CN115032906B - Digital twin room temperature prediction method, smart home equipment control method and device - Google Patents

Abstract

The invention relates to the technical field of temperature prediction, and provides a digital twin room temperature prediction method, an intelligent household equipment control method and a device, wherein the method comprises the steps of firstly obtaining thermal parameters, dimension parameters and outdoor temperature parameters of a target room; and then, based on the room temperature prediction model, determining the thermal parameter, the size parameter and the indoor temperature parameter of the target room corresponding to the outdoor temperature parameter of the target room. According to the method, the thermal parameters, the size parameters and the outdoor temperature parameters of the target room are introduced, the room temperature prediction model is combined to jointly determine the indoor temperature parameters of the target room, the constraint of the temperature sensor can be eliminated, the indoor temperature of the target room can be determined even if the temperature sensor is not installed in the target room, and the acquisition cost of the indoor temperature can be saved. Furthermore, in the method, the thermal parameters, the size parameters and the outdoor temperature parameters of the target room are introduced, so that the accuracy of the indoor temperature can be improved.

Description

Digital twin room temperature prediction method, smart home equipment control method and device

Technical Field

The present invention relates to the field of temperature prediction technology, and in particular to a digital twin room temperature prediction method, a smart home device control method and a device.

Background Art

With the widespread application of smart homes (home automation) and the increasing requirements of users for indoor comfort, it is very important to obtain the room temperature to control the smart home and ensure the indoor comfort of users.

In the prior art, temperature measurement is usually performed directly through temperature sensors installed indoors. However, due to cost considerations, the solution of installing temperature sensors indoors has not been popularized. For rooms without temperature sensors installed, the indoor temperature of the room cannot be obtained, which will lead to the subsequent inability to automatically control the smart home, and thus the inability to ensure the user's indoor comfort.

Therefore, there is an urgent need to provide a room temperature prediction method.

Summary of the invention

The present invention provides a digital twin room temperature prediction method, a smart home equipment control method and a device to solve the defects in the prior art.

The present invention provides a digital twin room temperature prediction method, comprising:

Acquiring thermal parameters, size parameters, and outdoor temperature parameters of a target room; wherein a smart home device with networking function is installed in the target room;

Determine, based on the room temperature prediction model, the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room;

The room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters.

According to a digital twin room temperature prediction method provided by the present invention, the thermal parameters include at least one of a sunshine parameter, a structural heat exchange parameter, a temperature adjustment parameter, and an airflow heat exchange parameter;

The sunshine parameter includes at least one of a sunshine direct area parameter, a sunshine angle parameter and a sunshine intensity parameter;

The structural heat exchange parameter includes at least one of a room external contact area parameter, a room internal contact area parameter, and a wall thermal conductivity parameter;

The temperature adjustment parameters include operating parameters of the temperature adjustment device in the target room;

The airflow heat exchange parameter includes at least one of a ventilation volume parameter and an outdoor wind speed parameter.

According to a digital twin room temperature prediction method provided by the present invention, the thermal parameters, the size parameters and the outdoor temperature parameters are obtained based on the following method:

Based on the user interaction device, receiving the thermal parameter, the size parameter and the outdoor temperature parameter input by the user;

Alternatively, the thermal parameter, the size parameter and the outdoor temperature parameter are determined based on the network address of the smart home device.

According to a digital twin room temperature prediction method provided by the present invention, the temperature adjustment device includes a heater, and the working parameters of the heater include working power;

The wall thermal conductivity parameter, the heater operating power and the size parameter are determined based on the following method:

Based on the network address, determine the average wall thermal conductivity, the average heating working power and the average size of the area where the room is located;

The average value of the wall thermal conductivity is used as the wall thermal conductivity parameter, the average value of the heater working power is used as the heater working power, and the average value of the size is used as the size parameter.

According to a digital twin room temperature prediction method provided by the present invention, the temperature adjustment device also includes an intelligent temperature adjustment device, and the intelligent temperature adjustment device includes at least one of an air conditioner, an electric heater, and a gas; the working parameters of the air conditioner, the working parameters of the electric heater, and the working parameters of the gas all include working power and working switch fields, and the ventilation volume parameters include ventilation volume and ventilation switch fields;

The operating parameters of the air conditioner, the operating parameters of the electric heater, the operating parameters of the gas, and the ventilation volume parameters are determined based on the following method:

Based on the network address, the working power of the air conditioner, the working power of the electric heater, the working power of the gas and the ventilation volume are collected, and based on the collection results, the working switch field of the air conditioner, the working switch field of the electric heater, the working switch field of the gas and the ventilation switch field are determined.

According to a digital twin room temperature prediction method provided by the present invention, the direct sunlight area parameter, the room external contact area parameter and the room internal contact area parameter all include a first surface positive value and a second surface positive value, the room temperature prediction model includes a first room temperature prediction model and a second room temperature prediction model, and the indoor temperature parameter includes a first indoor temperature and a second indoor temperature;

Accordingly, the step of determining the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters, and outdoor temperature parameters of the target room based on the room temperature prediction model includes:

Based on the first room temperature prediction model, determine a first indoor temperature of the target room corresponding to a first positive value of a sunlight direct area parameter of the target room, a first positive value of a room external contact area parameter, a first positive value of a room internal contact area parameter, a size parameter, and an outdoor temperature parameter;

Based on the second room temperature prediction model, determine the second surface positive value of the direct sunlight area parameter of the target room, the second surface positive value of the room's external contact area parameter, the second surface positive value of the room's internal contact area parameter, the size parameters and the second indoor temperature of the target room corresponding to the outdoor temperature parameters.

According to a digital twin room temperature prediction method provided by the present invention, the initial model of the room temperature prediction model includes a logistic regression model, a decision tree model, a perceptron model or a neural network model.

