Intelligent air conditioner adjusting method and device and electronic equipment

Abstract

The invention discloses an intelligent air conditioner adjusting method and device and electronic equipment and relates to the field of intelligent air conditioners. The method comprises the following steps: acquiring a plurality of indoor images; feature extraction is carried out on each indoor image, personnel activity states corresponding to each indoor image and time points corresponding to the personnel activity states are obtained, and the personnel activity states comprise an outgoing state, a sleep state, a sedentariness state and an activity state; inputting the personnel activity time sequence into a preset activity state prediction model to obtain a predicted activity state; according to a preset operation rule, air conditioner operation data corresponding to the predicted activity state is determined; acquiring outdoor environment parameters; according to the outdoor environment parameters, the air conditioner operation data are adjusted, and target air conditioner operation data are obtained; and determining to operate the air conditioner according to the target air conditioner operation data. According to the technical scheme, the air conditioner operation data are automatically adjusted according to the user activity state and the outdoor environment parameters, and energy waste is reduced.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to an intelligent air conditioning adjustment method, device and electronic equipment. Background Art

[0002] With the global climate change and the improvement of people's living standards, air conditioning has become an indispensable equipment in modern life, especially in hot or cold seasons. Air conditioning not only provides a comfortable indoor environment, but also affects people's health and work efficiency. According to statistics, the utilization rate of air conditioning systems in homes and commercial buildings in many countries is extremely high, especially in summer, when air conditioning runs almost all day long, consuming a lot of electricity resources. Therefore, improving the intelligence level of air conditioning systems and achieving efficient and energy-saving operation has become an important issue in modern society.

[0003] Currently, most traditional air conditioning systems rely on manual settings by the user, which has obvious shortcomings in actual use. For example, users often forget to adjust the air conditioning settings when they are away from home, causing the air conditioning to continue running when no one is living in the house, which will cause energy waste.

[0004] Therefore, there is an urgent need for an intelligent air conditioning adjustment method, device and electronic equipment. Summary of the invention

[0005] The present application provides an intelligent air conditioning adjustment method, device and electronic equipment, which automatically adjust air conditioning operation data according to user activity status and outdoor environmental parameters, thereby reducing energy waste.

[0006] In the first aspect of the present application, a smart air conditioning adjustment method is provided, the method comprising: acquiring multiple indoor images; performing feature extraction on each of the indoor images to obtain the personnel activity status corresponding to each of the indoor images and the time point corresponding to the personnel activity status, the personnel activity status including outdoor status, sleep status, sedentary status and active status; constructing a personnel activity time series according to the personnel activity status and the time point corresponding to the personnel activity status; inputting the personnel activity time series into a preset activity status prediction model to obtain a predicted activity status; determining the air conditioning operation data corresponding to the predicted activity status according to preset operation rules, the air conditioning operation data including an air conditioning operation mode and an air conditioning target temperature; acquiring outdoor environmental parameters, the outdoor environmental parameters including outdoor temperature and outdoor humidity; adjusting the air conditioning operation data according to the outdoor environmental parameters to obtain target air conditioning operation data; and determining to operate the air conditioner with the target air conditioning operation data.

[0007] By adopting the above technical solution, by acquiring indoor images, extracting features from indoor images to obtain the activity status of personnel and the corresponding time points, constructing a time series of personnel activities, and then using a preset activity status prediction model to predict the future activity status of personnel, and determining the air conditioning operation mode and the target temperature of the air conditioning based on the predicted activity status and the preset operation rules. At the same time, outdoor environmental parameters are also obtained to adjust and optimize the determined air conditioning operation data, and finally control the air conditioning to operate with the optimized target air conditioning operation data. This solution can accurately predict the user's activity status in the future by analyzing the user's historical activity status, adjust the air conditioning in advance, make the air conditioning operation more intelligent and humanized, and the operation parameters are more in line with the user's actual needs and preferences. In addition, the operation data can be adaptively adjusted according to the outdoor environmental parameters, while ensuring the user experience and taking into account energy conservation and environmental protection. When the user status changes, the air conditioning operation data can also be automatically adjusted, avoiding the trouble of users frequently manually adjusting the air conditioning. While improving the user's comfort, the energy utilization efficiency is improved and energy waste is reduced through the intelligent optimization of the air conditioning operation strategy.

[0008] Optionally, the feature extraction is performed on each of the indoor images to obtain the activity status of the person corresponding to each of the indoor images, specifically including: performing a preprocessing operation on the indoor images to obtain a target indoor image, the preprocessing operation including image size normalization, image noise removal and image enhancement; detecting a target person from the target indoor image using a target detection algorithm; extracting the human body key points of the target person, and calculating the set relationship between each of the human body key points to obtain posture features, the posture features including torso angle features and limb angle features; determining the activity status of the person according to the torso angle features and the limb angle features.

[0009] By adopting the above technical solution, the acquired indoor images are preprocessed, including size normalization, image noise removal and image enhancement, to optimize the image quality for subsequent analysis. Then, the target person in the image is detected by the target detection algorithm, and the key points of the human body are extracted to calculate the posture features. The different activity states of the person are judged by analyzing the angle features of the human body trunk and limbs. This method of first locating the human body and then analyzing the posture of the key points can accurately and efficiently judge different activity states, providing a reliable basis for state judgment for subsequent activity prediction and air conditioning control.

[0010] Optionally, determining the activity state of the person according to the torso angle characteristics and the limb angle characteristics specifically includes: when the torso angle characteristics represent that the torso of the target person is perpendicular to the ground, and the limb angle characteristics represent that the limbs of the target person are in an extended state, determining that the activity state of the person is an active state; when the torso angle characteristics represent that the torso of the target person is perpendicular to the ground, and the limb angle characteristics represent that the limbs of the target person are in a bent state, determining that the activity state of the person is a sedentary state; when the torso angle characteristics represent that the torso of the target person is at a preset angle to the ground, and the limb angle characteristics represent that the limbs of the target person are in a horizontal position, determining that the activity state of the person is a sleeping state; when the target person is not detected from the target indoor image within a preset time period, determining that the activity state of the person is an outing state.

