CN113266952A - Temperature control method and system for wall-mounted boiler and server - Google Patents
Temperature control method and system for wall-mounted boiler and server Download PDFInfo
- Publication number
- CN113266952A CN113266952A CN202110567682.4A CN202110567682A CN113266952A CN 113266952 A CN113266952 A CN 113266952A CN 202110567682 A CN202110567682 A CN 202110567682A CN 113266952 A CN113266952 A CN 113266952A
- Authority
- CN
- China
- Prior art keywords
- wall
- temperature
- heating temperature
- model
- human body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H9/00—Details
- F24H9/20—Arrangement or mounting of control or safety devices
Abstract
The invention discloses a temperature control method and system for a wall-mounted furnace and a server. The method comprises the steps of acquiring current human body data of a user from wearable equipment; inputting the current human body data into a preset model to obtain a heating temperature; and transmitting the heating temperature to a wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature. Wherein, through obtaining current human data from wearable equipment to confirm the heating temperature of hanging stove according to current human data, make the user when unable artifical heating temperature that sets up, the heating temperature of hanging stove still can change according to the human condition, and the heating temperature who has avoided the hanging stove is too high or low and influence user's use and experience.
Description
Technical Field
The invention relates to the technical field of household appliances, in particular to a temperature control method and system for a wall-mounted boiler and a server.
Background
With the popularization of energy sources, the wall-mounted boiler is widely applied to the domestic heating market as an economical energy-saving and environment-friendly heating device. The wall-mounted furnace is combined with floor heating or heating radiators, so that the requirement of the household central heating of a user can be met.
At present, the heating temperature of the wall-mounted boiler is usually set by a user operating a key or a remote controller of a display panel of the wall-mounted boiler. When the user is not indoor or is in the sleep state, the temperature demand to hanging stove can produce the change, and the user can't the manual work set up heating temperature this moment, and too high or too low temperature can influence user's use and experience.
Disclosure of Invention
The invention mainly aims to provide a temperature control method, a temperature control system and a server for a wall-mounted furnace, and aims to solve the technical problems that in the prior art, the heating temperature control of the wall-mounted furnace needs to be manually set, and the use experience of a user is reduced.
To achieve the above object, a first aspect of the present invention provides a temperature control method for a wall-hanging stove, the temperature control method comprising the steps of:
acquiring current body data of a user from a wearable device;
inputting the current human body data into a preset model to obtain a heating temperature;
and transmitting the heating temperature to the wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature.
Optionally, the preset model is obtained by:
acquiring multiple groups of historical human body data of a user, wherein the human body data comprises multiple types of electrocardio information, position information and body temperature information;
labeling temperature information corresponding to the wall-mounted furnace on each group of historical human body data to obtain labeled data;
and training the initial model according to the marked data to obtain a preset model.
Optionally, training the initial model according to the labeled data to obtain a preset model, including:
coding the marked data according to the temperature information and the preset temperature;
extracting target characteristics from the coded data, wherein the target characteristics comprise a plurality of body temperature characteristics, heart rate characteristics, position characteristics, blood pressure characteristics and blood oxygen characteristics;
and inputting the target characteristics into the initial model for training to obtain a preset model.
Optionally, the initial model is an Xgboost model; inputting the target characteristics into the initial model for training to obtain a preset model, wherein the training comprises the following steps:
inputting the target characteristics into an Xgboost model for training;
calculating the value of the loss function according to the output result of the Xgboost model;
and adjusting the hyper-parameter of the Xgboost model according to the value of the loss function, and then continuing training to obtain a preset model.
Optionally, the hyper-parameter is a learning rate, and the adjusting the hyper-parameter of the Xgboost model according to the value of the loss function includes:
calculating a difference between a previous value and a current value of the loss function;
determining a rate of decrease of the value of the loss function from the difference;
when the falling speed becomes small, the learning rate is reduced.
Optionally, the temperature control method further comprises:
determining whether the heating temperature is within a preset threshold range before transmitting the heating temperature to the wall-hanging stove;
and returning to the step of acquiring the current human body data of the user from the wearable device under the condition that the heating temperature is not within the preset threshold range.
Optionally, the temperature control method further comprises:
after the heating temperature is obtained, current position information is obtained from current human body data;
and sending the heating temperature to the wall-hanging furnace corresponding to the current position information.
A second aspect of the present invention provides a server, comprising: the temperature control program for the wall-hanging stove is configured to realize the steps of the temperature control method for the wall-hanging stove.
A third aspect of the present invention provides a temperature control system for a wall-hanging stove, the temperature control system for a wall-hanging stove comprising:
a wearable device;
a gateway device;
a wall-mounted furnace; and
as above, the wearable device communicates with the server, and the server communicates with the hanging stove via the gateway device.
Optionally, the temperature control system further comprises:
and the mobile terminal is communicated with the wearable equipment and used for acquiring the current human body data from the wearable equipment and sending the current human body data to the server.