The present invention also provides a smart home device control method, comprising:

Receive user demand instructions, perform semantic analysis on the user demand instructions, and determine user semantic analysis results;

Generate a control instruction based on the user semantic analysis result and the indoor temperature parameters of the target room obtained by the digital twin room temperature prediction method;

Based on the control instruction, the smart home devices in the target room are controlled.

The present invention also provides a digital twin room temperature prediction device, comprising:

An acquisition module, used to acquire thermal parameters, size parameters and outdoor temperature parameters of a target room; the target room is equipped with a smart home device with networking function;

A prediction module, for determining, based on a room temperature prediction model, indoor temperature parameters of the target room corresponding to thermal parameters, size parameters and outdoor temperature parameters of the target room;

The room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters.

The present invention also provides a smart home device control device, comprising:

A receiving module is used to receive a user demand instruction, and perform semantic analysis on the user demand instruction to determine a user semantic analysis result;

A generation module, used to generate a control instruction based on the user semantic analysis result and the indoor temperature parameter of the target room obtained by the digital twin room temperature prediction method;

A control module is used to control the smart home devices in the target room based on the control instruction.

The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the digital twin room temperature prediction method or smart home device control method as described above is implemented.

The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the digital twin room temperature prediction method or smart home device control method as described in any one of the above is implemented.

The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the digital twin room temperature prediction method or smart home device control method as described above.

The digital twin room temperature prediction method, smart home device control method and device provided by the present invention first obtain the thermal parameters, size parameters and outdoor temperature parameters of the target room; the target room is equipped with a smart home device with networking function; then, based on the room temperature prediction model, the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room are determined. The method introduces the thermal parameters, size parameters and outdoor temperature parameters of the target room, and combines the room temperature prediction model to jointly realize the determination of the indoor temperature parameters of the target room, which can get rid of the constraints of the temperature sensor. Even if the temperature sensor is not installed in the target room, the indoor temperature of the target room can be determined, which can save the cost of obtaining the indoor temperature. Moreover, in this method, the thermal parameters, size parameters and outdoor temperature parameters of the target room are introduced to improve the accuracy of the indoor temperature.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings in the following description without creative work.

FIG1 is a schematic flow chart of a digital twin room temperature prediction method provided by the present invention;

FIG2 is a schematic diagram of a flow chart of a smart home device control method provided by the present invention;

FIG3 is a schematic structural diagram of a digital twin room temperature prediction device provided by the present invention;

FIG4 is a schematic diagram of the structure of a smart home device control device provided by the present invention;

FIG. 5 is a schematic diagram of the structure of an electronic device provided by the present invention.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

In the prior art, temperature measurement is usually performed directly through a temperature sensor installed indoors, but the indoor temperature of a room without a temperature sensor installed cannot be obtained, which will result in the inability to automatically control the smart home and thus fail to ensure the user's indoor comfort. To this end, a digital twin room temperature prediction method is provided in an embodiment of the present invention to achieve the technical effect of obtaining the room temperature without a temperature sensor.

FIG1 is a schematic flow chart of a digital twin room temperature prediction method provided in an embodiment of the present invention. As shown in FIG1 , the method includes:

S11, obtaining thermal parameters, size parameters and outdoor temperature parameters of a target room; the target room is equipped with a smart home device with networking function;

S12, determining, based on a room temperature prediction model, indoor temperature parameters of the target room corresponding to thermal parameters, size parameters, and outdoor temperature parameters of the target room;

The room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters.

Specifically, the digital twin room temperature prediction method provided in the embodiment of the present invention is executed by a digital twin room temperature prediction device, which can be configured in a cloud server. The cloud server can be connected to smart home devices with networking functions installed in the target room to be measured through the Internet of Things (IOT).

First, step S11 is performed to obtain the thermal parameters, size parameters and outdoor temperature parameters of the target room. The target room refers to the room whose indoor temperature needs to be determined, and the target room may be installed with a smart home device with networking function. The smart home device may be a smart air conditioner, a smart window, a smart refrigerator, etc., which are not specifically limited here. The networking function of the smart home device can be realized through a built-in WIFI module or other wireless communication module.

Thermal parameters refer to parameters used to characterize room heat, and may include at least one of sunlight parameters, structural heat exchange parameters, temperature adjustment parameters, and airflow heat exchange parameters. Sunlight parameters refer to sunlight heat power or related parameters that affect sunlight heat in the room, structural heat exchange parameters refer to structural heat exchange heat power or related parameters that affect air heat exchange heat in the room, temperature adjustment parameters refer to working parameters of the temperature adjustment device in the room, such as working power, etc., and airflow heat exchange parameters refer to airflow heat exchange power in the room or related parameters that affect airflow heat exchange in the room.

The outdoor temperature parameter refers to the outdoor temperature or a related parameter that affects the outdoor ambient temperature. The related parameter may include the weather conditions of the area where the room is located and the longitude and latitude of the room, and may be represented by discrete values of cloudy, overcast, sunny, rainy, and snowy. The outdoor temperature may be determined by the weather conditions of the area where the room is located and the longitude and latitude of the room, and its unit is W/m ² .

Dimensional parameters refer to the dimensions of the room, which can include the length, width, and height of the room.

In the embodiment of the present invention, the thermal parameters, size parameters and outdoor temperature parameters of the target room are all indirect parameters related to the indoor temperature parameters of the target room. The acquisition of the thermal parameters, size parameters and outdoor temperature parameters of the target room can be achieved through the networking function of the smart home device installed in the target room, or can be manually input by the user on the application (APP) of the smart home device, which is not specifically limited here.

Then, step S12 is executed to introduce a room temperature prediction model, and the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room are determined by the room temperature prediction module. Here, the room temperature prediction model is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters. The any room can be any room, that is, the indoor temperature parameters of any room can be determined by the quantitative relationship characterized by the room temperature prediction model.

