Door and window self-adaptive regulation and control system and method based on AI multi-mode environment perception

Abstract

The invention discloses a door and window self-adaptive regulation and control system and method based on AI multi-mode environment perception, and relates to the technical field of intelligent control, and the method comprises the steps: obtaining environment perception data around a user residence, and air pressure data of doors and windows corresponding to all directions in the residence; on the basis of temperature data and humidity data in the environment sensing data, necessary regulation and control indexes of doors and windows at the current moment are obtained through calculation; on the basis of the air pressure data and the regulation and control necessary index, the required air flow intensity in the residence is obtained through calculation; and according to the air pressure difference corresponding to the required airflow intensity, a first door and window combination needing to be adjusted for adjusting and controlling air pressure is determined, so that the temperature and the air pressure in the residence of the user are adjusted and controlled. According to the invention, the self-adaptive regulation and control effect of doors and windows is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control, and particularly relates to a door and window adaptive regulation system and method based on AI multi-modal environment perception. BACKGROUND

[0002] With the development of artificial intelligence technology and Internet of Things technology, smart home technology is entering a stage of rapid development and change. When an AI large model is combined with a smart home device (for example, a smart door and window), the door and window can be adaptively regulated according to environment data. One of the main purposes of adaptive regulation of the door and window is to regulate the indoor environment.

[0003] In the related art, the automatic adjustment of the opening and closing states of the door and window can be realized according to sensor data to achieve intelligent control of the indoor environment. However, because there are usually multiple windows in different directions in a user's home, and different doors and windows make independent decisions, the door and window in different directions are easily affected by the environment in the direction where they are located, and cannot achieve the best regulation effect. SUMMARY

[0004] The main purpose of the present application is to provide a door and window adaptive regulation system and method based on AI multi-modal environment perception, which aims to solve the technical problem in the related art that different doors and windows make independent decisions, which easily leads to the door and window in different directions being affected by the environment in the direction where they are located, and cannot achieve the best regulation effect.

[0005] To achieve the above purpose, the embodiments of the present application provide a door and window adaptive regulation method based on AI multi-modal environment perception, which comprises: obtaining environment perception data around a user's residence and air pressure data at doors and windows corresponding to each direction inside the residence; based on temperature data and humidity data in the environment perception data, calculating a regulation necessary index of the door and window at the current time; based on the air pressure data and the regulation necessary index, calculating a required air flow intensity inside the residence; determining a first door and window combination required to adjust the regulation air pressure according to an air pressure difference corresponding to the required air flow intensity, to regulate the temperature and air pressure inside the user's residence.

[0006] In a possible implementation manner of the present application, based on temperature data and humidity data in the environment perception data, the regulation necessary index of the door and window at the current time is calculated, which comprises: obtaining an average temperature of the user using an air conditioner and an average power of the user using a humidifier; based on the average power, determining an average humidity inside the residence; According to the average humidity, the average temperature, the temperature data and the humidity data in the environment sensing data, a regulation necessity index of the door and window at the current time is calculated, and the average humidity and the average temperature are used to represent the suitable environment parameters of the user.

[0007] In a possible implementation of the present application, according to the average humidity, the average temperature, the temperature data and the humidity data in the environment sensing data, a regulation necessity index of the door and window at the current time is calculated, and the average humidity and the average temperature are used to represent the suitable environment parameters of the user. Based on the average temperature and the indoor and outdoor temperature data in the environment sensing data, a temperature regulation necessity index is calculated. Based on the average humidity and the indoor and outdoor humidity data in the environment sensing data, a humidity regulation necessity index is calculated. Based on the temperature regulation necessity index, the humidity regulation necessity index and the air quality index in the environment sensing data, the regulation necessity index of the door and window at the current time is determined.

[0008] In a possible implementation of the present application, based on the air pressure data and the regulation necessity index, a required air flow intensity in the residence is calculated, including: Based on the air pressure data, a first air pressure difference between the door and window in a target direction is calculated, and the target direction is any direction. Based on the first air pressure difference and the indoor and outdoor temperature difference at the current time, a maximum air flow intensity at the current time is calculated. A second air pressure difference between each door and window combination at the current time is determined, and a minimum air pressure difference in each second air pressure difference is extracted. Based on the minimum air pressure difference, a minimum air flow intensity at the current time is calculated. Based on the minimum air flow intensity, the maximum air flow intensity and the regulation necessity index, the required air flow intensity in the residence is calculated.

[0009] In a possible implementation of the present application, according to the air pressure difference corresponding to the required air flow intensity, a first door and window combination required to be adjusted for regulating air pressure is determined, including: A third air pressure difference required to reach the required air flow intensity is determined. Based on the second air pressure difference between any door and window combination and the third air pressure difference, an optimization degree of each door and window combination is calculated. The door and window combination corresponding to the maximum optimization degree is set as the door and window combination required to be adjusted for regulating air pressure.

[0010] In a possible implementation of the present application, the third air pressure difference required to reach the required air flow intensity is determined, including: The indoor and outdoor temperature difference at the current time and the height value of the residence are determined. The third air pressure difference value is calculated based on the indoor and outdoor temperature difference, the required air flow intensity, and the height value of the residence.

