阅读说明：本技术 电热地暖的温度控制方法、装置和系统 (Temperature control method, device and system for electric floor heating ) 是由 王浩强 张伟 王刚 王梦海 张亚飞 李永武 于 2021-01-08 设计创作，主要内容包括：本发明提供了一种电热地暖的温度控制方法、装置和系统,该方法包括：获取室内每个房间的实时温度、设定温度和人物信息,其中,所述人物信息用于表征每个房间内是否存在人物以及存在人物的房间中的人物所处状态；针对每个房间,根据当前房间的设定温度和人物信息,确定当前房间的目标温度。本发明的方案是根据当前房间的设定温度和人物信息,确定当前房间的目标温度,如此可以避免不同房间在何时都采用恒温控制,从而可以减少能源浪费,实现了室内温度的自动控制。(The invention provides a temperature control method, a device and a system for electric floor heating, wherein the method comprises the following steps: the method comprises the steps of obtaining real-time temperature, set temperature and character information of each indoor room, wherein the character information is used for representing whether characters exist in each indoor room or not and states of the characters in the indoor rooms with the characters; and determining the target temperature of the current room according to the set temperature and the character information of the current room aiming at each room. The scheme of the invention is that the target temperature of the current room is determined according to the set temperature and the character information of the current room, so that the situation that different rooms adopt constant temperature control can be avoided, the energy waste can be reduced, and the automatic control of the indoor temperature is realized.)

1. The temperature control method of the electric floor heating is characterized by comprising the following steps:

the method comprises the steps of obtaining real-time temperature, set temperature and character information of each indoor room, wherein the character information is used for representing whether characters exist in each indoor room or not and states of the characters in the indoor rooms with the characters;

and determining the target temperature of the current room according to the set temperature and the character information of the current room aiming at each room.

2. The method of claim 1, wherein determining the target temperature of the current room according to the set temperature and the personal information of the current room comprises:

determining whether people exist in the current room or not according to the people information of the current room;

if the person exists, determining the set temperature of the current room as the target temperature of the current room;

and if no person exists, determining the difference value between the set temperature of the current room and the first preset temperature as the target temperature of the current room.

3. The method of claim 2, wherein after the determining the set temperature of the current room as the target temperature of the current room, further comprising:

determining whether a bed exists in a current room or not according to a preset first neural network model;

if the bed exists, determining whether the contact ratio of the person in the current room and the bed is higher than a first preset value or not according to the first neural network model and determining whether the person in the current room does not move within a first preset time length or not;

and in a first preset time period, if the contact ratio of the person in the current room and the bed is higher than a first preset value and the person in the current room does not move within a first preset time period, determining the difference value between the set temperature of the current room and the second preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

4. The method of claim 2, wherein after the determining the set temperature of the current room as the target temperature of the current room, further comprising:

determining whether a dining table exists in a current room or not according to a preset first neural network model;

if the dining table exists, determining whether the contact ratio of the person in the current room and the dining table is higher than a second preset value or not according to the first neural network model and determining whether food exists on the dining table in the current room or not;

and if the coincidence degree of the person in the current room and the dining table is higher than the second preset value and food exists on the dining table in the current room, determining the difference value between the set temperature of the current room and the third preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

5. The method of claim 2, wherein after the determining the set temperature of the current room as the target temperature of the current room, further comprising:

determining whether a desk exists in a current room according to a preset first neural network model;

if the desk exists, determining whether the contact ratio of the person in the current room and the desk is higher than a third preset value according to the first neural network model and determining whether the person in the current room does not move within a second preset time period;

and if the contact ratio of the person in the current room and the desk is higher than a third preset value and the person in the current room does not move within a second preset time period, determining the sum of the set temperature of the current room and the fourth preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

6. The method of claim 2, wherein after the determining the set temperature of the current room as the target temperature of the current room, further comprising:

determining whether the number of times of limb movement of the person in the current room exceeds a preset number of times within a third preset time period according to a preset second neural network model;

and if the preset times are exceeded, determining the difference value of the fifth preset temperature of the set temperature of the current room as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

7. The method of any one of claims 1-6, wherein after obtaining the real-time temperature, the set temperature, and the personal information for each room in the room, further comprising:

and responding to the fact that no person exists in each room, and after the fourth preset time period, determining the difference value between the set temperature of each room and the sixth preset temperature as the target temperature of the room.

8. The method of any one of claims 1-6, wherein after obtaining the real-time temperature, the set temperature, and the personal information for each room in the room, further comprising:

for each room, performing:

and in response to that no person exists in each room except the bedroom and a person exists in each bedroom within the second preset time period, determining the difference value between the set temperature of each room except the bedroom and the seventh preset temperature as the target temperature of the room, and determining the difference value between the set temperature of each bedroom and the eighth preset temperature as the target temperature of the bedroom.

9. Temperature control device that electric heat ground warms up, its characterized in that includes:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring real-time temperature, set temperature and figure information of each indoor room, and the figure information is used for representing whether a figure exists in each indoor room and the state of the figure in the room with the figure;

and the first determining module is used for determining the target temperature of the current room according to the set temperature and the character information of the current room aiming at each room.

10. Temperature control device that electric heat ground warms up, its characterized in that includes: at least one memory and at least one processor;

the at least one memory to store a machine readable program;

the at least one processor, configured to invoke the machine readable program, to perform the method of any of claims 1 to 8.