The quantitative relationship can be determined by the thermal parameters, dimensional parameters and outdoor temperature parameters of the sample room carrying the indoor temperature tag, that is, the corresponding quantitative relationship can be obtained by analyzing the built-in connection between the thermal parameters, dimensional parameters and outdoor temperature parameters of the sample room and its indoor temperature tag.

The initial model of the room temperature prediction model can be a logistic regression model, a neural network model or a deep neural network (DNN) model. Through the thermal parameters, size parameters, outdoor temperature parameters and indoor temperature labels of the sample room, the initial model is continuously iterated to determine the model parameters of the room temperature prediction model that meet the prediction accuracy requirements.

When the initial model is a logistic regression model, the independent variables of the initial model are the thermal parameters, size parameters and outdoor temperature parameters of the sample room, and the dependent variable is the indoor temperature label of the sample room. The independent variables of the room temperature prediction model are the thermal parameters, size parameters and outdoor temperature parameters of any room, and the dependent variable is the indoor temperature parameter of any room.

When the initial model is a neural network model, the input of the initial model is the thermal parameters, size parameters and outdoor temperature parameters of the sample room, and the output is the indoor temperature label of the sample room. The input of the room temperature prediction model is the thermal parameters, size parameters and outdoor temperature parameters of any room, and the output is the indoor temperature parameters of any room.

It is understandable that the indoor temperature parameter of the target room may include the value of the indoor temperature, and the value of the indoor temperature may be an extreme value, such as a maximum value or a minimum value, or a value between the maximum value and the minimum value. This is related to the selection of the indoor temperature label of the sample room. If the indoor temperature label of the selected sample room is a maximum value, the indoor temperature parameter obtained by the room temperature prediction model is also a maximum value. If the indoor temperature label of the selected sample room is a minimum value, the indoor temperature parameter obtained by the room temperature prediction model is also a minimum value.

It should be noted that there is a quantitative relationship between the indoor temperature label of the sample room and the thermal parameters, size parameters and outdoor temperature parameters of the sample room. Therefore, the selection of the indoor temperature label of the sample room will be affected by the parameter values within the value range of the thermal parameters of the sample room. When the parameter values within the value range of the thermal parameters of the sample room are extreme values, the indoor temperature label of the sample room is also the temperature extreme value.

For the sample room, its radiated heat is equal to its received heat. The radiated heat power of the sample room can be determined by the blackbody radiation formula.

The formula for blackbody radiation is:

P＝σT ⁴

Wherein, P is the radiation power per unit area, σ＝5.67*10 ^-8 W*(m ^-2 *k ^-4 ), and T is the thermodynamic temperature, in K.

The radiant heat power of the sample room can be expressed as:

W ₁ =σS(T ₁ -T ₂ ) ⁴

Among them, _W1 is the radiant heat power of the sample room, S is the surface area of the sample room, which can be determined by the size parameters of the sample room, _T1 is the indoor temperature parameter of the sample room, and _T2 is the outdoor temperature parameter of the sample room.

On the other hand, the received heat power of the sample room is related to the thermal parameters of the sample room. Therefore, through the formula of the radiant heat power of the sample room mentioned above, a quantitative relationship between the thermal parameters, size parameters, room temperature parameters and indoor temperature parameters of any room can be established.

Digital twins make full use of physical models, integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, complete mapping in virtual space, and thus reflect the entire life cycle of the corresponding physical equipment. Digital twins can be regarded as a digital mapping system of one or more important, interdependent equipment systems. In an embodiment of the present invention, by considering the thermal parameters, dimensional parameters, and outdoor temperature parameters of the target room, the room temperature prediction of the digital twin is realized to obtain the indoor temperature parameters of the target room. The obtained indoor temperature parameters of the target room can be used to facilitate control decisions based on this information in the subsequent home appliance control process, and can also be provided directly to users, which is not specifically limited here.

The digital twin room temperature prediction method provided in the embodiment of the present invention first obtains the thermal parameters, size parameters and outdoor temperature parameters of the target room; the target room is equipped with a smart home device with networking function; then, based on the room temperature prediction model, the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room are determined. The method introduces the thermal parameters, size parameters and outdoor temperature parameters of the target room, and combines the room temperature prediction model to jointly realize the determination of the indoor temperature parameters of the target room, which can get rid of the constraints of the temperature sensor. Even if there is no temperature sensor installed in the target room, the indoor temperature of the target room can be determined, which can save the cost of obtaining the indoor temperature. Moreover, in this method, the introduction of the thermal parameters, size parameters and outdoor temperature parameters of the target room can improve the accuracy of the indoor temperature.

On the basis of the above embodiment, in the digital twin room temperature prediction method provided in the embodiment of the present invention, the thermal parameter includes at least one of a sunshine parameter, a structural heat exchange parameter, a temperature adjustment parameter, and an airflow heat exchange parameter;

The sunshine parameter includes at least one of a sunshine direct area parameter, a sunshine angle parameter and a sunshine intensity parameter;

The structural heat exchange parameter includes at least one of a room external contact area parameter, a room internal contact area parameter, and a wall thermal conductivity parameter;

The temperature adjustment parameters include operating parameters of the temperature adjustment device in the target room;

The airflow heat exchange parameter includes at least one of a ventilation volume parameter and an outdoor wind speed parameter.

Specifically, in an embodiment of the present invention, the thermal parameters may include at least one of sunlight parameters, structural heat exchange parameters, temperature regulation parameters, and airflow heat exchange parameters. The more parameter items included in the thermal parameters, the more factors are considered, so that the room temperature prediction model determined by the thermal parameters, size parameters and outdoor temperature parameters of the sample room carrying the indoor temperature label has higher accuracy, and thus the indoor temperature parameters of the target room obtained by the room temperature prediction model have higher accuracy.

Here, the sunshine parameter may include at least one of a sunshine direct area parameter, a sunshine angle parameter, and a sunshine intensity parameter.

