An air-drying behavior recognition method, device, equipment and storage medium

Abstract

The application relates to a drying behavior recognition method, device and equipment and a storage medium. Whether a drying event end condition is met is judged according to real-time collected user operation data and drying machine state data. The drying event end condition includes a first dynamic threshold judgment condition based on an operation interval, a second dynamic threshold judgment condition based on drying machine drying rod position retention or a matching judgment condition based on a preset drying completion operation sequence feature. If any drying event end condition is met, the current drying event is determined to be ended, and a correction window is started. If a new user operation instruction is detected again in the correction window, the current drying event end determination is cancelled, and the operation corresponding to the new user operation instruction is integrated into the current drying event. Compared with the prior art, the technical scheme of the application can realize high precision, strong adaptability, real-time performance and high anti-interference performance of drying event recognition, and improves the intelligent level of an intelligent drying machine.

Description

Technical Field

[0001] This application relates to the technical field of smart furniture, and in particular to a method, device, equipment and storage medium for recognizing drying behavior. Background Technology

[0002] With the rapid development of smart home technology, smart clothes drying racks with lifting control functions have become common household appliances. Accurate statistics of their operating data are the core foundation for realizing intelligent optimization of the equipment and are of great significance for improving the user experience and the level of intelligence of the equipment.

[0003] Currently, the industry's identification technologies for clothes drying rack events mainly fall into three categories: First, the single-operation statistics scheme, which classifies each user's up, down, and pause button operation as an independent event and records it through timestamps for statistical analysis; second, the thresholdless continuous statistics scheme, which does not set an event segmentation threshold and classifies all operations after the device is powered on as the same event until the device is powered off or manually reset; and third, the fixed time interval segmentation scheme, which divides events by preset fixed times and relies solely on a single time dimension for judgment. The above technologies show an evolutionary trend from single operation recording to continuous behavior statistics, but a comprehensive identification scheme that takes into account multi-dimensional needs has not yet been formed.

[0004] Furthermore, existing technologies for recognizing drying events on clothes dryers have significant flaws. For example, single-operation statistics methods split intermittent operations within the same drying process, while threshold-free methods merge different drying behaviors spaced several hours apart, leading to data distortion. Fixed thresholds cannot match the usage habits of different users and require manual adjustment, which is cumbersome. Moreover, there is a lag in response, relying on a passive segmentation logic that waits for the threshold to be met. Even if the user has finished drying, they still need to wait a fixed amount of time before the event is segmented. There is also a lack of a misjudgment correction mechanism. User accidental touches or temporary adjustments can easily lead to incorrect event segmentation or merging, making it difficult to meet the high-precision, adaptive, and real-time response requirements of smart clothes dryers. Summary of the Invention

[0005] This application provides a method, device, equipment, and storage medium for recognizing clothes drying behavior, which can achieve high precision, strong adaptability, real-time performance, and high anti-interference capability in clothes drying event recognition, thereby improving the intelligence level of smart clothes drying machines.

[0006] In a first aspect, this application provides a method for recognizing clothes drying behavior, comprising: real-time collection of user operation data and clothes drying machine status data; determining whether a clothes drying event termination condition is met based on the user operation data and clothes drying machine status data, wherein the clothes drying event termination condition includes a first dynamic threshold judgment condition based on the operation interval, a second dynamic threshold judgment condition based on the position of the clothes drying rod, or a matching judgment condition based on a preset sequence of features of completed clothes drying operations; if any of the clothes drying event termination conditions are met, the current clothes drying event is determined to have ended, and a correction window is initiated; if a new user operation instruction is detected again within the correction window, the determination of the current clothes drying event termination is revoked, and the operation corresponding to the new user operation instruction is incorporated into the current clothes drying event.

[0007] In one possible implementation, the first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying events.

[0008] In one possible implementation, the first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying data. Specifically, this includes: within a preset update cycle, statistically analyzing the operation interval duration and storage time in historical drying events; calculating the first and second updated dynamic thresholds based on the statistical results; determining whether the first and second updated dynamic thresholds fall within their respective preset boundary ranges; if so, using the first and second updated dynamic thresholds as the updated first and second dynamic thresholds; otherwise, selecting the boundary values ​​of the preset boundary ranges corresponding to the first and second updated dynamic thresholds as the updated first and second dynamic thresholds.

[0009] In one possible implementation, before collecting user operation data and clothes dryer status data in real time, the method further includes: initializing the system operating status of the clothes dryer, wherein the system operating status includes at least the cumulative count of the silent timer, the current position of the clothes dryer, the duration of stay at the current position, and the preset storage position of the clothes dryer.

[0010] In one possible implementation, the real-time acquisition of user operation data and clothes dryer status data specifically includes: real-time detection of user operation commands; if no user operation command is acquired, starting a silent timer for timing processing until the user operation command is acquired; recording the first cumulative count of the silent timer and resetting the silent timer; updating the cumulative count of the silent timer based on the first cumulative count; acquiring user operation data and clothes dryer status data corresponding to the user operation command, wherein the user operation data includes an operation timestamp, and the clothes dryer status data includes the first position of the clothes dryer rod and the duration of dwell at the first position; updating the current position of the clothes dryer based on the first position, and updating the dwell time at the current position based on the dwell time at the first position; associating the user operation command, the operation timestamp, and the first position to form operation data, and storing the operation data in the operation sequence cache of the clothes dryer.

[0011] In one possible implementation, the first dynamic threshold judgment condition based on the operation interval includes that the current position is not the preset storage position of the clothes drying rack, and the cumulative count of the silent timer is not less than the first dynamic threshold.