11. Temperature control system that electric heat ground warms up, its characterized in that includes: the system comprises terminal equipment, a cloud server, a gateway, a temperature control device and a power control device;

the temperature control device is the device of claim 10;

the terminal equipment is connected with the power control device sequentially through the cloud server, the gateway, the temperature control device and the power control device;

when the system is in a manual control mode, the terminal equipment is used for sending a control instruction to the power control device through the cloud server, the gateway and the temperature control device in sequence, or the terminal equipment is used for sending the control instruction to the power control device through the gateway and the temperature control device in sequence;

when the system is in an automatic control mode, the power control device is used for determining the heating power of the current room according to the real-time temperature of the current room and the target temperature of the current room sent by the temperature control device.

12. A computer readable medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 8.

Technical Field

The invention relates to the technical field of temperature control, in particular to a method, a device and a system for controlling the temperature of an electric floor heating system.

Background

The existing indoor floor heating mode generally adopts the following modes: the water is used as heat transfer medium, and a copper pipe or PVC plastic pipe which is filled with hot water is buried under the indoor floor or the ceramic tile. The above manner is constant water temperature control (i.e. constant temperature control). However, when there is no person in the room, the above method causes a waste of energy.

Therefore, there is a need for a method, a device and a system for controlling temperature of an electric floor heating system to solve the above problems.

Disclosure of Invention

The embodiment of the invention provides a temperature control method, a device and a system of an electric floor heating system, which can realize automatic control of indoor temperature and are beneficial to energy conservation.

In a first aspect, an embodiment of the present invention provides a temperature control method for an electric floor heating, including:

the method comprises the steps of obtaining real-time temperature, set temperature and character information of each indoor room, wherein the character information is used for representing whether characters exist in each indoor room or not and states of the characters in the indoor rooms with the characters;

and determining the target temperature of the current room according to the set temperature and the character information of the current room aiming at each room.

In one possible design, the determining the target temperature of the current room according to the set temperature and the personal information of the current room includes:

determining whether people exist in the current room or not according to the people information of the current room;

if the person exists, determining the set temperature of the current room as the target temperature of the current room;

and if no person exists, determining the difference value between the set temperature of the current room and the first preset temperature as the target temperature of the current room.

In one possible design, after the determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether a bed exists in a current room or not according to a preset first neural network model;

if the bed exists, determining whether the contact ratio of the person in the current room and the bed is higher than a first preset value or not according to the first neural network model and determining whether the person in the current room does not move within a first preset time length or not;

and in a first preset time period, if the contact ratio of the person in the current room and the bed is higher than a first preset value and the person in the current room does not move within a first preset time period, determining the difference value between the set temperature of the current room and the second preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

In one possible design, after the determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether a dining table exists in a current room or not according to a preset first neural network model;

if the dining table exists, determining whether the contact ratio of the person in the current room and the dining table is higher than a second preset value or not according to the first neural network model and determining whether food exists on the dining table in the current room or not;

and if the coincidence degree of the person in the current room and the dining table is higher than the second preset value and food exists on the dining table in the current room, determining the difference value between the set temperature of the current room and the third preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

In one possible design, after the determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether a desk exists in a current room according to a preset first neural network model;

if the desk exists, determining whether the contact ratio of the person in the current room and the desk is higher than a third preset value according to the first neural network model and determining whether the person in the current room does not move within a second preset time period;

and if the contact ratio of the person in the current room and the desk is higher than a third preset value and the person in the current room does not move within a second preset time period, determining the sum of the set temperature of the current room and the fourth preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

In one possible design, after the determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether the number of times of limb movement of the person in the current room exceeds a preset number of times within a third preset time period according to a preset second neural network model;

and if the preset times are exceeded, determining the difference value between the set temperature of the current room and the fifth preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

In one possible design, after the obtaining the real-time temperature, the set temperature, and the personal information of each room in the room, the method further includes:

and responding to the fact that no person exists in each room, and after the fourth preset time period, determining the difference value between the set temperature of each room and the sixth preset temperature as the target temperature of the room.

In one possible design, after the obtaining the real-time temperature, the set temperature, and the personal information of each room in the room, the method further includes:

for each room, performing:

and in response to that no person exists in each room except the bedroom and a person exists in each bedroom within the second preset time period, determining the difference value between the set temperature of each room except the bedroom and the seventh preset temperature as the target temperature of the room, and determining the difference value between the set temperature of each bedroom and the eighth preset temperature as the target temperature of the bedroom.

In a second aspect, an embodiment of the present invention provides a temperature control device for an electric floor heating, including:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring real-time temperature, set temperature and figure information of each indoor room, and the figure information is used for representing whether a figure exists in each indoor room and the state of the figure in the room with the figure;

and the first determining module is used for determining the target temperature of the current room according to the set temperature and the character information of the current room aiming at each room.

In a third aspect, an embodiment of the present invention provides a temperature control device for electric floor heating, including: at least one memory and at least one processor;

the at least one memory to store a machine readable program;

the at least one processor is configured to invoke the machine-readable program to perform the method described above.

In a fourth aspect, an embodiment of the present invention provides a temperature control system for electric floor heating, including: the system comprises terminal equipment, a cloud server, a gateway, a temperature control device and a power control device;

the temperature control device is the device as described above;

the terminal equipment is connected with the power control device sequentially through the cloud server, the gateway, the temperature control device and the power control device;

when the system is in a manual control mode, the terminal equipment is used for sending a control instruction to the power control device through the cloud server, the gateway and the temperature control device in sequence, or the terminal equipment is used for sending the control instruction to the power control device through the gateway and the temperature control device in sequence;

when the system is in an automatic control mode, the power control device is used for determining the heating power of the current room according to the real-time temperature of the current room and the target temperature of the current room sent by the temperature control device.

