Indoor environment control method, electronic equipment and storage medium

Abstract

The invention provides an indoor environment control method, electronic equipment and a storage medium. The method is applied to an indoor environment control system. The system comprises an image acquisition device; the method comprises the steps that an image collection device is used for collecting an indoor environment image to obtain image data, and the image data comprises at least one frame of environment image; based on the image data, parameter self-adjusting operation is executed, specifically, the image data are recognized through an image recognition algorithm to obtain indoor environment information, the environment information comprises indoor personnel number information and / or indoor personnel action feature information, and the personnel action feature information is used for representing the activity mean value of indoor personnel; inputting the environment information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result; adjusting control parameters of at least part of indoor equipment at least based on the environmental parameter adjustment result; wherein at least part of the equipment is used for controlling the indoor environment state. The method is helpful for improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to an indoor environment control method, electronic equipment and storage medium. Background Art

[0002] With the development of technology and the increasing demand for intelligent building management, traditional indoor environmental control methods have gradually shown many shortcomings. Specifically, traditional environmental control systems mainly rely on preset schedules or require manual intervention to adjust settings. This method lacks real-time response capabilities and cannot make timely adjustments based on actual usage, often resulting in unnecessary energy consumption and failure to respond to indoor changes in a timely manner, reducing user experience.

[0003] In view of this, this application is hereby filed. Summary of the invention

[0004] The present application is proposed in consideration of the above-mentioned problems. According to one aspect of the present application, there is provided an indoor environment control method for an indoor environment control system, the indoor environment control system comprising an image acquisition device for acquiring an indoor environment image; the method comprising: using the image acquisition device to acquire an indoor environment image to obtain image data, the image data comprising at least one frame of the environment image; based on the image data, performing the following parameter self-adjustment operations: using an image recognition algorithm to recognize the image data to obtain indoor environment information, the environment information comprising indoor personnel quantity information and / or indoor personnel motion feature information, the personnel motion feature information being used to represent the activity mean of the indoor personnel; inputting the environment information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result; at least based on the environment parameter adjustment result, adjusting the control parameters of at least part of the equipment in the room; wherein the at least part of the equipment is equipment for controlling the indoor environment state.

[0005] Exemplarily, the image data includes a continuous multi-frame environment image; the environmental information includes personnel quantity information corresponding one-to-one to the multi-frame environment image; the inputting of the environmental information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result includes: performing the following steps through the environment parameter adjustment model: determining the change in the number of personnel in the room based on the personnel quantity information corresponding one-to-one to the multi-frame environment image; generating a first environment parameter adjustment result according to the change in the number of personnel; or, the image data includes a continuous multi-frame environment image; the environmental information includes the personnel motion feature information; the inputting of the environmental information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result includes: performing the following steps through the environment parameter adjustment model: comparing the personnel motion feature information with a preset activity mean; comparing the personnel motion feature information with the preset activity mean according to the comparison between the personnel motion feature information and the preset activity mean; generating a first environment parameter adjustment result .... The second environmental parameter adjustment result is generated based on the comparison result of the preset activity mean; or, the image data includes a continuous multi-frame environmental image; the environmental information includes the number of people information and the personnel motion feature information corresponding to the multi-frame environmental image one-to-one; the environmental information is input into the pre-trained environmental parameter adjustment model to obtain the environmental parameter adjustment result, including: through the environmental parameter adjustment model, the following steps are performed: based on the one-to-one corresponding number of people information of the multi-frame environmental image, the change of the number of people in the room is determined; according to the change of the number of people, a first environmental parameter adjustment result is generated; the personnel motion feature information is compared with the preset activity mean; according to the comparison result of the personnel motion feature information and the preset activity mean, a second environmental parameter adjustment result is generated; combining the first environmental parameter adjustment result and the second environmental parameter adjustment result, a final environmental parameter adjustment result is generated.

[0006] Exemplarily, the combining of the first environmental parameter adjustment result and the second environmental parameter adjustment result to generate the final environmental parameter adjustment result includes: when the first environmental parameter adjustment result and the second environmental parameter adjustment result include the same type of environmental parameters, determining that the environmental parameters of this type in the second environmental parameter adjustment result are the environmental parameters of this type in the final environmental parameter adjustment result.

[0007] Exemplarily, the adjusting control parameters of at least part of the equipment in the room at least based on the environmental parameter adjustment result includes: adjusting the control parameters of at least part of the equipment based on the environmental adjustment parameters corresponding to at least part of the equipment included in the environmental parameter adjustment result; or, the indoor environment control system also includes a temperature sensor, and the adjusting control parameters of at least part of the equipment in the room at least based on the environmental parameter adjustment result includes: adjusting the control parameters of at least part of the equipment based on temperature information detected by the temperature sensor and the environmental adjustment parameters corresponding to at least part of the equipment included in the environmental parameter adjustment result.

[0008] Exemplarily, the method also includes: determining whether the image data has smoke features; performing a smoke response operation at least when the image data has smoke features; wherein the smoke response operation includes outputting an alarm message, and / or, at least part of the equipment includes a fresh air system, and the smoke response operation includes controlling the fresh air system to purify the smoke.

[0009] Preferably, the determining whether the image data has smoke features includes: for each frame of environmental image in the image data, performing color analysis and texture analysis on the environmental image to obtain color features and texture features of the environmental image; comparing the color features of the environmental image with preset color features; comparing the texture features of the environmental image with preset texture features; when the color features of the environmental image are the same as the preset color features, and the texture features of the environmental image are the same as the preset texture features, determining that the image data has smoke features.

[0010] Preferably, the image data includes a plurality of continuous frames of environment images; and the determining whether the image data has smoke features includes: using a motion detection algorithm to detect whether the image data has smoke features.

[0011] Exemplarily, the indoor environment control system includes a smoke sensor; performing a smoke response operation at least when smoke features exist in the image data includes: performing the smoke response operation when smoke features exist in the image data and / or the smoke sensor detects smoke.

[0012] Exemplarily, the method also includes: performing the following interactive parameter adjustment operations: determining the real-time action contained in the image data; comparing the real-time action with the preset action in the preset action library; when the real-time action is the same as any preset action in the preset action library, generating a control instruction corresponding to the preset action; based on the control instruction, adjusting the control parameters of at least part of the device.

