Air conditioner adaptive air guide control method and device, air conditioner and storage medium

Abstract

The application discloses an air conditioner adaptive air guide control method and device, computer equipment and a storage medium, and relates to the technical field of intelligent household appliance control. The method comprises the following steps: acquiring time sequence position data of a user and constructing a user movement track; determining track quality characteristics based on the user movement track, and determining a prediction result and a prediction reliability of a future movement position of the user based on the track quality characteristics; determining a user behavior state based on behavior characteristics in a user movement process, and dynamically determining a corresponding reliability determination threshold; and selecting a target air guide control strategy from multiple air guide control strategies according to the prediction reliability and the reliability determination threshold, and performing air guide control on the air conditioner. The application actively predicts a future position of the user through track prediction, eliminates air guide hysteresis, dynamically adjusts the reliability threshold according to the user behavior state, and adapts to the differentiated control requirements of different users.

Description

Technical Field

[0001] This invention relates to the field of intelligent home appliance control technology, and in particular to an adaptive airflow control method, device, air conditioner, and storage medium for an air conditioner. Background Technology

[0002] With the development of smart home technology, the automatic airflow function of air conditioners has gradually become an important means of improving indoor environmental comfort. Existing air conditioners typically use infrared human body sensors, pyroelectric sensors, or image acquisition devices to detect the user's current location and adjust the orientation of the airflow deflector based on the detected location, so that the airflow blows towards or avoids the user.

[0003] However, the aforementioned airflow control method relies primarily on the user's current location information. When the user is moving, their location may change before the airflow mechanism completes its adjustment, causing the movement of the airflow mechanism to lag behind the user's movement. This can lead to problems such as the air supply area failing to cover the user in a timely manner, cold or hot air blowing directly on the user, and frequent adjustments to the airflow deflector.

[0004] Furthermore, in real-world usage scenarios, users exhibit significant differences in their behavioral states, such as children running, adults walking, and the elderly sitting still. These different behavioral states require varying response speeds and air delivery accuracy from the airflow control system. However, existing airflow control methods typically employ uniform control thresholds and fixed control strategies, failing to differentiate adjustments based on user behavior. This results in delayed responses to active users and erroneous actions for quiet users, making it difficult to eliminate airflow lag while adapting to the diverse control needs of different users. Summary of the Invention

[0005] This invention provides an adaptive airflow control method, device, air conditioner, and storage medium for air conditioners, solving the problems of lag and inability to meet differentiated control requirements in existing airflow control systems.

[0006] In a first aspect, embodiments of the present invention provide an adaptive airflow control method for an air conditioner, the method comprising: Acquire the user's temporal location data and construct the user's movement trajectory based on the temporal location data; Based on the user's movement trajectory, determine the trajectory quality characteristics, and based on the trajectory quality characteristics, determine the prediction result of the user's future movement location and the corresponding prediction reliability. The user's behavior state is determined based on the user's behavioral characteristics during the user's movement, and a reliability judgment threshold corresponding to the user's behavior state is dynamically determined based on the user's behavior state. Based on the predicted reliability and the reliability determination threshold, a target airflow control strategy is selected from multiple airflow control strategies to control the airflow of the air conditioner.

[0007] Secondly, embodiments of the present invention also provide an adaptive airflow control device for an air conditioner, the device comprising: A trajectory construction unit is used to acquire the user's temporal location data and construct the user's movement trajectory based on the temporal location data; The prediction unit is used to determine trajectory quality features based on the user's movement trajectory, and to determine the prediction result of the user's future movement location and the corresponding prediction reliability based on the trajectory quality features. The threshold determination unit is used to determine the user's behavior state based on the user's behavior characteristics during the user's movement, and dynamically determine the reliability judgment threshold corresponding to the user's behavior state according to the user's behavior state. The strategy selection unit is used to select a target airflow control strategy from multiple airflow control strategies based on the predicted reliability and the reliability determination threshold to perform airflow control on the air conditioner.

[0008] Thirdly, embodiments of the present invention also provide an air conditioner, which includes a memory and a processor connected to the memory, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0009] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0010] This invention provides an adaptive airflow control method, apparatus, computer device, and storage medium for an air conditioner. The method includes: acquiring a user's temporal location data and constructing a user movement trajectory based on the temporal location data; determining trajectory quality characteristics based on the user movement trajectory and determining a prediction result of the user's future movement location and the corresponding prediction reliability based on the trajectory quality characteristics; determining the user's behavioral state based on behavioral characteristics during the user's movement and dynamically determining a reliability judgment threshold corresponding to the user's behavioral state; and selecting a target airflow control strategy from multiple airflow control strategies based on the predicted reliability and the reliability judgment threshold to perform airflow control on the air conditioner. This invention constructs a user movement trajectory and evaluates its quality characteristics. Based on this, it predicts the user's future movement location and outputs the prediction reliability. This transforms wind guidance control from passive tracking based on the current location to active prediction based on the future location, solving the lag problem of wind guidance control. Simultaneously, it identifies the user's behavioral state based on behavioral characteristics during movement, dynamically configures differentiated reliability judgment thresholds for different behavioral states, and adaptively selects wind guidance control strategies based on the comparison between the predicted reliability and the dynamic thresholds. This allows the system to flexibly adjust control sensitivity according to the user's behavioral state, solving the problem that existing wind guidance control cannot meet differentiated control requirements. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating the adaptive airflow control method for an air conditioner provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the first sub-process of the adaptive airflow control method for air conditioners provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the second sub-process of the adaptive airflow control method for air conditioners provided in this embodiment of the invention; Figure 4 This is a schematic diagram of the third sub-process of the adaptive airflow control method for air conditioners provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the fourth sub-process of the adaptive airflow control method for air conditioners provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the fifth sub-process of the adaptive airflow control method for air conditioners provided in an embodiment of the present invention; Figure 7This is a schematic diagram of the sixth sub-process of the adaptive airflow control method for air conditioners provided in this embodiment of the invention; Figure 8 This is a schematic block diagram of an adaptive airflow control device for an air conditioner provided in an embodiment of the present invention; Figure 9 This is a schematic block diagram of an air conditioner provided in an embodiment of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] It should be understood that, when used in this specification and the appended claims, the terms “comprising” and “including” indicate the presence of the described features, integrals, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, operations, elements, components and / or collections thereof.