According to the scheme provided by the embodiment of the invention, the current human body data of the user is acquired from the wearable device and input into the preset model to obtain the heating temperature. And transmitting the heating temperature to the wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature. Wherein, through obtaining current human data from wearable equipment to confirm the heating temperature of hanging stove according to current human data, make the user when unable artifical heating temperature that sets up, the heating temperature of hanging stove still can change according to the human condition, and the heating temperature who has avoided the hanging stove is too high or low and influence user's use and experience.
Drawings
FIG. 1 is a schematic diagram of a server architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a temperature control method for a wall-hanging stove according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an embodiment of the current body data of FIG. 2;
FIG. 4 is a schematic diagram of a construction process of the predetermined model in FIG. 2;
FIG. 5 is a training graph of an embodiment of the number of iterations of the predetermined model of FIG. 2 and the value of the loss function;
FIG. 6 is a training graph of the number of iterations of the predetermined model of FIG. 2 versus the value of the loss function in accordance with another embodiment;
FIG. 7 is a schematic flow chart illustrating a temperature control method for a wall-hanging stove according to another embodiment of the present invention;
FIG. 8 is a functional block diagram of an embodiment of a temperature control system for a wall hanging stove of the present invention;
fig. 9 is a functional block diagram of another embodiment of a temperature control system for a wall-hanging stove according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a server structure of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the server may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may comprise a display screen, an input unit such as a keyboard, and the optional user interface 1003 may also comprise a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high speed RAM memory or a stable memory such as a disk memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the architecture shown in FIG. 1 does not constitute a limitation of a server, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a temperature control program for a wall-hanging stove.
In the server shown in fig. 1, the network interface 1004 is mainly used for data communication with an external network; the user interface 1003 is mainly used for receiving input instructions of a user; the server calls, through the processor 1001, a temperature control program for the wall-hanging oven stored in the memory 1005, and performs the following operations:
acquiring current body data of a user from a wearable device;
inputting the current human body data into a preset model to obtain a heating temperature;
and transmitting the heating temperature to the wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature.
Further, the processor 1001 may call a temperature control program for the wall-hanging stove stored in the memory 1005, and also perform the following operations:
acquiring multiple groups of historical human body data of a user, wherein the human body data comprises multiple types of electrocardio information, position information and body temperature information;
labeling temperature information corresponding to the wall-mounted furnace on each group of historical human body data to obtain labeled data;
and training the initial model according to the marked data to obtain a preset model.
Further, the processor 1001 may call a temperature control program for the wall-hanging stove stored in the memory 1005, and also perform the following operations:
coding the marked data according to the temperature information and the preset temperature;
extracting target characteristics from the coded data, wherein the target characteristics comprise a plurality of body temperature characteristics, heart rate characteristics, position characteristics, blood pressure characteristics and blood oxygen characteristics;
and inputting the target characteristics into the initial model for training to obtain a preset model.
Further, the processor 1001 may call a temperature control program for the wall-hanging stove stored in the memory 1005, and also perform the following operations:
inputting the target characteristics into an Xgboost model for training;
calculating the value of the loss function according to the output result of the Xgboost model;
and adjusting the hyper-parameter of the Xgboost model according to the value of the loss function, and then continuing training to obtain a preset model.
Further, the processor 1001 may call a temperature control program for the wall-hanging stove stored in the memory 1005, and also perform the following operations:
calculating a difference between a previous value and a current value of the loss function;
determining a rate of decrease of the value of the loss function from the difference;
when the falling speed becomes small, the learning rate is reduced.
Further, the processor 1001 may call a temperature control program for the wall-hanging stove stored in the memory 1005, and also perform the following operations:
determining whether the heating temperature is within a preset threshold range before transmitting the heating temperature to the wall-hanging stove;
and returning to the step of acquiring the current human body data of the user from the wearable device under the condition that the heating temperature is not within the preset threshold range.
Further, the processor 1001 may call a temperature control program for the wall-hanging stove stored in the memory 1005, and also perform the following operations:
after the heating temperature is obtained, current position information is obtained from current human body data;
and sending the heating temperature to the wall-hanging furnace corresponding to the current position information.
The embodiment acquires the current human body data of the user from the wearable device; inputting the current human body data into a preset model to obtain a heating temperature; and transmitting the heating temperature to the wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature. Wherein, through obtaining current human data from wearable equipment to confirm the heating temperature of hanging stove according to current human data, make the user when unable artifical heating temperature that sets up, the heating temperature of hanging stove still can change according to the human condition, and the heating temperature who has avoided the hanging stove is too high or low and influence user's use and experience.
Based on the hardware structure, the embodiment of the temperature control method for the wall-hanging furnace is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart illustrating a temperature control method for a wall-hanging stove according to an embodiment of the invention.
In this embodiment, the temperature control method for the wall-hanging stove includes the steps of:
s10: acquiring current body data of a user from a wearable device;
it is understood that a wearable device refers to a mobile smart device that can be worn directly on a person or can be incorporated into clothing, accessories and record body data. The wearable device in this embodiment may be an electronic device such as glasses, a bracelet, a watch, and the like.