[0013] Exemplarily, the indoor environment control system has multiple working modes, including automatic mode, manual mode and preset scene mode; wherein, the control parameters of at least part of the equipment in the room are adjusted based at least on the environmental parameter adjustment result when the indoor environment control system is in the automatic mode, or the parameter self-adjustment operation is performed when the indoor environment control system is in the automatic mode.

[0014] Preferably, the adjusting of control parameters of at least part of the indoor equipment based at least on the environmental parameter adjustment result is performed when the indoor environment control system is in the automatic mode; when the indoor environment control system is in the manual mode, the method further includes: generating parameter adjustment suggestions based on the environmental parameter adjustment result; and sending the parameter adjustment suggestions to the user terminal.

[0015] Preferably, when the indoor environment control system is in the preset scene mode, the method further includes: identifying the current scene; generating an environmental parameter adjustment instruction corresponding to the current scene; and adjusting the control parameters of at least part of the equipment based on the environmental parameter adjustment instruction.

[0016] According to another aspect of the present application, an electronic device is provided, including a processor and a memory, wherein a computer program is stored in the memory, and the processor is used to execute the computer program to implement the above method.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, storing a computer program / instruction, and the computer program / instruction implements the above method when executed by a processor.

[0018] In the above technical solution, the indoor environmental information can be determined based on the indoor image data, and the control parameters of at least part of the indoor equipment can be adjusted based on the indoor environmental information to achieve control of the indoor environment. This environmental control method can adjust the indoor environmental parameters in real time and dynamically according to the number of people in the room and / or the characteristics of the people's movements, which can ensure that the indoor environment meets the needs of users, improve the comfort of users, and help avoid energy waste and improve energy efficiency. In short, this solution can solve the problems of poor flexibility and untimely response of indoor environmental control solutions in related technologies, and help to achieve intelligent and automated indoor environmental control.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0021] Figure 1 A schematic flow chart showing an indoor environment control method according to an embodiment of the present application; Figure 2 A schematic block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application more obvious, the example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0023] As described above, the traditional indoor environment control method mainly relies on a preset schedule or requires manual intervention to adjust the settings. In some embodiments of the related art, the control parameters of the indoor equipment are adjusted and set by a preset schedule to achieve control of the indoor environment. For example, the curtains are automatically opened in the morning and automatically closed in the evening. In other embodiments of the related art, the control parameters of the indoor equipment are adjusted by manual intervention of the user to achieve control of the indoor environment. These methods lack real-time response capabilities, poor flexibility, and cannot be adjusted in time based on actual usage (for example, the temperature setting parameters of the air conditioner cannot be adjusted in time according to the changes in the indoor temperature, and the gear of the fresh air system cannot be adjusted according to the indoor air conditions, etc.), which may lead to unnecessary energy consumption. And because this method cannot respond to the needs of indoor changes in time, the user experience is reduced. In view of this, the present application provides an indoor environment control method, an electronic device and a storage medium, which can adjust the indoor environment in real time and adaptively according to the indoor conditions, can solve the problems of poor flexibility and untimely response of the indoor environment control scheme in the related art, and help to achieve intelligent and automated indoor environment control.

[0024] According to one aspect of an embodiment of the present application, an indoor environment control method is provided. The method is used in an indoor environment control system. The indoor environment control system includes an image acquisition device for acquiring an indoor environment image.

[0025] It can be understood that in this article, indoor includes but is not limited to the indoor of a conference room, the indoor of a shopping mall, the indoor of a large venue, the indoor of a classroom, etc. Indoor environment control refers to controlling the control parameters of the equipment located indoors and used to adjust the indoor environment, such as controlling the temperature setting parameters of the air conditioner, controlling the gear of the fresh air system, controlling the brightness of the lighting system, controlling the opening and closing of the curtains, controlling the volume of the power amplifier, etc. The equipment used to adjust the indoor environment can be determined according to the actual configuration of different scenarios, and will not be repeated.

[0026] Figure 1 FIG. 1 is a schematic flow chart of an indoor environment control method according to an embodiment of the present application. Figure 1 As shown, the method includes step S110 and step S120.

[0027] In step S110, an image acquisition device is used to acquire an indoor environment image to obtain image data, where the image data includes at least one frame of the environment image.

[0028] Optionally, the image acquisition device may be any existing or future developed device that can be used to acquire images or videos, such as a camera or a still camera.

[0029] In the solution of this example, an image acquisition device may be used to acquire image data. The image data may be one or more frames of environmental images continuously captured by the image acquisition device at a preset frequency, or may be a video captured by the image acquisition device, each frame of which is a frame of environmental image.

[0030] In the solution of this example, the image acquisition device is used to acquire the indoor environment image. The setting position and quantity of the image acquisition device can be set according to actual needs and will not be described in detail.

[0031] In step S120, a parameter self-adjustment operation is performed based on the image data. As described above, indoor environment control refers to controlling the control parameters of a device located indoors and used to adjust the indoor environment. It can be understood that the parameter self-adjustment operation is an operation of adjusting the control parameters of the device used to adjust the indoor environment based on the image data.

[0032] like Figure 1 As shown, in the scheme of this example, the parameter self-adjustment operation includes step S121, step S122 and step S123.

[0033] In step S121, image data is recognized using an image recognition algorithm to obtain indoor environmental information, which includes indoor personnel quantity information and / or indoor personnel motion feature information, and the personnel motion feature information is used to represent the activity mean of indoor personnel.

[0034] Optionally, the image recognition algorithm may adopt any existing or future developed algorithm that can be used to identify the number of people in the image and the characteristic information of the indoor human action in the image data. For example, the deep learning framework TensorFlow or PyTorch may be used in combination with a convolutional neural network (CNN) to identify the number of people and behavioral characteristics. Of course, one or more of a deep learning-based point detection model, an attention mechanism-based model, etc. may also be used to implement the identification of the number of people in the image and the characteristic information of the indoor human action in the image data, which will not be described in detail.

[0035] Optionally, the image recognition algorithm can be trained by the following steps: obtaining sample image data and annotation results corresponding to each sample image data, the annotation results including information on the number of people in each frame of the environmental image in the corresponding sample image data and / or information on characteristic movements of people in the corresponding sample image data; identifying the sample image data using the image recognition algorithm to obtain environmental information corresponding to the sample image data; and optimizing the image recognition algorithm based on the difference between the environmental information corresponding to the identified sample image data and the annotation results corresponding to the sample image data.