[0015] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0016] Please see Figure 1 , Figure 1 This is a flowchart illustrating the adaptive airflow control method for air conditioners provided in this embodiment of the invention. This method can be applied to air conditioner controllers, such as the indoor unit controllers of wall-mounted air conditioners, cabinet air conditioners, or central air conditioners, and can achieve adaptive airflow control based on user movement trajectory prediction. Figure 1 As shown, the method includes steps S100 to S130.

[0017] S100: Obtain the user's temporal location data and construct the user's movement trajectory based on the temporal location data.

[0018] In this embodiment of the invention, a multi-source sensor module deployed on the indoor unit of an air conditioner can continuously and in real-time acquire the user's location data in the indoor space. Temporal location data refers to a set of user spatial location information with timestamps, arranged in chronological order. This data records the user's continuous displacement process in the indoor space from a temporal perspective.

[0019] User movement trajectory refers to the spatial path formed by connecting time-series location data sequentially in chronological order. This trajectory reflects the user's actual movement process in an indoor space.

[0020] For example, in a home living room application environment, the indoor unit of the air conditioner is installed on the wall, and a multi-source sensor module is integrated into the top or side of the indoor unit. The multi-source sensor module can include millimeter-wave radar and an infrared thermal imaging array. The millimeter-wave radar is installed above the air conditioner vent, operates at a frequency of 60 GHz, covers a 5m × 5m living area, and has a sampling frequency of 50 Hz, used to obtain the user's two-dimensional coordinates (X, Y). The infrared thermal imaging array consists of multiple pyroelectric sensors, installed in a concealed location inside the air conditioner, and operates synchronously with the millimeter-wave radar, with a sampling frequency of 50 Hz. It is used to supplement user location information in low-light environments and extract the center point of the human body's heat source through image processing. After receiving the raw sensor data, the controller performs data preprocessing and fusion processing to construct the user's movement trajectory in the living room.

[0021] It should be noted that this invention does not rely on wearable devices or mobile phone positioning, which require active user cooperation. It can automatically obtain user location data simply by using a non-contact sensor integrated on the air conditioner, which meets the needs of seamless use in home scenarios and lowers the user's usage threshold.

[0022] In some embodiments, such as in embodiments of the present invention, as Figure 2 As shown, step S100 includes steps S101-S104.

[0023] S101, acquire the user's first location data and second location data respectively; S102, synchronize the first position data and the second position data in time, and filter the synchronized first position data and second position data; S103, perform data fusion on the filtered first and second position data to obtain the user's position coordinates at different times; S104, Arrange the location coordinates in chronological order to construct the user's movement trajectory.

[0024] In this embodiment of the invention, the first location data and the second location data refer to user location information collected by different types of sensors. The first location data can be user two-dimensional coordinate data obtained by millimeter-wave radar. Millimeter-wave radar calculates the distance and orientation of a target object by transmitting and receiving electromagnetic waves in the millimeter-wave band and using the echo signal, thereby obtaining the user's coordinates (X, Y) in the detection plane. The second location data can be the coordinate data of the user's heat source center point obtained by an infrared thermal imaging array. The infrared thermal imaging array detects the infrared radiation emitted by the human body and extracts the geometric center point coordinates of the human body's heat source area through image processing. Specifically, the interference of environmental heat sources can be removed by background subtraction, and then the human body's heat source area can be separated from the thermal imaging image by a threshold segmentation algorithm, and the geometric center point of this area can be calculated as the user's location coordinates.

[0025] For example, in a home living room application environment, a millimeter-wave radar continuously scans a 5m × 5m detection area at a sampling frequency of 50Hz, outputting one frame of user coordinate data every 20ms. Simultaneously, an infrared thermal imaging array acquires indoor thermal images at the same sampling frequency, extracting the center point coordinates of the human body's heat source area using background subtraction and threshold segmentation algorithms. The two sensors independently acquire user location information based on different physical principles, providing redundant data sources for subsequent data fusion.

[0026] Time synchronization refers to aligning position data from different sensors according to a unified time base, ensuring that the first and second position data at the same moment can be correctly paired. Since there may be slight deviations in the sampling clocks of different sensors, time synchronization operations use methods such as interpolation or nearest neighbor matching to align the two sets of data to the same timestamp sequence.

[0027] Filtering refers to smoothing the time-synchronized position data to eliminate interference from sensor noise and outliers on the position coordinates. In this embodiment of the invention, a Kalman filter algorithm can be used to smooth the first position data (millimeter-wave radar data). Kalman filtering is a recursive optimal estimation algorithm that uses the system state equation and observation equation to make an optimal estimate of the position coordinates, taking into account the statistical characteristics of sensor noise, effectively suppressing coordinate jitter caused by measurement noise.

[0028] For example, in a home living room application environment, millimeter-wave radar produces weak echo signals and increased measurement noise when detecting edge areas, causing random fluctuations in the output coordinate data. After Kalman filtering, the jitter amplitude of the coordinate sequence is significantly reduced, and the position data becomes smoother and more stable, providing high-quality input data for subsequent data fusion and trajectory construction.

[0029] Data fusion refers to the comprehensive processing of pre-processed location data from different sensors to obtain a more accurate and reliable user location estimate than that from any single sensor. In this embodiment of the invention, a weighted average method can be used for data fusion, that is, the first location data and the second location data are assigned preset weights respectively, and then the weighted average value is calculated as the final user location coordinates.

[0030] The weighting can be dynamically adjusted based on the real-time signal-to-noise ratio of each sensor or a preset reliability level. For example, during the day when there is sufficient light, the infrared thermal imaging array is more susceptible to interference from environmental heat sources, so the weight of the second location data is reduced and the weight of the millimeter-wave radar data is increased; at night or in low-light environments, the performance of the infrared thermal imaging array is more stable, so the weight of the second location data is increased.

[0031] After fusion processing, the controller outputs the user's position coordinates at different times. Each position coordinate is associated with the corresponding timestamp to form a trajectory point sequence Pi = (Xi, Yi, Ti), where Xi and Yi are the user's coordinates in the two-dimensional plane, and Ti is the corresponding timestamp.

[0032] The location coordinates obtained after fusion processing are arranged sequentially from earliest to latest according to the timestamp, and the location coordinates of adjacent times are connected in space to construct the user's movement trajectory. The user's movement trajectory can be represented as an ordered sequence of trajectory points {P1, P2, ..., Pn}, where P1 is the location coordinate of the earliest time, Pn is the location coordinate of the latest time, and n is the total number of trajectory points.

[0033] For example, in a home living room application environment, the controller maintains a fixed-length sliding window in memory, storing all trajectory points within the last 10 seconds. As new trajectory points are continuously generated, the oldest trajectory points are removed from the window, and the newest trajectory points are added, thus forming a dynamically updated user movement trajectory. This sliding window mechanism ensures that the trajectory data contains sufficient historical information for trend analysis while avoiding excessive storage and computing resources being consumed by excessively long historical data.

[0034] S110, determine trajectory quality features based on the user's movement trajectory, and determine the prediction result of the user's future movement location and the corresponding prediction reliability based on the trajectory quality features.

[0035] In this embodiment of the invention, after constructing the user's movement trajectory, the quality of the trajectory is first evaluated to determine the trajectory quality characteristics. Trajectory quality characteristics refer to index parameters used to quantitatively describe the spatial continuity and stability of the user's movement trajectory. A high-quality trajectory means that the user moves continuously and smoothly in space, with good spatial coherence between trajectory points; a low-quality trajectory means that the user moves erratically in space or that the trajectory signal contains severe noise, and there is a lack of spatial coherence between trajectory points.

[0036] The prediction result refers to the estimated spatial coordinates of a user's likely location at a future time, based on the changing trend of the user's movement trajectory. Prediction reliability is a quantitative evaluation of the credibility of the prediction result; its value reflects the degree of certainty in location prediction based on the current trajectory quality.

[0037] For example, in a family living room environment, when a user walks in a straight line from the sofa to the dining table, their movement trajectory is continuous and smooth in space, with high trajectory quality characteristic values. In this case, predicting the user's position in the next 3 seconds based on the trajectory trend has high reliability and correspondingly high prediction reliability. Conversely, when the user paces back and forth in the living room or the trajectory signal is interfered with, the trajectory is discontinuous in space, with low trajectory quality characteristic values. In this case, the reliability of position prediction is low, and correspondingly low prediction reliability.

[0038] In some embodiments, such as in embodiments of the present invention, as Figure 3 As shown, step S110 includes steps S111-S114.

[0039] S111, map the trajectory points in the user's movement trajectory that are located within a preset time window to a pre-divided spatial grid; S112, determine the grid occupied by the trajectory point and the trajectory connected region formed by the occupied grid; S113, count the number of occupied grids and the number of connected regions of the trajectory; S114, Based on the number of occupied grids and the number of trajectory connected regions, determine the trajectory quality features that characterize the continuity of the user's movement trajectory.

[0040] S111, map the trajectory points in the user's movement trajectory that are located within a preset time window to a pre-divided spatial grid.

[0041] In this embodiment of the invention, the preset time window refers to a fixed time period backward from the current moment, such as the most recent 5 seconds. The spatial grid refers to a logical grid map pre-established in the controller's memory, which divides the indoor space detected and covered by the air conditioning sensor into several grid units of equal area, with each grid unit corresponding to a rectangular area in the actual space.

[0042] Mapping refers to calculating which grid cell each trajectory point falls into based on its spatial coordinates (X,Y), and then marking the trajectory point in the corresponding grid cell.

[0043] For example, in a home living room application environment, the controller maintains a 9×9 logical grid map in memory, consisting of 81 grid cells. Each grid cell represents a 0.5m×0.5m area in the actual space, and the entire grid map covers a 4.5m×4.5m detection area. The coordinates of all valid trajectory points generated within the last 5 seconds are mapped one by one to their corresponding grid cells. If the coordinates of a trajectory point are (2.3m, 1.7m), then its corresponding grid coordinates are (Gx, Gy) = (4, 3) (rounding down to the integer part), and this trajectory point is marked in the grid cell of the 4th column and 3rd row.

[0044] An occupied grid cell is a grid cell into which at least one trajectory point falls within a preset time window. A trajectory connectivity region is the largest set of grid cells connected together by spatial adjacency relationships (e.g., four-adjacency or eight-adjacency) within the occupied grid cells. In other words, if two occupied grid cells are spatially adjacent (sharing an edge or a corner), they belong to the same trajectory connectivity region; if two occupied grid cells are not spatially adjacent, they belong to different trajectory connectivity regions.

[0045] The process of determining the connected regions of a trajectory can be implemented using classic connected component labeling algorithms (such as the two-pass scanning method or the seed filling method).

[0046] For example, in a family living room environment, if a user walks along a straight line from the sofa to the dining table within the last 5 seconds, the grid points occupied by their trajectory points are spatially adjacent, forming a continuous connected region. If the user paces back and forth in the living room, the grid points occupied by their trajectory points may form two or more connected regions, each corresponding to a movement path in the same direction. If the trajectory signal is severely interfered with, the trajectory points may be scattered across multiple unconnected grids, forming a large number of connected regions, indicating a discontinuous trajectory.

[0047] After completing the mesh mapping and connected component labeling, two key values ​​are calculated: the number of occupied meshes, Nactive, which is the total number of mesh cells into which at least one trajectory point falls within a preset time window; and the number of trajectory connected regions, K, which is the total number of independent connected components formed by occupied meshes through spatial adjacency.

[0048] The number of occupied grid cells, Nactive, reflects the size of the user's activity range within a preset time window. The larger the Nactive value, the wider the spatial area traversed by the user. The number of connected regions, K, reflects the spatial continuity of the user's movement trajectory. The smaller K value (e.g., K=1 or K=2), the more continuous and smooth the user's movement path; the larger K value (e.g., K>3), the more dispersed or jumpy the user's movement path.

[0049] The trajectory quality feature is a quantitative indicator calculated based on the number of occupied grids and the number of connected regions in the trajectory, used to characterize the continuity of a user's movement trajectory.

[0050] First, the grid occupancy rate ρ = Nactive / Ntotal can be calculated, where Ntotal is the total number of grids in the grid map (e.g., 81). Then, the trajectory continuity index Kc is calculated based on the grid occupancy rate ρ and the number of connected regions K. For example, the continuity index can be calculated using the formula Kc = ρ × (1 - K / 5). In this formula, a larger ρ indicates that the trajectory covers more grids and has more comprehensive activity information, while a smaller K indicates that the trajectory is more coherent. Therefore, the closer Kc is to 1, the more coherent the trajectory, and the more reliable the basis for location prediction based on that trajectory; the closer Kc is to 0, the more scattered the trajectory or the less comprehensive the information, and the weaker the basis for location prediction based on that trajectory.

[0051] It should be noted that the above-mentioned calculation formula for the continuity index is only one specific implementation of the present invention. Those skilled in the art can use other mathematical expressions that can combine grid occupancy rate and the number of connected regions into a single continuity index according to actual needs. The present invention does not limit this.

[0052] In some embodiments, such as in embodiments of the present invention, as Figure 4 As shown, step S110 further includes steps S115-S119.

[0053] S115, compare the number of the trajectory connected regions with a preset number threshold; S116, if the number of connected regions of the trajectory is greater than the preset number threshold, the corresponding trajectory segment is determined as an abnormal trajectory segment, and the prediction of the user's future movement location based on the abnormal trajectory segment is stopped. S117, If the number of connected regions of the trajectory is less than or equal to the preset number threshold, then select multiple consecutive valid trajectory points from the user's movement trajectory; S118, determine the user's movement trend based on the multiple consecutive valid trajectory points, and determine the prediction result of the user's future movement location based on the movement trend; S119, determine the trajectory continuity index based on the number of occupied grids and the number of trajectory connected regions, and determine the prediction reliability based on the trajectory continuity index.

[0054] In this embodiment of the invention, the preset quantity threshold is a critical value used to determine whether the trajectory is continuous. For example, the preset quantity threshold can be set to 3. The number K of the trajectory connected regions obtained in step S113 is compared with the preset quantity threshold, and a decision is made based on the comparison result as to whether future location prediction can be performed based on the current trajectory.

[0055] If the number of connected regions of the trajectory is greater than the preset threshold, the corresponding trajectory segment is identified as an abnormal trajectory segment, and the prediction of the user's future location based on the abnormal trajectory segment is stopped.

[0056] When the number K of connected regions in a trajectory exceeds a preset threshold, it indicates that the user's movement trajectory is spatially discontinuous, with jumps or severe noise interference. In this case, the corresponding trajectory segment with an excessive number of connected regions (i.e., the user's movement trajectory within the preset time window) is identified as an abnormal trajectory segment, and predictions of future movement locations based on this abnormal trajectory segment are abandoned.

[0057] A trajectory segment refers to the portion of the user's movement trajectory that corresponds to a preset time window. When the trajectory is determined to be abnormal, the system does not output a valid prediction result, the prediction reliability is set to zero or an extremely low value, and subsequent wind guidance control will not rely on the prediction result.

[0058] For example, in a family living room environment, when multiple family members are active in the living room simultaneously, the sensor detects multiple scattered human targets. The trajectory points are spatially disorganized, and the number of connected regions K=5, which is greater than the preset threshold of 3. At this time, the system determines that the current trajectory is an abnormal trajectory segment, stops prediction, and avoids outputting incorrect prediction results based on chaotic trajectories, which could cause the air guide to sway erratically.

[0059] When the number K of connected regions in the trajectory is less than or equal to a preset threshold, it indicates that the user's movement trajectory is spatially continuous, and future location prediction can be performed based on this trajectory. In this case, the nearest multiple consecutive valid trajectory points are selected from the user's movement trajectory as the input data for prediction.

[0060] Valid trajectory points refer to trajectory points that are not marked as abnormal and are located on a continuous trajectory segment. The number of selected points can be set according to actual needs, for example, selecting the three most recent valid trajectory points P. t-2 P t-1 P t .

[0061] Motion trend refers to the direction and rate of change of a user's movement trajectory in recent times, which can be determined by analyzing the coordinate differences between multiple consecutive valid trajectory points.

[0062] Linear extrapolation can be used to determine the movement trend and calculate the prediction results. Specifically, the three most recent valid trajectories P are selected. t-2 P t-1 P t Calculate from P t-2 To P t The average displacement vector, i.e., the coordinate difference ΔX = X t -X t-2 ΔY=Y t -Y t-2 Assuming the user maintains this movement trend for a predetermined time period (e.g., the next 3 seconds), the predicted future target position Ptarget = (X... t +ΔX / 2,Y t +ΔY / 2).

[0063] It should be noted that "displacement vector" here refers to simple coordinate difference calculations, not complex physical vector calculations. Linear extrapolation is a prediction method with low computational cost and good real-time performance, suitable for situations where users move slowly and their trajectories are relatively smooth, such as in home environments. Those skilled in the art will understand that in other embodiments, polynomial fitting, spline interpolation, or trajectory prediction methods based on deep learning models can be used instead of linear extrapolation, and this invention does not limit this.

[0064] The trajectory continuity index Kc is calculated as described in step S114. The prediction reliability C is directly related to the trajectory continuity index Kc. In this embodiment of the invention, the prediction reliability C is directly equal to the trajectory continuity index Kc, i.e., C = Kc. This is because only when the trajectory height is continuous (high Kc) is the predicted position Ptarget obtained based on linear extrapolation reliable; if Kc is low, it indicates that the trajectory is messy and the prediction fails, and at this time the C value is low.

[0065] S120, determine the user's behavior state based on the user's behavioral characteristics during the user's movement, and dynamically determine the reliability judgment threshold corresponding to the user's behavior state according to the user's behavior state.

[0066] In this embodiment of the invention, user behavior state refers to the classification and determination result of the user's current activity type based on the motion characteristics exhibited by the user during movement. Behavioral characteristics refer to motion parameters that can reflect the user's activity pattern, including but not limited to changes in movement speed and direction.

[0067] The reliability threshold is a critical value used to judge whether the predicted reliability meets the execution conditions of a specific wind guidance strategy. Different user behavior states correspond to different reliability thresholds because different types of users have different requirements for the response speed and accuracy of wind guidance control. Dynamic determination means that the system automatically switches to the corresponding threshold configuration based on the real-time identified user behavior states, rather than using a fixed and uniform threshold.

[0068] For example, in a home living room environment, when a user moves quickly or changes direction frequently, the system determines that they are in an active state (such as children playing). At this time, the system lowers the reliability threshold, making the airflow control easier to trigger for a quick response. When a user moves slowly or stays in a certain position for a long time, the system determines that they are in a quiet state (such as an elderly person sitting quietly). At this time, the system raises the reliability threshold to avoid malfunctions caused by inaccurate trajectory prediction and ensure gentle and stable airflow.

[0069] In some embodiments, such as in embodiments of the present invention, as Figure 5 As shown, step S120 further includes steps S121-S124.

[0070] S121, determine the user's movement distance and direction within a preset time period based on the user's movement trajectory; S122, determine the user's average moving speed based on the moving distance and the preset time period, and determine the user's directional change characteristics based on the changes in the moving direction; S123, compare the average moving speed and the direction change feature with the corresponding behavior determination conditions respectively; S124, Confirm the behavior state based on the comparison result.

[0071] In this embodiment of the invention, the preset time period refers to a fixed time period traversing backward from the current moment, such as the most recent 5 seconds. The movement distance refers to the spatial displacement of the user from the starting position to the ending position within the preset time period, which can be obtained by calculating the Euclidean distance between the starting and ending trajectory points. The movement direction refers to the direction of the user's movement from the starting position to the ending position, which can be obtained by calculating the direction angle of the line connecting the starting and ending trajectory points.

[0072] The average moving speed Vavg is equal to the moving distance divided by the duration of the preset time period. For example, if the user moves 3m within the last 5 seconds, the average moving speed Vavg=3m / 5s=0.6m / s.

[0073] The direction change feature refers to the degree of change in the user's moving direction within the preset time period. The direction change can be quantified by comparing the direction angle difference between adjacent track points in the user's movement track. For example, calculate the direction angle of the connecting line between adjacent track points, count the number of times the direction angle change exceeds a preset angle threshold (such as 30°), or calculate the standard deviation of the direction angle, and use this as the direction change feature.

[0074] The behavior determination condition refers to a pre-set determination rule for distinguishing different user behavior states. The behavior determination conditions include a speed determination condition and a direction change determination condition.

[0075] The speed determination condition may include: comparing the average moving speed Vavg with a preset high speed threshold Vhigh and a preset low speed threshold Vlow. The direction change determination condition may include: comparing the direction change feature (such as the number of direction angle changes or the standard deviation of direction angles) with a preset change threshold.

[0076] According to the comprehensive comparison result of the average moving speed and the direction change feature, the user behavior states are divided into three categories: Active state: if Vavg>Vhigh or the direction changes sharply (the number of direction angle changes exceeds the preset threshold), it is determined that the user is in the active state. Such users move fast and change directions frequently, and a typical scenario is children running and playing in the living room.

[0077] Intermediate state: if Vlow<Vavg≤Vhigh and the direction change is medium, it is determined that the user is in the intermediate state. Such users move at a moderate speed with moderate direction changes, and a typical scenario is an adult walking normally in the living room.

[0078] Quiet state: if Vavg≤Vlow and the direction is stable, it is determined that the user is in the quiet state. Such users move slowly or stay in a certain position for a long time, and a typical scenario is an elderly person sitting quietly on a sofa.

[0079] In some embodiments, for example in the embodiment of the present invention, as Figure 6 shown, said step S120 further comprises steps S125 to S128.

[0080] S125, pre-configure a corresponding reliability threshold group for each user behavior state, each said reliability threshold group includes a first reliability threshold and a second reliability threshold smaller than said first reliability threshold; S126, invoking a first reliability threshold group when the user behavior state is an active state; S127, invoking a second reliability threshold group when the user behavior state is an intermediate state; S128, invoking a third reliability threshold group when the user behavior state is a quiet state; wherein corresponding reliability thresholds in the first reliability threshold group, the second reliability threshold group and the third reliability threshold group increase sequentially.

[0081] In the embodiment of the present invention, the reliability threshold group refers to a pair of threshold parameters pre-configured for each user behavior state, including a first reliability threshold C1 and a second reliability threshold C2, wherein C2<C1. The first reliability threshold C1 serves as a dividing line for distinguishing between high reliability and medium reliability, and the second reliability threshold C2 serves as a dividing line for distinguishing between medium reliability and low reliability.

[0082] Each user behavior state corresponds to an independent threshold group, and threshold values of different threshold groups are different, so as to adapt to sensitivity requirements of air guiding control under different behavior states.

[0083] When a user is in an active state, the system invokes the first reliability threshold group. Threshold values of the first reliability threshold group are the lowest, for example, C1=0.6 and C2=0.4. Since active users (such as children) move fast and have large trajectory changes, the air guiding system is required to respond quickly, therefore, the reliability determination threshold is lowered, so that an air guiding control strategy is triggered more easily. Even if the prediction reliability is not particularly high, the system is allowed to perform corresponding air guiding adjustment, so as to ensure timeliness of response.

[0084] When a user is in an intermediate state, the system invokes the second reliability threshold group. Threshold values of the second reliability threshold group are intermediate, for example, C1=0.7 and C2=0.5. A movement mode of a user in the intermediate state (such as an adult walking normally) is between active and quiet, and the system adopts a balanced threshold configuration to achieve a tradeoff between response speed and accuracy.

[0085] When a user is in a quiet state, the system invokes the third reliability threshold group. Threshold values of the third reliability threshold group are the highest, for example, C1=0.8 and C2=0.6. Since quiet users (such as the elderly) are sensitive to wind, move slowly and have small trajectory uncertainty, the system increases the reliability determination threshold, and performs precise air guiding only when the prediction reliability is very high, so as to avoid misoperation caused by inaccurate trajectory prediction and ensure soft and stable air supply.

[0086] The reliability thresholds in the first, second, and third reliability threshold groups increase sequentially, with C1 and C2 being the smallest in the first group and the largest in the third group. This increasing relationship reflects the design philosophy of differentiated adaptation for users with different behavioral states: active users require rapid response, thus lowering the threshold; quiet users require careful control, thus raising the threshold.

[0087] S130, select a target airflow control strategy from multiple airflow control strategies based on the predicted reliability and the reliability determination threshold to perform airflow control on the air conditioner.

[0088] In this embodiment of the invention, after obtaining the prediction reliability and the reliability judgment threshold corresponding to the current user behavior state, the two are compared numerically, and the target wind guidance control strategy most suitable for the current scenario is selected from a plurality of preset wind guidance control strategies based on the comparison result.

[0089] Airflow control strategy refers to the specific control scheme that controls the movement mode and target angle of the airflow guiding mechanism (such as air deflectors, louvers, etc.) of the air conditioner. Different airflow control strategies correspond to different airflow behaviors, such as accurately tracking the user's future location, oscillating the airflow within a certain range, or fixing the airflow to avoid the user's direction. Target airflow control strategy refers to the airflow control scheme that should be executed at the current moment after comparison and judgment.

[0090] For example, in a home living room environment, when the prediction reliability is high and the user is active, the system selects the "pre-emptive precise airflow" strategy, controlling the air deflector to deliver air directly to the location the user is about to reach, achieving the effect of "airflow following the user's movement"; when the prediction reliability is moderate, the system selects the "conservative airflow" strategy, controlling the air deflector to swing and deliver air within a certain range near the user's current location, balancing coverage and comfort; when the prediction reliability is low, the system selects the "extremely conservative airflow" strategy, controlling the air deflector to be fixed in a direction that avoids the user's current location, minimizing direct airflow to the user.

[0091] It should be noted that the above steps S100 to S130 are executed in a preset control cycle (e.g., every 200ms). Within each control cycle, the system completes a complete process of trajectory construction, quality assessment, position prediction, behavior recognition, threshold adjustment, and strategy selection, thereby achieving real-time adaptive adjustment of wind guidance control.

[0092] In some embodiments, such as in embodiments of the present invention, as Figure 7 As shown, step S130 includes steps S131 to S133.

[0093] S131, if the prediction reliability is greater than or equal to the first reliability threshold, the first air guiding control strategy is determined as the target air guiding control strategy, the air guiding target is determined according to the prediction result of the user's future movement location, and the air guiding mechanism of the air conditioner is controlled to face the air guiding target. S132, if the prediction reliability is less than the first reliability threshold and greater than the second reliability threshold, the second wind guidance control strategy is determined as the target wind guidance control strategy, the wind guidance adjustment area is determined according to the user's current position, the wind guidance mechanism is controlled to swing within the wind guidance adjustment area, and the swing center is biased towards the prediction result of the user's future movement position; S133, if the prediction reliability is less than or equal to the second reliability threshold, the third wind guidance control strategy is determined as the target wind guidance control strategy, wind guidance control based on the prediction result of the user's future movement position is stopped, and the wind guidance direction to avoid the user is determined according to the user's current position.

[0094] In this embodiment of the invention, when the prediction reliability C is greater than or equal to the first reliability threshold C1 corresponding to the current user behavior state, it indicates that the trajectory quality is high and the prediction result is highly reliable. The system determines the first wind guidance control strategy (i.e., the "early and accurate wind guidance" strategy) as the target wind guidance control strategy.

[0095] The first airflow control strategy is executed as follows: using the user's future movement position Ptarget predicted in step S118 as the airflow target, calculating the azimuth angle θtarget of Ptarget relative to the air conditioner outlet, controlling the airflow deflector to quickly rotate to the θtarget angle, so that the airflow is directed toward the location the user is about to reach, and continuously tracking this angle until the user stops moving or the prediction reliability drops below C1.

[0096] For example, in a family living room environment, a user walks quickly from the sofa to the dining table in a straight line. The trajectory is highly continuous, and the prediction reliability C = 0.85, which is greater than the first reliability threshold C1 = 0.7 of the current threshold group. The system controls the air deflector to turn towards the dining table in advance. When the user arrives at the table, the airflow has already covered the area, achieving a seamless and comfortable experience where the airflow follows the user's movement. This avoids the problem in traditional technologies where the air deflector action always lags behind changes in the user's position.

[0097] When the prediction reliability C is less than the first reliability threshold C1 and greater than the second reliability threshold C2, it indicates that the trajectory quality is moderate and the prediction result has some reference value but is not accurate enough. The system will determine the second wind guidance control strategy (i.e., the "conservative wind guidance" strategy) as the target wind guidance control strategy.

[0098] The second airflow control strategy is implemented as follows: instead of solely relying on the predicted position Ptarget, an airflow adjustment zone (e.g., a safety sector with radius R) is defined centered on the user's current position. The airflow guide plate is then controlled to oscillate slightly back and forth within this zone. The value of R can be dynamically adjusted based on the prediction reliability C; the lower the C, the larger the R, and the wider the sector coverage. Simultaneously, the predicted position Ptarget is used as the center reference point for the oscillation, causing the center of gravity of the oscillation to be slightly biased towards the predicted direction. The oscillation frequency can be set to 0.5Hz, and the amplitude should not exceed the edge of the sector.

[0099] For example, in a home living room environment, a user walks slowly with occasional pauses, their trajectory exhibiting some continuity but not complete smoothness. The prediction reliability C = 0.55, falling between C2 = 0.5 and C1 = 0.7. The system controls the air deflector to oscillate slightly within a safe sector near the user's current location, with the center of gravity slightly biased towards the predicted future location of the user. This ensures airflow covers the general area where the user is located while avoiding prolonged fixed-point blowing through micro-movements, thus balancing coverage and comfort.

[0100] When the prediction reliability C is less than or equal to the second reliability threshold C2, it indicates that the trajectory quality is poor and the prediction result is unreliable. The system will determine the third wind guidance control strategy (i.e., the "extremely conservative wind guidance" strategy) as the target wind guidance control strategy.

[0101] The third airflow control strategy is implemented as follows: The predicted location Ptarget is abandoned, and only the user's current location P is used. The azimuth angle θ of the user's current location relative to the air conditioner vent is calculated, and the air guide is fixed to point in a direction of θ+45° or θ-45° (i.e., avoiding direct frontal contact with the user, blowing towards the side or rear wall or ceiling). All dynamic adjustments based on trajectory prediction are paused until the prediction reliability recovers to above C2.

[0102] For example, in a home living room environment, a user sits still on the sofa watching TV, and the trajectory points are concentrated in a few grids for a long time. The prediction reliability C = 0.3, which is less than the second reliability threshold C2 = 0.5 of the current threshold group. The system stops the airflow control based on the prediction results and instead fixes the air deflector to a direction 45° away from the user's current position. The airflow is directed towards the side wall to form indirect air supply, minimizing direct airflow to the user while maintaining indoor air circulation.

[0103] The adaptive airflow control method for air conditioners disclosed in this invention constructs a user's movement trajectory and evaluates the trajectory quality characteristics. Based on this, it predicts the user's future movement position and outputs the prediction reliability, transforming airflow control from passive tracking based on the current position to active prediction based on the future position, thus solving the lag problem of airflow control. Simultaneously, it identifies the user's behavioral state based on the behavioral characteristics during movement, dynamically configures differentiated reliability judgment thresholds for different behavioral states, and adaptively selects the airflow control strategy based on the comparison result of the predicted reliability and the dynamic threshold. This allows the system to flexibly adjust the control sensitivity according to the user's behavioral state, solving the problem that existing airflow control methods cannot meet differentiated control requirements.

[0104] Figure 8 This is a schematic block diagram of an adaptive airflow control device 200 for an air conditioner provided in an embodiment of the present invention. Figure 8 As shown, corresponding to the above-described adaptive airflow control method for air conditioners, the present invention also provides an adaptive airflow control device 200 for air conditioners. This adaptive airflow control device 200 includes a unit for executing the above-described adaptive airflow control method for air conditioners. Specifically, please refer to... Figure 8 The adaptive airflow control device 200 for the air conditioner includes a trajectory construction unit 201, a prediction unit 202, a threshold determination unit 203, and a strategy selection unit 204.

[0105] The trajectory construction unit 201 is used to acquire the user's temporal location data and construct the user's movement trajectory based on the temporal location data. The prediction unit 202 is used to determine trajectory quality features based on the user's movement trajectory, and to determine the prediction result of the user's future movement location and the corresponding prediction reliability based on the trajectory quality features. The threshold determination unit 203 is used to determine the user behavior state based on the user's behavior characteristics during the user's movement, and dynamically determine the reliability judgment threshold corresponding to the user behavior state according to the user behavior state. The strategy selection unit 204 is used to select a target airflow control strategy from multiple airflow control strategies to perform airflow control on the air conditioner based on the predicted reliability and the reliability determination threshold.

[0106] In some embodiments, such as this one, the trajectory construction unit 201 further includes a first acquisition subunit, a synchronous filtering subunit, a data fusion subunit, and a trajectory arrangement subunit.

[0107] The first acquisition subunit is used to acquire the user's first location data and second location data respectively. The synchronization filtering subunit is used to synchronize the first position data and the second position data in time, and to filter the time-synchronized first position data and second position data. The data fusion subunit is used to fuse the filtered first and second position data to obtain the user's position coordinates at different times. The trajectory arrangement subunit is used to arrange the location coordinates in chronological order to construct the user's movement trajectory.

[0108] In some embodiments, such as this one, the prediction unit 202 further includes a grid mapping subunit, a connected component determination subunit, a statistics subunit, and a quality feature calculation subunit.

[0109] The grid mapping subunit is used to map trajectory points located within a preset time window in the user's movement trajectory to a pre-divided spatial grid. The connected component determination sub-unit is used to determine the grid occupied by the trajectory point and the trajectory connected region formed by the occupied grid. The statistics subunit is used to count the number of occupied grid cells and the number of trajectory connected regions. The quality feature calculation subunit is used to determine the trajectory quality features that characterize the continuity of the user's movement trajectory based on the number of occupied grids and the number of trajectory connected regions.

[0110] In some embodiments, such as this one, the prediction unit 202 further includes a threshold comparison subunit, an anomaly determination subunit, an effective point selection subunit, a trend prediction subunit, and a reliability determination subunit.

[0111] The threshold comparison subunit is used to compare the number of connected regions of the trajectory with a preset number threshold. An anomaly determination subunit is used to determine the corresponding trajectory segment as an abnormal trajectory segment and stop predicting the user's future movement location based on the abnormal trajectory segment if the number of connected regions of the trajectory is greater than the preset number threshold. The effective point selection subunit is used to select multiple consecutive effective trajectory points from the user's movement trajectory if the number of connected regions of the trajectory is less than or equal to the preset number threshold. The trend prediction subunit is used to determine the user's movement trend based on the multiple consecutive valid trajectory points, and to determine the prediction result of the user's future movement location based on the movement trend. The reliability determination subunit is used to determine the trajectory continuity index based on the number of occupied grids and the number of trajectory connected regions, and to determine the prediction reliability based on the trajectory continuity index.

[0112] In some embodiments, such as this one, the threshold determination unit 203 further includes a displacement determination subunit, a velocity direction calculation subunit, a behavior comparison subunit, and a state confirmation subunit.

[0113] The displacement determination subunit is used to determine the user's movement distance and direction within a preset time period based on the user's movement trajectory. The speed and direction calculation subunit is used to determine the user's average moving speed based on the moving distance and the preset time period, and to determine the user's direction change characteristics based on the changes in the moving direction. The behavior comparison subunit is used to compare the average moving speed and the direction change feature with the corresponding behavior determination conditions, respectively. The status confirmation subunit is used to confirm the behavior status based on the comparison result.

[0114] In some embodiments, such as this one, the threshold determination unit 203 further includes a threshold group configuration subunit, a first calling subunit, a second calling subunit, and a third calling subunit.

[0115] The threshold group configuration subunit is used to pre-configure a corresponding reliability threshold group for each user behavior state. Each reliability threshold group includes a first reliability threshold and a second reliability threshold that is less than the first reliability threshold. The first invocation subunit is used to invoke the first reliability threshold group when the user's behavior state is active. The second invocation subunit is used to invoke the second reliability threshold group when the user behavior state is in an intermediate state. The third invocation subunit is used to invoke the third reliability threshold group when the user behavior state is a quiet state. The reliability thresholds in the first reliability threshold group, the second reliability threshold group, and the third reliability threshold group increase sequentially.

[0116] In some embodiments, such as this one, the strategy selection unit 204 further includes a first strategy subunit, a second strategy subunit, and a third strategy subunit.

[0117] The first strategy subunit is used to determine the first air guiding control strategy as the target air guiding control strategy when the prediction reliability is greater than or equal to the first reliability threshold, determine the air guiding target based on the prediction result of the user's future movement location, and control the air guiding mechanism of the air conditioner to face the air guiding target. The second strategy subunit is used to determine the second wind guidance control strategy as the target wind guidance control strategy when the prediction reliability is less than the first reliability threshold and greater than the second reliability threshold, determine the wind guidance adjustment area according to the user's current position, control the wind guidance mechanism to swing within the wind guidance adjustment area, and make the swing center biased towards the prediction result of the user's future movement position. The third strategy subunit is used to determine the third wind guidance control strategy as the target wind guidance control strategy when the prediction reliability is less than or equal to the second reliability threshold, stop wind guidance control based on the prediction result of the user's future movement position, and determine the wind guidance direction to avoid the user based on the user's current position.

[0118] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned adaptive airflow control device and each unit of the air conditioner can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0119] The aforementioned adaptive airflow control device for air conditioners can be implemented as a computer program, which can, for example... Figure 9 The air conditioner shown is running.

[0120] Please see Figure 9 , Figure 9 This is a schematic block diagram of an air conditioner provided in an embodiment of this application. It can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0121] See Figure 9 The air conditioner 300 includes a processor 302, a memory, and an interface 307 connected via a system bus 301. The memory may include a non-volatile storage medium 303 and internal memory 304.

[0122] The non-volatile storage medium 303 may store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, it causes the processor 302 to execute an adaptive airflow control method for an air conditioner.

[0123] The processor 302 is used to provide computing and control capabilities to support the operation of the entire air conditioner 300.

[0124] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute an adaptive airflow control method for an air conditioner.

[0125] This interface 305 is used for communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the air conditioner 300 to which the present application is applied. The specific air conditioner 300 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0126] It should be understood that in the embodiments of this application, the processor 302 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0127] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0128] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program implements any embodiment of the above-described adaptive airflow control method for air conditioners.

[0129] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0130] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0131] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0132] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0133] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an air conditioner to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0134] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0135] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0136] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An adaptive airflow control method for an air conditioner, characterized in that, The method includes: Acquire the user's temporal location data and construct the user's movement trajectory based on the temporal location data; Based on the user's movement trajectory, determine the trajectory quality characteristics, and based on the trajectory quality characteristics, determine the prediction result of the user's future movement location and the corresponding prediction reliability. The user's behavior state is determined based on the user's behavioral characteristics during the user's movement, and a reliability judgment threshold corresponding to the user's behavior state is dynamically determined based on the user's behavior state. Based on the predicted reliability and the reliability determination threshold, a target airflow control strategy is selected from multiple airflow control strategies to control the airflow of the air conditioner.

2. The adaptive airflow control method for an air conditioner according to claim 1, characterized in that, The step of acquiring the user's temporal location data and constructing the user's movement trajectory based on the temporal location data includes: Obtain the user's first and second location data respectively; The first location data and the second location data are synchronized in time, and the synchronized first location data and second location data are filtered. The filtered first and second position data are fused to obtain the user's position coordinates at different times. The location coordinates are arranged in chronological order to construct the user's movement trajectory.

3. The adaptive airflow control method for an air conditioner according to claim 1, characterized in that, The determination of trajectory quality features based on the user's movement trajectory includes: Map the trajectory points in the user's movement trajectory that are located within a preset time window to a pre-divided spatial grid; Determine the grid occupied by the trajectory points and the trajectory connectivity region formed by the occupied grids; Count the number of occupied grid cells and the number of connected regions of the trajectory; Based on the number of occupied grids and the number of connected regions of the trajectory, a trajectory quality feature characterizing the continuity of the user's movement trajectory is determined.

4. The adaptive airflow control method for an air conditioner according to claim 3, characterized in that, The step of determining the prediction result of the user's future movement location and the corresponding prediction reliability based on the trajectory quality characteristics includes: Compare the number of connected regions of the trajectory with a preset number threshold; If the number of connected regions of the trajectory is greater than the preset number threshold, the corresponding trajectory segment is identified as an abnormal trajectory segment, and the prediction of the user's future movement location based on the abnormal trajectory segment is stopped. If the number of connected regions of the trajectory is less than or equal to the preset number threshold, then multiple consecutive valid trajectory points are selected from the user's movement trajectory; The user's movement trend is determined based on the multiple consecutive valid trajectory points, and the prediction result of the user's future movement location is determined based on the movement trend. The trajectory continuity index is determined based on the number of occupied grids and the number of trajectory connected regions, and the prediction reliability is determined based on the trajectory continuity index.

5. The adaptive airflow control method for an air conditioner according to claim 1, characterized in that, The process of determining user behavior state based on behavioral characteristics during user movement includes: The user's movement distance and direction within a preset time period are determined based on the user's movement trajectory. The user's average moving speed is determined based on the moving distance and the preset time period, and the user's directional change characteristics are determined based on the changes in the moving direction. The average moving speed and the direction change characteristics are compared with the corresponding behavior determination conditions, respectively. The behavioral state is confirmed based on the comparison results.

6. The adaptive airflow control method for an air conditioner according to claim 5, characterized in that, The step of dynamically determining the reliability threshold corresponding to the user behavior state based on the user behavior state includes: A corresponding reliability threshold group is pre-configured for each user behavior state, and each reliability threshold group includes a first reliability threshold and a second reliability threshold that is less than the first reliability threshold; If the user's behavior state is active, the first reliability threshold group is invoked. If the user behavior state is in an intermediate state, the second reliability threshold group is invoked. When the user's behavior state is quiet, the third reliability threshold group is invoked, wherein the corresponding reliability thresholds in the first reliability threshold group, the second reliability threshold group, and the third reliability threshold group increase sequentially.

7. The adaptive airflow control method for an air conditioner according to claim 6, characterized in that, The step of selecting a target airflow control strategy from multiple airflow control strategies based on the predicted reliability and the reliability determination threshold to perform airflow control on the air conditioner includes: If the prediction reliability is greater than or equal to the first reliability threshold, the first air guiding control strategy is determined as the target air guiding control strategy, the air guiding target is determined according to the prediction result of the user's future movement location, and the air guiding mechanism of the air conditioner is controlled to face the air guiding target. If the prediction reliability is less than the first reliability threshold and greater than the second reliability threshold, the second wind guidance control strategy is determined as the target wind guidance control strategy. The wind guidance adjustment area is determined according to the user's current position. The wind guidance mechanism is controlled to swing within the wind guidance adjustment area, and the swing center is biased towards the prediction result of the user's future movement position. If the prediction reliability is less than or equal to the second reliability threshold, the third wind guidance control strategy is determined as the target wind guidance control strategy, wind guidance control based on the prediction results of the user's future movement position is stopped, and the wind guidance direction to avoid the user is determined according to the user's current position.

8. An adaptive airflow control device for an air conditioner, characterized in that, The device includes: A trajectory construction unit is used to acquire the user's temporal location data and construct the user's movement trajectory based on the temporal location data; The prediction unit is used to determine trajectory quality features based on the user's movement trajectory, and to determine the prediction result of the user's future movement location and the corresponding prediction reliability based on the trajectory quality features. The threshold determination unit is used to determine the user's behavior state based on the user's behavior characteristics during the user's movement, and dynamically determine the reliability judgment threshold corresponding to the user's behavior state according to the user's behavior state. The strategy selection unit is used to select a target airflow control strategy from multiple airflow control strategies based on the predicted reliability and the reliability determination threshold to perform airflow control on the air conditioner.

9. An air conditioner, characterized in that, The air conditioner includes a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the computer program stored in the memory to perform the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the steps of the method as described in any one of claims 1-7.

Images