[0012] In one possible implementation, the second dynamic threshold judgment condition based on the position of the clothes drying rack includes that the current position is the storage position, and the duration of the current position is not less than the second dynamic threshold.

[0013] In one possible implementation, the matching judgment condition based on the preset drying completion operation sequence features includes that the current position is the storage position, and the operation sequence formed by the operation data cached in the operation sequence cache matches at least one drying completion operation sequence feature in the pre-stored operation feature library.

[0014] In one possible implementation, before determining whether the drying event termination condition is met based on user operation data and clothes dryer status data, the method further includes: obtaining an event status identifier in the system operation status of the clothes dryer; if a user operation command is collected and the event status identifier is "started", determining whether the drying event termination condition is met based on the user operation data and clothes dryer status data; if the user operation command is collected and the event status identifier is "not started", updating the event status identifier to "started", recording the operation timestamp corresponding to the user operation command as the start timestamp of the current drying event, and classifying the user operation command as the currently started drying event.

[0015] In one possible implementation, determining the end of the current drying event and initiating a correction window if any of the drying event end conditions are met specifically includes: if any of the drying event end conditions are met, recording the operation timestamp corresponding to the current user operation instruction as the end timestamp of the current drying event; clearing the operation sequence cache and updating the event status identifier in the system running status of the clothes dryer to not started; and starting a misjudgment correction timer with a duration of a preset time threshold to initiate the correction window.

[0016] In one possible implementation, the step of canceling the current drying event termination determination and incorporating the operation corresponding to the new user operation instruction into the current drying event if a new user operation instruction is detected again within the correction window specifically includes: canceling the termination determination of the current drying event and incorporating the new user operation instruction and its corresponding operation into the current drying event if a new user operation instruction is detected again within the correction window; obtaining and updating the termination timestamp of the current drying event based on the operation timestamp corresponding to the new user operation instruction; and resetting the misjudgment correction timer.

[0017] Secondly, this application provides a clothes drying behavior recognition device, including: a data acquisition module, an event end judgment module, an event end determination module, and a correction module; wherein, the data acquisition module is used to collect user operation data and clothes drying machine status data in real time; the event end judgment module is used to determine whether the clothes drying event end conditions are met based on the user operation data and clothes drying machine status data, wherein the clothes drying event end conditions include a first dynamic threshold judgment condition based on the operation interval, a second dynamic threshold judgment condition based on the position of the clothes drying machine rod, or a matching judgment condition based on a preset sequence of features of completed clothes drying operations; the event end judgment module is used to determine that the current clothes drying event has ended if any of the clothes drying event end conditions are met, and to start a correction window; the correction module is used to cancel the current clothes drying event end determination and incorporate the operation corresponding to the new user operation instruction into the current clothes drying event if a new user operation instruction is detected again in the correction window.

[0018] Thirdly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0019] This application provides a method, apparatus, device, and storage medium for identifying drying behavior, which has the following advantages compared with the prior art: Based on real-time collection of user operation data and clothes drying rack status data, the system determines whether the drying event termination conditions are met. These conditions include a first dynamic threshold based on the operation interval, a second dynamic threshold based on the position of the clothes drying rack rod, or a matching condition based on a preset drying completion operation sequence feature. If the drying event termination conditions are met, the current drying event is determined to have ended, and a correction window is initiated. If a new user operation command is detected within the correction window, the current drying event termination determination is revoked, and the drying event corresponding to the new user operation command is merged into the current drying event. Compared with existing technologies, this application's technical solution, through real-time collection of user operation data... Operational data and clothes drying rack status data provide comprehensive evidence for determining drying events. Combining dynamic threshold judgments based on operation intervals and location dwell times with matching judgments based on preset drying completion operation sequence features replaces the single judgment logic of existing technologies, significantly reducing the possibility of incorrect event splitting or merging and dramatically improving recognition accuracy. Furthermore, the application of dynamic thresholds can adapt to different users' operating habits without manual adjustment, solving the problem of poor adaptability of fixed thresholds. Matching judgments based on preset operation sequence features can identify the user's intention to end the event in real time, without waiting for the threshold to be met, improving the real-time performance of event segmentation. The correction window mechanism can cancel the original end judgment and merge operations when a new operation command is detected, effectively dealing with interference from user accidental touches and temporary adjustments, enhancing anti-interference capabilities. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0023] Figure 1 This is a flowchart illustrating one embodiment of a method for recognizing drying behavior provided in this application; Figure 2 This is a schematic diagram of one embodiment of a clothes drying behavior recognition device provided in this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0026] 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, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0027] 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 scope of the application. 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.

[0028] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0029] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0030] Example 1, see Figure 1 , Figure 1This is a flowchart illustrating one embodiment of a method for recognizing drying behavior provided in this application, as shown below. Figure 1 As shown, the method includes steps 101-104, as detailed below: Step 101: Collect user operation data and clothes drying rack status data in real time.

[0031] In one embodiment, before starting the clothes drying behavior recognition process and entering the real-time collection of user operation data and clothes drying machine status data, it is necessary to first complete the initialization configuration of basic parameters and system status to provide a unified benchmark for subsequent recognition logic; therefore, before the real-time collection of user operation data and clothes drying machine status data, the method further includes: when the smart clothes drying machine is detected to be powered on and started, initializing the first dynamic threshold and the second dynamic threshold.