[0011] In a possible implementation of the present application, the first door and window combination required for regulating the air pressure is determined according to the air pressure difference corresponding to the required air flow intensity, and the method further comprises: Based on the location of the user in the residence, the influence index of the air flow on the user at the current time is calculated. In the case where the influence index is greater than the preset threshold, the suitability index corresponding to each door and window combination is calculated based on the preference degree and the influence index. The door and window combination corresponding to the maximum suitability index is set as the first door and window combination required for current regulation.

[0012] In a possible implementation of the present application, the influence index of the air flow on the user at the current time is calculated based on the location of the user in the residence, and the method comprises: Obtaining historical movement path data of the user in the residence and a first coordinate of the user at the current time; Based on the historical movement path data, a second coordinate of the user at the next time and a first probability corresponding to the second coordinate are determined. The air flow path in the residence is simulated through a preset neural network model, and the overlap degree of the air flow path and the location of the user is calculated based on the air flow path, the first coordinate, and the first probability. Based on the overlap degree and the required air flow intensity, the influence index of the air flow on the user at the current time is calculated.

[0013] In a possible implementation of the present application, after the door and window combination corresponding to the maximum suitability index is set as the first door and window combination required for current regulation, the method further comprises: In the case where the suitability index is greater than or equal to a preset suitability threshold, the opening degree of the first door and window combination is calculated based on the regulation necessity index and the influence index. In the case where the suitability index is less than the preset suitability threshold, the opening degree of the first door and window combination is calculated based on the regulation necessity index, the suitability index, and the influence index. The first door and window combination is opened or closed according to the opening degree.

[0014] The present application also provides a door and window adaptive regulation system based on AI multi-modal environment perception, which comprises: An acquisition module is configured to acquire environmental perception data of a user's residence and air pressure data of doors and windows in each direction inside the residence. The first calculation module is configured to calculate a regulation necessity index of the door and window at the current time based on temperature data and humidity data in the environment perception data. The second calculation module is configured to calculate a required air flow intensity inside the residence based on the air pressure data and the regulation necessity index. The regulation module is configured to determine a first door and window combination that needs to be adjusted to regulate the air pressure according to an air pressure difference corresponding to the required air flow intensity, so as to regulate the temperature and air pressure inside the residence of the user.

[0015] Compared with the related art, in which different doors and windows make independent decisions, the doors and windows of different orientations are easily affected by the environment of the orientation where they are located, and the best regulation effect cannot be achieved. In the present application, by obtaining the environment perception data around the residence of the user and the air pressure data at the doors and windows corresponding to each direction inside the residence, the regulation necessity index of the doors and windows at the current time is calculated based on the temperature data and humidity data corresponding to the environment perception data. Then, the required air flow intensity inside the residence is calculated based on the air pressure data and the regulation necessity index. Then, the first door and window combination that needs to be adjusted to regulate the air pressure is determined according to the air pressure difference corresponding to the required air flow intensity. Thus, the door and window combination that needs to be opened or closed is determined according to the required air flow intensity of the whole residence, and the whole temperature and air flow of the residence are regulated by the door and window combination. By determining the best door and window combination for regulation, the doors and windows of different orientations are prevented from being affected by the environment of the orientation where they are located, so that the self-adaptive regulation of the doors and windows achieves the best regulation effect. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 FIG. 1 is a flowchart of a first embodiment of the door and window self-adaptive regulation method based on AI multi-modal environment perception of the present application; Figure 2 FIG. 2 is a flowchart of a second embodiment of the door and window self-adaptive regulation method based on AI multi-modal environment perception of the present application; Figure 3 FIG. 3 is a device structure diagram of a hardware running environment involved in the embodiment of the present application. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0018] The embodiment of the present application provides a door and window self-adaptive regulation method based on AI multi-modal environment perception. In the first embodiment of the door and window self-adaptive regulation method based on AI multi-modal environment perception of the present application, referring to Figure 1 , the method comprises the following steps. Step S10, obtain the environmental perception data of the user's residence and the air pressure data of the doors and windows corresponding to each direction inside the residence; Step S20, based on the temperature data and humidity data in the environmental perception data, calculate the necessary index for regulating the doors and windows at the current time; Step S30, based on the air pressure data and the necessary index for regulating, calculate the required air flow intensity inside the residence; Step S40, according to the air pressure difference corresponding to the required air flow intensity, determine the first door and window combination required to adjust the air pressure, so as to regulate the temperature and air pressure inside the user's residence.

[0019] The embodiment aims to determine the best door and window combination for regulation, so as to avoid the influence of doors and windows of different orientations on the environment of their orientation, and achieve the best regulation effect of self-adaptive regulation of doors and windows.

[0020] The specific steps are as follows: Step S10, obtain the environmental perception data of the user's residence and the air pressure data of the doors and windows corresponding to each direction inside the residence.

[0021] As an example, the door and window self-adaptive regulation method based on AI multi-modal environmental perception can be applied to a door and window self-adaptive regulation device based on AI multi-modal environmental perception. The door and window self-adaptive regulation device based on AI multi-modal environmental perception belongs to a door and window self-adaptive regulation system based on AI multi-modal environmental perception, which belongs to a door and window self-adaptive regulation equipment based on AI multi-modal environmental perception.

[0022] As an example, the environmental perception data can be the temperature, humidity, air quality, wind speed and wind direction of the user's residence and the like.

[0023] As an example, the air pressure data can be collected by a micro air pressure gauge installed at the window of the residence, so as to monitor the air pressure inside and outside the residence.