In a fifth aspect, the present invention provides a computer readable medium, on which computer instructions are stored, and when executed by a processor, the computer instructions cause the processor to execute the method described above.

According to the scheme, the temperature control method, the device and the system for the electric floor heating system, provided by the invention, the real-time temperature, the set temperature and the character information of each indoor room are obtained, wherein the character information is used for representing whether a character exists in each indoor room and the state of the character in the indoor room where the character exists, and then the target temperature of the current room is determined according to the set temperature and the character information of the current room. According to the technical scheme, the target temperature of the current room is determined according to the set temperature and the character information of the current room, so that the situation that different rooms are controlled at constant temperature at any time can be avoided, energy can be saved, and automatic control of indoor temperature is realized.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a flowchart of a temperature control method for an electric floor heating according to an embodiment of the present invention;

fig. 2 is a flowchart of a temperature control method for an electric floor heating according to another embodiment of the invention;

fig. 3 is a schematic diagram of a temperature control system for an electric floor heating provided by an embodiment of the present invention;

fig. 4 is a schematic diagram of a device where a temperature control device of an electric floor heating system provided by an embodiment of the invention is located;

fig. 5 is a schematic diagram of a temperature control device for electric floor heating according to an embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.

As described in the background art, the existing control means is "unified" control, that is, the same control strategy is adopted for all the day and each room to perform temperature control (that is, indoor heating is constant temperature control). However, in an actual usage scenario, the heating requirements of each room in the room are not consistent, for example, the sleeping time can be reduced appropriately, the room temperature can be reduced in an unmanned room, and the room temperature can be reduced in the daytime when no one is at home. That is, the existing control method cannot adapt to the heating demand change, which causes a certain energy waste.

In the actual electric floor heating use scene, the place where people are at home only occupies a very small part of the total area of the home, if the quick heating characteristic of an electric heating product (such as an electric heating floor or an electric heating ceramic tile) is utilized, the temperature of an unmanned area can be temporarily reduced, and when people enter the unmanned area, quick heating is carried out, so that energy conservation can be realized. In addition, for normal three-family, the user can carry out low-temperature operation on the floor heating in the working or learning time period in the daytime, the floor heating is rapidly heated before returning home, and the normal-temperature operation is recovered after returning home, so that the obvious energy-saving effect can be realized compared with the existing all-day constant-temperature operation mode.

The above is the inventive concept of the present invention, and the scheme provided by the present invention can be obtained based on the inventive concept, and the present invention is explained in detail below.

Fig. 1 is a flowchart of a temperature control method for electric floor heating according to an embodiment of the present invention. As shown in fig. 1, the method may include the steps of:

step 101, acquiring real-time temperature, set temperature and character information of each indoor room, wherein the character information is used for representing whether characters exist in each indoor room or not and states of the characters in the indoor rooms with the characters;

and 102, determining the target temperature of the current room according to the set temperature and the character information of the current room aiming at each room.

In the embodiment of the invention, the temperature control method determines the target temperature of the current room according to the set temperature and the character information of the current room, so that the situation that different rooms adopt constant temperature control at any time can be avoided, energy can be saved, and the automatic control of the indoor temperature is realized.

It is understood that the real-time temperature of each room in step 101 may be obtained by providing a first temperature sensor in each room, and the personal information of each room may be obtained by providing a personal information sensing sensor in each room, where the personal information sensing sensor includes, but is not limited to, an infrared sensor, an image sensor, an infrared thermal imaging sensor, and a camera, and the embodiment of the present invention is not limited in detail herein. In order to ensure the safety of the electric heating product in each room, the electric heating product in each room is further provided with a second temperature sensor for detecting the real-time temperature of the electric heating product, for example, when the detected temperature is higher than the safety temperature (for example, 40 ℃), the heating power of the electric heating product immediately becomes zero, i.e., the heat generation of the electric heating product is cut off.

Fig. 2 is a flowchart of a temperature control method for electric floor heating according to another embodiment of the present invention. As shown in fig. 2, in an embodiment of the present invention, the determining the target temperature of the current room according to the set temperature and the personal information of the current room includes:

step 202, determining whether people exist in the current room according to the people information of the current room.

In this step, as mentioned above, it can be determined whether there is a person in the current room by providing a person information sensing sensor, which is described below.

Step 203, if there is a person, determining the set temperature of the current room as the target temperature of the current room.

In this step, if there is a person in the current room, it indicates that the set temperature of the current room is a comfortable temperature that the user considers to be more ideal, and therefore the set temperature of the current room should be determined as the target temperature of the current room.

And 204, if no person exists, determining the difference value between the set temperature of the current room and the first preset temperature as the target temperature of the current room.

In this step, if there is no person in the current room, the target temperature of the current room can be lowered to a proper temperature for saving electricity, and the user does not feel any discomfort (e.g., cold) due to the lowered target temperature of the room. Wherein the first preset temperature may be, for example, 4-6 ℃.

In addition, since a user may frequently get in and out of some rooms within a period of time (e.g., 10min), in order to avoid continuously triggering a change of the target temperature of the room, a difference between the set temperature of the current room and the first preset temperature may be determined as the target temperature of the current room if there is no person in the current room for a preset period of time (e.g., 10 min).

In the embodiment of the invention, the temperature of the current room is adaptively controlled by determining whether a person exists in the current room, so as to realize energy-saving operation or energy conservation.

With continuing reference to fig. 2, in an embodiment of the present invention, after determining the set temperature of the current room as the target temperature of the current room, the method further includes:

step 205, determining whether a bed is in the current room according to a preset first neural network model.

