Air conditioning method, device and computer-readable storage medium based on the Internet of Things

Abstract

The embodiment of the present application discloses an air conditioning method, device and computer-readable storage medium based on the Internet of Things, which obtains the facial image of the object to be identified in the target area and the limb image corresponding to the facial image; performs expression recognition on the facial image to obtain the facial expression information of the object to be identified, and performs posture recognition on the limb image to obtain the behavior posture information of the object to be identified; identifies the behavior state of the object to be identified based on the facial expression information and the behavior posture information; obtains the location information of the object to be identified when the behavior state is the target behavior state, and determines the target air conditioner from the candidate air conditioners based on the location information; and performs air conditioning processing on the target area based on the target air conditioner. In this way, the target air conditioner is determined by identifying the behavior state and location information of the object to be identified, and accurate air conditioning processing is performed through the target air conditioner, thereby improving the control efficiency of the air conditioning equipment and thus improving the efficiency of air conditioning.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an air conditioning method, device and computer-readable storage medium based on the Internet of Things. Background Art

[0002] With the development of communication technology, various smart devices have appeared in people's lives, such as air conditioning equipment, which can meet users' needs for the current air environment through air conditioning functions in terms of temperature, humidity and ventilation. In actual usage scenarios, multiple air conditioning equipment are often configured in a public area with multiple people to meet the different air conditioning needs of users in different areas.

[0003] However, in public areas where many people dine, such as office areas during lunch breaks and dining areas in restaurants, there will be a strong odor in the public areas when many people dine, and the switch distribution of air-conditioning equipment in public areas is relatively complex. Diners often cannot find the corresponding air conditioner in a timely and accurate manner to perform air conditioning in the public areas, resulting in a strong odor in the public areas. Therefore, the control efficiency of the air-conditioning equipment is poor, which in turn makes the air conditioning efficiency low, resulting in a poor user experience. Summary of the invention

[0004] The embodiments of the present application provide an air conditioning method, device and computer-readable storage medium based on the Internet of Things, which can improve the control efficiency of air-conditioning equipment, thereby improving the efficiency of air conditioning, thereby improving the user experience.

[0005] The present application provides an air conditioning method based on the Internet of Things, including:

[0006] Acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image;

[0007] Performing expression recognition on the facial image to obtain facial expression information of the object to be identified, and performing posture recognition on the limb image to obtain behavior posture information of the object to be identified;

[0008] Based on the facial expression information and the behavioral posture information, identifying the behavioral state of the object to be identified;

[0009] When the behavior state of the object to be identified is a target behavior state, obtaining position information of the object to be identified, and determining a target air conditioner from candidate air conditioners according to the position information;

[0010] Based on the target air conditioning, air conditioning processing is performed on the target area.

[0011] Accordingly, the embodiment of the present application provides an air conditioning device based on the Internet of Things, including:

[0012] An image acquisition unit, used to acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image;

[0013] A feature extraction unit, used to perform expression recognition on the facial image to obtain facial expression information of the object to be identified, and perform posture recognition on the limb image to obtain behavior posture information of the object to be identified;

[0014] A state recognition unit, used to recognize the behavior state of the object to be recognized based on the facial expression information and the behavior posture information;

[0015] an air conditioner determination unit, configured to obtain position information of the object to be identified when the behavior state of the object to be identified is a target behavior state, and determine a target air conditioner from among candidate air conditioners based on the position information;

[0016] An air conditioning unit is used to perform air conditioning processing on the target area based on the target air conditioner.

[0017] In one embodiment, the image acquisition unit includes:

[0018] A time acquisition subunit, used to acquire the current time and detect the current time based on a preset behavior recognition time interval;

[0019] An image acquisition subunit, configured to acquire an object image of an object to be identified in a target area when detecting that the current time is within the preset behavior recognition time interval;

[0020] The image segmentation subunit is used to segment the object image to obtain the face image of the object to be identified and the limb image corresponding to the face image.

[0021] In one embodiment, the feature extraction unit includes:

[0022] A facial key point recognition subunit, used to recognize at least one facial key point corresponding to the object to be recognized in the facial image;

[0023] A facial feature extraction subunit, configured to extract facial image features corresponding to the object to be identified from the facial image according to the facial key points;

[0024] The facial expression information recognition subunit is used to recognize the facial expression information of the object to be recognized from the candidate expression information based on the facial image features.

[0025] In one embodiment, the feature extraction unit includes:

[0026] A limb key point recognition subunit, used to recognize at least one limb key point corresponding to the object to be recognized in the limb image;

[0027] A posture feature extraction subunit, used for extracting the posture features corresponding to the object to be identified in the limb image based on the limb key points and the time information corresponding to the limb image;

[0028] The behavior posture information recognition subunit is used to recognize the behavior posture information of the object to be recognized in the candidate posture information based on the posture feature.

[0029] In one embodiment, the state recognition unit includes:

[0030] A time information acquisition subunit, used to respectively acquire the time information corresponding to the facial expression information and the behavior posture information;

[0031] A matching subunit, configured to match the facial expression information and the behavior posture information based on the time information to obtain an expression posture information group, wherein the label posture information group includes at least one facial expression information and at least one behavior posture information;

[0032] The state recognition subunit is used to recognize the behavior state of the object to be recognized in the candidate behavior states according to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group.

[0033] In one embodiment, the air conditioning determination unit includes:

[0034] A quantity counting subunit is used for counting the number of target objects to be identified whose behavior state is a target behavior state among the objects to be identified based on the behavior state of the objects to be identified, so as to obtain the number of objects in the target state;

[0035] A comparison subunit, used to compare the number of objects in the target state with a preset object number threshold;

[0036] The position information acquisition subunit is used to acquire the position information of the target object to be identified when the number of objects in the target state is greater than the preset object number threshold.

