensional stitching on the plurality of gaussian vectors obtained by the gaussian discretization unit 414 to obtain a classification feature map; a classifier processing unit 416, configured to pass the classification feature map obtained by the two-dimensional stitching unit 415 through a classifier to obtain a classification loss function value; a gaussian density loss function value calculation unit 417 for calculating a gaussian density loss function value based on the gaussian probability density value; and a training unit 418 for calculating a weighted sum of the classification loss function value obtained by the classifier processing unit 416 and the gaussian density loss function value obtained by the gaussian density loss function value calculation unit 417 as a loss function value to train the converter-based encoder model and the classifier.
As shown in fig. 4, the inference module 420 includes: a data acquisition unit 421 for acquiring temperature data and humidity data at a series of time points of a predetermined time interval; a feature vector generating unit 422, configured to perform context coding on the temperature data and the humidity data at the series of time points obtained by the data obtaining unit 421 using the converter-based encoder model trained in the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors; a gaussian distribution sequence generating unit 423 for constructing a sequence of gaussian distributions of the sequence of temperature characteristic vectors and the sequence of humidity characteristic vectors obtained by the characteristic vector generating unit 422; a classification feature map generation unit 424, configured to perform discretization processing on each gaussian distribution in the sequence of gaussian distributions obtained by the gaussian distribution sequence generation unit 423 to obtain a plurality of gaussian vectors, and perform two-dimensional stitching on the plurality of gaussian vectors to obtain a classification feature map; and a classification unit 425 configured to pass the classification feature map obtained by the classification feature map generation unit 424 through a classifier to obtain a classification result indicating whether the current temperature and humidity are reasonable.
Here, it may be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the control system 400 of the smart device described above have been described in detail in the above description of the control method of the smart device with reference to fig. 1 to 3B, and thus, a repetitive description thereof will be omitted.
As described above, the control system 400 of the smart device according to the embodiment of the present application may be implemented in various terminal devices, such as a server of a control algorithm of the smart device, and the like. In one example, the control system 400 of the smart device according to the embodiment of the present application may be integrated into the terminal device as one software module and/or hardware module. For example, the control system 400 of the smart device may be a software module in the operating means of the terminal device, or may be an application developed for the terminal device; of course, the control system 400 of the smart device may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the control system 400 of the smart device and the terminal device may be separate devices, and the control system 400 of the smart device may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to an agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 5. As shown in fig. 5, the electronic device 10 includes one or more processors 11 and memory 12. The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus device and/or other form of connection mechanism (not shown).
The input device 13 may include, for example, a keyboard, a mouse, and the like.
The output device 14 can output various information including the classification result to the outside. The output devices 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 5, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and devices, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the functions in the control method of a smart device according to various embodiments of the present application described in the "exemplary methods" section of this specification above.
The computer program product may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages, for carrying out operations according to embodiments of the present application. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the control method of the smart device described in the "exemplary method" section above of this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations should be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. A control method of an intelligent device is characterized by comprising the following steps:
a training phase comprising:
acquiring training data, wherein the training data are temperature data and humidity data of a series of time points at a preset time interval;
context-coding the temperature data and the humidity data at the series of time points using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
constructing a sequence of Gaussian distributions of the sequence of the temperature characteristic vectors and the sequence of the humidity characteristic vectors, wherein the variance and the mean of each Gaussian distribution in the sequence of the Gaussian distributions are obtained by calculating the corresponding temperature characteristic vectors and humidity characteristic vectors based on a likelihood maximization calculation principle and by using Gaussian probability density values for adjusting data fusion;
discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors;
performing two-dimensional stitching on the plurality of Gaussian vectors to obtain a classification feature map;
passing the classification feature map through a classifier to obtain a classification loss function value;
calculating a gaussian density loss function value based on the gaussian probability density value; and
computing a weighted sum of the classification loss function value and the Gaussian density loss function value as a loss function value to train the converter-based encoder model and the classifier; and
an inference phase comprising:
acquiring temperature data and humidity data of a series of time points of a preset time interval;
context-coding the temperature data and the humidity data at the series of time points using the converter-based encoder model trained to be completed in the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
constructing a sequence of Gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors;
discretizing each Gaussian distribution in the sequence of Gaussian distributions to obtain a plurality of Gaussian vectors, and performing two-dimensional splicing on the Gaussian vectors to obtain a classification feature map; and
and passing the classification characteristic diagram through a classifier to obtain a classification result for indicating whether the current temperature and humidity are reasonable or not.
2. The control method of a smart device of claim 1, wherein context coding the temperature data and the humidity data for the series of time points using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors comprises:
converting each of the temperature data into a temperature input vector and each of the humidity data into a humidity input vector by an embedding unit of the encoder model;
inputting all of the temperature input vectors and all of the humidity input vectors into a converter of the encoder model to obtain the sequence of temperature feature vectors and the sequence of humidity feature vectors.
