Method, device and equipment for determining user event state and storage medium
By acquiring the air conditioner's running time and correcting the sleep start time, the problem of high misjudgment rate and insufficient real-time performance in judging the sleep state of electrical appliances is solved, achieving more accurate determination of user event status and intelligent control.
Patent Information
- Application Number
- CN202411261335.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2026-03-17
AI Technical Summary
Existing technologies for determining the user event status of electrical equipment, especially the sleep state, suffer from high misjudgment rates and insufficient real-time performance, affecting the accuracy of intelligent control.
By obtaining the continuous operating time of the air conditioner over a past cycle, the sleep start time is determined, and then corrected based on the current relative time. The sleep time zone is redefined, and combined with the air conditioner's operating characteristics, the current real-time clock is inferred, thereby improving the accuracy of sleep event state determination.
This improves the accuracy of sleep event status determination, thereby enhancing the accuracy of intelligent device control and ensuring the intelligent regulation function of electrical appliances such as air conditioners.
Smart Images

Figure CN121680133A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of smart home technology, such as methods, apparatus, devices, and storage media for determining user event states. Background Technology
[0002] With the development of artificial intelligence (AI) technology, many electrical appliances can be intelligently controlled, such as air conditioner sleep monitoring and refrigerator recipe recommendations. The intelligent control of these appliances is based on the user event status in the application scenario. User events can be divided into multiple categories, such as sleep, work, study, entertainment, dining, and exercise. The following example uses sleep.
[0003] Sleep is a highly regular biological activity. For example, people everywhere typically fall asleep between 8 PM and midnight, according to local time, and sleep for about 6 to 10 hours, waking up between 5 AM and 9 AM the next morning. Currently, time is not considered in the judgment process; using the same criteria for non-sleep-onset periods as for typical sleep-onset periods can easily lead to misjudgments. Furthermore, related sleep reports use retrospective algorithms, meaning that after collecting a large amount of data, the analysis results are obtained by retrospectively analyzing N (e.g., 7) hours of historical data to determine whether a sleep event occurred, sleep stage, etc. Medical instruments, such as polysomnography (PSG), and common devices such as wristbands and sleep belts, all acquire long-term retrospective data, which is then analyzed by machine algorithms or by physicians based on experience.
[0004] However, for scenarios requiring real-time determination of sleep onset and wakefulness, and sleep stages, such as functions controlling air conditioning temperature and airflow, the determination results need to be obtained as quickly as possible with low latency. Specifically, this could involve automatically turning off the air conditioning after determining the user is awake and has left; switching to sleep mode when the user wants to rest; and automatically adjusting the temperature during the user's sleep. In these cases, the aforementioned a posteriori algorithms are ineffective due to insufficient real-time performance; while related real-time algorithms, making judgments with limited data, suffer from high misjudgment rates and lack practicality.
[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention
[0006] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.
[0007] This disclosure provides a method, apparatus, system, and storage medium for determining user event states, in order to address the technical problem that the accuracy of user event state determination during electrical equipment control needs to be improved.
[0008] In some embodiments, the method includes:
[0009] Get the current continuous running time of the air conditioner within the past period;
[0010] If the current continuous running time is greater than the first set running time, determine the current relative time corresponding to the start time of the current continuous running time within the current cycle time period, starting from the recorded sleep start time;
[0011] Based on the current relative time, the sleep start time is corrected, and the corrected time is recorded as the current sleep start time. The sleep time range corresponding to the user's sleep event is then determined based on the current sleep start time.
[0012] In some embodiments, it also includes:
[0013] If the sleep start time is not recorded, and the current continuous running time is longer than the set running time, the start time of the current continuous running time will be recorded as the sleep start time and determined as the start point of each cycle time period.
[0014] In some embodiments, the correction of the sleep onset time includes:
[0015] Obtain the current relative time difference between the current relative time and the sleep initiation time;
[0016] If the absolute value of the current relative time difference is less than or equal to the first duration and is greater than zero, the sleep start time is moved by a set movement value according to the movement direction matched by the current relative time difference, and the current sleep start time is obtained and determined as the starting point of each cycle time period.
[0017] If the absolute value of the current relative time difference is greater than the first duration, obtain the first running duration of the air conditioner within the set time period in the current cycle. If the first running duration meets the set conditions, determine the start time of the current continuous running time as the current sleep start time and determine it as the start point of each cycle period.
[0018] In some embodiments, obtaining the first operating time of the air conditioner within a set time period in the current cycle includes:
[0019] Based on the start time of sleep, determine the nighttime period and obtain the continuous nighttime running time of the air conditioner during the nighttime period;
[0020] Get the cumulative running time of the air conditioner within the second time period starting from the starting point in the current cycle.
[0021] In some embodiments, determining the start time of the current continuous runtime as the current sleep start time includes:
[0022] If the continuous running time at night is less than or equal to the first set duration, and the cumulative running time is less than or equal to the first set duration, the start time of the current continuous running time will be determined as the current sleep start time.
