Sucking behavior identification method and device, smoking set and storage medium

Abstract

The invention discloses a smoking behavior identification method and device, a smoking set and a storage medium. The method comprises the following steps: acquiring output information of a smoking set in each unit time, and determining first reference information corresponding to each unit time; based on the first reference information corresponding to each unit time, determining a first identification condition for the output information of each unit time; determining second reference information based on the output information of the plurality of first unit times under the condition that the output information of the plurality of continuous first unit times meets a first identification condition; and based on the second reference information, judging the output information of each unit time after the first unit time according to a second identification condition, and under the condition that the output information of the second unit time meets the second identification condition, determining that an effective smoking behavior of the smoking set is detected. The accuracy of effective suction behavior recognition is improved by judging the rising feature and the falling feature of the output information of each unit time.

Description

Technical Field

[0001] This invention relates to the field of smart smoking device technology, and in particular to a method, device, smoking device, and storage medium for recognizing smoking behavior. Background Technology

[0002] With the increasing popularity of heated tobacco products, more and more of these products are supporting the recognition of users' smoking behavior.

[0003] Currently, the identification of vaping behavior can be achieved through the parameter of the battery cell output duty cycle, for example, by feature recognition of the waveform of the battery cell output duty cycle. In the process of realizing this invention, it was found that the prior art has at least the following technical problems: the identification of vaping behavior based solely on the parameter of the battery cell output duty cycle is too simplistic. Furthermore, due to the uniformity of factors such as the tightness of the cigarette, the airway design of the smoking device, and the amount of energy stored in the heating element, the waveform characteristics of the battery cell output duty cycle are not obvious, resulting in poor accuracy in identifying vaping behavior. Summary of the Invention

[0004] This invention provides a method, device, smoking device, and storage medium for identifying smoking behavior, so as to improve the accuracy of identifying smoking behavior in smoking devices.

[0005] According to one aspect of the present invention, a method for identifying suction behavior is provided, comprising:

[0006] Obtain the output information of the smoking device at each unit of time, and determine the first reference information corresponding to each unit of time;

[0007] Based on the first reference information corresponding to each unit time, the output information of each unit time is determined according to the first identification condition;

[0008] If the output information of multiple consecutive first unit time periods satisfies the first identification condition, the second reference information is determined based on the multiple first unit time periods of output information.

[0009] If the multiple first unit time periods meet the preset triggering conditions, the output information of each unit time period is further judged based on the second reference information to determine the second identification conditions. If the cumulative duration of the multiple first unit time periods is less than the preset duration threshold and the output information of the second unit time period is detected to meet the second identification conditions, it is determined that an effective smoking behavior of the smoking device has been detected.

[0010] Optionally, determining the first reference information corresponding to each unit time includes: for the current unit time, if the output information of the previous unit time does not meet the first identification condition, then determining the first reference information corresponding to the current unit time based on the output information of multiple unit times in the previous historical time period corresponding to the current unit time; if the output information of the previous unit time meets the first identification condition, then determining the first reference information corresponding to the previous unit time as the first reference information corresponding to the current unit time.

[0011] Optionally, determining the first reference information corresponding to the current unit time based on the output information of multiple unit times within the previous historical time period corresponding to the current unit time includes: determining the average of the output information of multiple unit times within the previous historical time period corresponding to the current unit time as the first reference information corresponding to the current unit time.

[0012] Optionally, the first identification condition includes the difference between any output information per unit time and the first reference information corresponding to the unit time being greater than a first preset threshold; and / or, the second identification condition includes the output information per unit time being less than the second reference information.

[0013] Optionally, determining the second reference information based on the plurality of first unit time output information includes: recording the maximum information among the plurality of first unit time output information; determining the second reference information based on the maximum information, wherein the second reference information is less than the maximum information and greater than the first preset threshold.

[0014] Optionally, the method further includes: counting a plurality of consecutive first unit time intervals; if the number of the plurality of consecutive first unit time intervals meets a number threshold, determining that the plurality of first unit time intervals meet the preset triggering condition, and performing a step of determining the output information of each unit time interval after the first unit time interval based on the second reference information to determine the second identification condition.

[0015] Optionally, the method further includes: when the output information in any unit time does not meet the first identification condition, and the difference between the output information in the unit time and the first reference information corresponding to the unit time is less than a second preset threshold, the count of the first unit time is cleared to zero.

[0016] Optionally, the method further includes: determining the cumulative duration corresponding to the plurality of first unit times; and if the cumulative duration is greater than the preset duration threshold, clearing the cumulative duration, the count of the first unit times, and the second reference information to zero respectively.