The direct sunlight area parameter refers to the direct sunlight area or related parameters that affect the direct sunlight area. The related parameters may include the room window area and the area of the room window blocked by the environment. The difference between the room window area and the area of the room window blocked by the environment can be used as the direct sunlight area. The units of the room window area, the area of the room window blocked by the environment and the direct sunlight area are all square meters (m ² ).

The sunshine angle parameter refers to the sunshine angle or related parameters that affect the sunshine angle, for example, the current time and the longitude and latitude of the room. The current time can be represented by the number of seconds from 0:00 on January 1 of the current year to the current time, and the unit can be s. The sunshine angle can be determined by the current time and the longitude and latitude of the room, and its unit is degree (°).

The sunshine intensity parameter refers to the sunshine intensity or related parameters that affect the sunshine intensity, for example, the weather conditions of the area where the room is located and the longitude and latitude of the room. The weather conditions of the area where the room is located can be represented by discrete values of cloudy, overcast, sunny, rainy, and snowy. The value of sunshine intensity can be determined by the weather conditions of the area where the room is located and the longitude and latitude of the room. The unit is W/m ² .

The structural heat exchange parameter may include at least one of a room-to-external contact area parameter, a room-to-internal contact area parameter, and a wall thermal conductivity parameter.

The room external contact area parameter refers to the value of the room external contact area, which can be the area of the room directly in contact with the outdoor environment, such as the external wall area, external window area, etc., and its unit is ^m2 .

The room internal contact area parameter refers to the value of the room internal contact area, which can be the area of the room directly contacting other rooms or areas in the building where the room is located, such as the inner wall area, inner window area, etc., and its unit is ^m2 .

The wall thermal conductivity parameter refers to the value of the thermal conductivity of the room wall, which is related to the material used for the wall.

The heat source of the temperature regulating device in the target room refers to the device that can adjust the temperature in the target room, which may include central heating equipment such as a heater, or equipment installed in the room according to user needs, such as at least one of air conditioning, electric heater and gas. The operating parameters of the temperature regulating device may refer to the parameters that affect the temperature regulating performance of the temperature regulating device, such as operating power, etc.

The airflow heat exchange parameter refers to the airflow heat exchange power or related parameters that affect the airflow heat exchange, and the related parameters may include at least one of the ventilation volume parameter, the outdoor wind speed parameter, and the room temperature parameter. The ventilation volume parameter is the room ventilation volume, in m ³ /s. The outdoor wind speed parameter is the outdoor environment wind speed of the room, in m/s.

In the embodiment of the present invention, the categories and subcategories of thermal parameters are provided, which can further optimize the performance of the room temperature prediction model, thereby improving the accuracy of room temperature prediction.

On the basis of the above-mentioned embodiment, in the digital twin room temperature prediction method provided in the embodiment of the present invention, the thermal parameters, the size parameters and the outdoor temperature parameters are obtained based on the following method:

Based on the user interaction device, receiving the thermal parameter, the size parameter and the outdoor temperature parameter input by the user;

Alternatively, the thermal parameter, the size parameter and the outdoor temperature parameter are determined based on the network address of the smart home device.

Specifically, in the embodiment of the present invention, when obtaining the thermal parameters, size parameters and outdoor temperature parameters of the target room, the following two methods can be used to determine: one method is to determine in advance, which requires the use of a user interaction device, which can be a terminal device with a smart home device application installed, such as a mobile phone, a tablet, etc. The user can input the thermal parameters, size parameters and outdoor temperature parameters of the target room on the user interaction device, and the information input by the user can be received and stored by the room temperature prediction module through the networking function of the user interaction device.

Another method is a situation that may not be determined in advance due to user neglect or ignorance. This method requires using the network address of the smart home device to determine the thermal parameters, size parameters and outdoor temperature parameters of the target room. Through the network address, the average value of the relevant parameters of the area where the target room is located or the indirect parameters that can determine the relevant parameters can be obtained, which are not specifically limited here.

Similarly, the thermal parameters, size parameters and outdoor temperature parameters of the sample room can also be obtained by the above-mentioned method of obtaining the thermal parameters, size parameters and outdoor temperature parameters of the target room. It is only necessary to replace the target room with the sample room. The sample room is also installed with smart home devices with networking functions, which will not be repeated here.

It is understandable that of the two methods of obtaining parameters, the first method with user participation can be preferred. If the relevant parameters are not obtained through the first method, the second method is used, so that the indoor temperature parameters of the target room can be obtained more accurately.

In an embodiment of the present invention, when determining the thermal parameters, size parameters and outdoor temperature parameters of a target room or a sample room, two different methods can be used to achieve this. Even if the user is unable to provide the thermal parameters, size parameters and outdoor temperature parameters of the target room or the sample room, they can be obtained through other methods. This can not only ensure the determination of the room temperature prediction model, but also ensure the smooth acquisition of the indoor temperature parameters of the target room.

On the basis of the above-mentioned embodiment, in the digital twin room temperature prediction method provided in the embodiment of the present invention, the temperature adjustment device includes a heater, and the working parameters of the heater include working power;

The wall thermal conductivity parameter, the heater operating power and the size parameter are determined based on the following method:

Based on the network address, determine the average wall thermal conductivity, the average heating working power and the average size of the area where the room is located;

The average value of the wall thermal conductivity is used as the wall thermal conductivity parameter, the average value of the heater working power is used as the heater working power, and the average value of the size is used as the size parameter.

Specifically, in an embodiment of the present invention, when determining the wall thermal conductivity parameters, heater working parameters and size parameters of the target room, the following method can be used: first, according to the network address, the average wall thermal conductivity, the average heater working power and the average size of the area where the target room is located are determined, and then the above average values can be used as relevant parameters of the target room, that is, the average wall thermal conductivity is used as the wall thermal conductivity parameter of the target room, the average heater working power is used as the heater working power of the target room, and the average size is used as the size parameter of the target room.

