WO2020042417A1 - 控制空调的方法、装置和空调装置 - Google Patents

控制空调的方法、装置和空调装置 Download PDF

Info

Publication number
WO2020042417A1
WO2020042417A1 PCT/CN2018/119603 CN2018119603W WO2020042417A1 WO 2020042417 A1 WO2020042417 A1 WO 2020042417A1 CN 2018119603 W CN2018119603 W CN 2018119603W WO 2020042417 A1 WO2020042417 A1 WO 2020042417A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
preset
data
air conditioner
air
Prior art date
Application number
PCT/CN2018/119603
Other languages
English (en)
French (fr)
Inventor
肖龙
陈翀
连圆圆
秦萍
万会
冯德兵
马诗蓉
Original Assignee
珠海格力电器股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 珠海格力电器股份有限公司 filed Critical 珠海格力电器股份有限公司
Publication of WO2020042417A1 publication Critical patent/WO2020042417A1/zh

Links

Images

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/89Arrangement or mounting of control or safety devices
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00Control inputs relating to air properties

Definitions

  • the present application relates to the field of air conditioning control, and in particular, to a method, an apparatus, and an air conditioning apparatus for controlling an air conditioner.
  • users can control the air conditioner using intelligent control modes such as client control, voice control, and body movement control.
  • intelligent control modes such as client control, voice control, and body movement control.
  • the above-mentioned intelligent control method releases the user from the traditional remote control.
  • the user can remotely control the operating parameters of the air conditioner in the home by controlling the air conditioning software on the mobile phone terminal to achieve preheating, precooling, and humidity adjustment of air purification in the home environment.
  • the user's voice or body movements control the operating parameters of the air conditioner.
  • the user still needs to set the operating parameters of the air conditioner, or the air conditioner can only perform cooling and heating according to the preset wind speed and sweeping angle, which cannot effectively be based on different ages and conditions.
  • the object performs cooling and heating in a specific area.
  • the embodiments of the present application provide a method, a device, and an air conditioner for controlling an air conditioner, so as to at least solve a technical problem that the same air conditioner cannot simultaneously adjust to the needs of different objects.
  • a method for controlling an air conditioner including: obtaining object information of at least one object in a preset area; using the preset model to process the object information of at least one object, and obtaining at least one object
  • the operating data of the air-conditioning device corresponding to the object is obtained by using multiple sets of data to learn and train through the neural network.
  • Each set of data in the multiple sets of data includes: object information and operating data corresponding to the object information; controlling the air conditioner The device adjusts the environmental parameters of the sub-area where the object is located according to the operation data corresponding to the at least one object.
  • a device for controlling an air conditioner including: an acquisition module configured to acquire object information of at least one object in a preset area; and a processing module configured to use a preset model to at least one
  • the object information of the object is processed to obtain the operation data of the air-conditioning device corresponding to at least one object.
  • the preset model is obtained by using multiple sets of data to learn and train through the neural network. Each set of data in the multiple sets of data includes: the object The operation data corresponding to the information and the object information; the control module is configured to control the air conditioner to adjust the environmental parameters of the sub-area where the object is located according to the operation data corresponding to the at least one object.
  • an air-conditioning apparatus including: a sensor configured to acquire and obtain object information of at least one object in a preset area; and a controller configured to use a preset model for at least one object.
  • the object information is processed to obtain the operation data of the air-conditioning device corresponding to the at least one object, and the air-conditioning device is controlled to adjust the environmental parameters of the sub-area where the object is located according to the operation data corresponding to the at least one object.
  • the preset model is to use Multiple sets of data are obtained through neural network learning and training. Each set of data in the multiple sets of data includes: object information and operating data corresponding to the object information.
  • a storage medium includes a stored program, where the program executes a method for controlling an air conditioner.
  • a processor is further provided.
  • the processor is configured to run a program, and the method for controlling the air conditioner is executed when the program is run.
  • the method of determining the operation data of the air conditioner corresponding to the object based on the neural network is adopted.
  • the air conditioner uses the preset model to the object of the at least one object.
  • the information is processed to obtain the operation data of the air conditioning device corresponding to the at least one object, and finally the air conditioning device is controlled to adjust the environmental parameters of the sub-area where the object is located according to the operation data corresponding to the at least one object.
  • the preset model is obtained by learning and training through a neural network using multiple sets of data, and each set of data in the multiple sets of data includes object information and running data corresponding to the object information.
  • different object information corresponds to different operation data. Therefore, when there are multiple objects in the preset area, operation data of multiple air conditioners can be obtained, and then the air conditioner responds to different objects according to the object. Corresponding operation data is operated to achieve the purpose of cooling or heating in a specific area according to the needs of different objects, and further achieve the technical effect of improving user comfort.
  • FIG. 1 is a flowchart of a method for controlling an air conditioner according to an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of an optional preset model according to an embodiment of the present application.
  • FIG. 3 is a schematic diagram of an optional neural network according to an embodiment of the present application.
  • FIG. 4 is a schematic diagram of an optional convolutional neural network according to an embodiment of the present application.
  • FIG. 5 is a schematic diagram of an optional wind deflector angle according to an embodiment of the present application.
  • FIG. 6 is a flowchart of an optional wind deflector angle according to an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a device for controlling an air conditioner according to an embodiment of the present application.
  • an embodiment of a method for controlling an air conditioner is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. The logical order is shown in the flowchart, but in some cases the steps shown or described may be performed in a different order than here.
  • FIG. 1 is a flowchart of a method for controlling an air conditioner according to an embodiment of the present application. As shown in FIG. 1, the method includes the following steps:
  • Step S102 Obtain object information of at least one object in a preset area.
  • the preset area includes multiple sub-areas, and one or more objects may or may not exist in each sub-area.
  • the object information of the at least one object includes at least one of the following: the number of the at least one object, the position of the at least one object, the body temperature of the at least one object, and the body state information of the at least one object, wherein the body state information of the at least one object may be Including: the age of at least one subject, whether pregnant, physical health data (eg, whether you are sick, whether you have a legacy disease, etc.).
  • the air conditioner has a sensor, and the sensor may include, but is not limited to, a common image sensor and an infrared image sensor.
  • the sensor of the air conditioner can collect object information of the objects in the preset area.
  • the sensor may collect image information in a preset area, and the controller in the air conditioner further performs recognition processing on the image information to obtain object information of at least one object.
  • step S104 the object information of at least one object is processed by using a preset model to obtain the operation data of the air-conditioning device corresponding to the at least one object.
  • the preset model is obtained by using multiple sets of data to learn and train through a neural network. Each set of data in the data includes: object information and operation data corresponding to the object information.
  • a neural network-related algorithm may be used to train the preset model.
  • the neural network-related algorithm may include, but is not limited to, a feedback neural network algorithm, a recommendation algorithm, and the like.
  • the neural network structure may include one or more of a fully connected neural network, a convolutional neural network, and a recurrent neural network.
  • the operation data corresponding to at least one object can be obtained through the preset model, that is, the operation data of different objects may be different, and the operation data corresponding to the object can make the comfort of the object the best. It can be seen that, through step S104, operation data of the air-conditioning apparatus that makes each object reach the optimal comfort level can be obtained.
  • step S106 the air conditioner is controlled to adjust the environmental parameters of the sub-area where the object is located according to the operation data corresponding to the at least one object.
  • the operation data of the air-conditioning device includes at least one of the following: the operating frequency of the compressor, the angle of the air deflector, the air volume level, and the speed of the fan.
  • the controller in the air conditioner may control the air conditioner to output different wind volumes, wind speeds, and different sub-regions according to different physical states and positions of different objects.
  • Environmental parameters such as temperature, thereby achieving the purpose of cooling or heating in a specific area according to the needs of different objects.
  • the air conditioner uses the pre- It is assumed that the model processes the object information of at least one object to obtain the operation data of the air-conditioning device corresponding to the at least one object, and finally controls the air-conditioning device to adjust the environmental parameters of the sub-region where the object is located according to the operation data corresponding to the at least one object.
  • the preset model is obtained by learning and training through a neural network using multiple sets of data, and each set of data in the multiple sets of data includes object information and running data corresponding to the object information.
  • the air conditioner before processing the object information of the at least one object using the preset model to obtain the operation data, the air conditioner first needs to acquire the object information of the at least one object.
  • the air conditioner may obtain object information of at least one object based on any one or more of the following three ways.
  • Method 1 Use image analysis to obtain object information of at least one object.
  • the specific process may include the following steps:
  • Step S10 Acquire a thermal imaging image of a preset area based on the thermal imaging sensor
  • Step S12 Analyze the thermal imaging image to determine the number, location and temperature of at least one object in the preset area
  • Step S14 comparing the body temperature of at least one subject with a preset body temperature level to obtain a comparison result
  • Step S16 Collect image information in a preset area based on the camera
  • Step S18 Determine body state information of at least one object according to the image information and the comparison result.
  • the thermal imaging sensor may acquire an image in a preset area to obtain a thermal imaging image.
  • the thermal imaging image represents a heat distribution in the preset area.
  • a darker part of the thermal imaging image Indicates that the area corresponding to the part has higher heat, which means that there are more objects in the area corresponding to the part.
  • the color depth in the thermal imaging image can also represent the body temperature of each object. It can be known from the foregoing that by collecting thermal imaging images of the preset area, information such as the number of objects existing in the preset area, the position distribution of the objects, and the body temperature of the objects can be determined.
  • the controller After obtaining the body temperature of the object, the controller compares the body temperature of each object with a preset body temperature level to determine the body temperature level where the body temperature of each object is.
  • the preset body temperature level can be divided into: normal level (not higher than 37.5 degrees Celsius), low heat level (37.3-38 degrees Celsius), medium heat level (38.1-39 degrees Celsius), and high heat level (39.1-41 degrees Celsius) High grade (above 41 degrees Celsius).
