CN110631221A - Control method and device of air conditioner, terminal and storage medium - Google Patents
Control method and device of air conditioner, terminal and storage medium Download PDFInfo
- Publication number
- CN110631221A CN110631221A CN201810569971.6A CN201810569971A CN110631221A CN 110631221 A CN110631221 A CN 110631221A CN 201810569971 A CN201810569971 A CN 201810569971A CN 110631221 A CN110631221 A CN 110631221A
- Authority
- CN
- China
- Prior art keywords
- information
- air conditioner
- parameter adjustment
- adjustment information
- sample
- 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.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
Abstract
The invention discloses a control method, a control device, a control terminal and a storage medium of an air conditioner, wherein the method comprises the following steps: acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user; inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information; and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information. According to the invention, the user operation is reduced, the time is saved, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of smart home, in particular to a control method and device of an air conditioner, a terminal and a storage medium.
Background
The air conditioner can adjust and control the temperature of the indoor ambient air, and when the air conditioner adjusts and controls the indoor ambient air to different degrees, the corresponding working state and working parameters are different. The working parameter information of the air conditioner in different states is mainly manually set by a user, and after the setting of the user is completed, the air conditioner controls each parameter through a set control logic which is stored in advance by an air conditioner technician, so that the working of the air conditioner is realized.
However, the conventional air conditioner is mainly controlled by a user manually during adjustment, and the user cannot achieve a good comfort level after once adjustment, so that multiple adjustments may be needed, the operation is complicated, the time is wasted, and the user experience is reduced.
Disclosure of Invention
The invention provides a control method, a control device, a control terminal and a storage medium of an air conditioner, which are used for solving the problems that in the prior art, manual adjustment operation of a user is complicated, time is wasted, and user experience is reduced.
The invention provides a control method of an air conditioner, which is applied to a terminal and comprises the following steps:
acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information;
and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information.
Further, the physical state information includes at least one of: the accumulated step number of the air conditioner user in a set time length, the heart rate of the air conditioner user and the mood index of the air conditioner user.
Further, before the obtaining of the target parameter adjustment information, the method further includes:
judging whether the intelligent mode of the air conditioner is started currently;
if yes, the subsequent steps are carried out.
Further, the training process of the equipment control model comprises the following steps:
acquiring sample working parameter information set by a user corresponding to each sample parameter adjustment information aiming at each sample parameter adjustment information in a training set;
according to the obtained sample parameter adjustment information and sample working parameter information corresponding to the sample parameter adjustment information, inputting the sample parameter adjustment information into an equipment control model, obtaining candidate working parameter information corresponding to the sample parameter adjustment information, and performing iterative training on the equipment control model.
Further, if the equipment control model is trained based on a neural network, iteratively training the equipment control model comprises:
after the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information enter a network from an input layer in an equipment control model, determining the output value of each neuron in the input layer in the candidate working parameter information corresponding to the sample parameter adjustment information;
forward the sample parameter adjustment information and the output value of each neuron to a hidden layer in an equipment control model;
the hidden layer determines an error item value of each neuron according to the stored weight value of the layer of each neuron at the current moment and the output value of each neuron;
an output layer in the equipment control model determines a weight gradient corresponding to the error term value of each neuron and judges whether the weight gradient of each neuron is smaller than a set gradient threshold value or not;
if not, updating the weight value of the layer of each neuron at the current moment, which is stored in the equipment control model, according to the weight gradient of each neuron;
if so, determining that the iterative training is completed.
Further, before the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information enter the network from the input layer in the equipment control model, the method further includes:
and inputting the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information into a forgetting gate in an equipment control model, wherein the forgetting gate reserves candidate working parameter sub-information in the candidate working parameter information according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and updates the candidate working parameter information into the candidate working parameter sub-information.
Further, after the target operating parameter information is sent to the air conditioner, the method further includes:
judging whether a work parameter information adjusting operation of a user sent by the air conditioner is received, wherein the work parameter information adjusting operation carries the adjusted work parameter information;
and if so, correcting the equipment control model according to the adjusted working parameter information.
The invention provides a control device of an air conditioner, which is applied to a terminal and comprises:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring target parameter adjustment information, and the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
the determining module is used for inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information;
and the control module is used for sending the target working parameter information to the air conditioner so that the air conditioner works according to the target working parameter information.
Further, the physical state information includes at least one of: the accumulated step number of the air conditioner user in a set time length, the heart rate of the air conditioner user and the mood index of the air conditioner user.
Further, the apparatus further comprises:
the judging module is used for judging whether the intelligent mode of the air conditioner is started at present; if yes, triggering the acquisition module.
Further, the apparatus further comprises:
the training module is used for acquiring sample working parameter information set by an air conditioner user corresponding to each sample parameter adjustment information aiming at each sample parameter adjustment information in a training set; according to the obtained sample parameter adjustment information and sample working parameter information corresponding to the sample parameter adjustment information, inputting the sample parameter adjustment information into an equipment control model, obtaining candidate working parameter information corresponding to the sample parameter adjustment information, and performing iterative training on the equipment control model.
