CN116481149B - Method and system for configuring indoor environment parameters - Google Patents
Method and system for configuring indoor environment parameters Download PDFInfo
- Publication number
- CN116481149B CN116481149B CN202310728099.6A CN202310728099A CN116481149B CN 116481149 B CN116481149 B CN 116481149B CN 202310728099 A CN202310728099 A CN 202310728099A CN 116481149 B CN116481149 B CN 116481149B
- Authority
- CN
- China
- Prior art keywords
- model
- home terminal
- human body
- indoor environment
- parameters
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000013145 classification model Methods 0.000 claims description 58
- 230000004927 fusion Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 abstract 1
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 239000002699 waste material Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- 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
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides a method and a system for configuring indoor environment parameters, comprising the following steps: when a plurality of human bodies exist in the current indoor environment, acquiring target image information of each human body in the current indoor environment; determining a comfortable environment configuration most suitable for the human body at present based on the target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters comprise temperature, humidity and PM2.5; determining a target indoor electrical appliance to be configured in an indoor environment based on the comfortable environment configuration; and sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration. According to the invention, when different human bodies exist in the indoor environment, the current comfortable environment configuration most suitable for the human bodies is determined, so that the indoor environment is managed and regulated based on the indoor electrical appliances.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and a system for configuring indoor environment parameters.
Background
Currently, when a human body is in an indoor environment, it is generally required to adjust temperature, humidity, air quality, wind speed, etc. in order to ensure comfort. In order to realize the adjustment of the indoor environment, a user can configure various indoor electrical appliances in the indoor environment to adjust various parameters so as to achieve the optimal comfortable environment; such as air conditioners, purifiers, humidifiers, etc.
However, different human bodies have different feelings on the environment, that is, different comfortable environments required by different human bodies have some differences, and at present, different indoor environment management cannot be performed according to the different human bodies. Furthermore, the current use data of the household appliances are not well applied, so that the waste of data resources is caused.
Disclosure of Invention
The invention mainly aims to provide a method and a system for configuring indoor environment parameters, which aim to overcome the defect that the indoor environment management cannot be differentiated according to different human bodies at present, and also overcome the defect of data resource waste.
To achieve the above object, the present invention provides a method for configuring indoor environment parameters, comprising the steps of:
when a plurality of human bodies exist in the current indoor environment, acquiring target image information of each human body in the current indoor environment;
Determining a comfortable environment configuration most suitable for the human body at present based on the target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5;
determining a target indoor electrical appliance to be configured in an indoor environment based on the comfortable environment configuration;
transmitting the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and configuring the parameters of the indoor environment based on the target indoor electric appliance so that the indoor environment is in the optimal configuration;
setting a data recording time point every other hour;
at each data recording time point, recording the number of times the air conditioner, the purifier and the humidifier are used for configuring the indoor environment in a preset time period before the data recording time point, and recording a corresponding time period; the times are respectively recorded as a first time, a second time and a third time, and a time vector is formed as follows: { first number of times, second number of times, third number of times };
forming training pairs by the frequency vectors and the corresponding time periods;
inputting a plurality of training pairs into a preset network model for iterative training, and obtaining an electrical preference model after training is completed; wherein the appliance preference model is used to predict preference habits of different time periods in the air conditioner, purifier and humidifier.
Further, the step of determining a comfortable environment configuration currently most suitable for the human body based on the target image information of the human body includes:
inputting the target image information of the human body into a preset age classification model for detection to obtain age classifications corresponding to the human bodies; the age classification comprises young children, adults and old people, and the age classification model is a deep learning network model which is trained in advance;
if the age classification results of the human bodies are different, determining a target age classification with the highest priority according to the age classification priority stored in the database; wherein, the age classification priority meets the requirement of the old > young > adults;
and obtaining target indoor environment parameter configuration corresponding to the target age classification based on the mapping relation between the age classification stored in the database and the indoor environment parameter configuration, and taking the target indoor environment parameter configuration as the current comfortable environment configuration which is most suitable for the human body.
Further, before the step of determining the comfortable environment configuration most suitable for the human body currently based on the target image information of the human body, the method includes:
Acquiring positioning information of a current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
acquiring a first model parameter sent by the first home terminal, a second model parameter sent by the second home terminal and a third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
acquiring an initial network model, wherein the initial network model has initial model parameters;
updating the initial model parameters of the initial network model into first model parameters to obtain a first network model; updating the initial model parameters of the initial network model into second model parameters to obtain a second network model; updating the initial model parameters of the initial network model into third model parameters to obtain a third network model;
Collecting human body images in a plurality of indoor environments;
the same human body image is respectively input into the first network model, the second network model and the third network model for prediction; if the prediction results are different, discarding the human body image; if the predicted results are the same, the predicted results are used as labels of the human body images; forming training image data by the human body image and the corresponding label;
and acquiring a public data set, inputting a plurality of training image data and the public data set into the initial network model for training, and obtaining the age classification model.