  • the body temperature level of each object's body temperature it can be initially determined whether the object is sick, and then combined with the image information in the preset area collected by the camera, such as the face image of each object, the clothing of each object, etc. To further determine the body state information of the subject.
  • the controller can determine that the subject A is in a sick state.
  • Method 2 Use the method of combining image analysis and user input to obtain the object information of at least one object.
  • the specific process may include the following steps:
  • Step S20 Acquire a thermal imaging image of a preset area based on the thermal imaging sensor
  • Step S22 Analyze the thermal imaging image to determine the number, location and temperature of at least one object in the preset area
  • step S22 the body state information input by at least one object is acquired.
  • the method of obtaining the number, location, and temperature of at least one object is the same as the methods defined in steps S10 to S12, and details are not described herein again.
  • the difference from the first method is that in the second method, the body state information of at least one object is obtained by the object through input.
  • Method 3 Use the combination of image analysis and database query to obtain the object information of at least one object.
  • the specific process may include the following steps:
  • Step S30 Acquire a thermal imaging image of a preset area based on the thermal imaging sensor
  • Step S32 Analyze the thermal imaging image to determine the number, location and temperature of at least one object in the preset area
  • Step S34 obtaining registration information of at least one object
  • Step S36 Query body status information of at least one subject from a hospital database according to the registration information.
  • the method for obtaining the number, location, and temperature of at least one object is the same as the method defined in steps S10 to S12, and is not repeated here.
  • At least one object may be registered in an application program that controls the air conditioning device.
  • the air conditioning device may obtain registration information of the at least one object.
  • the registration information may include, but is not limited to, the contact information, name, Avatars and more.
  • the client queries from the hospital database in the cloud to reach the body state information of the object corresponding to the registration information.
  • the hospital database stores the patient's contact information, name, and medical history.
  • the object information of the at least one object can be obtained through a combination of any one or more of the above three methods, and then the controller can use the preset model to process the object information of the at least one object.
  • the controller Before using the preset model to process the object information of at least one object, the controller first needs to build a preset module, wherein the process of constructing the preset module is as follows:
  • Step S40 Obtain a data set, where the data set includes information data of a space where multiple groups of air conditioning devices are located;
  • Step S42 preprocessing the data set to obtain a processed data set
  • Step S44 training the processed data set to obtain a preset model
  • step S46 the preset model is stored in the model server, wherein the model server is configured to store the preset model.
  • the sensor of the air conditioning device obtains a data set by collecting multiple sets of information data in different time periods and different spaces.
  • the data set needs to be subjected to normalized preprocessing, so that the processed data set is used as a training sample of the neural network to train a preset model.
  • the preset model is stored in the model server.
  • the model server stores the latest preset model.
  • the latest preset model is stored in the model server.
  • the first preset model is stored in the model server.
  • the model server stores the first preset model in the model server. The second preset model replaces the first preset model.
  • model server may be a cloud server
  • the air-conditioning device obtains the preset model in the model server and / or updates the preset model in the model server through wireless communication.
  • the controller uses the preset model to process the object information of the at least one object to obtain the operation data of the air conditioning device corresponding to the at least one object.
  • the specific method may include the following steps:
  • Step S1040 Obtain the latest preset model from the model server
  • step S1042 the object information of the at least one object is analyzed based on the latest preset model to obtain running data.
  • FIG. 2 a schematic structural diagram of a preset model is shown in FIG. 2.
  • the input of the preset model is the object information in step S102, including the number of objects, the position information of each object, the temperature of each object, the age range of each object, whether the object is pregnant, whether the object is healthy, The target value set by the subject and the subject's feedback on comfort.
  • the controller Before the object information is input into the preset model, the controller first performs linear processing and / or non-linear processing on the object information.
  • linear processing methods include, but are not limited to, normalized linear processing methods
  • non-linear processing methods include, but are not limited to, logarithmic transformation, square root transformation, and cubic root transformation.
  • the preset model is learned based on the neural network
  • the structure of the neural network algorithm includes a fully connected neural network, a convolutional neural network, and a recurrent neural network.
  • the fully connected neural network includes an input layer, a hidden layer, and an output layer, as shown in FIG. 3.
  • the number of nodes in the input layer is determined by the input data.
  • the input layer includes the number of objects, location information of each object, body temperature of each object, age range of each object, whether the object is pregnant, whether the object is healthy, and object settings. There are 7 pieces of data such as the target value of the object and the feedback information about the comfort of the object, then the node of the input layer is 7.
  • the number of hidden layers and the number of nodes in each layer are determined by the quality of the output of the algorithm. Among them, if the results are underfitting, the number of hidden layers and the number of nodes in each layer increase appropriately; if overfitting, then The number of hidden layers and the number of nodes in each layer are appropriately reduced. There is only one layer in the output layer, and the number of nodes is determined by the type of output. As shown in Figure 3, the output of the preset model is the compressor's operating frequency, wind deflector angle, air volume level, and other four outputs. Is 4. In the case of 4 levels of air volume, the frequency of compressor operation, the angle of the air deflector, and the 4th volume of air volume, the preset model has 6 outputs, and the corresponding number of output layer nodes is 6.
  • FIG. 4 is a schematic diagram of a convolutional neural network.
  • the convolutional neural network is also divided into three layers, that is, an input layer, a hidden layer, and an output layer.
  • the number of nodes in the input layer is determined by the input data. For example, the number of objects, the position information of each object, the temperature of each object, the age range of each object, whether the object is pregnant, whether the object is healthy, and the object settings. 7 data such as the target value of the object and the feedback information about the comfort of the object are used as the nodes of the input layer.
  • the input data needs to be changed to an even number, generally by adding input data
  • the ambient temperature method can get a 2 * 4 matrix input.
  • the basic layer of the hidden layer is a convolution layer, a pooling layer, and some have a fully connected layer. According to the actual output results, the convolution layer and the pooling layer are together. There is a convolution layer, and a pool will be connected later. In general, there will be multiple convolution and pooling layers, followed by one or two fully connected layers. There is only one output layer, and the number of nodes is determined by the type of output.
  • the operating data of the air conditioning device can be achieved, such as the operating frequency of the compressor, the angle of the air deflector, and the air volume.
  • the angle of the air baffle of the controller can divide the fan-shaped area that can be radiated by the air-conditioning device into equal small fan-shaped areas. As shown in FIG. 5, the angle of each small fan is 25 degrees. The angle of the fan-shaped wind deflector is 25 degrees, and the second fan-shaped wind deflector is 50 degrees.
  • the controller may further receive at least one object for the environmental parameter adjustment of the air conditioner. Feedback information, and update the preset model according to the feedback information.
  • the specific method may include: obtaining feedback information of at least one object;
  • Step S50 determining whether the air conditioning device performs a shutdown operation when the feedback information indicates that the comfort of at least one object is poor;
  • Step S52 In the case where the air-conditioning device performs a shutdown operation, update the preset model according to the feedback information, and store the updated preset model in the model server;
  • step S54 when the air-conditioning device does not perform a shutdown operation, the operation data is adjusted according to the feedback information.
  • step S56 if the feedback information indicates that the comfort of the at least one object is good, the step of acquiring the object information of the at least one object in the preset area is performed.
  • At least one object may input feedback information to the air-conditioning apparatus through voice, limb movement, and other methods.
  • the controller controls the air conditioner to adjust the environmental parameters of the sub-area where the object is located according to the operating data corresponding to the at least one object, which may include the following steps:
  • Step S60 Acquire a sub-area of each object in the preset area and the running data corresponding to each object;
  • step S62 the air conditioner is controlled to adjust the environmental parameters of the sub-area where the object is located according to the operating data corresponding to each object, wherein the environmental parameters include at least one of the following: temperature and humidity.
  • the air conditioner obtains the number of objects of at least one object in the preset area, position information of each object, and Parameters such as the body temperature of each person, the age of each person, whether they are pregnant, whether they are healthy, and user comfort.
  • the air-conditioning operating parameters such as the operating frequency of the air-conditioning compressor, the angle of the air deflector, and the air volume level are obtained in real time. Temperature and humidity improve the user experience.
  • FIG. 6 illustrates an optional method for controlling an air conditioner.
  • the process of controlling the air conditioner is as follows: Specifically, after the user turns on the air conditioner, the air conditioner loads the latest preset model from the model server, and simultaneously controls the sensor to collect object information, and to pre-collect the collected object information. deal with. Since the preset model initially loaded by the air conditioner is a public model, it is applicable to all scenarios, but it may not be the best model in this scenario.
  • the air-conditioning device may also receive feedback information fed back by the subject, and determine whether the feedback information indicates that the comfort of the subject is good. Among them, when the comfort is good, the air conditioner executes the step of acquiring the target information.
  • the air conditioning device In the case of poor comfort, it is detected whether the air conditioning device performs a shutdown operation.
  • the air conditioner does not perform a shutdown operation, adjust the operating parameters according to the feedback information of the object, for example, adjust the speed of the fan in the air conditioner, the opening degree of the electronic expansion valve, etc .; if the air conditioner performs a shutdown operation, it will update The later preset model is stored in the model server.
  • an embodiment of a device for controlling an air conditioner is also provided. It should be noted that the device can execute the method for controlling an air conditioner in Embodiment 1.
  • 7 is a schematic structural diagram of a device for controlling an air conditioner according to an embodiment of the present application. As shown in FIG. 7, the device includes an obtaining module 701, a processing module 703, and a control module 705.
  • the obtaining module 701 is configured to obtain object information of at least one object in a preset area, where the object information of the at least one object includes at least one of the following: the number of the at least one object, the position of the at least one object, and the at least one object Body temperature and body state information of at least one object;