Further, if the equipment control model is trained based on a neural network, the training module is specifically configured to determine an output value of each neuron in an input layer in the equipment control model after the sample parameter adjustment information and candidate working parameter information corresponding to the sample parameter adjustment information enter the network from the input layer; forward the sample parameter adjustment information and the output value of each neuron to a hidden layer in an equipment control model; the hidden layer determines an error item value of each neuron according to the stored weight value of the layer of each neuron at the current moment and the output value of each neuron; an output layer in the equipment control model determines a weight gradient corresponding to the error term value of each neuron and judges whether the weight gradient of each neuron is smaller than a set gradient threshold value or not; if not, updating the weight value of the layer of each neuron at the current moment, which is stored in the equipment control model, according to the weight gradient of each neuron; if so, determining that the iterative training is completed.
Further, the training module is further configured to input the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information into a forgetting gate in the equipment control model before the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information enter the network from an input layer in the equipment control model, where the forgetting gate reserves the candidate working parameter sub-information in the candidate working parameter information according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and updates the candidate working parameter information into the candidate working parameter sub-information.
Further, the apparatus further comprises:
the correction module is used for judging whether the adjustment operation of the working parameter information of the user sent by the air conditioner is received or not after the target working parameter information is sent to the air conditioner, wherein the adjustment operation of the working parameter information carries the adjusted working parameter information; and if so, correcting the equipment control model according to the adjusted working parameter information.
The invention provides a terminal which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for finishing mutual communication by the memory through the communication bus;
the memory has stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of any of the methods described above.
The invention provides a computer-readable storage medium having stored therein a computer program which, when executed by a processor, performs the method steps of any of the above.
The invention provides a control method, a control device, a control terminal and a storage medium of an air conditioner, wherein the method comprises the following steps: acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user; inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information; and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information. According to the method and the device, the terminal can acquire the target parameter adjustment information comprising at least one of the data of the external environment where the air conditioner is located and the body state information of the user corresponding to the air conditioner, the target working parameter information corresponding to the target parameter adjustment information is determined according to the pre-trained equipment control model, and the air conditioner is controlled to work according to the target working parameter information, so that the air conditioner can be accurately controlled, the user operation is reduced, the time is saved, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of a control process of an air conditioner according to example 1 of the present invention;
fig. 2 is a schematic structural diagram of an LSTM neural network according to embodiment 4 of the present invention;
fig. 3 is a schematic diagram of a model training process provided in embodiment 4 of the present invention;
fig. 4 is a schematic diagram of a control process of an air conditioner according to example 6 of the present invention;
fig. 5 is a schematic structural diagram of a terminal according to embodiment 7 of the present invention;
fig. 6 is a schematic diagram of a control device of an air conditioner according to an embodiment of the present invention.
Detailed Description
In order to reduce user operation, save time and improve user experience, embodiments of the present invention provide a method and an apparatus for controlling an air conditioner, an electronic device, and a storage medium.
The control method of the air conditioner provided by the embodiment of the invention can be applied to a terminal, and the terminal comprises a hardware layer, an operating system layer running on the hardware layer and an application layer running on the operating system.
The hardware layer includes hardware such as a Central Processing Unit (CPU), a Memory Management Unit (MMU), and a Memory.
The operating system may be any one or more computer operating systems that implement folder merging by a Process (Process), such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system. The application layer can display applications, and the applications can be preset system applications or newly added applications for users.
In the embodiment of the present invention, the terminal may be a handheld device such as a smart phone and a tablet computer, or a terminal device such as a desktop computer and a portable computer, which is not particularly limited in the embodiment of the present invention, as long as the control of the air conditioner can be realized by running a program in which a code of the control method of the air conditioner in the embodiment of the present invention is recorded.
The execution main body of the control of the air conditioner in the embodiment of the present invention may be a terminal, or a functional module capable of calling a program and executing the program in the terminal.
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
fig. 1 is a schematic diagram of a control process of an air conditioner according to an embodiment of the present invention, where the process includes the following steps:
s101: acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user.
The control method of the air conditioner provided by the embodiment of the invention is applied to the terminal, the terminal can acquire the target parameter adjustment information, and the target parameter adjustment information can be data of the external environment where the air conditioner is located, body state information of an air conditioner user, external environment data where the air conditioner is located and body state information of the air conditioner user.
The data of the external environment at the air conditioner place that this terminal acquireed can be the external environment data that the sensor according to the air conditioner installation was gathered, can be terminal connection server, the weather information of the air conditioner place that inquires, the external environment's at air conditioner place data is relevant with the function of air conditioner, includes the temperature at least, if the air conditioner still has the function dehumidification and air-purifying, then the external environment's at air conditioner place data should still include at least: humidity and air quality.
The body state information of the air conditioner user acquired by the terminal may be body state information acquired through intelligent home single items such as intelligent wearable equipment used by the air conditioner user, body state information acquired through a user terminal used by the air conditioner user, and body state information input into the terminal by the air conditioner user.
The information of the air conditioner user can be stored in the terminal, and the information of the air conditioner user can be information of an intelligent household single product or a user terminal used by the air conditioner user.
The physical state information includes at least one of: the accumulated step number of the air conditioner user in a set time length, the heart rate of the air conditioner user and the mood index of the air conditioner user.
The set time period may be any time period, such as 1 hour or 1 day. The mood index of the user may be related to the current weather, such as a low mood index of the user in cloudy days, a high mood index of the user in sunny days.
S102: inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information.