[0032] In one embodiment, before collecting user operation data and clothes drying rack status data in real time, the method further includes: initializing the system operating status of the clothes drying rack, wherein the system operating status includes at least the cumulative count of the silent timer, the current position of the clothes drying rack, the duration of stay at the current position, and the preset storage position of the clothes drying rack.

[0033] Preferably, the system operating status also includes event status identifiers and operation sequence caches.

[0034] In one embodiment, the initialization of the clothes drying rack's system operation status includes resetting the accumulated time of the silent timer to zero, determining the preset storage location of the clothes drying rack, and resetting the dwell time at the current location to zero.

[0035] Preferably, the initialization of the clothes drying rack's system operating status further includes setting the event status identifier to an unstarted identifier and clearing the operation sequence cache.

[0036] Specifically, when initializing the first dynamic threshold and the second dynamic threshold, it is checked whether there are historically stored first and second historical dynamic thresholds; if they exist, the first dynamic threshold and the second dynamic threshold are respectively set to the historically stored first and second historical dynamic thresholds; if they do not exist, the first dynamic threshold and the second dynamic threshold are set to their respective initial default values.

[0037] Preferably, the first dynamic threshold is an operation interval threshold, and the second dynamic threshold is a storage location dwell threshold; the initial default value of the first dynamic threshold is 1 hour, and the initial default value of the second dynamic threshold is 10 minutes.

[0038] Specifically, the system operation status of the clothes drying rack is fully initialized. For example, the event status flag is set to "Not Started," indicating that no drying events have been triggered yet; the cumulative count of the silent timer used to count the duration of no operation is cleared to ensure that the no-operation time count starts from zero; the current position of the clothes drying rack is set to a preset storage position, which is a fully raised storage mechanical positioning point confirmed by a Hall sensor or limit switch; the dwell time at the current position is cleared to ensure accurate starting of the count of the clothes drying rack's dwell time at any position; in addition, the operation sequence cache used to store operation data is cleared to prepare for subsequent data collection and storage.

[0039] Specifically, after completing the initial threshold settings and system operation status initialization, the system officially enters the standby state and can start the continuous collection process of user operation data and clothes drying rack status data to ensure that there is an accurate and unified initial benchmark when judging drying events based on the updated system operation status.

[0040] In one embodiment, the first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying events.

[0041] Specifically, the periodic updates of the first and second dynamic thresholds are automatically completed by the self-learning model based on the user's historical drying events. It can automatically adapt to the usage habits of different users without manual intervention. The updates are achieved through data statistics threshold calculation and boundary verification to ensure that the thresholds are accurately adapted to the user's usage habits.

[0042] In one embodiment, when the first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying events, the operation interval duration and storage time in the historical drying events are statistically analyzed within a preset update cycle. The first updated dynamic threshold and the second updated dynamic threshold are calculated based on the statistical results. It is determined whether the first updated dynamic threshold and the second updated dynamic threshold fall within their respective preset boundary ranges. If so, the first updated dynamic threshold and the second updated dynamic threshold are used as the updated first dynamic threshold and the second dynamic threshold. Otherwise, the boundary values ​​of the preset boundary ranges corresponding to the first updated dynamic threshold and the second updated dynamic threshold are selected as the updated first dynamic threshold and the second dynamic threshold.

[0043] Specifically, the first dynamic threshold and the second dynamic threshold are updated through a preset fixed update cycle; preferably, the preset fixed update cycle is from 00:00 to 02:00 every day, which is a low-load period for the device and will not affect the normal use of the user.

[0044] Specifically, when periodically updating the first dynamic threshold and the second dynamic threshold, the self-learning model automatically extracts the user's historical clothes drying events over the past 30 days to calculate the interval between adjacent operations in all clothes drying events, i.e., the time difference between the timestamps of two consecutive user operation commands; and calculates the dwell time at the storage position, i.e., the duration during which no user operation occurs after the clothes dryer reaches the storage position, ensuring that the statistical data can fully reflect the user's regular usage rhythm.

[0045] Specifically, when calculating the first and second dynamic thresholds based on statistical results, for the first dynamic threshold T1, the 95th percentile of the statistically obtained interval duration data of adjacent operations is used as the first dynamic threshold. This calculation method can filter out the interference of extremely short interval operations, ensuring that 95% of normal operation intervals will not trigger erroneous segmentation, thus balancing adaptability and stability. For the second dynamic threshold T2, the average dwell time at the storage location is used as the basis, with an additional preset first time added as the second dynamic threshold. This not only conforms to the average dwell time of users but also reserves a certain buffer time, balancing the real-time performance of event segmentation with the risk of misjudgment. Preferably, the preset first time is 2 minutes.

[0046] Preferably, the first dynamic threshold T1 can also be optimized by integrating environmental data such as temperature and humidity, weather conditions, and clothing weight sensors. For example, when the drying interval of users may be extended on rainy days, the algorithm will automatically adjust the first dynamic threshold T1 based on the newly added environmental data to further improve the accuracy of event segmentation.

[0047] Preferably, the boundary range of the first dynamic threshold is 20 minutes to 2 hours, and the boundary range of the second dynamic threshold is 3 minutes to 15 minutes. The self-learning model will determine whether the calculated first and second updated dynamic thresholds fall within the corresponding boundary ranges: if the updated dynamic thresholds are within the boundary ranges, they will be directly used as the updated first and second dynamic thresholds; if the updated thresholds exceed the boundary ranges, the limit value of the corresponding boundary range will be selected as the final threshold. The updated first dynamic threshold T1 and second dynamic threshold T2 will be persistently stored, replacing the original thresholds, and will be automatically read and used for drying event segmentation during the next system initialization, realizing dynamic iterative optimization of the thresholds.