[0036] The sample image data can be obtained by pre-collection. For example, a large amount of image data containing diverse scenes such as different lighting conditions, number of people, and behavioral characteristics can be collected in advance. Then, these image data are accurately annotated to generate a high-quality data set for training. In some embodiments, the sample image data can be subjected to enhancement operations such as random rotation, scaling, cropping, and color adjustment to obtain diverse sample image data. This solution helps to enhance the adaptability of the image recognition algorithm to different lighting conditions and complex backgrounds, thereby helping to improve the recognition accuracy of the image recognition algorithm.

[0037] In some embodiments, the image recognition model can also be obtained in the following way: First, a basic model is pre-trained on a large-scale general dataset (such as ImageNet). This model has strong image recognition capabilities by learning the features of a large number of general images. Then, the pre-trained model is applied to specific data of indoor environments (i.e., specific image data) and fine-tuned to make the model more suitable for the recognition of the number of people and behavioral characteristics in indoor scenes. The fine-tuning process includes continuing to train the model on indoor image datasets to adapt to specific environments and lighting conditions. In some embodiments, during the model fine-tuning process, a multi-scale convolution kernel design can also be used. This design allows the model to capture local details and global structural features in the image at the same time, thereby improving the detection ability of targets of different sizes and distances. Multi-scale feature extraction is usually integrated into the model architecture during the fine-tuning process. Model training and optimization: After completing the above steps, the Adam optimizer or other advanced optimization algorithms are used to train the model and adjust the parameters. This process involves repeated iterations to gradually minimize the loss function to improve the recognition accuracy of the model. Model training and optimization are steps after transfer learning and multi-scale feature extraction to ensure that the model performs best in a specific scenario.

[0038] In some embodiments, the trained image recognition algorithm may also be subjected to a robustness test. For example, the algorithm may be subjected to a robustness test by introducing different disturbance conditions such as illumination, angle, and occlusion to ensure its stability in complex environments.

[0039] In some embodiments, during the execution of the method of this example, new image data can be continuously collected and annotated, and the image recognition algorithm can be incrementally trained and updated using the new image data to continuously adapt to new scenarios and needs.

[0040] As described above, the environmental information includes the number of people in the room and / or the motion feature information of the people in the room, and the motion feature information of the people is used to represent the activity mean of the people in the room. In some embodiments, the environmental information includes the number of people in the room. When the image data includes one frame of environmental image, the environmental information includes the number of people information corresponding to the frame of environmental image. When the image data includes multiple frames of environmental images, the environmental information includes the number of people information corresponding to each frame of environmental image. In other embodiments, the environmental information includes the motion feature information of the people. In this embodiment, the image data includes multiple frames of continuous environmental images. By identifying the multiple frames of continuous environmental images, the activity of the people in the room (such as walking, adding or removing clothes, etc.) can be detected, and the motion frequency of the people, that is, the activity mean, can be obtained according to the activity. Of course, the environmental information can also include the number of people in the room and the motion feature information of the people in the room at the same time, which will not be repeated.

[0041] In step S122, the environmental information is input into the pre-trained environmental parameter adjustment model to obtain an environmental parameter adjustment result.

[0042] Optionally, the pre-trained environmental parameter adjustment model may adopt any existing or future developed neural network model that can output corresponding environmental parameter adjustment results according to environmental information, such as a convolutional neural network model, a fully connected neural network model, etc.

[0043] In this article, the environmental parameter adjustment result refers to the parameter used to make the indoor environment meet the user's needs, and the parameter may include control parameters corresponding to at least some of the devices. At least some of the devices are devices used to control the indoor environmental state, and the at least some of the devices include but are not limited to air conditioners, fresh air systems, lighting systems, curtains, power amplifiers, projection equipment, electric screens, indoor security systems, electronic whiteboards, etc. The environmental parameter adjustment result may include environmental parameters corresponding to different devices one by one, for example, it may include temperature parameters of the air conditioner (for example, if the current temperature of the air conditioner is 24°, the temperature parameter may be 26°), gear parameters of the fresh air system (for example, first gear, second gear, third gear, etc.), brightness parameters of the lighting system (for example, the brightness gear of the lighting system or the light intensity of the lighting system), switch setting parameters of the curtain (i.e., controlling the curtain to open or close), etc. Changes in these parameters can change the indoor environmental state, so that the indoor environment can be more in line with user needs.

[0044] In the solution of this example, the environmental parameter adjustment result can be obtained based on the environmental information. For ease of understanding, the following description is given by taking at least part of the equipment including an air conditioner as an example.

[0045] In some embodiments, the environmental information includes information about the number of people in the room. The pre-trained environmental parameter adjustment model can determine the environmental parameter adjustment result according to the number of people information (the mean of each number of people information corresponding to the image data). For example, the pre-trained environmental parameter adjustment model can be used to perform the following steps: compare the current number of people information with the historical number of people information (i.e., the number of people information corresponding to the image data acquired last time) to obtain the environmental parameter adjustment result. When it is determined that the number of people has increased, the temperature of the air conditioner is lowered to increase the cooling intensity of the air conditioner. For example, if the current temperature of the air conditioner is 26°, the temperature parameter can be 24°. In other embodiments, the pre-trained environmental parameter adjustment model can be used to perform the following steps: compare the number of people information corresponding to the environmental information (when the image data includes multiple frames of environmental images, it can be the mean of the number of people information corresponding to each of the multiple frames of environmental images) with multiple ranges of number of people, determine which range of number of people the current number of people is in, and output the environmental parameter adjustment result corresponding to the range of number of people. For example, when at least part of the equipment includes an air conditioner, the temperature parameter corresponding to the range of number of people can be output. The range of number of people and the corresponding environmental parameter adjustment result can be preset according to actual needs and will not be repeated. Of course, in addition to the above-mentioned methods, the pre-trained environment parameter adjustment model can perform other steps to obtain the environment parameter adjustment result. For example, the environment parameter adjustment result can be output according to the change in the number of people corresponding to the image data.