[0023] In some embodiments, determining the start time of the current continuous runtime as the current sleep start time includes:
[0024] If the current continuous running time exceeds the first set running time, update the current occurrence count recorded.
[0025] Based on the current number of occurrences, the current frequency of occurrence within the statistical time period is obtained, where the statistical time period is longer than the periodic time period;
[0026] If the current occurrence frequency is greater than the set frequency value, the start time of the current continuous running time will be determined as the current sleep start time.
[0027] In some embodiments, it also includes:
[0028] Based on the sleep time zone and the air conditioner's operating status, determine the user event status. User events include one or more of the following: events at home, events away from home, and the usual time for air conditioner use.
[0029] In some embodiments, the apparatus for determining user event states includes a processor and a memory storing program instructions, the processor being configured to execute the above-described method for determining user event states when executing the program instructions.
[0030] In some embodiments, the device.
[0031] In some embodiments, the storage medium stores program instructions that, when executed, perform the method described above for determining user event states.
[0032] The method, apparatus, and system for determining user event status provided in this disclosure can achieve the following technical effects:
[0033] Based on the characteristics of air conditioner operation during user sleep, the sleep start time is determined. Furthermore, within each cycle time period, taking the recorded sleep start time as the starting point, the current relative time corresponding to the start time of the continuous operation time that satisfies the characteristics of air conditioner operation during user sleep is determined. Based on the previous relative time, the current sleep start time is estimated, and the sleep time region and non-sleep time region are re-divided. In this way, the current real-time clock (RTC) can be inferred, and the accuracy of sleep event state determination can be improved, thereby improving the accuracy of intelligent control of the device.
[0034] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description
[0035] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:
[0036] Figure 1 This is a schematic diagram of a smart home architecture provided in an embodiment of this disclosure;
[0037] Figure 2 This is a flowchart illustrating a method for determining the state of a user event provided in an embodiment of this disclosure;
[0038] Figure 3 This is a flowchart illustrating a method for determining the state of a user event provided in an embodiment of this disclosure;
[0039] Figure 4 This is a schematic diagram of a device for determining the state of a user event provided in an embodiment of this disclosure;
[0040] Figure 5 This is a schematic diagram of a device for determining the state of a user event provided in an embodiment of this disclosure;
[0041] Figure 6 This is a schematic diagram of a device for determining the state of a user event provided in an embodiment of this disclosure;
[0042] Figure 7 This is a schematic diagram of a device provided in an embodiment of this disclosure. Detailed Implementation
[0043] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.
[0044] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.
[0045] Unless otherwise stated, the term "multiple" means two or more.
[0046] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.
[0047] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.
[0048] Figure 1 This is a schematic diagram of a smart home architecture provided in an embodiment of this disclosure. Figure 1 As shown, a smart home may include: a backend server, an edge gateway, and multiple smart devices, such as: air conditioners, televisions, washing machines, robot vacuum cleaners, smart windows, smart curtains, smart speakers, etc.
[0049] The edge gateway can communicate with each home appliance and connect to the backend server network. In this way, it can comprehensively utilize IoT, cloud computing, mobile internet and big data technologies, combined with automatic control technology, to effectively combine home appliance intelligent control, home environment perception, family health perception, home security perception, information exchange and consumer services, creating a healthy, safe, comfortable, low-carbon and convenient personalized home life.
[0050] Of course, in some embodiments, the architecture of a smart home may include a backend server and multiple smart devices. One or more of these smart devices have strong computing power and can communicate with the backend server and other smart home appliances. This comprehensively utilizes IoT, cloud computing, mobile internet, and big data technologies, combined with automatic control technologies, to achieve a smart home lifestyle. Specific examples will not be listed here.
[0051] In a smart home, some smart devices may choose not to connect to the internet, or their connection may be faulty. This ensures data processing locally while maximizing user privacy. However, some smart devices still require intelligent control based on user event states within their application scenario. For example, an air conditioner needs to control its airflow and temperature based on the user's sleep state. The sleep time zone corresponding to the user's sleep event may require clock information. However, without internet connectivity, the air conditioner may lack accurate clock information, resulting in inaccurate determination of the sleep time zone and consequently, less accurate and intelligent control of the air conditioner's airflow and temperature.
[0052] Therefore, in this embodiment, a periodic time can be preset, such as 24 hours, 12 hours, or 48 hours, etc., and this periodic time can be evenly divided into n consecutive sampling segments. Based on the continuous running time of the air conditioner obtained at the sampling point time corresponding to each sampling segment, the sleep start time is determined. Then, the current relative time corresponding to the start time of the continuous running time that meets the characteristics of air conditioner operation during the user's sleep period is recorded within the current periodic time starting from the sleep start time. The sleep start time is determined, and the sleep time area and non-sleep time area are re-divided. In this way, the current real-time clock (RTC) can be inferred, and the accuracy of sleep event state determination can be improved, thereby improving the accuracy of intelligent control of the device.