The human body data refers to data related to a human body, and may be information such as electrocardiographic information (e.g., heart rate, blood pressure, etc.), exercise status, body temperature information, skin information, sleep information, identity information, pressure information, body fatigue, position information, blood pressure, etc. of a user, which is not limited in this embodiment. Further, referring to fig. 2 and 3 together, the exercise state may be an acceleration of Running (Running), an acceleration of fast standing up (standing upfs), an acceleration of slow standing up (standing upfl), an acceleration of squatting down (going down), an acceleration of standing up after squatting (going up), an acceleration of lying down slowly (lying down fs), an acceleration of Walking (Walking), an acceleration of Jumping (Jumping), an acceleration of sitting down (sitting down), and the like.
The body data of the user are changed in real time, and the wearable device can continuously acquire the body data of the user within a period of time, so that the current body data can be understood as the body data of the user acquired by the wearable device at the current moment.
With the development of technology, intelligent wearable devices become important choices of consumers gradually, according to statistics of quarter tracking reports in IDC China wearable device market, the goods output of the intelligent wearable devices in China only in 2019 reaches 1 hundred million, according to investigation of relevant organizations, the annual growth rate of the intelligent wearable devices is about 30-50%, and the increment is considerable.
Compared with electronic equipment such as a mobile phone, the intelligent wearable equipment has the natural advantages of being wearable, and the wearable characteristics of the intelligent wearable equipment determine that the intelligent wearable equipment can collect key biological characteristic information (such as heart rate, blood oxygen, blood pressure, body temperature, motion state, body fatigue, sleep information, body pressure information, skin information, body identity information and the like) of a human body by carrying various sensor equipment. The smart watch in the wearable device can even carry satellite positioning systems such as GPS and Beidou, and Location Based Services (LBS) of the mobile phone is realized. The collected information is used as important decision content for subsequent processing, especially strong interaction with intelligent household appliances, more scenes such as identity authentication and health information can be achieved compared with a mobile phone, and interaction between a person and a machine can be promoted to be higher intensity by matching with the intelligent household appliances.
In this embodiment, through wearable device and hanging stove control combination, detect information such as user's position, skin state, electrocardio state, sleep state, body temperature state by wearable device to adjust the heating temperature of hanging stove according to these information, can make the user keep the most comfortable life state.
In a particular implementation, the server may obtain current body data of the user by communicating with the wearable device. In one embodiment, the wearable device can transmit current human body data to mobile terminals such as mobile phones, and the mobile terminals such as the mobile phones transmit the current human body data to the server through the gateway device, or the mobile terminals such as the mobile phones directly communicate through public cloud; in another embodiment, the wearable device may directly transmit the current human body data to the server through a public cloud, or may communicate with the gateway device through a Universal Subscriber Identity Module (USIM) Module, a bluetooth Module, a WiFi Module, or the like inside the wearable device, and transmit the current human body data through the gateway device.
S20: inputting the current human body data into a preset model to obtain a heating temperature;
it can be understood that the preset model can be obtained by performing data model building by using algorithms such as Xgboost, Catboost, LightGBM and the like and training based on the relationship between human body data and the heating temperature of the wall-hanging stove. In specific implementation, when the number of the wall-hanging furnaces is multiple and the wall-hanging furnaces are installed in different rooms, the preset model can be obtained based on training of the relationship among human body data, the on-off state of the wall-hanging furnaces, the positions of the wall-hanging furnaces and the corresponding heating temperatures. Accordingly, after the current human body data are input into the preset model, the on-off state of each indoor wall-mounted furnace and the heating temperature corresponding to each wall-mounted furnace can be obtained, and therefore each room can set comfortable temperature according to the human body data of a user. In another embodiment, the current human body data is input into a preset model, after the heating temperature corresponding to the current human body data is obtained, the current position information is obtained from the current human body data, and the heating temperature is sent to the wall-hanging stove corresponding to the current position information. Thus, the heating of a certain room can be independently adjusted according to the requirement.
The preset model is mainly based on a machine learning scheme, in other extensible schemes, a deep learning model based on a Long Short-Term Memory network (LSTM) model can be adopted, the LSTM model can well process a time sequence-based classification decision scheme, and a training processing framework of the whole model is the same as that of the machine learning model.
S30: and transmitting the heating temperature to the wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature.
It should be understood that the server may communicate the heating temperature to the wall-hanging stove by communicating with the wall-hanging stove. In an embodiment, the server issues the heating temperature to the inside automatically controlled board of hanging stove through gateway equipment in, and automatically controlled board control hanging stove intelligence adjusts the temperature to provide more comfortable house living environment, can the wall built-up heating automatically when the user leaves the home or when going on business, realized the purpose of fuel saving and environmental protection.