[0011] By adopting the above technical solution, when the trunk is perpendicular to the ground and the limbs are stretched, it is in an active state; when the trunk is perpendicular but the limbs are bent, it is in a sedentary state; when the trunk is at a certain angle to the ground and the limbs are placed horizontally, it is in a sleeping state; if no person is detected for a period of time, it is judged as an away state. This method of distinguishing the activity state based on the posture and angle characteristics of the human body is intuitive and efficient, and makes full use of the activity information contained in the posture of the human body. The judgment rules of the angle relationship between key points can realize the rapid classification of the activity state of people.

[0012] Optionally, before inputting the personnel activity time series into a preset activity status prediction model to obtain the predicted activity status, the method also includes: obtaining time series sample data, the time series sample data including a historical activity state sequence and a duration corresponding to the historical activity state sequence; constructing a seq2seq model, the seq2seq model including an encoder and a decoder, the encoder being used to encode the input historical activity state sequence, and the decoder being used to predict the personnel activity status at the next moment; and using the time series sample data to train the seq2seq model to obtain the preset activity state prediction model.

[0013] By adopting the above technical solution, historical activity state sequences and their durations are obtained as training samples, and then a seq2seq model including an encoder and a decoder is constructed to train the time series sample data, so that the seq2seq model can predict the most likely activity state of a person at the next moment given a historical activity state sequence.

[0014] Optionally, the air conditioning operation data corresponding to the predicted activity state is determined according to preset operation rules, specifically including: when the predicted activity state is an outing state, determining that the air conditioning operation mode is an off mode; when the predicted activity state is a sleeping state, determining that the air conditioning operation mode is a sleeping mode, and setting the air conditioning target temperature to a preset sleeping temperature; when the predicted activity state is a sedentary state, determining that the air conditioning operation mode is a cooling mode or a heating mode, and setting the air conditioning target temperature to a preset comfort temperature; when the predicted activity state is an active state, determining that the air conditioning operation mode is an air supply mode.

[0015] By adopting the above technical solution, when the predicted activity state is out of the state, the air conditioner operation mode is off mode to save energy; when the predicted activity state is sleeping state, the air conditioner enters sleep mode and sets the preset sleeping temperature; when the predicted activity state is sedentary state, the cooling or heating mode is turned on and adjusted to the preset comfortable temperature; when the predicted activity state is active state, it switches to air supply mode to maintain air circulation. This air conditioning control solution based on user activity state fully considers the user's air conditioning use needs in different activity states, automatically switches the air conditioning working mode and temperature parameters according to the changes in the predicted activity state, and has a better user experience.

[0016] Optionally, the air-conditioning operation data is adjusted according to the outdoor environmental parameters to obtain target air-conditioning operation data, specifically including: obtaining historical outdoor environmental parameters and corresponding user temperature adjustment behavior data, the user temperature adjustment behavior data including the user's temperature adjustment time, temperature adjustment amplitude and target temperature after temperature adjustment; constructing a user temperature adjustment behavior prediction model, the user temperature adjustment behavior prediction model is used to predict the user's temperature adjustment behavior according to the current outdoor environmental parameters; inputting the outdoor temperature and the outdoor humidity into the user temperature adjustment behavior prediction model to obtain a predicted temperature adjustment amplitude; adjusting the air-conditioning target temperature according to the predicted temperature adjustment amplitude to obtain the target air-conditioning operation data.

[0017] By adopting the above technical solution, the user temperature adjustment behavior prediction model is constructed by obtaining historical outdoor environmental parameters and user temperature adjustment behavior data, and then the current outdoor temperature and outdoor humidity are input into the user temperature adjustment behavior prediction model to obtain the predicted user temperature adjustment behavior, which is used to correct the air-conditioning target temperature, so that the operating parameters are closer to the user's real needs. This solution uses machine learning technology to learn the correlation between the user's historical temperature adjustment behavior and the historical outdoor environmental parameters, predict the temperature adjustment behavior that the user may take under the current outdoor environmental conditions, and realize the dynamic adaptation of air-conditioning parameters and outdoor environment. Compared with fixed air-conditioning parameters, this adaptive adjustment method can effectively respond to changes in outdoor temperature and humidity. When the outdoor environment changes drastically, such as sudden temperature rises and falls, the user's possible adjustment preferences are predicted by the user temperature adjustment behavior prediction model to adjust the air-conditioning in advance, avoiding the degradation of the user experience caused by environmental changes. At the same time, long-term accumulation of environmental and behavioral data and iterative update of the user temperature adjustment behavior prediction model can continuously optimize the air-conditioning control strategy and better fit the user's habits and preferences.

[0018] Optionally, constructing a user temperature adjustment behavior prediction model specifically includes: taking the historical outdoor environment parameters as sample features and the user temperature adjustment behavior data as sample labels to construct a training sample set; selecting a preset machine learning algorithm, using the training sample set for training to obtain a machine learning model for predicting user temperature adjustment behavior, and using the machine learning model as the user temperature adjustment behavior prediction model.

[0019] By adopting the above technical solution, historical outdoor environmental parameters are used as sample features, and user temperature adjustment behavior data is used as sample labels to construct a training sample set. Then, a machine learning algorithm is applied for training to obtain a user temperature adjustment behavior prediction model. By learning the mapping relationship between a large number of outdoor environmental parameters and user temperature adjustment behaviors, the user's temperature adjustment preferences under different environmental conditions can be characterized. It can evolve by continuously learning user habits and adjust the indoor environment in a more intelligent and personalized way.