[0048] Preferably, in addition to automatically and periodically updating the first dynamic threshold and the second dynamic threshold based on a self-learning model, the application-side threshold fine-tuning function is also supported to manually update the first dynamic threshold and the second dynamic threshold, so as to support users to manually adjust the offset of the first dynamic threshold and the second dynamic threshold according to special needs, taking into account both adaptability and flexibility.

[0049] In one embodiment, the real-time acquisition of user operation data and clothes dryer status data specifically includes: real-time detection of user operation commands; if no user operation command is acquired, starting a silent timer for timing processing until the user operation command is acquired; recording the first cumulative count of the silent timer and resetting the silent timer; updating the cumulative count of the silent timer based on the first cumulative count; acquiring user operation data and clothes dryer status data corresponding to the user operation command, wherein the user operation data includes an operation timestamp, and the clothes dryer status data includes the first position of the clothes dryer rod and the duration of dwell at the first position; updating the current position of the clothes dryer based on the first position, and updating the dwell time at the current position based on the dwell time at the first position; associating the user operation command, the operation timestamp, and the first position to form operation data, and storing the operation data in the operation sequence cache of the clothes dryer.

[0050] Specifically, the user operation commands include, but are not limited to, up, down, and pause commands, and the triggering methods for these commands include, but are not limited to, manual, app, and voice triggering methods. User operation data includes specific operation content, operation timestamps, and operation time intervals, while clothes drying rack status data includes the position of the clothes drying rack rods and the duration of their position. Specifically, by continuously monitoring for user input, if no user input is detected, the system will start a silent timer to accumulate the count. This silent timer is specifically used to count the duration of inactivity. Once a user input is detected, the system immediately records the first accumulated count of the silent timer and then resets the silent timer to zero, completing the phased statistics and updates of the inactivity duration and providing data support for subsequent operation interval judgment.

[0051] Specifically, upon receiving a user operation command, the system simultaneously acquires the corresponding user operation data and clothes dryer status data. The user operation data includes an operation timestamp, and the clothes dryer status data includes the first position of the clothes dryer rod and the duration of dwell time at that position. The operation timestamp accurately records the time of the operation, providing a basis for event duration calculation and operation interval statistics. The first position of the clothes dryer rod is the real-time physical position of the device when the operation command is executed. If the user operation command is to pause, the current real-time physical position of the clothes dryer rod is collected as the first position of the clothes dryer rod. If the user's operation command is to lower the clothes dryer, the real-time physical position of the clothes dryer after the lowering operation is collected as the first position of the clothes dryer rod. The first position is collected and confirmed by the position sensor and used to determine whether the device is in the storage state. The dwell time at the first position is the duration of no operation of the clothes dryer at the first position. Based on the collected first position, the system will update the current position parameters of the clothes dryer in real time to ensure that the current position is consistent with the actual state of the device. At the same time, the dwell time at the first position replaces the original dwell time at the current position to complete the real-time update of the device's dwell state and provide the latest data for the position state trigger judgment.

[0052] Preferably, the user operation data also includes specific operation content and operation time interval.

[0053] Specifically, the user operation instructions collected this time, the corresponding operation timestamps, and the first position are associated and bound to form an operation data that includes the operation type, operation timestamp, and first position corresponding to the user operation instructions, ensuring the complete correspondence between the operation behavior and the spatiotemporal state; and the operation data is stored in the operation sequence cache in chronological order.

[0054] Preferably, the operation sequence cache is specifically used to store the most recent preset number of operation data. When new operation data is stored, causing the cached data volume of the operation sequence cache to exceed the preset number of data, the system will automatically overwrite the oldest historical operation data, always keeping the cached data as the latest and most valuable operation record, providing data support for operation sequence feature matching in subsequent multi-dimensional judgment steps; preferably, the preset number of data is 5.

[0055] Step 102: Based on user operation data and clothes drying rack status data, determine whether the drying event termination condition is met. The drying event termination condition includes a first dynamic threshold judgment condition based on the operation interval, a second dynamic threshold judgment condition based on the position of the clothes drying rack rod, or a matching judgment condition based on the preset drying completion operation sequence features.

[0056] In one embodiment, before determining whether the drying event termination condition is met based on user operation data and clothes dryer status data, the method further includes: obtaining an event status identifier in the system operation status of the clothes dryer; if a user operation command is collected and the event status identifier is "started", determining whether the drying event termination condition is met based on the user operation data and clothes dryer status data; if the user operation command is collected and the event status identifier is "not started", updating the event status identifier to "started", recording the operation timestamp corresponding to the user operation command as the start timestamp of the current drying event, and classifying the user operation command as the currently started drying event.

[0057] Specifically, the event status identifiers in the current system operation status are read in real time. The event status identifiers include two states: started and not started, which correspond to the system operation scenarios of a drying event in progress and a drying event not triggered, respectively, to ensure that subsequent judgments are only made for the effective drying process.

[0058] Specifically, if the system collects user operation instructions and the current event status is marked as started, it indicates that a certain drying event is in the process of execution, which meets the premise of determining whether the event has ended. The system will then enter the subsequent multi-dimensional judgment stage to verify whether the drying event ends based on the updated system running status.