[0017] Optionally, after acquiring the output information of the smoking device at each unit time, the method further includes: filtering the output information at each unit time to remove noise information from the output information at multiple units time.

[0018] Optionally, the method further includes: counting the detected effective sucking behaviors, and controlling the working state of the smoking device based on the number of effective sucking behaviors.

[0019] According to another aspect of the present invention, a device for identifying suction behavior is provided, comprising:

[0020] The energy acquisition module is used to acquire the output information of the smoking device at each unit of time;

[0021] The determination module is used to determine first reference information corresponding to each unit time, and to determine first identification conditions for the output information of each unit time based on the first reference information. If the output information of multiple consecutive first unit times meets the first identification conditions, second reference information is determined based on the output information of the multiple first unit times. If the multiple first unit times meet a preset trigger condition, the second identification conditions are determined for the output information of each unit time based on the second reference information. If the cumulative duration of the multiple first unit times is less than a preset duration threshold, and the output information of the second unit time is detected to meet the second identification conditions, it is determined that an effective smoking behavior of the smoking device has been detected.

[0022] According to another aspect of the present invention, a smoking device is provided, the smoking device comprising:

[0023] At least one processor; and

[0024] A memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the suction behavior recognition method according to any embodiment of the present invention.

[0026] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for identifying suction behavior as described in any embodiment of the present invention.

[0027] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method for identifying suction behavior as described in any embodiment of the present invention.

[0028] The technical solution of this invention continuously acquires the output information of the smoking device at each unit time during the smoking phase, dynamically determines the first reference information corresponding to each unit time, judges the rising characteristics of the output information and the first reference information at each unit time based on the first identification conditions, and determines the second reference information based on the satisfaction of the rising characteristics. Then, it judges the falling characteristics of the output information at each unit time based on the second identification conditions and the second reference information. When both rising and falling characteristics are detected, a valid smoking behavior is determined. By judging the rising and falling characteristics of the output information at each unit time, the accuracy of valid smoking behavior identification is improved.

[0029] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a flowchart of a method for recognizing suction behavior provided in an embodiment of the present invention;

[0032] Figure 2 This is a schematic diagram of the output energy waveform provided in an embodiment of the present invention;

[0033] Figure 3 This is a partial waveform diagram of the output energy provided in an embodiment of the present invention;

[0034] Figure 4 This is a flowchart of a method for recognizing suction behavior provided in an embodiment of the present invention;

[0035] Figure 5 This is a schematic diagram of the structure of a suction behavior recognition device provided in an embodiment of the present invention;

[0036] Figure 6 This is a schematic diagram of the structure of a smoking device that implements an embodiment of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] Figure 1 This is a flowchart of a method for identifying smoking behavior provided by an embodiment of the present invention. This embodiment can be applied to the situation where smoking behavior is identified based on output information when the smoking device is in operation. The method can be executed by a smoking behavior identification device, which can be implemented in hardware and / or software and can be configured in the smoking device.

[0040] Optionally, the output information of the smoking device includes one or more of the battery output duty cycle and output energy. The control unit in the smoking device drives a heating element to heat the heated non-combustible cigarette. This heating element can be a heating plate or heating wire, or a sensor that generates eddy currents by inducing a changing magnetic field, which then generates heat. The heating element is driven by an output power control module. During the smoking process, the output energy of the smoking device is less affected by the surrounding environment and its own components, exhibiting strong data stability. This avoids interference from factors such as the tightness of the cigarette, the airway design of the smoking device, and the amount of energy stored in the heating element during the smoking behavior detection process, thus improving the accuracy of smoking behavior recognition. During the smoking phase, the output energy changing over time can form an output energy waveform; for example, see [link to example]. Figure 2 , Figure 2 This is a schematic diagram of the output energy waveform provided in an embodiment of the present invention. According to... Figure 2It is known that the sucking behavior causes a relative change in the output energy waveform, forming a distinct peak. In this embodiment, during the sucking phase of the smoking device, the fluctuation characteristics of the output energy of the device are identified in real time to identify effective sucking behavior. The fluctuation characteristics include rising and falling features, which are identified through a first identification condition and a second identification condition, respectively.

[0041] like Figure 1 As shown, the method includes:

[0042] S110. Obtain the output information of the smoking device at each unit time, and determine the first reference information corresponding to each unit time.