The terminal stores the equipment control model trained according to the sample parameter adjustment information and the sample working parameter information, so that the target working parameter information corresponding to the target parameter adjustment information can be determined according to the target parameter adjustment information and based on the trained equipment control model.
This equipment control model that training was accomplished can be for the equipment control model that learns in advance to the use of air conditioner according to this air conditioner user, can be for the equipment control module that big user was confirmed to the use of air conditioner under the big data analysis, can be for the use to the air conditioner according to the user, revise back equipment control model in real time.
The target operating parameter information is related to the function of the air conditioner, and at least comprises a startup and shutdown function, an operating mode and an operating temperature, wherein the operating mode comprises cooling and heating, and wind speed, and if the air conditioner also has the functions of dehumidifying and purifying air, the target operating parameter information at least comprises: dehumidification gear and air purification intensity.
S103: and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information.
And after determining the target working parameter information output in the equipment control model, the terminal sends the target working parameter information to the air conditioner so that the air conditioner works according to the target working parameter information.
According to the embodiment of the invention, the terminal can acquire the target parameter adjustment information comprising at least one item of data of the external environment where the air conditioner is located and the body state information of the user corresponding to the air conditioner, and the target working parameter information corresponding to the target parameter adjustment information is determined according to the pre-trained equipment control model, so that the air conditioner is controlled to work according to the target working parameter information, the accurate control of the air conditioner can be realized, the user operation is reduced, the time is saved, and the user experience is improved.
Example 2:
on the basis of the foregoing embodiment, in an embodiment of the present invention, before the obtaining the target parameter adjustment information, the method further includes:
judging whether the intelligent mode of the air conditioner is started currently;
if yes, the subsequent steps are carried out.
When the air conditioner user uses the air conditioner, if the air conditioner user opens the intelligent mode of the air conditioner, the target parameter adjustment information is obtained again, the target parameter adjustment information is input into the equipment control model, and the target working parameter information corresponding to the target parameter adjustment information is determined, so that the air conditioner can be controlled according to different use requirements of the air conditioner user, and the user experience is further improved.
If the air conditioner recognizes that the air conditioner user opens the intelligent mode of the air conditioner, the air conditioner can send information that the air conditioner user has opened the intelligent mode to the terminal to inform the terminal that the air conditioner user has opened the intelligent mode.
Certainly, the working parameter information of the air conditioner in the non-intelligent mode is manually adjusted by an air conditioner user, at the moment, the air conditioner can send the working parameter information manually adjusted by the air conditioner user to the terminal, and the terminal corrects the trained equipment control model according to the working parameter information manually adjusted by the air conditioner user and the acquired parameter adjustment information.
According to the embodiment of the invention, the air conditioner can be controlled according to different use requirements of an air conditioner user, and the user experience is further improved.
Example 3:
in order to implement training of an equipment control model, on the basis of the above embodiments, in an embodiment of the present invention, a training process of the equipment control model includes:
acquiring sample working parameter information set by an air conditioner user corresponding to each sample parameter adjustment information aiming at each sample parameter adjustment information in a training set;
according to the obtained sample parameter adjustment information and sample working parameter information corresponding to the sample parameter adjustment information, inputting the sample parameter adjustment information into an equipment control model, obtaining candidate working parameter information corresponding to the sample parameter adjustment information, and performing iterative training on the equipment control model.
The equipment control model in the embodiment of the invention can be a model based on neural network training.
Specifically, the training set includes a large amount of sample parameter adjustment information, the sample parameter adjustment information included in the training set is a sample used for model training, and for each sample parameter adjustment information in the training set, the terminal acquires sample working parameter information set by an air conditioner user corresponding to the sample parameter adjustment information.
The target parameter adjustment information to be acquired when the air conditioner is controlled should be consistent with the data type included in the sample parameter adjustment information in the training set of the equipment control model during training, and if the sample parameter adjustment information in the training set during training of the equipment control model includes the data of the external environment where the air conditioner is located and the body state information of the air conditioner user, the target parameter adjustment information to be acquired when the air conditioner is controlled should also include the data of the external environment where the air conditioner is located and the body state information of the air conditioner user.
And carrying out iterative training on the equipment control model through back propagation calculation according to the acquired sample working parameter information set by the air conditioner user corresponding to each sample parameter adjustment information.
In the process of training the equipment control model, preliminary iterative judgment can be carried out on candidate working parameter information corresponding to sample parameter adjustment information output by the equipment control model and sample working parameter information set by an air conditioner user corresponding to the sample parameter adjustment information, and specifically, a corresponding loss function output value can be determined for each sample parameter adjustment information, the sample working parameter information corresponding to the sample parameter adjustment information and a loss function of the equipment control model; judging whether the output value of the loss function is smaller than a preset value or not; if so, determining that the iterative training is finished, and if not, continuing the iterative training.
If the equipment control model is learned in advance, in the process of learning in advance, the air conditioner user sets the air conditioner mode by himself and continuously sets a period, the period is usually one week, the data of the current intelligent household single product used by the air conditioner user, namely the body state information of the air conditioner user, and the operation data of the air conditioner, namely the data of the external environment are transmitted to the cloud end on a chip or transmitted to the cloud end, and the processed original data are used as the input of the algorithm. And (3) predicting by using a previously added algorithm on the chip or the cloud, and outputting an air conditioner setting mode at the current moment, namely the working parameter information of the air conditioner when an air conditioner user starts an air conditioner intelligent mode.