[0024] Specifically, a control device for controlling the opening and closing of each door and window in the residence is installed, such as a hinge window opener, a sliding window motor, etc. For outdoor environmental monitoring, a raindrop sensor, a temperature and humidity sensor, a noise sensor and a PM2.5 / CO2 sensor are installed outside the window of the residence, and the monitoring contents of the sensors are as follows: Raindrop sensor: monitors the water droplets on the glass surface outside the residence to determine whether it is raining outside; Temperature and humidity sensor: used to monitor the real-time humidity and temperature outside the residence; It should be noted that the temperature and humidity sensor needs to be installed in a position where the sun cannot directly shine to prevent the sun from directly shining and causing the temperature to be too high, thereby causing data monitoring errors.

[0025] Noise sensor: used to monitor the noise outside the residence, including construction noise, traffic noise, etc. PM2.5 / CO2 sensor: used to monitor the air quality outside the residence.

[0026] For indoor environmental monitoring, in addition to temperature and humidity sensors, PM2.5 / CO2 sensors, a miniature barometer and a visual sensor (camera) are also installed inside the residence. The monitoring content of the sensors is as follows: Miniature barometer: installed at the window of the residence, used to monitor the air pressure inside and outside the residence; Visual sensor: installed in each room of the residence, used to monitor the security inside the residence and locate the user's position inside the residence.

[0027] It should be noted that while collecting data through sensors, the system also determines the weather conditions of the current area through the Internet and GPS, including climate, wind speed, wind direction, etc.

[0028] After completing the arrangement of the above-mentioned multi-modal sensors, the environmental information inside and outside the residence is monitored according to the preset working parameters of each sensor, and the obtained monitoring data is uploaded to the adaptive control system. The obtained data is preprocessed and stored in the designated area of the system.

[0029] Step S20, based on the temperature data and humidity data in the environmental perception data, the control necessary index of the door and window at the current time is calculated.

[0030] As an example, the temperature data is the temperature data inside and outside the residence, and the humidity data is the temperature data inside and outside the residence. By collecting the temperature and humidity inside and outside the house, combined with the user's usual suitable temperature parameters, it is determined whether the environmental information inside the house is the user's suitable environmental information, for example, whether the temperature meets the user's usual suitable temperature requirements, etc. When the indoor environment does not meet the user's suitable living standards, the opening and closing of the door and window need to be adjusted to adjust the environmental parameters (temperature, humidity and air flow, etc.) inside the house.

[0031] As an example, the control necessary index is used to represent the necessity of adjusting the indoor environmental parameters through the door and window. The closer the outdoor environment is to the suitable environmental parameters, the larger the control necessary index, and the higher the control necessity.

[0032] Among them, the step S20 of calculating the control necessary index of the door and window at the current time based on the temperature data and humidity data in the environmental perception data further includes steps S21-S23, including: Step S21, obtaining the average temperature of the air conditioner used by the user and the average power of the humidifier used.

[0033] As an example, the average temperature is calculated by the collected air conditioner usage data, and the average power is calculated by the collected humidifier usage data.

[0034] As an example, first, collect the user's air conditioner and humidifier usage data, including the first air conditioner temperature , the humidifier power and the device working time , ; then, taking the working time as the weight, calculate the average temperature , average power of the user using the air conditioner or humidifier.

[0035] As an example, the calculation method of the average temperature may be: wherein, represents the number of times of using the air conditioner; represents the total use time of the air conditioner, which can be monitored by the sensor arranged on the air conditioner, and the total use time can be the air conditioner use time within a week, i.e. the sum of all air conditioner use times, represents the time proportion of the air conditioner in the time use, represents the air conditioner temperature in the time use.

[0036] As an example, the calculation method of the average power may be: wherein, represents the number of times of using the humidifier; represents the total use time of the humidifier, which can be monitored by the sensor arranged on the humidifier, and the total use time can be the humidifier use time within a week, i.e. the sum of all humidifier use times, represents the time proportion of the humidifier in the time use, represents the humidifier power in the time use.

[0037] Step S22, determining the average humidity in the residence based on the average power.

[0038] As an example, when the average power of the humidifier The larger it is, the greater the humidity in the house will be. Combined with the size of the house and the humidity influence coefficient per unit power of the humidifier, the average humidity in the house can be determined.

[0039] As an example, the average humidity The calculation method can be: in, Indicates the ambient humidity of the area; Indicates the room area, Indicates the room height, Indicates the coefficient of influence of humidifier on room humidity; Indicates the conversion coefficient between humidifier power and humidity, Indicates the impact of current power on humidity. The conversion coefficient can be obtained from the factory information of the humidifier.

[0040] Step S23, based on the average humidity, average temperature, temperature data and humidity data in the environmental perception data, calculate the necessary index for regulating doors and windows at the current moment. The average humidity and average temperature are used to characterize the user's suitable environmental parameters.

[0041] As an example, the average temperature , average humidity That is, the user's suitable environmental parameters. According to the temperature and humidity of the indoor and outdoor environment, as well as the user's suitable environmental parameters, the necessary index of door and window regulation at the current moment is determined, that is, the necessity of door and window regulation.

[0042] The step S23 of calculating the necessary index for controlling doors and windows at the current moment based on the average humidity, average temperature, and temperature and humidity data in the environmental sensing data includes: Based on the average temperature and indoor and outdoor temperature data in the environmental perception data, the necessary temperature control index is calculated.