[0037] In one embodiment, the air conditioning unit comprises:

[0038] A working state detection subunit, used for detecting the working state of the target air conditioner;

[0039] a mode adjustment subunit, configured to turn on the target air conditioner and adjust the working mode of the target air conditioner to a target working mode when the working state is the off state;

[0040] The air conditioning subunit is used to perform air conditioning processing on the target area based on the target working mode.

[0041] In addition, an embodiment of the present application also provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the steps in any one of the Internet of Things-based air conditioning methods provided in the embodiments of the present application.

[0042] In addition, an embodiment of the present application also provides a computer device, including a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to implement the air conditioning method based on the Internet of Things provided in an embodiment of the present application.

[0043] The embodiment of the present application also provides a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the air conditioning method based on the Internet of Things provided in the embodiment of the present application.

[0044] The embodiment of the present application obtains the facial image of the object to be identified in the target area and the limb image corresponding to the facial image; performs expression recognition on the facial image to obtain the facial expression information of the object to be identified, and performs posture recognition on the limb image to obtain the behavior posture information of the object to be identified; identifies the behavior state of the object to be identified based on the facial expression information and the behavior posture information; obtains the position information of the object to be identified when the behavior state of the object to be identified is the target behavior state, and determines the target air conditioner in the candidate air conditioners according to the position information; performs air conditioning processing on the target area based on the target air conditioner. In this way, the behavior state of the object to be identified is identified by obtaining the facial image and limb image of the object to be identified, and when the behavior state of the object to be identified is the target behavior state, the target air conditioner is determined in the candidate air conditioners according to the position information of the object to be identified, so that the target area is accurately air-conditioned by the target air conditioner, thereby improving the control efficiency of the air-conditioning equipment, further improving the efficiency of air conditioning, and thus improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 This is a schematic diagram of an implementation scenario of an air conditioning method based on the Internet of Things provided in an embodiment of the present application;

[0047] Figure 2 It is a flow chart of an air conditioning method based on the Internet of Things provided in an embodiment of the present application;

[0048] Figure 3 is another flow chart of an air conditioning method based on the Internet of Things provided in an embodiment of the present application;

[0049] Figure 4 It is a structural schematic diagram of an air conditioning device based on the Internet of Things provided in an embodiment of the present application;

[0050] Figure 5 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0052] The embodiments of the present application provide an air conditioning method, device and computer-readable storage medium based on the Internet of Things. The air conditioning device based on the Internet of Things can be integrated in a computer device, which can be a server or a terminal.

[0053] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a smart air conditioner, smart TV, tablet computer, laptop computer, desktop computer, smart speaker, smart phone and other devices that support IoT connection, but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0054] See also Figure 1 , taking the integration of air conditioning devices based on the Internet of Things into terminals as an example, Figure 1 The present invention provides a schematic diagram of an implementation scenario of an air conditioning method based on the Internet of Things provided in an embodiment of the present application, wherein the terminal may be a smart air conditioner, a smart TV, a smart phone, a tablet computer, a laptop computer, a desktop computer, or any other computer device that can perform parameter settings, but is not limited thereto. The terminal may obtain a facial image of an object to be identified in a target area and a limb image corresponding to the facial image; perform expression recognition on the facial image to obtain facial expression information of the object to be identified, and perform posture recognition on the limb image to obtain behavioral posture information of the object to be identified; identify the behavioral state of the object to be identified based on the facial expression information and behavioral posture information; when the behavioral state of the object to be identified is the target behavioral state, obtain the location information of the object to be identified, and determine the target air conditioner from the candidate air conditioners based on the location information; and perform air conditioning processing on the target area based on the target air conditioner.

[0055] It should be noted that Figure 1 The schematic diagram of the implementation environment scenario of the air conditioning method based on the Internet of Things is only an example. The implementation environment scenario of the air conditioning method based on the Internet of Things described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. It is known to those skilled in the art that with the evolution of air conditioning based on the Internet of Things and the emergence of new business scenarios, the technical solution provided by this application is also applicable to similar technical problems.

[0056] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0057] This embodiment will be described from the perspective of an air conditioning device based on the Internet of Things. The air conditioning device based on the Internet of Things can be specifically integrated into a computer device, and the computer device can be a terminal. This application does not limit this.

[0058] See also Figure 2 , Figure 2 1 is a flow chart of an air conditioning method based on the Internet of Things provided in an embodiment of the present application. The air conditioning method based on the Internet of Things includes:

[0059] In step 101, a facial image of an object to be identified in a target area and a limb image corresponding to the facial image are obtained.

[0060] The target area may be an area that is air-conditioned, for example, an office area, a cafeteria, or other areas that require air conditioning, and the object to be identified may be an object in the target area, for example, a person in the target area, for example, an office worker, etc. The facial image may be an image including the facial area of ​​the object to be identified, and the limb image may be an image including the limbs of the object to be identified, for example, an image including limbs such as arms and head. It should be noted that the acquired facial image of the object to be identified may correspond to the limb image, for example, an image collected at the same time or in the same time period, that is, the facial image and the limb image corresponding to the facial image may be images generated by the object to be identified at the same time.

[0061] There are many ways to obtain the facial image of the object to be identified in the target area and the limb image corresponding to the facial image. For example, a time interval can be pre-set, and when the current time is in the time interval, the facial image of the object to be identified in the target area and the limb image corresponding to the facial image can be collected. Optionally, the time interval can be a meal time period. During the meal time period, the air in the target area has a strong smell, so air conditioning is required in time to effectively ventilate and replace air in the target area. For example, the time interval can be set to 8:00-9:30, 11:00-13:00, 17:00-19:00 and other meal time periods. The specific time interval can be set according to actual conditions and is not limited here.