It can be understood that the above method can still be used to determine the wall thermal conductivity parameters, heating working parameters and size parameters of the sample room. The difference is that the average wall thermal conductivity, average heating working power and average size of the area where the sample room is located are used as the relevant parameters of the sample room, that is, the average wall thermal conductivity is used as the wall thermal conductivity parameter of the sample room, the average heating working power is used as the heating working power of the sample room, and the average size is used as the size parameter of the sample room.

In the embodiment of the present invention, the average value of the relevant parameters of the area where the room is located is used as the value of the relevant parameter, so that the relevant parameter can be obtained when the user cannot provide at least one of the thermal parameters, size parameters and outdoor temperature parameters of the target room or sample room. In addition, the average value of the relevant parameters of the area where the room is located can represent the commonality of the area where the room is located, thereby reducing the personalization of the target room or sample room and avoiding a large deviation from the actual value.

On the basis of the above embodiments, in the digital twin room temperature prediction method provided in the embodiments of the present invention, the temperature adjustment device further includes an intelligent temperature adjustment device, and the intelligent temperature adjustment device includes at least one of an air conditioner, an electric heater, and a gas; the working parameters of the air conditioner, the working parameters of the electric heater, and the working parameters of the gas all include working power and working switch fields, and the ventilation volume parameters include ventilation volume and ventilation switch fields;

The operating parameters of the air conditioner, the operating parameters of the electric heater, the operating parameters of the gas, and the ventilation volume parameters are determined based on the following method:

Based on the network address, the working power of the air conditioner, the working power of the electric heater, the working power of the gas and the ventilation volume are collected, and based on the collection results, the working switch field of the air conditioner, the working switch field of the electric heater, the working switch field of the gas and the ventilation switch field are determined.

Specifically, in an embodiment of the present invention, the temperature regulating device may be an intelligent temperature regulating device, that is, an intelligent home device with networking function, and the intelligent temperature regulating device may include at least one of air conditioning, electric heater and gas. The working parameters of the air conditioning, the parameters of the electric heater and the working parameters of the gas may include working power and working switch fields. The working power is the working power of the corresponding intelligent temperature regulating device when it is working. The working switch field is used to judge whether the corresponding intelligent temperature regulating device is working effectively, that is, whether the room temperature prediction device can obtain the working parameters of the corresponding intelligent temperature regulating device. If it is effective, that is, the room temperature prediction device can obtain the corresponding working parameters, and then the working switch field can be set to 1. Otherwise, if it is invalid, that is, the room temperature prediction device cannot obtain the corresponding working parameters, the working switch field can be set to 0.

Similarly, the ventilation volume parameter may also include ventilation volume and ventilation switch fields, where the ventilation volume is the flow rate of air entering or leaving the window per unit time. The ventilation switch field is used to determine whether the room temperature prediction device can obtain the ventilation volume. If it can be obtained, the ventilation switch field can be set to 1. Otherwise, if the room temperature prediction device cannot obtain the ventilation volume, the ventilation switch field can be set to 0.

Furthermore, the working parameters of the air conditioner, the working parameters of the electric heater, the working parameters of the gas, and the ventilation volume parameters can all be determined by the following method: that is, according to the network address of the smart home device, the working power of the air conditioner, the working power of the electric heater, the working power of the gas, and the ventilation volume are collected. If the working power and/or ventilation volume are collected, the collection result is the corresponding value; if not collected, the collection result is empty.

After that, according to the collection result, the working switch field of the air conditioner, the working switch field of the electric heater, the working switch field of the gas, and the ventilation switch field are determined. That is, when the collection result is a corresponding value, the corresponding switch field takes a value of 1, and when the collection result is empty, the corresponding switch field takes a value of 0.

In an embodiment of the present invention, corresponding switch fields are added to the working parameters of the air conditioner, the working parameters of the electric heater, the working parameters of the gas, and the ventilation volume parameters, so that the influence of the corresponding parameters on the indoor temperature parameters can be ignored as much as possible when the corresponding parameter values cannot be obtained.

On the basis of the above embodiment, in the digital twin room temperature prediction method provided in the embodiment of the present invention, the direct sunlight area parameter, the room external contact area parameter and the room internal contact area parameter all include a first surface positive value and a second surface positive value, the room temperature prediction model includes a first room temperature prediction model and a second room temperature prediction model, and the indoor temperature parameter includes a first indoor temperature and a second indoor temperature;

Accordingly, the step of determining the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters, and outdoor temperature parameters of the target room based on the room temperature prediction model includes:

Based on the first room temperature prediction model, determine a first indoor temperature of the target room corresponding to a first positive value of a sunlight direct area parameter of the target room, a first positive value of a room external contact area parameter, a first positive value of a room internal contact area parameter, a size parameter, and an outdoor temperature parameter;

Based on the second room temperature prediction model, determine the second surface positive value of the direct sunlight area parameter of the target room, the second surface positive value of the room's external contact area parameter, the second surface positive value of the room's internal contact area parameter, the size parameters and the second indoor temperature of the target room corresponding to the outdoor temperature parameters.

Specifically, in the embodiment of the present invention, the direct sunlight area parameter, the room external contact area parameter, and the room internal contact area parameter all include a first positive value and a second positive value, the first positive value can be a maximum area value, and the second positive value can be a minimum area value. In other words, these three parameters can all obtain a value range, and the first positive value of the corresponding parameter of the sample room can be used to determine the first room temperature prediction model in combination with other fixed parameters and the room temperature label of the sample room; and the second positive value of the corresponding parameter of the sample room can be used to determine the second room temperature prediction model in combination with other fixed parameters and the room temperature label of the sample room.

Thus, the first room temperature prediction model can be used to determine the first indoor temperature of any room, and the second room temperature prediction model can be used to determine the second indoor temperature of any room. In other words, the indoor temperature parameters of any room include the first indoor temperature and the second indoor temperature, the first indoor temperature can be the maximum value of the indoor temperature parameter, and the second indoor temperature can be the minimum value of the indoor temperature parameter.