According to the embodiment of the invention, the equipment control model is trained, so that the air conditioner can be accurately controlled according to the trained equipment control model when the air conditioner is controlled.
Example 4:
on the basis of the foregoing embodiments, in an embodiment of the present invention, if the equipment control model is trained based on a neural network, the iteratively training the equipment control model includes:
after the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information enter a network from an input layer in an equipment control model, determining the output value of each neuron in the input layer in the candidate working parameter information corresponding to the sample parameter adjustment information;
forward the sample parameter adjustment information and the output value of each neuron to a hidden layer in an equipment control model;
the hidden layer determines an error item value of each neuron according to the stored weight value of the layer of each neuron at the current moment and the output value of each neuron;
an output layer in the equipment control model determines a weight gradient corresponding to the error term value of each neuron and judges whether the weight gradient of each neuron is smaller than a set gradient threshold value or not;
if not, updating the weight value of the layer of each neuron at the current moment, which is stored in the equipment control model, according to the weight gradient of each neuron;
if so, determining that the iterative training is completed.
When the control device model is trained based on the neural Network, the control device model may be based on any neural Network such as LSTM (Long Short-Term Memory), RNN (Recurrent neural Network), and the like, which is not limited herein.
In the following, the control device model is trained based on LSTM as an example for detailed description, and it is believed that those skilled in the art can achieve the same model training effect by using other neural networks in combination with the model training process provided by the embodiment of the present invention, and details are not described herein.
As shown in fig. 2, which is a schematic diagram of a neural network structure of LSTM, each box represents an LSTM at a different time, four small boxes marked in each box represent four parts under the LSTM at the same time, and the neural network is a feedforward type neural network, time t represents a current time, t-1 represents a previous time of the current time, and t +1 represents a next time of the current time.
The feedforward type neural network is composed of at least an input layer itHidden layer, output layer otThe sample data in the training set is composed of input layerAnd the output layer judges whether the model training is finished according to the output value of the hidden layer, and the model output determined by the output layer is iterated back to enter the input layer to continue the model training process.
When the sample data of the training set is networked by the input layer, the first training may be the sample parameter adjustment information and the default candidate working parameter information corresponding to the sample parameter adjustment information (x shown in fig. 2)t) The output value of each neuron in the input layer is determined in the candidate working parameter information corresponding to the sample parameter adjustment information, and the output value of each neuron can be understood as sub-information of the candidate working parameter information. The process of calculating the output value of each neuron in the input layer in the forward direction belongs to the prior art, and is not described herein.
After the output value of each neuron in the input layer is determined, the hidden layer reversely calculates the error term value of each neuron, and the back propagation comprises two directions: the method comprises the steps of firstly, reversely propagating along time, calculating an error item at each moment from the current moment t, and secondly, propagating the error item to the upper layer, namely, determining the error item value of each neuron according to the stored weight value of each neuron on the layer where the current moment is located and the target working parameter sub-information of each neuron. The process of calculating the error term value of each neuron in reverse belongs to the prior art, and is not described herein.
After the error item value of each neuron is determined, the output layer calculates the gradient of each weighted value according to the corresponding error item value, updates the weighted value according to the gradient, namely determines the weighted gradient corresponding to the error item value of each neuron, judges whether the weighted gradient of each neuron is smaller than a set gradient threshold value, if not, updates the weighted value of the layer where each neuron is located at the current moment according to the weighted gradient of each neuron, and if so, determines that the iterative training is completed. The process of calculating the gradient of each weight value according to the error term value and updating the weight values belongs to the prior art, and is not described herein.
As can be seen from the above, the training process may be a process of training the weight values of each neuron at different layers at different times, and is a process of iteratively updating the weight values. The first update process is a process of updating the initial weight value.
A process schematic diagram in a model training process is shown in fig. 3, when training is performed for the first time and later, a hidden layer i represents an i-th hidden layer, information input into the hidden layer includes output at the last moment, current input parameter 1, current input parameter 2, current input parameter 3, current input parameter 4, current input parameter 5 and the like, wherein the output at the last moment is target working parameter sub-information of each neuron determined by the input layer according to candidate working parameter information output by the output layer at the last moment, and the current input parameter 1, the current input parameter 2, the current input parameter 3, the current input parameter 4, the current input parameter 5 and the like are sample parameter adjustment information in a training set. Candidate working parameter information output by the output layer at the current moment is obtained through calculation of the hidden layer and the output layer, and the candidate working parameter information comprises information used for controlling an air conditioner, such as temperature, an operation mode, startup and shutdown, wind speed and the like.
According to the embodiment of the invention, the equipment control model is adjusted through the output result of each training, so that the accuracy in the air conditioner control process is further improved.
Example 5:
on the basis of the foregoing embodiments, in an embodiment of the present invention, before entering the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information into a network from an input layer in an equipment control model, the method further includes:
and inputting the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information into a forgetting gate in an equipment control model, wherein the forgetting gate reserves candidate working parameter sub-information in the candidate working parameter information according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and updates the candidate working parameter information into the candidate working parameter sub-information.
As shown in FIG. 2, the LSTM at each moment is further provided with a forgetting gate f during the training process to achieve the effect of further accurate controltThe data input into the input layer is preprocessed.
The sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information are input to a forgetting gate in the equipment control model, and the forgetting gate is used for determining whether the newly generated candidate working parameter information is useful currently, so that the candidate working parameter sub-information is reserved in the candidate working parameter information according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and the candidate working parameter sub-information is input to an input layer as the candidate working parameter information, namely the information input in the input layer can be the processed candidate working parameter information corresponding to the sample parameter adjustment information.
Specifically, the forgetting gate may generate a value passing through 0 to 1 according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and determine whether to retain information of the candidate working parameter information according to a comparison relationship between the value and a preset value, and if so, which information of the candidate working parameter information needs to be retained, so that in the embodiment of the present invention, the candidate working parameter sub-information may be partial information or all information of the candidate working parameter information, or the candidate working parameter sub-information may be empty.
When the input gate works, the excitation function sigmoid is used for determining which values are used for updating, the excitation function tanh is used for generating a new candidate value, the two parts are combined to determine the output value of each neuron in the input layer, so that the hidden layer determines an error term value according to the output value of each neuron, and the output layer determines whether iterative training is completed.
When the output layer works, whether iterative training is finished is determined, and the method also comprises the step of firstly passing through a stimulus function sigmoid, scaling the input value by a stimulus function tanh, and calculating with a stimulus function sigmoid to determine the working parameter information (shown as h in FIG. 2) corresponding to the sample parameter adjustment information at the current timet). The excitation function sigmoid is denoted by σ and the excitation function tanh is denoted by tanh as shown in fig. 2.
In the embodiment of the invention, the forgetting gate is adopted to preprocess the data input into the input layer, thereby further achieving the effect of accurate control.
Example 6:
on the basis of the foregoing embodiments, in an embodiment of the present invention, after the sending the target operating parameter information to the air conditioner, the method further includes:
judging whether a work parameter information adjusting operation of an air conditioner user sent by the air conditioner is received, wherein the work parameter information adjusting operation carries adjusted work parameter information;
and if so, correcting the equipment control model according to the adjusted working parameter information.
The air conditioner carries out the back of working according to the target working parameter information that the terminal sent, the air conditioner user can also adjust the working parameter information of air conditioner according to self demand and custom, if need the adjustment, the air conditioner user can carry out the working parameter information adjustment operation to the air conditioner, the working parameter information adjustment operation carries the working parameter information after the adjustment, if yes, the air conditioner sends the air conditioner user's working parameter information adjustment operation to the terminal, the terminal is according to the working parameter information after the adjustment, continue study and revise the equipment control model of current saving, thereby make the equipment control model after the revision, when carrying out air conditioning control, can be better satisfy the air conditioner user demand, provide more comfortable environment for the air conditioner user.
And if the air conditioner does not start the intelligent mode, the terminal can correct the equipment control model in real time according to the manual setting of the air conditioner user.
As shown in fig. 4, when the air conditioner user uses the air conditioner, if the intelligent mode is turned on, the data of sensing the physical state data of the air conditioner user and inquiring the weather condition of the location of the user of the current smart home are transmitted to the chip or the cloud, algorithm learning is performed by combining the data of each mode set by using the air conditioner last time, and the real-time state output of the algorithm is used as the basis for setting each mode of the air conditioner; taking the algorithm learning and output as the next round of input; if the air conditioner user does not start the intelligent mode, each mode of the air conditioner is set directly according to the air conditioner user, and the set mode of the time is transmitted to the cloud end to be used as the input of the next round of algorithm. According to the above, each time the intelligent mode is used, the mode of the air conditioner is set according to the historical data, the current environmental change and the current physical condition of the user of the air conditioner, and when the set mode is not used, the air conditioner can record the new mode running state.
Example 7:
on the basis of the foregoing embodiments, an embodiment of the present invention further provides a terminal, as shown in fig. 5, including: the system comprises a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory 503 are communicated with each other through the communication bus 504;
the memory 503 has stored therein a computer program which, when executed by the processor 501, causes the processor 501 to perform the steps of:
acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information;
and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface 502 is used for communication between the above-described terminal and other devices.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a central processing unit, a Network Processor (NP), and the like; but may also be a Digital instruction processor (DSP), an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.
In the embodiment of the invention, when the processor executes the program stored in the memory, the target parameter adjustment information including at least one of the data of the external environment where the air conditioner is located and the body state information of the user corresponding to the air conditioner is obtained, the target working parameter information corresponding to the target parameter adjustment information is determined according to the pre-trained equipment control model, and the air conditioner is controlled to work according to the target working parameter information, so that the air conditioner can be accurately controlled, the user operation is reduced, the time is saved, and the user experience is improved.
Example 8:
on the basis of the foregoing embodiments, an embodiment of the present invention further provides a computer storage readable storage medium, in which a computer program executable by a terminal is stored, and when the program is run on the terminal, the terminal is caused to execute the following steps:
acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information;
and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information.
The above-mentioned computer readable storage medium may be any available medium or data storage device that can be accessed by a processor in a terminal, including but not limited to magnetic memory such as a flexible disk, a hard disk, magnetic tape, magneto-optical disk (MO), etc., optical memory such as CD, DVD, BD, HVD, etc., and semiconductor memory such as ROM, EPROM, EEPROM, nonvolatile memory (NANDFLASH), Solid State Disk (SSD), etc.