[0062] In step 102, expression recognition is performed on the facial image to obtain facial expression information of the object to be identified, and posture recognition is performed on the body image to obtain behavior posture information of the object to be identified.

[0063] The facial expression information may be information extracted from the facial image including facial expressions of the object to be identified, for example, it may include expressions such as blowing air from the mouth (spicy, hot), opening the mouth (eating), chewing, swallowing, emotions (satisfied by delicious food, depressed by unpalatable food), etc. The behavior posture information may be information extracted from the body image including the behavior posture of the object to be identified, for example, it may include behavior postures such as lowering the head, raising the arm to take chopsticks, holding (holding) the bowl, wiping the mouth, lowering the head with the arm moving from the table to the mouth, moving the arm from the mouth area to the table and putting it down, raising the head, etc.

[0064] There are many ways to perform expression recognition on a facial image and obtain facial expression information of an object to be recognized. For example, at least one facial key point corresponding to the object to be recognized can be recognized in the facial image, and facial image features corresponding to the object to be recognized can be extracted from the facial image based on the facial key points. Based on the facial image features, the facial expression information of the object to be recognized can be recognized from candidate expression information.

[0065] The facial key points may be key points in the facial region of the object to be identified in the facial image, for example, the mouth, nose, eyes, eyebrows and other key points, and the facial image features may be information representing the facial expressions of the object to be identified extracted from the facial image based on the facial key points. The candidate expression information may be some pre-set expression information to be selected, for example, expression information such as blowing through the mouth (spicy, hot), opening the mouth, chewing, swallowing, expressions indicating deliciousness, expressions indicating unpalatableness and other types of expression information.

[0066] Among them, based on the facial image features, there can be multiple ways to identify the facial expression information of the object to be identified in the candidate expression information. For example, the expression features corresponding to the candidate expression information can be extracted, and the feature similarity between the expression features and the facial image features of the object to be identified can be calculated. According to the feature similarity, the expression features that best match the facial image features of the object to be identified can be screened out from the expression features corresponding to the candidate expression information, so that the candidate expression information corresponding to the best matching expression features can be determined as the facial expression information of the object to be identified.

[0067] The expression feature may be a feature that represents candidate expression information, and the feature similarity may be information that represents the degree of similarity between the expression feature and the facial image feature.

[0068] There are many ways to perform posture recognition on a limb image and obtain the behavioral posture information of the object to be identified. For example, at least one limb key point corresponding to the object to be identified can be identified in the limb image, and based on the limb key point and the time information corresponding to the limb image, the posture feature corresponding to the object to be identified is extracted from the limb image, and based on the posture feature, the behavioral posture information of the object to be identified is identified in the candidate posture information.

[0069] The limb key points may be key points in the limb area of ​​the object to be identified in the limb image, for example, they may be key points of the upper limbs, the head, etc., wherein the upper limbs may include key points corresponding to the left hand, the left elbow joint, the left shoulder, the right hand, the right elbow joint, the right shoulder, etc. The time information may be the time when the limb image is collected, and the posture feature may be information representing the posture behavior of the object to be identified extracted from the limb image based on the limb key points. The candidate posture information may be some pre-set behavioral postures to be selected.

[0070] Among them, based on the limb key points and the time information corresponding to the limb image, there can be multiple ways to extract the posture features corresponding to the object to be identified in the limb image. For example, the limb images can be arranged according to the time information corresponding to each limb image to obtain multiple continuous limb images, and the position coordinates of the limb key points in the multiple continuous limb images can be extracted. According to the changes in the position coordinates of the limb key points, the motion trajectory of the limb joints is calculated, and a limb joint change matrix is ​​generated based on the motion trajectory of the limb joints. Based on the limb joint change matrix, the posture features corresponding to the object to be identified can be obtained.

[0071] After the posture features corresponding to the object to be identified are extracted from the limb image based on the limb key points and the time information corresponding to the limb image, the behavioral posture information of the object to be identified can be identified in the candidate posture information based on the posture features. There are many ways to identify the behavioral posture information of the object to be identified in the candidate posture information based on the posture features. For example, the candidate posture features corresponding to the candidate posture information can be extracted, and the feature similarity between the candidate posture features and the posture features of the object to be identified can be calculated. According to the feature similarity, the candidate posture features that best match the posture features of the object to be identified can be screened out from the candidate posture features corresponding to the candidate posture information, so that the candidate posture information corresponding to the best matching candidate posture features can be determined as the behavioral posture information of the object to be identified. The candidate posture features can be features that can characterize the candidate posture information.

[0072] Optionally, feature extraction can be performed directly on the terminal for facial images and limb images, or when the computing power of the terminal is poor, the facial image of the object to be identified in the target area and the limb image corresponding to the facial image can be sent to the server, and feature extraction can be performed on the facial image and limb image through the server. The specific selection can be made according to actual conditions, and this application is not limited here.

[0073] In step 103, the behavior state of the object to be identified is identified based on the facial expression information and the behavior posture information.

[0074] The behavior state may be a state of a behavior action of the object to be identified, for example, it may be a behavior state such as eating, sleeping, drinking water, etc.

[0075] There are multiple ways to identify the behavior state of the object to be identified based on the facial expression information and the behavior posture information. For example, the facial expression information and the behavior posture information corresponding to the facial expression information can be combined, and a matching behavior state can be screened out from the candidate behavior states according to the combined facial expression information and behavior posture information. The candidate behavior state can be at least one preset behavior state, for example, it can include behavior states such as eating, sleeping, drinking water, etc.