Further, the step of inputting the target image information of the human body into a preset age classification model for detection to obtain the age classification corresponding to each human body comprises the following steps:
inputting the target image information of the human body into the first network model, the second network model and the third network model for prediction; judging whether the prediction results are consistent with the prediction results of the age classification model, if not, discarding the target image information of the human body, and re-collecting the target image information of each human body in the current indoor environment; and if the prediction results are consistent, determining that the prediction results of the age classification model are correct.
Further, before the step of determining the comfortable environment configuration most suitable for the human body currently based on the target image information of the human body, the method includes:
acquiring positioning information of a current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
acquiring a first model parameter sent by the first home terminal, a second model parameter sent by the second home terminal and a third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
performing fusion operation on the first model parameter, the second model parameter and the third model parameter to obtain a fusion model parameter;
Acquiring an initial network model, wherein the initial network model has initial model parameters;
updating the initial model parameters of the initial network model into the fusion model parameters to obtain a fusion network model;
and acquiring a training sample manufactured aiming at the current indoor environment, acquiring a public data set, inputting the training sample and the public data set into the fusion network model for training again, and obtaining the age classification model.
Further, the step of determining a target indoor appliance to be configured in the indoor environment based on the comfortable environment configuration includes:
acquiring various parameters in the comfortable environment configuration;
acquiring all indoor electrical appliances of the indoor environment access network;
acquiring the function of each indoor electric appliance, and judging whether the function comprises parameters for adjusting the comfortable environment configuration; and if so, taking the corresponding indoor electric appliance as the target indoor electric appliance.
The invention also provides a system for configuring indoor environment parameters, which comprises:
the first acquisition unit is used for acquiring target image information of each human body in the current indoor environment when a plurality of human bodies exist in the current indoor environment;
A first determining unit configured to determine a comfortable environment configuration currently most suitable for the human body based on target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5;
the second determining unit is used for determining target indoor appliances needing to be configured in the indoor environment based on the comfortable environment configuration;
and the configuration unit is used for sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration.
Further, the first determining unit includes:
the detection subunit is used for inputting the target image information of the human body into a preset age classification model for detection to obtain age classifications corresponding to the human bodies; the age classification comprises young children, adults and old people, and the age classification model is a deep learning network model which is trained in advance;
a determining subunit, configured to determine, if the age classification results of the human bodies are different, a target age classification with a highest priority according to the age classification priority stored in the database; wherein, the age classification priority meets the requirement of the old > young > adults;
The configuration subunit is configured to obtain a target indoor environment parameter configuration corresponding to the target age classification based on the mapping relationship between the age classification stored in the database and the indoor environment parameter configuration, and use the target indoor environment parameter configuration as the current comfortable environment configuration most suitable for the human body.
Further, the system comprises:
the first acquisition unit is used for acquiring positioning information of the current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
the second obtaining unit is used for obtaining the first model parameter sent by the first home terminal, the second model parameter sent by the second home terminal and the third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
A third acquisition unit configured to acquire an initial network model, the initial network model having initial model parameters;
the updating unit is used for updating the initial model parameters of the initial network model into first model parameters to obtain a first network model; updating the initial model parameters of the initial network model into second model parameters to obtain a second network model; updating the initial model parameters of the initial network model into third model parameters to obtain a third network model;
the second acquisition unit is used for acquiring human body images in a plurality of indoor environments;
the prediction unit is used for respectively inputting the same human body image into the first network model, the second network model and the third network model for prediction; if the prediction results are different, discarding the human body image; if the predicted results are the same, the predicted results are used as labels of the human body images; forming training image data by the human body image and the corresponding label;
and the training unit is used for acquiring a public data set, inputting a plurality of training image data and the public data set into the initial network model for training, and obtaining the age classification model.
The invention also provides a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of any of the methods described above when the computer program is executed.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the preceding claims.
The invention provides a method and a system for configuring indoor environment parameters, comprising the following steps: when a plurality of human bodies exist in the current indoor environment, acquiring target image information of each human body in the current indoor environment; determining a comfortable environment configuration most suitable for the human body at present based on the target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5; determining a target indoor electrical appliance to be configured in an indoor environment based on the comfortable environment configuration; and sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration. According to the invention, when different human bodies exist in the indoor environment, the current comfortable environment configuration most suitable for the human bodies is determined, so that the indoor environment parameters are adjusted based on the indoor electrical appliances.
Drawings
FIG. 1 is a schematic diagram showing steps of a method for configuring indoor environment parameters according to an embodiment of the present invention;
FIG. 2 is a block diagram of a system for configuring indoor environment parameters in accordance with one embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, in one embodiment of the present invention, a method for configuring indoor environment parameters is provided, including the steps of:
step S1, when a plurality of human bodies exist in a current indoor environment, acquiring target image information of each human body in the current indoor environment;
step S2, determining the comfortable environment configuration most suitable for the human body at present based on the target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5;
Step S3, determining a target indoor electric appliance to be configured in the indoor environment based on the comfortable environment configuration;
and S4, sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration.