[0020] In a second aspect of the present application, an intelligent air conditioning adjustment device is provided, the device comprising: an acquisition module and a processing module, wherein: the acquisition module is used to acquire multiple indoor images; the processing module is used to extract features from each of the indoor images to obtain the personnel activity status corresponding to each of the indoor images and the time point corresponding to the personnel activity status, the personnel activity status including outing status, sleeping status, sedentary status and active status; the processing module is also used to construct a personnel activity time series according to the personnel activity status and the time point corresponding to the personnel activity status; the processing module is also used to input the personnel activity time series into a preset activity status prediction model to obtain a predicted activity status; the processing module is also used to determine the air conditioning operation data corresponding to the predicted activity status according to preset operation rules, the air conditioning operation data including the air conditioning operation mode and the air conditioning target temperature; the acquisition module is also used to acquire outdoor environmental parameters, the outdoor environmental parameters including outdoor temperature and outdoor humidity; the processing module is also used to adjust the air conditioning operation data according to the outdoor environmental parameters to obtain target air conditioning operation data; the processing module is also used to determine to operate the air conditioner with the target air conditioning operation data.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By acquiring indoor images, extracting features from indoor images to obtain the activity status of personnel and the corresponding time points, constructing a time series of personnel activities, and then using the preset activity status prediction model to predict the future activity status of personnel, and determining the air conditioning operation mode and air conditioning target temperature based on the predicted activity status and preset operation rules. At the same time, outdoor environmental parameters are also obtained to adjust and optimize the determined air conditioning operation data, and finally control the air conditioning to operate with the optimized target air conditioning operation data. This solution can accurately predict the user's activity status in the future by analyzing the user's historical activity status, adjust the air conditioning in advance, make the air conditioning operation more intelligent and humanized, and the operation parameters are more in line with the user's actual needs and preferences. In addition, the operation data can be adaptively adjusted according to the outdoor environmental parameters, taking into account energy conservation and environmental protection while ensuring user experience. When the user status changes, the air conditioning operation data can also be automatically adjusted, avoiding the trouble of users frequently manually adjusting the air conditioning. While improving user comfort, the energy utilization efficiency is improved and energy waste is reduced through intelligent optimization of the air conditioning operation strategy.

[0024] 2. Preprocess the acquired indoor images, including size normalization, image noise removal, and image enhancement, to optimize image quality for subsequent analysis. Then use the target detection algorithm to detect the target person in the image, extract the key points of the human body to calculate the posture features, and judge the different activity states of the person by analyzing the angle features of the human body trunk and limbs. This method of first locating the human body and then analyzing the key point posture can accurately and efficiently judge different activity states, providing a reliable state judgment basis for subsequent activity prediction and air conditioning control.

[0025] 3. When the predicted activity state is going out, the air conditioner operation mode is off mode to save energy; when the predicted activity state is sleeping, the air conditioner enters sleep mode and sets the preset sleeping temperature; when the predicted activity state is sedentary, the cooling or heating mode is turned on and adjusted to the preset comfortable temperature; when the predicted activity state is active, the air conditioner switches to air supply mode to maintain air circulation. This air conditioner control solution based on user activity status fully considers the user's air conditioner usage needs in different activity states, automatically switches the air conditioner's working mode and temperature parameters according to the changes in the predicted activity state, and has a better user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of an intelligent air conditioning adjustment method disclosed in an embodiment of the present application; Figure 2 It is a module schematic diagram of an intelligent air conditioning regulating device disclosed in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0027] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0028] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0029] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0030] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0031] This application provides an intelligent air conditioning adjustment method, referring to Figure 1 , Figure 1 1 is a flow chart of an intelligent air conditioning adjustment method provided in an embodiment of the present application. The method is applied to a server and includes steps S101 to S108, which are as follows: Step S101: Acquire multiple indoor images.

[0032] In step S101, the server establishes a communication connection with the indoor camera and obtains real-time image data from the camera regularly or on demand. The camera can be an ordinary visible light camera or a dedicated camera with infrared or depth perception capabilities to adapt to different ambient lighting conditions and data acquisition requirements. During the data acquisition process, the server establishes a connection with the camera's communication interface (such as USB, HDMI, network interface), and sends image acquisition instructions to the camera according to a preset acquisition frequency (such as once every 5 seconds). After receiving the instruction, the camera starts to capture images and transmits the image data to the server.

[0033] In the intelligent air conditioning system, protecting user privacy is a crucial task. In order to minimize the impact on user privacy in the process of acquiring indoor images, the server can take the following improvement measures: Use low-resolution or blurred cameras. The server can use a low-resolution camera (such as less than 300,000 pixels), or blur the original image during image acquisition, so that sensitive information such as facial features and identity features in the image cannot be clearly identified, but at the same time, sufficient information can be retained for behavioral status analysis.

[0034] Step S102: extract features from each indoor image to obtain the activity status of the person corresponding to each indoor image and the time point corresponding to the activity status of the person. The activity status of the person includes the outing state, the sleeping state, the sedentary state and the active state.

[0035] In step S102, a preprocessing operation is performed on the indoor image to obtain a target indoor image, the preprocessing operation includes image size normalization, image noise removal and image enhancement; a target detection algorithm is used to detect a target person from the target indoor image; the human body key points of the target person are extracted, and the set relationship between each human body key point is calculated to obtain posture features, the posture features include torso angle features and limb angle features; the activity state of the person is determined based on the torso angle features and limb angle features.

[0036] Specifically, after receiving the indoor image, the server first performs a series of preprocessing operations on the indoor image to improve the accuracy and efficiency of subsequent feature extraction. The preprocessing operations include image size normalization, image noise removal, and image enhancement; among them, image size normalization is to uniformly scale or crop indoor images of different resolutions and sizes to a specified standard size (such as 640x480 pixels) to facilitate subsequent feature extraction; image noise removal uses image filtering algorithms (such as median filtering and Gaussian filtering) to denoise the indoor image, reduce noise points, burrs and other interference information in the image, and improve image quality; image enhancement uses image enhancement technology (such as histogram equalization and contrast stretching) to optimize the image, so that the target person and key features in the image are more prominent and clear. After the preprocessing steps, the server can obtain the target indoor image, and the server performs target person detection on the target indoor image, and locates and extracts the area where the person is located from the image. The target detection algorithm uses the YOLO algorithm based on deep learning. The YOLO algorithm learns the visual characteristics and spatial distribution of the human body by training a large amount of human image data, so that it can quickly and accurately detect human targets in new images. The YOLO algorithm divides the target indoor image into several grids, predicts several bounding boxes for each grid, and then deletes redundant bounding boxes through non-maximum suppression, and finally determines the location of the target person.