[0076] Among them, according to the combined facial expression information and behavioral posture information, there are many ways to filter out matching behavioral states from the candidate behavioral states. For example, if the facial expression information is an open mouth, and the corresponding behavioral posture information is lowering the head with the arm moving from the table toward the mouth, then the most matching behavioral state can be found in the candidate behavioral states as dining, etc.

[0077] Optionally, an object image corresponding to the object to be identified may also be collected. The object image may be an image including the object to be identified and objects surrounding the object to be identified. Image recognition technology may be used to detect in the object image whether there are tableware such as take-out boxes and microwaveable lunch boxes within a certain distance of the object to be identified, so as to further determine whether the behavior state of the object to be identified is a dining state.

[0078] In step 104, when the behavior state of the object to be identified is the target behavior state, the position information of the object to be identified is acquired, and the target air conditioner is determined from the candidate air conditioners according to the position information.

[0079] The target behavior state may be a dining state. When the behavior state of the object to be identified is a dining state, a strong or unpleasant smell may appear in the target area. At this time, air conditioning operations such as ventilation and air exchange may be performed on the target area. The position information may be information including the position of the object to be identified in the target area. The candidate air conditioner may be at least one air conditioner installed in the target area. The target air conditioner may be an air conditioner selected from the candidate air conditioners based on the position of the object to be identified. For example, it may be an air conditioner that is closest to the object to be identified among the candidate air conditioners, or it may be an air conditioner that performs air conditioning on the area where the object to be identified is located.

[0080] Optionally, air conditioning processing can be performed after the number of objects to be identified in the target behavior state in the target area meets a certain number. For example, assuming that the target area is an office area and the target behavior state is a dining state, when the number of people in the dining state in the office area is greater than a certain number, the air quality will be in a poor state. At this time, the target air conditioner is triggered to perform air conditioning processing such as ventilation and air exchange on the office area.

[0081] In step 105, air conditioning is performed on the target area based on the target air conditioning.

[0082] Among them, based on the target air conditioner, there can be multiple ways to perform air conditioning processing on the target area. For example, the working status of the target air conditioner can be detected. When the working status is off, the target air conditioner can be turned on, and the working mode of the target air conditioner can be adjusted to the target working mode, and the target area can be air conditioned based on the target working mode.

[0083] The working state may be the working state of the target air conditioner, for example, it may include an on state and an off state, etc. The target working mode may be a pre-set working mode, for example, it may be a ventilation / air exchange mode (if there is no such mode, the wind temperature may be set to the current room temperature). Thus, when the target air conditioner is in the on state, the air conditioning processing instruction may be ignored to avoid affecting the current user's use. When the air conditioner is in the off state, the target air conditioner may be turned on, and the working mode of the target air conditioner may be set to the target working mode (for example, ventilation / air exchange mode).

[0084] Optionally, when it is detected that the number of objects to be identified in the target area that are not in the target behavior state is small, or when the current time is not within the air conditioning time interval, the initial state of the air conditioner can be restored to avoid wasting power resources.

[0085] In the prior art, the air conditioners configured in public areas such as office areas and canteens are basically arranged with multiple air conditioner switches arranged together, and it is impossible to intuitively determine which switch corresponds to which air conditioner position. When there are too many people dining in the target area, resulting in excessive odor in the public area and the air conditioner needs to be adjusted for air conditioning, it is necessary to try the switch multiple times to find the correct switch, which is cumbersome and time-consuming, resulting in low control efficiency of the air conditioning equipment, further reducing the efficiency of air conditioning. In order to solve the above problems, optionally, the embodiment of the present application can use the communication method of the Internet of Things programmable logic controller (PLC) to communicate and connect part or all of the cameras installed in the target area with the air conditioning control panel of the air conditioner installed in the target area, so that the camera can be controlled to collect the facial image and limb image of the object to be identified based on the Internet of Things connection, and the behavior state of the object to be identified can be identified according to the facial image and limb image. When the behavior state is the target behavior state, the target air conditioner can be screened out from the candidate air conditioners, so that the target area can be air conditioned by the target air conditioner, thereby improving the control efficiency of the air conditioning equipment and further improving the efficiency of air conditioning.

[0086] As can be seen from the above, the present application obtains the facial image of the object to be identified in the target area and the limb image corresponding to the facial image; performs expression recognition on the facial image to obtain the facial expression information of the object to be identified, and performs posture recognition on the limb image to obtain the behavior posture information of the object to be identified; identifies the behavior state of the object to be identified based on the facial expression information and the behavior posture information; when the behavior state of the object to be identified is the target behavior state, obtains the position information of the object to be identified, and determines the target air conditioner in the candidate air conditioners according to the position information; and performs air conditioning processing on the target area based on the target air conditioner. In this way, the behavior state of the object to be identified is identified by obtaining the facial image and limb image of the object to be identified, and when the behavior state of the object to be identified is the target behavior state, the target air conditioner is determined in the candidate air conditioners according to the position information of the object to be identified, so that the target area is accurately air-conditioned by the target air conditioner, thereby improving the control efficiency of the air-conditioning equipment, further improving the efficiency of air conditioning, and thus improving the user experience.

[0087] According to the method described in the above embodiment, the following is further described in detail with examples.

[0088] In this embodiment, a specific description will be given by taking the specific integration of the air conditioning device based on the Internet of Things in a terminal as an example.

[0089] For a better description of the embodiments of this application, please refer to Figure 3 .like Figure 3 As shown, Figure 3Another schematic diagram of the process of the air conditioning method based on the Internet of Things provided in the embodiment of the present application. The specific process is as follows:

[0090] In step 201, the terminal obtains the current time and detects the current time based on a preset behavior recognition time interval. When it is detected that the current time is within the preset behavior recognition time interval, the object image of the object to be recognized in the target area is obtained, and the object image is divided to obtain the facial image of the object to be recognized and the limb image corresponding to the facial image.