One of the usage scenarios of the present embodiment is: when the user leaves home, the wearable device detects the current human body data (including position information) of the user, and interacts with the server through the mobile phone or directly, the server processes the current human body data to obtain the heating temperature, and sends the heating temperature to the wall-mounted furnace through the gateway device, and the wall-mounted furnace cools down or closes according to the heating temperature to achieve the purpose of energy conservation.
Another usage scenario of this embodiment is: when a user is in a sleep state at home, the wearable device detects current human body data (including a skin drying state, a sleep state, electrocardiogram information and the like) of the user, the wearable device interacts with the server through a mobile phone or directly, the server processes the current human body data to obtain heating temperature, the heating temperature is issued to the wall-mounted furnace through the gateway device, and the wall-mounted furnace dynamically adjusts the temperature according to the heating temperature, so that the sleep quality cannot be influenced by dryness and humidity of the indoor environment and overhigh or overlow indoor temperature.
The embodiment acquires the current human body data of the user from the wearable device; inputting the current human body data into a preset model to obtain a heating temperature; and transmitting the heating temperature to the wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature. Wherein, through obtaining current human data from wearable equipment to confirm the heating temperature of hanging stove according to current human data, make the user when unable artifical heating temperature that sets up, the heating temperature of hanging stove still can change according to the human condition, and the heating temperature who has avoided the hanging stove is too high or low and influence user's use and experience.
Further, as shown in fig. 4, fig. 4 is a schematic diagram of a construction process of the predetermined model in fig. 2. In this embodiment, the preset model is obtained by the following steps:
s21: acquiring multiple groups of historical human body data of a user, wherein the human body data comprises multiple types of electrocardio information, position information and body temperature information;
it should be understood that the historical body data of the user may also be obtained from the wearable device, and after obtaining the historical body data, the data is taken as sample data. In an embodiment, the sample data may be divided into 5 parts, wherein 4 parts are used for training the model and 1 part is used for evaluating the model, and of course, other parts of the sample data may be divided, which is not limited in this embodiment.
S22: labeling temperature information corresponding to the wall-mounted furnace on each group of historical human body data to obtain labeled data;
each group of historical human body data needs to be labeled in advance, and if a certain group of historical human body data is: the temperature of the human body is 36 ℃, the heartbeat is 120 times/minute, and the position is a living room, and then the temperature corresponding to the historical human body data can be marked as 30 ℃.
S23: and training the initial model according to the marked data to obtain a preset model.
Specifically, the marked data can be encoded according to the temperature information and the preset temperature; extracting target characteristics from the coded data, wherein the target characteristics comprise a plurality of body temperature characteristics, heart rate characteristics, position characteristics, blood pressure characteristics and blood oxygen characteristics; and inputting the target characteristics into the initial model for training to obtain a preset model.
In a specific implementation, the preset temperature may be set to a common heating temperature of the wall-hanging stove, such as 27 ℃. By encoding the labeled data, the labeled data can be divided into a plurality of different modes, for example, mode 1 is off, mode 2 is cooling, mode 3 is heating, and mode 4 is holding temperature. For example, if the temperature marked by a certain group of historical human body data is 30 ℃, the group of historical human body data can be encoded into a mode 2, i.e., cooling, after the temperature is compared with a preset temperature.
In the process of extracting the target characteristics from the coded data, the coded data can be preprocessed, such as normalization processing, and the data are mapped into the range of 0-1, so that the iterative computation speed can be increased, and the convenience and the rapidness of data processing can be improved. After the coded data are normalized, PCA (principal component analysis) feature selection is carried out on the data, dimension reduction can be carried out on the data, and features (body temperature features, heart rate features, position features, blood pressure features, blood oxygen features and the like) which are relatively large in correlation with heating temperature are extracted, so that subsequent calculation is facilitated.
The initial model in this embodiment may be a variety of models, and taking the case that the initial model is an Xgboost model as an example, after the target feature is obtained, the target feature may be input into the Xgboost model for training; calculating the value of the loss function according to the output result of the Xgboost model; and adjusting the hyper-parameter of the Xgboost model according to the value of the loss function, and then continuing training to obtain a preset model.
Of course, before the target features are input into the Xgboost model, the target features may be scrambled, and by scrambling the data, the robustness of the data may be enhanced, and since the model ignores the order of the sample data during learning, a better learning effect may be generated.
It should be noted that extreme Gradient Boosting (Xgboost) is an open source machine learning project, which is developed from a Gradient Boosting Decision Tree (GBDT), and the GBDT algorithm is efficiently implemented and improved in algorithm and engineering based on the GBDT algorithm. Xgboost is an integrated machine learning algorithm based on a decision tree, and realizes the optimization process of learning by using an addition model and a forward step algorithm by taking gradient lifting as a framework. The method has the advantages of high speed, good effect, capability of processing large-scale data, supporting multiple languages, supporting custom loss functions and the like.
The base learner in the Xgboost may perform the boosting calculation based on a tree model, such as a Classification And Regression Tree (CART), or may perform the boosting calculation based on a linear model, such as a gbinear linear classifier.