3. The control method of a smart device according to claim 2, wherein constructing the sequence of gaussian distributions of the sequence of temperature and humidity eigenvectors comprises:
calculating the mean and variance of each Gaussian distribution in the sequence of Gaussian distributions according to the following formula;
wherein 1 isN＝[1,1,…,1]And N isiIs a Gaussian probability density value used for adjusting data fusion.
4. The control method of a smart device of claim 3, wherein passing the classification signature through a classifier to obtain classification loss function values comprises:
performing full-join encoding on the classification feature map using a plurality of full-join layers of the classifier to obtain a classification feature vector;
inputting the classification feature vector into a Softmax classification function of the classifier to obtain a classification result; and
and calculating a cross entropy value between the classification result and the real value as the classification loss function value.
5. The control method of a smart device of claim 4, wherein calculating a Gaussian density loss function value based on the Gaussian probability density value comprises:
calculating the Gaussian density loss function value based on the Gaussian probability density value according to the following formula;
wherein the formula is:
6. the smart device control method of claim 5, wherein calculating a weighted sum of the classification loss function values and the Gaussian density loss function values as loss function values to train the converter-based encoder model and the classifier comprises:
in each iteration, the parameters of the encoder model are updated by back-propagation of the gradient descent with the loss function values, and then the parameters of the classifier are updated by back-propagation of the gradient descent with the loss function values.
7. A control system for a smart device, comprising:
a training module comprising:
the training data acquisition unit is used for acquiring training data, wherein the training data are temperature data and humidity data of a series of time points at a preset time interval;
an encoding unit configured to perform context encoding on the temperature data and the humidity data at the series of time points obtained by the training data obtaining unit using a converter-based encoder model to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
a gaussian distribution constructing unit configured to construct a sequence of gaussian distributions of the sequence of temperature feature vectors and the sequence of humidity feature vectors obtained by the encoding unit, wherein a variance and a mean of each gaussian distribution in the sequence of gaussian distributions are obtained by calculating corresponding temperature feature vectors and humidity feature vectors based on a likelihood maximization calculation principle and using gaussian probability density values for adjusting data fusion;
a gaussian discretization unit configured to discretize each gaussian distribution in the sequence of gaussian distributions obtained by the gaussian distribution constructing unit to obtain a plurality of gaussian vectors;
the two-dimensional splicing unit is used for performing two-dimensional splicing on the plurality of Gaussian vectors obtained by the Gaussian discretization unit to obtain a classification feature map;
the classifier processing unit is used for enabling the classification characteristic graph obtained by the two-dimensional splicing unit to pass through a classifier so as to obtain a classification loss function value;
a gaussian density loss function value calculation unit for calculating a gaussian density loss function value based on the gaussian probability density value; and
a training unit for calculating a weighted sum of the classification loss function value obtained by the classifier processing unit and the gaussian density loss function value obtained by the gaussian density loss function value calculation unit as a loss function value to train the converter-based encoder model and the classifier; and
an inference module comprising:
a data acquisition unit for acquiring temperature data and humidity data at a series of time points at predetermined time intervals;
a feature vector generation unit, configured to perform context coding on the temperature data and the humidity data at the series of time points obtained by the data acquisition unit using the converter-based encoder model trained in the training phase to obtain a sequence of temperature feature vectors and a sequence of humidity feature vectors;
a gaussian distribution sequence generating unit configured to construct a sequence of gaussian distributions of the sequence of temperature characteristic vectors and the sequence of humidity characteristic vectors obtained by the characteristic vector generating unit;
the classification characteristic map generation unit is used for carrying out discretization processing on each Gaussian distribution in the Gaussian distribution sequence obtained by the Gaussian distribution sequence generation unit to obtain a plurality of Gaussian vectors and carrying out two-dimensional splicing on the Gaussian vectors to obtain a classification characteristic map; and
and the classification unit is used for enabling the classification characteristic diagram obtained by the classification characteristic diagram generation unit to pass through a classifier so as to obtain a classification result which is used for indicating whether the current temperature and humidity are reasonable or not.
8. The control system of a smart device of claim 7, wherein the encoding unit is further configured to:
converting each of the temperature data into a temperature input vector and each of the humidity data into a humidity input vector by an embedding unit of the encoder model;
inputting all of the temperature input vectors and all of the humidity input vectors into a converter of the encoder model to obtain the sequence of temperature feature vectors and the sequence of humidity feature vectors.
9. The control system of the smart device of claim 7, wherein the Gaussian distribution construction unit is further configured to:
calculating the mean and variance of each Gaussian distribution in the sequence of Gaussian distributions according to the following formula;
wherein 1 isN＝[1,1,…,1]And N isiIs a Gaussian probability density value used for adjusting data fusion.