[0091] In the embodiment of the present application, a specific description is given by taking the target area as an office area and the target behavior state as a dining state as an example.

[0092] The current time may be the current time, and the preset behavior recognition time interval may be a preset time interval for recognizing the behavior state of the object to be recognized, for example, it may be a dining time period such as 8:00-9:30, 11:00-13:00, 17:00-19:00, etc. The object image may be an image including the object to be recognized.

[0093] Optionally, some or all of the cameras installed in the target area can be communicatively connected to the air-conditioning control panel of the air-conditioning installed in the target area by using the communication method of the Internet of Things programmable logic controller (PLC), so that when the terminal detects that the current time is within the preset behavior recognition time interval, it can call the camera to collect the object image of the object to be identified in the target area, so that the object image can be divided to obtain the facial image of the object to be identified and the limb image corresponding to the facial image.

[0094] In step 202, the terminal identifies at least one facial key point corresponding to the object to be identified in the facial image, extracts facial image features corresponding to the object to be identified in the facial image based on the facial key points, and identifies facial expression information of the object to be identified in the candidate expression information based on the facial image features.

[0095] The facial key points may be key points in the facial region of the object to be identified in the facial image, for example, the mouth, nose, eyes, eyebrows and other key points, and the facial image features may be information representing the facial expressions of the object to be identified extracted from the facial image based on the facial key points. The candidate expression information may be some pre-set expression information to be selected, for example, expression information such as blowing through the mouth (spicy, hot), opening the mouth, chewing, swallowing, expressions indicating deliciousness, expressions indicating unpalatableness and other types of expression information.

[0096] Among them, there are many ways for the terminal to identify the facial expression information of the object to be identified in the candidate expression information based on the facial image features. For example, the terminal can extract the expression features corresponding to the candidate expression information, calculate the feature similarity between the expression features and the facial image features of the object to be identified, and screen out the expression features that best match the facial image features of the object to be identified from the expression features corresponding to the candidate expression information according to the feature similarity, so that the candidate expression information corresponding to the best matching expression features can be determined as the facial expression information of the object to be identified.

[0097] The expression feature may be a feature that represents candidate expression information, and the feature similarity may be information that represents the degree of similarity between the expression feature and the facial image feature.

[0098] In step 203, the terminal identifies at least one limb key point corresponding to the object to be identified in the limb image, extracts posture features corresponding to the object to be identified in the limb image based on the limb key point and the time information corresponding to the limb image, and identifies the behavioral posture information of the object to be identified in the candidate posture information based on the posture features.

[0099] The limb key points may be key points in the limb area of ​​the object to be identified in the limb image, for example, they may be key points of the upper limbs, the head, etc., wherein the upper limbs may include key points corresponding to the left hand, the left elbow joint, the left shoulder, the right hand, the right elbow joint, the right shoulder, etc. The time information may be the time when the limb image is collected, and the posture feature may be information representing the posture behavior of the object to be identified extracted from the limb image based on the limb key points. The candidate posture information may be some pre-set behavioral postures to be selected.

[0100] Among them, the terminal can have multiple ways to extract the posture features corresponding to the object to be identified in the limb image based on the limb key points and the time information corresponding to the limb image. For example, the terminal can arrange the limb images according to the time information corresponding to each limb image to obtain multiple continuous limb images, extract the position coordinates of the limb key points in the multiple continuous limb images, calculate the movement trajectory of the limb joints according to the changes in the position coordinates of the limb key points, and generate a limb joint change matrix based on the movement trajectory of the limb joints. Based on the limb joint change matrix, the posture features corresponding to the object to be identified can be obtained.

[0101] After the posture features corresponding to the object to be identified are extracted from the limb image based on the limb key points and the time information corresponding to the limb image, the terminal can identify the behavioral posture information of the object to be identified in the candidate posture information based on the posture features. There are many ways for the terminal to identify the behavioral posture information of the object to be identified in the candidate posture information based on the posture features. For example, the terminal can extract the candidate posture features corresponding to the candidate posture information, calculate the feature similarity between the candidate posture features and the posture features of the object to be identified, and select the candidate posture features that best match the posture features of the object to be identified from the candidate posture features corresponding to the candidate posture information according to the feature similarity, so that the candidate posture information corresponding to the best matching candidate posture features can be determined as the behavioral posture information of the object to be identified. The candidate posture feature can be a feature that can characterize the candidate posture information.

[0102] Optionally, the terminal can directly perform feature extraction on the facial image and the limb image, or when the computing power of the terminal is poor, the facial image of the object to be identified in the target area and the limb image corresponding to the facial image can be sent to the server, and the facial image and the limb image can be extracted by the server. The specific selection can be made according to the actual situation, and this application is not limited here.

[0103] In step 204, the terminal obtains the time information corresponding to the facial expression information and the behavioral posture information respectively, matches the facial expression information and the behavioral posture information based on the time information, obtains an expression posture information group, and identifies the behavioral state of the object to be identified in the candidate behavioral states according to the time information corresponding to the facial expression information and the behavioral posture information in the expression posture information group.

[0104] Among them, the time information can be the time for obtaining facial expression information and behavioral posture information, the label posture information group can be a combination of facial expression information and behavioral posture information matched based on the time information, the label posture information group can include at least one facial expression information and at least one behavioral posture information, and the candidate behavioral state can be at least one preset behavioral state, for example, it can include behavioral states such as eating, sleeping, and drinking water.