After the initial model is constructed, the hyper-parameters of the initial model need to be set first, and the hyper-parameters need to be adjusted continuously in the training process of the model.
It should be understood that the hyper-parameters are parameters that are pre-defined before the learning process is started, and not parameters that are derived through training. In general, the hyper-parameters need to be optimized, and a set of optimal hyper-parameters is selected for the model, so as to improve the learning performance and effect. The commonly used method for adjusting parameters by using hyper-parameters comprises the following steps: grid search, random search, Bayesian optimization and the like.
In this embodiment, the hyper-parameters to be defined include a learning rate, a sampling depth, a sub-node weight, a down-sampling rate, and a joint sampling rate.
In one embodiment, the learning rate range is set to be 0.1-0.05, the sampling depth is any one natural number of 4, 5 and 6, the weight of the child node is 1 or 2, the down sampling rate is 0.9, and the joint sampling rate is 0.9.
During the training process, the value of the loss function can be calculated according to the output result of the Xgboost model; and adjusting the learning rate, the sampling depth and the sub-node weight of the Xgboost model according to the value of the loss function.
Wherein, when adjusting the learning rate, a difference between a previous value and a current value of the loss function may be calculated; determining a rate of decrease of the value of the loss function from the difference; when the falling speed becomes small, the learning rate is reduced.
The learning rate determines whether and when the objective function converges to a local minimum, and an appropriate learning rate enables the objective function to converge to a local minimum in an appropriate time. In an embodiment, when the initial value of the learning rate is 0.1, if the value of the loss function decreases and becomes slow as the number of iterations increases, the learning rate may be adjusted to be small, and if the trend of the change in the value of the loss function is stable, the learning rate may not be changed.
In an embodiment, when the sampling depth is 6, since the more the sampling depth is, the more the model tends to be locally optimized, and at the same time, the more the amount of calculation is, in order to prevent the model from being limited to the local optimization and make the model tend to be truly optimized, the sampling depth may be appropriately reduced according to the value of the loss function, such as setting the sampling depth to 4 or 5. As shown in fig. 5, fig. 5 is a training graph of an embodiment of iteration times (iterations) and loss function value (loss), and after the sampling depth is changed, the model can reach true optimum from local optimum.
In an embodiment, when the weight of the child node is 2, the left sub-tree node and the right sub-tree node with the focus weight greater than or equal to 2 are discarded step by step in the training process, so that the interference of the nodes with smaller weights can be reduced, and the accuracy of the model is improved.
In an embodiment, since the down-sampling rate and the joint sampling rate control the ratio of random sampling per tree, reducing the values of these two parameters makes the algorithm more conservative and avoids over-fitting, however, when the down-sampling rate and the joint sampling rate are set too small, the deviation of fitting of training samples may be increased, so that, after the down-sampling rate and the joint sampling rate are both set to 0.9 in model training, the down-sampling rate and the joint sampling rate are not adjusted or reduced properly in the training process.
In the training process of the model, the tree complexity formula is as follows:
wherein T is the number of leaf nodes of each tree,
is the square of the weight of the leaf node on the tree, gamma is a penalty term of L1 regular, and lambda is a penalty term of L2 regular. In the training process, in order to prevent excessive data in the training process, lambda is usually set between 0 and 1.
It should be appreciated that in machine learning, an additional term is typically added to the loss function, commonly referred to as L1 regularization and L2 regularization. The regularization term is generally a monotonically increasing function of the complexity of the model, with the more complex the model, the larger the regularization value. Where L1 regularization is the sum of absolute values of each element in the vector, and L2 regularization is the squaring of each element of the vector, summing, and then square root.
Referring to fig. 6, fig. 6 is a training graph of another embodiment of the number of iterations of the preset model and the value of the loss function in fig. 2, as can be seen from fig. 6, as the number of iterations (iterations) increases, the logarithm (loglos) of the value of the loss function decreases rapidly, and when the number of iterations reaches 30, the logarithm of the value of the loss function approaches 0.1, which means that the model has strong generalization capability, occupies small resources, and is trained rapidly.
Further, when the historical human body data is divided into 5 parts, wherein 4 parts are used for training the model and 1 part is used for evaluating the model, after 30 iterations of the Xgboost model of the present embodiment, the preset model is evaluated by using the evaluation model, and it can be detected that the precision of the preset model reaches more than 99%.
In the embodiment, multiple groups of historical human body data of a user are acquired, wherein the human body data comprise multiple types of electrocardio information, position information and body temperature information; labeling temperature information corresponding to the wall-mounted furnace on each group of historical human body data to obtain labeled data; and training the initial model according to the marked data to obtain a preset model. The method has the advantages that the operation speed can be effectively increased by carrying out preprocessing such as labeling, coding and feature extraction on historical human body data, the Xgboost model is used as an initial model, the preset function is obtained by training, the training speed is high, the model precision is high, and the accuracy of heating temperature prediction is improved.