[0046] In some embodiments, the environmental information includes characteristic information of indoor human motions. The pre-trained environmental parameter adjustment model can determine the environmental parameter adjustment result based on the characteristic information of human motions. For example, the pre-trained environmental parameter adjustment model can be used to perform the following steps: compare the human motion characteristic information with a plurality of preset activity mean ranges to determine the preset activity mean range (which can be referred to as the target mean range) to which the human motion characteristic information belongs. Then, the environmental parameter adjustment result corresponding to the target mean range is output. Of course, the pre-trained environmental parameter adjustment model can be used to compare the human motion characteristic information with the preset activity mean to obtain the environmental parameter adjustment result, which will not be described in detail.

[0047] In some embodiments, the environmental information may include information about the number of people in the room and information about the motion characteristics of the people in the room. In this embodiment, the environmental parameter adjustment results corresponding to the number of people in the room and the motion characteristics of the people in the room may be output respectively, and the final environmental parameter adjustment result may be obtained by combining the two environmental parameter adjustment results. The specific steps of outputting the environmental parameter adjustment result according to the number of people in the room or the motion characteristics of the people in the room have been described in detail above and will not be repeated here.

[0048] In step S123, control parameters of at least some of the equipment in the room are adjusted based at least on the result of the environmental parameter adjustment; wherein at least some of the equipment is used to control the indoor environmental state.

[0049] In some embodiments, after obtaining the environmental parameter adjustment result, the control parameters of at least some of the equipment in the room can be adjusted directly according to the environmental parameter adjustment result, that is, the control parameters of each device are adjusted according to the parameters of each device included in the environmental parameter adjustment result.

[0050] In other embodiments, the indoor environment control system may further include an environmental sensor (such as a temperature sensor, a humidity sensor, a smoke sensor, etc.) for sensing environmental conditions. In this embodiment, the control parameters of at least part of the indoor equipment may be adjusted based on the environmental parameters detected by the environmental sensor and the result of the environmental parameter adjustment. This helps to further ensure that the adjusted indoor environment meets the needs of the user.

[0051] In a specific embodiment, at least some of the devices may include air conditioners, fresh air systems, lighting systems, curtains, and power amplifiers. In this embodiment, through the above steps S121, S122, and S123, the control parameters of some or all of these devices can be adjusted to make the indoor environment meet user needs. Taking the conference room as an example, when the number of people in the conference room increases, the temperature parameters of the air conditioner can be lowered through the above steps, the gear of the fresh air system can be increased, the brightness of the lighting system can be increased, and the position of the curtains can be adjusted to prevent direct sunlight. At the same time, the volume of the power amplifier can be increased to ensure that the sound can cover the entire conference room.

[0052] In the above technical solution, the indoor environmental information can be determined based on the indoor image data, and the control parameters of at least part of the indoor equipment can be adjusted based on the indoor environmental information to achieve control of the indoor environment. This environmental control method can adjust the indoor environmental parameters in real time and dynamically according to the number of people in the room and / or the characteristics of the people's movements, which can ensure that the indoor environment meets the needs of users, improve the comfort of users, and help avoid energy waste and improve energy efficiency. In short, this solution can solve the problems of poor flexibility and untimely response of indoor environmental control solutions in related technologies, and help to achieve intelligent and automated indoor environmental control.

[0053] Exemplarily, the image data includes a continuous plurality of frames of environmental images; the environmental information includes information on the number of people corresponding to the plurality of frames of environmental images; step S122, inputting the environmental information into a pre-trained environmental parameter adjustment model to obtain an environmental parameter adjustment result, may specifically include the following steps: performing the following steps through the environmental parameter adjustment model: determining a change in the number of people in the room based on the information on the number of people corresponding to the plurality of frames of environmental images; generating a first environmental parameter adjustment result according to the change in the number of people. In this example, the final environmental parameter adjustment result is the first environmental parameter adjustment result.

[0054] In this embodiment, the change in the number of people in the room can be determined based on the one-to-one correspondence between the number of people in the multiple frames of environmental images. For example, two adjacent frames of environmental images in the multiple frames of environmental images can be compared to determine the change in the number of people. The number of environmental images is 3 frames for illustration. The number of people corresponding to the 3 frames of images can be 5, 5, and 8, respectively. In this case, the change in the number of people is an increase in the number of people.

[0055] After obtaining the change in the number of people, the first environmental parameter adjustment result can be generated according to the change in the number of people. For example, when the number of people in the room increases, the temperature of the air conditioner can be lowered and / or the gear of the fresh air system can be increased. Otherwise, the temperature of the air conditioner can be increased and / or the gear of the fresh air system can be lowered. In a specific embodiment, the air conditioning temperature is 26°, and the gear of the fresh air system is the first gear. When the number of people in the room increases, the temperature parameter included in the first environmental parameter adjustment result can be 24°, and the gear parameter can be the second gear (in this embodiment, the higher the gear, the stronger the air purification efficiency of the fresh air system), so as to determine the appropriate temperature and air quality in the room.

[0056] The above technical solution can ensure that the indoor environment meets user needs and improve user comfort by adjusting indoor environmental parameters in real time and dynamically according to changes in the number of people indoors.

[0057] Exemplarily, the image data includes multiple frames of continuous environment images; the environment information includes personnel action feature information; step S122, inputting the environment information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result, can specifically include the following steps: by using the environment parameter adjustment model, performing the following steps: comparing the personnel action feature information with a preset activity mean; generating a second environment parameter adjustment result according to the comparison result of the personnel action feature information with the preset activity mean. In this example, the final environment parameter adjustment result is the second environment parameter adjustment result.

[0058] In this embodiment, the preset activity mean can be obtained by a user through specific settings based on experience or actual needs, or it can be the personnel motion feature information corresponding to the historical image data before the currently acquired image data. In a specific embodiment, the image data can be first acquired and a basic personnel motion feature information can be determined, and the basic personnel motion feature information is used as the preset activity mean. Then the current personnel motion feature information is calculated in real time, and the personnel motion frequency can be dynamically evaluated through continuous monitoring. For example, when there are more walking, adding or removing clothes, etc. on the scene, the system will detect an increase in the activity mean, indicating that the personnel are more active; conversely, if most people are sitting and moving less, the activity mean will decrease, indicating that the overall motion frequency is low. Based on this real-time activity mean, environmental parameters can be adjusted in real time, such as increasing or decreasing the air conditioning intensity, to ensure that the indoor environment meets current needs.