[0037] For the detected target person area, the server further extracts the key point information of the human body, such as the position and posture of the head, torso, and limbs. After obtaining the target, the server further extracts the key point features of the human body. The key points of the human body usually refer to some joints and endpoints of the human body, such as the top of the head, neck, shoulders, elbows, wrists, hips, knees, and ankles. The server uses the OpenPose human key point extraction algorithm. The OpenPose algorithm learns the spatial relationship between the human skeletal structure and joints by training the human posture dataset, so that the coordinates of the key points can be accurately located in the target person image.

[0038] After extracting the key points of the human body, the server needs to calculate the set relationship between each key point to obtain the human posture features. Here, two types of features are mainly calculated: trunk angle features and limb angle features. The trunk angle feature reflects the degree of inclination of the human trunk, which can be obtained by calculating the angle between the line connecting the neck key point and the hip key point and the vertical direction. The limb angle feature reflects the degree of bending of the human limbs, which can be obtained by calculating the angle between the lines connecting the joint points of the upper arm, lower arm, thigh, and calf. For example, the angle between the two vectors formed by the shoulder key point, elbow key point, and wrist key point can be calculated as the angle feature of the upper arm. By calculating these angle features, the server can obtain a quantitative description of the human posture. The server determines the activity status of the person based on the trunk angle features and limb angle features.

[0039] In a possible implementation, the activity state of a person is determined based on the torso angle features and the limb angle features, specifically including: when the torso angle features represent that the torso of the target person is perpendicular to the ground, and the limb angle features represent that the limbs of the target person are in an extended state, the activity state of the person is determined to be an active state; when the torso angle features represent that the torso of the target person is perpendicular to the ground, and the limb angle features represent that the limbs of the target person are in a bent state, the activity state of the person is determined to be a sedentary state; when the torso angle features represent that the torso of the target person is at a preset angle to the ground, and the limb angle features represent that the limbs of the target person are all in a horizontal position, the activity state of the person is determined to be a sleeping state; when the target person is not detected from the target indoor image within a preset time period, the activity state of the person is determined to be an outing state.

[0040] Specifically, the activity status of a person includes an active state, a sedentary state, a sleeping state, and an outing state; for the judgment of the activity status, the server analyzes the angle characteristics of the target person's trunk to determine whether it is perpendicular to the ground. The server achieves this by calculating the angle between the central axis of the trunk and the ground normal vector. When the angle is close to 90 degrees (such as between 85 degrees and 95 degrees), the trunk can be considered to be perpendicular to the ground. At the same time, the server analyzes the angle characteristics of the target person's limbs to determine whether it is in an extended state. The server achieves this by calculating the angle between the line between the joints of the limbs and the central axis of the trunk. When the angle is close to 180 degrees (such as between 170 degrees and 190 degrees), the limbs can be considered to be in an extended state. When the trunk is perpendicular to the ground and the limbs are in an extended state, the server can determine that the person is currently in an active state, such as walking.

[0041] For the judgment of sedentary state, the server analyzes the target person's torso angle characteristics to determine whether it is perpendicular to the ground. Similar to the judgment of activity state, when the angle between the central axis of the torso and the ground normal vector is close to 90 degrees (such as between 85 degrees and 95 degrees), the torso can be considered to be perpendicular to the ground. The server analyzes the angle characteristics of the target person's limbs to determine whether they are in a bent state. The server achieves this by calculating the angle between the connecting line between the joints of the limbs and the central axis of the torso. When the angle is significantly less than 180 degrees (such as between 90 degrees and 150 degrees), the limbs can be considered to be in a bent state. When the torso is perpendicular to the ground and the limbs are in a bent state, the server can determine that the person is currently in a sedentary state, such as doing sedentary activities such as office work, study, and watching TV.

[0042] For the judgment of sleeping state, the server analyzes the target person's torso angle features to determine whether it presents a preset angle with the ground. The server achieves this by calculating the angle between the torso center axis and the ground normal vector. When the angle is close to 0 degrees or 180 degrees (such as -10 degrees to 10 degrees, or between 170 degrees and 190 degrees), the torso can be considered to be horizontal with the ground. The server analyzes the target person's limb angle features to determine whether they are all in a horizontal position. The server achieves this by calculating the angle between the line between the limb joints and the ground normal vector. When the angles are close to 0 degrees or 180 degrees (such as -10 degrees to 10 degrees, or between 170 degrees and 190 degrees), the limbs can be considered to be in a horizontal position. When the torso is horizontal with the ground and the limbs are all in a horizontal position, the server can determine that the person is currently in a sleeping state.

[0043] For out-of-town status judgment, the server will continuously monitor the target indoor image within a preset time period (such as 30 minutes) and determine whether there is a person through the target person detection algorithm. If the target person cannot be detected from the image within the preset time period (such as 30 consecutive minutes), the server can determine that the person is currently out of town.

[0044] Step S103: constructing a personnel activity time series according to the personnel activity states and the time points corresponding to the personnel activity states.

[0045] In step S103, the server first reads the results of personnel activity status recognition within a period of time (such as the past week) from the database, including the activity status label corresponding to each time point (such as "active state", "sleeping state", etc.) and timestamp information (such as "2023-05-20 08:30:00"). These data are usually arranged in chronological order with time as the primary key and activity state as the value. The server constructs a complete personnel activity time series according to the order of timestamps. The personnel activity time series records the activity status information corresponding to each time point at a fixed time interval (such as 1 minute), forming a continuous state change sequence, such as "...active state, active state, sedentary state, sedentary state, sleeping state, sleeping state...".

[0046] Step S104: inputting the personnel activity time series into a preset activity state prediction model to obtain a predicted activity state.

[0047] Before step S104, the method also includes: obtaining time series sample data, the time series sample data includes a historical activity state sequence and a duration corresponding to the historical activity state sequence; constructing a seq2seq model, the seq2seq model includes an encoder and a decoder, the encoder is used to encode the input historical activity state sequence, and the decoder is used to predict the activity state of the personnel at the next moment; using the time series sample data to train the seq2seq model to obtain a preset activity state prediction model.