[0043] As an example, based on the user's average temperature , combined with the indoor temperature at the current moment (taking moment t as an example) , outdoor temperature , calculate the Time temperature control necessary index , that is, the closer the outdoor environment is to the suitable environmental parameters, the higher the necessity of regulation. Among them, the temperature regulation necessity index The calculation method can be: Among them, norm() is the normalization function, Used to prevent the denominator from being 0.

[0044] Based on the average humidity and the indoor and outdoor humidity data in the environmental perception data, the humidity regulation necessity index is calculated.

[0045] As an example, the humidity regulation necessity index may be calculated as follows: wherein, represents the average humidity, represents the indoor humidity, represents the outdoor humidity, and norm() is a normalization function. is used to prevent the denominator from being 0.

[0046] Based on the temperature regulation necessity index, the humidity regulation necessity index, and the air quality index in the environmental perception data, the regulation necessity index of the door and window at the current time is determined.

[0047] As an example, according to the temperature regulation necessity index and the humidity regulation necessity index, and in combination with the difference in air quality between the indoor and outdoor, the regulation necessity index of the door and window at the current time is determined, wherein the regulation necessity index of the door and window adaptive regulation at the time may be calculated as follows: wherein, and respectively represent the air quality index of the outdoor and the indoor; represents the temperature regulation necessity index, represents the humidity regulation necessity index, and norm() represents a normalization function, wherein f() represents a sigmoid function with a value range of [0, 1].

[0048] In step S30, based on the air pressure data and the regulation necessity index, the required air flow intensity inside the residence is calculated.

[0049] As an example, when the regulation of the opening and closing state of the door and window is needed to achieve the regulation of the environment inside the residence, since different combinations of doors and windows will cause different adjustment effects on the environment inside the residence (different combinations of doors and windows, different paths of air flow, and different influences on the indoor environment), in order to be closer to the user's suitable environment parameters, the environmental difference between the indoor and outdoor of the residence and the opening combination of the door and window need to be analyzed, and according to the regulation necessity index and the air pressure data of each window, the required air flow intensity inside the residence is calculated.

[0050] As an example, when the required temperature and humidity are reached in a residence, there will be a corresponding air pressure value. It is necessary to analyze the difference between the current air pressure value in the house and the required air pressure value to determine the airflow intensity required after opening the window so that the interior of the residence can reach the user's suitable environmental parameters. The airflow intensity value calculated at this time is the required airflow intensity.

[0051] The step S30 of calculating the required airflow intensity inside the residence based on the air pressure data and the necessary control index includes: Based on the air pressure data, a first air pressure difference between doors and windows corresponding to a target direction is calculated, where the target direction is any direction.

[0052] As an example, the embodiments of the present application are mainly used in the scenario of through-draft control in a house. Through-draft is a common phenomenon in houses with north-south or east-west ventilation. That is, by opening the windows on both sides, the outside wind is allowed to pass through the house, thereby taking away the odor and heat in the house, and achieving the purpose of ventilation and heat dissipation. However, in the actual control process, it may happen that one side of the window is exposed to strong sunlight, while the other side of the window is exposed to weak light. At this time, because different doors and windows make independent decisions, the side with strong sunlight may close the window to avoid the temperature rise in the house due to exposure to the sun. Since the through-draft duct is cut off, a negative pressure vortex is formed on the other side with weak light, causing whistling noise, which in turn affects the rest of the residents.

[0053] As an example, windows of different orientations are classified according to the user's residence structure. In the living room, there is often at least one pair of north-south or east-west windows to increase ventilation inside the house. There may also be doors and windows facing opposite directions between different bedrooms. The target direction is based on the first For example, the corresponding doors and windows are The direction of window, and for the The opposite direction of the direction is recorded as The direction of A window.

[0054] As an example, according to The direction of Air pressure at the window , calculate the residence The average air pressure in each direction ; Further, calculate the residence The average air pressure in each direction The average air pressure in the opposite direction The difference , take the absolute value of the difference Recorded as The first air pressure difference in the direction.

[0055] Based on the first air pressure difference value and the indoor-outdoor temperature difference at the current time, the maximum air flow intensity at the current time is calculated.

[0056] As an example, according to the first air pressure difference value and the indoor-outdoor temperature difference at the current time, the maximum air flow intensity at the current time is calculated. The maximum air flow intensity at the current time is calculated based on the first air pressure difference value and the indoor-outdoor temperature difference at the current time. The maximum air flow intensity at the current time is calculated based on the first air pressure difference value and the indoor-outdoor temperature difference at the current time. It is to be noted that when there is a temperature difference between the indoor and outdoor, the higher the indoor-outdoor temperature difference, the stronger the air flow intensity generated, and the value is proportional to the floor height of the residence. The calculation method of the maximum air flow intensity can be: wherein, is the first air pressure difference value, represents the floor height of the residence, represents the indoor-outdoor temperature difference, and are normalized before calculation.

[0057] The second air pressure difference value between each door and window combination at the current time is determined, and the minimum air pressure difference in each second air pressure difference value is extracted.

[0058] As an example, the second air pressure difference value is the air pressure difference between the door and window combinations in any opposite direction except the target direction of the door and window combination at the current time. After determining the second air pressure difference value between each door and window combination, the minimum value in the plurality of second air pressure difference values is selected , to obtain the minimum air pressure difference, which is represented as .