  • the processing module 703 is configured to process the object information of the at least one object using a preset model to obtain operating data of the air-conditioning device corresponding to the at least one object, wherein the preset model is It is obtained by using multiple sets of data to learn and train through a neural network.
  • Each set of data in the multiple sets of data includes: object information and operation data corresponding to the object information; and a control module 705 configured to control the air conditioner to operate data corresponding to at least one object Adjust the environmental parameters of the sub-region where the object is located.
  • obtaining module 701, processing module 703, and control module 705 correspond to steps S102 to S106 in Embodiment 1.
  • the three modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the above. What was disclosed in Example 1.
  • the acquisition module includes: a first acquisition module, a first determination module, a comparison module, a second acquisition module, and a second determination module.
  • the first acquisition module is configured to acquire a thermal imaging image of a preset area based on a thermal imaging sensor.
  • the first determination module is configured to analyze the thermal imaging image to determine the number, location, and location of at least one object in the preset area.
  • Body temperature a comparison module configured to compare the body temperature of at least one object with a preset body temperature level to obtain a comparison result
  • a second acquisition module configured to acquire image information in a preset area based on a camera; a second determination module configured to set To determine the body state information of at least one object based on the image information and the comparison result.
  • first acquisition module corresponds to steps S10 to S18 in Embodiment 1.
  • the five modules and corresponding steps are The implementation example is the same as the application scenario, but is not limited to the content disclosed in the above embodiment 1.
  • the acquisition module includes a third acquisition module, a third determination module, and a first acquisition module.
  • the third acquisition module is configured to acquire a thermal imaging image of a preset area based on a thermal imaging sensor; the third determination module is configured to analyze the thermal imaging image to determine the number, location, and location of at least one object in the preset area.
  • Body temperature; a first acquisition module configured to acquire body state information input by at least one object.
  • the third acquisition module, the third determination module, and the first acquisition module correspond to steps S20 to S22 in Embodiment 1.
  • the three modules and the corresponding steps implement the same examples and application scenarios, but It is not limited to the content disclosed in the first embodiment.
  • the acquisition module includes a fourth acquisition module, a fourth determination module, a second acquisition module, and a query module.
  • the fourth acquisition module is configured to acquire a thermal imaging image of a preset area based on the thermal imaging sensor; the fourth determination module is configured to analyze the thermal imaging image to determine the number, location, and location of at least one object in the preset area; Body temperature; a second acquisition module configured to acquire registration information of at least one object; a query module configured to query and obtain body state information of at least one object from a hospital database according to the registration information.
  • fourth acquisition module, fourth determination module, second acquisition module, and query module correspond to steps S30 to S36 in Embodiment 1. Examples and application scenarios implemented by the four modules and corresponding steps The same, but not limited to the content disclosed in the first embodiment.
  • the device for controlling the air conditioner further includes: a third acquisition module, a first processing module, a training module, and a storage module.
  • the third acquisition module is configured to acquire a data set, where the data set includes information data of a plurality of groups of air-conditioning devices; the first processing module is configured to preprocess the data set to obtain a processed data set; training A module configured to train a processed data set to obtain a preset model; a storage module configured to store a preset model in a model server, wherein the model server is configured to store a preset model.
  • the third acquisition module, the first processing module, the training module, and the storage module correspond to steps S40 to S46 in Embodiment 1.
  • the four modules and the corresponding steps implement the same examples and application scenarios. However, it is not limited to the content disclosed in the first embodiment.
  • the processing module includes a fourth acquisition module and an analysis module.
  • the fourth acquisition module is configured to acquire the latest preset model from the model server;
  • the analysis module is configured to analyze object information of at least one object based on the latest preset model to obtain operating data.
  • the device for controlling the air conditioner further includes a fifth obtaining module, a determining module, an updating module, and an adjusting module.
  • the fifth acquisition module is configured to acquire feedback information of at least one object;
  • the determination module is configured to determine whether the air conditioning device performs a shutdown operation when the feedback information indicates that the comfort of the at least one object is poor;
  • the update module is configured to be used in the air conditioner
  • the preset model is updated according to the feedback information, and the updated preset model is stored in the model server;
  • the adjustment module is set to be based on the feedback when the air conditioner does not perform the shutdown operation The information adjusts the operating data.
  • the device for controlling the air conditioner further includes a sixth obtaining module and an executing module.
  • the sixth acquisition module is configured to acquire feedback information of at least one object;
  • the execution module is configured to execute acquisition of object information of at least one object in a preset area when the feedback information indicates that the at least one object is comfortable. step.
  • control module includes a seventh acquisition module and an adjustment module.
  • the seventh acquisition module is configured to acquire a sub-area of each object in a preset area and the operation data corresponding to each object;
  • the adjustment module is configured to control the air-conditioning device to adjust the position where the object is located according to the operation data corresponding to each object.
  • the environmental parameters of the sub-region, where the environmental parameters include at least one of the following: temperature, humidity.
  • the seventh acquisition module and the adjustment module correspond to steps S60 to S62 in Embodiment 1.
  • the two modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those described in Embodiment 1. Public content.
  • an embodiment of an air-conditioning apparatus is also provided. It should be noted that the air-conditioning apparatus can execute the method for controlling air-conditioning in Embodiment 1.
  • the air conditioner includes: a sensor and a controller.
  • the sensor is configured to collect and obtain object information of at least one object in a preset area; and the controller is configured to process the object information of the at least one object using a preset model to obtain the operation of the air conditioning device corresponding to the at least one object.
  • Each set of data includes: object information and operation data corresponding to the object information.
  • the air conditioner uses the preset model to process the object information of the at least one object.
  • the preset model is obtained by learning and training through a neural network using multiple sets of data, and each set of data in the multiple sets of data includes object information and running data corresponding to the object information.
  • the object information of the at least one object includes at least one of the following: the number of the at least one object, the position of the at least one object, the body temperature of the at least one object, and the body state information of the at least one object.
  • a thermal imaging sensor collects a thermal imaging image of a preset area, and the controller analyzes the thermal imaging image to determine the number, location, and body temperature of at least one object in the preset area, and compares at least A subject's body temperature is compared with a preset body temperature level to obtain a comparison result. Then, the camera collects image information in a preset area, and the controller determines body state information of at least one object according to the image information and the comparison result.
  • a thermal imaging sensor acquires a thermal imaging image of a preset area, and the controller analyzes the thermal imaging image to determine the number, location, and body temperature of at least one object in the preset area.
  • the processor obtains body state information input by at least one object.
  • the thermal imaging sensor collects a thermal imaging image of a preset area, and the controller analyzes the thermal imaging image to determine the number, location, and body temperature of at least one object in the preset area.
  • the controller acquires registration information of at least one object, and obtains body state information of at least one object from a hospital database according to the registration information.
  • the controller before processing the object information of the at least one object by using a preset model to obtain the operation data of the air conditioning device corresponding to the at least one object, the controller obtains the data set, and preprocesses the data set, after obtaining the processed data Data set, and then train the processed data set to obtain a preset model, and finally store the preset model in a model server, where the model server is configured to store the preset model, and the data set includes information about the space where multiple sets of air conditioning devices are located data.
  • the controller obtains the latest preset model from the model server, and analyzes object information of at least one object based on the latest preset model to obtain operating data.
  • the controller after controlling the air conditioner to adjust the environmental parameters of the sub-area where the object is located according to the operation data corresponding to the at least one object, obtains feedback information of the at least one object.
  • the feedback information indicates that the comfort of at least one object is poor, determine whether the air conditioning device performs a shutdown operation; when the air conditioning device performs a shutdown operation, update the preset model according to the feedback information, and store the updated preset model In the model server; when the air-conditioning device does not perform a shutdown operation, the operation data is adjusted according to the feedback information.
  • the step of acquiring the object information of the at least one object in the preset area is performed.
  • the controller obtains the sub-area of each object in the preset area and the operating data corresponding to each object, and controls the air-conditioning device to adjust the sub-area where the object is located according to the operating data corresponding to each object.
  • Environmental parameters where the environmental parameters include at least one of the following: temperature, humidity.
  • a storage medium is also provided.
  • the storage medium includes a stored program, where the program executes the method for controlling an air conditioner provided in Embodiment 1.
  • a processor is further provided.
  • the processor is configured to run a program, and the method for controlling the air conditioner provided in Embodiment 1 is executed when the program runs.
  • the disclosed technical content can be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit may be a logical function division.
  • multiple units or components may be combined or may be combined. Integration into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each of the units may exist separately physically, or two or more units may be integrated into one unit.
  • the above integrated unit may be implemented in the form of hardware or in the form of software functional unit.
  • the integrated unit When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially a part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium. , Including a number of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application.
  • the foregoing storage media include: U disks, Read-Only Memory (ROM), Random Access Memory (RAM), mobile hard disks, magnetic disks, or optical disks, and other media that can store program codes .
  • the solution provided in the embodiment of the present application can be applied to air conditioning control, and a preset model obtained through learning and training of a neural network is used to determine the most suitable air conditioning operation data of a user, which solves the technical problem that the same air conditioner cannot be adjusted to the needs of different objects at the same time To improve user comfort.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