[0048] Specifically, the server reads the results of identifying the activity status of people within a certain time range (such as the past month) from the database as time series sample data. Each time series sample data consists of two parts: a historical activity state sequence, which records the changes in the activity status of people within the past period of time (such as 1 hour); and a duration sequence, which records the duration of each activity state. For example, a sample data can be expressed as: Historical activity state sequence: ["sedentary state", "sedentary state", "active state", "active state", "sleeping state"] Duration sequence: [20min, 10min, 15min, 5min, 10min] The server divides the acquired time series sample data into training set, validation set and test set according to a certain ratio. The training set is used for model parameter learning, the validation set is used for model hyperparameter tuning, and the test set is used for model performance evaluation. The server builds a preset activity state prediction model based on the Seq2Seq (Sequence-to-Sequence) model to predict the activity state change trend in the future based on the activity state sequence in the past. The Seq2Seq model consists of two parts: an encoder, which is responsible for encoding the input historical activity state sequence into a vector representation of a fixed length; and a decoder, which is responsible for gradually generating the output future activity state sequence based on the encoding vector. The encoder uses a recurrent neural network to input the historical activity state sequence one by one, and obtains an encoding vector containing historical information at the last time step. The decoder also uses a recurrent neural network, with the encoding vector as the initial state, to gradually predict and generate the future activity state sequence. At each time step, the decoder generates the activity state at the next moment based on the current hidden state and the activity state predicted at the previous moment. In addition, the server can also introduce an attention mechanism between the encoder and the decoder, so that the decoder can adaptively focus on the output of the encoder at different time steps when generating the activity state at each moment, thereby improving the accuracy of the prediction. The server uses the divided training set data to train the constructed Seq2Seq model and optimize the parameters of the model so that it can predict the future activity state change trend as accurately as possible based on the historical activity state sequence.

[0049] During the training process, the server sets a loss function (such as cross entropy loss) to measure the difference between the activity state sequence predicted by the model and the actual activity state sequence, and uses the back propagation algorithm and optimizer (such as Adam) to minimize the loss function and adjust the model parameters. During the training process, the server will regularly evaluate the performance of the model on the validation set, and dynamically adjust the learning rate and regularization coefficient based on the evaluation results to prevent the model from overfitting or underfitting. After multiple rounds of iterative training, the server obtains a performance-optimized Seq2Seq activity state prediction model (i.e., the preset activity state prediction model), which can be used for actual personnel activity state prediction tasks.

[0050] In step S104, the server reads the personnel activity status recognition results within the latest period of time (such as the past 1 hour) from the database, and constructs a personnel activity time series as the input data of the preset activity status prediction model. The server inputs the personnel activity time series into the preset activity status prediction model, starts the forward reasoning process of the model, and automatically predicts and generates the activity state sequence within a period of time in the future. During the reasoning process, the encoder part of the preset activity state prediction model reads the input personnel activity state sequence, gradually updates the hidden state, and outputs a coding vector containing historical information at the last time step. Next, the decoder part of the preset activity state prediction model uses the coding vector as the initial state and gradually generates the predicted future activity state sequence. At each time step, the decoder generates the probability distribution of each activity state at the next moment based on the current hidden state and the activity state predicted at the previous moment, and selects the predicted activity state with the highest probability as the prediction result.

[0051] Step S105: determining the air-conditioning operation data corresponding to the predicted activity state according to the preset operation rules, where the air-conditioning operation data includes the air-conditioning operation mode and the air-conditioning target temperature.

[0052] In step S105, when the predicted activity state is the outing state, the air conditioning operation mode is determined to be the off mode; when the predicted activity state is the sleeping state, the air conditioning operation mode is determined to be the sleeping mode, and the air conditioning target temperature is set to the preset sleeping temperature; when the predicted activity state is the sedentary state, the air conditioning operation mode is determined to be the cooling mode or the heating mode, and the air conditioning target temperature is set to the preset comfort temperature; when the predicted activity state is the active state, the air conditioning operation mode is determined to be the air supply mode.

[0053] Specifically, when the server predicts that the user's activity state is out of the room, it indicates that the user is not currently in the room and does not need to maintain a comfortable temperature in the room. The server sets the operation mode of the air conditioner to the off mode, that is, completely stops the operation of the air conditioner to avoid unnecessary energy waste. When the server predicts that the user's activity state is in the sleep state, it indicates that the user is currently resting, has high requirements for temperature comfort, and is more sensitive to noise. The server sets the operation mode of the air conditioner to the sleep mode, that is, it runs at a lower wind speed and noise, provides stable and uniform air supply, and creates a quiet and comfortable sleeping environment. The server sets the target temperature of the air conditioner to a preset sleep temperature, which is usually 2-3 degrees Celsius lower than the normal ambient temperature, such as 26 degrees Celsius. The preset sleep temperature is the optimal sleep temperature range obtained based on a large number of user usage data and feedback, as well as scientific research on human comfort, and this application does not limit this. When the server predicts that the user's activity state is a sedentary state, it indicates that the user is currently performing a sedentary static activity, such as office, study, watching TV, etc., has high requirements for temperature comfort, and hopes to maintain a certain amount of air circulation.

[0054] The server sets the operating mode of the air conditioner to cooling mode or heating mode. The specific mode to be selected depends on the difference between the current indoor and outdoor temperatures and the user's historical preferences. When the indoor temperature is higher than the outdoor temperature and higher than the user's upper limit of comfort temperature (such as 28 degrees Celsius), the server will start the cooling mode to reduce the room temperature to a comfortable temperature range. When the indoor temperature is lower than the outdoor temperature and lower than the user's lower limit of comfort temperature (such as 20 degrees Celsius), the server will start the heating mode to raise the room temperature to a comfortable temperature range. The server sets the target temperature of the air conditioner to a preset comfort temperature, which is usually between 22-26 degrees Celsius and is fine-tuned according to the user's personal preferences and historical settings. The preset comfort temperature is the optimal sedentary comfort temperature range based on physiological research on human thermal balance, as well as a large amount of user usage data and feedback. It can be adjusted according to actual conditions, and this application does not limit this. When the user activity state predicted by the server is active, it indicates that the user is currently performing indoor activities of a certain intensity, such as housework, indoor exercise, etc., which generates more heat and has higher requirements for air quality and circulation. The server sets the air conditioning operation mode to air supply mode, which enhances indoor air circulation by supplying air at a higher wind speed, promptly discharges carbon dioxide, sweat, etc. generated by user activities, and keeps the indoor air fresh and dry.