In this step, the first neural network model may be a lightweight multi-objective detection neural network model, such as MobileNet-SSD, MobileNet-Yolo, etc., and is not particularly limited herein. Whether a bed exists in a current room or not can be determined through a preset or pre-trained first neural network model, for example, an image sensor is arranged in each room, and the first neural network model can perform target recognition on an image input by the image sensor, which is referred to as bed recognition herein. In some embodiments, the results of target recognition may be classified by setting a confidence threshold, for example, when the recognition result is a bed and the confidence is greater than 80%, the recognition result may be considered correct.

It should be noted that if the result of the first neural network model identification is a bed, the room can be considered as a bedroom, but it cannot be further determined whether the user goes to sleep. This is because if the user goes to sleep, the target temperature of the bedroom can be controlled, for example, by appropriately lowering a certain temperature, so that the user can sleep more comfortably. Therefore, it is necessary to further identify other factors using the first neural network model to improve the accuracy of identifying that the user enters the sleep state.

And step 206, if the bed exists, determining whether the contact ratio of the person in the current room and the bed is higher than a first preset value according to the first neural network model and determining whether the person in the current room does not move within a first preset time.

In this step, the first neural network model may identify objects, such as persons and beds. The contact ratio between the person in the current room and the bed is higher than a first preset value, and the person in the current room is determined not to move within a first preset time period, so that the user can be considered to enter the sleep state, and the target temperature of the room can be automatically controlled to be properly reduced. In some embodiments, the first preset value may be, for example, 90%, and the first preset time period may be, for example, 30min, which is not specifically limited herein.

However, if the coincidence degree of the person and the bed in the current room is not higher than the first preset value, it may be interpreted that the person is not in the bed, and there is no reason to consider the user in the sleep state. Secondly, even if the contact ratio between the person in the current room and the bed is higher than the first preset value, if the person in the current room moves within the first preset time period, it can be stated that the user has not completely entered the sleep state, for example, the user is rolling over the reverse side. Therefore, in the embodiment of the present invention, it is determined that the user has completely entered the sleep state by determining that the contact ratio between the person in the current room and the bed is higher than the first preset value and determining that the person in the current room has not moved within the first preset time period.

Step 207, in a first preset time period, if the contact ratio of the person in the current room and the bed is higher than a first preset value and the person in the current room does not move within the first preset time period, determining the difference value between the set temperature of the current room and the second preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

In this step, as shown in step 206, after the user completely enters the sleep state, in order to improve the sleep quality of the user, the difference between the set temperature of the current room and the second preset temperature may be considered to be determined as the target temperature of the current room. In some embodiments, the second predetermined temperature may be 2-4 ℃.

In contrast, if it cannot be determined that the user is in the sleep state through the first neural network model, it is not necessary to adjust the target temperature of the current room, that is, to determine the set temperature (e.g., 25 ℃) of the current room as the target temperature of the current room.

In the embodiment of the invention, whether the person in the current room is in the sleep state can be determined through the preset first neural network model, and when the person is in the sleep state, the set temperature of the current room is properly reduced by a certain temperature so as to improve the sleep quality of a user.

In an embodiment of the present invention, after determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether a dining table exists in a current room or not according to a preset first neural network model;

if the dining table exists, determining whether the contact ratio of the person in the current room and the dining table is higher than a second preset value or not according to the first neural network model and determining whether food exists on the dining table in the current room or not;

and if the coincidence degree of the person in the current room and the dining table is higher than the second preset value and food exists on the dining table in the current room, determining the difference value between the set temperature of the current room and the third preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

In the embodiment of the invention, whether the character in the current room is in a dining state can be determined through the preset first neural network model, and when the character is in the dining state, the set temperature in the current room is properly reduced by a certain temperature so as to improve the appetite of the user.

The first neural network model may be a lightweight multi-target detection neural network model, such as MobileNet-SSD, MobileNet-YoLo, and the like, and is not particularly limited herein. Whether a dining table exists in a current room or not can be determined through a preset or pre-trained first neural network model, for example, an image sensor is arranged in each room, and the first neural network model can perform target recognition on an image input by the image sensor, which is referred to as recognition of the dining table herein. In some embodiments, the results of the target recognition may be classified by setting a confidence threshold, for example, when the recognition result is a dining table and the confidence is greater than 80%, the recognition result may be considered to be correct.

If the table is identified as a result of the first neural network model, the room can be considered as a restaurant, but it cannot be further determined whether the user is eating. This is because if the user is having meals, the target temperature of the restaurant can be controlled, for example, to appropriately lower a certain temperature, so that the user's meals are more comfortable. Therefore, it is necessary to further identify other factors by using the first neural network model to improve the accuracy of identifying that the user is in a dining state.

The first neural network model may identify objects, such as people and tables. The contact ratio between the person in the current room and the dining table is higher than the second preset value, and food is determined to be on the dining table in the current room, then the user can be considered to have entered the dining state, and at the moment, the target temperature in the room can be automatically controlled to be properly reduced. In some embodiments, the second preset value may be, for example, 90%, and is not specifically limited herein.

However, if the coincidence degree between the person in the current room and the table is not higher than the second preset value, it may be said that the person is not at the table, and there is no reason to consider the user to be in a dining state. Secondly, even if the coincidence degree of the person in the current room and the dining table is higher than the second preset value, if no food is on the dining table in the current room, the user can be considered to be not in a dining state, for example, the user only sits at the dining table for rest. Therefore, in the embodiment of the present invention, it is determined that the user has completely entered the dining state by determining that the coincidence degree between the person in the current room and the dining table is higher than the second preset value and determining that there is food on the dining table in the current room.