[0053] Figure 2 This is a flowchart illustrating a method for determining the state of a user event, provided in an embodiment of this disclosure. Based on Figure 1 and Figure 2 The process of determining the user event status, using an air conditioner, or other smart devices that can be connected to the air conditioner, or a backend server that can be connected to the air conditioner, includes:
[0054] Step 201: Obtain the current continuous running time of the air conditioner within the past period.
[0055] Different application scenarios and user events may correspond to different time periods. For example, a user's sleep event may have a time period of 24 hours, 12 hours, etc., while a user's work event may have a time period of 7 days, 30 days, etc. The time period can be evenly divided into n consecutive sampling segments, where n is an integer greater than or equal to 1. In this way, the start time of each sampling segment can be determined as the current sampling point, allowing us to obtain the current continuous running time of the air conditioner within the past time period ending at that moment.
[0056] For example: the cycle time can be 24 hours, divided into 24 segments, starting from T0. Each hourly interval is represented by T1, T2, etc. Every 24 hours (when T=24), T24 is reset to T0, and the day variable (Day) is incremented by one. Alternatively, the cycle time can be 7 days, divided into 7 segments, starting from T0. Each dayly interval is represented by T1, T2, etc. Every 7 days (when T=7), T7 is reset to T0, and the week variable (Day) is incremented by one.
[0057] Therefore, upon arrival at the sampling point, the device, such as an air conditioner, smart speaker, or backend server, can query whether the air conditioner has been turned on within a past period. If it is confirmed that the air conditioner has been turned on, the current continuous running time of the air conditioner within the past period can be queried.
[0058] For example, if the device finds that the air conditioner was turned on twice in the past period, once for 2 hours and once for 3 hours, then the current continuous running time can be 3 hours. In other words, the longest continuous running time in the past period is determined as the current continuous running time.
[0059] Step 202: If the current continuous running time is greater than the first set running time, determine the current relative time corresponding to the start time of the current continuous running time within the current cycle time period starting from the recorded sleep start time.
[0060] Sleep is a highly regular biological activity. For example, people everywhere fall asleep between 8 PM and midnight according to local time, with a sleep duration of about 6 to 10 hours, and wake up between 5 AM and 9 AM the next morning. Therefore, if an air conditioner runs continuously for more than 5 hours, it usually coincides with a user's sleep period. Once the user's sleep period is determined, the air conditioner can perform sleep control, including: sleep state monitoring, real-time sleep staging, and adjusting temperature and airflow, etc. Therefore, the initial set operating time can be 5 hours, 5.5 hours, or 6 hours, depending on the user's physiological characteristics, the corresponding season, etc.
[0061] Suppose a user turns on the air conditioner at a set time, and the air conditioner runs for 2 hours without adjusting the temperature. Since the current continuous running time is less than or equal to 5 hours, which is less than the first set running time, the user's sleep time range cannot be inferred. However, in some embodiments, if the number of times the user repeatedly triggers (close to the time of the last action) within a unit time period (on a day) meets a set threshold condition, the user's current event state is determined. This user event can be recorded as an action taken before the user "sleeps," and used to iteratively determine the possible time of user event A, such as possibly running the air conditioner for two hours before sleeping. In this case, the air conditioner does not perform real-time sleep control.
[0062] Alternatively, the user might turn on the air conditioner before going to sleep at night (e.g., turning it on at 8 PM and falling asleep at 10 PM; "before going to sleep" does not mean immediately turning off the lights and going to bed), set it to run for 2 hours, and then have it automatically turn off. The user might then turn the air conditioner back on during the night and manually turn it off three hours later. The time interval between these two air conditioner runs is 4 hours. However, the obtained continuous running time is less than or equal to the first set running time, so it is not considered a user sleep event. Therefore, the above user actions could also be: "the user sets the air conditioner to run for 2 hours at 9 AM, then the air conditioner automatically turns off," and "the user turns the air conditioner back on at 2 PM, and manually turns it off three hours later," with the final shutdown time being 5 PM. Therefore, it is not possible to uniquely determine that the user was sleeping at night. In other words, if there is no record of continuous air conditioner operation for more than 5 hours in the past 24 hours, a user sleep event cannot be determined.
[0063] If the current continuous running time exceeds the first set running time, the status of the user's sleep event or sleep event can be determined. At this point, the start time of the current continuous running time can be determined as the sleep start time Ton0. If a sleep start time Ton has already been recorded within the current period corresponding to the current time, meaning the start time T0 of the current period is already a recorded sleep start time, and Ton = T0, then the relative time corresponding to Ton0 can be determined using T0 as a reference point. This gives the current relative time between the start time of the current continuous running time and the recorded sleep start time.
[0064] For example, if the recorded sleep start time is 10 PM, which corresponds to T0 of the current cycle time period, the start time of the current continuous running time may be 12 AM, which corresponds to T2; or it may be 9 PM, which corresponds to T23; or it may be 10 AM, which corresponds to T12, and so on.