一种控制空调的方法,包括:获取预设区域内的至少一个对象的对象信息(S102);使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据(S104),其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据;控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节(S106)。另外还公开了一种控制空调的装置和空调装置。

Description

控制空调的方法、装置和空调装置 技术领域
本申请涉及空调控制领域,具体而言,涉及一种控制空调的方法、装置和空调装置。
背景技术
随着生活水平的不断提高,人们对生活品质的要求也越来越高。现代生活中,人类的工作、娱乐、生活等大部分时间处于室内,因此,人们对室内环境品质的需求随之提高。对舒适、节能、健康的室内环境的追求也越来越高。同时,随着人们对室内环境要求的提高,空调系统也在不断地改进之中,目前的空调系统已从初期单纯的制冷制热向舒适、节能方向发展。
目前,用户可以采用客户端控制、语音控制、肢体动作控制等智能化控制模式控制空调,上述的智能化控制方法将用户从传统的遥控器控制中解放出来。例如,用户在下班后可通过手机终端上的控制空调软件对家中的空调的运行参数进行远程网络控制,实现对家庭环境的预热、预冷以及湿度调整空气净化等,或者,在家中通过采集用户的声音或肢体动作实现对空调运行参数的控制。
然而,在上述控制过程中,仍需要用户对空调的运行参数进行设置,或是空调只能按照预先设定好的风速、扫风角度进行制冷制热,无法有效的根据不同年龄、不同状态的对象进行特定区域的制冷制热。
针对上述同一空调无法同时针对不同对象的需求进行调整的问题,目前尚未提出有效的解决方案。
发明内容
本申请实施例提供了一种控制空调的方法、装置和空调装置,以至少解决同一空调无法同时针对不同对象的需求进行调整的技术问题。
根据本申请其中一实施例,提供了一种控制空调的方法,包括:获取预设区域内的至少一个对象的对象信息;使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,其中,预设模型为使用多组数据通过 神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据;控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。
根据本申请其中一实施例,还提供了一种控制空调的装置,包括:获取模块,设置为获取预设区域内的至少一个对象的对象信息;处理模块,设置为使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据;控制模块,设置为控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。
根据本申请其中一实施例,还提供了一种空调装置,包括:传感器,设置为采集获取预设区域内的至少一个对象的对象信息;控制器,设置为使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,并控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节,其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据。
根据本申请其中一实施例,还提供了一种存储介质,该存储介质包括存储的程序,其中,程序执行控制空调的方法。
根据本申请其中一实施例,还提供了一种处理器,该处理器设置为运行程序,其中,程序运行时执行控制空调的方法。
在本申请实施例中,采用基于神经网络确定对象所对应的空调装置的运行数据的方式,在获取预设区域内的至少一个对象的对象信息之后,空调使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,最后控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据。
在上述过程中,不同的对象信息对应不同的运行数据,因此,在预设区域内存在多个对象的情况下,可得到多个空调装置的运行数据,进而空调装置针对不同对象按照与该对象对应的运行数据运行,从而达到了根据不同对象的需求进行特定区域的制冷或制热的目的,进而实现了提高用户舒适度的技术效果。
由此可见,本申请所提供的方案可以解决同一空调无法同时针对不同对象的需求进行调整的技术问题。
附图说明
此处所说明的附图用来提供对本申请的进一步理解,构成本申请的一部分,本申请的示意性实施例及其说明用于解释本申请,并不构成对本申请的不当限定。在附图中:
图1是根据本申请实施例的一种控制空调的方法流程图;
图2是根据本申请实施例的一种可选的预设模型的结构示意图;
图3是根据本申请实施例的一种可选的神经网络的示意图;
图4是根据本申请实施例的一种可选的卷积神经网络的示意图;
图5是根据本申请实施例的一种可选的导风板角度的示意图;
图6是根据本申请实施例的一种可选的导风板角度的流程图;以及
图7是根据本申请实施例的一种控制空调的装置结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本申请一部分的实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都应当属于本申请保护的范围。
需要说明的是,本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
实施例1
根据本申请实施例,提供了一种控制空调的方法实施例,需要说明的是,在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行,并且,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。
图1是根据本申请实施例的控制空调的方法流程图,如图1所示,该方法包括如下步骤:
步骤S102,获取预设区域内的至少一个对象的对象信息。
需要说明的是,预设区域包含多个子区域,每个子区域内可以存在一个或多个对象,也可不存在对象。另外,至少一个对象的对象信息至少包括如下之一:至少一个对象的数量、至少一个对象的位置以及至少一个对象的体温、至少一个对象的身体状态信息,其中,至少一个对象的身体状态信息可以包括:至少一个对象的年龄段、是否怀孕、身体健康数据(例如,是否正在生病,是否具有遗产病等)。
可选的,空调装置具有传感器,该传感器可以包括但不限于普通的图像传感器、红外图像传感器。其中,空调装置的传感器可采集预设区域内的对象的对象信息。例如,在传感器为普通的图像传感器的情况下,传感器可采集预设区域内的图像信息,空调装置中的控制器进一步对图像信息进行识别处理,以得到至少一个对象的对象信息。
步骤S104,使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据。
可选的,在步骤S104中,可使用神经网络相关的算法对预设模型进行训练,其中,与神经网络相关的算法可以包括但不限于反馈式神经网络算法、推荐算法等。另外,神经网络结构可以包括全连接神经网络、卷积神经网络、循环神经网络的一种或多种。
需要说明的是,通过预设模型可以得到与至少一个对象对应的运行数据,即不同的对象可能对象的运行数据是不同的,而与对象对应的运行数据可使得该对象的舒适度最佳。由此可见,通过步骤S104可得到使每个对象达到最佳舒适度的空调装置的运行数据。
步骤S106,控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。
需要说明的是,空调装置的运行数据至少包括如下之一:压缩机的运行频率、导风板角度、风量等级、风机转速等。
可选的,在得到不同对象对应的运行数据之后,空调装置中的控制器可根据不同对象的不同身体状态、所处位置的不同,控制空调装置对不同的子区域输出不同的风量、风速以及温度等环境参数,从而实现了根据不同对象的需求进行特定区域的制冷 或制热的目的。
基于上述步骤S102至步骤S106所限定的方案,可以获知,采用基于神经网络确定对象所对应的空调装置的运行数据的方式,在获取预设区域内的至少一个对象的对象信息之后,空调使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,最后控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据。
容易注意到的是,不同的对象信息对应不同的运行数据,因此,在预设区域内存在多个对象的情况下,可得到多个空调装置的运行数据,进而空调装置针对不同对象按照与该对象对应的运行数据运行,从而达到了根据不同对象的需求进行特定区域的制冷或制热的目的,进而实现了提高用户舒适度的技术效果。
由此可见,本申请所提供的方案可以解决同一空调无法同时针对不同对象的需求进行调整的技术问题。
需要说明的是,在使用预设模型对至少一个对象的对象信息进行处理得到运行数据之前,空调装置首先需要获取至少一个对象的对象信息。可选的,空调装置可基于以下三种方式中的任意一种或多种来获取至少一个对象的对象信息。
方式一:采用图像分析的方式获取至少一个对象的对象信息,具体过程可以包括如下步骤:
步骤S10,基于热成像传感器采集预设区域的热成像图像;
步骤S12,对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温;
步骤S14,比对至少一个对象的体温与预设体温等级,得到比对结果;
步骤S16,基于摄像头采集预设区域内的图像信息;
步骤S18,根据图像信息以及比对结果确定至少一个对象的身体状态信息。
具体的,热成像传感器可采集预设区域内的图像,得到热成像图像,其中,热成像图像表征了预设区域内热量的分布情况,可选的,热成像图像中的颜色越深的部分,表明该部分对应的区域内热量较高,即表明该部分对应的区域内对象较多。另外,在预设区域内存在的对象较少时,热成像图像中的颜色深浅还可表征每个对象的体温。 由上述内容可知,通过采集预设区域的热成像图像可以确定预设区域内存在的对象的数量、对象的位置分布以及对象的体温等信息。在得到对象的体温之后,控制器将每个对象的体温与预设体温等级进行比对,确定每个对象的体温所在的体温等级。可选的,预设体温等级可分为:正常等级(不高于37.5摄氏度)、低热等级(37.3-38摄氏度)、中等度热等级(38.1-39摄氏度)、高热等级(39.1-41摄氏度)、超高等级(41摄氏度以上)。根据每个对象的体温所在的体温等级可初步确定该对象是否生病,然后再结合摄像头所采集到的预设区域内的图像信息,例如,每个对象的人脸图像、每个对象的穿着等,进一步确定对象的身体状态信息。例如,检测到对象A的体温等级为低热等级,并通过摄像头所采集到的该对象的图像确定对象A穿着的衣物要多于其他人,并且,对象A的脸色比其他对象憔悴。由此,控制器可确定对象A处于生病状态。