After the user completely enters the dining state, in order to make the dining quality of the user higher, the difference value between the set temperature of the current room and the third preset temperature may be considered to be determined as the target temperature of the current room. In some embodiments, the third predetermined temperature may be 2-4 ℃.

In contrast, if it cannot be determined that the user is in the dining state through the first neural network model, it is not necessary to adjust the target temperature of the current room, that is, to determine the set temperature (e.g., 25 ℃) of the current room as the target temperature of the current room.

In an embodiment of the present invention, after determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether a desk exists in a current room according to a preset first neural network model;

if the desk exists, determining whether the contact ratio of the person in the current room and the desk is higher than a third preset value according to the first neural network model and determining whether the person in the current room does not move within a second preset time period;

and if the contact ratio of the person in the current room and the desk is higher than a third preset value and the person in the current room does not move within a second preset time period, determining the sum of the set temperature of the current room and the fourth preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

In the embodiment of the invention, whether the character in the current room is in the working and learning state can be determined through the preset first neural network model, and when the character is in the working and learning state, the set temperature in the current room is properly increased by a certain temperature so as to improve the working and learning concentration of the user.

The first neural network model may be a lightweight multi-target neural network model, such as MobileNet-SSD or MobileNet-YoLo, and is not particularly limited herein. Whether the current room has a desk or not can be determined through a preset or pre-trained first neural network model, for example, an image sensor is arranged in each room, and the first neural network model can perform target recognition on an image input by the image sensor, which is referred to as recognition of the desk herein. In some embodiments, the result of the target recognition may be classified by setting a confidence threshold, for example, when the recognition result is a desk and the confidence is greater than 80%, the recognition result may be considered correct.

If the first neural network model recognizes a desk, the room may be considered as a study room, but it cannot be further determined whether the user is working or learning. This is because if the user is working and learning, the target temperature of the study room can be controlled, for example, to be appropriately raised to make the user's working and learning more attentive. Therefore, it is necessary to further identify other factors by using the first neural network model to improve the identification accuracy of the user in the working learning state.

The first neural network model may identify objects, such as people and desks. If the contact ratio between the person in the current room and the desk is higher than the third preset value and the person in the current room is determined not to move within the second preset time period, the user can be considered to enter the working and learning state, and the target temperature of the room can be automatically controlled to be properly increased. In some embodiments, the third preset value may be, for example, 90%, and the second preset time period may be, for example, 30min, which is not specifically limited herein.

However, if the degree of coincidence between the character in the current room and the desk is not higher than the third preset value, it may be interpreted that the character is not at the desk, and there is no reason to consider the user to be in the work and study state. Secondly, even if the contact ratio between the person in the current room and the desk is higher than the third preset value, if the person in the current room moves within the second preset time period, it can be stated that the user has not completely entered the work and study state. Therefore, in the embodiment of the present invention, it is determined that the user has completely entered the work and study state by determining that the degree of contact between the person in the current room and the desk is higher than the third preset value and determining that the person in the current room has not moved within the second preset time period.

After the user completely enters the work learning state, in order to make the work learning concentration of the user higher, the sum of the set temperature of the current room and the fourth preset temperature may be considered to be determined as the target temperature of the current room. In some embodiments, the fourth predetermined temperature may be 1-3 ℃.

In contrast, if it cannot be determined that the user is in the working learning state through the first neural network model, it is not necessary to adjust the target temperature of the current room, that is, to determine the set temperature (e.g., 25 ℃) of the current room as the target temperature of the current room.

In an embodiment of the present invention, after determining the set temperature of the current room as the target temperature of the current room, the method further includes:

determining whether the number of times of limb movement of the person in the current room exceeds a preset number of times within a third preset time period according to a preset second neural network model;

and if the preset times are exceeded, determining the difference value between the set temperature of the current room and the fifth preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

In the embodiment of the invention, whether the character in the current room is in a motion state can be determined through the preset second neural network model, and when the character is in the motion state, the set temperature of the current room is properly reduced by a certain temperature so as to reduce the sense of dryness when the user moves.

It should be noted that the second neural network model may be a motion detection neural network model, such as LRCN, TSN, C3D, etc., and is not limited herein. The body movement state of the person in the current room can be determined through a preset or pre-trained second neural network model, for example, a camera is arranged in each room, and the second neural network model can identify a moving target of a video stream input by the camera, which is referred to herein as identifying the body amplitude of the person in the video stream. In some embodiments, the result of the target recognition may be classified by setting a confidence threshold, for example, when the recognition result is a limb and the confidence is greater than 80%, the recognition result may be considered to be correct. Then, in the video stream, the number of times of limb movement of the person in the current room is determined by comparing the change frequency of the limb coordinates of several video frame images within a third preset time period, for example, the third preset time period may be 10min, and if the number of times of limb movement of the person within 10min exceeds a preset number (for example, 20 times), the person may be considered to be in a motion state, so that the target temperature of the current room is controlled to be appropriately lowered to reduce the feeling of dryness when the user moves. For example, the fifth preset temperature is 4-6 ℃.

In an embodiment of the present invention, after the acquiring the real-time temperature, the set temperature and the personal information of each room in the room, the method further includes:

and responding to the fact that no person exists in each room, and after the fourth preset time period, determining the difference value between the set temperature of each room and the sixth preset temperature as the target temperature of the room.