10. An electronic device, comprising:
a processor; and
memory in which computer program instructions are stored, which, when executed by the processor, cause the processor to carry out the method of controlling a smart device according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129871.8A CN114548246A (en) | 2022-02-11 | 2022-02-11 | Control method and system of intelligent device and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129871.8A CN114548246A (en) | 2022-02-11 | 2022-02-11 | Control method and system of intelligent device and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114548246A true CN114548246A (en) | 2022-05-27 |
Family
ID=81672716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210129871.8A Withdrawn CN114548246A (en) | 2022-02-11 | 2022-02-11 | Control method and system of intelligent device and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114548246A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116147130A (en) * | 2023-04-18 | 2023-05-23 | 杭州行至云起科技有限公司 | Intelligent home control system and method thereof |
| CN116866054A (en) * | 2023-07-25 | 2023-10-10 | 安徽百方云科技有限公司 | Public information safety monitoring system and method thereof |
| CN116870654A (en) * | 2023-07-10 | 2023-10-13 | 滁州锡安环保科技有限责任公司 | Industrial waste gas treatment system and method thereof |
| CN116893336A (en) * | 2023-07-11 | 2023-10-17 | 浙江和能电力设备有限公司 | High-low voltage switching device and method thereof |
| WO2024000800A1 (en) * | 2022-06-30 | 2024-01-04 | 福建省龙德新能源有限公司 | Energy management control system for preparation of lithium hexafluorophosphate and control method therefor |
| CN116870654B (en) * | 2023-07-10 | 2024-06-07 | 广东源锦自动化科技有限公司 | Industrial waste gas treatment system and method thereof |
-
2022
- 2022-02-11 CN CN202210129871.8A patent/CN114548246A/en not_active Withdrawn
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024000800A1 (en) * | 2022-06-30 | 2024-01-04 | 福建省龙德新能源有限公司 | Energy management control system for preparation of lithium hexafluorophosphate and control method therefor |
| CN116147130A (en) * | 2023-04-18 | 2023-05-23 | 杭州行至云起科技有限公司 | Intelligent home control system and method thereof |
| CN116870654A (en) * | 2023-07-10 | 2023-10-13 | 滁州锡安环保科技有限责任公司 | Industrial waste gas treatment system and method thereof |
| CN116870654B (en) * | 2023-07-10 | 2024-06-07 | 广东源锦自动化科技有限公司 | Industrial waste gas treatment system and method thereof |
| CN116893336A (en) * | 2023-07-11 | 2023-10-17 | 浙江和能电力设备有限公司 | High-low voltage switching device and method thereof |
| CN116893336B (en) * | 2023-07-11 | 2024-04-02 | 宁夏隆基电气有限公司 | High-low voltage switching device and method thereof |
| CN116866054A (en) * | 2023-07-25 | 2023-10-10 | 安徽百方云科技有限公司 | Public information safety monitoring system and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114548246A (en) | Control method and system of intelligent device and electronic device | |
| CN115796173B (en) | Data processing method and system for supervising reporting requirements | |
| CN111860588A (en) | Training method for graph neural network and related equipment | |
| CN115783923B (en) | Elevator fault mode identification system based on big data | |
| CN115171317A (en) | Internet of things smart home method and system and electronic equipment | |
| CN116015837A (en) | Intrusion detection method and system for computer network information security | |
| CN116247824B (en) | Control method and system for power equipment | |
| KR20190078899A (en) | Visual Question Answering Apparatus Using Hierarchical Visual Feature and Method Thereof | |
| CN111797589A (en) | Text processing network, neural network training method and related equipment | |
| CN114092972A (en) | Intelligent peep-proof electronic equipment display method and system and electronic equipment | |
| CN117077075A (en) | Water quality monitoring system and method for environmental protection | |
| JPWO2019229931A1 (en) | Information processing equipment, control methods, and programs | |
| CN116307624A (en) | Resource scheduling method and system of ERP system | |
| CN110533184B (en) | Network model training method and device | |
| CN116759053A (en) | Medical system prevention and control method and system based on Internet of things system | |
| CN116092701A (en) | Control system and method based on health data analysis management platform | |
| CN116629211B (en) | Writing method and system based on artificial intelligence | |
| CN115862151B (en) | Data processing system and method for predicting response capability of old people based on game | |
| CN116759047A (en) | Data intelligent monitoring system and method for hemodialysis | |
| CN115661758A (en) | Public place crowd density monitoring method and system based on artificial intelligence | |
| CN115510900A (en) | Automatic circuit fault diagnosis method and system | |
| CN111126566A (en) | Abnormal furniture layout data detection method based on GAN model | |
| CN112489044A (en) | Graphene electrothermal film contact detection method for heating device | |
| CN115993507B (en) | Fault distance measurement method of electrified railway traction power supply system | |
| CN113393934B (en) | Health trend estimation method and prediction system based on vital sign big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220527 |