[0059] Specifically, if the system collects a user operation command, but the current event status is marked as not started, it indicates that the user operation command is the starting operation that triggers a new drying event. At this time, the system will immediately update the event status, switching it from not started to started, and record the operation timestamp corresponding to the user operation command as the start timestamp of the newly started drying event. In addition, the triggered operation will be directly assigned to the currently started drying event, completing the binding of event and operation, laying the foundation for subsequent operation sequence statistics and event duration calculation. After the status update, start timestamp recording, and operation assignment are completed, the system returns to the data collection stage for continuous monitoring and does not enter the termination condition judgment process for the time being.

[0060] In one embodiment, the first dynamic threshold judgment condition based on the operation interval includes that the current position is not the preset storage position of the clothes drying rack, and the cumulative count of the silent timer is not less than the first dynamic threshold.

[0061] Specifically, when the current position of the clothes drying rack is not the preset storage position, and the cumulative count of the silent timer reaches or exceeds the first dynamic threshold, it indicates that the user has not performed any operation on the device for a relatively long period of time, and it can be determined that the current drying operation has been terminated. This judgment condition is used to handle special scenarios where the clothes are not stored but there is no operation for a long time. For example, if the user forgets to fully raise and store the clothes drying rack after hanging the clothes, or temporarily goes out and the device is in an unstored state for a long time, the drying event can be automatically segmented by the first dynamic threshold constraint to avoid incomplete event statistics due to user omissions, while taking into account the accuracy and adaptability of the judgment.

[0062] In one embodiment, the second dynamic threshold judgment condition based on the position of the clothes drying rack includes the current position being the storage position, and the duration of the current position being stayed is not less than the second dynamic threshold.

[0063] Specifically, when the clothes drying rack is currently in the storage position, and the inactive dwell time in the storage position reaches or exceeds the second dynamic threshold, it indicates that the user has completed the drying operation and has no intention of further adjustment. The device is in a stable storage state, and the drying event segmentation is triggered at this time. This judgment condition is used to handle the normal scenario of stable dwell time after storage. It avoids the passive lag problem of waiting for a fixed time in the existing technology, and adapts to the usage habits of different users through dynamic thresholds, ensuring that the event segmentation is both accurate and in line with the actual use scenario.

[0064] In one embodiment, the matching judgment condition based on the preset drying completion operation sequence features includes that the current position is the storage position, and the operation sequence formed by the operation data cached in the operation sequence cache matches at least one drying completion operation sequence feature in the pre-stored operation feature library.

[0065] Specifically, when the current position of the clothes drying rack is the storage position, and the operation sequence formed by the operation sequence cache matches any drying completion operation sequence feature in the pre-stored operation feature library, the judgment condition is met. This judgment condition does not require waiting for the position dwell threshold to be met, and can identify the user's intention to finish drying in real time, which greatly improves the real-time performance of event segmentation. It solves the response lag problem caused by passively waiting for the threshold in the existing technology, and at the same time covers the typical drying habits of most users, ensuring the accuracy and practicality of the judgment.

[0066] Preferably, the drying completion operation sequence features stored in the pre-stored operation feature library include, but are not limited to, a first operation sequence feature, a second operation sequence feature, and a third operation sequence feature. The first operation sequence feature is: descent → pause for ≥5 minutes → rise → storage position; the second operation sequence feature is: descent → rise → storage position; and the third operation sequence feature is: multiple start-stop cycles ≤30 seconds / time → rise → storage position.

[0067] Preferably, the matching condition corresponding to the first operation sequence feature is that the duration of stay at the current position is not less than 5 minutes, and the current position is a storage position; the matching condition corresponding to the second operation sequence feature is that there is no pause operation and the current position is a storage position; the matching condition corresponding to the third operation sequence feature is that the duration of a single start-stop operation is not more than 30 seconds, and the number of starts and stops is not less than 2.

[0068] Preferably, the pre-stored operation feature library in the matching judgment conditions based on the preset drying completion operation sequence features can be replaced by a deep learning model; for example, the matching judgment conditions based on the preset drying completion operation sequence features include that the current position is the storage position, and the operation sequence formed by the operation data cached in the operation sequence cache matches the various drying completion operation sequence features learned by the deep learning model trained with a large amount of user operation data.

[0069] Preferably, the deep learning model is trained with a large amount of user operation data to automatically learn the operation sequence features of more complex drying scenarios, such as segmented hanging of clothes and picking up and putting away single items of clothing in the middle, so as to achieve coverage of more edge scenarios.

[0070] Specifically, when determining whether the drying event termination conditions are met based on user operation data and clothes dryer status data, three judgment conditions are executed in parallel and complement each other. This covers both the special scenario of the clothes not being tidied up and the regular scenario of the clothes being tidied up, as well as the real-time intent recognition scenario. The system extracts core data such as the current position, silent timer duration, current position dwell time, and operation sequence cache from the updated system running status, and substitutes them into the three judgment conditions for verification. As long as any judgment condition is met, the determination that the drying event termination conditions are met is completed, and then the system enters the segmentation stage of drying event termination. If all conditions are not met, the system returns to the data collection step, continuously updates the system running status, and waits for the next verification.

[0071] Step 103: If any of the conditions for ending the drying event are met, the current drying event is determined to have ended, and the correction window is started.

[0072] In one embodiment, if any of the drying event termination conditions are met, the operation timestamp corresponding to the current user operation instruction is recorded as the termination timestamp of the current drying event; the operation sequence cache is cleared, and the event status identifier in the system running status of the clothes dryer is updated to not started; a misjudgment correction timer with a duration of a preset time threshold is started to initiate the correction window.

[0073] Specifically, the operation timestamp corresponding to the user operation command that triggered the current termination condition is extracted and used as the termination timestamp of the current drying event. This timestamp, together with the start timestamp recorded when the event started, forms the time span of this drying event, providing accurate data for subsequent operation data statistics, such as the duration of a single drying session.

[0074] Specifically, the operation sequence cache storing the data of the last 5 operations is cleared, and the historical operation data of the user operation instruction-operation timestamp-first position related to this event is deleted to avoid old data interfering with the judgment of the next drying event; and the event status identifier in the system running status is updated from started to not started, indicating that the current drying event has been initially segmented, and the system returns to the waiting state to prepare for receiving new drying operations and starting new events.

[0075] Specifically, a preset misjudgment correction timer is activated. The timer has a fixed duration of 3 minutes, and its activation marks the official opening of the correction window. The correction window is used to deal with sudden interference operations such as accidental touches and temporary adjustments by users, providing remedial space for possible missegmentation and ensuring the accuracy of event segmentation. After the misjudgment correction timer is activated, the misjudgment correction monitoring stage is entered, continuously monitoring for new user operation commands until the misjudgment correction timer expires.

[0076] In one embodiment, if the termination condition of any of the drying events is not met, it means that the same drying event is being executed at this time, and the user operation corresponding to the current user operation instruction is a continuous adjustment to this event. In this case, the user operation corresponding to the current user operation instruction is directly assigned to the currently ongoing drying event. There is no need to restart the event or update the start timestamp. Only the data collection step is returned, and the system running status is continuously updated to ensure the integrity of the operation associated with the event.

[0077] Step 104: If a new user operation command is detected again in the correction window, the current drying event termination determination is cancelled, and the operation corresponding to the new user operation command is merged into the current drying event.

[0078] In one embodiment, if a new user operation command is detected again within the correction window, the termination determination of the current drying event is revoked, and the new user operation command and its corresponding operation are assigned to the current drying event; the termination timestamp of the current drying event is obtained and updated based on the operation timestamp corresponding to the new user operation command; and the misjudgment correction timer is reset.

[0079] In one embodiment, in addition to synchronously resetting the misjudgment correction timer, the silent timer is also synchronously reset.

[0080] Specifically, within the 3-minute correction window after the misjudgment correction timer starts, it continuously monitors for new user operation commands to deal with unexpected interference scenarios such as user accidental touches and temporary adjustments, ensuring the accuracy of the drying event segmentation.

[0081] Specifically, if a new user operation command is detected in the correction window, it indicates that the previous determination of the end of the drying event was incorrect. First, the previous determination of the end of the current drying event is cancelled, and the current drying event is restored to its unfinished state to avoid the same drying process being split into multiple drying events due to incorrect segmentation. At the same time, the new user operation command and its corresponding multi-dimensional status data are also attributed to the current drying event to ensure the integrity of the operation associated with the event and accurately reflect the user's continuous usage behavior.

[0082] Specifically, the system extracts the operation timestamp corresponding to the new user's operation command and updates the current drying event's end timestamp with this timestamp, replacing the previously recorded end timestamp. This clarifies the latest end point of the event and provides accurate data for subsequent duration statistics. Simultaneously, the system resets the silent timer and the misjudgment correction timer: the silent timer restarts counting the duration without operation after being cleared, and the misjudgment correction timer stops counting after being cleared, with the correction window closing accordingly. After completing the above operations, the system returns to the data collection step to continue collecting data in real time and updating the system's operating status, awaiting the next multi-dimensional judgment to ensure that subsequent event judgments are not affected by this misjudgment correction operation.

[0083] In one embodiment, if no new user operation command is detected in the correction window, it is determined that the current drying event end determination is consistent with the user's actual intention and there is no erroneous segmentation. At this time, the current drying event segmentation officially takes effect.

[0084] In one embodiment, the operation sequence cache is kept clear to avoid interference from old data; the event status flag is kept set to not started to indicate that the system has returned to the ready-to-trigger state and can respond to new drying operation commands at any time; and the data collection step is returned to restart the continuous collection process of user operation data and clothes dryer status data, and the system operation status parameters such as silent timer, current position, and dwell time are updated in real time, waiting for new user operation commands to trigger the next drying event, ensuring that the entire recognition process is smooth and continuously adapts to the user's subsequent usage needs.

[0085] In one embodiment, after the current drying event is segmented and takes effect, the effective motor running time corresponding to the effective drying event can be extracted, and energy consumption data can be determined based on the effective motor running time. The effective motor running time and energy consumption data corresponding to all drying events within a preset period are integrated to generate a structured drying energy consumption report, providing multi-dimensional data support for equipment energy-saving optimization.

[0086] Specifically, when extracting the effective motor runtime corresponding to an effective drying event, the operation time period corresponding to the motor operation can be filtered out based on the event start timestamp and event end timestamp, combined with the operation data stored in the operation sequence cache. For example, the effective running time of the clothes dryer during the rising and falling process can be excluded, and the pause and no-operation rest periods can be excluded, so as to accurately calculate the actual motor runtime of a single drying event.

[0087] Example 2, see Figure 2 , Figure 2 This is a schematic diagram of one embodiment of a clothes drying behavior recognition device provided in this application. Corresponding to the above-described clothes drying behavior recognition method, this application also provides a clothes drying behavior recognition device. This clothes drying behavior recognition device includes modules for executing the above-described clothes drying behavior recognition method, and can be configured in a desktop computer, tablet computer, laptop computer, or other terminal; specifically, the clothes drying behavior recognition device includes a data acquisition module 201, an event end judgment module 202, an event end determination module 203, and a correction module 204.