[0059] Based on the minimum air pressure difference, the minimum air flow intensity at the current time is calculated.

[0060] As an example, according to the calculation method of the maximum air flow intensity, the minimum air flow intensity at the current time can be calculated based on the minimum air pressure difference.

[0061] Based on the minimum air flow intensity, the maximum air flow intensity, and the regulation necessity index, the required air flow intensity inside the residence is calculated.

[0062] As an example, based on the minimum air flow intensity and the maximum air flow intensity, the air flow intensity range generated in the residence after regulating the opening and closing state of the door and window at the current time (the time) is determined.

[0063] ​​​​​Further, in combination with the first control necessary index , and the second airflow intensity range generated in the house at the third time , the required airflow intensity of the house at the third time wherein MS represents the house area, H represents the room height, represents the control necessary index, represents the maximum airflow intensity, norm represents the normalization function, and the value range is [0, 1].

[0064] It should be noted that the minimum airflow intensity is not used in the formula, but the minimum airflow intensity determines the lower limit of the required airflow intensity. When the required airflow intensity of the house at the third time is determined, the required airflow intensity of the house at the third time is determined.

[0065] Step S40, according to the air pressure difference corresponding to the required airflow intensity, determining the first door and window combination required to adjust the air pressure, so as to control the temperature and air pressure in the user's house.

[0066] As an example, the required airflow intensity corresponds to an air pressure difference. According to the air pressure difference, the air pressure difference value of each door and window required to be controlled is determined, and then the door and window combination required to be controlled is selected to control the temperature and air pressure in the user's house.

[0067] As an example, the door and window combination can be in the same direction or in different directions. The purpose of selecting the door and window combination is to make the process of controlling the door and window not affected by the environment in each direction, so as to realize overall control, so that the internal environment of the house reaches the user's required suitable environment standard.

[0068] wherein the step S40 of determining the first door and window combination required to adjust the air pressure according to the air pressure difference corresponding to the required airflow intensity, comprises: determining the third air pressure difference value required to reach the required airflow intensity again; As an example, in combination with the minimum required airflow intensity of the house at the third time , the third air pressure difference value required to reach the airflow intensity is determined again ; wherein the step of determining the third air pressure difference value required to reach the required airflow intensity again, comprises: determining the indoor-outdoor temperature difference and the height of the residence at the current time; calculating a third air pressure difference value based on the indoor-outdoor temperature difference, the required air flow intensity, and the height of the residence.

[0069] As an example, the third air pressure difference value may be calculated as follows: wherein, represents the required air flow intensity, represents the height of the floor where the residence is located, represents the indoor-outdoor temperature difference, and and are normalized respectively before calculation, to prevent the denominator from being 0.

[0070] calculating the preference degree of each door and window combination based on the second air pressure difference value and the third air pressure difference value between any door and window combination; As an example, the preference degree of the first door and window combination at the first time is calculated based on the second air pressure difference value between any two windows in any two directions in the residence at the first time, and the third air pressure difference value required to achieve the air flow intensity. wherein, to prevent the denominator from being 0.

[0071] setting the door and window combination corresponding to the maximum preference degree as the door and window combination that needs to be adjusted for air pressure regulation.

[0072] As an example, the door and window combination with the maximum preference degree is selected and set as the door and window combination that needs to be automatically regulated, and the opening degree of the door and window combination is controlled to adjust the temperature and humidity in the residence. The door and window combination is not limited to windows, but also includes sliding glass doors and other doors that can be automatically controlled.

[0073] ​​The application provides a door and window self-adaptive regulation method based on AI multi-modal environment perception. Compared with the related art, in which different doors and windows make independent decisions, the doors and windows of different orientations are easily affected by the environment of their orientation, and the best regulation effect cannot be achieved. In the application, environment perception data around the user's residence and air pressure data at the doors and windows corresponding to each direction inside the residence are obtained. Based on the temperature data and humidity data corresponding to the environment perception data, the regulation necessity index of the doors and windows at the current time is calculated. Then, based on the air pressure data and the regulation necessity index, the required air flow intensity inside the residence is calculated. Then, according to the air pressure difference corresponding to the required air flow intensity, the first door and window combination required to adjust the air pressure is determined. Thus, the door and window combination required to be opened or closed is determined according to the required air flow intensity of the whole residence. The overall temperature and air flow of the residence are regulated by the door and window combination. By determining the best door and window combination for regulation, the doors and windows of different orientations are prevented from being affected by the environment of their orientation, so that the self-adaptive regulation of the doors and windows achieves the best regulation effect.

[0074] Further, with reference to Figure 2 Based on the first embodiment of the application, another embodiment of the application is provided. After the step S40 of determining the first door and window combination required to adjust the air pressure according to the air pressure difference corresponding to the required air flow intensity, the embodiment further includes: Step S50, calculating the influence index of the air flow on the user at the current time based on the location of the user in the residence. As an example, by positioning the location of the user in the residence, the influence index of the air flow on the user under the current opening and closing state is determined, and then the opening and closing state of the door and window is adjusted.