In this embodiment, as described in the above step S1, when there are a plurality of human bodies in the current indoor environment, the target image information of each human body in the current indoor environment may be acquired by the camera set in the indoor environment, it may be understood that one image information may be acquired for each human body separately, or one image including all human bodies may be acquired, which is not limited herein.
As described in the above step S2, based on the target image information of the human body, determining a comfortable environment configuration currently most suitable for the human body; the comfortable environment configuration is suitable for the current human body, and is differentiated according to different human bodies. The comfortable environment configuration comprises optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5; for example, the comfort environment configuration described above includes: the temperature is 25.5 ℃, the humidity is 65%, and PM is 2.5-20 mug/m.
As described in the above step S3, it is determined that the comfortable environment configuration needs to be adjusted by using corresponding indoor appliances, and the indoor environment has a plurality of indoor appliances, so that it is necessary to select a target indoor appliance capable of configuring the comfortable environment configuration from the plurality of indoor appliances in the indoor environment.
After determining the target indoor electrical appliance, the target indoor electrical appliance can send the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electrical appliance, and the target indoor electrical appliance can detect each environmental parameter of the current indoor environment after receiving the optimal configuration and judge whether each environmental parameter is in the corresponding optimal configuration, if so, adjustment is not needed; if not, the target indoor electric appliance is required to be adopted to adjust the environmental parameters so that the indoor environment is in the optimal configuration.
In this embodiment, the target indoor electric appliance includes an air conditioner, a purifier, and a humidifier; after the step S4 of performing parameter configuration of the indoor environment based on the target indoor electrical apparatus, the method includes:
step S5, setting a data recording time point every other hour; for example, each quasi-point time may be regarded as a data recording time point, such as an eight-point integer, a nine-point integer.
Step S6, recording the times of the air conditioner, the purifier and the humidifier used for configuring the indoor environment in a preset time period before the data recording time point at each data recording time point, and recording the corresponding time period; the times are respectively recorded as a first time, a second time and a third time, and a time vector is formed as follows: { first number of times, second number of times, third number of times }; for example, the preset time period is 3 hours, when one of the data recording time points is eight points, the number of times that the air conditioner, the purifier and the humidifier are used for configuring the indoor environment in the period of 5-8 points is obtained, and so on, the data is obtained.
Step S7, forming training pairs by the frequency vectors and the corresponding time periods;
step S8, inputting a plurality of training pairs into a preset network model for iterative training, and obtaining an electrical preference model after training; wherein the appliance preference model is used to predict preference habits of different time periods in the air conditioner, purifier and humidifier later when needed.
In this embodiment, based on the above process, not only is the data of the home appliance used effectively, avoiding the waste of data resources, but also the above appliance preference model can be obtained for determining preference habits.
In an embodiment, the step S2 of determining a comfortable environment configuration most suitable for the human body at present based on the target image information of the human body includes:
step S21, inputting the target image information of the human body into a preset age classification model for detection to obtain age classifications corresponding to the human bodies; the age classification comprises young children, adults and old people, and the age classification model is a deep learning network model which is trained in advance;
step S22, if the age classification results of the human bodies are different, determining a target age classification with the highest priority according to the age classification priority stored in the database; wherein, the age classification priority meets the requirement of the old > young > adults;
step S23, obtaining target indoor environment parameter configuration corresponding to the target age classification based on the mapping relation between the age classification stored in the database and the indoor environment parameter configuration, and taking the target indoor environment parameter configuration as the current comfortable environment configuration which is most suitable for the human body.
In this embodiment, when there are multiple human bodies in the indoor environment, it is necessary to make the human body with high age priority meet the best comfortable environment preferentially according to the age of the human body and the age priority; for example, when the elderly, young children, and adults (young adults) exist in the indoor environment, the priority of the elderly is highest, so that the indoor environment preferably satisfies the optimal comfort environment of the elderly.
Therefore, it is necessary to classify the ages of the human bodies in the indoor environment, specifically, input the target image information of the human bodies into a preset age classification model for detection, and obtain the age classification corresponding to each human body through detection; if the ages of the human bodies in the indoor environment are different, the age classification results of the human bodies are different, and at the moment, the target age classification with the highest priority can be determined according to the age classification priority stored in the database, if the indoor environment has the old, the old is the highest priority; when no old people exist in the indoor environment, the child is the highest in priority, and the child is the adult. And finally, obtaining target indoor environment parameter configuration corresponding to the target age classification based on the mapping relation between the age classification stored in the database and the indoor environment parameter configuration, and taking the target indoor environment parameter configuration as the current comfortable environment configuration which is most suitable for the human body. According to the comfortable environment configuration, the environment parameters of the indoor environment are configured, and although the environment parameters cannot meet the requirements of all human bodies, the environment parameters of old people or young children can be preferentially met, so that the indoor environment management which is differentiated according to the differences of the human bodies is formed.