[0043] S120. Based on the first reference information corresponding to each unit time, determine the first identification condition for the output information of each unit time.

[0044] S130. If the output information of multiple consecutive first unit time periods satisfies the first identification condition, determine the second reference information based on the multiple first unit time periods of output information.

[0045] S140. When the plurality of first unit time periods meet the preset triggering conditions, the output information of each unit time period is further judged based on the second reference information to determine the second identification conditions. When the cumulative duration of the plurality of first unit time periods is less than the preset duration threshold and the output information of the second unit time period is detected to meet the second identification conditions, it is determined that an effective smoking behavior of the smoking device is detected.

[0046] After the smoking device is started, it enters the inhalation phase, during which the inhalation behavior is detected. Specifically, the smoking device starts in response to the trigger operation of the start button, and the starting process can be completed after a preset time.

[0047] During the vaping detection phase, the operating parameters of the smoking device are acquired in real time, and the output information of the device per unit time is determined based on these parameters. Optionally, the output information per unit time refers to the output energy per unit time. The operating parameters of the smoking device can include the current and voltage of the device during operation. The output energy of the device per unit time is based on the current, voltage, battery output duty cycle, and the duration of the unit time. Optionally, the output energy = current * voltage * battery output duty cycle * duration of the unit time. The duration of the unit time can be 20ms; however, this duration is not limited and can be determined according to the requirements for identifying vaping behavior. The voltage and current per unit time can be the average voltage and average current per unit time, respectively.

[0048] Since the operating parameters of the smoking device include noise information, the output information per unit time also includes noise information. To improve the accuracy of the output information per unit time and reduce the interference of noise information on data energy, the acquired output information per unit time is filtered to remove noise information from multiple unit time output information. Optionally, Kalman filtering is performed on the acquired output information per unit time. Kalman filtering reduces interference information in the filtered output information, providing accurate data for the identification of smoking behavior.

[0049] In this embodiment, a first identification condition is set to identify the rising characteristics of the output information (here, the filtered output information, as referred to below as the output information per unit time) acquired sequentially for each unit time. For each unit time, if the difference between the output information of that unit time and the first reference information of that unit time satisfies the first identification condition, then it is determined that that unit time has a rising characteristic. The first reference information per unit time is used to characterize the output information of the portion of unit time preceding that unit time, providing data reference for determining the rising characteristic of the output information of that unit time.

[0050] The first identification condition includes that the difference between the output information per unit time and the first reference information corresponding to the unit time is greater than a first preset threshold. If the output information of any unit time meets the first identification condition, it indicates that the output information of that unit time has a significant increasing trend relative to the output information of the previous unit time, which conforms to the rising characteristic.

[0051] according to Figure 2 It is known that the output information of the smoking device fluctuates throughout the entire smoking process. Using a single reference information to judge the rising characteristics of the output information over multiple units of time during the entire smoking process can lead to inaccurate identification. In this embodiment, the first reference information for each unit of time is dynamically determined based on the overall trend of the smoking device throughout the entire smoking process. The first reference information for different units of time can be the same or different to improve the accuracy of judging the rising characteristics for each unit of time.

[0052] Optionally, the first reference information for each unit of time can be determined based on the output information of multiple units of time within the previous historical time period corresponding to that unit of time. For example, the average of the output information of multiple units of time within the previous historical time period corresponding to that unit of time can be used as the first reference information for that unit of time.

[0053] For example, the suction phase is time-accumulated, and the accumulated duration is divided into preset time periods. For any unit of time, the time period to which that unit of time belongs is determined, and the first reference information for that unit of time is determined based on the output information of multiple units of time within the preceding time period. For example, taking a unit of time of 20ms as an example, the preset time period can be 1s, and a certain unit of time is located in the 2nd second. Accordingly, the first reference information for that unit of time is determined based on the output information of multiple units of time within the 1st second.

[0054] For example, for any unit time, the output information of multiple unit times within a preset time period between the unit times is determined based on a preset time window to determine the first reference information of the unit time. For example, if the unit time is 20ms, the preset time period can be 1s, and a certain unit time is the m-th unit time. The first reference information of the unit time is determined based on the output information of multiple unit times within a consecutive 1s before the unit time.

[0055] It can be explained that, for the first unit of time in the suction phase, the first reference information for the first unit of time can be the output information of the first unit of time or a preset initial value. Taking the output information as the output energy as an example, the corresponding first reference information for the unit of time can be the average output energy of multiple units of time in the previous historical time period corresponding to that unit of time. Taking the output information as the cell output duty cycle as an example, the corresponding first reference information for the unit of time can be the average cell output duty cycle of multiple units of time in the previous historical time period corresponding to that unit of time.