Further, as shown in fig. 7, fig. 7 is a schematic flow chart of another embodiment of the temperature control method of the present invention, and in this embodiment, the method further includes the following steps:
s40: determining whether the heating temperature is within a preset threshold range before transmitting the heating temperature to the wall-hanging stove;
it should be noted that, in order to ensure the accuracy of the wall-mounted boiler receiving the heating temperature, before the server sends the heating temperature to the wall-mounted boiler, the heating temperature needs to be verified to determine whether the temperature is within a reasonable range.
Typically, the minimum temperature of the wall-hanging stove is 10 ℃ or 20 ℃ and the maximum temperature is 30 ℃, so the prediction threshold range may be 10 ℃ to 30 ℃ or 20 ℃ to 30 ℃.
S50: and returning to the step of acquiring the current human body data of the user from the wearable device under the condition that the heating temperature is not within the preset threshold range.
When the heating temperature is not within the preset threshold range, the heating temperature obtained by calculation of the server cannot be used as a basis for adjusting the temperature of the wall-hanging stove, and at the moment, the current human body data needs to be obtained from the wearable device again and then calculated, so that the temperature adjustment error of the wall-hanging stove is avoided.
When the heating temperature is within the preset threshold range, the heating temperature obtained by calculation of the server can be used as a basis for adjusting the temperature of the wall-hanging stove, and at the moment, the server transmits the heating temperature to the wall-hanging stove, so that the wall-hanging stove adjusts the temperature according to the heating temperature.
This embodiment is through before conveying the hanging stove with heating temperature, and it is in presetting threshold value within range to confirm heating temperature, under the condition that heating temperature is not in presetting threshold value within range, returns the step of obtaining user's current human data from wearable equipment, has avoided the hanging stove to heat according to improper heating temperature effectively, has improved temperature regulation's accuracy.
The embodiment of the invention further provides a temperature control system.
Referring to fig. 8, fig. 8 is a functional block diagram of an embodiment of a temperature control system according to the present invention.
In this embodiment, the temperature control system includes: a wearable device 10; a gateway device 20; a wall-mounted boiler 30; and the server 40 in the above embodiment, the wearable device 10 communicates with the server 40, and the server 40 communicates with the wall-hanging stove 30 via the gateway device 20.
The wearable device 10 may be an electronic device such as glasses, a bracelet, a watch, and the like; gateway device 20 may be a soft routing, hard routing, etc. device. The server 40 includes: the temperature control program of the wall-hanging stove is configured to realize the temperature control method for the wall-hanging stove in the embodiment.
In an embodiment, the wearable device 10 is connected with the server 40, the server 40 is connected with the wall-hanging stove 30 through the gateway device 20, the wearable device 10 collects current human body data of a user and transmits the current human body data to the server 40 through a public cloud, the server 40 sends a heating temperature to the wall-hanging stove 30 through the gateway device 20 after obtaining the heating temperature according to the current human body data, and the wall-hanging stove 30 adjusts the indoor temperature according to the heating temperature.
Further, wearable device 10 communicates with server 40 via gateway device 20.
It should be noted that, when a USIM module, a bluetooth module, or a WiFi module is built in the wearable device 10, the wearable device 10 may send current human body data to the server 40 through the gateway device 20 through the above modules, after the server 40 obtains a heating temperature according to the current human body data, the heating temperature is sent to the wall-hanging stove 30 through the gateway device 40, and the wall-hanging stove 30 adjusts the indoor temperature according to the heating temperature.
Referring to fig. 8 and 9 together, fig. 9 is a functional block diagram of another embodiment of a temperature control system according to the present invention.
Further, the temperature control system further comprises: and the mobile terminal 50 is communicated with the wearable device 10 and is used for acquiring the current human body data from the wearable device 10 and sending the current human body data to the server 40.
The mobile terminal 50 may be a mobile phone, a tablet, or other electronic devices.
In one embodiment, the wearable device 10 is connected to a mobile terminal 50, the mobile terminal 50 is connected to a server 40 through a gateway device 20 or a public cloud, and the server 40 is connected to the wall-hanging stove 30 through the gateway device 20. Gather user's current human data by wearable device 10, the user obtains current human data through mobile terminal 50 to convey to server 40 through gateway device 20 or public cloud, after server 40 obtained the heating temperature according to current human data, send the heating temperature to hanging stove 30 through gateway device 20, hanging stove 30 adjusts indoor temperature according to the heating temperature.
This embodiment is through setting up wearable equipment, gateway equipment, hanging stove and server in the temperature control system who is used for the hanging stove, and wearable equipment and server communication, the server communicates through gateway equipment and hanging stove, have realized the automatic control of hanging stove heating temperature, provide more comfortable house living environment for the user.
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, method, article, or system 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, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A temperature control method for a wall-hanging stove is characterized by comprising the following steps:
acquiring current body data of a user from a wearable device;
inputting the current human body data into a preset model to obtain a heating temperature;
and transmitting the heating temperature to a wall-hanging furnace so that the wall-hanging furnace can adjust the temperature according to the heating temperature.