方式二:采用图像分析与用户输入相结合的方式获取至少一个对象的对象信息,具体过程可以包括如下步骤:
步骤S20,基于热成像传感器采集预设区域的热成像图像;
步骤S22,对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温;
步骤S22,获取至少一个对象输入的身体状态信息。
需要说明的是,在上述步骤S20至步骤S22所限定的方案中,获取至少一个对象的数量、所在位置以及体温的方法与步骤S10至步骤S12所限定的方法相同,在此不再赘述赘述。其中,与方式一的不同之处在于,在方式二中,至少一个对象的身体状态信息由对象通过输入得到。
方式三:采用图像分析与数据库查询相结合的方式获取至少一个对象的对象信息,具体过程可以包括如下步骤:
步骤S30,基于热成像传感器采集预设区域的热成像图像;
步骤S32,对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温;
步骤S34,获取至少一个对象的注册信息;
步骤S36,根据注册信息从医院数据库中查询得到至少一个对象的身体状态信息。
需要说明的是,在上述步骤S30至步骤S32所限定的方案中,获取至少一个对象的数量、所在位置以及体温的方法与步骤S10至步骤S12所限定的方法相同,在此不 再赘述赘述。
另外,至少一个对象可在控制空调装置的应用程序中进行注册,此时,空调装置可获取到至少一个对象的注册信息,其中,注册信息中可以包含但不限于注册对象的联系方式、姓名、头像等。客户端在得到注册信息之后,从云端的医院数据库中查询达到与注册信息相对应的对象的身体状态信息,其中,医院数据库中存储有病人的联系方式、姓名以及病历。
需要说明的是,通过以上三种方式中的任意一种或多种的组合可得到至少一个对象的对象信息,进而控制器可使用预设模型对至少一个对象的对象信息进行处理。在在使用预设模型对至少一个对象的对象信息进行处理之前,控制器首先需要构建预设模块,其中,预设模块的构建过程如下:
步骤S40,获取数据集,其中,数据集包括多组空调装置所在空间的信息数据;
步骤S42,对数据集进行预处理,得到处理后的数据集;
步骤S44,对处理后的数据集进行训练得到预设模型;
步骤S46,存储预设模型至模型服务器中,其中,模型服务器设置为存储预设模型。
具体的,空调装置的传感器通过采集不同时间段、不同空间的多组信息数据得到数据集。为满足神经网络对数据集的要求,在得到数据集之后,需要对数据集进行归一化的预处理,使处理后的数据集作为神经网络的训练样本,对预设模型进行训练。在完成对预设模型的训练之后,将预设模型存储在模型服务器中。
需要说明的是,在数据集构造之后,数据集以多维数值矩阵的形式存在。另外,模型服务器中存储有最新的预设模型。可选的,模型服务器中仅存储最新的预设模型,例如,模型服务器中存储有第一预设模型,在对第一预设模型进行更新得到第二预设模型之后,在模型服务器中将第二预设模型替换掉第一预设模型。
此外,还需要说明的是,模型服务器可以云端服务器,空调装置通过无线通信的方式获取模型服务器中的预设模型和/或对模型服务器中的预设模型进行更新。
另外,在得到预设模型之后,控制器使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,具体方法可以包括如下步骤:
步骤S1040,从模型服务器中获取最新的预设模型;
步骤S1042,基于最新的预设模型对至少一个对象的对象信息进行分析,得到运行数据。
在一种可选的方案中,如图2所示的预设模型的结构示意图。由图2可知,预设模型的输入为步骤S102中的对象信息,包括对象数量、每个对象的位置信息、每个对象的体温、每个对象的年龄段、对象是否怀孕、对象是否健康、对象设定的目标值以及对象针对舒适性的反馈信息。在将对象信息输入预设模型之前,控制器首先对对象信息进行线性处理和/或非线性处理。其中,线性处理方法包括但不限于归一化线性处理方法,非线性处理方法包括但不限于对数变换、平方根变换、立方根变换等处理方法。
需要说明的是,预设模型是基于神经网络学习得到的,而神经网络算法的结构包括全连接神经网络、卷积神经网络以及循环神经网络。其中,全连接神经网络包括输入层、隐藏层和输出层,如图3所示。输入层的节点数由输入的数据决定,其中,输入层包括对象数量、每个对象的位置信息、每个对象的体温、每个对象的年龄段、对象是否怀孕、对象是否健康、对象设定的目标值以及对象针对舒适性的反馈信息等7个数据,则输入层的节点为7。隐藏层的层数和每层的节点数由算法输出结果的好坏决定,其中,如果结果欠拟合,则隐藏层的层数和每层的节点数适当的增加;如果过拟合,则隐藏层的层数和每层的节点数适当的减少。输出层的只有一层,节点数由输出的种类决定,如图3所示,预设模型的输出为压缩机运行的频率、导风板角度、风量等级以及其他等4个输出,则节点数为4。而在风量等级有4档的情况下,压缩机运行的频率、导风板角度,加上4档风量,则预设模型具有6个输出,此时对应的输出层节点数为6。
可选的,图4为卷积神经网络的示意图,其中,卷积神经网络也分为三层,即输入层、隐藏层、输出层。其中,输入层的节点数由输入的数据决定,例如,将对象数量、每个对象的位置信息、每个对象的体温、每个对象的年龄段、对象是否怀孕、对象是否健康、对象设定的目标值以及对象针对舒适性的反馈信息等7个数据作为输入层的节点,由于需要将上述数据变为矩阵输入预设模型,因此需将输入的数据变为偶数个,一般通过添加输入数据,例如,环境温度的方式,可以得到2*4的矩阵输入。隐藏层的基本层有卷积层、池化层,有的有全连接层,根据实际输出结果考虑,卷积层和池化层是一起的,有一个卷积层,后面就会接一个池化层,一般会有多个卷积、池化层,后面接一个或两个全连接层。输出层只有一层,节点数由输出的种类决定。
需要说明的是,经过预设模型处理后,可达到空调装置的运行数据,例如,压缩机的运行频率、导风板角度、风量等。其中,控制器导风板角度可将空调装置所能辐 射的扇形区域划分成等量的小扇形区域,如图5所示,每个小扇形的角度为25度,则定位到第一块小扇形的导风板角度为25度,第二块扇形的导风板为50度。
为了提高用户的舒适度,在控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节之后,控制器还可接收至少一个对象针对空调装置调节环境参数的情况的反馈信息,并根据反馈信息更新预设模型。具体方法可以包括:获取至少一个对象的反馈信息;
步骤S50,在反馈信息指示至少一个对象舒适性差的情况下,判断空调装置是否执行关机操作;
步骤S52,在空调装置执行关机操作的情况下,根据反馈信息对预设模型进行更新,并将更新后的预设模型存储在模型服务器中;
步骤S54,在空调装置未执行关机操作的情况下,根据反馈信息对运行数据进行调整。
步骤S56,在反馈信息指示至少一个对象舒适性良好的情况下,执行获取预设区域内的至少一个对象的对象信息的步骤。
需要说明的是,至少一个对象可通过语音、肢体动作等方式向空调装置输入反馈信息。
在一种可选的方案,控制器控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节,可以包括如下步骤:
步骤S60,获取每个对象在预设区域的子区域以及每个对象对应的运行数据;
步骤S62,根据每个对象对应的运行数据控制空调装置调节该对象所在的子区域的环境参数,其中,环境参数至少包括如下之一:温度、湿度。
需要说明的是,空调装置通过热成像技术、摄像头采集图片进行图片识别技术以及用户自己输入、医院数据获取等方式得到预设区域内的至少一个对象的对象数量、每个对象的位置信息、每个人员的体温、每个人的年龄段、是否怀孕、是否健康以及用户舒适度的反馈信息等参数。通过神经网络实时的得到空调压缩机运行频率、导风板角度、风量等级等空调运行参数,从而实现针对不同人群、不同身体状况的在不同的位置但基于同一个空调下,空调输出最适宜的温度和湿度,提高了用户体验。
在一种可选的方案中,图6示出了一种可选的控制空调的方法。由图6可知,控制空调的过程如下:具体的,在用户开启空调装置之后,空调装置从模型服务器中加 载最新的预设模型,同时控制传感器采集对象信息,并对采集到的对象信息进行预处理。由于空调装置初始加载的预设模型是大众模型,对于所有的场景均适用,但可能不是本场景的最有模型。因此,在得到预设模型之后,需要基于当前场景所采集到的信息数据对预设模型进行在线重复学习,利用所采集到并经过预处理的对象信息作为训练样本,进行神经网络训练,建立与当前场景最匹配的预设模型,进一步的得到运行数据,并使空调装置根据运行数据对对象所在的子区域的环境参数进行调节。在对子区域的环境参数调节的过程中,空调装置还可接收对象反馈的反馈信息,并判断反馈信息是否指示对象的舒适性良好。其中,在舒适性良好的情况下,空调装置执行获取对象信息的步骤。在舒适性较差的情况下,检测空调装置是否执行关机操作。在空调装置未执行关机操作的情况下,根据对象的反馈信息调整运行参数,例如,调节空调装置中风机的转速、电子膨胀阀的开度等;在空调装置执行关机操作的情况下,将更新后的预设模型存储至模型服务器中。
实施例2
根据本申请实施例,还提供了一种控制空调的装置实施例,需要说明的是,该装置可执行实施例1中的控制空调的方法。其中,图7是根据本申请实施例的控制空调的装置结构示意图,如图7所示,该装置包括:获取模块701、处理模块703以及控制模块705。
其中,获取模块701,设置为获取预设区域内的至少一个对象的对象信息,其中,至少一个对象的对象信息至少包括如下之一:至少一个对象的数量、至少一个对象的位置以及至少一个对象的体温、至少一个对象的身体状态信息;处理模块703,设置为使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据;控制模块705,设置为控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。
需要说明的是,上述获取模块701、处理模块703以及控制模块705对应于实施例1中的步骤S102至步骤S106,三个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