In an embodiment, before the step S2 of determining the comfortable environment configuration most suitable for the human body currently based on the target image information of the human body, the method includes:
Step S201, positioning information of the current indoor environment is obtained, and a first home terminal, a second home terminal and a third home terminal are matched from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification; since the age classification model used in the indoor environment is a deep learning network model, which requires pre-training, and training data in the indoor environment is limited, joint training can be performed with reference to classification models used in other households. In order to avoid too much difference of classification models among different families, when selecting the classification models of the first family terminal, the second family terminal and the third family terminal, preferentially selecting the first family terminal, the second family terminal and the third family terminal, wherein the distance between the position of the first family terminal, the second family terminal and the positioning information of the indoor environment is within a preset range; when the distance is relatively close, families have a certain similarity, and the reference degree is higher.
Step S202, acquiring a first model parameter sent by the first home terminal, a second model parameter sent by the second home terminal and a third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed; the network model in the indoor environment has little training data, but the training data is related to some privacy of each family, so it is not preferable to directly acquire the training data of the first family, the second family and the third family, but acquire the first model parameter transmitted by the first family terminal, the second model parameter transmitted by the second family terminal and the third model parameter transmitted by the third family terminal, and the respective model parameters do not have privacy data, and are only weights of the respective parameters in the model. Therefore, the privacy data of each family cannot be revealed by transmitting the model parameters, and privacy protection is facilitated.
Step S203, an initial network model is obtained, wherein the initial network model has initial model parameters; the initial network model is a deep learning network model on a management system terminal in the indoor environment.
Step S204, updating the initial model parameters of the initial network model into first model parameters to obtain a first network model; updating the initial model parameters of the initial network model into second model parameters to obtain a second network model; updating the initial model parameters of the initial network model into third model parameters to obtain a third network model; in this embodiment, three different network models can be obtained by the above method, and since the model parameters are the model parameters of the classification models on the first home terminal, the second home terminal, and the third home terminal, the three network models are also corresponding to the classification models on the first home terminal, the second home terminal, and the third home terminal.
Step S205, collecting human body images in a plurality of indoor environments;
step S206, the same human body image is respectively input into the first network model, the second network model and the third network model for prediction; if the prediction results are different, discarding the human body image; if the predicted results are the same, the predicted results are used as labels of the human body images; forming training image data by the human body image and the corresponding label; it can be understood that if the confidence levels of the first network model, the second network model and the third network model for classifying the human body in the indoor environment are all high, the prediction results obtained by the first network model, the second network model and the third network model should be the same; if the predicted result is different, the confidence is low, and the predicted result is not suitable to be used as a label corresponding to the human body image. This process corresponds to labeling the human body image in the indoor environment to obtain training image data suitable for the indoor environment.
Step S207, a public data set is obtained, a plurality of training image data and the public data set are input into the initial network model for training, and the age classification model is obtained. In this embodiment, since the number of the training image data is small, in order to avoid the model from being over-fitted, the training data amount needs to be increased, and thus, a public data set in the internet database, which is public data, is acquired. And inputting the training image data and the public data set into the initial network model for training to obtain the age classification model. In the process, the training data volume is increased, the training image data of the indoor environment is adopted, pertinence is achieved, and the accuracy and the confidence of model training are improved.
In another embodiment, after the step S21 of inputting the target image information of the human body into a preset age classification model to detect, the step of detecting to obtain the age classification corresponding to each human body includes:
step S211, inputting the target image information of the human body into the first network model, the second network model and the third network model for prediction; judging whether the prediction results are consistent with the prediction results of the age classification model, if not, discarding the target image information of the human body, and re-collecting the target image information of each human body in the current indoor environment; and if the prediction results are consistent, determining that the prediction results of the age classification model are correct.
In another embodiment, before the step S2 of determining the comfortable environment configuration most suitable for the human body currently based on the target image information of the human body, the method includes:
step S2a, positioning information of the current indoor environment is obtained, and a first home terminal, a second home terminal and a third home terminal are matched from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification; this step is similar to step S201 described above, and will not be described again here.
Step S2b, acquiring a first model parameter sent by the first home terminal, a second model parameter sent by the second home terminal and a third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed; this step is similar to step S202 described above, and will not be described again here.
Step S2c, fusion operation is carried out on the first model parameter, the second model parameter and the third model parameter, and fusion model parameters are obtained; in this embodiment, in order to combine the characteristics of the first model parameter, the second model parameter, and the third model parameter, the first model parameter, the second model parameter, and the third model parameter are fused, so that the model parameters of the classification models of the plurality of home terminals are referred to, and the confidence of the models is enhanced.