Furthermore, since the maximum and minimum values of the indoor temperature parameters of the target room are obtained, the value range of the indoor temperature parameters of the target room can be obtained, and the indoor temperature change of the target room can be given, which is helpful to automatically control the smart home devices in the target room according to the indoor temperature parameters.

In the embodiment of the present invention, since parameters such as the direct sunlight area parameter, the room external contact area parameter and the room internal contact area parameter all have a range of values, a first room temperature prediction model and a second room temperature prediction model can be obtained, and then the extreme values of the two indoor temperature parameters can be obtained, and the range of values of the indoor temperature parameters can be given, which is helpful to automatically control the smart home devices in the target room according to the indoor temperature parameters, and provide a control basis for the decision-making of automatic control.

Based on the above embodiments, the digital twin room temperature prediction method provided in the embodiments of the present invention, the initial model of the room temperature prediction model includes a logistic regression model, a decision tree model, a perceptron model or a neural network model.

Specifically, in an embodiment of the present invention, the initial model of the room temperature prediction model may include not only a logistic regression model and a neural network model, but also a decision tree model and a perceptron model, etc. These models can be used to accurately characterize the thermal parameters, dimensional parameters and the complex quantitative relationship between the outdoor temperature parameters and the indoor temperature parameters of any room.

The decision tree model may be a Gradient Boosting Decision Tree (GBDT) model.

As shown in FIG. 2 , based on the above embodiment, a smart home device control method is provided in an embodiment of the present invention, including:

S21, receiving a user demand instruction, and performing semantic analysis on the user demand instruction to determine a user semantic analysis result;

S22, generating a control instruction based on the user semantic analysis result and the indoor temperature parameter of the target room obtained by the digital twin room temperature prediction method;

S23: Control the smart home devices in the target room based on the control instruction.

Specifically, the smart home device control method provided in the embodiment of the present invention is executed by a smart home device control device, which can be configured in a cloud server.

First, step S21 is executed to receive a user demand instruction, which may be a voice instruction, such as "a little hot", "a little cold", etc. After receiving the user demand instruction, semantic analysis is performed on the user demand instruction, and the user demand instruction may be first converted into text, and then the text is analyzed to determine the user semantic analysis result.

Then, step S22 is executed to generate a control instruction based on the user semantic analysis result and the indoor temperature parameter of the target room obtained by the digital twin room temperature prediction method provided in the above embodiments. The control instruction can be an instruction for controlling the smart home device in the panel room. The smart home device can be a temperature control device such as an air conditioner, electric heater, and gas in the target room, or a smart window for changing the ventilation volume parameter of the target room to adjust the indoor temperature.

The generation of the control instruction can be based on the user semantic analysis result and the indoor temperature parameter of the target room, and can be implemented in combination with the outdoor temperature parameter. For example, if the user semantic analysis result is "a bit hot" and the indoor temperature parameter is greater than the outdoor temperature parameter, the control instruction can be an opening instruction for the smart window; if the indoor temperature parameter is less than or equal to the outdoor temperature parameter, the control instruction can be an opening instruction for the air conditioner in cooling mode. If the user semantic analysis result is "a bit cold" and the indoor temperature parameter is greater than the outdoor temperature parameter, the control instruction can be an opening instruction for electric heaters and gas, or an opening instruction for the air conditioner in heating mode; if the indoor temperature parameter is less than or equal to the outdoor temperature parameter, the control instruction can be an opening instruction for the smart window.

Then, step S23 is performed to control the smart home device in the target room according to the control instruction, that is, the control instruction is sent to the corresponding smart home device so that the corresponding smart home device executes the received control instruction.

The smart home device control method provided in the embodiments of the present invention adopts the indoor temperature parameters of the target room obtained by the digital twin room temperature prediction method provided in the above embodiments, combined with the user semantic analysis results, to achieve control of the smart home devices in the target room without the aid of temperature sensors, thereby reducing the control cost of the smart home devices and improving the control efficiency and accuracy.

As shown in FIG3 , based on the above embodiment, a digital twin room temperature prediction device is provided in an embodiment of the present invention, including:

An acquisition module 31 is used to acquire thermal parameters, size parameters and outdoor temperature parameters of a target room; the target room is equipped with a smart home device with networking function;

A prediction module 32, for determining, based on a room temperature prediction model, indoor temperature parameters of the target room corresponding to thermal parameters, size parameters and outdoor temperature parameters of the target room;

The room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters.

On the basis of the above embodiment, in the digital twin room temperature prediction device provided in the embodiment of the present invention, the thermal parameter includes at least one of a sunshine parameter, a structural heat exchange parameter, a temperature adjustment parameter and an airflow heat exchange parameter;

The sunshine parameter includes at least one of a sunshine direct area parameter, a sunshine angle parameter and a sunshine intensity parameter;

The structural heat exchange parameter includes at least one of a room external contact area parameter, a room internal contact area parameter, and a wall thermal conductivity parameter;

The temperature adjustment parameters include operating parameters of the temperature adjustment device in the target room;

The airflow heat exchange parameter includes at least one of a ventilation volume parameter and an outdoor wind speed parameter.

On the basis of the above embodiment, in the digital twin room temperature prediction device provided in the embodiment of the present invention, the acquisition module is specifically used for:

Based on the user interaction device, receiving the thermal parameter, the size parameter and the outdoor temperature parameter input by the user;

Alternatively, the thermal parameter, the size parameter and the outdoor temperature parameter are determined based on the network address of the smart home device.

On the basis of the above embodiment, in the digital twin room temperature prediction device provided in the embodiment of the present invention, the temperature adjustment device includes a heater, and the working parameters of the heater include working power;

The acquisition module is also specifically used for:

Based on the network address, determine the average wall thermal conductivity, the average heating working power and the average size of the area where the room is located;

The average value of the wall thermal conductivity is used as the wall thermal conductivity parameter, the average value of the heater working power is used as the heater working power, and the average value of the size is used as the size parameter.