在一种可选的方案中,获取模块包括:第一采集模块、第一确定模块、比对模块、第二采集模块以及第二确定模块。其中,第一采集模块,设置为基于热成像传感器采集预设区域的热成像图像;第一确定模块,设置为对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温;比对模块,设置为比对至少一个对 象的体温与预设体温等级,得到比对结果;第二采集模块,设置为基于摄像头采集预设区域内的图像信息;第二确定模块,设置为根据图像信息以及比对结果确定至少一个对象的身体状态信息。
需要说明的是,上述第一采集模块、第一确定模块、比对模块、第二采集模块以及第二确定模块对应于实施例1中的步骤S10至步骤S18,五个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
在一种可选的方案中,获取模块包括:第三采集模块、第三确定模块以及第一获取模块。其中,第三采集模块,设置为基于热成像传感器采集预设区域的热成像图像;第三确定模块,设置为对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温;第一获取模块,设置为获取至少一个对象输入的身体状态信息。
需要说明的是,上述第三采集模块、第三确定模块以及第一获取模块对应于实施例1中的步骤S20至步骤S22,三个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
在一种可选的方案中,获取模块包括:第四采集模块、第四确定模块、第二获取模块以及查询模块。其中,第四采集模块,设置为基于热成像传感器采集预设区域的热成像图像;第四确定模块,设置为对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温;第二获取模块,设置为获取至少一个对象的注册信息;查询模块,设置为根据注册信息从医院数据库中查询得到至少一个对象的身体状态信息。
需要说明的是,上述第四采集模块、第四确定模块、第二获取模块以及查询模块对应于实施例1中的步骤S30至步骤S36,四个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
在一种可选的方案中,控制空调的装置还包括:第三获取模块、第一处理模块、训练模块以及存储模块。其中,第三获取模块,设置为获取数据集,其中,数据集包括多组空调装置所在空间的信息数据;第一处理模块,设置为对数据集进行预处理,得到处理后的数据集;训练模块,设置为对处理后的数据集进行训练得到预设模型;存储模块,设置为存储预设模型至模型服务器中,其中,模型服务器设置为存储预设模型。
需要说明的是,上述第三获取模块、第一处理模块、训练模块以及存储模块对应于实施例1中的步骤S40至步骤S46,四个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
在一种可选的方案中,处理模块包括:第四获取模块以及分析模块。其中,第四获取模块,设置为从模型服务器中获取最新的预设模型;分析模块,设置为基于最新的预设模型对至少一个对象的对象信息进行分析,得到运行数据。
需要说明的是,上述第四获取模块以及分析模块对应于实施例1中的步骤S1040至步骤S1042,两个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
在一种可选的方案中,控制空调的装置还包括:第五获取模块、判断模块、更新模块以及调整模块。其中,第五获取模块,设置为获取至少一个对象的反馈信息;判断模块,设置为在反馈信息指示至少一个对象舒适性差的情况下,判断空调装置是否执行关机操作;更新模块,设置为在空调装置执行关机操作的情况下,根据反馈信息对预设模型进行更新,并将更新后的预设模型存储在模型服务器中;调整模块,设置为在空调装置未执行关机操作的情况下,根据反馈信息对运行数据进行调整。
在一种可选的方案中,控制空调的装置还包括:第六获取模块以及执行模块。其中,第六获取模块,设置为获取至少一个对象的反馈信息;执行模块,设置为在反馈信息指示至少一个对象舒适性良好的情况下,执行获取预设区域内的至少一个对象的对象信息的步骤。
在一种可选的方案中,控制模块包括:第七获取模块以及调节模块。其中,第七获取模块,设置为获取每个对象在预设区域的子区域以及每个对象对应的运行数据;调节模块,设置为根据每个对象对应的运行数据控制空调装置调节该对象所在的子区域的环境参数,其中,环境参数至少包括如下之一:温度、湿度。
需要说明的是,上述第七获取模块以及调节模块对应于实施例1中的步骤S60至步骤S62,两个模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例1所公开的内容。
实施例3
根据本申请实施例,还提供了一种空调装置实施例,需要说明的是,该空调装置可执行实施例1中的控制空调的方法。其中,该空调装置包括:传感器和控制器。
其中,传感器,设置为采集获取预设区域内的至少一个对象的对象信息;控制器,设置为使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,并控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节,其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数 据。
由上可知,采用基于神经网络确定对象所对应的空调装置的运行数据的方式,在获取预设区域内的至少一个对象的对象信息之后,空调使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据,最后控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。其中,预设模型为使用多组数据通过神经网络学习训练得到的,多组数据中的每组数据均包括:对象信息以及对象信息对应的运行数据。
容易注意到的是,不同的对象信息对应不同的运行数据,因此,在预设区域内存在多个对象的情况下,可得到多个空调装置的运行数据,进而空调装置针对不同对象按照与该对象对应的运行数据运行,从而达到了根据不同对象的需求进行特定区域的制冷或制热的目的,进而实现了提高用户舒适度的技术效果。
由此可见,本申请所提供的方案可以解决同一空调无法同时针对不同对象的需求进行调整的技术问题。
需要说明的是,至少一个对象的对象信息至少包括如下之一:至少一个对象的数量、至少一个对象的位置以及至少一个对象的体温、至少一个对象的身体状态信息。
在一种可选的方案中,热成像传感器采集预设区域的热成像图像,控制器对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温,并比对至少一个对象的体温与预设体温等级,得到比对结果。然后,摄像头采集预设区域内的图像信息,控制器根据图像信息以及比对结果确定至少一个对象的身体状态信息。
在另一种可选的方案中,热成像传感器采集预设区域的热成像图像,控制器对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温,同时,控制器获取至少一个对象输入的身体状态信息。
还存在一种可选的方案,热成像传感器采集预设区域的热成像图像,控制器对热成像图像进行分析,确定预设区域内至少一个对象的数量、所在位置以及体温。控制器获取至少一个对象的注册信息,并根据注册信息从医院数据库中查询得到至少一个对象的身体状态信息。
可选的,在使用预设模型对至少一个对象的对象信息进行处理,得到与至少一个对象对应的空调装置的运行数据之前,控制器获取数据集,并对数据集进行预处理,得到处理后的数据集,然后对处理后的数据集进行训练得到预设模型,最后存储预设模型至模型服务器中,其中,模型服务器设置为存储预设模型,数据集包括多组空调装置所在空间的信息数据。
在一种可选的方案中,控制器从模型服务器中获取最新的预设模型,并基于最新的预设模型对至少一个对象的对象信息进行分析,得到运行数据。
其中,在控制空调装置按照至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节之后,控制器获取至少一个对象的反馈信息。在反馈信息指示至少一个对象舒适性差的情况下,判断空调装置是否执行关机操作;在空调装置执行关机操作的情况下,根据反馈信息对预设模型进行更新,并将更新后的预设模型存储在模型服务器中;在空调装置未执行关机操作的情况下,根据反馈信息对运行数据进行调整。在反馈信息指示至少一个对象舒适性良好的情况下,执行获取预设区域内的至少一个对象的对象信息的步骤。
在一种可选的方案中,控制器获取每个对象在预设区域的子区域以及每个对象对应的运行数据,并根据每个对象对应的运行数据控制空调装置调节该对象所在的子区域的环境参数,其中,环境参数至少包括如下之一:温度、湿度。
实施例4
根据本申请其中一实施例,还提供了一种存储介质,该存储介质包括存储的程序,其中,程序执行实施例1所提供的控制空调的方法。
实施例5
根据本申请其中一实施例,还提供了一种处理器,该处理器设置为运行程序,其中,程序运行时执行实施例1所提供的控制空调的方法。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
在本申请的上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中,应该理解到,所揭露的技术内容,可通过其它的方式实现。其中,以上所描述的装置实施例仅仅是示意性的,例如所述单元的划分,可以为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,单元或模块的间接耦合或通信连接,可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案 的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅是本申请的优选实施方式,应当指出,对于本技术领域的普通技术人员来说,在不脱离本申请原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本申请的保护范围。
工业实用性
本申请实施例提供的方案,可以应用于空调控制中,通过神经网络学习训练得到的预设模型确定最适宜用户的空调运行数据,解决了同一空调无法同时针对不同对象的需求进行调整的技术问题,提高了用户舒适度。