S2d, acquiring an initial network model, wherein the initial network model has initial model parameters; the initial network model is a deep learning network model on a management system terminal in the indoor environment.
Step S2e, updating the initial model parameters of the initial network model into the fusion model parameters to obtain a fusion network model;
and S2f, acquiring a training sample manufactured aiming at the current indoor environment, acquiring a public data set, inputting the training sample and the public data set into the fusion network model, and training again to obtain the age classification model. In this embodiment, since the number of training samples is small, in order to avoid the model from being over-fitted, the training data amount needs to be increased, and thus, a public data set in the internet database, which is public data, is acquired. And inputting the training sample and the public data set into the initial network model for training to obtain the age classification model. In the process, the training data volume is increased, the training sample manufactured aiming at the current indoor environment is adopted, pertinence is achieved, and the accuracy and the confidence of model training are improved.
In an embodiment, a solution for determining a target indoor appliance in an indoor scene is provided, specifically, based on the comfort environment configuration, a step S3 of determining a target indoor appliance that needs to be configured in an indoor environment includes:
acquiring various parameters in the comfortable environment configuration;
acquiring all indoor electrical appliances of the indoor environment access network;
acquiring the function of each indoor electric appliance, and judging whether the function comprises parameters for adjusting the comfortable environment configuration; and if so, taking the corresponding indoor electric appliance as the target indoor electric appliance.
Referring to fig. 2, in one embodiment of the present invention, there is also provided a system for configuring indoor environment parameters, including:
the first acquisition unit is used for acquiring target image information of each human body in the current indoor environment when a plurality of human bodies exist in the current indoor environment;
a first determining unit configured to determine a comfortable environment configuration currently most suitable for the human body based on target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5;
the second determining unit is used for determining target indoor appliances needing to be configured in the indoor environment based on the comfortable environment configuration;
And the configuration unit is used for sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration.
A setting unit configured to set a data recording time point every hour;
a recording unit for recording the number of times the air conditioner, the purifier and the humidifier are used for configuring the indoor environment in a preset time period before the data recording time point at each data recording time point, and recording the corresponding time period; the times are respectively recorded as a first time, a second time and a third time, and a time vector is formed as follows: { first number of times, second number of times, third number of times };
the composing unit is used for composing the frequency vector and the corresponding time period into training pairs;
the preference model training unit is used for inputting a plurality of training pairs into a preset network model to perform iterative training, and the training is completed to obtain an electrical preference model; wherein the appliance preference model is used to predict preference habits of different time periods in the air conditioner, purifier and humidifier.
In an embodiment, the first determining unit includes:
the detection subunit is used for inputting the target image information of the human body into a preset age classification model for detection to obtain age classifications corresponding to the human bodies; the age classification comprises young children, adults and old people, and the age classification model is a deep learning network model which is trained in advance;
a determining subunit, configured to determine, if the age classification results of the human bodies are different, a target age classification with a highest priority according to the age classification priority stored in the database; wherein, the age classification priority meets the requirement of the old > young > adults;
the configuration subunit is configured to obtain a target indoor environment parameter configuration corresponding to the target age classification based on the mapping relationship between the age classification stored in the database and the indoor environment parameter configuration, and use the target indoor environment parameter configuration as the current comfortable environment configuration most suitable for the human body.
In another embodiment, the system comprises:
the first acquisition unit is used for acquiring positioning information of the current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
The second obtaining unit is used for obtaining the first model parameter sent by the first home terminal, the second model parameter sent by the second home terminal and the third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
a third acquisition unit configured to acquire an initial network model, the initial network model having initial model parameters;
the updating unit is used for updating the initial model parameters of the initial network model into first model parameters to obtain a first network model; updating the initial model parameters of the initial network model into second model parameters to obtain a second network model; updating the initial model parameters of the initial network model into third model parameters to obtain a third network model;
the second acquisition unit is used for acquiring human body images in a plurality of indoor environments;
the prediction unit is used for respectively inputting the same human body image into the first network model, the second network model and the third network model for prediction; if the prediction results are different, discarding the human body image; if the predicted results are the same, the predicted results are used as labels of the human body images; forming training image data by the human body image and the corresponding label;
And the training unit is used for acquiring a public data set, inputting a plurality of training image data and the public data set into the initial network model for training, and obtaining the age classification model.
In this embodiment, for specific implementation of each unit and subunit in the system for configuring indoor environment parameters, please refer to the method embodiment described in the foregoing embodiment for configuring indoor environment parameters, and no further description is given here.