2. The temperature control method of claim 1, wherein the preset model is obtained by:
acquiring multiple groups of historical human body data of a user, wherein the human body data comprises multiple types of electrocardio information, position information and body temperature information;
labeling temperature information corresponding to the wall-mounted furnace on each group of historical human body data to obtain labeled data;
and training the initial model according to the marked data to obtain the preset model.
3. The method of claim 2, wherein the training the initial model according to the labeled data to obtain the predetermined model comprises:
coding the marked data according to the temperature information and a preset temperature;
extracting target characteristics from the coded data, wherein the target characteristics comprise a plurality of body temperature characteristics, heart rate characteristics, position characteristics, blood pressure characteristics and blood oxygen characteristics;
and inputting the target characteristics into an initial model for training to obtain the preset model.
4. The temperature control method of claim 3, wherein the initial model is an Xgboost model; inputting the target features into an initial model for training to obtain the preset model, wherein the training comprises:
inputting the target features into an Xgboost model for training;
calculating the value of a loss function according to the output result of the Xgboost model;
and adjusting the hyper-parameter of the Xgboost model according to the value of the loss function and then continuing training to obtain the preset model.
5. The method of claim 4, wherein the hyperparameter is a learning rate, and wherein the adjusting the hyperparameter of the Xgboost model according to the value of the loss function comprises:
calculating a difference between a previous value and a current value of the loss function;
determining a rate of fall of the value of the loss function from the difference;
when the falling speed becomes small, the learning rate is decreased.
6. The temperature control method according to any one of claims 1 to 5, further comprising:
determining whether the heating temperature is within a preset threshold range before transmitting the heating temperature to a wall-hanging stove;
and returning to the step of acquiring the current human body data of the user from the wearable device when the heating temperature is not within the preset threshold range.
7. The temperature control method as claimed in claims 1 to 5, further comprising:
after the heating temperature is obtained, current position information is obtained from the current human body data;
and sending the heating temperature to the wall-hanging furnace corresponding to the current position information.
8. A server, characterized in that the server comprises: a memory, a processor, and a temperature control program of a wall-hanging stove stored on the memory and executable on the processor, the temperature control program of the wall-hanging stove being configured to implement the temperature control method for the wall-hanging stove according to any one of claims 1 to 7.
9. A temperature control system for a wall-hanging stove, comprising:
a wearable device;
a gateway device;
a wall-mounted furnace; and
the server of claim 8, the wearable device in communication with the server, the server in communication with the hanging stove via the gateway device.
10. The temperature control system of claim 9, further comprising:
and the mobile terminal is communicated with the wearable equipment and is used for acquiring the current human body data from the wearable equipment and sending the current human body data to the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567682.4A CN113266952A (en) | 2021-05-24 | 2021-05-24 | Temperature control method and system for wall-mounted boiler and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567682.4A CN113266952A (en) | 2021-05-24 | 2021-05-24 | Temperature control method and system for wall-mounted boiler and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113266952A true CN113266952A (en) | 2021-08-17 |
Family
ID=77232640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567682.4A Pending CN113266952A (en) | 2021-05-24 | 2021-05-24 | Temperature control method and system for wall-mounted boiler and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113266952A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104833063A (en) * | 2015-06-04 | 2015-08-12 | 安徽建筑大学 | Air conditioner control method and system |
| KR20170063206A (en) * | 2015-11-30 | 2017-06-08 | 롯데알미늄 주식회사 | Boiler automatic control apparatus based body temperature and method thereof |
| CN106989517A (en) * | 2017-05-24 | 2017-07-28 | 美的智慧家居科技有限公司 | Electric heater switchs intelligent control method and device |
| CN107976905A (en) * | 2017-11-17 | 2018-05-01 | 深圳和而泰数据资源与云技术有限公司 | A kind of apparatus control method, device, electronic equipment and storage medium |
| CN109654672A (en) * | 2018-11-13 | 2019-04-19 | 珠海格力电器股份有限公司 | A kind of air conditioning control method and air-conditioning |
| CN110822616A (en) * | 2018-08-13 | 2020-02-21 | 格力电器（武汉）有限公司 | Automatic air conditioner adjusting method and device |