[0055] Step S106: Acquire outdoor environmental parameters, which include outdoor temperature and outdoor humidity.

[0056] In step S106, during the installation and deployment of the intelligent air conditioning control system, it is necessary to install a temperature sensor and a humidity sensor at a suitable location outdoors to collect outdoor environmental parameters in real time. The server obtains the outdoor temperature through the temperature sensor and the outdoor humidity through the humidity sensor.

[0057] Step S107: adjusting the air-conditioning operation data according to the outdoor environmental parameters to obtain target air-conditioning operation data.

[0058] In step S107, historical outdoor environmental parameters and corresponding user temperature adjustment behavior data are obtained, and the user temperature adjustment behavior data includes the user's temperature adjustment time, temperature adjustment amplitude and target temperature after temperature adjustment; a user temperature adjustment behavior prediction model is constructed, and the user temperature adjustment behavior prediction model is used to predict the user's temperature adjustment behavior according to the current outdoor environmental parameters; the outdoor temperature and outdoor humidity are input into the user temperature adjustment behavior prediction model to obtain a predicted temperature adjustment amplitude; the air-conditioning target temperature is adjusted according to the predicted temperature adjustment amplitude to obtain target air-conditioning operation data.

[0059] Specifically, the server obtains historical outdoor environmental parameters and corresponding user temperature adjustment behavior data as the data basis for training the user temperature adjustment behavior prediction model. Historical outdoor environmental parameters can be obtained from the meteorological department or self-built environmental monitoring equipment, mainly including outdoor temperature and humidity indicators. User temperature adjustment behavior data can be obtained by recording the user's actual operations, mainly including the user's temperature adjustment time, temperature adjustment amplitude, and target temperature after temperature adjustment. For example, the server can record the time point of each time the user adjusts the air-conditioning temperature, the temperature values ​​before and after the temperature adjustment, and the temperature adjustment amplitude (such as +1°C, -2°C, etc.).

[0060] In one possible implementation, a user temperature adjustment behavior prediction model is constructed, specifically including: taking historical outdoor environmental parameters as sample features and user temperature adjustment behavior data as sample labels to construct a training sample set; selecting a preset machine learning algorithm, using the training sample set for training, obtaining a machine learning model for predicting user temperature adjustment behavior, and using the machine learning model as the user temperature adjustment behavior prediction model.

[0061] Specifically, the server prepares a data set for training the machine learning model, namely, a training sample set. The training sample set consists of two parts: sample features and sample labels. Here, sample features refer to factors that affect the user's temperature adjustment behavior, mainly historical outdoor environmental parameters, such as outdoor temperature and outdoor humidity; sample labels refer to the user's actual temperature adjustment behavior under specific environmental conditions, including temperature adjustment time, temperature adjustment amplitude, target temperature after temperature adjustment, etc. The server collects and organizes historical data over a period of time, matches the outdoor environmental parameters with the corresponding user temperature adjustment behavior, and constructs a complete training sample. For example, if the server collects that the user lowers the air conditioning temperature by 3°C when the outdoor temperature is 30°C and the humidity is 50%, a training sample can be constructed, in which the sample features are 30°C and 50%, and the sample label is -3°C. In this way, the server can obtain a training sample set with a large amount of data covering different environmental conditions and user behaviors. Next, the server selects a suitable machine learning algorithm to build a user temperature adjustment behavior prediction model. In this application, a neural network algorithm is used to construct a user streak behavior prediction model. After selecting a machine learning algorithm, the server uses a training sample set to train the algorithm to obtain the final user temperature adjustment behavior prediction model. Specifically, the server inputs the training sample set into the selected machine learning algorithm, and through continuous learning and optimization, automatically extracts the laws and patterns of user temperature adjustment behavior from the training sample set, and encapsulates these laws and patterns in a mathematical model. The training process usually requires multiple iterations, and each iteration updates the parameters of the model so that it can better fit the training data. Finally, the server integrates the trained machine learning model into the intelligent air conditioning adjustment system as a user temperature adjustment behavior prediction model.

[0062] After obtaining the trained user temperature adjustment behavior prediction model, the server can use the model to intelligently adjust the air conditioning operation data according to the current outdoor environmental parameters. Specifically, the server inputs the currently collected outdoor temperature and outdoor humidity into the user temperature adjustment behavior prediction model, and the model predicts the temperature adjustment range that the user may make in the current environment. For example, the current outdoor temperature is 35°C and the humidity is 60%. The server inputs these two values ​​into the user temperature adjustment behavior prediction model. The user temperature adjustment behavior prediction model may predict that the user will lower the air conditioning temperature by 2°C. The adjusted air conditioning target temperature, together with other air conditioning operation parameters (such as air conditioning operation mode), constitute the final target air conditioning operation data.

[0063] Step S108: Determine to operate the air conditioner according to the target air conditioner operation data.

[0064] In step S108, the server generates optimized target air-conditioning operation data according to the user temperature adjustment behavior prediction model in step S107 and the current outdoor environmental parameters. The server encapsulates the target air-conditioning operation data into control instructions and sends them to the smart air-conditioning regulator in the user's home through the network (such as Wi-Fi, mobile network). After receiving the control instructions sent by the server, the air-conditioning controller parses the target operating parameters and converts them into control signals that can be directly executed by the air-conditioning equipment. The air-conditioning controller sends the control signal converted from the target operating parameters to the air-conditioning equipment through wired or wireless means (such as infrared, WIFI, Bluetooth, etc.). After receiving the control signal, the microprocessor of the air-conditioning equipment adjusts the working state of the air-conditioning compressor, fan, electronic expansion valve and other components according to the instructions in the signal to achieve control of the cooling / heating power and the air supply temperature.