[0059] The above technical solution can adjust the indoor environmental parameters in real time and dynamically by comparing the current personnel motion feature information with the preset activity mean, thereby ensuring that the indoor environment meets user needs and improving user comfort.

[0060] Exemplarily, the image data includes a continuous multi-frame environment image; the environment information includes personnel quantity information and personnel motion characteristic information corresponding one-to-one to the multi-frame environment image; step S122, inputting the environment information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result, which can specifically include the following steps: through the environment parameter adjustment model, performing the following steps: based on the personnel quantity information corresponding one-to-one to the multi-frame environment image, determining the change in the number of people in the room; based on the change in the number of people, generating a first environment parameter adjustment result; comparing the personnel motion characteristic information with a preset activity mean; generating a second environment parameter adjustment result based on the comparison result of the personnel motion characteristic information with the preset activity mean; combining the first environment parameter adjustment result and the second environment parameter adjustment result to generate a final environment parameter adjustment result.

[0061] The generation method of the first environmental parameter adjustment result and the second environmental parameter adjustment result has been described in detail above and will not be repeated here.

[0062] After obtaining the first environmental parameter adjustment result and the second environmental parameter adjustment result, the first environmental parameter adjustment result and the second environmental parameter adjustment result can be combined to generate a final environmental parameter adjustment result. For example, the final environmental parameter adjustment result can be generated by combining the first environmental parameter adjustment result and the second environmental parameter adjustment result according to a preset priority. For example, when the priority of the number of personnel information is greater than the priority of the personnel motion characteristic information, the first environmental parameter adjustment result can be determined as the first environmental parameter adjustment result. When the priority of the number of personnel information is less than the priority of the personnel motion characteristic information, the second environmental parameter adjustment result can be determined as the final environmental parameter adjustment result. Of course, the first environmental parameter adjustment result and the second environmental parameter adjustment result can also be combined according to the type of environmental parameters to obtain the final environmental parameter adjustment result. It can be understood that the first environmental parameter adjustment result and the second environmental parameter adjustment result may include environmental parameters of the same type or different types of environmental parameters. For different types of environmental parameters, the environmental parameters of the type can be directly added to the final environmental parameter adjustment result; for the same type of environmental parameters, the environmental parameters corresponding to the information with higher priority (the number of personnel information or the personnel motion characteristic information) can be added to the final environmental parameter adjustment result according to the preset priority. In this embodiment, the same type refers to the same parameter of the same device. For example, when the first environmental parameter adjustment result and the second environmental parameter adjustment result both include temperature adjustment results for adjusting the temperature of the air conditioner, the first environmental parameter adjustment result and the second environmental parameter adjustment result include environmental parameters of the same type.

[0063] For example, the first environmental parameter adjustment result includes temperature parameters and gear parameters, and the second environmental parameter adjustment result includes temperature parameters, brightness parameters and switch setting parameters. If the priority of personnel quantity information is lower than the priority of personnel motion characteristic information, the final environmental parameter adjustment result includes the gear parameters derived from the first environmental parameter adjustment result and the temperature parameters, brightness parameters and switch setting parameters derived from the second environmental parameter adjustment result.

[0064] The above technical solution can obtain a more accurate final environmental parameter adjustment result by combining the environmental parameter adjustment results obtained based on the number of people information and the characteristic information of people's movements. The final environmental parameter adjustment result obtained by combining the change of the number of people in the room and the activity of people can further ensure that the indoor environment meets the needs of users, thereby helping to further improve the comfort of users.

[0065] In the steps of the above example, the final environmental parameter adjustment result is obtained based on the personnel data volume information and / or the personnel action feature information. It can be understood that the environmental parameter adjustment result used in step S123 is the final environmental parameter adjustment result in the above example.

[0066] Exemplarily, combining the first environmental parameter adjustment result and the second environmental parameter adjustment result to generate a final environmental parameter adjustment result includes: when the first environmental parameter adjustment result and the second environmental parameter adjustment result include the same type of environmental parameters, determining that the environmental parameters of the type in the second environmental parameter adjustment result are the environmental parameters of the type in the final environmental parameter adjustment result.

[0067] In this embodiment, when the first environmental parameter adjustment result and the second environmental parameter adjustment result include the same type of environmental parameters, the environmental parameters of this type are adjusted based on the second environmental parameter adjustment result. For example, when both the second environmental parameter adjustment result and the first environmental parameter adjustment result include temperature parameters, the temperature parameter in the final environmental parameter adjustment result is the same as the temperature parameter included in the second environmental parameter adjustment result.

[0068] The above technical solution comprehensively adjusts the environmental parameters based on the personnel quantity information and the personnel motion characteristic information, and gives priority to the environmental parameters determined based on the personnel motion characteristic information when the types of the included environmental parameters are the same. This method can make the adjusted indoor environment more in line with user needs and improve the user experience.

[0069] Exemplarily, based at least on the environmental parameter adjustment result, control parameters of at least some of the equipment in the room are adjusted, including: based on the environmental adjustment parameters corresponding to at least some of the equipment included in the environmental parameter adjustment result, control parameters of at least some of the equipment are adjusted.

[0070] In the solution of this example, the control parameters of the corresponding device can be adjusted directly according to the environmental parameters in the environmental parameter adjustment result. For example, if the temperature parameter in the environmental parameter adjustment result is 24°, then in this example, the control parameter of the air conditioner can be directly set to 24°. This adjustment method is convenient and simple, and can realize the rapid adjustment of the control parameters of at least some devices, so that the indoor environment can be quickly adjusted to make the indoor environment more in line with user needs.

[0071] Exemplarily, the indoor environment control system also includes a temperature sensor, which adjusts the control parameters of at least some of the equipment in the room based at least on the environmental parameter adjustment result, including: adjusting the control parameters of at least some of the equipment based on the temperature information detected by the temperature sensor and the environmental adjustment parameters corresponding to at least some of the equipment included in the environmental parameter adjustment result.