[0065] In some embodiments, if the sleep start time is not recorded within the current periodic time corresponding to the current time, i.e., the sleep start time is not locked, then if the current continuous running time is greater than 5 hours or 7 hours, i.e., the current continuous running time is greater than the first set running time, then Ton0 can be recorded as the sleep start time Ton within each periodic time, and it will be determined as the starting point of each periodic time, i.e., Ton = T0. In this way, if the current continuous running time is greater than the set running time when the sleep start time is not recorded, the start time of the current continuous running time will be recorded as the sleep start time and determined as the starting point of each periodic time.
[0066] Step 203: Correct the sleep start time based on the current relative time, record the corrected time as the current sleep start time, and determine the sleep time range corresponding to the user's sleep event based on the current sleep start time.
[0067] The current relative time obtained may be T0, T1, T3, T8, T10, T20, or T23, etc. The current relative time difference between the current relative time and the sleep start time can be obtained, and the sleep start time can be corrected based on the current relative time difference. The corrected time is then recorded as the current sleep start time.
[0068] For example: if the current relative time is T0, then the current relative time difference ΔT between the current relative time and the sleep start time is 0; if the current relative time is T3, then the current relative time difference ΔT between the current relative time and the sleep start time is 3-0=3; if the current relative time is T20, then the current relative time difference ΔT between the current relative time and the sleep start time is 20-0(24)=-4; if the current relative time is T23, then the current relative time difference ΔT between the current relative time and the sleep start time is 23-0(24)=-1. Here, if Ti, if i is greater than a certain set value, such as 12, 16, or 20, then T0 can be T24.
[0069] In some embodiments, when the absolute value of the current relative time difference is less than or equal to the first duration and is greater than zero, the sleep start time is moved by a set movement value according to the movement direction matched by the current relative time difference to obtain the current sleep start time, and is determined as the starting point of each cycle time period; when the absolute value of the current relative time difference is greater than the first duration, the first running time of the air conditioner within a set time period in the current cycle time period is obtained, and if the first running time meets the set conditions, the start time of the current continuous running time is determined as the current sleep start time, and is determined as the starting point of each cycle time period.
[0070] For example, Ton might be 10 PM, the period is 24 hours, sampling is performed every hour, and the first duration can be 2 or 3. The shift value can be set to 1 hour or 2 hours. The current sleep start time is recorded in the current period, which locks Ton, corresponding to T0 of the current period. The current relative time is determined to be T2, i.e., ΔT = 2. Since |ΔT| is less than or equal to the first duration, and ΔT > 0, it can be shifted by 1 hour in the direction of time growth, i.e., Ton = T1. The obtained current sleep start time Ton is determined as the starting point of each period.
[0071] If the current relative time is determined to be T23, i.e. ΔT = -1, since |ΔT| is less than or equal to the first duration, and ΔT < 0, then we can move 1 hour in the direction of decreasing time, i.e., Ton = T23, and determine the current sleep start time Ton as the starting point of each cycle time period.
[0072] Of course, if |ΔT| = 0, then there is no need to correct the recorded sleep start time.
[0073] If the determined current relative time is T10, i.e., ΔT = 10, since |ΔT| is greater than the first duration, it is necessary to further determine the current sleep start time based on the air conditioner's operating status. In some embodiments, obtaining the first operating time of the air conditioner within a set time period in the current cycle includes: determining the nighttime period based on the sleep start time, and obtaining the continuous nighttime operating time of the air conditioner during the nighttime period; obtaining the cumulative operating time of the air conditioner within a second duration starting from the beginning of the current cycle. Thus, if the continuous nighttime operating time is less than or equal to the first set duration, and the cumulative operating time is less than or equal to the first set duration, the sleep start time can be corrected, and the start time of the current continuous operating time can be determined as the current sleep start time.
[0074] If the sleep start time (Ton) is 10 PM, then the period from 10 PM to 10 PM generally falls under the nighttime range. Therefore, the continuous nighttime operation time of the air conditioner during this period can be obtained. If the second duration is 10 hours, then the cumulative operation time of the air conditioner within the 10 hours starting from Ton can be obtained. If the continuous nighttime operation time exceeds the first set duration, or the cumulative operation time exceeds the first set duration, then no correction is needed to the recorded sleep start time.
[0075] For example: Given a fixed Ton, if the sleep start time is recorded and Ton = T0, and the air conditioner is turned on and runs continuously for more than 5 hours during the daytime (excluding nighttime), then during the nighttime, the air conditioner's continuous running time (i.e., the nighttime continuous running time) is greater than 5 hours, or the cumulative running time within 10 hours after Ton (i.e., the cumulative running time) is greater than 5 hours, then "the air conditioner is turned on and runs continuously for more than 5 hours during the daytime" will not affect the correction of Ton. Otherwise, Ton may be corrected, and thus, a correction may occur.
[0076] Subsequently, if the condition "air conditioning is turned on and runs continuously for more than 5 hours during the day" occurs multiple times, but is accompanied by "the air conditioning runs continuously for more than 5 hours during the night or during the 10 hours of intermittent operation after Ton", then Ton will not be corrected. However, if the condition "air conditioning is turned on and runs continuously for more than 5 hours during the day" occurs multiple times, but "the air conditioning runs continuously for more than 5 hours at night does not meet the above conditions", then when the cumulative time reaches the correction judgment condition (e.g., three out of five days), Ton will be corrected. The start time of Ton is the air conditioning start time in the condition "air conditioning is turned on and runs continuously for more than 5 hours during the day", that is, the start time of the current continuous running time is determined as the current sleep start time, and is also determined as the start point of each cycle time period. Therefore, in some embodiments, determining the start time of the current continuous running time as the current sleep start time includes: updating the recorded current occurrence count when the current continuous running time is greater than a first set running time; obtaining the current occurrence frequency within the statistical time period based on the current occurrence count, wherein the statistical time period is greater than the cycle time period; and determining the start time of the current continuous running time as the current sleep start time when the current occurrence frequency is greater than a set frequency value.
[0077] In this way, once devices such as air conditioners, smart speakers, or backend servers record the current sleep start time, the corresponding sleep time range for the user's sleep event can be determined based on the current sleep start time. For example, within each 24-hour period starting from Ton, T0-T12 can be defined as the sleep time range, allowing the air conditioner to perform intelligent sleep control.
[0078] As can be seen, in this embodiment of the present disclosure, the sleep start time is determined based on the characteristics of the air conditioner's operation during the user's sleep. Furthermore, the sleep start time is corrected based on the current relative time corresponding to the start time of the continuous operation time that satisfies the characteristics of the air conditioner's operation during the user's sleep within each cycle time period, thereby determining the current sleep start time and re-dividing the sleep time region and the non-sleep time region. In this way, the current real-time clock (RTC) can be inferred, and the accuracy of sleep event state determination can be improved, thereby improving the accuracy of intelligent control of the device.
[0079] Of course, there can be various user events, including one or more of the following: events at home, events away from home, and the usual time for air conditioning use. Therefore, in some embodiments, the user event status can be determined based on the sleep time zone and the operating status of the air conditioner. The user events include one or more of the following: events at home, events away from home, and the usual time for air conditioning use.
[0080] For example, if the defined sleep time range is T0-T12, and the air conditioner is not running during the non-sleep time range (T13-T0), it can be inferred that the user is away from home. If the air conditioner is not running for more than 4 hours during T13-T0, and this occurs for 5 or 6 consecutive days out of every 7 days, then weekdays and non-weekdays within that 7-day cycle can be inferred. Of course, based on the sleep time range (T0-T12), the air conditioner's operating mode, target temperature, etc., it's possible to determine the user's season and air conditioner usage habits, etc., which will not be listed here.
[0081] Therefore, based on the estimated current sleep start time, one, two, or more user event states can be determined, improving the accuracy of user event state determination and thus improving the accuracy of device intelligent control.
[0082] Of course, in some embodiments, the current RTC can be obtained through other networked devices in the smart home, or, in the case of recording the sleep start time for the first time, the RTC corresponding to the sleep start time can be determined through networked devices, thereby increasing the success rate and accuracy of inferring the RTC corresponding to the current sleep start time.
[0083] The following describes the operation process in a specific embodiment, illustrating the user event status determination process provided by the embodiments of the present invention.
[0084] In one embodiment of this disclosure, Figure 1 In the smart home shown, the air conditioner can determine the status of user events. The cycle time period is 24 hours, the first set running time can be 5 hours, the first duration can be 3 hours, the second duration can be 10 hours, and the set movement value can be 1 hour.
[0085] Figure 3 This is a flowchart illustrating a method for determining the state of a user event, provided in an embodiment of this disclosure. Based on Figure 3 The process of determining the state of a user event includes:
[0086] Step 301: The air conditioner obtains the current continuous running time of the air conditioner in the past 24 hours.
[0087] The period is 24 hours, which can be divided into 24 consecutive sampling segments. That is, every hour, the current continuous running time of the air conditioner in the past 24 hours is obtained. At this time, if the air conditioner has run in the past 24 hours with the current time as the endpoint, the continuous running time of the air conditioner is obtained. If there are multiple running processes, the air conditioner can determine the longest continuous running time as the current continuous running time.
[0088] Step 302: Determine if the current continuous running time is greater than 5 hours? If yes, proceed to step 303; otherwise, return to step 301.
[0089] Step 303: Determine if the sleep start time has been recorded? If not, proceed to step 304; otherwise, proceed to step 305.
[0090] Step 304: The air conditioner records the start time of the current continuous running time as the sleep start time Ton, and determines Ton as the start time T0 of each cycle time period. Then proceed to step 314.
[0091] Step 305: The air conditioner determines the current relative time Tn corresponding to the start time of the current continuous running time within the current cycle time period, starting from the recorded sleep start time.
[0092] Where n = 0, 1, ..., 23.