On the basis of the above embodiment, in the digital twin room temperature prediction device provided in the embodiment of the present invention, the temperature adjustment device further includes an intelligent temperature adjustment device, and the intelligent temperature adjustment device includes at least one of an air conditioner, an electric heater, and a gas; the working parameters of the air conditioner, the working parameters of the electric heater, and the working parameters of the gas all include working power and working switch fields, and the ventilation volume parameters include ventilation volume and ventilation switch fields;

The acquisition module is also specifically used for:

Based on the network address, the working power of the air conditioner, the working power of the electric heater, the working power of the gas and the ventilation volume are collected, and based on the collection results, the working switch field of the air conditioner, the working switch field of the electric heater, the working switch field of the gas and the ventilation switch field are determined.

On the basis of the above embodiment, in the digital twin room temperature prediction device provided in the embodiment of the present invention, the direct sunlight area parameter, the room external contact area parameter and the room internal contact area parameter all include a first surface positive value and a second surface positive value, the room temperature prediction model includes a first room temperature prediction model and a second room temperature prediction model, and the indoor temperature parameter includes a first indoor temperature and a second indoor temperature;

Accordingly, the prediction module is specifically used for:

Based on the first room temperature prediction model, determine a first indoor temperature of the target room corresponding to a first positive value of a sunlight direct area parameter of the target room, a first positive value of a room external contact area parameter, a first positive value of a room internal contact area parameter, a size parameter, and an outdoor temperature parameter;

Based on the second room temperature prediction model, determine the second positive value of the direct sunlight area parameter of the target room, the second positive value of the external contact area parameter of the room, the second positive value of the internal contact area parameter of the room, the size parameters and the second indoor temperature of the target room corresponding to the outdoor temperature parameters.

Based on the above embodiments, in the digital twin room temperature prediction device provided in the embodiments of the present invention, the initial model of the room temperature prediction model includes a logistic regression model, a decision tree model, a perceptron model or a neural network model.

Specifically, the functions of each module in the digital twin room temperature prediction device provided in the embodiment of the present invention correspond one-to-one to the operating procedures of each step in the above-mentioned method embodiment, and the effects achieved are also consistent. Please refer to the above-mentioned embodiment for details, and no further details will be given in the embodiment of the present invention.

As shown in FIG. 4 , based on the above embodiment, an embodiment of the present invention provides a smart home device control device, including:

The receiving module 41 is used to receive a user demand instruction, and perform semantic analysis on the user demand instruction to determine a user semantic analysis result;

A generation module 42 is used to generate a control instruction based on the user semantic analysis result and the indoor temperature parameter of the target room obtained by the digital twin room temperature prediction method;

The control module 43 is used to control the smart home devices in the target room based on the control instruction.

Figure 5 illustrates a schematic diagram of the physical structure of an electronic device. As shown in Figure 5, the electronic device may include: a processor (Processor) 510, a communication interface (Communications Interface) 520, a memory (Memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the digital twin room temperature prediction method provided in the above embodiments, the method comprising: obtaining thermal parameters, size parameters and outdoor temperature parameters of the target room; the target room is installed with smart home devices with networking function; based on the room temperature prediction model, determining the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room; wherein the room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and the room temperature prediction model is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters; or, executing the smart home device control method provided in the above embodiments, the method comprising: receiving a user demand instruction, and performing semantic analysis on the user demand instruction to determine the user semantic analysis result; generating a control instruction based on the user semantic analysis result and the indoor temperature parameters of the target room obtained by the above digital twin room temperature prediction method; and controlling the smart home device in the target room based on the control instruction.

In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the digital twin room temperature prediction method provided in the above embodiments, the method comprising: obtaining thermal parameters, size parameters and outdoor temperature parameters of the target room; the target room is installed with a smart home device with networking function; based on the room temperature prediction model, determining the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room; wherein the room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and the room temperature prediction model is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters; or, executing the smart home device control method provided in the above embodiments, the method comprising: receiving a user demand instruction, and performing semantic analysis on the user demand instruction to determine the user semantic analysis result; based on the user semantic analysis result and the indoor temperature parameters of the target room obtained by the above digital twin room temperature prediction method, generating a control instruction; based on the control instruction, controlling the smart home device in the target room.

On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the digital twin room temperature prediction method provided in the above embodiments, the method comprising: obtaining thermal parameters, size parameters and outdoor temperature parameters of the target room; the target room is installed with a smart home device with networking function; based on the room temperature prediction model, determining the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room; wherein the room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of a sample room carrying an indoor temperature tag, and the room temperature prediction model is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters; or, executing the smart home device control method provided in the above embodiments, the method comprising: receiving a user demand instruction, and performing semantic analysis on the user demand instruction to determine the user semantic analysis result; generating a control instruction based on the user semantic analysis result and the indoor temperature parameters of the target room obtained by the above digital twin room temperature prediction method; and controlling the smart home device in the target room based on the control instruction.

The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (11)