Referring to fig. 3, in an embodiment of the present invention, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing human body image data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of configuring indoor environment parameters.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of configuring indoor environment parameters. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
In summary, the method and system for configuring indoor environment parameters provided in the embodiment of the present invention include: when a plurality of human bodies exist in the current indoor environment, acquiring target image information of each human body in the current indoor environment; determining a comfortable environment configuration most suitable for the human body at present based on the target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5; determining a target indoor electrical appliance to be configured in an indoor environment based on the comfortable environment configuration; and sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration. According to the invention, when different human bodies exist in the indoor environment, the current comfortable environment configuration most suitable for the human bodies is determined, so that the indoor environment parameters are adjusted based on the indoor electrical appliances.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (4)
1. A method of configuring indoor environmental parameters, comprising the steps of:
when a plurality of human bodies exist in the current indoor environment, acquiring target image information of each human body in the current indoor environment;
Determining a comfortable environment configuration most suitable for the human body at present based on the target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5;
determining a target indoor electrical appliance to be configured in an indoor environment based on the comfortable environment configuration; the target indoor electrical appliance comprises an air conditioner, a purifier and a humidifier;
transmitting the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and configuring the parameters of the indoor environment based on the target indoor electric appliance so that the indoor environment is in the optimal configuration;
setting a data recording time point every other hour;
at each data recording time point, recording the number of times the air conditioner, the purifier and the humidifier are used for configuring the indoor environment in a preset time period before the data recording time point, and recording a corresponding time period; the times are respectively recorded as a first time, a second time and a third time, and a time vector is formed as follows: { first number of times, second number of times, third number of times };
forming training pairs by the frequency vectors and the corresponding time periods;
Inputting a plurality of training pairs into a preset network model for iterative training, and obtaining an electrical preference model after training is completed; wherein the appliance preference model is used for predicting preference habits of different time periods in the air conditioner, the purifier and the humidifier;
the step of determining a comfortable environment configuration currently most suitable for the human body based on the target image information of the human body includes:
inputting the target image information of the human body into a preset age classification model for detection to obtain age classifications corresponding to the human bodies; the age classification comprises young children, adults and old people, and the age classification model is a deep learning network model which is trained in advance;
if the age classification results of the human bodies are different, determining a target age classification with the highest priority according to the age classification priority stored in the database; wherein, the age classification priority meets the requirement of the old > young > adults;
obtaining target indoor environment parameter configuration corresponding to the target age classification based on the mapping relation between the age classification stored in the database and the indoor environment parameter configuration, and taking the target indoor environment parameter configuration as the current comfortable environment configuration which is most suitable for the human body;
Before the step of determining the comfortable environment configuration most suitable for the human body currently based on the target image information of the human body, the method comprises the following steps:
acquiring positioning information of a current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
acquiring a first model parameter sent by the first home terminal, a second model parameter sent by the second home terminal and a third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
acquiring an initial network model, wherein the initial network model has initial model parameters;
Updating the initial model parameters of the initial network model into first model parameters to obtain a first network model; updating the initial model parameters of the initial network model into second model parameters to obtain a second network model; updating the initial model parameters of the initial network model into third model parameters to obtain a third network model;
collecting human body images in a plurality of indoor environments;
the same human body image is respectively input into the first network model, the second network model and the third network model for prediction; if the prediction results are different, discarding the human body image; if the predicted results are the same, the predicted results are used as labels of the human body images; forming training image data by the human body image and the corresponding label;
acquiring a public data set, inputting a plurality of training image data and the public data set into the initial network model for training to obtain the age classification model;
the step of inputting the target image information of the human body into a preset age classification model for detection to obtain the age classification corresponding to each human body comprises the following steps:
Inputting the target image information of the human body into the first network model, the second network model and the third network model for prediction; judging whether the prediction results are consistent with the prediction results of the age classification model, if not, discarding the target image information of the human body, and re-collecting the target image information of each human body in the current indoor environment; and if the prediction results are consistent, determining that the prediction results of the age classification model are correct.
2. The method of configuring indoor environment parameters according to claim 1, wherein before the step of determining a comfortable environment configuration currently most suitable for the human body based on the target image information of the human body, comprising:
acquiring positioning information of a current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
Acquiring a first model parameter sent by the first home terminal, a second model parameter sent by the second home terminal and a third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
performing fusion operation on the first model parameter, the second model parameter and the third model parameter to obtain a fusion model parameter;
acquiring an initial network model, wherein the initial network model has initial model parameters;
updating the initial model parameters of the initial network model into the fusion model parameters to obtain a fusion network model;
and acquiring a training sample manufactured aiming at the current indoor environment, acquiring a public data set, inputting the training sample and the public data set into the fusion network model for training again, and obtaining the age classification model.
3. The method of configuring indoor environment parameters according to claim 1, wherein the step of determining a target indoor appliance to be configured in an indoor environment based on the comfort environment configuration comprises:
Acquiring various parameters in the comfortable environment configuration;
acquiring all indoor electrical appliances of the indoor environment access network;
acquiring the function of each indoor electric appliance, and judging whether the function comprises parameters for adjusting the comfortable environment configuration; and if so, taking the corresponding indoor electric appliance as the target indoor electric appliance.