[0105] There are multiple ways to identify the behavior state of the object to be identified in the candidate behavior state according to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group. For example, the behavior state of the expression posture information group corresponding to the object to be identified can be analyzed according to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group, and the behavior state of the object to be identified can be identified in the candidate behavior state according to the analysis result. For example, the expression posture information group can be identified according to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group, and the behavior of the object to be identified lowering its head and moving its arm from the desktop to the mouth, opening its mouth, moving its arm from the mouth area to the desktop and putting it down, chewing, etc. can be identified. According to these behaviors, candidate behavior states that match these behaviors can be screened out from the candidate behavior states, and then the behavior state of the object to be identified can be obtained.

[0106] In step 205, the terminal counts the number of target objects to be identified whose behavior state is the target behavior state among the objects to be identified based on the behavior state of the objects to be identified, obtains the number of objects in the target state, and compares the number of objects in the target state with a preset object number threshold.

[0107] The number of target state objects may be the number of target objects to be identified whose behavior state is the target behavior state among the objects to be identified, and the preset object number threshold may be a pre-set critical value. When the number of target state objects is greater than the critical value, subsequent air conditioning processing may be performed, and when the number of target state objects is not greater than the critical value, subsequent air conditioning processing may not be performed. For example, in an office area, when there are many people in a dining state, the smell in the office area is heavy and the air quality is poor, and air conditioning processing such as ventilation may be performed.

[0108] In step 206, when the number of objects in the target state is greater than a preset object number threshold, the terminal obtains the position information of the target object to be identified, and determines the target air conditioner from the candidate air conditioners according to the position information.

[0109] In order to achieve accurate air conditioning processing and improve air conditioning efficiency, the terminal can obtain the location information of the target object to be identified when the number of objects in the target state is greater than the preset object number threshold, so as to determine the target air conditioner responsible for air conditioning in the area where the object to be identified is located among the candidate air conditioners based on the location information.

[0110] Among them, there are many ways for the terminal to determine the target air conditioner among the candidate air conditioners based on the location information. For example, the terminal can pre-divide the target area according to the area that each candidate air conditioner is responsible for air conditioning in the target area, obtain the target sub-area corresponding to each candidate air conditioner, and associate each candidate air conditioner with the corresponding target sub-area. When the location information of the target object to be identified is obtained, it is detected in which target sub-area the location information is located, and the candidate air conditioner associated with the target sub-area where the location information is located is determined as the target air conditioner.

[0111] In step 207, the terminal detects the working state of the target air conditioner, and when the working state is off, turns on the target air conditioner, adjusts the working mode of the target air conditioner to the target working mode, and performs air conditioning processing on the target area based on the target working mode.

[0112] The working state may be the working state of the target air conditioner, for example, it may include an on state and an off state, etc. The target working mode may be a pre-set working mode, for example, it may be a ventilation / air exchange mode (if there is no such mode, the wind temperature may be set to the current room temperature). Thus, when the target air conditioner is in the on state, the air conditioning processing instruction may be ignored to avoid affecting the current user's use. When the air conditioner is in the off state, the target air conditioner may be turned on, and the working mode of the target air conditioner may be set to the target working mode (for example, ventilation / air exchange mode).

[0113] Optionally, when the terminal detects that there are few objects to be identified in the target behavior state in the target area, or when the current time is not within the air conditioning time interval, the terminal can restore the initial state of the air conditioner to avoid wasting power resources.

[0114] As can be seen from the above, the embodiment of the present application obtains the current time through the terminal, and detects the current time based on the preset behavior recognition time interval. When it is detected that the current time is within the preset behavior recognition time interval, the object image of the object to be recognized in the target area is obtained, and the object image is divided to obtain the facial image of the object to be recognized and the limb image corresponding to the facial image; the terminal recognizes at least one facial key point corresponding to the object to be recognized in the facial image, and according to the facial key point, extracts the facial image features corresponding to the object to be recognized in the facial image, and based on the facial image features, recognizes the facial expression information of the object to be recognized in the candidate expression information; the terminal recognizes at least one limb key point corresponding to the object to be recognized in the limb image, and based on the limb key point and the time information corresponding to the limb image, extracts the posture features corresponding to the object to be recognized in the limb image, and based on the posture features, recognizes the behavior posture information of the object to be recognized in the candidate posture information; the terminal obtains the facial The facial expression information and the time information corresponding to the behavior posture information are matched based on the time information to obtain an expression posture information group, and the behavior state of the object to be identified in the candidate behavior states is identified according to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group; based on the behavior state of the object to be identified, the terminal counts the number of target objects to be identified whose behavior state is the target behavior state in the object to be identified to obtain the number of target state objects, and compares the number of target state objects with a preset object number threshold; when the number of target state objects is greater than the preset object number threshold, the terminal obtains the location information of the target object to be identified, and determines the target air conditioner in the candidate air conditioners based on the location information; the terminal detects the working state of the target air conditioner, and when the working state is off, turns on the target air conditioner, adjusts the working mode of the target air conditioner to the target working mode, and performs air conditioning processing on the target area based on the target working mode. In this way, by detecting the current time, when the current time is within the preset behavior recognition time interval, the face image and body image of the object to be recognized in the target area are obtained, and the behavior state of the object to be recognized is identified based on the face image and the body image, so as to count the number of target objects to be recognized whose behavior state is the target behavior state among the objects to be recognized, and obtain the number of target state objects, and when the number of target state objects is greater than the preset object number threshold, the position information of the target object to be recognized is obtained, so as to determine the target air conditioner among the candidate air conditioners based on the position information, and adjust the working mode of the target air conditioner to the target working mode, so as to perform accurate air conditioning processing on the target area through the target air conditioner, thereby improving the control efficiency of the air-conditioning equipment, further improving the efficiency of air conditioning, and thus improving the user experience.

[0115] In order to better implement the above method, an embodiment of the present invention further provides an air conditioning device based on the Internet of Things, which can be integrated in a terminal.