[0093] Step 306: The air conditioner obtains the current relative time difference ΔT between the current relative time Tn and the sleep start time T0.
[0094] Where ΔT = Tn - T0(T24). -12 ≤ ΔT ≤ 12, or -10 ≤ ΔT ≤ 14, etc.
[0095] Step 307: Determine if |ΔT| is equal to zero. If yes, return to step 301; otherwise, proceed to step 308.
[0096] Step 308: Determine if |ΔT|>3 is true. If not, proceed to step 309; if yes, proceed to step 310.
[0097] Step 309: The air conditioner moves the sleep start time by a set value according to the current relative time difference and the moving direction, thus obtaining the current sleep start time and determining it as the starting point for each cycle time period. Proceed to step 314.
[0098] If ΔT > 0, then shift by 1 hour in the direction of time increase, i.e., Ton = T1, and determine the current sleep start time Ton as the starting point of each cycle period. If ΔT < 0, then shift by 1 hour in the direction of time decrease, i.e., Ton = T23, and determine the current sleep start time Ton as the starting point of each cycle period.
[0099] Step 310: The air conditioner determines the nighttime period based on the recorded sleep start time, and obtains the continuous nighttime running time Ty of the air conditioner during the nighttime period, as well as the cumulative running time Tl of the air conditioner within 10 hours from the starting point Ton in the current cycle period.
[0100] Step 311: Determine if Ty > 5 is true. If yes, return to step 301; otherwise, proceed to step 312.
[0101] Step 312: Determine if Tl>5 is true. If yes, return to step 301; otherwise, proceed to step 313.
[0102] Step 313: The air conditioner determines the start time of the current continuous running time as the current sleep start time, and also determines it as the start time of each cycle time period. Proceed to step 314.
[0103] Currently, the air conditioner can also update the recorded number of occurrences; based on the number of occurrences, the current occurrence frequency within 5 days is obtained. If the current occurrence frequency is greater than the set frequency value (35%, 40%, or 50%), the start time of the current continuous running time is determined as the current sleep start time.
[0104] Step 314: The air conditioner determines the sleep time zone corresponding to the user's sleep event based on the current sleep start time and performs corresponding intelligent sleep control.
[0105] As can be seen, in this embodiment, the current continuous running time of the 24-hour air conditioner is obtained. If the current continuous running time is greater than 5 hours, the current relative time corresponding to the start time of the current continuous running time within the current period of time starting from the recorded sleep start time is determined. The sleep start time is then corrected to determine the current sleep start time, and the sleep time region and non-sleep time region are re-divided. In this way, the current real-time clock (RTC) can be inferred, and the accuracy of sleep event status determination can be improved, thereby improving the accuracy of intelligent control of the device.
[0106] Combination Figure 4 This disclosure provides an apparatus 400 for determining the state of a user event, which can be applied to smart devices in a smart home, such as air conditioners, televisions, smart speakers, or backend servers, etc., and includes: an acquisition module 410, a relative determination module 420, and a correction and estimation module 430.
[0107] The acquisition module 410 is configured to acquire the current continuous running time of the air conditioner within a past period.
[0108] The relative determination module 420 is configured to determine the current relative time corresponding to the start time of the current continuous running time within the current cycle time period, starting from the recorded sleep start time, when the current continuous running time is greater than the first set running time.
[0109] The correction prediction module 430 is configured to correct the sleep start time based on the current relative time, record the corrected time as the current sleep start time, and determine the sleep time range corresponding to the user's sleep event based on the current sleep start time.
[0110] In some embodiments, it also includes:
[0111] The initial determination module is configured to, if the current continuous running time is greater than the set running time and the sleep start time is not recorded, record the start time of the current continuous running time as the sleep start time and determine it as the start point of each cycle time period.
[0112] In some embodiments, the corrected prediction module 430 includes:
[0113] The difference determination unit is configured to obtain the current relative time difference between the current relative time and the sleep start time.
[0114] The first correction unit is configured to, when the absolute value of the current relative time difference is less than or equal to the first duration and greater than zero, move the sleep start time by a set movement value according to the movement direction matched by the current relative time difference, thereby obtaining the current sleep start time and determining it as the starting point of each cycle time period.
[0115] The second correction unit is configured to, when the absolute value of the current relative time difference is greater than the first duration, obtain the first running time of the air conditioner within a set time period in the current cycle time period, and when the first running time meets the set conditions, determine the start time of the current continuous running time as the current sleep start time, and determine it as the start point of each cycle time period.
[0116] In some embodiments, the first correction unit is specifically configured to determine the nighttime period based on the sleep start time and obtain the nighttime continuous running time of the air conditioner during the nighttime period; and obtain the cumulative running time of the air conditioner within a second duration starting from the start point in the current period.
[0117] In some embodiments, the first correction unit is further configured to determine the start time of the current continuous running time as the current sleep start time when the continuous running time at night is less than or equal to a first set duration and the cumulative running time is less than or equal to the first set duration.