4. A system for configuring parameters of an indoor environment, comprising:
the first acquisition unit is used for acquiring target image information of each human body in the current indoor environment when a plurality of human bodies exist in the current indoor environment;
a first determining unit configured to determine a comfortable environment configuration currently most suitable for the human body based on target image information of the human body; the comfortable environment configuration comprises an optimal configuration of a plurality of parameters in the indoor environment, wherein the parameters at least comprise temperature, humidity and PM2.5;
the second determining unit is used for determining target indoor appliances needing to be configured in the indoor environment based on the comfortable environment configuration; the target indoor electrical appliance comprises an air conditioner, a purifier and a humidifier;
the configuration unit is used for sending the optimal configuration of each parameter in the comfortable environment configuration to the corresponding target indoor electric appliance, and carrying out parameter configuration of the indoor environment based on the target indoor electric appliance so as to enable the indoor environment to be in the optimal configuration;
A setting unit configured to set a data recording time point every hour;
a recording unit for recording the number of times the air conditioner, the purifier and the humidifier are used for configuring the indoor environment in a preset time period before the data recording time point at each data recording time point, and recording the corresponding time period; the times are respectively recorded as a first time, a second time and a third time, and a time vector is formed as follows: { first number of times, second number of times, third number of times };
the composing unit is used for composing the frequency vector and the corresponding time period into training pairs;
the preference model training unit is used for inputting a plurality of training pairs into a preset network model to perform iterative training, and the training is completed to obtain an electrical preference model; wherein the appliance preference model is used for predicting preference habits of different time periods in the air conditioner, the purifier and the humidifier;
the first determination unit includes:
the detection subunit is used for inputting the target image information of the human body into a preset age classification model for detection to obtain age classifications corresponding to the human bodies; the age classification comprises young children, adults and old people, and the age classification model is a deep learning network model which is trained in advance;
A determining subunit, configured to determine, if the age classification results of the human bodies are different, a target age classification with a highest priority according to the age classification priority stored in the database; wherein, the age classification priority meets the requirement of the old > young > adults;
a configuration subunit, configured to obtain a target indoor environment parameter configuration corresponding to the target age classification based on a mapping relationship between the age classification stored in the database and the indoor environment parameter configuration, and use the target indoor environment parameter configuration as the current comfortable environment configuration most suitable for the human body;
the system comprises:
the first acquisition unit is used for acquiring positioning information of the current indoor environment, and matching a first home terminal, a second home terminal and a third home terminal from a network big database according to the positioning information; the distance between the position of the first home terminal, the second home terminal and the third home terminal and the positioning information is within a preset range; the first home terminal, the second home terminal and the third home terminal are respectively three home terminal devices, and each of the first home terminal, the second home terminal and the third home terminal is provided with a classification model which is trained and used for age classification;
The second obtaining unit is used for obtaining the first model parameter sent by the first home terminal, the second model parameter sent by the second home terminal and the third model parameter sent by the third home terminal; the first model parameter, the second model parameter and the third model parameter are model parameters when training of the corresponding classification model is completed;
a third acquisition unit configured to acquire an initial network model, the initial network model having initial model parameters;
the updating unit is used for updating the initial model parameters of the initial network model into first model parameters to obtain a first network model; updating the initial model parameters of the initial network model into second model parameters to obtain a second network model; updating the initial model parameters of the initial network model into third model parameters to obtain a third network model;
the second acquisition unit is used for acquiring human body images in a plurality of indoor environments;
the prediction unit is used for respectively inputting the same human body image into the first network model, the second network model and the third network model for prediction; if the prediction results are different, discarding the human body image; if the predicted results are the same, the predicted results are used as labels of the human body images; forming training image data by the human body image and the corresponding label;
And the training unit is used for acquiring a public data set, inputting a plurality of training image data and the public data set into the initial network model for training, and obtaining the age classification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310728099.6A CN116481149B (en) | 2023-06-20 | 2023-06-20 | Method and system for configuring indoor environment parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310728099.6A CN116481149B (en) | 2023-06-20 | 2023-06-20 | Method and system for configuring indoor environment parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116481149A CN116481149A (en) | 2023-07-25 |