Claims (13)

  1. 一种控制空调的方法,包括:
    获取预设区域内的至少一个对象的对象信息;
    使用预设模型对所述至少一个对象的对象信息进行处理,得到与所述至少一个对象对应的空调装置的运行数据,其中,所述预设模型为使用多组数据通过神经网络学习训练得到的,所述多组数据中的每组数据均包括:所述对象信息以及所述对象信息对应的运行数据;
    控制所述空调装置按照所述至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。
  2. 根据权利要求1所述的方法,其中,所述至少一个对象的对象信息至少包括如下之一:所述至少一个对象的数量、所述至少一个对象的位置以及所述至少一个对象的体温、所述至少一个对象的身体状态信息,其中,获取预设区域内的至少一个对象的对象信息,包括:
    基于热成像传感器采集所述预设区域的热成像图像;
    对所述热成像图像进行分析,确定所述预设区域内所述至少一个对象的数量、所在位置以及体温;
    比对所述至少一个对象的体温与预设体温等级,得到比对结果;
    基于摄像头采集所述预设区域内的图像信息;
    根据所述图像信息以及所述比对结果确定所述至少一个对象的身体状态信息。
  3. 根据权利要求1所述的方法,其中,所述至少一个对象的对象信息至少包括如下之一:所述至少一个对象的数量、所述至少一个对象的位置以及所述至少一个对象的体温、所述至少一个对象的身体状态,其中,获取预设区域内的至少一个对象的对象信息,包括:
    基于热成像传感器采集所述预设区域的热成像图像;
    对所述热成像图像进行分析,确定所述预设区域内所述至少一个对象的数量、所在位置以及体温;
    获取所述至少一个对象输入的身体状态信息。
  4. 根据权利要求1所述的方法,其中,所述至少一个对象的对象信息至少包括如下之一:所述至少一个对象的数量、所述至少一个对象的位置以及所述至少一个对象的体温、所述至少一个对象的身体状态,其中,获取预设区域内的至少一个对象的对象信息,包括:
    基于热成像传感器采集所述预设区域的热成像图像;
    对所述热成像图像进行分析,确定所述预设区域内所述至少一个对象的数量、所在位置以及体温;
    获取所述至少一个对象的注册信息;
    根据所述注册信息从医院数据库中查询得到所述至少一个对象的身体状态信息。
  5. 根据权利要求1所述的方法,其中,在使用预设模型对所述至少一个对象的对象信息进行处理,得到与所述至少一个对象对应的空调装置的运行数据之前,所述方法还包括:
    获取数据集,其中,所述数据集包括多组所述空调装置所在空间的信息数据;
    对所述数据集进行预处理,得到处理后的数据集;
    对所述处理后的数据集进行训练得到所述预设模型;
    存储所述预设模型至模型服务器中,其中,所述模型服务器设置为存储所述预设模型。
  6. 根据权利要求5所述的方法,其中,使用预设模型对所述至少一个对象的对象信息进行处理,得到与所述至少一个对象对应的空调装置的运行数据,包括:
    从所述模型服务器中获取最新的预设模型;
    基于所述最新的预设模型对所述至少一个对象的对象信息进行分析,得到所述运行数据。
  7. 根据权利要求5所述的方法,其中,在控制所述空调装置按照所述至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节之后,所述方法还包括:
    获取所述至少一个对象的反馈信息;
    在所述反馈信息指示所述至少一个对象舒适性差的情况下,判断所述空调装 置是否执行关机操作;
    在所述空调装置执行所述关机操作的情况下,根据所述反馈信息对所述预设模型进行更新,并将更新后的预设模型存储在所述模型服务器中;
    在所述空调装置未执行所述关机操作的情况下,根据所述反馈信息对所述运行数据进行调整。
  8. 根据权利要求5所述的方法,其中,在控制所述空调装置按照所述至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节之后,所述方法还包括:
    获取所述至少一个对象的反馈信息;
    在所述反馈信息指示所述至少一个对象舒适性良好的情况下,执行所述获取预设区域内的至少一个对象的对象信息的步骤。
  9. 根据权利要求1所述的方法,其中,控制所述空调装置按照所述至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节,包括:
    获取每个对象在所述预设区域的子区域以及所述每个对象对应的运行数据;
    根据所述每个对象对应的运行数据控制所述空调装置调节该对象所在的子区域的环境参数,其中,所述环境参数至少包括如下之一:温度、湿度。
  10. 一种控制空调的装置,包括:
    获取模块,设置为获取预设区域内的至少一个对象的对象信息;
    处理模块,设置为使用预设模型对所述至少一个对象的对象信息进行处理,得到与所述至少一个对象对应的空调装置的运行数据,其中,所述预设模型为使用多组数据通过神经网络学习训练得到的,所述多组数据中的每组数据均包括:所述对象信息以及所述对象信息对应的运行数据;
    控制模块,设置为控制所述空调装置按照所述至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节。
  11. 一种空调装置,包括:
    传感器,设置为采集获取预设区域内的至少一个对象的对象信息;
    控制器,设置为使用预设模型对所述至少一个对象的对象信息进行处理,得到与所述至少一个对象对应的空调装置的运行数据,并控制所述空调装置按照所 述至少一个对象对应的运行数据对该对象所在的子区域的环境参数进行调节,其中,所述预设模型为使用多组数据通过神经网络学习训练得到的,所述多组数据中的每组数据均包括:所述对象信息以及所述对象信息对应的运行数据。
  12. 一种存储介质,所述存储介质包括存储的程序,其中,所述程序执行权利要求1至9中任意一项所述的控制空调的方法。
  13. 一种处理器,所述处理器设置为运行程序,其中,所述程序运行时执行权利要求1至9中任意一项所述的控制空调的方法。
PCT/CN2018/119603 2018-08-31 2018-12-06 控制空调的方法、装置和空调装置 WO2020042417A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811014406.XA CN109140665A (zh) 2018-08-31 2018-08-31 控制空调的方法、装置和空调装置
CN201811014406.X 2018-08-31