| CN111006303A (en) * | 2019-12-13 | 2020-04-14 | 艾沃（深圳）智能环境科技有限公司 | Intelligent heating control system and method |
| CN111102643A (en) * | 2018-10-26 | 2020-05-05 | 芜湖美的厨卫电器制造有限公司 | Wall-mounted furnace and control method and system thereof |
| CN111197866A (en) * | 2018-11-20 | 2020-05-26 | 芜湖美的厨卫电器制造有限公司 | Wall-mounted furnace and control method and system thereof |
| CN111639807A (en) * | 2020-05-29 | 2020-09-08 | 携程计算机技术（上海）有限公司 | Model training method, duration prediction method, system, device and medium |
| CN111950585A (en) * | 2020-06-29 | 2020-11-17 | 广东技术师范大学 | XGboost-based underground comprehensive pipe gallery safety condition assessment method |
| CN212618628U (en) * | 2020-07-13 | 2021-02-26 | 芜湖美的厨卫电器制造有限公司 | A device and hanging stove for adjusting hanging stove heating |
-
2021
- 2021-05-24 CN CN202110567682.4A patent/CN113266952A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104833063A (en) * | 2015-06-04 | 2015-08-12 | 安徽建筑大学 | Air conditioner control method and system |
| KR20170063206A (en) * | 2015-11-30 | 2017-06-08 | 롯데알미늄 주식회사 | Boiler automatic control apparatus based body temperature and method thereof |
| CN106989517A (en) * | 2017-05-24 | 2017-07-28 | 美的智慧家居科技有限公司 | Electric heater switchs intelligent control method and device |
| CN107976905A (en) * | 2017-11-17 | 2018-05-01 | 深圳和而泰数据资源与云技术有限公司 | A kind of apparatus control method, device, electronic equipment and storage medium |
| CN110822616A (en) * | 2018-08-13 | 2020-02-21 | 格力电器（武汉）有限公司 | Automatic air conditioner adjusting method and device |
| CN111102643A (en) * | 2018-10-26 | 2020-05-05 | 芜湖美的厨卫电器制造有限公司 | Wall-mounted furnace and control method and system thereof |
| CN109654672A (en) * | 2018-11-13 | 2019-04-19 | 珠海格力电器股份有限公司 | A kind of air conditioning control method and air-conditioning |
| CN111197866A (en) * | 2018-11-20 | 2020-05-26 | 芜湖美的厨卫电器制造有限公司 | Wall-mounted furnace and control method and system thereof |
| CN111006303A (en) * | 2019-12-13 | 2020-04-14 | 艾沃（深圳）智能环境科技有限公司 | Intelligent heating control system and method |
| CN111639807A (en) * | 2020-05-29 | 2020-09-08 | 携程计算机技术（上海）有限公司 | Model training method, duration prediction method, system, device and medium |
| CN111950585A (en) * | 2020-06-29 | 2020-11-17 | 广东技术师范大学 | XGboost-based underground comprehensive pipe gallery safety condition assessment method |
| CN212618628U (en) * | 2020-07-13 | 2021-02-26 | 芜湖美的厨卫电器制造有限公司 | A device and hanging stove for adjusting hanging stove heating |
Non-Patent Citations (2)
| Title |
|---|
| 杨正森: "基于FTRL和XGBoost算法的产品故障预测模型", 《计算机系统应用》 * |
| 邓卓: "基于集成学习的乳腺癌分类研究", 《中国医疗设备》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106152408B (en) | Intelligent air conditioner controller, control method and air conditioner | |
| CN109489212B (en) | Intelligent sleep control method, adjustment system and equipment for air conditioner | |
| CN109945421A (en) | Progress control method, operating control device and household appliance | |
| CN105446156B (en) | Control method, the device and system of household electrical appliance based on artificial intelligence | |
| CN108413588B (en) | Personalized air conditioner control system and method based on thermal imaging and BP neural network | |
| CN107525243A (en) | The control system and method for air-conditioner temperature | |
| CN111121237B (en) | Air conditioner, control method thereof, server, and computer-readable storage medium | |
| CN103970554B (en) | A kind of control method of household appliances function upgrading | |
| US20210215377A1 (en) | Ventilation control apparatus and ventilation system | |
| CN105068513A (en) | Intelligent home energy management method based on social network behavior perception | |
| CN107229262A (en) | A kind of intelligent domestic system | |
| CN108427310A (en) | Intelligent home furnishing control method, device and computer readable storage medium | |
| US20190064929A1 (en) | System and method for gesture recognition | |
| CN114237069A (en) | Indoor environment control method, device, system and storage medium | |
| CN110822616A (en) | Automatic air conditioner adjusting method and device | |
| CN107360066A (en) | A kind of household service robot and intelligent domestic system | |
| CN111121239B (en) | Intelligent control method and system for intelligent household appliance and intelligent household appliance | |
| CN106647295B (en) | Smart home system and cooperative operation method thereof | |
| CN113325762A (en) | Intelligent building personalized energy utilization control method, system, device and equipment | |
| CN109883016A (en) | A kind of air pleasant degree adjusting method and equipment | |
| CN115220357A (en) | Comfortable energy-saving intelligent building control method, system and server | |
| CN110989430A (en) | Smart home linkage method and system and readable storage medium | |
| CN113266952A (en) | Temperature control method and system for wall-mounted boiler and server | |
| CN112099374A (en) | Indoor environment comfort control method and system, electronic equipment and storage medium | |
| CN108647608A (en) | A kind of implementation method of the smart home burglary-resisting system based on Identification of Images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210817 |