1. A digital twin room temperature prediction method, comprising: Acquiring thermal parameters, size parameters, and outdoor temperature parameters of a target room; wherein a smart home device with networking function is installed in the target room; Determine, based on the room temperature prediction model, the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters and outdoor temperature parameters of the target room; The room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of the sample room carrying the indoor temperature tag, and the room temperature prediction model is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters; The thermal parameters include sunshine parameters and structural heat exchange parameters, wherein the sunshine parameters include sunshine direct area parameters, and the structural heat exchange parameters include room external contact area parameters and room internal contact area parameters; The direct sunlight area parameter, the room external contact area parameter and the room internal contact area parameter all include a first surface positive value and a second surface positive value, the room temperature prediction model includes a first room temperature prediction model and a second room temperature prediction model, and the indoor temperature parameter includes a first indoor temperature and a second indoor temperature; Accordingly, the step of determining the indoor temperature parameters of the target room corresponding to the thermal parameters, size parameters, and outdoor temperature parameters of the target room based on the room temperature prediction model includes: Based on the first room temperature prediction model, determine a first surface positive value of a sunlight direct area parameter of the target room, a first surface positive value of a room external contact area parameter, a first surface positive value of a room internal contact area parameter, a size parameter, and a first indoor temperature of the target room corresponding to an outdoor temperature parameter; Based on the second room temperature prediction model, determine the second positive value of the direct sunlight area parameter of the target room, the second positive value of the external contact area parameter of the room, the second positive value of the internal contact area parameter of the room, the size parameters and the second indoor temperature of the target room corresponding to the outdoor temperature parameters. 2. The digital twin room temperature prediction method according to claim 1, characterized in that the thermal parameters also include at least one of a temperature adjustment parameter and an airflow heat exchange parameter; The sunshine parameter also includes at least one of a sunshine angle parameter and a sunshine intensity parameter; The structural heat exchange parameters also include wall thermal conductivity parameters; The temperature adjustment parameters include operating parameters of the temperature adjustment device in the target room; The airflow heat exchange parameter includes at least one of a ventilation volume parameter and an outdoor wind speed parameter. 3. The digital twin room temperature prediction method according to claim 2, characterized in that the thermal parameters, the size parameters and the outdoor temperature parameters are obtained based on the following method: Based on the user interaction device, receiving the thermal parameter, the size parameter and the outdoor temperature parameter input by the user; Alternatively, the thermal parameter, the size parameter and the outdoor temperature parameter are determined based on the network address of the smart home device. 4. The digital twin room temperature prediction method according to claim 3, characterized in that the temperature adjustment device includes a heater, and the working parameters of the heater include working power; The wall thermal conductivity parameter, the heater operating power and the size parameter are determined based on the following method: Based on the network address, determine the average wall thermal conductivity, the average heating working power and the average size of the area where the room is located; The average value of the wall thermal conductivity is used as the wall thermal conductivity parameter, the average value of the heater working power is used as the heater working power, and the average value of the size is used as the size parameter. 5. The digital twin room temperature prediction method according to claim 3 is characterized in that the temperature regulating device further comprises an intelligent temperature regulating device, and the intelligent temperature regulating device comprises at least one of an air conditioner, an electric heater and a gas; the working parameters of the air conditioner, the working parameters of the electric heater and the working parameters of the gas all comprise working power and working switch fields, and the ventilation volume parameters comprise ventilation volume and ventilation switch fields; The operating parameters of the air conditioner, the operating parameters of the electric heater, the operating parameters of the gas, and the ventilation volume parameters are determined based on the following method: Based on the network address, the working power of the air conditioner, the working power of the electric heater, the working power of the gas and the ventilation volume are collected, and based on the collection results, the working switch field of the air conditioner, the working switch field of the electric heater, the working switch field of the gas and the ventilation switch field are determined. 6. The digital twin room temperature prediction method according to any one of claims 1-5 is characterized in that the initial model of the room temperature prediction model includes a logistic regression model, a decision tree model, a perceptron model or a neural network model. 7. A smart home device control method, characterized by comprising: Receive user demand instructions, perform semantic analysis on the user demand instructions, and determine user semantic analysis results; Generate a control instruction based on the user semantic analysis result and the indoor temperature parameter of the target room obtained by the digital twin room temperature prediction method according to any one of claims 1 to 6; Based on the control instruction, the smart home devices in the target room are controlled. 8. A digital twin room temperature prediction device, comprising: An acquisition module, used to acquire thermal parameters, size parameters and outdoor temperature parameters of a target room; the target room is equipped with a smart home device with networking function; A prediction module, for determining, based on a room temperature prediction model, indoor temperature parameters of the target room corresponding to thermal parameters, size parameters and outdoor temperature parameters of the target room; The room temperature prediction model is determined based on the thermal parameters, size parameters and outdoor temperature parameters of the sample room carrying the indoor temperature tag, and the room temperature prediction model is used to characterize the quantitative relationship between the thermal parameters, size parameters and outdoor temperature parameters of any room and the indoor temperature parameters; The thermal parameters include sunshine parameters and structural heat exchange parameters, the sunshine parameters include sunshine direct area parameters, and the structural heat exchange parameters include room external contact area parameters and room internal contact area parameters; The direct sunlight area parameter, the room external contact area parameter and the room internal contact area parameter all include a first surface positive value and a second surface positive value, the room temperature prediction model includes a first room temperature prediction model and a second room temperature prediction model, and the indoor temperature parameter includes a first indoor temperature and a second indoor temperature; Accordingly, the prediction module is specifically used for: Based on the first room temperature prediction model, determine a first surface positive value of a sunlight direct area parameter of the target room, a first surface positive value of a room external contact area parameter, a first surface positive value of a room internal contact area parameter, a size parameter, and a first indoor temperature of the target room corresponding to an outdoor temperature parameter; Based on the second room temperature prediction model, determine the second surface positive value of the direct sunlight area parameter of the target room, the second surface positive value of the room's external contact area parameter, the second surface positive value of the room's internal contact area parameter, the size parameters and the second indoor temperature of the target room corresponding to the outdoor temperature parameters. 9. A smart home device control device, comprising: A receiving module is used to receive a user demand instruction, and perform semantic analysis on the user demand instruction to determine a user semantic analysis result; A generation module, used to generate a control instruction based on the user semantic analysis result and the indoor temperature parameter of the target room obtained by the digital twin room temperature prediction method according to any one of claims 1 to 6; A control module is used to control the smart home devices in the target room based on the control instruction. 10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the digital twin room temperature prediction method as described in any one of claims 1 to 6 or the smart home device control method as described in claim 7 is implemented. 11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the digital twin room temperature prediction method as described in any one of claims 1 to 6 or the smart home device control method as described in claim 7 is implemented.