[0075] As an example, in the process of self-adaptive regulation of the door and window, the direct influence of the environment on the user also needs to be considered. For example, when the user is on the air flow path, the fast wind speed and large air volume will cause the user to feel uncomfortable, or when the window is opened, the strong light will shine on the user, causing the user to feel burning, etc., reducing the comfort of the user. Therefore, the opening and closing state of the door and window needs to be further adjusted according to the user's location.

[0076] As an example, the influence index is used to represent the influence degree of the air flow on the user. The greater the influence index, the greater the influence degree.

[0077] The step S50 of calculating the influence index of the air flow on the user at the current time based on the location of the user in the residence includes: Obtaining historical moving path data of the user in the residence and a first coordinate of the user at the current time.

[0078] As an example, through a camera or the like, historical movement path data of a user in a public area is acquired, and a first coordinate where the user is currently located is determined.

[0079] Based on the historical movement path data, a second coordinate where the user is located at a next time point and a first probability corresponding to the second coordinate are determined.

[0080] As an example, based on the historical movement path data of the user, a second coordinate where the user is likely to be located at a next time point after the current time point and a first probability corresponding to the second coordinate are calculated.

[0081] It should be noted that when determining the probability of being in different positions, a three-dimensional coordinate system is constructed in the room to determine the coordinate of the position where the user is located, and then the probability is determined by the number of times the coordinate appears, and then the current position of the current user (t time point) and the possible position and the first probability of the next time point (t+1 time point) determined by the above process are combined , wherein r represents the second coordinate where the user is likely to appear at the next time point, and t+1 represents the t+1 time point.

[0082] The first probability can be obtained by taking the current position of the user as a reference, counting the number of times the position coordinate appears at the next time point (t+1 time point) when the user is at the current position in the historical movement path data. For example, the number of times of moving to position A at the next time point is 2, the number of times of moving to position B is 5, and the number of times of moving to position C is 3. The first probability corresponding to position A is 2 / 10, the first probability corresponding to position B is 1 / 2, and the first probability corresponding to position A is 3 / 10.

[0083] The air flow path in the residence is simulated by a preset neural network model, and based on the air flow path, the first coordinate and the first probability, the degree of overlap between the air flow path and the position where the user is located is calculated.

[0084] As an example, according to the known adaptive control door and window combination and the current user residence structure, the air flow path is simulated by an artificial intelligence model, and the degree of overlap between the air flow path and the position where the user is located at the t time point is calculated combined with the position where the user is located in the residence at the t time point and the possible position where the user is located at the next time point, and the simulated air flow path , wherein represents an overlap judgment coefficient of the air flow path and the position of the user at the t time point, represents an overlap judgment coefficient of the air flow path and the position of the user at the t+1 time point when the user is at the second coordinate. When the air flow path passes through the user, it is judged as overlapping, and when it overlaps ​, vice versa when not overlapping ; represents the number of times of overlapping between the airflow path and the possible position of the user at the next time, represents the first probability.

[0085] Based on the degree of overlapping and the required airflow intensity, the influence index of the airflow on the user at the current time is calculated.

[0086] As an example, based on the degree of overlapping, the first required airflow intensity of the dwelling at the first time , the influence index of the airflow on the user at the first time is determined When the degree of overlapping is higher and the airflow intensity is greater, the influence of the airflow on the user is greater, and the influence index The calculation method of the influence index can be: wherein norm() represents a normalization function, represents the degree of overlapping.

[0087] Step S60, in the case where the influence index is greater than a preset threshold, based on the preference degree and the influence index, the suitability index corresponding to each door and window combination is calculated.

[0088] As an example, when the influence index of the airflow on the user at the first time is greater than the preset threshold, it indicates that the airflow has a great influence on the user's life at this time, and therefore the current door and window combination does not meet the requirements, and the door and window combination is selected according to the preference degree of the door and window combination, and the suitability index corresponding to each door and window combination is calculated.

[0089] As an example, in combination with the preference degree of the first door and window combination and the influence index of the airflow on the user at the first combination, the suitability index of the first door and window combination is calculated : wherein norm() represents a normalization function, for preventing the denominator from being zero.

[0090] Step S70, the door and window combination corresponding to the maximum suitability index is set as the first door and window combination required for the current regulation and control.

[0091] As an example, the suitability index ​​​​The maximum door and window combination is the door and window combination currently being adaptively regulated.

[0092] The method further comprises, after step S70 of setting the door and window combination corresponding to the maximum suitability index as the first door and window combination required for current regulation, the following steps: In the case where the suitability index is greater than or equal to the preset suitability threshold, the opening and closing degree of the first door and window combination is calculated based on the regulation necessity index and the influence index.

[0093] As an example, in the case where the suitability index is greater than or equal to the preset suitability threshold, the opening and closing degree of the first door and window combination is calculated based on the regulation necessity index and the influence index. The regulation necessity index of the kth door and window combination at the moment The influence index of the air flow on the user The opening and closing degree of the current door and window combination is calculated based on the regulation necessity index The greater the regulation necessity index and the smaller the influence index , the greater the opening and closing degree of the window, and the greater the opening and closing degree means the greater the opening, and vice versa.

[0094] It should be noted that the value range of the opening and closing degree of the window is [0, 1], i.e., when the opening and closing degree is equal to 1, the window is fully open, and when the opening and closing degree is equal to 0, the window is fully closed.

[0095] As an example, the preset suitability threshold can be 0.7, 0.8, etc., and is not limited in particular.