[0056] Based on the above embodiments, according to Figure 2 It can be seen that as the output information per unit time with an increasing characteristic continues to increase, the output information of multiple units of time in the previous historical time period corresponding to each unit time also increases accordingly. Since the first identification condition is to determine the difference between the output information of each unit time and the first reference information, in order to avoid interference with the determination of the difference due to the increase of the output information of multiple units of time in the previous historical time period corresponding to each unit time, that is, the increase of the first reference information corresponding to each unit time, when the output information of any unit time is detected to meet the first identification condition, the first reference information is maintained in the subsequent unit time and the first reference information corresponding to the subsequent unit time is not updated until the identification of one suction behavior ends.

[0057] Optionally, for the current unit of time, if the output information of the previous unit of time does not meet the first identification condition, then the first reference information corresponding to the current unit of time is determined based on the output information of multiple units of time in the previous historical time period corresponding to the current unit of time; if the output information of the previous unit of time meets the first identification condition, then the first reference information corresponding to the previous unit of time is determined as the first reference information corresponding to the current unit of time.

[0058] For example, for the nth unit time, the first reference information corresponding to the nth unit time is determined based on the output information of multiple unit times in the previous time period. If the difference between the output information and the first reference information in the nth unit time satisfies the first identification condition, the nth unit time is determined to have an increasing characteristic. For the (n+1)th unit time, since the output information of the nth unit time increases, when determining the first reference information corresponding to the (n+1)th unit time based on the output information of multiple unit times in the previous time period, there may be instances where the output information and the first reference information of the (n+1)th unit time do not meet the first identification condition, resulting in a discrepancy between the feature identification result of the (n+1)th unit time and the actual situation. To address this issue, if the output information of the nth unit time satisfies the first identification condition, the first reference information corresponding to the (n+1)th unit time is not updated; instead, the first reference information corresponding to the nth unit time is used as the first reference information corresponding to the (n+1)th unit time.

[0059] See Figure 3 , Figure 3 This is a partial waveform diagram of the output energy provided in an embodiment of the present invention. Figure 3 The solid black line represents the output energy per unit time, and the solid green line represents the first reference information per unit time. Figure 3 If the difference between the output energy and the first reference information in a unit of time is greater than the first preset threshold Qt, the first reference information remains unchanged in subsequent units of time (the continuously unchanged green solid line part).

[0060] It can be explained that, according to Figure 3 It can be seen that the end of the identification of a single suction behavior includes the end of the identification of a valid suction behavior or the end of the identification of an abnormal suction behavior.

[0061] In this embodiment, the accuracy of rising feature recognition is improved by flexibly setting the first reference information corresponding to each unit time. Here, the unit time that meets the first recognition condition can be recorded as the first unit time. Since the suction behavior has a certain duration, there are multiple consecutive unit times that meet the first recognition condition. To avoid occasional abrupt changes in the output information of a small number of unit times interfering with the recognition of the suction behavior, the first unit times that meet the first recognition condition are counted to determine the duration of the rising feature.

[0062] Based on the above embodiments, a preset trigger condition is set to indicate the determination of the second identification condition. The preset trigger condition may be that the number of first unit time intervals meets a quantity threshold. Optionally, multiple consecutive first unit time intervals are counted; if the number of consecutive first unit time intervals meets the quantity threshold, it indicates that the rising characteristic of the output information has lasted for a certain duration, conforming to the continuous rising characteristic of the suction behavior, i.e., the preset trigger condition is met. The output information of each unit time interval after the preset trigger condition is then determined according to the second identification condition to identify the falling characteristic. If the number of consecutive first unit time intervals does not meet the quantity threshold, it indicates that the rising characteristic of the output information has not lasted for a certain duration. The determination of the output information of the next unit time interval continues until the number of first unit time intervals meets the preset trigger condition. The output information of subsequent received unit time intervals is then determined according to the second identification condition.