[0065] For example, if the target air conditioning operation data requires the air conditioner to operate in cooling mode and adjust the indoor temperature to 26°C, the air conditioning equipment will start the compressor, compress the refrigerant and send it to the heat exchanger of the indoor unit. At the same time, the indoor unit fan will be controlled to run at a medium speed to send cold air into the room until the indoor temperature reaches 26°C and stabilizes near this temperature.

[0066] Reference Figure 2The present application also provides an intelligent air conditioning adjustment device, which is a server, and the server includes an acquisition module 201 and a processing module 202, wherein: the acquisition module 201 is used to acquire multiple indoor images; the processing module 202 is used to extract features from each indoor image to obtain the personnel activity state corresponding to each indoor image and the time point corresponding to the personnel activity state, and the personnel activity state includes an outing state, a sleeping state, a sedentary state, and an active state; the processing module 202 is also used to construct a personnel activity time series according to the personnel activity state and the time point corresponding to the personnel activity state; the processing module 202 is also used to input the personnel activity time series into a preset activity state prediction model to obtain a predicted activity state; the processing module 202 is also used to determine the air conditioning operation data corresponding to the predicted activity state according to the preset operation rules, and the air conditioning operation data includes an air conditioning operation mode and an air conditioning target temperature; the acquisition module 201 is also used to acquire outdoor environmental parameters, and the outdoor environmental parameters include outdoor temperature and outdoor humidity; the processing module 202 is also used to adjust the air conditioning operation data according to the outdoor environmental parameters to obtain target air conditioning operation data; the processing module 202 is also used to determine to operate the air conditioner with the target air conditioning operation data.

[0067] In a possible implementation, the processing module 202 performs feature extraction on each indoor image to obtain the activity status of the person corresponding to each indoor image, specifically including: the processing module 202 performs preprocessing operations on the indoor images to obtain a target indoor image, the preprocessing operations include image size normalization, image noise removal and image enhancement; the processing module 202 uses a target detection algorithm to detect a target person from the target indoor image; the processing module 202 extracts the human body key points of the target person, and calculates the set relationship between each human body key point to obtain posture features, the posture features include torso angle features and limb angle features; the processing module 202 determines the activity status of the person based on the torso angle features and limb angle features.

[0068] In a possible implementation, the processing module 202 determines the activity state of the person based on the torso angle characteristics and the limb angle characteristics, specifically including: when the torso angle characteristics represent that the torso of the target person is perpendicular to the ground, and the limb angle characteristics represent that the limbs of the target person are in an extended state, the processing module 202 determines that the activity state of the person is an active state; when the torso angle characteristics represent that the torso of the target person is perpendicular to the ground, and the limb angle characteristics represent that the limbs of the target person are in a bent state, the processing module 202 determines that the activity state of the person is a sedentary state; when the torso angle characteristics represent that the torso of the target person is at a preset angle to the ground, and the limb angle characteristics represent that the limbs of the target person are in a horizontal position, the processing module 202 determines that the activity state of the person is a sleeping state; when the target person is not detected from the target indoor image within a preset time period, the processing module 202 determines that the activity state of the person is an outing state.

[0069] In a possible implementation, the processing module 202 inputs the personnel activity time series into a preset activity status prediction model to obtain the predicted activity status. The method further includes: the acquisition module 201 acquires time series sample data, the time series sample data includes a historical activity status sequence and a duration corresponding to the historical activity status sequence; the processing module 202 constructs a seq2seq model, the seq2seq model includes an encoder and a decoder, the encoder is used to encode the input historical activity status sequence, and the decoder is used to predict the personnel activity status at the next moment; the processing module 202 uses the time series sample data to train the seq2seq model to obtain a preset activity status prediction model.

[0070] In a possible implementation, the processing module 202 determines the air conditioning operation data corresponding to the predicted activity state according to preset operation rules, specifically including: when the predicted activity state is an outing state, the processing module 202 determines that the air conditioning operation mode is an off mode; when the predicted activity state is a sleeping state, the processing module 202 determines that the air conditioning operation mode is a sleeping mode, and sets the air conditioning target temperature to a preset sleeping temperature; when the predicted activity state is a sedentary state, the processing module 202 determines that the air conditioning operation mode is a cooling mode or a heating mode, and sets the air conditioning target temperature to a preset comfort temperature; when the predicted activity state is an active state, the processing module 202 determines that the air conditioning operation mode is an air supply mode.

[0071] In a possible implementation, the processing module 202 adjusts the air-conditioning operation data according to the outdoor environmental parameters to obtain the target air-conditioning operation data, specifically including: the acquisition module 201 acquires the historical outdoor environmental parameters and the corresponding user temperature adjustment behavior data, the user temperature adjustment behavior data includes the user's temperature adjustment time, temperature adjustment amplitude and the target temperature after temperature adjustment; the processing module 202 constructs a user temperature adjustment behavior prediction model, and the user temperature adjustment behavior prediction model is used to predict the user's temperature adjustment behavior according to the current outdoor environmental parameters; the processing module 202 inputs the outdoor temperature and outdoor humidity into the user temperature adjustment behavior prediction model to obtain the predicted temperature adjustment amplitude; the processing module 202 adjusts the air-conditioning target temperature according to the predicted temperature adjustment amplitude to obtain the target air-conditioning operation data.

[0072] In one possible implementation, the processing module 202 constructs a user temperature adjustment behavior prediction model, specifically including: the processing module 202 uses historical outdoor environmental parameters as sample features and user temperature adjustment behavior data as sample labels to construct a training sample set; the processing module 202 selects a preset machine learning algorithm, uses the training sample set for training, obtains a machine learning model for predicting user temperature adjustment behavior, and uses the machine learning model as a user temperature adjustment behavior prediction model.

[0073] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0074] The present application also provides an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0075] The communication bus 302 is used to realize the connection and communication between these components.

[0076] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0077] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0078] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0079] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of an intelligent air conditioning adjustment method.

[0080] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call an application program for an intelligent air conditioning regulating device stored in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0081] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments.