[0118] In some embodiments, the first correction unit is further configured to update the recorded current occurrence count when the current continuous running time is greater than a first set running time; obtain the current occurrence frequency within a statistical time period based on the current occurrence count, wherein the statistical time period is greater than the periodic time period; and determine the start time of the current continuous running time as the current sleep start time when the current occurrence frequency is greater than a set frequency value.
[0119] In some embodiments, it also includes:
[0120] The event prediction module is configured to determine the user event status based on the sleep time zone and the air conditioner's operating status. User events include one or more of the following: events at home, events away from home, and the user's habitual air conditioner usage time.
[0121] The process of determining the user event state using the apparatus for determining the user event state is further described below with reference to specific embodiments.
[0122] In one embodiment of this disclosure, the device for determining the user event status can be applied to an air conditioner, wherein the periodic time is 24 hours, the first set running time can be 5 hours, the first duration can be 3 hours, the second duration can be 10 hours, and the set movement value can be 1 hour.
[0123] like Figure 5 As shown, the device 400 for determining the state of a user event may include: an acquisition module 410, a relative determination module 420, a correction estimation module 430, an initial determination module 440, and an event estimation module 450. The correction estimation module 430 may include: a difference determination unit 431, a first correction unit 432, and a second correction unit 433.
[0124] The acquisition module 410 acquires the current continuous running time of the air conditioner over the past 24 hours. If the current continuous running time is greater than 5 hours, and the air conditioner has not recorded a sleep start time, the initial determination module 440 can record the start time of the current continuous running time as the sleep start time Ton, and determine Ton as the starting point T0 of each cycle time period. If the air conditioner has recorded a sleep start time, the relative determination module 420 determines the current relative time Tn corresponding to the start time of the current continuous running time within the current cycle time period starting from the recorded sleep start time.
[0125] Thus, the difference determination unit 431 in the correction prediction module 430 can obtain the current relative time difference ΔT between the current relative time and the sleep start time. When 0 < |ΔT| ≤ 3, the first correction unit 432 can move the sleep start time by a set movement value according to the movement direction matched by the current relative time difference, thereby obtaining the current sleep start time and determining it as the starting point of each cycle time period.
[0126] If ΔT > 0, the first correction unit 432 can move 1 hour in the direction of time increase, i.e., Ton = T1, and determine the current sleep start time Ton as the starting point of each cycle time period. If ΔT < 0, the first correction unit 432 can move 1 hour in the direction of time decrease, i.e., Ton = T23, and determine the current sleep start time Ton as the starting point of each cycle time period.
[0127] Of course, if |ΔT|>3, the second correction unit 433 can determine the nighttime period based on the recorded sleep start time, and obtain the nighttime continuous operation time Ty of the air conditioner during the nighttime period, as well as the cumulative operation time Tl of the air conditioner within 10 hours from the starting point Ton in the current cycle period.
[0128] If Ty≤5 and Tl≤5, the second correction unit 433 can update the recorded current occurrence count; based on the current occurrence count, the current occurrence frequency within 5 days is obtained; if the current occurrence frequency is greater than 40%, the start time of the current continuous running time is determined as the current sleep start time.
[0129] In this way, after determining the current sleep period, the correction and prediction module 430 can determine the sleep time zone corresponding to the user's sleep event based on the current sleep start time, and perform corresponding intelligent sleep control.
[0130] Furthermore, the event prediction module 450 can determine the user event status based on the sleep time zone and the air conditioner's operating status, and then perform corresponding air conditioner control. User events include one or more of the following: events at home, events away from home, and the user's habitual air conditioner usage time.
[0131] As can be seen, in this embodiment, the device for determining user event states acquires the current continuous operating time of the air conditioner over 24 hours. If the current continuous operating time is greater than 5 hours, it determines the current relative time corresponding to the start time of the current continuous operating time within the current period, starting from the recorded sleep start time. It then corrects the sleep start time, determines the current sleep start time, and re-divides the sleep time region and the non-sleep time region. This allows for the estimation of the current real-time clock (RTC) and improves the accuracy of sleep event state determination, thereby enhancing the accuracy of intelligent device control. Furthermore, based on the estimated current sleep start time, it can determine one, two, or more user event states, further improving the accuracy of user event state determination and thus enhancing the accuracy of intelligent air conditioner control.
[0132] Combination Figure 6This disclosure provides an apparatus 600 for determining the state of a user event, including a processor 1000 and a memory 1001, and may further include a communication interface 1002 and a bus 1003. The processor 1000, communication interface 1002, and memory 1001 can communicate with each other via the bus 1003. The communication interface 1002 can be used for information transmission. The processor 1000 can invoke logical instructions stored in the memory 1001 to execute the method for determining the state of a user event as described in the above embodiment.
[0133] Furthermore, the logic instructions in the aforementioned memory 1001 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.
[0134] The memory 1001, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 1000 executes functional applications and data processing by running the program instructions / modules stored in the memory 1001, that is, it implements the method for determining user event states in the above method embodiments.