[0063] During the counting process of the first unit of time, if the output information of any unit of time does not meet the first identification condition, and the difference between the output information of that unit of time and the first reference information corresponding to that unit of time is less than the second preset threshold, then it is determined that the accumulated output information of multiple first unit of time does not belong to valid suction behavior, and the accumulated count of the first unit of time is cleared, that is, the accumulated count of the first unit of time is set to zero. See also Figure 3 , Figure 3 In the equation, Ct represents the duration of the first unit of time that satisfies the quantity threshold. Figure 3 If the duration of multiple first unit time intervals that meet the first identification condition exceeds Ct, that is, if multiple first unit time intervals meet the preset trigger condition, the output information of subsequent unit time intervals is judged according to the second identification condition. In some embodiments, a fallback flag is set. The initial value of the fallback flag can be 0. If the number of multiple first unit time intervals meets the quantity threshold, the fallback flag is set to 1 to indicate that multiple first unit time intervals meet the preset trigger condition.

[0064] When a first unit time that meets the first identification condition is detected, second reference information is generated based on the output information of multiple first unit times. The second reference information is the reference information of the output information fallback stage and is used to determine the second identification condition for the output information of the unit time after the preset trigger condition is met.

[0065] Optionally, determining the second reference information based on the output information of the plurality of first unit time intervals includes: recording the maximum information among the output information of the plurality of first unit time intervals; determining the second reference information based on the maximum information, wherein the second reference information is less than the maximum information and greater than the first preset threshold Qt. For example, the second reference information may be the average or median value of the maximum information and the first preset threshold Qt; or, the second reference information may be determined based on a preset proportion of the maximum information, such as the maximum information * 80%. It is understood that the second reference information differs during the identification process of different suction actions. Taking the output information as output energy as an example, correspondingly, the second reference information is a second reference energy, determined based on the maximum energy among the output energies of the plurality of first unit time intervals.

[0066] Optionally, the second identification condition includes that the output information per unit time is less than the second reference information. The unit time that satisfies the second identification condition is recorded as the second unit time, wherein the second unit time and the first unit time may partially overlap, the first unit time may be distributed before and after the moment when the preset trigger condition is met, and the second unit time is distributed after the moment when the preset trigger condition is met.

[0067] After the preset triggering condition is met, monitoring the second unit time that meets the second identification condition over multiple subsequent unit time intervals indicates that after the output information of multiple first unit time intervals conforms to the rising characteristic, there is a second unit time interval where the output information conforms to the falling characteristic. This further indicates that the output information of multiple unit time intervals conforms to the rising and falling characteristics of effective suction behavior, thus confirming that effective suction behavior has been detected.

[0068] If, within a series of consecutive unit time intervals, the output information of multiple consecutive first unit time intervals satisfies the first identification condition, and at least one second unit time interval's output information satisfies the second identification condition, and the second unit time interval is after the first unit time interval, then a valid suction behavior is determined to be detected. If no fallback feature of the output information is detected after the fallback flag is set to 1, i.e., no second unit time interval satisfies the second identification condition, then an abnormal suction behavior is determined to be detected. Alternatively, if no fallback feature of the output information is detected within a preset time period after the fallback flag is set to 1, then an abnormal suction behavior is determined to be detected.

[0069] Optionally, after detecting that the fallback flag is at position 1 (meeting a preset trigger condition), timing is triggered for the first unit time that meets the first identification condition, and the cumulative duration corresponding to multiple consecutive first unit times is determined; if the cumulative duration is greater than a preset duration threshold and no output information meeting the second identification condition is detected, it is determined that abnormal smoking behavior of the smoking device has been detected. If the cumulative duration is less than the preset duration threshold and output information meeting the second identification condition is detected, it is determined that valid smoking behavior of the smoking device has been detected. For example, see Figure 3 , Figure 3 The cumulative duration T1 corresponding to the first unit time represented by the waveform on the right exceeds the preset duration threshold Tmax, and no output information for the second unit time is detected that meets the second identification condition, thus it is determined to be an abnormal suction behavior. Figure 3 If the cumulative duration T1 corresponding to the first unit time in the waveform on the left does not exceed the preset duration threshold, the output information of the second unit time is detected to meet the second recognition condition, and it is determined to be a valid suction behavior.

[0070] If the output information of the second unit time meets the second identification condition, the detection of the current vaping behavior can be determined to be over. Alternatively, if abnormal vaping behavior of the smoking device is detected, the detection of the current vaping behavior can be determined to be over. Accordingly, when the vaping behavior ends, the first reference information, the second reference information, and the cumulative duration or count of the first unit time are all cleared to avoid interference with the identification process of the next vaping behavior.

[0071] Based on the above embodiments, the method further includes: counting the detected effective sucking behaviors, and controlling the working state of the smoking device based on the number of effective sucking behaviors. When the number of effective sucking behaviors reaches a preset sucking frequency threshold, it indicates that the cigarette has been smoked, and the smoking device is controlled to exit the heating state, which helps to improve the smoking device's endurance and save on device consumption.