| CN116481149B true CN116481149B (en) | 2023-09-01 |
Family
ID=87219900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310728099.6A Active CN116481149B (en) | 2023-06-20 | 2023-06-20 | Method and system for configuring indoor environment parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116481149B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117968222B (en) * | 2024-04-01 | 2024-05-28 | 深圳市森皓伟业制冷设备有限公司 | Control method and device of refrigeration equipment based on target detection |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111076379A (en) * | 2019-12-26 | 2020-04-28 | 海信集团有限公司 | Room temperature control method and air conditioner |
| JP2020153618A (en) * | 2019-03-22 | 2020-09-24 | Ｆｐｔソフトウェアジャパン株式会社 | Air conditioning control server device, air conditioning control method and air conditioning control system |
| CN112032985A (en) * | 2020-07-24 | 2020-12-04 | 奇酷互联网络科技（深圳）有限公司 | Air conditioner adjusting method and system, intelligent terminal and storage medium |
| CN114234381A (en) * | 2021-11-26 | 2022-03-25 | 国网上海市电力公司 | Central air conditioner control method and system based on reinforcement learning |
| KR20220055813A (en) * | 2020-10-27 | 2022-05-04 | 주식회사 나인와트 | A platform for providing notification of the ventilation status of welfare centers to the elderly and managing the environment of welfare centers |
| JP2022085821A (en) * | 2020-11-27 | 2022-06-08 | 広東美的制冷設備有限公司 | Air conditioner, its control method, and computer storage medium |
| CN115654675A (en) * | 2022-09-16 | 2023-01-31 | Tcl空调器(中山)有限公司 | Air conditioner operation parameter recommendation method and related equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8547036B2 (en) * | 2011-11-20 | 2013-10-01 | Available For Licensing | Solid state light system with broadband optical communication capability |
| CN108224691B (en) * | 2017-12-22 | 2019-08-16 | 银河水滴科技（北京）有限公司 | A kind of air conditioner system control method and device |
| US12072117B2 (en) * | 2021-09-17 | 2024-08-27 | Airthinx, Inc | Environment management systems and methods |
-
2023
- 2023-06-20 CN CN202310728099.6A patent/CN116481149B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020153618A (en) * | 2019-03-22 | 2020-09-24 | Ｆｐｔソフトウェアジャパン株式会社 | Air conditioning control server device, air conditioning control method and air conditioning control system |
| CN111076379A (en) * | 2019-12-26 | 2020-04-28 | 海信集团有限公司 | Room temperature control method and air conditioner |
| CN112032985A (en) * | 2020-07-24 | 2020-12-04 | 奇酷互联网络科技（深圳）有限公司 | Air conditioner adjusting method and system, intelligent terminal and storage medium |
| KR20220055813A (en) * | 2020-10-27 | 2022-05-04 | 주식회사 나인와트 | A platform for providing notification of the ventilation status of welfare centers to the elderly and managing the environment of welfare centers |
| JP2022085821A (en) * | 2020-11-27 | 2022-06-08 | 広東美的制冷設備有限公司 | Air conditioner, its control method, and computer storage medium |
| CN114234381A (en) * | 2021-11-26 | 2022-03-25 | 国网上海市电力公司 | Central air conditioner control method and system based on reinforcement learning |
| CN115654675A (en) * | 2022-09-16 | 2023-01-31 | Tcl空调器(中山)有限公司 | Air conditioner operation parameter recommendation method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116481149A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116481149B (en) | Method and system for configuring indoor environment parameters | |
| CN109818839B (en) | Personalized behavior prediction method, device and system applied to smart home | |
| WO2019101083A1 (en) | Voice data processing method, voice-based interactive device, and storage medium | |
| KR102639900B1 (en) | Air conditioner | |
| US10382556B2 (en) | Iterative learning for reliable sensor sourcing systems | |
| CN111306700A (en) | Air conditioner control method and device and computer storage medium | |
| CN112532746B (en) | Cloud edge cooperative sensing method and system | |
| JP2008269215A (en) | Unique pattern detection system, model learning device, unique pattern detector method, and computer program | |
| JP2020154785A (en) | Prediction method, prediction program, and model learning method | |
| CN108921952B (en) | Object functionality prediction method, device, computer equipment and storage medium | |
| CN113919923B (en) | Live broadcast recommendation model training method, live broadcast recommendation method and related equipment | |
| Bugeja et al. | Functional classification and quantitative analysis of smart connected home devices | |
| CN112116025A (en) | User classification model training method and device, electronic equipment and storage medium | |
| CN112146236A (en) | Adjusting system, control method, control device, line control device, server and medium | |
| CN114442697A (en) | Temperature control method, equipment, medium and product | |
| CN113325767B (en) | Scene recommendation method and device, storage medium and electronic equipment | |
| CN113158057A (en) | Buddha meridian recommendation processing device, computer equipment and storage medium | |
| CN109993312B (en) | Equipment, information processing method thereof and computer storage medium | |
| CN112541129B (en) | Method and device for processing interaction event | |
| CN117480510A (en) | Generating confidence scores for machine learning model predictions | |
| Farina et al. | Real-time auto calibration for heterogeneous wireless sensor networks | |
| CN112270927A (en) | Intelligent interaction method based on environment adjusting equipment and intelligent interaction equipment | |
| CN110502715A (en) | Click the prediction technique and device of probability | |
| CN112348045A (en) | Training method and training device for neural network and electronic equipment | |
| CN114281192B (en) | Household equipment control method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |