Temperature adjusting equipment, control method and device thereof, electronic equipment and storage medium

Abstract

The invention provides temperature adjusting equipment and a control method and device thereof, electronic equipment and a storage medium, and the method comprises the steps: carrying out the data collection of an in-bed user in a target space, and obtaining a target position point set of the in-bed user; determining bed position information of a bed in the target space according to the target position point set; and controlling the temperature adjusting equipment according to the bed position information. According to the embodiment of the invention, the position of the bed in the target space can be accurately recognized, and the intelligent strategy of the air conditioner is driven based on the recognition result, so that the comfort, the energy-saving property and the user experience are improved.

Description

Technical Field

[0001] This application belongs to the technical field of temperature regulation equipment control, specifically relating to a temperature regulation equipment and its control method, device, electronic equipment and storage medium. Background Technology

[0002] In related technologies, temperature control devices can be set to sleep mode to create a comfortable sleeping environment for users by adjusting the temperature, fan speed, etc. while they are sleeping; however, this still cannot avoid the problem of the air blown by the temperature control device blowing directly on the user while they are sleeping. Summary of the Invention

[0003] In view of the above problems, a temperature regulation device, control method, apparatus, electronic device, and storage medium are proposed to overcome or at least partially solve the above problems, including: A method for controlling a temperature regulating device, the temperature regulating device being used to regulate the temperature of a target space, the method comprising: Data is collected from the bed users in the target space to obtain the target location point set of the bed users; Based on the target location point set, determine the bed location information of the bed in the target space; The temperature control device is controlled based on the bed location information.

[0004] In some embodiments, determining the bed location information in the target space based on the target location point set includes: The dimensions of the bed are determined based on the target location point set. Based on the target location point set, determine the center point information and major axis direction information of the bed; The bed position information is determined based on the size information, the center point information, and the major axis direction information.

[0005] In some embodiments, the target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; the size information shown includes bed length information and bed width information; Determining the bed's dimensions based on the target location point set includes: From the set of target location points, determine the maximum lateral coordinate, the minimum lateral coordinate, the maximum longitudinal coordinate, and the minimum longitudinal coordinate; Calculate the first difference between the maximum horizontal coordinate and the minimum horizontal coordinate, and the second difference between the maximum vertical coordinate and the minimum vertical coordinate; The bed length information and bed width information are determined based on the first difference and the second difference.

[0006] In some embodiments, the target location point set includes multiple time-segmented subsets, each subset including multiple location point information; determining the bed length information and bed width information based on the first difference and the second difference includes: Determine the first discrete interval to which the first difference is mapped, and determine the first length information based on the first discrete interval; Determine the second discrete interval to which the second difference is mapped, and determine the second length information based on the second discrete interval; Based on multiple first length information, determine the first length information of the target; and based on multiple second length information, determine the second length information of the target; Based on the first length information and the second length information of the target, the bed length information and the bed width information are determined.

[0007] In some embodiments, determining the target first length information based on a plurality of first length information includes: By statistically analyzing the frequencies of multiple first-length information values, the first probability of each first-length information value is obtained. The first length information with a first probability exceeding a first threshold is taken as the first length information of the target; When the first probability of the first length information of each value does not exceed the first threshold, the first length information with the highest first probability is taken as the target first length information; or, when the first probability of the first length information of each value does not exceed the first threshold, the first length information of the first value is taken as the target first length information.

[0008] In some embodiments, the target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; determining the center point information and major axis direction information of the bed based on the target location point set includes: Based on the target location point set, determine the horizontal average coordinates and the vertical average coordinates, and based on the horizontal average coordinates and the vertical average coordinates, determine the center point information; Principal component analysis is performed on the target location point set, and the major axis direction information is determined based on the direction of the first principal component.

[0009] In some embodiments, determining the bed position information based on the size information, the center point information, and the major axis direction information includes: Using the center point information as the center of the bed, and based on the size information and the major axis direction information, the coordinate range information of the bed is determined; The bed location information is determined based on the coordinate range information.

[0010] In some embodiments, controlling the temperature regulation device based on the bed location information includes: Based on the bed location information, determine the location information of the target body part of the bed user; The angle of the air vent of the temperature regulating device is adjusted according to the location information of the aforementioned part.

[0011] In some embodiments, the method further includes: Acquire multimodal data and determine the user's status based on the multimodal data; the user's status includes whether they are in bed or out of bed. The temperature control device is controlled according to the user's status.

[0012] This application embodiment also provides a control device for a temperature regulating device, the temperature regulating device being used to regulate the temperature of a target space, the device comprising: The point set determination module is used to collect data on the bed users in the target space to obtain the target location point set of the bed users. The bed location determination module is used to determine the bed location information of the bed in the target space based on the target location point set; The equipment control module is used to control the temperature regulation equipment based on the bed position information.

[0013] This application also provides a temperature regulating device, which uses the control method for the temperature regulating device described above.

[0014] This application also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the control method of the temperature regulation device described above.

[0015] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described control method for a temperature regulating device.

[0016] The embodiments of this application have the following advantages: In this embodiment, data is collected from users in bed within the target space to obtain a set of target location points for those users. Based on this set of target location points, the bed's location information within the target space is determined. Based on the bed's location information, the temperature control equipment is controlled. This embodiment allows for accurate identification of the bed's location within the target space, and the identification results drive intelligent air conditioning strategies to improve comfort, energy efficiency, and user experience. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a flowchart illustrating the steps of a control method for a temperature regulating device according to an embodiment of this application; Figure 2 This is a flowchart illustrating the steps of a control method for a temperature regulating device according to another embodiment of this application. Figure 3 This is a system flowchart of an embodiment of this application; Figure 4 This is a flowchart of a bed calculation method according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a control device for a temperature regulating device according to an embodiment of this application. Detailed Implementation

[0018] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] With the popularization of smart homes and smart air conditioners, indoor environmental control is shifting from "fixed-point control" to "sensor-driven personalized control".

[0020] Modern air conditioning systems have the ability to control temperature, humidity, wind speed, and wind direction, as well as to connect with other smart devices, but their ability to sense "user space (such as bed)" is still limited.

[0021] Traditional methods based on infrared pyroelectric (PIR) or cameras suffer from drawbacks such as low recognition accuracy, high privacy risks, insufficient capture of micro-motions, or susceptibility to light.

[0022] Millimeter-wave radar (mmWave) has become an ideal sensing solution for indoor human position and activity detection due to its advantages of penetrating smoke, being usable in low-light environments, and accurately capturing human body micro-movements and spatial coordinates.

[0023] While the relevant technologies can detect the presence or movement of a human body, they cannot perform long-term statistical identification of "bed contours / sizes and angles" and use the results for automated adjustment of air conditioning supply strategies.

[0024] In particular, in sleep scenarios, it is necessary to distinguish between the "heat dissipation needs at the moment of entering the bed" and the "comfort and avoidance of direct airflow needs after falling asleep," and to achieve directional airflow by taking into account the orientation and size of the bed.

[0025] Existing technologies still suffer from insufficient accuracy, robustness, and practicality in automatically identifying beds, inferring bed length, width, and orientation from micro-motion sequences, and incorporating these identification results into closed-loop air conditioning control. Therefore, this application proposes a bed identification calculation method and drives intelligent air conditioning strategies based on the identification results to improve comfort, energy efficiency, and user experience.

[0026] Reference Figure 1 The diagram illustrates a flowchart of a control method for a temperature regulating device according to an embodiment of this application, which may include the following steps: Step 101: Collect data on the bed users in the target space to obtain the target location point set of the bed users.

[0027] This application aims to solve the problem that existing temperature control devices cannot accurately identify the position of the bed, thus making it impossible to achieve intelligent directional air supply and dynamic adjustment for sleep based on the bed's position information; through this application, the comfort and energy efficiency of the sleep environment can be improved, and the discomfort of direct airflow can be avoided.

[0028] The temperature control device can be an air conditioner, an air cooler, a fan, or other device that has the function of regulating ambient temperature; this application does not limit this.

[0029] In some embodiments, the temperature control device may be deployed in a target space to regulate the temperature of the target space; for example, the target space may be a bedroom, in which a bed for a user to sleep may be deployed.

[0030] Temperature control devices can be equipped with sensors, or temperature control devices can be connected to sensors; the sensors can be millimeter-wave radar sensors.

[0031] In some embodiments, a sensor (e.g., a millimeter-wave radar sensor) can be invoked to collect data on users in bed in the target space. Taking a millimeter-wave radar sensor as an example, the millimeter-wave radar sensor can be used to transmit millimeter waves into the target space to complete the data collection on users in bed in the target space. Here, a user in bed refers to a user who is in bed. For example, the user can be a user who is sleeping in bed.

[0032] After collecting data on the bed users in the target space, a target location point set of the bed users can be obtained. For example, the target location point set may include multiple location point information, and each location point information may include the location information of a coordinate point. This location information can be used to characterize the location of the bed users in the target space.

[0033] In some embodiments, the sensor can be controlled to sample at a certain frequency to obtain multiple location point information; these multiple location information points can form a target location point set.

[0034] In this application embodiment, in addition to sleeping in the target space, the user may also perform other activities, such as walking, reading, and other non-sleeping activities; during these activities, the user is actually not in bed, and it is unreasonable to predict the position of the bed based on the user's position information during these activities; based on this, this application can also determine whether the user is sleeping when collecting data.

[0035] For example, taking a millimeter-wave radar sensor as an example, its output data may include location information and velocity / micro-motion energy; based on the velocity / micro-motion energy, it can be determined whether the user is in bed.

[0036] Specifically, the movement speed and micro-motion energy of bedridden users are extremely low; based on this characteristic, after obtaining the speed / micro-motion energy, the magnitude of the value can be used to determine whether a user is bedridden.

[0037] In another example, when determining whether a user is in bed based on speed / micro-motion energy, the duration can also be considered. That is, the user is determined to be in bed only when the speed / micro-motion energy is below a preset threshold and continues for a preset duration. This application does not limit this.

[0038] Step 102: Determine the bed location information in the target space based on the target location point set.

[0039] In some embodiments, when a user is sleeping in a bed, they may be sleeping in different positions on the bed. Therefore, after obtaining the target location point set, this application can infer the location of the bed in the target space based on the location of the user in the bed represented by the target location point set, i.e., the bed location information. The bed location information may include the location of the bed in the target space, specifically, it may include the location of the edge of the bed in the target space.

[0040] Step 103: Control the temperature regulation equipment according to the bed location information.

[0041] After determining the bed location information, embodiments of this application can control the airflow speed, temperature, etc. of the temperature regulating device according to the bed location information; for example, the temperature regulating device can be controlled to blow air towards a location other than the head of the bed; for another example, the temperature regulating device can be controlled to blow air at a first temperature towards the head of the bed and to blow air at a second temperature towards a location other than the head of the bed, where the first temperature is higher than the second temperature; for yet another example, the temperature regulating device can be controlled to blow air at a first wind speed towards the head of the bed and to blow air at a second wind speed towards a location other than the head of the bed, where the first wind speed is lower than the second wind speed. Embodiments of this application do not impose any limitations on this.

[0042] In this embodiment, data is collected from users in bed within the target space to obtain a set of target location points for those users. Based on this set of target location points, the bed's location information within the target space is determined. Based on the bed's location information, the temperature control equipment is controlled. This embodiment allows for accurate identification of the bed's location within the target space, and the identification results drive intelligent air conditioning strategies to improve comfort, energy efficiency, and user experience.

[0043] Reference Figure 2 The diagram illustrates a flowchart of another control method for a temperature regulating device according to an embodiment of this application, which may include the following steps: Step 201: Collect data on the bed users in the target space to obtain the target location point set of the bed users.

[0044] In some embodiments, sensors can be invoked to collect data on bed users in the target space; after collecting data on bed users in the target space, a set of target location points of bed users can be obtained.

[0045] Step 202: Determine the bed's dimensions based on the target location point set.

[0046] After obtaining the target location point set, the size information of the bed in the target space can be determined based on the region composed of the target location point set; the size information can be used to represent the size of the bed in the target space.

[0047] In some embodiments of this application, the target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; the indicated size information includes bed length information and bed width information; this application can determine the bed size information through the following sub-steps: Sub-step 11: From the target location point set, determine the maximum and minimum lateral coordinates, as well as the maximum and minimum longitudinal coordinates.

[0048] In some embodiments, the target location point set may include multiple location point information, each location point information may include a horizontal coordinate and a vertical coordinate; the bed size information may include bed length information to represent the length of the bed, and bed width information to represent the width of the bed.

[0049] After obtaining the target location point set, the maximum horizontal coordinate with the largest value, the minimum horizontal coordinate with the smallest value, the maximum vertical coordinate with the smallest value, and the minimum vertical coordinate with the smallest value can be determined from all the location point information in the target location point set, in order to estimate the approximate size of the bed in the target space.

[0050] Sub-step 12: Calculate the first difference between the maximum and minimum horizontal coordinates, and the second difference between the maximum and minimum vertical coordinates.

[0051] After determining the maximum and minimum lateral coordinates, as well as the maximum and minimum longitudinal coordinates, this application can calculate the difference between the maximum and minimum lateral coordinates, i.e., the first difference. This first difference can be used to determine the length or width of the bed.

[0052] Additionally, the difference between the maximum and minimum longitudinal coordinates, known as the second difference, can be calculated. This second difference can be used to determine the length or width of the bed.

[0053] Sub-step 13: Determine the bed length and bed width information based on the first difference and the second difference.

[0054] In practical applications, the dimensions of beds on the market are basically fixed; for example, 1.5 meters * 2.0 meters, 1.8 meters * 2.0 meters. Based on this, this application can determine the bed length and width information according to the first difference and the second difference. For example, if the first difference is smaller than the second difference, the first difference can be used as the bed width information and the second difference as the bed length information; in another example, if the first difference is larger than the second difference, the first difference can be used as the bed length information and the second difference as the bed width information.

[0055] In another example, if both the first difference and the second difference are not greater than 1.5 meters, then 1.5 meters can be used as the bed width information; since there is no bed that is 1.5 meters long normally, 2.0 meters or 1.9 meters can be used as the bed length information, and this application embodiment does not limit this.

[0056] In some embodiments, when a user is sleeping in bed, they may toss and turn, resulting in the user being in different positions at different times. Based on this, in order to resist the influence of a single short-term disturbance on the size determination, this application can divide the time a user spends in bed at night into several time segments, and obtain bed length information and bed width information for each time segment. Then, the bed length information and bed width information that appear most frequently can be counted as the final bed length information and bed width information of the bed in the target space. This application embodiment does not limit this.

[0057] In some embodiments of this application, the target location point set includes multiple time segment subsets, each subset including multiple location point information; this application can implement sub-step 13 in the following manner: The process involves determining the first discrete interval to which the first difference is mapped, and determining the first length information based on the first discrete interval; determining the second discrete interval to which the second difference is mapped, and determining the second length information based on the second discrete interval; determining the target first length information based on multiple first length information; determining the target second length information based on multiple second length information; and determining the bed length information and bed width information based on the target first length information and the target second length information.

[0058] In some embodiments, the time a user spends in bed at night can be divided into several time segments, each time segment corresponding to a subset of the target location points set; each subset may include multiple location point information.

[0059] When determining the bed length and width information, we can first determine the first discrete interval to which the first difference maps and the second discrete interval to which the second difference maps; for example, multiple discrete intervals can be preset: i.(0,1000]→1000; ii.(1000,1200]→1200; iii.(1200,1500]→1500; iv.(1500,1800]→1800; v.(1800,2000]→2000; vi. 2000 → 2000 (upper limit truncation). Unit is mm.

[0060] After determining the first difference and the second difference, the discrete intervals to which the first difference and the second difference belong can be determined; for example, if the first difference is 900mm and the second difference is 1950mm, then the first discrete interval can be determined as i and the second discrete interval as v.

[0061] After determining the first discrete interval and the second discrete interval, the first length information and the second length information can be determined according to the values ​​set for different discrete intervals; continuing the above example: if v corresponds to 1000mm and v corresponds to 2000mm, then the first length information can be determined to be 1000mm and the second length information to be 2000mm. This application embodiment does not limit this.

[0062] For multiple subsets, a first length information and a second length information can be determined respectively, thereby obtaining multiple first length information and multiple second length information.

[0063] After obtaining multiple first length information and multiple second length information, the first length information that meets the size requirements of the bed and has the highest frequency of occurrence can be determined from the multiple first length information as the target first length information; in addition, the second length information that meets the size requirements of the bed and has the highest frequency of occurrence can also be determined from the multiple second length information as the target second length information.

[0064] After determining the first and second length information of the target, the bed length and width information of the bed in the target space can be determined based on the first and second length information of the target.

[0065] In some embodiments of this application, the target first length information can be determined in the following manner: Statistical frequency analysis is performed on multiple first length information values ​​to obtain the first probability of each first length information value; the first length information value whose first probability exceeds a first threshold is taken as the target first length information value; when the first probability of each first length information value does not exceed the first threshold, the first length information value with the highest first probability is taken as the target first length information value; or, when the first probability of each first length information value does not exceed the first threshold, the first length information value of the first value is taken as the target first length information value.

[0066] In some embodiments, after obtaining the first length information of all subsets, the frequency of occurrence of these first length information can be statistically analyzed to obtain the probability of occurrence of the first length information of each value, i.e., the first probability.

[0067] After obtaining the first probability, the first length information whose first probability exceeds the first threshold can be used as the target first length information; for example, the first threshold can be 70%, and this application embodiment does not limit it.

[0068] In another example, if none of the first probabilities exceed the first threshold, then the first length information with the highest first probability can be used as the target first length information.

[0069] In another instance, if none of the first probabilities exceed the first threshold, the default size "first value" can also be used as the target first length information.

[0070] In other embodiments of this application, the second length information of the target can be determined in the same way; since the method is the same, the embodiments of this application will not be described again here.

[0071] Step 203: Determine the center point information and major axis direction information of the bed based on the target location point set.

[0072] In some embodiments, after determining the target location point set, the center point information and major axis direction information of the bed in the target space can also be determined based on the target location point set; wherein, the center point information can refer to the position of the center point of the bed, and the major axis direction information can refer to the direction of the main axis of the bed, such as the direction of the length.

[0073] In some embodiments of this application, the center point information and major axis direction information of the bed can be determined by the following sub-steps: Sub-step 21: Based on the target location point set, determine the horizontal average coordinates and vertical average coordinates, and based on the horizontal average coordinates and vertical average coordinates, determine the center point information.

[0074] In some embodiments, the center point information is the center position of the bed in the target space; this application can first determine the average horizontal coordinate based on all the horizontal coordinates in the target position point set; and determine the average vertical coordinate based on all the vertical coordinates.

[0075] For example, for multiple subsets, the average horizontal coordinate and average vertical coordinate of each subset can be determined first; then the average value can be taken to obtain the final average horizontal coordinate and average vertical coordinate. This application embodiment does not limit this.

[0076] After determining the final average horizontal and vertical coordinates, the average horizontal and vertical coordinates can be used as the location of the center point of the bed in the target space; specifically, the average horizontal and vertical coordinates can be used as the center point information.

[0077] Sub-step 22: Perform principal component analysis on the target location point set and determine the major axis direction information based on the direction of the first principal component.

[0078] In some embodiments, after obtaining the target location point set, principal component analysis (PCA) can be performed on the target location point set to obtain the first principal component. After obtaining the first principal component, its direction can be used as the direction corresponding to the major axis direction information, i.e., the direction of the bed's principal axis (major axis). The first principal component can refer to the orthogonal feature dimension with the largest variance extracted from the high-dimensional data. It is a linear combination of the original features and also the principal component that carries the most core information of the original data. It is the projection result of the data in the direction with the "most concentrated information".

[0079] Step 204: Determine the bed position information based on the dimension information, center point information, and major axis direction information.

[0080] After determining the dimensional information, center point information, and major axis direction information, this application can deduce the bed position information in the target space based on the dimensional information, center point information, and major axis direction information.

[0081] In some embodiments of this application, the bed location information can be determined through the following sub-steps: Sub-step 31: Using the center point information as the center of the bed, determine the coordinate range information of the bed based on the size information and the direction of the major axis.

[0082] In some embodiments, after obtaining the size information, center point information, and major axis direction information, the bed region can be constructed based on the size information, using the coordinates corresponding to the center point information as the bed center and the direction corresponding to the major axis direction information as the major axis direction of the bed. This yields the coordinate range information of the bed in the target space. For example, the coordinate range information can refer to the coordinate positions of the four vertices of the bed in the target space, or it can refer to the coordinate positions of the edges of the bed in the target space; this embodiment does not limit this.

[0083] Sub-step 32: Determine the bed location information based on the coordinate range information.

[0084] After determining the coordinate range information, the bed position information in the target space can be determined based on the coordinate range information.

[0085] Step 205: Based on the bed location information, determine the location information of the target body part of the bed user.

[0086] In some embodiments, after determining the bed location information, the location information of the target part (e.g., head) of the user in bed can also be determined based on the bed location information.

[0087] For example, the position of the head of the bed can be determined from the bed position information based on velocity / micro-motion energy; then, the position of the head of the bed can be used as the position information of the target part of the bed user.

[0088] In another example, the position of the head of the bed can be determined based on a set of target location points. Specifically, the width of the user's head on the bed is smaller than the width of the user's feet on the bed. Based on this, the width at one end and the width at the other end in the direction corresponding to the long axis information can be determined first based on the set of target location points. Then, by comparing the two widths, the end of the head of the bed in the direction corresponding to the long axis information can be determined. This embodiment of the application does not limit this.

[0089] Step 206: Adjust the angle of the air vent of the temperature control equipment according to the location information.

[0090] After determining the location information, this application can adjust the angle of the air vent of the temperature control device according to the location information to avoid blowing directly on the head of the bed user.

[0091] In some embodiments of this application, the above method may further include the following steps: Acquire multimodal data and determine the user's status based on the multimodal data; the user's status includes whether they are in bed or out of bed; control the temperature regulation equipment according to the user's status.

[0092] In some embodiments, when determining whether a user is in bed, multimodal data can also be used to avoid analysis errors due to anomalies in one type of data. The multimodal data may include the target location point set output by the millimeter-wave radar sensor, the infrared data output by the passive infrared sensor, and the temperature and humidity data output by the temperature and humidity sensor.

[0093] After obtaining multimodal data, the user's status in the target space can be determined by combining the multimodal data. If the user is determined to be in bed, then the user can be identified as a bedridden user; at this time, the temperature control device can be controlled in sleep mode.

[0094] Conversely, if the user is determined to be out of bed, then the user is not in bed; in this case, the temperature control device can be controlled in non-sleep mode; specifically, the temperature control device can be controlled by exiting sleep mode; the specific control method is not limited in this embodiment.

[0095] In this embodiment, data is collected from users in bed within the target space to obtain a set of target location points for the users. Based on the target location point set, the size information of the bed is determined. Based on the target location point set, the center point information and major axis direction information of the bed are determined. Based on the size information, center point information, and major axis direction information, the bed position information is determined. Based on the bed position information, the positional information of the target part of the user in bed is determined. Based on the positional information, the angle of the air vents of the temperature control device is adjusted. This embodiment solves the problem of not being able to achieve intelligent directional airflow and dynamic adjustment for sleep based on the bed position due to the inability to accurately identify the bed's position, size, and orientation. This embodiment also improves the comfort and energy efficiency of the user's sleep environment and avoids discomfort from direct airflow.

[0096] Below, we will take the air conditioner in the bedroom as an example, and combine it with... Figure 3 and Figure 4 The technical solution of this application will be described in more detail; Figure 3 A system flowchart according to an embodiment of this application is shown. Figure 4 A flowchart illustrating a bed calculation method according to an embodiment of this application is shown.

[0097] The air conditioner is equipped with a millimeter-wave radar sensor that communicates with the air conditioner's main control unit via a serial port, transmitting millimeter-wave data to the main control unit. The main control unit analyzes and processes the millimeter-wave data to identify and determine the presence, location, and movement trajectory of a human body. The millimeter-wave radar sensor monitors the status of human targets in the room in real time, detecting their presence, location distance, angle, and movement trajectory.

[0098] The air conditioning system mainly includes the following equipment and software modules: Hardware equipment: 1. Millimeter-wave radar sensor (mmWave): It has the ability to detect target distance, azimuth, velocity / micro-motion and output two-dimensional coordinates (x,y) (i.e., two-dimensional coordinates); it is installed on the air conditioner unit and arranged facing the bedroom bed area.

[0099] 2. Main control unit (MCU (Microcontroller Unit) / SoC (System on Chip)): Responsible for serial communication, data processing, control decisions and peripheral linkage (lighting, voice module, air conditioning fan and air direction actuator).

[0100] 3. Wind direction actuator: It can realize vertical and horizontal air sweeping, and supports directional air supply and wind avoidance angle control.

[0101] 4. Communication interfaces: Serial port (UART (Universal Asynchronous Receiver / Transmitter) / RS232 (Recommended Standard 232) / TTL (Transistor-Transistor Logic)) and IoT module (Wi-Fi / Bluetooth) are used to interact with mobile apps / cloud (but core identification is done locally to protect privacy).

[0102] 5. Auxiliary sensors (optional): temperature and humidity sensor, PIR (Passive Infrared) sensor; used for redundancy occupancy detection.

[0103] Software modules: 1. Data acquisition module: responsible for reading point coordinates (x, y) and timestamps from millimeter-wave radar sensors at a fixed frequency, and performing necessary coordinate system unification (with the air conditioner body as the origin).

[0104] 2. Preprocessing module: Includes noise reduction filtering (such as median filtering and Kalman filtering), low-energy point removal, velocity threshold filtering, and short-time discrete point removal.

[0105] 3. Time window selection module: Detects and marks "candidate windows in bed" (e.g., 0-20 minute window in the early stage of bed admission) and sets statistical segments.

[0106] 4. Statistical Mapping Module: Calculates the minimum horizontal coordinate x_min, maximum horizontal coordinate x_max, horizontal average coordinate x_mean, minimum vertical coordinate y_min, maximum vertical coordinate y_max, and vertical average coordinate y_mean for multiple time segments. It also calculates the first difference x_diff and the second difference y_diff and maps them to predefined discrete intervals (1000 / 1200 / 1500 / 1800 / 2000mm).

[0107] 5. Orientation and Dimension Determination Module: Based on the statistical frequency of each mapping result and according to empirical thresholds (70%, etc.) and rules (such as prioritizing length of 2000), determine the bed length and bed width information, and accurately determine the long axis orientation information through PCA / spindle fitting.

[0108] 6. Bed Area Construction Module: Construct a rectangular bed area using center point information, bed length information, bed width information, and major axis direction information, and mark the bed boundary in the coordinate system.

[0109] 7. Occupancy determination module: Real-time detection of whether the human body is located within the bed area, and performs shake reduction processing based on continuous detection time and micro-motion intensity.

[0110] 8. Air Conditioning Strategy Generation Module: Generates specific action sequences (temperature change curves, wind speed, air vent angle, lighting linkage commands, etc.) based on occupancy / time / user settings.

[0111] 9. Self-learning module: Adjusts probability thresholds, mapping boundaries, and time window strategies based on multi-night data to improve recognition robustness.

[0112] 10. Security and Privacy Module: Enables options for local processing, minimal log storage, and encrypted transmission.

[0113] Specifically: After the system is started, the air conditioner’s built-in millimeter-wave radar sensor continuously samples data at night. The system first confirms the user as a bed user through a short window (e.g., 0–20 minutes after entering the bed) and marks this segment as a “bed candidate window”.

[0114] Subsequently, the extreme values ​​and mean values ​​of the coordinates for each segment of the entire night's bedtime are statistically analyzed in several time periods (suggested hourly or half-hourly), and x_diff and y_diff are calculated and mapped to discrete intervals based on predefined intervals.

[0115] Frequency statistics and probability fusion were performed on all time segments. The bed length, bed width, center point and long axis direction information were determined by combining majority voting and PCA principal axis analysis, and then the bed location information was determined.

[0116] Finally, the bed location information is used to determine the user in bed and trigger various sleep scene controls for the air conditioner to perform control (e.g., directional strong airflow → low-noise circulating airflow, wind avoidance strategy, lighting linkage, and voice triggering, etc.). The system optimizes parameters on multi-dimensional data through a self-learning module to achieve robust recognition and comfortable temperature control strategies.

[0117] Specific implementation process: 1. Data acquisition and preprocessing; (1) Sampling frequency and data format: a. The sampling frequency of the millimeter-wave radar sensor can be set between 10 and 50 Hz to ensure the capture of micro-movements and rolling over events. Each record includes a timestamp t, horizontal coordinate x, vertical coordinate y, velocity / micro-movement energy (optional), and the confidence level for each record.

[0118] b. Data is sent to the main control unit via serial port timed packets: the packet format can be: [t, id, x, y, v, conf]; where id can be the data ID, x and y can be in mm, and conf can be the confidence level.

[0119] (2) Noise reduction and initial point cloud screening: a. Use median filtering to remove isolated noise, and Kalman filtering to smooth the trajectory.

[0120] b. If the radar target confidence / conf value is below the threshold (e.g., conf < 0.3), points can be removed.

[0121] c. Eliminate static debris reflection points based on velocity / micro-motion energy (judged as fixed objects without micro-motion).

[0122] (3) Cluster segmentation: a. If multiple moving targets (pets, etc.) appear in the bedroom, density clustering (such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise)) is used to segment the trajectories of different targets, and the main target set is selected based on the proportion of time when moving targets appear throughout the night, the frequency of occurrence, or the energy of micro-motion to determine the bed location.

[0123] 2. Select the bedtime window; (1) Initial on-bed candidate window identification: a. Monitor short periods of time (e.g., 0–20 minutes after a user lies down) when people enter the bed area at night as a candidate window for bed entry. This window can be identified by continuously detected micro-movements that remain within a certain spatial range. Users can also define a "nighttime bedtime period" through the app to assist in determining whether to go to bed (default 22:00–07:00).

[0124] (2) Continuous judgment and de-jittering: a. To avoid false triggers (such as brief stops, walking past the bedside, etc.), the human body must remain in the bed area for at least N seconds (e.g., 30 seconds) or continuous micro-movement events must be detected before "entering the bed" is confirmed.

[0125] 3. Segmented statistics and mapping; (1) Time segmentation strategy: a. Divide the nighttime bedtime into several time segments (it is recommended to use 1-hour segments or half-hour segments to improve granularity). Example: 00:00–01:00, 01:00–02:00, …, 05:00–06:00 (6 segments in total). The main purpose of segmentation is to resist the influence of individual short-term disturbances on size determination.

[0126] (2) Calculation of statistics for each segment a. For each subset collected within a segment, calculate: x_min, x_max, x_mean, y_min, y_max, y_mean.

[0127] b. Calculate the difference: x_diff = |x_max - x_min|; y_diff = |y_max - y_min|.

[0128] (3) Discrete difference mapping: a. Map x_diff and y_diff to discrete intervals (in mm): i.(0,1000]→1000; ii.(1000,1200]→1200; iii.(1200,1500]→1500; iv.(1500,1800]→1800; v.(1800,2000]→2000; vi.2000→2000 (upper limit truncation).

[0129] b. After mapping, we obtain the first length information mapped_x and the second length information mapped_y.

[0130] (4) Determine the length / width direction (within the segment) a. For each time segment, if mapped_x > mapped_y, then x is determined to be the length and y to be the width of that time segment; otherwise, y is determined to be the length and x to be the width; if they are equal, then that segment is not counted in the length / width count.

[0131] b. Count the number of times x is judged as long and the number of times y is judged as wide in all segments. If the number of times x is judged as long is greater than the number of times y is judged as long, then the x-axis direction is determined as the bed length overall; otherwise, y is the bed length.

[0132] (5) Probability calculation and threshold decision: a. Calculate the probability distribution of the mapped_x and mapped_y categories for all segments by counting the number of segments (count / total number of segments): first probability and second probability.

[0133] b. If the probability of a certain category is greater than the first threshold of 70% (an empirical value that can be adjusted through self-learning), then that category is directly selected as the final value. If the first threshold is not reached, then the two candidate categories with the highest probabilities are selected for subsequent judgment (for example, 2000mm is given priority as a candidate bed length, and if the probabilities of the two are equal or include 2000mm, then 2000mm is selected first).

[0134] (6) Rules for final determination of length and width: a. Bed width is usually 1000 / 1200 / 1500 / 1800 / 2000 mm; bed length is usually 1800 / 2000 mm (2000 mm is the mainstream).

[0135] b. If the value is ≤1500, it is considered as the bed width; for the bed length, the candidate with the highest probability or the candidate containing 2000 is selected first, and 2000 is selected first.

[0136] c. The bed length information (bed_length_value) and bed width information (bed_width_value) are finally determined by a combination of voting and probability.

[0137] (7) Handling special cases: a. If multiple stable clusters are detected (a stable cluster refers to a set of target points that exist continuously in space and have a limited range of positional changes after statistical analysis of point cloud data continuously sampled by millimeter-wave radar over a time window. It reflects a target area in a room that continuously exists and conforms to the characteristics of human activity (e.g., a person resting on a bed) (e.g., a double bed with significant positional offset between the two people), the bed area is defined by the smallest bounding rectangle containing the two clusters, or by the main cluster (the "main cluster" is the cluster with the highest comprehensive score among all stable clusters based on duration, point density, and micro-motion energy. If two or more stable clusters are detected with similar scores, the bed area is defined by the smallest bounding rectangle enclosing the two clusters) as the center of the bed, and the App prompts "Multiple people detected, please confirm the bed" for manual correction.

[0138] b. If there are large fluctuations at night or insufficient data, the system will revert to using the default bed size (e.g., 1500×2000) and continue learning.

[0139] 4. Calculation of center point and orientation; (1) Calculation of the center point: a. Horizontal average coordinate x_center = average (x_mean for each time segment) b. Overall average coordinate y_center = average (y_mean for each time segment) c. The center point is (x_center, y_center).

[0140] (2) Orientation and principal axis estimation (PCA method) a. Perform principal component analysis on the target location point set; the direction of the first principal component is the direction of the bed's principal axis (major axis). This method can automatically correct for any angle of bed placement within the room, outperforming axis alignment methods that only compare x / y differences.

[0141] b. Compare the PCA principal axis direction with the x / y axis to determine whether the bed length direction is along the x or y axis or in between, and rotate the final length and width rectangle by that angle and map it in the room coordinate system.

[0142] (3) Calculation of rectangular boundary (with direction): Using the center point as the center of the bed, and based on the determined dimensional information and major axis direction information, calculate the range of the x-coordinate and y-coordinate of the rectangular area of ​​the bed in the coordinate system: If the length of the bed is along the x-axis, then: x-axis range: x_min(bed)=x_center-0.5*bed_length_value; x_max(bed)=x_center+0.5*bed_length_value; y-axis range: y_min(bed)=y_center-0.5*bed_width_value; y_max(bed)=y_center+0.5*bed_width_value; If the length of the bed is along the y-axis, then: x-axis range: y_min(bed)=y_center-0.5*bed_length_value; y_max(bed)=y_center+0.5*bed_length_value; x-axis range: x_min(bed)=x_center-0.5*bed_width_value; x_max(bed)=x_center+0.5*bed_width_value; 5. Real-time occupancy determination and debouncing; (1) Judgment rules: a. If, within M consecutive sampling points (e.g., for 30 seconds), the human body coordinates fall within the rectangular area of ​​the bed and the micro-motion intensity is higher than the threshold, then it is determined that the user is on the bed.

[0143] b. If a point briefly slips out of bed (turns over and extends its leg), it is not immediately judged as leaving the bed. Instead, a time window is used to de-shake (leaving the bed requires N seconds, for example, 60 seconds).

[0144] (2) Multiple people handling: a. If multiple targets are detected simultaneously and fall within the bed area, it is determined to be a multi-person situation; the air conditioning strategy can be switched to "multi-person mode" (e.g., increase the total air supply or supply air at an angle of ±10° based on the average position of the multi-person targets).

[0145] (3) Compensation for misjudgment: a. When the radar signal is interfered with or the confidence level decreases, auxiliary sensors (temperature and humidity changes, PIR) are used to provide redundant confirmation; if it is still impossible to determine, the system will be downgraded to the default strategy and the log will be recorded for self-learning optimization.

[0146] Specifically, a confidence fusion method is used—the confidence of the millimeter-wave radar sensor is combined with the confidence of the auxiliary sensor, CPIR and CTH (PIR represents passive infrared and TH represents temperature and humidity), to form a comprehensive confidence Ctotal, and then a final judgment is made based on a threshold and a time window.

[0147] (3.1) Calculation of confidence scores for each sensor: Millimeter-wave radar sensor: The confidence level Cmm∈[0,1] has been output by the main process (e.g., calculated based on the number of points, cluster stability, and target tracking duration).

[0148] PIR sensor: If a continuous "person" event is detected within the decision window, set CPIR=0.9; if it is a short pulse or discontinuous, assign a value of 0.4; if no detection is detected, assign 0.

[0149] Temperature and humidity sensor (TH): Estimates respiration correlation by measuring the slope and amplitude of temperature / humidity changes within a short window. Calculate the short-time difference ΔRH (maximum humidity increment) and ΔT (maximum temperature increment).

[0150] If ΔRH > RHth (e.g., 0.2%RH) and there is a periodicity (respiratory rate range 0.1–0.5Hz), then CTH = 0.7; if there is only a weak amplitude but a continuous increase, then CTH = 0.45; otherwise, CTH = 0.

[0151] (3.2) Comprehensive confidence level fusion: Ctotal=1-(1 wmmCmm)(1 wPIRCPIR)(1 wTHCTH); Where wmm, wPIR, and wTH are the weights of each sensor; Recommended initial values: wmm=0.6, wPIR=0.25, wTH=0.15. This formula ensures a higher confidence level when multiple pieces of evidence are present, and a lower confidence level when a single piece of evidence is weak.

[0152] (3.3) Timing verification and debouncing: For bed entry determination, it is required that within the determination window Win (e.g., 30s), Ctotal continuously exceeds the threshold Tin (e.g., 0.6) for at least thold_int (e.g., 15s).

[0153] For the determination of leaving the bed, Ctotal is required to be lower than the bed leaving threshold Tout (e.g., 0.3) and continue for thold_out (e.g., 60s) to avoid false alarms when turning over.

[0154] If Ctota fluctuates around the threshold (e.g., 0.45–0.65), it is marked as "low confidence" and a redundancy rule is triggered (see below): Redundant confirmation logic (decision process); High-confidence path (direct determination); If Ctota ≥ 0.75, the status is directly determined to be "in bed"; if this condition is continuously met, the bed entry scenario is triggered.

[0155] Intermediate confidence path (requires further confirmation); If 0.4 ≤ Ctota < 0.75: Check the evidence from the auxiliary sensor alone. If the PIR continuously emits a resident signal (CPIR≥0.8) and there are slight respiratory characteristics (CTH≥0.3), the status will be upgraded to "in bed".

[0156] If there is insufficient supporting evidence, remain "pending" and continue to observe Wobbs (e.g., 60 seconds). If there is no improvement after exceeding Wobbs, revert to the default strategy.

[0157] Low-confidence path (backoff) If Ctota < 0.4 and there is no clear evidence for PIR / TH, it is considered "unconfirmable". The system is downgraded to the default air conditioning strategy (e.g., no directional strong wind, use energy-saving mode) and the moment is recorded in the log as a training sample.

[0158] Conflict handling: If the millimeter wave strongly indicates "person" (high Cmm) but the PIR remains inactive and the temperature and humidity do not change, it may be a false alarm by the radar (reflection / pet / abnormal operating conditions). In this case, reduce the weight of the millimeter wave and enter the observation window. If the conflict continues, a prompt will be triggered (the App will notify the user to check or allow manual confirmation).

[0159] 6. Intelligent air conditioning control strategy; (1) Bed entry trigger (initial bed entry; trigger condition: user enters bed and the time is within the "nighttime period"); a. Action sequence (default): i. Lighting: Linked with the lights, the brightness is linearly reduced to 5% within 30 seconds.

[0160] ii. Air conditioning: Triggers the "sleep curve", lowering the temperature by 0.5–1.0°C (configurable) within 20 minutes, gradually reducing the fan speed from medium to low, and directing the airflow upwards or away from the bed surface (automatically adjusting the airflow direction according to the bed's orientation).

[0161] iii. Airflow: Use directional strong airflow to help dissipate heat for the first 10 minutes, then switch to low-noise circulating airflow and avoid direct airflow towards the head of the bed.

[0162] (2) Sleep onset period (the long period after falling asleep): a. The priority strategy is "low noise + avoid direct airflow"; b. Support the "air supply in the first half of the night / wind avoidance in the second half of the night" strategy: Based on historical behavior or user preferences, moderately increase air supply in the first half of the night (e.g., 22:30–02:00) to promote heat dissipation, and reduce the wind speed or adjust the wind direction in the second half of the night (02:00–06:00) to avoid waking up; c. If the bed is detected to be turned over or the degree of turning over is increased, the local air supply will be increased briefly to assist in heat dissipation.

[0163] (3) Special scenarios and personalized triggers: a. Voice / App-customizable "Automatically Triggered in Bed" scenarios: Users can define automatic activation of sleep white noise / night light / soothing music, etc., upon getting into bed. The system provides an API for third-party devices to use.

[0164] b. When the air conditioner in a user's room is set to target special needs such as the elderly or children, different fan speeds and directions can be activated according to the user's preset settings.

[0165] (4) Directional control strategy for air vents: a. Based on the bed's center and orientation, calculate the spatial vector between the air conditioner vent and the bed's position, and select the vent's pitch and yaw angles to achieve directional airflow or draft avoidance. Directional airflow targets slightly below the bed's center or the middle of the body, while draft avoidance directs the vent upwards or away from the head of the bed.

[0166] b. When performing airflow maneuvers, incorporate a smooth trajectory (e.g., no more than X degrees per second) to avoid sudden changes in noise and wind feel.

[0167] (5) Energy saving and safety strategies: a. If no significant micro-movements are detected throughout the night (deep sleep), the temperature control bandwidth can be appropriately widened to save energy (e.g., ±0.5°C), but this will not affect comfort.

[0168] b. If the system detects that the bed has been occupied for a long time and the temperature is abnormal (too high or too low), it will issue a prompt and may also push notifications to the App.

[0169] 7. Communication and Interface: 1. Serial port data protocol: a. Millimeter wave → main controller: {t, x, y, v, conf} continuous stream; the main controller determines the sampling and integration window according to the configuration.

[0170] b. Main controller → Air conditioning controller / actuator: Sends action commands (set_temp, set_fan_speed, set_vane_angle, etc.) via internal bus.

[0171] 2. App / Cloud Interface: a. The system will only send necessary status updates (bed identified / unidentified, current policy, alarms) to the cloud; raw data is stored locally by default and can be uploaded for model optimization based on user authorization. All uploads require explicit user authorization and encrypted transmission.

[0172] 8. Self-learning and parameter optimization: (1) Parameter adaptation: a. The system records the mapping statistical distribution, voting results and judgment success rate over multiple nights, and automatically fine-tunes the bed boundary, 70% threshold and time window length based on the posterior probability.

[0173] b. For different room layouts or air conditioner installation heights, the system operates with a more lenient strategy for the first few nights and performs parameter convergence in the background.

[0174] 2. Feedback and User Interaction: a. Display the recognition results (bed frame) to the user in the app and allow manual fine-tuning (position / size / angle) for quick correction in extreme cases and use as learning annotations.

[0175] The solution's operational process in actual air conditioning application scenarios (detailed illustrative): The following describes the actual system operation process using "typical bedtime (22:30)" as an example: 1.21:50–22:30: The system is in a waiting-to-go-to-bedtime state, continuously sampling with millimeter waves and performing light preprocessing. The App sets the default bedtime to 22:30.

[0176] 2.22:30: When a human body is detected entering the bed area and staying in the bed area for ≥30 seconds, the system marks this period as "bed entry trigger".

[0177] a. Triggering action: Send a command to gradually dim the lights (linearly reduce to 5% within 30 seconds); the air conditioner executes the sleep curve (cooling down by 0.5–1.0°C within 20 minutes, fan speed from medium to low, and the air vent slightly tilted upwards to avoid directly facing the head of the bed).

[0178] b. At the same time, use directional strong wind for 10 minutes to promote heat dissipation.

[0179] 3.22:45: The sleep curve is complete. The micro-motion frequency has been detected to decrease. The system will reduce the fan speed to low speed circulation and set the air outlet to a wind-avoiding angle so that the head of the bed is not directly exposed to the airflow.

[0180] 4.00:30: If the system detects increased body movement (possibly due to turning over or sweating), it will briefly increase the local airflow and slightly adjust the air vents to point towards the bed area, before resuming low-noise operation.

[0181] 5.02:30 (late night): If the user prefers to "avoid the wind in the late night", the system will automatically reduce the fan speed and continue to maintain the temperature curve; if the system detects that the user is moving strongly and their body temperature is rising, the system will turn on the directional air supply for a short time to help dissipate heat.

[0182] 6.06:30: User leaves the bed (human body continuously away from the bed area for ≥600s), the system closes the sleep scene, restores the daytime strategy and uploads (optional) the night summary to the App.

[0183] This application utilizes millimeter-wave motion data acquisition and probability mapping-based bed size and orientation recognition. This invention can accurately determine the bed area and drive the air conditioner to achieve directional airflow and sleep curve control, reducing discomfort from direct airflow, improving cooling efficiency, and achieving intelligent linkage with lighting, voice, and other scenarios, while protecting user privacy (local processing, no camera).

[0184] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0185] Reference Figure 5 This diagram illustrates the structure of a control device for a temperature regulating apparatus according to an embodiment of this application. The temperature regulating apparatus is used to regulate the temperature of a target space; the apparatus may include the following modules: The point set determination module 501 is used to collect data on bed users in the target space to obtain the target location point set of bed users. The bed location determination module 502 is used to determine the bed location information of the bed in the target space based on the target location point set; The equipment control module 503 is used to control the temperature regulation equipment based on the bed location information.

[0186] In one optional embodiment of this application, the bed location determination module 502 is used to determine the size information of the bed based on the target location point set; determine the center point information and major axis direction information of the bed based on the target location point set; and determine the bed location information based on the size information, center point information, and major axis direction information.

[0187] In one optional embodiment of this application, the target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; the size information shown includes bed length information and bed width information. The bed location determination module 502 is used to determine the maximum lateral coordinate, minimum lateral coordinate, maximum longitudinal coordinate, and minimum longitudinal coordinate from the target location point set; calculate the first difference between the maximum lateral coordinate and the minimum lateral coordinate, and the second difference between the maximum longitudinal coordinate and the minimum longitudinal coordinate; and determine the bed length information and bed width information based on the first difference and the second difference.

[0188] In one optional embodiment of this application, the target location point set includes multiple time segment subsets, each subset including multiple location point information; the bed determination module 502 is used to determine the first discrete interval to which the first difference is mapped, and determine the first length information based on the first discrete interval; determine the second discrete interval to which the second difference is mapped, and determine the second length information based on the second discrete interval; determine the target first length information based on multiple first length information; and determine the target second length information based on multiple second length information; and determine the bed length information and bed width information based on the target first length information and the target second length information.

[0189] In one optional embodiment of this application, the bed determination module 502 is used to statistically analyze the frequency of multiple first length information to obtain the first probability of each value of the first length information; to take the first length information whose first probability exceeds a first threshold as the target first length information; when the first probability of each value of the first length information does not exceed the first threshold, to take the first length information with the largest first probability as the target first length information; or, when the first probability of each value of the first length information does not exceed the first threshold, to take the first length information of the first value as the target first length information.

[0190] In one optional embodiment of this application, the target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; the bed determination module 502 is used to determine the horizontal average coordinate and the vertical average coordinate based on the target location point set, and to determine the center point information based on the horizontal average coordinate and the vertical average coordinate; to perform principal component analysis on the target location point set, and to determine the major axis direction information based on the direction of the first principal component.

[0191] In one optional embodiment of this application, the bed location determination module 502 is used to determine the coordinate range information of the bed based on the center point information, the size information, and the major axis direction information, and to determine the bed location information based on the coordinate range information.

[0192] In one optional embodiment of this application, the device control module is used to determine the location information of the target part of the user in bed based on the bed location information; and to adjust the angle of the air vent of the temperature regulating device based on the location information.

[0193] In one optional embodiment of this application, the device control module 503 is further configured to acquire multimodal data and determine the user's status based on the multimodal data; the user's status includes bed-entry status or bed-exit status; and control the temperature regulation device based on the user's status.

[0194] In this embodiment, data is collected from users in bed within the target space to obtain a set of target location points for those users. Based on this set of target location points, the bed's location information within the target space is determined. Based on the bed's location information, the temperature control equipment is controlled. This embodiment allows for accurate identification of the bed's location within the target space, and the identification results drive intelligent air conditioning strategies to improve comfort, energy efficiency, and user experience.

[0195] This application also provides a temperature regulating device that can be controlled using the above-described temperature regulating device control method. For example, the temperature regulating device can be an air conditioner, fan, air conditioning fan, etc., and this application does not limit this to such devices.

[0196] This application also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the control method of the temperature regulation device described above.

[0197] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described control method for a temperature regulating device.

[0198] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0199] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0200] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0201] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0202] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0203] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0204] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0205] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0206] The above provides a detailed description of the temperature regulation device, its control method, apparatus, electronic device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A control method for a temperature regulating device, characterized in that, The temperature regulating device is used to regulate the temperature of the target space, and the method includes: Data is collected from the bed users in the target space to obtain the target location point set of the bed users; Based on the target location point set, determine the bed location information of the bed in the target space; The temperature control device is controlled based on the bed location information.

2. The method according to claim 1, characterized in that, The step of determining the bed location information in the target space based on the target location point set includes: The dimensions of the bed are determined based on the target location point set. Based on the target location point set, determine the center point information and major axis direction information of the bed; The bed position information is determined based on the size information, the center point information, and the major axis direction information.

3. The method according to claim 2, characterized in that, The target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; the size information shown includes bed length information and bed width information; Determining the bed's dimensions based on the target location point set includes: From the set of target location points, determine the maximum lateral coordinate, the minimum lateral coordinate, the maximum longitudinal coordinate, and the minimum longitudinal coordinate; Calculate the first difference between the maximum horizontal coordinate and the minimum horizontal coordinate, and the second difference between the maximum vertical coordinate and the minimum vertical coordinate; The bed length information and bed width information are determined based on the first difference and the second difference.

4. The method according to claim 3, characterized in that, The target location point set includes multiple time-segmented subsets, and each subset includes multiple location point information; The step of determining the bed length information and bed width information based on the first difference and the second difference includes: Determine the first discrete interval to which the first difference is mapped, and determine the first length information based on the first discrete interval; Determine the second discrete interval to which the second difference is mapped, and determine the second length information based on the second discrete interval; Based on multiple first length information, determine the first length information of the target; and based on multiple second length information, determine the second length information of the target; Based on the first length information and the second length information of the target, the bed length information and the bed width information are determined.

5. The method according to claim 4, characterized in that, The step of determining the target first length information based on multiple first length information includes: By statistically analyzing the frequencies of multiple first-length information values, the first probability of each first-length information value is obtained. The first length information with a first probability exceeding a first threshold is taken as the first length information of the target; When the first probability of the first length information of each value does not exceed the first threshold, the first length information with the highest first probability is taken as the target first length information; or, when the first probability of the first length information of each value does not exceed the first threshold, the first length information of the first value is taken as the target first length information.

6. The method according to claim 2, characterized in that, The target location point set includes multiple location point information, each location point information including a horizontal coordinate and a vertical coordinate; determining the center point information and major axis direction information of the bed based on the target location point set includes: Based on the target location point set, determine the horizontal average coordinates and the vertical average coordinates, and based on the horizontal average coordinates and the vertical average coordinates, determine the center point information; Principal component analysis is performed on the target location point set, and the major axis direction information is determined based on the direction of the first principal component.

7. The method according to claim 2, characterized in that, Determining the bed position information based on the size information, the center point information, and the major axis direction information includes: Using the center point information as the center of the bed, and based on the size information and the major axis direction information, the coordinate range information of the bed is determined; The bed location information is determined based on the coordinate range information.

8. The method according to claim 1, characterized in that, The step of controlling the temperature regulation device based on the bed location information includes: Based on the bed location information, determine the location information of the target body part of the bed user; The angle of the air vent of the temperature regulating device is adjusted according to the location information of the aforementioned part.

9. The method according to claim 1, characterized in that, The method further includes: Acquire multimodal data and determine the user's status based on the multimodal data; the user's status includes whether they are in bed or out of bed. The temperature control device is controlled according to the user's status.

10. A control device for a temperature regulating equipment, characterized in that, The temperature regulating device is used to regulate the temperature of the target space, and the device includes: The point set determination module is used to collect data on the bed users in the target space to obtain the target location point set of the bed users. The bed location determination module is used to determine the bed location information of the bed in the target space based on the target location point set; The equipment control module is used to control the temperature regulation equipment based on the bed position information.

11. A temperature regulating device, characterized in that, The application uses a control method for the temperature regulating device as described in any one of claims 1-9.

12. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the control method of the temperature regulating device as described in any one of claims 1 to 9.

13. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the control method of the temperature regulating device as described in any one of claims 1 to 9.

Images