[0072] In this example, at least some of the devices include air conditioners. Based on the temperature information detected by the temperature sensor and the environmental adjustment parameters corresponding to at least some of the devices included in the environmental parameter adjustment result, the control parameters of at least some of the devices are adjusted, including: when the environmental parameter adjustment result includes the temperature parameter, the control parameters of the air conditioner are adjusted based on the temperature parameter; when the environmental parameter adjustment result does not include the temperature parameter, it is determined whether the temperature information is greater than a temperature threshold; when the temperature information is greater than the temperature threshold, the control parameters of the air conditioner are adjusted to increase the cooling intensity of the air conditioner (for example, the temperature of the air conditioner can be lowered, the air volume of the air conditioner can be increased, etc.).

[0073] The above technical solution can adjust the indoor temperature in combination with the environmental parameter adjustment result and the temperature information detected by the temperature sensor. This adjustment method can improve the temperature adjustment accuracy and flexibility, thereby further improving the comfort of the indoor environment.

[0074] Exemplarily, the method may further include the following steps: determining whether the image data has smoke features; performing a smoke response operation at least when the image data has smoke features; wherein the smoke response operation includes outputting an alarm message, and / or, at least part of the equipment includes a fresh air system, and the smoke response operation includes controlling the fresh air system to purify the smoke.

[0075] Optionally, any existing or future developed algorithm or neural network model that can be used to identify smoke features through image data can be used to determine whether the image data has smoke features. For example, it can be implemented through a convolutional neural network, an attention mechanism model, etc. Of course, it is also possible to determine whether the image data has smoke features based on the features of each frame of the image data (such as color, texture, etc.), which will not be elaborated.

[0076] In some embodiments, the smoke response operation may include outputting alarm information. The output methods of the alarm information include, but are not limited to, text, voice, light, etc. For example, the alarm light may be controlled to flash, the alarm may be controlled to emit an alarm sound, and the alarm information may be sent to a user terminal (such as a user's mobile phone) to remind the user in time.

[0077] In other embodiments, at least part of the equipment includes a fresh air system, and the smoke response operation includes controlling the fresh air system to purify the smoke. In this embodiment, the fresh air system can be controlled to purify the smoke, for example, the gear of the fresh air system can be increased to improve its air purification ability.

[0078] Optionally, before determining whether the image data has smoke features, the method may further include the following steps: preprocessing each frame of the environment image in the image data, wherein the preprocessing method includes but is not limited to filtering, denoising, contrast enhancement, etc. By preprocessing the environment image, possible smoke areas can be highlighted, thereby improving the accuracy of determining whether the image data has smoke features.

[0079] The above technical solution can detect whether there are smoke features in the image data, and then perceive the signs of smoke in the room, indirectly realizing the recognition of indoor smoking, open flames and other scenarios. At the same time, by executing smoke response operations, the suitability of the indoor environment can be ensured and safety can be improved.

[0080] Exemplarily, determining whether image data has smoke features may specifically include the following steps: for each frame of environmental image in the image data, performing color analysis and texture analysis on the environmental image to obtain the color features and texture features of the environmental image; comparing the color features of the environmental image with preset color features; comparing the texture features of the environmental image with preset texture features; when the color features of the environmental image are the same as the preset color features, and the texture features of the environmental image are the same as the preset texture features, determining that the image data has smoke features.

[0081] The method for color analysis and texture analysis of environmental images can be implemented by using any one or several existing or future developed algorithms or neural network models that can realize color feature extraction and texture feature extraction, which will not be elaborated here.

[0082] It can be understood that smoke usually has unique color characteristics and texture characteristics. Specifically, smoke usually appears light gray or white, and has blurred edges and irregular shapes. According to such unique color characteristics and texture characteristics, accurate identification of smoke can be achieved.

[0083] Optionally, the preset color feature and the preset texture feature can be obtained by pre-recognition. For example, a large number of images including smoke features can be pre-recognized, and the preset color feature and the preset texture feature can be obtained based on the recognition results.

[0084] In this example, the same features refer to the similarity between the two features being greater than a preset similarity threshold. Take the texture feature as an example for illustration. In the scheme of this embodiment, the similarity between the texture feature of the environment image and the preset texture feature can be calculated. When the similarity is greater than the preset similarity threshold, it can be considered that the texture feature in the environment image matches the texture feature of the smoke, that is, the texture feature of the environment image is the same as the preset texture feature. The confirmation method of the color feature is similar to this and will not be repeated.

[0085] The above technical solution can more accurately determine whether the image includes smoke features by identifying the color features and texture features of the image, and thus can more accurately determine whether the image data includes smoke features, which can provide a more accurate basis for subsequent steps.

[0086] Exemplarily, the image data includes a continuous multi-frame environment image; determining whether the image data has smoke features includes: using a motion detection algorithm to detect whether the image data has smoke features. In the scheme of this example, the motion detection algorithm can be combined to identify continuously changing areas in the multi-frame environment image. It can be understood that when smoke floats in the air, it will produce continuous dynamic changes in the image, and this feature can be distinguished from the background. The scheme of this example can use a motion detection algorithm combined with continuous multi-frame environment images to more accurately determine whether there is smoke in the room, which can provide a more accurate basis for indoor environment adjustment.

[0087] Exemplarily, the indoor environment control system includes a smoke sensor; performing a smoke response operation at least when smoke features exist in the image data may include the following steps: performing a smoke response operation when smoke features exist in the image data and / or the smoke sensor detects smoke.

[0088] In the solution of this example, the image data and the smoke sensor can be combined to detect whether there is smoke in the room. This multiple detection method can provide more comprehensive detection capabilities and help improve the accuracy of smoke detection. In some embodiments, when there are smoke features in the image data and the smoke sensor detects smoke, a higher level of response measures can be taken, such as sounding an alarm and sending an alarm message to the user terminal at the same time.

[0089] Exemplarily, the method may also include the following steps: performing the following interactive parameter adjustment operations: determining the real-time action contained in the image data; comparing the real-time action with the preset action in the preset action library; when the real-time action is the same as any preset action in the preset action library, generating a control instruction corresponding to the preset action; based on the control instruction, adjusting the control parameters of at least part of the device.

[0090] The preset actions in the preset action library can be obtained by presetting. For example, a user can pre-set multiple preset actions and save them in the preset action library. In some embodiments, the user can customize the preset actions on the user terminal (such as a smart phone or tablet computer) and bind each preset action to the operation instructions of each indoor device, such as lighting control of the lighting system, air conditioning temperature adjustment, etc., which helps to achieve personalized control and improve the user experience.