Publications (1)

Publication Number Publication Date
WO2020042417A1 true WO2020042417A1 (zh) 2020-03-05

Family

ID=64825959

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/119603 WO2020042417A1 (zh) 2018-08-31 2018-12-06 控制空调的方法、装置和空调装置

Country Status (2)

Country Link
CN (1) CN109140665A (zh)
WO (1) WO2020042417A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110207338A (zh) * 2019-05-20 2019-09-06 珠海格力电器股份有限公司 一种空调控制方法、装置、存储介质及空调
CN110578987B (zh) * 2019-08-08 2021-02-19 安徽美博智能电器有限公司 基于云端的空调防火系统、方法及存储介质
CN110736233B (zh) * 2019-10-29 2020-10-16 珠海格力电器股份有限公司 空调控制方法及装置
CN110749055A (zh) * 2019-10-29 2020-02-04 珠海格力电器股份有限公司 控制空调的方法、装置和系统
CN110865666A (zh) * 2019-12-09 2020-03-06 Oppo广东移动通信有限公司 温度控制方法、装置、存储介质及电子设备
CN111306091B (zh) * 2020-03-31 2022-07-15 佛山市云米电器科技有限公司 智能家居设备、智能出风系统及其出风段变化的控制方法
CN111561771A (zh) * 2020-06-16 2020-08-21 重庆大学 一种空调温度智能调节方法
CN115875813A (zh) * 2022-12-06 2023-03-31 珠海格力电器股份有限公司 送风控制方法、空调器及存储介质
CN116481128B (zh) * 2023-05-10 2023-11-24 佛山市清源科技有限公司 空气净化系统、空气净化方法及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1414313A (zh) * 2002-12-05 2003-04-30 上海交通大学 个性化空调器
CN104374053A (zh) * 2014-11-25 2015-02-25 珠海格力电器股份有限公司 一种智能控制方法、装置及系统
CN105890109A (zh) * 2016-03-31 2016-08-24 华南理工大学 一种房间空调器在线长效性能检测及优化运行方法
CN107816781A (zh) * 2017-10-31 2018-03-20 珠海格力电器股份有限公司 空调的控制方法和装置
CN108019901A (zh) * 2017-11-16 2018-05-11 青岛安森克电子有限公司 一种定向调节空调

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5860286A (en) * 1997-06-06 1999-01-19 Carrier Corporation System monitoring refrigeration charge
CN105910225A (zh) * 2016-04-18 2016-08-31 浙江大学 一种基于人员信息检测的空调负荷控制系统及方法
CN108181837B (zh) * 2017-11-28 2020-11-27 珠海格力电器股份有限公司 控制方法及控制装置
CN108279573B (zh) * 2018-02-05 2019-05-28 北京儒博科技有限公司 基于人体属性检测的控制方法、装置、智能家电和介质
CN108413588B (zh) * 2018-02-12 2021-03-02 北京工业大学 一种基于热成像及bp神经网络的个性化空调控制系统及方法
CN108426349B (zh) * 2018-02-28 2020-04-17 天津大学 基于复杂网络与图像识别的空调个性化健康管理方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1414313A (zh) * 2002-12-05 2003-04-30 上海交通大学 个性化空调器
CN104374053A (zh) * 2014-11-25 2015-02-25 珠海格力电器股份有限公司 一种智能控制方法、装置及系统
CN105890109A (zh) * 2016-03-31 2016-08-24 华南理工大学 一种房间空调器在线长效性能检测及优化运行方法
CN107816781A (zh) * 2017-10-31 2018-03-20 珠海格力电器股份有限公司 空调的控制方法和装置
CN108019901A (zh) * 2017-11-16 2018-05-11 青岛安森克电子有限公司 一种定向调节空调

Also Published As

Publication number Publication date
CN109140665A (zh) 2019-01-04

Similar Documents

Publication Publication Date Title
WO2020042417A1 (zh) 控制空调的方法、装置和空调装置
CN106152408B (zh) 智能空调控制器、控制方法及空调器
US10871302B2 (en) Artificial intelligence air conditioner and control method thereof
US11022333B2 (en) Control for device in a predetermined space area
TWI617200B (zh) 智能空調控制系統及其智能控制方法
CN108052014A (zh) 智能家居的控制方法、系统及计算机可读存储介质
US9551503B2 (en) Comfort control system, user-end subsystem thereof, and system-end device thereof
WO2023115928A1 (zh) 室内环境控制方法、装置、系统及存储介质
CN112378056B (zh) 智能空调控制方法、装置、计算机设备和存储介质
CN108332373B (zh) 一种室内环境状态的控制方法、装置、存储介质及空调
CN106642513A (zh) 智能节能环境调控系统及方法
CN109489212A (zh) 一种空调智能睡眠控制方法、调整系统及设备
CN107229262A (zh) 一种智能家居系统
WO2023035678A1 (zh) 用于控制空调的方法及装置、空调、存储介质
CN110017586A (zh) 运行控制方法、装置、空调器和计算机可读存储介质
CN110726212B (zh) 空调器的控制方法及装置、空调器设备
CN108388141A (zh) 一种基于人脸识别的智慧家庭控制系统和方法
CN109602264A (zh) 一种基于卷积神经网络的食物识别智能烹饪控制方法
CN110749055A (zh) 控制空调的方法、装置和系统
CN110736232A (zh) 空调控制方法及装置
CN114838470A (zh) 一种暖通空调的控制方法和系统
CN110726215B (zh) 空调器及其控制方法、装置、存储介质和处理器
CN110779143B (zh) 空调的控制方法、装置、设备和空调
CN108426349A (zh) 基于复杂网络与图像识别的空调个性化健康管理方法
CN108419439A (zh) 家用设备学习方法、及服务器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18931820

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18931820

Country of ref document: EP

Kind code of ref document: A1