The computer readable storage medium provided in the embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, the computer program obtains target parameter adjustment information including at least one of data of an external environment where an air conditioner is located and body state information of a user corresponding to the air conditioner, determines target working parameter information corresponding to the target parameter adjustment information according to a pre-trained device control model, and controls the air conditioner to work according to the target working parameter information, so that accurate control of the air conditioner can be achieved, user operation is reduced, time is saved, and user experience is improved.
Fig. 6 is a schematic diagram of a control apparatus 600 of an air conditioner according to an embodiment of the present invention, applied to a terminal, the apparatus including:
an obtaining module 601, configured to obtain target parameter adjustment information, where the target parameter adjustment information includes at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
a determining module 602, configured to input the target parameter adjustment information into a pre-trained device control model, and determine, based on the device control model, target working parameter information corresponding to the target parameter adjustment information, where the device control model is trained according to sample parameter adjustment information and sample working parameter information;
and the control module 603 is configured to send the target operating parameter information to the air conditioner, so that the air conditioner operates according to the target operating parameter information.
The physical state information includes at least one of: the accumulated step number of the air conditioner user in a set time length, the heart rate of the air conditioner user and the mood index of the air conditioner user.
The device further comprises:
a judging module 604, configured to judge whether the air conditioner currently has the intelligent mode turned on; if so, the acquisition module 601 is triggered.
The device further comprises:
the training module 605 is configured to obtain, for each sample parameter adjustment information in the training set, sample working parameter information set by an air conditioner user corresponding to each sample parameter adjustment information; according to the obtained sample parameter adjustment information and sample working parameter information corresponding to the sample parameter adjustment information, inputting the sample parameter adjustment information into an equipment control model, obtaining candidate working parameter information corresponding to the sample parameter adjustment information, and performing iterative training on the equipment control model.
If the equipment control model is trained based on a neural network, the training module 605 is specifically configured to determine an output value of each neuron in an input layer in the equipment control model after the sample parameter adjustment information and candidate working parameter information corresponding to the sample parameter adjustment information enter the network from the input layer in the equipment control model; forward the sample parameter adjustment information and the output value of each neuron to a hidden layer in an equipment control model; the hidden layer determines an error item value of each neuron according to the stored weight value of the layer of each neuron at the current moment and the output value of each neuron; an output layer in the equipment control model determines a weight gradient corresponding to the error term value of each neuron and judges whether the weight gradient of each neuron is smaller than a set gradient threshold value or not; if not, updating the weight value of the layer of each neuron at the current moment, which is stored in the equipment control model, according to the weight gradient of each neuron; if so, determining that the iterative training is completed.
The training module 605 is further configured to input the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information into a forgetting gate in the equipment control model before the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information enter the network from an input layer in the equipment control model, where the forgetting gate reserves candidate working parameter sub-information in the candidate working parameter information according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and updates the candidate working parameter information into the candidate working parameter sub-information.
The device further comprises:
a correction module 606, configured to determine whether a working parameter information adjustment operation of a user sent by the air conditioner is received after the target working parameter information is sent to the air conditioner, where the working parameter information adjustment operation carries adjusted working parameter information; and if so, correcting the equipment control model according to the adjusted working parameter information.
According to the embodiment of the invention, the terminal can acquire the target parameter adjustment information comprising at least one item of data of the external environment where the air conditioner is located and the body state information of the user corresponding to the air conditioner, and the target working parameter information corresponding to the target parameter adjustment information is determined according to the pre-trained equipment control model, so that the air conditioner is controlled to work according to the target working parameter information, the accurate control of the air conditioner can be realized, the user operation is reduced, the time is saved, and the user experience is improved.
For the system/apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (16)
1. A control method of an air conditioner is applied to a terminal, and the method comprises the following steps:
acquiring target parameter adjustment information, wherein the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information;
and sending the target working parameter information to the air conditioner, so that the air conditioner works according to the target working parameter information.
2. The method of claim 1, wherein the physical state information comprises at least one of: the accumulated step number of the air conditioner user in a set time length, the heart rate of the air conditioner user and the mood index of the air conditioner user.
3. The method of claim 1, wherein prior to obtaining the target parameter adjustment information, the method further comprises:
judging whether the intelligent mode of the air conditioner is started currently;
if yes, the subsequent steps are carried out.
4. The method of claim 1, wherein the training process of the plant control model comprises:
acquiring sample working parameter information set by an air conditioner user corresponding to each sample parameter adjustment information aiming at each sample parameter adjustment information in a training set;
according to the obtained sample parameter adjustment information and sample working parameter information corresponding to the sample parameter adjustment information, inputting the sample parameter adjustment information into an equipment control model, obtaining candidate working parameter information corresponding to the sample parameter adjustment information, and performing iterative training on the equipment control model.
5. The method of claim 4, wherein if the plant control model is trained based on a neural network, the iteratively training the plant control model comprises:
after the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information enter a network from an input layer in an equipment control model, determining the output value of each neuron in the input layer in the candidate working parameter information corresponding to the sample parameter adjustment information;
forward the sample parameter adjustment information and the output value of each neuron to a hidden layer in an equipment control model;
the hidden layer determines an error item value of each neuron according to the stored weight value of the layer of each neuron at the current moment and the output value of each neuron;
an output layer in the equipment control model determines a weight gradient corresponding to the error term value of each neuron and judges whether the weight gradient of each neuron is smaller than a set gradient threshold value or not;
if not, updating the weight value of the layer of each neuron at the current moment, which is stored in the equipment control model, according to the weight gradient of each neuron;
if so, determining that the iterative training is completed.