[0091] In the solution of this example, each preset action can correspond to a control instruction. For example, the action of making a fist can be set to turn on the lighting system. The action of waving the hand can be set to turn on the fresh air system. Of course, the preset action can also be a combination of actions. For example, the action of waving the hand first and then making a fist can be corresponded to the instruction to turn on the lighting system. The specific preset actions and their corresponding control instructions can be set according to actual needs and will not be repeated here.

[0092] Optionally, any existing or future developed action recognition algorithm or neural network model may be used to determine the real-time action contained in the image data. For example, a 3D convolutional neural network model, a Transformer network model, etc. may be used.

[0093] In the solution of this example, comparing the real-time action with the preset action in the preset action library may include the following steps: calculating the similarity between the real-time action and the preset action; when the similarity is greater than a similarity threshold, determining that the real-time action is the same as the preset action. In a specific embodiment, a convolutional neural network may be used to compare the real-time action with each preset action in the preset action library.

[0094] In the above technical solution, users can use specific actions to adjust the control parameters of at least part of the equipment. This control method does not require any physical contact or voice commands, which greatly enhances the portability and sense of technology of the operation. In addition, this method can quickly adjust the indoor environment according to the needs of the user, which helps to further ensure that the indoor environment meets the needs of the user.

[0095] In some embodiments, before adjusting the control parameters of at least some devices based on the control instruction, the method may further include: sending the control instruction to a user terminal; the step of adjusting the control parameters of at least some devices based on the control instruction is performed after receiving a confirmation instruction sent by the user terminal. In this example solution, the control instruction can be sent to the user terminal, and the user can confirm the control instruction through the control terminal. After the user confirms, the control parameters are adjusted based on the control instruction. This can avoid misidentification and ensure accurate execution of the operation.

[0096] Exemplarily, the parameter self-adjustment operation is executed when the interactive parameter adjustment operation does not generate a control instruction. In the solution of this example, the environmental parameters are adjusted according to the user's customized action (i.e., preset action) first, and when the user's customized action is not recognized, the indoor environmental parameters are automatically adjusted according to the number of people in the room and / or the characteristics of the people's actions through the parameter self-adjustment operation.

[0097] Exemplarily, the indoor environment control system has multiple working modes, including automatic mode, manual mode and preset scene mode; wherein, at least based on the environmental parameter adjustment result, the control parameters of at least part of the equipment in the room are adjusted when the indoor environment control system is in automatic mode, or the parameter self-adjustment operation is performed when the indoor environment control system is in automatic mode.

[0098] In the solution of this example, when the indoor environment control system is in manual mode, the user needs to adjust the indoor environment parameters by manual control. When the indoor environment control system is in automatic mode, the indoor environment parameters can be automatically adjusted by parameter self-adjustment operation. When the indoor environment control system is in preset scene mode, different environmental parameters can be set according to different recognized scenes.

[0099] In the above solution, the indoor environment control system includes multiple working modes. The user can select a suitable working mode according to the needs, which can make the current indoor environment adjustment method more in line with the user's needs, thereby helping to improve the user experience.

[0100] Exemplarily, at least based on the environmental parameter adjustment result, the control parameters of at least part of the indoor equipment are adjusted when the indoor environment control system is in automatic mode; when the indoor environment control system is in manual mode, the method also includes: generating parameter adjustment suggestions based on the environmental parameter adjustment result; and sending the parameter adjustment suggestions to the user terminal.

[0101] In the solution of this example, parameter adjustment suggestions can be generated based on the environmental parameter adjustment results. The parameter adjustment suggestions can provide a reference for users. Users can manually adjust indoor environmental parameters according to the received parameter adjustment suggestions, which helps to improve adjustment efficiency and can assist users to adjust the indoor environment more reasonably.

[0102] Exemplarily, when the indoor environment control system is in a preset scene mode, the method further includes: identifying a current scene; generating an environmental parameter adjustment instruction corresponding to the current scene; and adjusting control parameters of at least part of the equipment based on the environmental parameter adjustment instruction.

[0103] Optionally, the image data may be identified using a deep neural network model for scene recognition to identify the current scene. The deep neural network model may be obtained by training the deep neural network model using a pre-labeled sample data set until the recognition accuracy of the deep neural network model reaches an accuracy threshold. Of course, other methods may also be used to identify the scene. For example, scene selection information sent by a user terminal may be received, and the current scene may be identified based on the scene selection information.

[0104] Optionally, the step of generating an environmental parameter adjustment instruction corresponding to the current scene is performed when the identified current scene is different from the historical scene. The historical scene is the scene determined by the last identification.

[0105] The type of scene and the environmental parameter adjustment instructions corresponding to different scenes can be set according to actual needs. Taking the conference room as an example, the scene types can include lecture scenes and office scenes. When it is recognized that the current scene switches from an office scene to a lecture scene, the control parameters of the lighting system can be adjusted to increase the lights in the podium area, lower the lights in other areas, and adjust the power amplifier to ensure that the sound covers the entire conference room. In addition, the projection screen can be controlled to open for user convenience. When it is recognized that the current scene switches from a lecture scene to an office scene, the lights can be adjusted to be globally consistent and the volume of the power amplifier can be restored to normal.

[0106] The above technical solution can adopt different environmental parameter adjustment methods according to different scenarios, which helps to make the indoor environment meet the user's current usage needs and helps to improve the user's usage experience.

[0107] According to another aspect of the embodiments of the present application, an electronic device is also provided. Figure 2 FIG. 1 is a schematic block diagram of an electronic device according to an embodiment of the present application. Figure 2 As shown, the electronic device 200 includes: a processor 210 and a memory 220. The memory 220 stores a computer program, and the processor 210 is used to execute the computer program to implement the above method.

[0108] According to another aspect of the embodiment of the present application, a computer-readable storage medium is also provided. The storage medium stores a computer program / instruction, and the computer program / instruction implements the above method when executed by the processor. The storage medium may include, for example, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0109] A person skilled in the art can easily understand the implementation structure, working principle and beneficial effects of the electronic device and the computer-readable storage medium by reading the above method, and will not be described in detail for the sake of brevity.