[0116] For example, Figure 4 As shown, it is a structural schematic diagram of an air conditioning device based on the Internet of Things provided in an embodiment of the present application. The air conditioning device based on the Internet of Things may include an image acquisition unit 301, a feature extraction unit 302, a state recognition unit 303, an air conditioning determination unit 304 and an air conditioning unit 305, as follows:

[0117] An image acquisition unit 301 is used to acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image;

[0118] The feature extraction unit 302 is used to perform expression recognition on the facial image to obtain facial expression information of the object to be recognized, and perform posture recognition on the limb image to obtain behavior posture information of the object to be recognized;

[0119] A state recognition unit 303 is used to recognize the behavior state of the object to be recognized based on the facial expression information and the behavior posture information;

[0120] The air conditioner determination unit 304 is used to obtain the position information of the object to be identified when the behavior state of the object to be identified is the target behavior state, and determine the target air conditioner from the candidate air conditioners according to the position information;

[0121] The air conditioning unit 305 is used to perform air conditioning processing on the target area based on the target air conditioner.

[0122] In one embodiment, the image acquisition unit 301 includes:

[0123] A time acquisition subunit, used to acquire the current time and detect the current time based on a preset behavior recognition time interval;

[0124] An image acquisition subunit is used to acquire an object image of an object to be identified in a target area when detecting that the current time is within the preset behavior recognition time interval;

[0125] The image segmentation subunit is used to segment the object image to obtain the facial image of the object to be identified and the limb image corresponding to the facial image.

[0126] In one embodiment, the feature extraction unit 302 includes:

[0127] A facial key point recognition subunit, used to recognize at least one facial key point corresponding to the object to be recognized in the facial image;

[0128] A facial feature extraction subunit, used to extract facial image features corresponding to the object to be identified in the facial image according to the facial key points;

[0129] The facial expression information recognition subunit is used to recognize the facial expression information of the object to be recognized from the candidate expression information based on the facial image features.

[0130] In one embodiment, the feature extraction unit 302 includes:

[0131] A limb key point recognition subunit, used to recognize at least one limb key point corresponding to the object to be recognized in the limb image;

[0132] A posture feature extraction subunit, used for extracting the posture feature corresponding to the object to be identified in the limb image based on the limb key points and the time information corresponding to the limb image;

[0133] The behavior posture information recognition subunit is used to recognize the behavior posture information of the object to be recognized in the candidate posture information based on the posture feature.

[0134] In one embodiment, the state identification unit 303 includes:

[0135] A time information acquisition subunit, used to respectively acquire the time information corresponding to the facial expression information and the behavior posture information;

[0136] A matching subunit, used for matching the facial expression information and the behavior posture information based on the time information to obtain an expression posture information group, wherein the label posture information group includes at least one piece of the facial expression information and at least one piece of the behavior posture information;

[0137] The state recognition subunit is used to recognize the behavior state of the object to be recognized in the candidate behavior states according to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group.

[0138] In one embodiment, the air conditioning determination unit 304 includes:

[0139] A quantity counting subunit is used to count the number of target objects to be identified whose behavior state is a target behavior state among the objects to be identified based on the behavior state of the objects to be identified, so as to obtain the number of objects in the target state;

[0140] A comparison subunit, used to compare the number of objects in the target state with a preset object number threshold;

[0141] The position information acquisition subunit is used to acquire the position information of the target object to be identified when the number of objects in the target state is greater than the preset object number threshold.

[0142] In one embodiment, the air conditioning unit 305 comprises:

[0143] A working state detection subunit, used to detect the working state of the target air conditioner;

[0144] A mode adjustment subunit, used for turning on the target air conditioner when the working state is the off state, and adjusting the working mode of the target air conditioner to the target working mode;

[0145] The air conditioning subunit is used to perform air conditioning processing on the target area based on the target working mode.

[0146] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0147] As can be seen from the above, the embodiment of the present application obtains the facial image of the object to be identified in the target area and the limb image corresponding to the facial image through the image acquisition unit 301; the feature extraction unit 302 performs expression recognition on the facial image to obtain the facial expression information of the object to be identified, and performs posture recognition on the limb image to obtain the behavior posture information of the object to be identified; the state recognition unit 303 identifies the behavior state of the object to be identified based on the facial expression information and the behavior posture information; the air conditioning determination unit 304 obtains the position information of the object to be identified when the behavior state of the object to be identified is the target behavior state, and determines the target air conditioning in the candidate air conditioners according to the position information; the air conditioning unit 305 performs air conditioning processing on the target area based on the target air conditioner. In this way, the behavior state of the object to be identified is identified by acquiring the facial image and limb image of the object to be identified, and when the behavior state of the object to be identified is the target behavior state, the target air conditioner is determined in the candidate air conditioners according to the position information of the object to be identified, so that the target area is accurately air-conditioned by the target air conditioner, the control efficiency of the air conditioning equipment is improved, the efficiency of air conditioning is further improved, and the user experience is improved.

[0148] The present application also provides a computer device, such as Figure 5 As shown, it shows a schematic diagram of the structure of a computer device involved in an embodiment of the present application, and the computer device may be a terminal. Specifically:

[0149] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that Figure 5The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0150] The processor 401 is the control center of the computer device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 402 and calling data stored in the memory 402, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0151] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and air conditioning based on the Internet of Things by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0152] The computer device also includes a power supply 403 for supplying power to various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 403 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0153] The computer device may further include an input unit 404, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0154] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402, thereby realizing various functions, as follows:

[0155] Acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image; perform expression recognition on the facial image to obtain facial expression information of the object to be identified, and perform posture recognition on the limb image to obtain behavioral posture information of the object to be identified; identify the behavioral state of the object to be identified based on the facial expression information and the behavioral posture information; when the behavioral state of the object to be identified is a target behavioral state, acquire the position information of the object to be identified, and determine a target air conditioner from candidate air conditioners based on the position information; and perform air conditioning processing on the target area based on the target air conditioner.