6. The method of claim 5, wherein before entering the sample parameter adjustment information and the candidate operating parameter information corresponding to the sample parameter adjustment information into a network from an input layer in an equipment control model, the method further comprises:
and inputting the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information into a forgetting gate in an equipment control model, wherein the forgetting gate reserves candidate working parameter sub-information in the candidate working parameter information according to the sample parameter adjustment information and the candidate working parameter information corresponding to the sample parameter adjustment information, and updates the candidate working parameter information into the candidate working parameter sub-information.
7. The method of any one of claims 1-6, wherein after sending the target operating parameter information to the air conditioner, the method further comprises:
judging whether a work parameter information adjusting operation of an air conditioner user sent by the air conditioner is received, wherein the work parameter information adjusting operation carries adjusted work parameter information;
and if so, correcting the equipment control model according to the adjusted working parameter information.
8. A control device of an air conditioner, applied to a terminal, the device comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring target parameter adjustment information, and the target parameter adjustment information comprises at least one of data of an external environment where an air conditioner is located and body state information of an air conditioner user;
the determining module is used for inputting the target parameter adjustment information into a pre-trained equipment control model, and determining target working parameter information corresponding to the target parameter adjustment information based on the equipment control model, wherein the equipment control model is trained according to sample parameter adjustment information and sample working parameter information;
and the control module is used for sending the target working parameter information to the air conditioner so that the air conditioner works according to the target working parameter information.
9. The apparatus of claim 8, wherein the physical state information comprises at least one of: the accumulated step number of the air conditioner user in a set time length, the heart rate of the air conditioner user and the mood index of the air conditioner user.
10. The apparatus of claim 8, wherein the apparatus further comprises:
the judging module is used for judging whether the intelligent mode of the air conditioner is started at present; if yes, triggering the acquisition module.
11. The apparatus of claim 8, wherein the apparatus further comprises:
the training module is used for acquiring sample working parameter information set by an air conditioner user corresponding to each sample parameter adjustment information aiming at each sample parameter adjustment information in a training set; according to the obtained sample parameter adjustment information and sample working parameter information corresponding to the sample parameter adjustment information, inputting the sample parameter adjustment information into an equipment control model, obtaining candidate working parameter information corresponding to the sample parameter adjustment information, and performing iterative training on the equipment control model.
12. The apparatus of claim 11, wherein if the device control model is trained based on a neural network, the training module is specifically configured to determine an output value of each neuron in an input layer after the sample parameter adjustment information and candidate operating parameter information corresponding to the sample parameter adjustment information enter the network from the input layer in the device control model; forward the sample parameter adjustment information and the output value of each neuron to a hidden layer in an equipment control model; the hidden layer determines an error item value of each neuron according to the stored weight value of the layer of each neuron at the current moment and the output value of each neuron; an output layer in the equipment control model determines a weight gradient corresponding to the error term value of each neuron and judges whether the weight gradient of each neuron is smaller than a set gradient threshold value or not; if not, updating the weight value of the layer of each neuron at the current moment, which is stored in the equipment control model, according to the weight gradient of each neuron; if so, determining that the iterative training is completed.
13. The apparatus of claim 12, wherein the training module is further configured to input the sample parameter adjustment information and the candidate operating parameter information corresponding to the sample parameter adjustment information into a forgetting gate in an equipment control model before the sample parameter adjustment information and the candidate operating parameter information corresponding to the sample parameter adjustment information enter a network from an input layer in the equipment control model, and the forgetting gate retains a candidate operating parameter sub-information in the candidate operating parameter information according to the sample parameter adjustment information and the candidate operating parameter information corresponding to the sample parameter adjustment information and updates the candidate operating parameter information into the candidate operating parameter sub-information.
14. The apparatus of any one of claims 8-13, further comprising:
the correction module is used for judging whether the adjustment operation of the working parameter information of the user sent by the air conditioner is received or not after the target working parameter information is sent to the air conditioner, wherein the adjustment operation of the working parameter information carries the adjusted working parameter information; and if so, correcting the equipment control model according to the adjusted working parameter information.
15. A terminal is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
the memory has stored therein a computer program which, when executed by the processor, causes the processor to carry out the steps of the method of any one of claims 1 to 7.
16. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810569971.6A CN110631221A (en) | 2018-06-05 | 2018-06-05 | Control method and device of air conditioner, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810569971.6A CN110631221A (en) | 2018-06-05 | 2018-06-05 | Control method and device of air conditioner, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110631221A true CN110631221A (en) | 2019-12-31 |
Family
ID=68966233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810569971.6A Pending CN110631221A (en) | 2018-06-05 | 2018-06-05 | Control method and device of air conditioner, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110631221A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111397131A (en) * | 2020-03-30 | 2020-07-10 | 广东美的制冷设备有限公司 | Air conditioning equipment, control method and device thereof and electronic equipment |
| CN111928423A (en) * | 2020-06-30 | 2020-11-13 | 青岛海尔空调电子有限公司 | Defrosting control method for air conditioning unit |
| CN113377018A (en) * | 2020-03-09 | 2021-09-10 | 青岛海尔空调器有限总公司 | Intelligent control method and intelligent control equipment of air conditioner |
| WO2021258695A1 (en) * | 2020-06-23 | 2021-12-30 | 珠海格力电器股份有限公司 | Method and apparatus for air conditioning in sleep environment, and electronic device |
| CN114963458A (en) * | 2021-02-23 | 2022-08-30 | 海信集团控股股份有限公司 | Thermal comfort parameter prediction method and device |
| CN116068910A (en) * | 2023-04-06 | 2023-05-05 | 江西财经大学 | Intelligent home control method and system based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信（山东）空调有限公司 | Air conditioner control method, server and air conditioner system |
| CN106407649A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Onset time automatic picking method of microseismic signal on the basis of time-recursive neural network |
| CN106960252A (en) * | 2017-03-08 | 2017-07-18 | 深圳市景程信息科技有限公司 | Methods of electric load forecasting based on long Memory Neural Networks in short-term |
| CN107622329A (en) * | 2017-09-22 | 2018-01-23 | 深圳市景程信息科技有限公司 | The Methods of electric load forecasting of Memory Neural Networks in short-term is grown based on Multiple Time Scales |
-
2018
- 2018-06-05 CN CN201810569971.6A patent/CN110631221A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信（山东）空调有限公司 | Air conditioner control method, server and air conditioner system |
| CN106407649A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Onset time automatic picking method of microseismic signal on the basis of time-recursive neural network |
| CN106960252A (en) * | 2017-03-08 | 2017-07-18 | 深圳市景程信息科技有限公司 | Methods of electric load forecasting based on long Memory Neural Networks in short-term |
| CN107622329A (en) * | 2017-09-22 | 2018-01-23 | 深圳市景程信息科技有限公司 | The Methods of electric load forecasting of Memory Neural Networks in short-term is grown based on Multiple Time Scales |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377018A (en) * | 2020-03-09 | 2021-09-10 | 青岛海尔空调器有限总公司 | Intelligent control method and intelligent control equipment of air conditioner |
| CN111397131A (en) * | 2020-03-30 | 2020-07-10 | 广东美的制冷设备有限公司 | Air conditioning equipment, control method and device thereof and electronic equipment |
| CN111397131B (en) * | 2020-03-30 | 2021-12-21 | 广东美的制冷设备有限公司 | Air conditioning equipment, control method and device thereof and electronic equipment |
| WO2021258695A1 (en) * | 2020-06-23 | 2021-12-30 | 珠海格力电器股份有限公司 | Method and apparatus for air conditioning in sleep environment, and electronic device |
| CN111928423A (en) * | 2020-06-30 | 2020-11-13 | 青岛海尔空调电子有限公司 | Defrosting control method for air conditioning unit |
| CN111928423B (en) * | 2020-06-30 | 2023-05-26 | 青岛海尔空调电子有限公司 | Defrosting control method for air conditioning unit |
| CN114963458A (en) * | 2021-02-23 | 2022-08-30 | 海信集团控股股份有限公司 | Thermal comfort parameter prediction method and device |
| CN116068910A (en) * | 2023-04-06 | 2023-05-05 | 江西财经大学 | Intelligent home control method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110631221A (en) | Control method and device of air conditioner, terminal and storage medium | |
| EP3411634B1 (en) | Data learning server and method for generating and using learning model thereof | |
| CN108919669B (en) | Intelligent home dynamic decision method and device and service terminal | |
| CN110578994B (en) | Operation method and device | |
| US20180283723A1 (en) | Data learning server and method for generating and using learning model thereof | |
| CN111738098B (en) | Vehicle identification method, device, equipment and storage medium | |
| CN110781969B (en) | Air conditioner air volume control method, device and medium based on deep reinforcement learning | |
| CN109358515A (en) | A kind of home equipment control method, device, control equipment and readable storage medium storing program for executing | |
| CN111609534B (en) | Temperature control method and device and central temperature control system | |
| CN110836509A (en) | Household equipment control method and device, control equipment and readable storage medium | |
| CN110471276B (en) | Apparatus for creating model functions for physical systems | |
| JP2020154785A (en) | Prediction method, prediction program, and model learning method | |
| CN110598906A (en) | Method and system for controlling energy consumption of superstores in real time based on deep reinforcement learning | |
| CN104075402A (en) | Intelligent air conditioner control method and system | |
| CN111103790A (en) | Parameter setting method and device of PID controller, storage medium, terminal and system | |
| WO2022041987A1 (en) | Intelligent control method and intelligent control device for air conditioner | |
| CN111338227A (en) | Electronic appliance control method and control device based on reinforcement learning and storage medium | |
| CN110925936A (en) | Air conditioner control method and device, computer equipment and storage medium | |
| CN111059716A (en) | Method and device for adjusting air conditioner parameters and storage medium | |
| CN113310182B (en) | Control method of temperature adjusting equipment and electronic equipment | |
| CN110779175A (en) | Operation mode control method and device | |
| CN112944624B (en) | Method for air conditioner control and air conditioner | |
| JP2022510667A (en) | Methods and equipment for predicting energy consumption | |
| CN114234388B (en) | Control method and device for air conditioner, air conditioner and storage medium | |
| CN111781840B (en) | Model-free self-adaptive water mixing temperature control system and method based on deep reinforcement learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191231 |
|
| RJ01 | Rejection of invention patent application after publication |