In an embodiment of the present invention, when no person exists in each room, after a fourth preset time (for example, 30min), all the residents may be considered to be out at this time, and in order to implement energy-saving operation of the electric floor heating system, the target temperatures of all the rooms may be considered to be reduced by a certain temperature value, for example, the sixth preset temperature is 10 ℃.

It is understood that, when no person exists in the current room, the foregoing embodiment may reduce the target temperature of the current room by an appropriate temperature, for example, by a first preset temperature, in order to save power. However, this does not conflict with the solution of the present embodiment, and it is understood that the solution of the previous embodiment is triggered instantaneously (or after a period of time (e.g. 10 min)), and the solution of the present embodiment is triggered after 30 min. For example, when a person in a room is 10min after the person in the room exits from the room, the target temperature of the room is controlled to be a difference value between the set temperature and the first preset temperature; and when the people in all the rooms are 30min after the people in all the rooms exit from the rooms, controlling the target temperature of all the rooms to be the difference value between the set temperature and a sixth preset temperature, wherein the first preset temperature can be 4-6 ℃, and the sixth preset temperature can be 10 ℃.

In an embodiment of the present invention, after the acquiring the real-time temperature, the set temperature and the personal information of each room in the room, the method further includes:

for each room, performing:

and in response to that no person exists in each room except the bedroom and a person exists in each bedroom within the second preset time period, determining the difference value between the set temperature of each room except the bedroom and the seventh preset temperature as the target temperature of the room, and determining the difference value between the set temperature of each bedroom and the eighth preset temperature as the target temperature of the bedroom.

In an embodiment of the invention, the second preset time period may be 11 pm to 7 am, and in this time period, the electric floor heating system may perform energy-saving operation by monitoring whether the user is in a sleep state. Specifically, in the second preset time period, in response to that no person exists in each room except the bedroom and that the person exists in each bedroom, it may be determined that the user of the bedroom is in the sleep state at this time, and therefore, in order to achieve energy-saving operation of the electric floor heating system, it may be considered that the target temperature of all rooms except the bedroom (for example, a living room, a dining room, a toilet, a balcony, and the like) is reduced by a certain temperature value, for example, the seventh preset temperature is 10 ℃. In addition, in order to improve the sleep quality of the user, the temperature value of the bedroom room can be properly reduced, for example, the eighth preset temperature is 2-4 ℃.

It should be noted that, the embodiment and the aforementioned scheme for determining whether the user enters the sleep state by using the first neural network model may cooperate with each other, that is, if the room of the user is not configured with hardware equipped with the first neural network model, the sleep state may also be monitored by using the scheme, so as to achieve automatic control of the room temperature. Of course, if the room of the user is configured with the hardware loaded with the first neural network model, if the monitoring result of the embodiment is that the user is in a sleep state, and the monitoring result of the scheme for determining whether the user enters the sleep state by using the first neural network model is that the user is not in the sleep state, since the monitoring precision of the technical scheme of the latter is higher, the monitoring result to be determined at this time is that the user is not in the sleep state, that is, the temperature change of the room is not controlled, so as to better realize the automatic control of the room temperature.

The following describes a method for determining whether a person is present in a current room by providing a personal information sensing sensor, wherein only three sensing sensors are exemplified herein.

(1) The figure information induction sensor is an infrared sensor

The infrared sensor can receive human body infrared signals within the range of 1-2 m, and can not be directly used for judging whether people exist in a room or not due to the fact that the sensing distance is limited and people movement cannot be sensed, so that the infrared sensor can be respectively installed on the inner side and the outer side of each room door. If people enter from the outside of the door, the infrared sensor positioned outside the door is triggered before the infrared sensor positioned inside the door; if a person walks out of the door, the infrared sensor located inside the door triggers before the infrared sensor located outside the door. Based on this, whether someone enters the current room can be judged through the infrared sensor, namely whether the person exists in the room is determined. It should be noted that the scheme is suitable for scenes of a small number of users, and the recognition accuracy is low in scenes with a large number of users, and the scene recognition is difficult to use. The pseudo-code (or logic principle) of its triggering can be as follows:

traversing a set of infrared sensors on each door (including an out-door infrared sensor and an in-door infrared sensor) (a corresponds to a room inside the door, B corresponds to a room outside the door):

IF the infrared sensors inside and outside the IF door are all triggered, then

IF the infrared sensor in the door is triggered earlier than the infrared sensor outside the door, then

The person leaves from the room A and enters the room B;

IF the infrared sensor outside the door is triggered earlier than the infrared sensor inside the door, the person leaves the room B and enters the room a.

(2) The figure information induction sensor is an image sensor

The image sensor has wide range of action, and through proper hardware selection, the image sensor can work at low illumination, and the image sensor can be used for monitoring whether people exist in each room by being installed at a proper position of each room. The scheme is suitable for public places. The pseudo-code (or logic principle) of its triggering can be as follows:

loading a MobileNetSSD neural network model;

traversing the image sensor of each room;

reading an image of an image sensor of a current room;

processing the received image into a gray image and adjusting the size to 300 x 300;

and taking the received gray level image as the input of a neural network, and performing image recognition:

IF there is a person in the IF recognition result and the confidence is greater than 80, then

The existence of a person in the current room is proved.

(3) The figure information induction sensor is an infrared thermal imaging sensor

The infrared thermal imaging sensor has the characteristic of directly carrying out thermal detection, can obtain thermal images, can be used in a dark light environment, has no privacy risk, has strong reliability because the human body temperature characteristic is obvious and is higher than the background temperature, but has higher cost compared with an image sensor. The pseudo-code (or logic principle) of its triggering can be as follows:

loading a MobileNetSSD neural network model;

traversing the infrared thermal imaging sensors of each room;

reading a thermal image of an infrared thermal imaging sensor of a current room;

processing the received thermal image into a grayscale image and adjusting the size to 300 × 300;

taking the received gray level image as the input of a neural network to carry out image recognition;

IF there is a person in the IF recognition result and the confidence is greater than 80, then

IF is equal to the average temperature of the corresponding region-the temperature of the human body <2 deg.C, then

The existence of a person in the current room is proved.

It should be noted that the infrared thermal imaging sensor may measure an average temperature of an area (i.e., a corresponding area) where a human body is located, or may measure a temperature of the human body.

Fig. 3 is a schematic diagram of a temperature control system of an electric floor heating system provided by an embodiment of the invention. As shown in fig. 3, the system includes a terminal device 301, a cloud server 302, a gateway 303, a temperature control device 304, and a power control device 305;

temperature control device 305 is the device in which the temperature control device shown in fig. 4 is located (i.e., temperature control device 305 is a physical device);

the terminal equipment 301 is connected with the cloud server 302, the gateway 303, the temperature control device 304 and the power control device 305 in sequence;

when the system is in a manual control mode, the terminal device 301 is used for sending a control instruction to the power control device 305 sequentially through the cloud server 302, the gateway 303 and the temperature control device 304, or the terminal device 301 is used for sending the control instruction to the power control device 305 sequentially through the gateway 303 and the temperature control device 304;

while the system is in the automatic control mode, for each room, the power control means 305 is adapted to determine the heating power of the current room based on the real-time temperature of the current room and the target temperature of the current room sent by the temperature control means 304.

In the embodiment of the invention, the temperature control system of the electric floor heating system can realize short-distance control and remote control through the mobile terminal, so that the use convenience of a user is improved.

Specifically, the temperature control device may include an operation core module and a sensing module, wherein the operation core module may select an embedded core board having a certain operation performance, such as a raspberry pi or a jetsonnano core board, and is mainly responsible for data processing and data interaction. The sensing module is a character information sensing sensor in the above contents. The sensing module sends the data of the personal information to the operation core module, and the operation core module processes the data of the personal information, analyzes the personal information of the current room, generates a corresponding control command and sends the control command to the power control device. Besides, the operation core module also plays a role of a wireless control intermediary. The cell-phone APP of user can be connected to temperature control device through wifi, and the rethread carries out the instruction transmission with the power control device in each room. The mobile phone APP sends the control instruction to the power control device (remote control at this time) through the cloud server, the gateway and the temperature control device in sequence, or sends the control instruction to the power control device (close control at this time) through the gateway and the temperature control device in sequence; meanwhile, the power control device can send the real-time temperature of each room monitored by the power control device to the operation core module of the temperature control device for temporary storage, and then the real-time temperature of each room is monitored by sequentially passing through the gateway and the cloud server and synchronizing to the mobile phone APP.

It is understood that the temperature control system may also reserve an access interface (e.g., API interface) for accessing a relevant department (e.g., a national grid). For example, the application method is as follows: a) if the urban power consumption is stable and the pressure of the power consumption load is not high, the system set balance temperature can be improved through a control instruction, namely, the power consumption of the electric floor heating system is improved, and the redundant consumed energy can be stored in a building body in the form of heat energy; b) when the urban electricity peak is reached, the system setting balance temperature can be properly reduced through the control instruction, the electricity consumption of the electric floor heating system is reduced, and the damage to the power supply system caused by a large amount of electricity is prevented.

It should be noted that, when the temperature control system is in the manual control mode, the power control device can only be controlled manually through the mobile phone APP or the control panel thereon. At this time, the temperature control module is only used as a data server for collecting the state data and forwarding the control instruction.

Further, the power control device is used for determining the heating power of the current room according to the real-time temperature of the current room and the target temperature of the current room sent by the temperature control device, and specifically comprises the following steps: 1) if the difference value between the real-time temperature of the current room and the target temperature of the current room sent by the temperature control device is more than 1 ℃, determining that the heating power of the current room is zero; 2) if the difference value between the target temperature of the current room sent by the temperature control device and the real-time temperature of the current room is more than or equal to 2 ℃, determining that the heating power of the current room is increased by 50%; 3) if the difference value between the target temperature of the current room sent by the temperature control device and the real-time temperature of the current room is more than or equal to 1 ℃ and less than 2 ℃, determining that the heating power of the current room is increased by 30%; 4) if the difference value between the target temperature of the current room sent by the temperature control device and the real-time temperature of the current room is more than or equal to 0.5 ℃ and less than 1 ℃, determining that the heating power of the current room is increased by 10%; 5) and if the difference value between the target temperature of the current room sent by the temperature control device and the real-time temperature of the current room is greater than or equal to 0 ℃ and less than 0.5 ℃, determining that the heating power of the current room is increased by 1%.

In summary, the temperature control system provided in the embodiment of the present invention can save a large amount of energy on the premise of satisfying the heating demand of the residents, and can also achieve better heating experience through different control modes, and achieve fine adjustment of the heating temperature through scene detection (for example, a sleep mode, a dining mode, a work and study mode, and a sport mode), thereby obtaining the best heating experience. In the aspect of use of a user, a mobile phone remote control function is added for the personal user, so that the use convenience is improved; aiming at a power supply system of a community manager or a city, the power supply system provides the capacity of uniformly managing a large amount of equipment, and can effectively assist a power grid to realize peak clipping and valley filling.

As shown in fig. 4 and 5, the embodiment of the invention provides a device where a temperature control device for electric floor heating is located and the temperature control device for electric floor heating. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware aspect, as shown in fig. 4, a hardware structure diagram of a device in which the temperature control device for electric floor heating provided in the embodiment of the present invention is located is shown, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 4, the device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing a packet, in general. Taking a software implementation as an example, as shown in fig. 5, as a logical apparatus, the apparatus is formed by reading a corresponding computer program instruction in a non-volatile memory into a memory by a CPU of a device in which the apparatus is located and running the computer program instruction.

As shown in fig. 5, the temperature control device for electric floor heating provided by this embodiment includes:

the acquiring module 501 is used for acquiring real-time temperature, set temperature and person information of each room in a room, wherein the person information is used for representing whether a person exists in each room and the state of the person in the room with the person;

the first determining module 502 determines, for each room, a target temperature of the current room according to the set temperature and the personal information of the current room.

In this embodiment of the present invention, the obtaining module 501 may be configured to perform step 101 in the foregoing method embodiment, and the first determining module 502 may be configured to perform step 102 in the foregoing method embodiment.

In an embodiment of the present invention, the first determining module 502 is configured to perform the following operations:

determining whether people exist in the current room or not according to the people information of the current room;

if the person exists, determining the set temperature of the current room as the target temperature of the current room;

and if no person exists, determining the difference value between the set temperature of the current room and the first preset temperature as the target temperature of the current room.

In an embodiment of the present invention, the first determining module 502 is configured to, after performing the determining of the set temperature of the current room as the target temperature of the current room, perform the following operations:

determining whether a bed exists in a current room or not according to a preset first neural network model;

if the bed exists, determining whether the contact ratio of the person in the current room and the bed is higher than a first preset value or not according to the first neural network model and determining whether the person in the current room does not move within a first preset time length or not;

and in a first preset time period, if the contact ratio of the person in the current room and the bed is higher than a first preset value and the person in the current room does not move within a first preset time period, determining the difference value between the set temperature of the current room and the second preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

In an embodiment of the present invention, the first determining module 502 is configured to, after performing the determining of the set temperature of the current room as the target temperature of the current room, perform the following operations:

determining whether a dining table exists in a current room or not according to a preset first neural network model;

if the dining table exists, determining whether the contact ratio of the person in the current room and the dining table is higher than a second preset value or not according to the first neural network model and determining whether food exists on the dining table in the current room or not;

and if the coincidence degree of the person in the current room and the dining table is higher than the second preset value and food exists on the dining table in the current room, determining the difference value between the set temperature of the current room and the third preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

In an embodiment of the present invention, the first determining module 502 is configured to, after performing the determining of the set temperature of the current room as the target temperature of the current room, perform the following operations:

determining whether a desk exists in a current room according to a preset first neural network model;

if the desk exists, determining whether the contact ratio of the person in the current room and the desk is higher than a third preset value according to the first neural network model and determining whether the person in the current room does not move within a second preset time period;

and if the contact ratio of the person in the current room and the desk is higher than a third preset value and the person in the current room does not move within a second preset time period, determining the sum of the set temperature of the current room and the fourth preset temperature as the target temperature of the current room, and otherwise, determining the set temperature of the current room as the target temperature of the current room.

In an embodiment of the present invention, the first determining module 502 is configured to, after performing the determining of the set temperature of the current room as the target temperature of the current room, perform the following operations:

determining whether the number of times of limb movement of the person in the current room exceeds a preset number of times within a third preset time period according to a preset second neural network model;

and if the preset times are exceeded, determining the difference value between the set temperature of the current room and the fifth preset temperature as the target temperature of the current room, otherwise, determining the set temperature of the current room as the target temperature of the current room.

In one embodiment of the present invention, further comprising:

and the second determining module is used for responding to the situation that no person exists in each room, and after the fourth preset time period, determining the difference value between the set temperature of each room and the sixth preset temperature as the target temperature of the room.

In one embodiment of the present invention, further comprising:

an execution module, configured to execute, for each room:

and in response to that no person exists in each room except the bedroom and a person exists in each bedroom within the second preset time period, determining the difference value between the set temperature of each room except the bedroom and the seventh preset temperature as the target temperature of the room, and determining the difference value between the set temperature of each bedroom and the eighth preset temperature as the target temperature of the bedroom.

It can be understood that the structure illustrated in the embodiment of the invention does not constitute a specific limitation on the temperature control device of the electric floor heating system. In other embodiments of the present invention, the temperature control device of the electric floor heating may include more or fewer components than those shown, or some components may be combined, some components may be separated, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

Because the content of information interaction, execution process, and the like among the modules in the device is based on the same concept as the method embodiment of the present invention, specific content can be referred to the description in the method embodiment of the present invention, and is not described herein again.

The embodiment of the invention also provides a temperature control device of the electric floor heating, which comprises: at least one memory and at least one processor;

the at least one memory to store a machine readable program;

the at least one processor is used for calling the machine readable program to execute the temperature control method of the electric floor heating system in any embodiment of the invention.

Embodiments of the present invention also provide a computer-readable medium storing instructions for causing a computer to perform a method of temperature control of an electric floor heating as described herein. Specifically, a method or an apparatus equipped with a storage medium on which a software program code that realizes the functions of any of the above-described embodiments is stored may be provided, and a computer (or a CPU or MPU) of the method or the apparatus is caused to read out and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.

Further, it should be clear that the functions of any one of the above-described embodiments can be implemented not only by executing the program code read out by the computer, but also by performing a part or all of the actual operations by an operation method or the like operating on the computer based on instructions of the program code.

Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion unit to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.

The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.