[0135] The memory 1001 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 1001 may include high-speed random access memory and may also include non-volatile memory.
[0136] This disclosure provides an apparatus for determining the state of a user event, including a processor and a memory storing program instructions, wherein the processor is configured to execute a method for determining the state of a user event when executing the program instructions.
[0137] Combination Figure 7 This disclosure provides a device, which may be an air conditioner, a smart speaker, or a backend server, etc., including: a device body 700, configured with the aforementioned user event state determination device 400 (600). The user event state determination device 400 (600) is installed on the device body. The installation relationship described herein is not limited to placement inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections, or signal transmission connections. Those skilled in the art will understand that the user event state determination device 400 (600) can be adapted to feasible device bodies to achieve other feasible embodiments.
[0138] This disclosure provides a storage medium storing program instructions that, when executed, perform the method described above for determining user event states.
[0139] This disclosure provides a computer program product, which includes a computer program stored on a storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to perform the above-described method for determining user event states.
[0140] The aforementioned storage medium can be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.
[0141] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code; it can also be a transient storage medium.
[0142] The foregoing description and accompanying drawings fully illustrate embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included or replace parts and features of other embodiments. The scope of the embodiments of this disclosure includes the entire scope of the claims and all available equivalents of the claims. While the terms “first,” “second,” etc., may be used in this application to describe elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, a first element may be called a second element without changing the meaning of the description, and similarly, a second element may be called a first element, provided that all occurrences of “first element” are consistently renamed and all occurrences of “second element” are consistently renamed. First and second elements are both elements, but may not be the same element. Moreover, the terminology used in this application is only for describing embodiments and is not intended to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to also include the plural forms. Similarly, the term “and / or” as used herein means including one or more of the associated listed elements and all possible combinations thereof. Additionally, when used herein, the terms “comprise” and its variations “comprises” and / or “comprising” refer to the presence of stated 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 groups thereof. Without further limitations, an element defined by the phrase “comprising an…” does not exclude the presence of additional identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.
[0143] 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, or a combination of computer software and electronic hardware. 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 implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0144] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0145] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
Claims
1. A method for user event state determination, characterized by, The method comprises: acquiring a current continuous running time of the air conditioner in a past cycle time period; in a case where the current continuous running time is greater than a first set running time length, determining a current relative time corresponding to a start time of the current continuous running time in a current cycle time period with a recorded sleep start time as a starting point; correcting the sleep start time according to the current relative time, recording a corrected time as a current sleep start time, and determining a sleep time region corresponding to a user sleep event according to the current sleep start time.
2. The method of claim 1, wherein, The method further comprises: in a case where the sleep start time is not recorded, if the current continuous running time is greater than the set running time length, recording the start time of the current continuous running time as the sleep start time, and determining the sleep start time as a starting point of each cycle time period.
3. The method of claim 1, wherein, The method further comprises: obtaining a current relative time difference between the current relative time and the sleep start time; in a case where an absolute value of the current relative time difference is less than or equal to a first time length and greater than zero, moving the sleep start time by a set moving value according to a moving direction matched with the current relative time difference to obtain the current sleep start time, and determining the current sleep start time as a starting point of each cycle time period; in a case where the absolute value of the current relative time difference is greater than the first time length, acquiring a first running time length of the air conditioner in a set time in the current cycle time period, and in a case where the first running time length meets a set condition, determining the start time of the current continuous running time as the current sleep start time, and determining the current sleep start time as a starting point of each cycle time period.
4. The method of claim 3, wherein, The method further comprises: determining a night time period according to the sleep start time, and acquiring a night continuous running time of the air conditioner in the night time period; acquiring a cumulative running time of the air conditioner in a second time length from the starting point in the current cycle time period.
5. The method of claim 4, wherein, The method further comprises: in a case where the night continuous running time is less than or equal to a first set time length and the cumulative running time is less than or equal to the first set time length, determining the start time of the current continuous running time as the current sleep start time.
6. The method of claim 4, wherein, The method further comprises: in a case where the current continuous running time is greater than the first set running time length, updating a recorded current occurrence number; obtaining a current occurrence frequency in a statistical time period according to the current occurrence number, wherein the statistical time period is greater than the cycle time period; in a case where the current occurrence frequency is greater than a set frequency value, determining the start time of the current continuous running time as the current sleep start time.
7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: determining a user event state according to the sleep time region and a running state of the air conditioner, wherein the user event comprises one or more of the following: an in-home event, an away-from-home event, an air conditioner use habit time, and the like.
8. An apparatus for user event state determination, the apparatus comprising a processor and a memory having stored therein program instructions, the apparatus being characterized by: The processor is configured to execute the program instructions to perform the method for user event state determination according to any one of claims 1-7.
9. An apparatus, comprising: The apparatus comprises: a device body; the apparatus for user event state determination according to claim 8 is installed on the device body.
10. A storage medium storing program instructions, characterized in that, The program instructions, when executed, perform the method for user event state determination according to any one of claims 1-7.