[0088] The data acquisition module 201 is used to collect user operation data and clothes drying machine status data in real time.

[0089] The event end judgment module 202 is used to determine whether the drying event end conditions are met based on user operation data and clothes drying machine status data. The drying event end conditions include a first dynamic threshold judgment condition based on the operation interval, a second dynamic threshold judgment condition based on the position of the clothes drying rod, or a matching judgment condition based on the preset drying completion operation sequence features.

[0090] The event end determination module 203 is used to determine the current drying event is over if any of the drying event end conditions are met, and to start the correction window.

[0091] The correction module 204 is used to cancel the current drying event termination determination and incorporate the operation corresponding to the new user operation instruction into the current drying event if a new user operation instruction is detected again in the correction window.

[0092] In one embodiment, the first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying events.

[0093] In one embodiment, the first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying data. Specifically, this includes: within a preset update cycle, statistically analyzing the operation interval duration and storage time in historical drying events; calculating the first and second updated dynamic thresholds based on the statistical results; determining whether the first and second updated dynamic thresholds fall within their respective preset boundary ranges; if so, using the first and second updated dynamic thresholds as the updated first and second dynamic thresholds; otherwise, selecting the boundary values ​​of the preset boundary ranges corresponding to the first and second updated dynamic thresholds as the updated first and second dynamic thresholds.

[0094] In one embodiment, the clothes drying behavior recognition device provided in this application further includes: an initialization module; wherein the initialization module is used to set the first dynamic threshold and the second dynamic threshold to their respective initial default values, and to initialize the system operating state of the clothes drying machine, wherein the system operating state includes at least the cumulative count of the silent timer, the current position of the clothes drying machine, the duration of stay at the current position, and the preset storage position of the clothes drying machine.

[0095] In one embodiment, the data acquisition module 201 is used to acquire user operation data and clothes dryer status data in real time, specifically including: real-time detection of user operation commands; if the user operation command is not acquired, starting the silent timer for timing processing until the user operation command is acquired; recording the first cumulative count of the silent timer and resetting the silent timer; updating the cumulative count of the silent timer based on the first cumulative count; acquiring user operation data and clothes dryer status data corresponding to the user operation command, wherein the user operation data includes an operation timestamp, and the clothes dryer status data includes the first position of the clothes dryer rod and the duration of stay at the first position; updating the current position of the clothes dryer based on the first position, and updating the duration of stay at the current position based on the duration of stay at the first position; associating the user operation command, the operation timestamp, and the first position to form operation data, and storing the operation data in the operation sequence cache of the clothes dryer.

[0096] In one embodiment, the first dynamic threshold judgment condition based on the operation interval includes that the current position is not the preset storage position of the clothes drying rack, and the cumulative count of the silent timer is not less than the first dynamic threshold.

[0097] In one embodiment, the second dynamic threshold judgment condition based on the position of the clothes drying rack includes the current position being the storage position, and the duration of the current position being stayed is not less than the second dynamic threshold.

[0098] In one embodiment, the matching judgment condition based on the preset drying completion operation sequence features includes that the current position is the storage position, and the operation sequence formed by the operation data cached in the operation sequence cache matches at least one drying completion operation sequence feature in the pre-stored operation feature library.

[0099] In one embodiment, the event termination judgment module 202, before determining whether the drying event termination condition is met based on user operation data and clothes dryer status data, further includes: obtaining an event status identifier in the system operation status of the clothes dryer; if a user operation command is collected and the event status identifier is "started", determining whether the drying event termination condition is met based on the user operation data and clothes dryer status data; if the user operation command is collected and the event status identifier is "not started", updating the event status identifier to "started", recording the operation timestamp corresponding to the user operation command as the start timestamp of the current drying event, and classifying the user operation command as the currently started drying event.

[0100] In one embodiment, the event end determination module 203 is used to determine the current drying event is over if any of the drying event end conditions are met, and to start a correction window. Specifically, it includes: if any of the drying event end conditions are met, recording the operation timestamp corresponding to the current user operation instruction as the end timestamp of the current drying event; clearing the operation sequence cache and updating the event status identifier in the system running status of the clothes dryer to not started; starting a misjudgment correction timer with a duration of a preset time threshold to start the correction window.

[0101] In one embodiment, the correction module 204 is configured to, if a new user operation command is detected again within the correction window, cancel the current drying event termination determination and incorporate the operation corresponding to the new user operation command into the current drying event. Specifically, this includes: if a new user operation command is detected again within the correction window, canceling the termination determination of the current drying event and assigning the new user operation command and its corresponding operation to the current drying event; obtaining and updating the termination timestamp of the current drying event based on the operation timestamp corresponding to the new user operation command; and resetting the misjudgment correction timer.

[0102] The aforementioned drying behavior recognition device can implement the drying behavior recognition method of the above method embodiments. The options in the above method embodiments are also applicable to this embodiment, and will not be detailed here.

[0103] Therefore, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the drying behavior recognition method provided in any of the foregoing method embodiments.

[0104] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.

[0105] 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 application.

[0106] In the several embodiments provided in this application, 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.

[0107] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application 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.

[0108] 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 this application, 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 a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0109] 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.

[0110] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Since these modifications and variations fall within the scope of the claims and their equivalents, this application also intends to include these modifications and variations.