[0156] The specific implementation of each of the above operations can be found in the previous embodiments, which will not be described in detail here. It should be noted that the computer device provided in the embodiment of the present application and the air conditioning method based on the Internet of Things in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above method embodiment, which will not be described in detail here.

[0157] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0158] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the air conditioning methods based on the Internet of Things provided in the embodiment of the present application. For example, the instructions can execute the following steps:

[0159] Acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image; perform expression recognition on the facial image to obtain facial expression information of the object to be identified, and perform posture recognition on the limb image to obtain behavioral posture information of the object to be identified; identify the behavioral state of the object to be identified based on the facial expression information and the behavioral posture information; when the behavioral state of the object to be identified is a target behavioral state, acquire the position information of the object to be identified, and determine a target air conditioner from candidate air conditioners based on the position information; and perform air conditioning processing on the target area based on the target air conditioner.

[0160] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0161] Since the instructions stored in the computer-readable storage medium can execute the steps in any one of the air conditioning methods based on the Internet of Things provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the air conditioning methods based on the Internet of Things provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0162] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the various optional implementations provided in the above embodiments.

[0163] The above is a detailed introduction to an air conditioning method, device and computer-readable storage medium based on the Internet of Things provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An air conditioning method based on the Internet of Things, characterized in that: include: Acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image; Performing expression recognition on the facial image to obtain facial expression information of the object to be identified, and performing posture recognition on the limb image to obtain behavior posture information of the object to be identified; Based on the facial expression information and the behavioral posture information, identifying the behavioral state of the object to be identified; When the behavior state of the object to be identified is a target behavior state, obtaining position information of the object to be identified, and determining a target air conditioner from candidate air conditioners according to the position information; Based on the target air conditioning, air conditioning processing is performed on the target area.

2. The air conditioning method based on the Internet of Things according to claim 1, characterized in that: The step of acquiring a facial image of an object to be identified in a target area and a limb image corresponding to the facial image comprises: Acquire the current time, and detect the current time based on a preset behavior recognition time interval; When it is detected that the current time is within the preset behavior recognition time interval, acquiring an object image of the object to be recognized in the target area; The object image is divided to obtain a facial image of the object to be identified and a limb image corresponding to the facial image.

3. The air conditioning method based on the Internet of Things according to claim 1, characterized in that: The performing expression recognition on the facial image to obtain facial expression information of the object to be recognized includes: Identifying at least one facial key point corresponding to the object to be identified in the facial image; Extracting facial image features corresponding to the object to be identified from the facial image according to the facial key points; Based on the facial image features, the facial expression information of the object to be identified is identified from the candidate expression information.

4. The air conditioning method based on the Internet of Things according to claim 1, characterized in that: The step of performing posture recognition on the limb image to obtain the behavior posture information of the object to be recognized includes: Identifying at least one limb key point corresponding to the object to be identified in the limb image; Extracting posture features corresponding to the object to be identified in the limb image based on the limb key points and time information corresponding to the limb image; Based on the posture features, the behavior posture information of the object to be identified is identified in the candidate posture information.

5. The air conditioning method based on the Internet of Things according to claim 1, characterized in that: The step of identifying the behavior state of the object to be identified based on the facial expression information and the behavior posture information includes: Respectively obtaining the time information corresponding to the facial expression information and the behavior posture information; Based on the time information, the facial expression information and the behavior posture information are matched to obtain an expression posture information group, wherein the expression posture information group includes at least one facial expression information and at least one behavior posture information; According to the time information corresponding to the facial expression information and the behavior posture information in the expression posture information group, the behavior state of the object to be identified is identified from the candidate behavior states.

6. The air conditioning method based on the Internet of Things according to claim 1, characterized in that: When the behavior state of the object to be identified is the target behavior state, obtaining the position information of the object to be identified includes: Based on the behavior state of the object to be identified, counting the number of target objects to be identified whose behavior state is a target behavior state among the objects to be identified, to obtain the number of objects in the target state; Comparing the number of objects in the target state with a preset object number threshold; When the number of objects in the target state is greater than the preset object number threshold, the position information of the target object to be identified is obtained.

7. The air conditioning method based on the Internet of Things according to claim 1, characterized in that: The step of performing air conditioning processing on the target area based on the target air conditioner includes: Detecting the working status of the target air conditioner; When the working state is the off state, turning on the target air conditioner, and adjusting the working mode of the target air conditioner to the target working mode; The target area is air-conditioned based on the target operating mode.

8. An air conditioning device based on the Internet of Things, characterized in that: include: An image acquisition unit, used to acquire a facial image of an object to be identified in a target area and a limb image corresponding to the facial image; A feature extraction unit, used to perform expression recognition on the facial image to obtain facial expression information of the object to be identified, and perform posture recognition on the limb image to obtain behavior posture information of the object to be identified; A state recognition unit, used to recognize the behavior state of the object to be recognized based on the facial expression information and the behavior posture information; an air conditioner determination unit, configured to obtain position information of the object to be identified when the behavior state of the object to be identified is a target behavior state, and determine a target air conditioner from among candidate air conditioners based on the position information; An air conditioning unit is used to perform air conditioning processing on the target area based on the target air conditioner.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the air conditioning method based on the Internet of Things as described in any one of claims 1 to 7.

10. A computer device, characterized in that: It comprises a memory and a processor; the memory stores an application program, and the processor is used to run the application program in the memory to execute the steps in the air conditioning method based on the Internet of Things as described in any one of claims 1 to 7.

Images