[0110] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0111] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0113] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0114] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various application aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the application point is that the corresponding technical problem can be solved with less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0115] Those skilled in the art will understand that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstract and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0116] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0117] The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules in the electronic device according to the embodiment of the present application. The present application may also be implemented as a device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0118] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0119] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for controlling an indoor environment, characterized in that: Used in an indoor environment control system, the indoor environment control system includes an image acquisition device for acquiring an indoor environment image; The method comprises: Using the image acquisition device to acquire an indoor environment image to obtain image data, wherein the image data includes at least one frame of the environment image; Based on the image data, the following parameter self-adjustment operations are performed: Recognize the image data using an image recognition algorithm to obtain indoor environmental information, wherein the environmental information includes indoor personnel quantity information and / or indoor personnel motion feature information, wherein the indoor personnel motion feature information is used to represent the activity mean of the indoor personnel; Inputting the environmental information into a pre-trained environmental parameter adjustment model to obtain an environmental parameter adjustment result; At least based on the environmental parameter adjustment result, adjusting control parameters of at least part of the equipment in the room; Wherein, at least part of the devices are devices for controlling indoor environmental conditions.

2. The method according to claim 1, characterized in that The image data includes a continuous plurality of frames of environment images; the environment information includes personnel quantity information corresponding one-to-one to the plurality of frames of environment images; The step of inputting the environmental information into a pre-trained environmental parameter adjustment model to obtain an environmental parameter adjustment result includes: performing the following steps through the environmental parameter adjustment model: Determine the change of the number of people in the room based on the one-to-one correspondence between the multiple frames of environmental images; Generating a first environmental parameter adjustment result according to the change in the number of personnel; or, The image data includes a continuous multi-frame environment image; the environment information includes the personnel action feature information; the inputting the environment information into a pre-trained environment parameter adjustment model to obtain an environment parameter adjustment result includes: performing the following steps through the environment parameter adjustment model: Comparing the personnel action characteristic information with a preset activity mean; Generate a second environmental parameter adjustment result according to a comparison result between the personnel action characteristic information and the preset activity mean; or, The image data includes a continuous plurality of frames of environment images; the environment information includes personnel quantity information and personnel action feature information corresponding to the plurality of frames of environment images one by one; The step of inputting the environmental information into a pre-trained environmental parameter adjustment model to obtain an environmental parameter adjustment result includes: performing the following steps through the environmental parameter adjustment model: Determine the change of the number of people in the room based on the one-to-one correspondence between the multiple frames of environmental images; Generating a first environmental parameter adjustment result according to the change in the number of personnel; Comparing the personnel action characteristic information with a preset activity mean; Generate a second environmental parameter adjustment result according to a comparison result between the personnel action characteristic information and the preset activity mean; The first environmental parameter adjustment result and the second environmental parameter adjustment result are combined to generate a final environmental parameter adjustment result.

3. The method according to claim 2, characterized in that The combining the first environmental parameter adjustment result and the second environmental parameter adjustment result to generate a final environmental parameter adjustment result includes: When the first environmental parameter adjustment result and the second environmental parameter adjustment result include the same type of environmental parameters, the environmental parameters of the type in the second environmental parameter adjustment result are determined as the environmental parameters of the type in the final environmental parameter adjustment result.

4. The method according to any one of claims 1 to 3, characterized in that: The step of adjusting control parameters of at least part of the equipment in the room based at least on the result of adjusting the environmental parameters includes: adjusting control parameters of at least part of the equipment based on the environmental adjustment parameters corresponding to at least part of the equipment included in the environmental parameter adjustment result; or, The indoor environment control system further includes a temperature sensor, and the control parameters of at least part of the indoor equipment are adjusted based at least on the environmental parameter adjustment result, including: Based on the temperature information detected by the temperature sensor and the environmental adjustment parameters corresponding to the at least part of the equipment included in the environmental parameter adjustment result, the control parameters of the at least part of the equipment are adjusted.

5. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Determining whether the image data has smoke features; At least when there is a smoke feature in the image data, performing a smoke response operation; Wherein, the smoke response operation includes outputting alarm information, and / or, the at least part of the equipment includes a fresh air system, and the smoke response operation includes controlling the fresh air system to purify the smoke; Preferably, the determining whether the image data has smoke features includes: For each frame of environment image in the image data, Performing color analysis and texture analysis on the environment image to obtain color features and texture features of the environment image; Comparing the color characteristics of the environment image with the preset color characteristics; Comparing the texture features of the environment image with preset texture features; When the color feature of the environment image is the same as the preset color feature, and the texture feature of the environment image is the same as the preset texture feature, determining that the image data has a smoke feature; Preferably, the image data includes a continuous plurality of frames of environment images; and the step of determining whether the image data has smoke features includes: A motion detection algorithm is used to detect whether smoke features exist in the image data.

6. The method according to claim 5, characterized in that The indoor environment control system includes a smoke sensor; the smoke response operation is performed when at least the image data has smoke features, including: When smoke features exist in the image data and / or the smoke sensor detects smoke, the smoke response operation is performed.

7. The method according to any one of claims 1 to 3, characterized in that: The method further includes: performing the following interactive parameter adjustment operations: determining real-time actions contained in the image data; Comparing the real-time action with the preset actions in the preset action library; When the real-time action is the same as any preset action in the preset action library, generating a control instruction corresponding to the preset action; Based on the control instruction, control parameters of at least part of the equipment are adjusted.

8. The method according to any one of claims 1 to 3, characterized in that: The indoor environment control system has multiple working modes, including automatic mode, manual mode and preset scene mode; Wherein, the adjusting of the control parameters of at least part of the indoor equipment based at least on the environmental parameter adjustment result is performed when the indoor environmental control system is in the automatic mode, or the parameter self-adjustment operation is performed when the indoor environmental control system is in the automatic mode; Preferably, the adjusting of the control parameters of at least part of the indoor equipment based at least on the environmental parameter adjustment result is performed when the indoor environment control system is in the automatic mode; when the indoor environment control system is in the manual mode, the method further includes: Based on the environmental parameter adjustment result, generating parameter adjustment suggestions; Sending the parameter adjustment suggestion to the user terminal; Preferably, when the indoor environment control system is in the preset scene mode, the method further includes: Identify the current scene; Generate an environmental parameter adjustment instruction corresponding to the current scene; Based on the environmental parameter adjustment instruction, control parameters of at least part of the equipment are adjusted.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: A computer program / instruction is stored, and when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images