[0072] The technical solution provided in this embodiment continuously acquires the output information of the smoking device at each unit time during the smoking phase, dynamically determines the first reference information corresponding to each unit time, judges the rising characteristics of the output information and the first reference information at each unit time based on the first identification conditions, and determines the second reference information based on the satisfaction of the rising characteristics. Then, it judges the falling characteristics of the output information at each unit time based on the second identification conditions and the second reference information. When both rising and falling characteristics are detected, a valid smoking behavior is determined. By judging the rising and falling characteristics of the output information at each unit time, the accuracy of valid smoking behavior identification is improved.

[0073] Based on the above embodiments, this invention also provides a preferred example of a method for identifying suction behavior, see [link to example]. Figure 4 , Figure 4 This is a flowchart of a method for identifying smoking behavior provided by an embodiment of the present invention. In this embodiment, the smoking behavior of a smoking device is identified based on output energy. After the smoking device completes its startup and enters the smoking stage, the output energy Q1 for each unit time period is calculated. Kalman filtering is applied to the obtained output energy Q1 for each unit time period to reduce noise information in the output energy, resulting in a filtered output energy Q2. For each unit time period, a first reference information Qa is determined. When the output energy of the previous unit time period meets the first identification condition, the first reference information Qa corresponding to the current unit time period is the same as the first reference information Qa corresponding to the previous unit time period. When the output energy of the previous unit time period does not meet the first identification condition, the average output energy of multiple units within the previous historical time period corresponding to the current unit time period is determined as the first reference information corresponding to the current unit time period.

[0074] If the difference between the output energy Q2 and the first reference information Qa in any given unit time is greater than a first preset threshold Qt, then the first identification condition is met. The number of unit times that meet the first identification condition is counted, and the maximum value of the output energy Q2 in each unit time that meets the first identification condition is recorded. If the difference between the output energy Q2 and the first reference information Qa in any given unit time is not greater than the first preset threshold Qt, and the difference between the output energy Q2 and the first reference information Qa in that unit time is greater than a minimum difference threshold Qm, then no counting is performed, and the first identification condition is continued for the output energy in the next unit time. If the difference between the output energy Q2 and the first reference information Qa in any given unit time is not greater than the first preset threshold Qt, and the difference between the output energy Q2 and the first reference information Qa in that unit time is less than a second preset threshold Qm, then the number C1 of unit times that meet the first identification condition is reset to zero.

[0075] When the number of units C1 that satisfy the first identification condition meets the quantity threshold Ct, the fallback flag is set to 1 to indicate that the preset trigger condition is met, and the determination of the second identification condition for the output energy of subsequent units of time is initiated. The duration of units that satisfy the first identification condition is accumulated to determine the cumulative duration T1 of units that satisfy the first identification condition.

[0076] If the cumulative duration T1 is less than a preset duration threshold, and the output energy per unit time satisfies the second identification condition (i.e., the output energy per unit time is less than the second reference information), then a valid suction behavior is determined to have been detected. If the cumulative duration T1 is greater than the preset duration threshold, and no output energy per unit time satisfies the second identification condition, then an abnormal suction behavior is determined to have been detected. The second reference information is determined based on the maximum energy of the output energy per unit time across multiple units that satisfy the first identification condition.

[0077] Figure 5 This is a schematic diagram of the structure of a suction behavior recognition device provided in an embodiment of the present invention. Figure 5 As shown, the device includes an energy acquisition module 210 and a determination module 220.

[0078] The energy acquisition module 210 is used to acquire the output information of the smoking device at each unit of time.

[0079] The determination module 220 is used to determine first reference information corresponding to each unit time; to determine first identification conditions for the output information of each unit time based on the first reference information; to determine second reference information based on the output information of multiple consecutive first unit times when the first identification conditions are met; to continue to determine second identification conditions for the output information of each unit time based on the second reference information when the multiple first unit times meet preset trigger conditions; and to determine effective smoking behavior of the smoking device when the cumulative duration of the multiple first unit times is less than a preset duration threshold and the output information of the second unit time is detected to meet the second identification conditions.

[0080] The technical solution of this embodiment continuously acquires the output information of the smoking device at each unit time during the smoking phase, dynamically determines the first reference information corresponding to each unit time, judges the rising characteristics of the output information and the first reference information at each unit time based on the first identification conditions, and determines the second reference information based on the satisfaction of the rising characteristics. