Equipment control method and system based on artificial intelligence

Abstract

The present invention provides an artificial intelligence-based equipment control method and system, the method comprising: determining a temperature threshold range based on outdoor environmental parameters, obtaining an initial indoor temperature, determining an operation mode and initial operation parameters based on the initial indoor temperature and the temperature threshold range; obtaining an identification frame corresponding to a person in an indoor image, obtaining an indoor person influence factor based on the identification frame; determining to adjust the air supply volume based on the indoor person influence factor, and determining the real-time air supply volume; determining a location area of ​​the air conditioner in the indoor image, determining a sweeping strategy through the location area and the identification frame, and generating operation parameters based on the air supply temperature, the real-time air supply volume and the sweeping strategy to control the operation of the air conditioner. Based on the indoor image, the indoor personnel flow situation is grasped in real time, and the indoor flow rate is automatically and intelligently adapted to the change of the indoor flow rate through real-time and adjustable air supply volume. By generating operation parameters in real time, the operation parameters are adaptively adjusted according to the indoor flow rate situation, thereby improving the use perception.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based device control method and system. Background Art

[0002] Electricity plays an important role in our daily life and is one of the important energy sources in daily life. It has brought great convenience to daily life. Electrical equipment corresponding to electricity has also been widely used in daily life.

[0003] Electrical equipment generally refers to appliances that use electricity, mainly referring to some common household electrical appliances that provide convenience for life, such as televisions, air conditioners, refrigerators, etc. Take air conditioners as an example. They are installed indoors and adjust the indoor ambient temperature by controlling the wind speed, wind direction and temperature of the air to provide a more comfortable indoor environment.

[0004] However, the current control of air conditioners is generally done by users manually setting the air conditioner body through a remote control device, but the set control parameters cannot adapt to changes in indoor human flow, that is, manual control methods are difficult to maintain the optimal indoor ambient temperature, affecting the user experience. Summary of the invention

[0005] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an equipment control method and system based on artificial intelligence, aiming to solve the technical problems in the prior art that the operating parameters of the air conditioner are set by manual control, which cannot adapt to changes in indoor human flow and is difficult to maintain the optimal indoor ambient temperature, affecting the user experience.

[0006] In order to achieve the above objectives, in a first aspect, an embodiment of the present application provides an artificial intelligence-based device control method for controlling the operation of an air conditioner, the artificial intelligence-based device control method comprising the following steps:

[0007] Acquire outdoor environmental parameters, determine a temperature threshold range based on the outdoor environmental parameters, acquire an initial indoor temperature, determine an operation mode based on the initial indoor temperature and the temperature threshold range, and determine initial operation parameters through the temperature threshold range, wherein the initial operation parameters include a supply air temperature and an initial supply air volume;

[0008] Acquire an indoor image, perform personnel recognition on the indoor image to obtain identification frames corresponding to the personnel, obtain a total area of ​​a region through the indoor image, obtain an area occupancy factor through an occupation ratio of the identification frames in the indoor image, and determine a personnel load factor based on the number of the identification frames;

[0009] Determine the personnel load and the fresh air load according to the total area of ​​the area, the area occupancy factor and the personnel load factor, obtain the adjusted air supply volume based on the personnel load and the fresh air load at different times, and determine the real-time air supply volume based on the adjusted air supply volume and the initial air supply volume;

[0010] The location area of ​​the air conditioner is determined in the indoor image, the sweeping air strategy is determined through the location area and the identification frame, the operating parameters are generated based on the supply air temperature, the real-time supply air volume and the sweeping air strategy, and the operation of the air conditioner is controlled through the operating parameters.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: the temperature threshold range is determined by the outdoor environmental parameters, the optimal indoor environmental temperature is determined with reference to the external environment, and the optimal temperature of the human body surface at different periods is adapted; by acquiring the indoor image, the indoor personnel flow situation is grasped in real time based on the indoor image, and when the number of indoor personnel changes, the indoor personnel impact factor is acquired in real time and used as a condition for optimizing the air supply volume of the air conditioner, and when the change in the number of indoor personnel affects the indoor environmental temperature, the indoor environmental temperature is timely adjusted back to the temperature threshold range through the change in the air supply volume, that is, the change in indoor human flow is automatically and intelligently adapted through the real-time and adjustable air supply volume, thereby improving the user experience; by acquiring the sweeping air strategy, the area where the personnel are located is avoided to a certain extent during air supply, thereby avoiding discomfort caused by long-term direct blowing on the personnel; the operating parameters are generated in real time based on the air supply temperature, the real-time air supply volume and the sweeping air strategy, and can be adaptively adjusted according to different indoor human flow situations, thereby improving the user's perception of use and the user experience while realizing more intelligent air conditioning control.

[0012] Furthermore, the operating mode includes a standby mode, a cooling mode and a heating mode, and the step of determining the operating mode based on the initial indoor temperature and the temperature threshold range includes:

[0013] comparing the initial indoor temperature with the temperature threshold range;

[0014] If the initial indoor temperature is lower than the temperature threshold range, it is determined to enter the heating mode; if the initial indoor temperature is higher than the temperature threshold range, it is determined to enter the cooling mode; if the initial indoor temperature is within the temperature threshold range, it is determined to enter the standby mode.

[0015] Furthermore, the step of performing person recognition on the indoor image to obtain an identification frame corresponding to the person includes:

[0016] Adjusting the indoor image to a preset size to obtain an input image;

[0017] Inputting the input image as an input value into a feature extraction network model to obtain a heat map;

[0018] A thermal center point is determined in the thermal map, and the size of the thermal center point is restored to form an identification frame corresponding to the person.

[0019] Furthermore, the calculation formula of the personnel load is:

[0020] ,

[0021] in, represents the personnel load at time t, represents the clustering coefficient, represents the total area of ​​the region, represents the area occupancy factor at time t, represents the personnel load factor at time t;

[0022] The calculation formula of the fresh air load is:

[0023] ,

[0024] in, represents the fresh air load at time t, Indicates the minimum fresh air volume, represents the outdoor air enthalpy, Indicates the indoor air enthalpy;

[0025] The calculation formula for adjusting the air supply volume is:

[0026] ,

[0027] in, represents the regulated air supply volume at time t, represents the personnel load at time t-1, represents the fresh air load at time t-1, Indicates the air enthalpy at the air outlet. Indicates the air density.

[0028] Furthermore, the step of determining the wind sweeping strategy through the location area and the identification frame includes:

[0029] Determine a wind sweeping area in the indoor image through a mapping relationship between the air conditioner and the location area;

[0030] The wind sweeping area is divided into a direct wind sweeping area and an avoidance area based on the identification frame, and a first wind sweeping speed and a second wind sweeping speed are respectively allocated to the direct wind sweeping area and the avoidance area, wherein the first wind sweeping speed is less than the second wind sweeping speed;

[0031] A wind sweep strategy is generated based on the direct sweep area, the avoidance area, the first wind sweep speed, and the second wind sweep speed.

[0032] Furthermore, after the steps of determining the location area of ​​the air conditioner in the indoor image, determining the air sweeping strategy by the location area and the identification frame, generating operating parameters based on the supply air temperature, the real-time supply air volume and the air sweeping strategy, and controlling the operation of the air conditioner by the operating parameters, the method further includes:

[0033] Whether to enter the shutdown mode is determined based on the number of the identification frames in the indoor image in different frames.

[0034] In a second aspect, an embodiment of the present application provides an artificial intelligence-based device control system, which is applied to the artificial intelligence-based device control method as described in the first aspect above, and the system includes:

[0035] A first acquisition module is used to acquire outdoor environmental parameters, determine a temperature threshold range based on the outdoor environmental parameters, acquire an initial indoor temperature, determine an operation mode based on the initial indoor temperature and the temperature threshold range, and determine initial operation parameters through the temperature threshold range, wherein the initial operation parameters include a supply air temperature and an initial supply air volume;

[0036] A second acquisition module is used to acquire an indoor image, perform personnel recognition on the indoor image to acquire identification frames corresponding to the personnel, acquire a total area of ​​a region through the indoor image, acquire an area occupancy factor through an occupation ratio of the identification frames in the indoor image, and determine a personnel load factor based on the number of the identification frames;

[0037] an adjustment module, configured to determine a personnel load and a fresh air load according to the total area of ​​the area, the area occupancy factor and the personnel load factor, obtain an adjusted air supply volume based on the personnel load and the fresh air load at different times, and determine a real-time air supply volume based on the adjusted air supply volume and the initial air supply volume;

[0038] An execution module is used to determine the location area of ​​the air conditioner in the indoor image, determine the air sweeping strategy through the location area and the identification box, generate operating parameters based on the supply air temperature, real-time supply air volume and the air sweeping strategy, and control the operation of the air conditioner through the operating parameters.

[0039] In a third aspect, an embodiment of the present application provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the artificial intelligence-based device control method as described in the first aspect above is implemented.

[0040] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the artificial intelligence-based device control method as described in the first aspect above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of a device control method based on artificial intelligence in a first embodiment of the present invention;

[0042] Figure 2 It is a structural block diagram of an equipment control system based on artificial intelligence in the second embodiment of the present invention;

[0043] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0044] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0045] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0047] See also Figure 1 The first embodiment of the present invention provides an artificial intelligence-based device control method for controlling the operation of an air conditioner. The artificial intelligence-based device control method includes the following steps:

[0048] S10: Acquire outdoor environmental parameters, determine a temperature threshold range based on the outdoor environmental parameters, acquire an initial indoor temperature, determine an operation mode based on the initial indoor temperature and the temperature threshold range, and determine initial operation parameters through the temperature threshold range, wherein the initial operation parameters include a supply air temperature and an initial supply air volume;

[0049] The outdoor environmental parameters include outdoor temperature and seasonal parameters. In this embodiment, the outdoor environmental parameters can be retrieved and obtained by connecting to the cloud. The step of determining the temperature threshold range based on the outdoor environmental parameters is specifically as follows: determining the initial threshold range by the seasonal parameters, such as in winter, the initial threshold range is 18°C~25°C, and narrowing the initial threshold range by the outdoor temperature to obtain the temperature threshold range. For example, when the outdoor temperature is below zero, the initial threshold range is narrowed to 18°C~20°C to form the temperature threshold range.

[0050] In this embodiment, the initial indoor temperature is obtained by setting a temperature sensor indoors. After obtaining the temperature threshold range, the temperature threshold range can be determined as the optimal indoor ambient temperature, and then the supply air temperature is obtained by the temperature difference between the air outlet of the air conditioner and the room, and the initial supply air volume is generated accordingly.

[0051] The step S10 comprises:

[0052] S110: Compare the initial indoor temperature with the temperature threshold range;

[0053] S120: If the initial indoor temperature is lower than the temperature threshold range, it is determined to enter the heating mode; if the initial indoor temperature is higher than the temperature threshold range, it is determined to enter the cooling mode; if the initial indoor temperature is within the temperature threshold range, it is determined to enter the standby mode.

[0054] It should be noted that the operation mode and the initial operation parameters are determined only when the air conditioner is started.

[0055] S20: Acquire an indoor image, perform personnel recognition on the indoor image to obtain identification frames corresponding to the personnel, obtain a total area of ​​a region through the indoor image, obtain an area occupancy factor through an occupation ratio of the identification frames in the indoor image, and determine a personnel load factor based on the number of the identification frames;

[0056] In this embodiment, the indoor image is obtained by a camera installed indoors. It can be understood that during the operation of the air conditioner, the indoor image is continuously obtained in several consecutive frames to facilitate real-time grasp of changes in indoor human flow, and then real-time adjustment of the indoor ambient temperature.

[0057] The step S20 comprises:

[0058] S210: Adjusting the indoor image to a preset size to obtain an input image;

[0059] Preferably, the preset size is 512*512*3.

[0060] S220: Inputting the input image as an input value into a feature extraction network model to obtain a heat map;

[0061] Preferably, the feature extraction network model is a CenterNet network model, which outputs the heat map by downsampling and upsampling the input image several times and combining the features in the downsampling process with the features in the upsampling process.

[0062] S230: Determine a thermal center point in the thermal map, and restore the size of the thermal center point to form an identification frame corresponding to the person:

[0063] The thermal map includes several thermal areas. The thermal center point is formed by obtaining the center point of the thermal area. After obtaining the thermal center point, the thermal center point is used as a reference and expanded into the identification frame by a preset length dimension and a preset width dimension. By first determining the thermal center point and forming the identification frame by the thermal center point, the inaccurate identification of the number of people and their locations caused by partial overlap of indoor people can be avoided, and the change of indoor human flow can be accurately grasped.

[0064] The area occupancy factor refers to the number of people per square meter at the current moment. The personnel load factor refers to the sum of the sensible heat and latent heat of indoor people under light activity conditions. It can be understood that the indoor personnel influencing factor includes the area occupancy factor and the personnel load factor.

[0065] S30: determining the personnel load and the fresh air load according to the total area of ​​the area, the area occupancy factor and the personnel load factor, obtaining the adjusted air supply volume based on the personnel load and the fresh air load at different times, and determining the real-time air supply volume based on the adjusted air supply volume and the initial air supply volume;

[0066] The calculation formula for the personnel load is:

[0067] ,

[0068] in, represents the personnel load at time t, represents the clustering coefficient, represents the total area of ​​the region, represents the area occupancy factor at time t, represents the personnel load factor at time t;

[0069] The calculation formula of the fresh air load is:

[0070] ,

[0071] in, represents the fresh air load at time t, Indicates the minimum fresh air volume, represents the outdoor air enthalpy, Indicates the indoor air enthalpy.

[0072] In an indoor environment, the heat emitted by the human body will be dissipated into the indoor environment through heat convection, heat radiation, etc., and then affect the indoor ambient temperature. As the number of people increases, the influence becomes greater. The role of fresh air is to improve indoor air quality and enhance the comfort of indoor people. Similarly, as the number of people increases, more fresh air will be needed to achieve the above purposes. Therefore, as the indoor flow of people changes, its impact on the indoor ambient temperature and the demand for fresh air are also constantly changing. By concretizing it as the personnel load and the fresh air load as the adjustment indicators of the air supply volume of the air conditioner, the operation of the air conditioner can be fully adapted to the changes in the indoor flow of people.

[0073] The calculation formula for adjusting the air supply volume is:

[0074] ,

[0075] in, represents the regulated air supply volume at time t, represents the personnel load at time t-1, represents the fresh air load at time t-1, Indicates the air enthalpy at the air outlet. It can be understood that the real-time air supply volume is the sum of the initial air supply volume and the adjusted air supply volume.

[0076] S40: determining a location area of ​​the air conditioner in the indoor image, determining an air sweeping strategy according to the location area and the identification frame, generating operating parameters based on the air supply temperature, the real-time air supply volume and the air sweeping strategy, and controlling the operation of the air conditioner according to the operating parameters;

[0077] The step S40 comprises:

[0078] S410: determining a wind sweeping area in the indoor image according to a mapping relationship between the air conditioner and the location area;

[0079] During the air outlet process of the air conditioner, in order to perform faster and more balanced temperature regulation, it is necessary to adjust the air outlet direction to cover the indoor space by sweeping the air. It can be understood that the angle area formed by the air conditioner and the air outlet direction of the air conditioner is determined as the sweeping area.

[0080] S420: dividing the wind sweeping area into a direct sweeping area and an avoidance area based on the identification frame, and assigning a first wind sweeping speed and a second wind sweeping speed to the direct sweeping area and the avoidance area, respectively, wherein the first wind sweeping speed is less than the second wind sweeping speed;

[0081] Determine whether the identification frame exists in the wind sweeping area. If the identification frame does not exist in the wind sweeping area, generate the wind sweeping strategy with the initial wind sweeping speed. For example, if the wind sweeping area is 120 degrees, the wind is swept at the initial wind sweeping speed of 1 degree / second, and the air supply time for completing one wind sweeping area is 120 seconds. It can be understood that the control of the wind sweeping speed is essentially to control the speed of rotation of the fan blades of the air conditioner.

[0082] If the identification frame exists in the wind sweeping area, it is determined that there are people in the wind sweeping area. Through the relative position relationship between the identification frame and the position area, the fan-shaped wind sweeping area can be divided into a number of sub-sectors, and the sub-sectors are the direct sweeping area or the avoidance area. It can be understood that the identification frame does not exist in the direct sweeping area, and the identification frame exists in the avoidance area. Taking the above explanation as an example, in the direct sweeping area, the first wind sweeping speed is 1 degree / second, and in the avoidance area, the second wind sweeping speed is 2 degrees / second, that is, if the direct sweeping area and the avoidance area are both 10 degrees, the time to complete the air supply in the direct sweeping area is 10 seconds, and the time to complete the air supply in the avoidance area is 5 seconds.

[0083] S430: generating a wind sweeping strategy based on the direct sweeping area, the avoidance area, the first wind sweeping speed, and the second wind sweeping speed;

[0084] The temperature threshold range is determined by the outdoor environmental parameters, and the optimal indoor environmental temperature is determined with reference to the external environment, so as to adapt to the optimal temperature of the human body surface at different periods; by acquiring the indoor image, the indoor personnel flow situation is grasped in real time based on the indoor image, and when the number of indoor personnel changes, the indoor personnel impact factor is acquired in real time and used as a condition for optimizing the air supply volume of the air conditioner. When the change in the number of indoor personnel affects the indoor environmental temperature, the indoor environmental temperature is adjusted back to the temperature threshold range in time through the change in the air supply volume, that is, the change in indoor human flow is automatically and intelligently adapted through the real-time and adjustable air supply volume, thereby improving the user experience; by acquiring the sweeping air strategy, the area where the personnel are located is avoided to a certain extent when supplying air, so as to avoid discomfort caused by long-term direct blowing on the personnel; the operating parameters are generated in real time based on the air supply temperature, the real-time air supply volume and the sweeping air strategy, and can be adaptively adjusted according to different indoor human flow situations, thereby improving the user perception and user experience while realizing more intelligent air conditioning control.

[0085] Preferably, the artificial intelligence-based device control method further includes:

[0086] S50: judging whether to enter a shutdown mode based on the number of identification frames in the indoor image in different frames;

[0087] Specifically, the number of the identification frames in the indoor images under different frames is counted. When the identification frame does not exist in the indoor image under a certain frame, the indoor environment is judged to be in an unmanned state, and the indoor image of the frame is determined as the starting image. It is judged whether there is an identification frame in the indoor images within a preset frame number range after the starting image. If the identification frame does not exist in any of the indoor images within the preset frame number range, the indoor environment is judged to be in an unmanned state, and the shutdown mode is entered.

[0088] By continuously acquiring the identification frame in the indoor image, it is possible to automatically determine whether there are people in the room. When there is no one in the room, the machine can be shut down to avoid energy waste caused by not executing the shutdown operation, thereby reducing energy consumption. By continuously determining within the preset frame number range, it is possible to avoid shutdown in a short period of time when there is no one, resulting in energy waste caused by subsequent repeated restarts, thereby effectively improving the level of intelligent control.

[0089] See also Figure 2The second embodiment of the present invention provides an artificial intelligence-based equipment control system, which is applied to the artificial intelligence-based equipment control method described in the above embodiment, and will not be repeated here. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0090] The system comprises:

[0091] A first acquisition module 10 is used to acquire outdoor environmental parameters, determine a temperature threshold range based on the outdoor environmental parameters, acquire an initial indoor temperature, determine an operation mode based on the initial indoor temperature and the temperature threshold range, and determine initial operation parameters through the temperature threshold range, wherein the initial operation parameters include a supply air temperature and an initial supply air volume;

[0092] The first acquisition module 10 includes:

[0093] A first unit is used to compare the initial indoor temperature with the temperature threshold range;

[0094] The second unit is used to determine whether to enter the heating mode if the initial indoor temperature is lower than the temperature threshold range; determine whether to enter the cooling mode if the initial indoor temperature is higher than the temperature threshold range; and determine whether to enter the standby mode if the initial indoor temperature is within the temperature threshold range;

[0095] The second acquisition module 20 is used to acquire an indoor image, perform personnel recognition on the indoor image to acquire identification frames corresponding to the personnel, acquire the total area of ​​the region through the indoor image, acquire the area occupancy factor through the occupancy ratio of the identification frames in the indoor image, and determine the personnel load factor based on the number of the identification frames;

[0096] The second acquisition module 20 includes:

[0097] A third unit is used to adjust the indoor image to a preset size to obtain an input image;

[0098] A fourth unit is used for inputting the input image as an input value into a feature extraction network model to obtain a heat map;

[0099] The fifth unit is used to determine a thermal center point in the thermal map, and restore the size of the thermal center point to form an identification frame corresponding to the person;

[0100] The adjustment module 30 is used to determine the personnel load and the fresh air load according to the total area of ​​the area, the area occupancy factor and the personnel load factor, obtain the adjusted air supply volume based on the personnel load and the fresh air load at different times, and determine the real-time air supply volume based on the adjusted air supply volume and the initial air supply volume;

[0101] an execution module 40, configured to determine a location area of ​​the air conditioner in the indoor image, determine a sweeping air strategy according to the location area and the identification frame, generate operating parameters based on the supply air temperature, the real-time supply air volume and the sweeping air strategy, and control the operation of the air conditioner according to the operating parameters;

[0102] The execution module 40 includes:

[0103] A sixth unit, configured to determine a wind sweeping area in the indoor image according to a mapping relationship between the air conditioner and the location area;

[0104] A seventh unit is used to separate the wind sweeping area into a direct wind sweeping area and an avoidance area based on the identification frame, and allocate a first wind sweeping speed and a second wind sweeping speed to the direct wind sweeping area and the avoidance area respectively, wherein the first wind sweeping speed is less than the second wind sweeping speed;

[0105] An eighth unit is used to generate a wind sweeping strategy based on the direct sweeping area, the avoidance area, the first wind sweeping speed, and the second wind sweeping speed.

[0106] Preferably, the system further comprises:

[0107] The control module 50 is used to determine whether to enter the shutdown mode based on the number of the identification frames in the indoor image in different frames.

[0108] The present invention also provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the artificial intelligence-based device control method as described in the above technical solution is implemented.

[0109] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the device control method based on artificial intelligence as described in the above technical solution is implemented.

[0110] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0111] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An artificial intelligence-based device control method for controlling the operation of an air conditioner, It is characterized in that The device control method based on artificial intelligence comprises the following steps: Acquire outdoor environmental parameters, determine a temperature threshold range based on the outdoor environmental parameters, acquire an initial indoor temperature, determine an operation mode based on the initial indoor temperature and the temperature threshold range, and determine initial operation parameters through the temperature threshold range, wherein the initial operation parameters include a supply air temperature and an initial supply air volume; Acquire an indoor image, perform personnel recognition on the indoor image to obtain identification frames corresponding to the personnel, obtain a total area of ​​a region through the indoor image, and obtain an area occupancy factor through an occupation ratio of the identification frames in the indoor image, and determine a personnel load factor based on the number of the identification frames, wherein the area occupancy factor refers to the number of personnel per square meter at a current moment, and the personnel load factor refers to the sum of the sensible heat and latent heat of the indoor personnel; The step of performing person recognition on the indoor image to obtain an identification frame corresponding to the person comprises: Adjusting the indoor image to a preset size to obtain an input image; Inputting the input image as an input value into a feature extraction network model to obtain a heat map; Determine a thermal center point in the thermal map, and restore the size of the thermal center point to form an identification frame corresponding to the person; Determine the personnel load and the fresh air load according to the total area of ​​the area, the area occupancy factor and the personnel load factor, obtain the adjusted air supply volume based on the personnel load and the fresh air load at different times, and determine the real-time air supply volume based on the adjusted air supply volume and the initial air supply volume; The calculation formula for the personnel load is: ， in, represents the personnel load at time t, represents the clustering coefficient, represents the total area of ​​the region, represents the area occupancy factor at time t, represents the personnel load factor at time t; The calculation formula of the fresh air load is: ， in, represents the fresh air load at time t, Indicates the minimum fresh air volume, represents the outdoor air enthalpy, Indicates the indoor air enthalpy; The calculation formula for adjusting the air supply volume is: ， in, represents the regulated air supply volume at time t, represents the personnel load at time t-1, represents the fresh air load at time t-1, Indicates the air enthalpy at the air outlet. Indicates the air density; Determine a location area of ​​the air conditioner in the indoor image, determine an air sweeping strategy according to the location area and the identification frame, generate operating parameters based on the air supply temperature, the real-time air supply volume and the air sweeping strategy, and control the operation of the air conditioner according to the operating parameters; The step of determining the wind sweeping strategy through the location area and the identification frame includes: Determine a wind sweeping area in the indoor image through a mapping relationship between the air conditioner and the location area; The wind sweeping area is divided into a direct wind sweeping area and an avoidance area based on the identification frame, and a first wind sweeping speed and a second wind sweeping speed are respectively allocated to the direct wind sweeping area and the avoidance area, wherein the first wind sweeping speed is less than the second wind sweeping speed; A wind sweep strategy is generated based on the direct sweep area, the avoidance area, the first wind sweep speed, and the second wind sweep speed.