[0082] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0086] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0087] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0088] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An intelligent air conditioning adjustment method, characterized in that: The method comprises: Acquire multiple indoor images; Extracting features from each of the indoor images to obtain the activity status of a person corresponding to each of the indoor images and the time point corresponding to the activity status of the person, wherein the activity status of the person includes an outing state, a sleeping state, a sedentary state, and an active state; Constructing a personnel activity time series according to the personnel activity status and the time points corresponding to the personnel activity status; Inputting the personnel activity time series into a preset activity state prediction model to obtain a predicted activity state; Determining, according to a preset operation rule, air conditioning operation data corresponding to the predicted activity state, the air conditioning operation data including an air conditioning operation mode and an air conditioning target temperature; Acquiring outdoor environmental parameters, wherein the outdoor environmental parameters include outdoor temperature and outdoor humidity; According to the outdoor environment parameters, the air conditioning operation data is adjusted to obtain target air conditioning operation data; It is determined to operate the air conditioner according to the target air conditioner operation data.

2. The method according to claim 1, characterized in that The extracting features of each of the indoor images to obtain the activity status of the personnel corresponding to each of the indoor images specifically includes: Performing a preprocessing operation on the indoor image to obtain a target indoor image, wherein the preprocessing operation includes image size normalization, image noise removal, and image enhancement; Detecting a target person from the target indoor image using a target detection algorithm; Extracting the key points of the human body of the target person, and calculating the set relationship between each of the key points of the human body to obtain posture features, wherein the posture features include trunk angle features and limb angle features; The activity state of the person is determined according to the torso angle characteristics and the limb angle characteristics.

3. The method according to claim 2, characterized in that The determining the activity state of the person according to the torso angle features and the limb angle features specifically includes: When the trunk angle feature indicates that the trunk of the target person is perpendicular to the ground, and the limb angle feature indicates that the limbs of the target person are in an extended state, determining that the activity state of the person is an active state; When the trunk angle feature indicates that the trunk of the target person is perpendicular to the ground, and the limb angle feature indicates that the limbs of the target person are in a bent state, it is determined that the activity state of the person is a sedentary state; When the trunk angle feature indicates that the trunk of the target person is at a preset angle to the ground, and the limb angle feature indicates that the limbs of the target person are in a horizontal position, it is determined that the activity state of the person is a sleeping state; When the target person is not detected from the target indoor image within a preset time period, it is determined that the activity state of the person is an outing state.

4. The method according to claim 1, characterized in that: Before inputting the personnel activity time series into a preset activity state prediction model to obtain a predicted activity state, the method further includes: Acquire time series sample data, wherein the time series sample data includes a historical activity state sequence and a duration corresponding to the historical activity state sequence; Constructing a seq2seq model, wherein the seq2seq model includes an encoder and a decoder, wherein the encoder is used to encode an input historical activity state sequence, and the decoder is used to predict the activity state of a person at the next moment; The seq2seq model is trained using the time series sample data to obtain the preset activity state prediction model.

5. The method according to claim 1, characterized in that The determining, according to the preset operation rules, the air conditioning operation data corresponding to the predicted activity state specifically includes: When the predicted activity state is an outing state, determining the air conditioning operation mode to be an off mode; When the predicted activity state is a sleeping state, determining that the air-conditioning operation mode is a sleeping mode, and setting the air-conditioning target temperature to a preset sleeping temperature; When the predicted activity state is a sedentary state, determining that the air conditioner operation mode is a cooling mode or a heating mode, and setting the air conditioner target temperature to a preset comfort temperature; When the predicted activity state is the activity state, the air conditioning operation mode is determined to be the air supply mode.

6. The method according to claim 1, characterized in that The adjusting the air-conditioning operation data according to the outdoor environment parameters to obtain target air-conditioning operation data specifically includes: Acquire historical outdoor environmental parameters and corresponding user temperature adjustment behavior data, wherein the user temperature adjustment behavior data includes the user's temperature adjustment time, temperature adjustment amplitude, and target temperature after temperature adjustment; Constructing a user temperature adjustment behavior prediction model, wherein the user temperature adjustment behavior prediction model is used to predict the user temperature adjustment behavior according to current outdoor environment parameters; Inputting the outdoor temperature and the outdoor humidity into the user temperature adjustment behavior prediction model to obtain a predicted temperature adjustment range; The air-conditioning target temperature is adjusted according to the predicted temperature adjustment amplitude to obtain the target air-conditioning operation data.

7. The method according to claim 6, characterized in that The step of constructing a user temperature adjustment behavior prediction model specifically includes: The historical outdoor environmental parameters are used as sample features and the user temperature adjustment behavior data are used as sample labels to construct a training sample set; A preset machine learning algorithm is selected, and the training sample set is used for training to obtain a machine learning model for predicting the user's temperature adjustment behavior, and the machine learning model is used as the user's temperature adjustment behavior prediction model.

8. An intelligent air conditioning regulating device, characterized in that: The device comprises an acquisition module (201) and a processing module (202), wherein: An acquisition module (201), used for acquiring a plurality of indoor images; A processing module (202) is used to extract features from each of the indoor images to obtain the activity status of a person corresponding to each of the indoor images and the time point corresponding to the activity status of the person, wherein the activity status of the person includes an outing state, a sleeping state, a sedentary state, and an active state; The processing module (202) is further used to construct a personnel activity time series according to the personnel activity status and the time points corresponding to the personnel activity status; The processing module (202) is further used to input the personnel activity time series into a preset activity state prediction model to obtain a predicted activity state; The processing module (202) is further used to determine the air-conditioning operation data corresponding to the predicted activity state according to a preset operation rule, wherein the air-conditioning operation data includes an air-conditioning operation mode and an air-conditioning target temperature; The acquisition module (201) is further used to acquire outdoor environmental parameters, wherein the outdoor environmental parameters include outdoor temperature and outdoor humidity; The processing module (202) is further used to adjust the air-conditioning operation data according to the outdoor environmental parameters to obtain target air-conditioning operation data; The processing module (202) is further used to determine whether to operate the air conditioner according to the target air conditioner operation data.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images