[0096] As an example, when the suitability index of the door and window combination is greater, the upper limit of the opening degree of the window is higher, and taking the preset suitability threshold of 0.8 as an example, it is stipulated that when the suitability index of the kth door and window combination is , the value range of the opening and closing degree is [0, 1], and vice versa, i.e., the value range of the opening and closing degree is [0, ].

[0097] As an example, in the case where the suitability index is greater than or equal to the preset suitability threshold, the opening and closing degree is calculated in the following manner: wherein represents the regulation necessity index, represents the influence index, and the denominator is used to prevent the denominator from being zero.

[0098] In the case where the suitability index is less than the preset suitability threshold, the opening and closing degree of the first door and window combination is calculated based on the regulation necessity index, the suitability index, and the influence index.

[0099] ​As an example, in the case that the suitability index is less than a preset suitability threshold, the opening degree of the door and window The calculation manner can be: wherein, represents the suitability index, represents the regulation necessity index, represents the influence index, is used to prevent the denominator from being zero.

[0100] In this embodiment, in the process of self-adaptive regulation of the doors and windows in the residence, the risks outside the residence also need to be considered. For example, when it is raining, snowing, or hailing, or when a stranger stays outside the door for a long time, the risk outside the house is greater. At the same time, users on lower floors also need to consider whether there is a possibility that a stranger will invade the house from the window. The artificial intelligence technology is used to intelligently judge the above-mentioned risk conditions, and when a risk occurs, the doors and windows of the residence are closed and warning information is sent to the user through the APP.

[0101] In this embodiment, by calculating the influence degree of the air flow on the user and the regulation necessity index of the door and window, the opening degree of the door and window combination is determined, so as to improve the comfort of the user in the residence.

[0102] The application also provides a door and window self-adaptive regulation system based on AI multi-modal environment perception, which comprises: An acquisition module, which is used to acquire environment perception data around a user's residence and air pressure data at doors and windows corresponding to each direction inside the residence; A first calculation module, which is used to calculate a regulation necessity index of the door and window at the current time based on temperature data and humidity data in the environment perception data; A second calculation module, which is used to calculate a required air flow intensity inside the residence based on the air pressure data and the regulation necessity index; A regulation module, which is used to determine a first door and window combination that needs to be adjusted to regulate the air pressure according to an air pressure difference corresponding to the required air flow intensity, so as to regulate the temperature and air pressure inside the user's residence.

[0103] Referring to Figure 3 , Figure 3 is a device structure diagram of a hardware running environment involved in the embodiment of the application.

[0104] As Figure 3As shown, the door and window adaptive regulation device based on AI multi-modal environment perception can include a processor 1001, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize the connection communication between the processor 1001 and the memory 1005.

[0105] Optionally, the door and window adaptive regulation device based on AI multi-modal environment perception can further include a user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, a WiFi module, and the like. The user interface can include a display screen (Display), an input sub-module such as a keyboard (Keyboard), and the optional user interface can further include a standard wired interface, a wireless interface. The network interface can include a standard wired interface, a wireless interface (such as a WI-FI interface).

[0106] Those skilled in the art can understand that Figure 3 The structure of the door and window adaptive regulation device based on AI multi-modal environment perception shown in the figure does not constitute a limitation on the door and window adaptive regulation device based on AI multi-modal environment perception, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0107] As Figure 3 As shown, the memory 1005 as a storage medium can include an operating system, a network communication module, and a door and window adaptive regulation program based on AI multi-modal environment perception. The operating system is a program that manages and controls the hardware and software resources of the door and window adaptive regulation device based on AI multi-modal environment perception, supports the running of the door and window adaptive regulation program based on AI multi-modal environment perception and other software and / or programs. The network communication module is used to realize the communication between the components in the memory 1005, and the communication between other hardware and software in the door and window adaptive regulation system based on AI multi-modal environment perception.

[0108] In Figure 3 In the door and window adaptive regulation device based on AI multi-modal environment perception, the processor 1001 is used to execute the door and window adaptive regulation program based on AI multi-modal environment perception stored in the memory 1005, and realize the steps of any one of the door and window adaptive regulation methods based on AI multi-modal environment perception described above.

[0109] The specific embodiments of the door and window adaptive regulation device based on AI multi-modal environment perception of the present application are basically the same as the above-mentioned embodiments of the door and window adaptive regulation method based on AI multi-modal environment perception, and will not be repeated here.

[0110] It should be noted that, in the present document, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0111] The above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0112] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, and of course, they can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods of various embodiments of the present application.

[0113] The above is only the preferred embodiment of the present application, and does not limit the application range of the present application. Any equivalent structure or equivalent flow transformation made by using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, is also included in the application protection range of the present application.

[0114] It should be noted that: the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0115] Each of the embodiments in the present specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the differences from other embodiments.

Claims

1. A door and window adaptive control method based on AI multimodal environment perception, characterized in that: The method comprises: Obtain environmental perception data around the user's residence, as well as air pressure data at doors and windows in all directions inside the residence; Calculate the necessary index for controlling doors and windows at the current moment based on the temperature data and humidity data in the environmental sensing data; Calculating the required airflow intensity inside the residence based on the air pressure data and the control necessity index; According to the air pressure difference corresponding to the required airflow intensity, the first door and window combination that needs to be adjusted for regulating the air pressure is determined to regulate the temperature and air pressure inside the user's residence.

2. The door and window adaptive control method based on AI multimodal environmental perception according to claim 1, characterized in that: The step of calculating the necessary index for controlling doors and windows at the current moment based on the temperature data and humidity data in the environmental sensing data includes: Get the average temperature of the air conditioner and the average power of the humidifier used by the user; determining an average humidity within the residence based on the average power; The necessary index for regulating doors and windows at the current moment is calculated based on the average humidity, the average temperature, and the temperature and humidity data in the environmental perception data. The average humidity and the average temperature are used to characterize the suitable environmental parameters for the user.

3. The door and window adaptive control method based on AI multimodal environmental perception according to claim 2, characterized in that: The step of calculating the necessary index for controlling doors and windows at the current moment based on the average humidity, the average temperature, and the temperature and humidity data in the environmental sensing data includes: Calculating a temperature control necessary index based on the average temperature and indoor and outdoor temperature data in the environmental sensing data; Calculating a necessary humidity control index based on the average humidity and indoor and outdoor humidity data in the environmental sensing data; Based on the temperature control necessity index, the humidity control necessity index and the air quality index in the environmental perception data, the control necessity index of the doors and windows at the current moment is determined.

4. The door and window adaptive control method based on AI multimodal environment perception according to claim 1, characterized in that: The step of calculating the required airflow intensity inside the residence based on the air pressure data and the necessary control index includes: Calculating a first air pressure difference between doors and windows corresponding to a target direction based on the air pressure data, where the target direction is any direction; Calculating the maximum airflow intensity at the current moment based on the first air pressure difference and the temperature difference between indoor and outdoor at the current moment; Determine the second air pressure difference between each door and window combination at the current moment, and extract the minimum air pressure difference among each of the second air pressure differences; Based on the minimum air pressure difference, the minimum airflow intensity at the current moment is calculated; The required airflow intensity inside the residence is calculated based on the minimum airflow intensity, the maximum airflow intensity and the control necessity index.

5. The door and window adaptive control method based on AI multimodal environment perception according to claim 4 is characterized in that: The determining of the first door and window combination required to adjust the air pressure according to the air pressure difference corresponding to the required airflow intensity includes: determining a third air pressure difference required to re-achieve the required airflow intensity; Based on the second air pressure difference and the third air pressure difference between any door and window combinations, calculating the preference of each door and window combination; The door and window combination corresponding to the maximum preference value is set as the first door and window combination required to be adjusted for regulating the air pressure.

6. The door and window adaptive control method based on AI multimodal environment perception according to claim 5 is characterized in that: Determining the third air pressure difference required to re-achieve the required airflow intensity includes: Determine the current temperature difference between indoor and outdoor temperatures and the height of the residence; A third air pressure difference is calculated based on the indoor and outdoor temperature difference, the required airflow intensity, and the residence height.

7. The method for adaptively controlling doors and windows based on AI multimodal environmental perception according to claim 5, characterized in that: The step of determining the first door and window combination that needs to be adjusted to control the air pressure according to the air pressure difference corresponding to the required airflow intensity further includes: Calculate the impact index of airflow on the user at the current moment based on the user's location in the residence; When it is determined that the influence index is greater than a preset threshold, the suitability index corresponding to each door and window combination is calculated based on the preference and the influence index; The door and window combination corresponding to the maximum value of the suitability index is set as the first door and window combination required for the current regulation.

8. The method for adaptively controlling doors and windows based on AI multimodal environmental perception according to claim 7, characterized in that: The calculation of the airflow impact index on the user at the current moment based on the user's location in the residence includes: Obtain the user's historical movement path data within the residence and the user's current first coordinates; Determining, based on the historical movement path data, a second coordinate of the user at a next moment and a first probability corresponding to the second coordinate; simulating an airflow path within the residence using a preset neural network model, and calculating a degree of overlap between the airflow path and the user's location based on the airflow path, the first coordinate, and the first probability; Based on the overlap degree and the required airflow intensity, an impact index of the airflow on the user at the current moment is calculated.

9. The method for adaptively controlling doors and windows based on AI multimodal environmental perception according to claim 7, characterized in that: After setting the door and window combination corresponding to the maximum suitability index as the first door and window combination required for current regulation, the method further includes: When the suitability index is greater than or equal to a preset suitability threshold, the degree of opening and closing of the first door and window combination is calculated based on the control necessity index and the influence index; When the suitability index is less than a preset suitability threshold, the degree of opening and closing of the first door and window combination is calculated based on the control necessity index, the suitability index, and the influence index; The first door and window assembly is opened or closed according to the opening and closing degree.

10. An adaptive door and window control system based on AI multimodal environmental perception, characterized in that: The door and window adaptive control system based on AI multimodal environmental perception includes: An acquisition module is used to acquire environmental perception data around the user's residence, as well as air pressure data at doors and windows corresponding to various directions inside the residence; a first calculation module, configured to calculate a necessary index for regulating doors and windows at a current moment based on the temperature data and humidity data in the environmental sensing data; a second calculation module, configured to calculate a required airflow intensity inside the residence based on the air pressure data and the control necessity index; A control module is used to determine the first door and window combination that needs to be adjusted to control the air pressure based on the air pressure difference corresponding to the required airflow intensity, so as to control the temperature and air pressure inside the user's residence.

Images