2. The device control method based on artificial intelligence according to claim 1, It is characterized in that The operation mode includes a standby mode, a cooling mode, and a heating mode, and the step of determining the operation mode based on the initial indoor temperature and the temperature threshold range includes: comparing the initial indoor temperature with the temperature threshold range; If the initial indoor temperature is lower than the temperature threshold range, it is determined to enter the heating mode; if the initial indoor temperature is higher than the temperature threshold range, it is determined to enter the cooling mode; if the initial indoor temperature is within the temperature threshold range, it is determined to enter the standby mode.

3. The device control method based on artificial intelligence according to claim 1, It is characterized in that After the steps of determining the location area of ​​the air conditioner in the indoor image, determining the air sweeping strategy by the location area and the identification frame, generating operating parameters based on the air supply temperature, the real-time air supply volume and the air sweeping strategy, and controlling the operation of the air conditioner by the operating parameters, the method further includes: Whether to enter the shutdown mode is determined based on the number of the identification frames in the indoor image in different frames.

4. An artificial intelligence-based equipment control system, applied to the artificial intelligence-based equipment control method according to any one of claims 1 to 3, It is characterized in that The system comprises: A first acquisition module is used to acquire outdoor environmental parameters, determine a temperature threshold range based on the outdoor environmental parameters, acquire an initial indoor temperature, determine an operation mode based on the initial indoor temperature and the temperature threshold range, and determine initial operation parameters through the temperature threshold range, wherein the initial operation parameters include a supply air temperature and an initial supply air volume; A second acquisition module is used to acquire an indoor image, perform personnel recognition on the indoor image to acquire an identification frame corresponding to the personnel, acquire a total area of ​​a region through the indoor image, and acquire an area occupancy factor through an occupation ratio of the identification frame in the indoor image, and determine a personnel load factor based on the number of the identification frames, wherein the area occupancy factor refers to the number of personnel per square meter at the current moment, and the personnel load factor refers to the sum of the sensible heat and latent heat of the indoor personnel; The second acquisition module includes: A third unit is used to adjust the indoor image to a preset size to obtain an input image; A fourth unit is used to input the input image as an input value into a feature extraction network model to obtain a heat map; The fifth unit is used to determine a thermal center point in the thermal map, and restore the size of the thermal center point to form an identification frame corresponding to the person; an adjustment module, configured to determine a personnel load and a fresh air load according to the total area of ​​the area, the area occupancy factor and the personnel load factor, obtain an adjusted air supply volume based on the personnel load and the fresh air load at different times, and determine a real-time air supply volume based on the adjusted air supply volume and the initial air supply volume; The calculation formula for the personnel load is: ， in, represents the personnel load at time t, represents the clustering coefficient, represents the total area of ​​the region, represents the area occupancy factor at time t, represents the personnel load factor at time t; The calculation formula of the fresh air load is: ， in, represents the fresh air load at time t, Indicates the minimum fresh air volume, represents the outdoor air enthalpy, Indicates the indoor air enthalpy; The calculation formula for adjusting the air supply volume is: ， in, represents the regulated air supply volume at time t, represents the personnel load at time t-1, represents the fresh air load at time t-1, Indicates the air enthalpy at the air outlet. Indicates the air density; an execution module, configured to determine a location area of ​​the air conditioner in the indoor image, determine an air sweeping strategy through the location area and the identification frame, generate operating parameters based on the air supply temperature, the real-time air supply volume and the air sweeping strategy, and control the operation of the air conditioner through the operating parameters; The execution module includes: A sixth unit, configured to determine a wind sweeping area in the indoor image according to a mapping relationship between the air conditioner and the location area; A seventh unit is used to separate the wind sweeping area into a direct wind sweeping area and an avoidance area based on the identification frame, and allocate a first wind sweeping speed and a second wind sweeping speed to the direct wind sweeping area and the avoidance area respectively, wherein the first wind sweeping speed is less than the second wind sweeping speed; An eighth unit is used to generate a wind sweeping strategy based on the direct sweeping area, the avoidance area, the first wind sweeping speed, and the second wind sweeping speed.

5. A computer comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the artificial intelligence-based device control method according to any one of claims 1 to 3 is implemented.

Images