[0111] The above description is merely a specific embodiment of this application, but the scope of protection of this application 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 this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for recognizing drying behavior, characterized in that, include: Real-time collection of user operation data and clothes drying rack status data; Based on user operation data and clothes drying rack status data, determine whether the drying event end conditions are met. The drying event end conditions include a first dynamic threshold judgment condition based on the operation interval, a second dynamic threshold judgment condition based on the position of the clothes drying rack rod, or a matching judgment condition based on the preset drying completion operation sequence features. If any of the aforementioned conditions for the end of a drying event are met, the current drying event is determined to have ended, and a correction window is initiated. If a new user operation command is detected again within the correction window, the current drying event termination determination is revoked, and the operation corresponding to the new user operation command is incorporated into the current drying event.

2. The method as described in claim 1, characterized in that, The first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying events; The first dynamic threshold and the second dynamic threshold are periodically updated based on the user's historical drying data, specifically including: Within the preset update cycle, the operation interval and the duration of time spent in the storage location are statistically analyzed in historical drying events; Calculate the first and second updated dynamic thresholds based on the statistical results; Determine whether the first updated dynamic threshold and the second updated dynamic threshold fall within their respective preset boundary ranges. If so, use the first updated dynamic threshold and the second updated dynamic threshold as the updated first dynamic threshold and the second dynamic threshold. Otherwise, select the boundary value of the preset boundary range corresponding to the first updated dynamic threshold and the second updated dynamic threshold as the updated first dynamic threshold and the second dynamic threshold.

3. The method as described in claim 1, characterized in that, Before the real-time collection of user operation data and clothes drying rack status data, the following is also included: Initialize the system operating status of the clothes drying rack, wherein the system operating status includes at least the cumulative count of the silent timer, the current position of the clothes drying rack, the duration of stay at the current position, and the preset storage position of the clothes drying rack.

4. The method as described in claim 3, characterized in that, The real-time collection of user operation data and clothes drying rack status data specifically includes: The system detects user operation commands in real time. If no user operation command is detected, the system starts the silent timer to process the time until the user operation command is detected. The system records the first cumulative count of the silent timer and resets the silent timer. The system updates the cumulative count of the silent timer based on the first cumulative count. Obtain user operation data and clothes dryer status data corresponding to the user operation command, wherein the user operation data includes an operation timestamp, and the clothes dryer status data includes the first position of the clothes dryer rod and the duration of stay at the first position; The current position of the clothes drying rack is updated based on the first position, and the dwell time at the current position is updated based on the dwell time at the first position; The user operation command, the operation timestamp, and the first location are associated to form operation data, and the operation data is stored in the operation sequence cache of the clothes drying machine.

5. The method as described in claim 4, characterized in that, The first dynamic threshold judgment condition based on the operation interval includes that the current position is not the preset storage position of the clothes drying rack, and the cumulative count of the silent timer is not less than the first dynamic threshold. The second dynamic threshold judgment condition based on the position of the clothes drying rack includes that the current position is the storage position, and the duration of the current position is not less than the second dynamic threshold. The matching judgment conditions based on the preset drying completion operation sequence features include the current position being the storage position, and the operation sequence formed by the operation data cached in the operation sequence cache matching at least one drying completion operation sequence feature in the pre-stored operation feature library.

6. The method as described in claim 1, characterized in that, Before determining whether the conditions for ending the drying event are met based on user operation data and clothes drying rack status data, the process also includes: Obtain the event status identifiers from the system operating status of the clothes drying rack; If a user operation command is collected and the event status is marked as started, determine whether the conditions for ending the drying event are met based on the user operation data and the clothes drying machine status data. If the user operation command is collected and the event status identifier is not started, then the event status identifier is updated to started, the operation timestamp corresponding to the user operation command is recorded as the start timestamp of the current drying event, and the user operation command is assigned to the currently started drying event.

7. The method as described in claim 1, characterized in that, If any of the aforementioned conditions for ending the drying event are met, the current drying event is determined to have ended, and a correction window is initiated, specifically including: If any of the conditions for ending the drying event are met, the timestamp of the operation corresponding to the current user operation instruction is recorded as the timestamp of the end of the current drying event. Clear the operation sequence cache of the clothes drying rack and update the event status flag in the system running status of the clothes drying rack to "not started"; Start a misjudgment correction timer with a preset time threshold duration to initiate the correction window.

8. The method as described in claim 7, characterized in that, If a new user operation command is detected again within the correction window, the current drying event termination determination is revoked, and the operation corresponding to the new user operation command is incorporated into the current drying event. Specifically, this includes: If a new user operation command is detected again within the correction window, the termination determination of the current drying event is cancelled, and the new user operation command and its corresponding operation are assigned to the current drying event. Obtain and update the end timestamp of the current drying event based on the operation timestamp corresponding to the new user's operation instruction; Reset the misjudgment correction timer.

9. A device for recognizing drying behavior, characterized in that, include: Data acquisition module, event termination judgment module, event termination determination module, and correction module; The data acquisition module is used to collect user operation data and clothes drying machine status data in real time. The event end judgment module is used to determine whether the drying event end conditions are met based on user operation data and clothes drying rack status data. The drying event end conditions include a first dynamic threshold judgment condition based on the operation interval, a second dynamic threshold judgment condition based on the position of the clothes drying rack rod, or a matching judgment condition based on the preset drying completion operation sequence features. The event end determination module is used to determine the current drying event is over if any of the drying event end conditions are met, and to start the correction window. The correction module is configured to, if a new user operation command is detected again within the correction window, cancel the current drying event termination determination and incorporate the operation corresponding to the new user operation command into the current drying event.

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 method as described in any one of claims 1-8.

Images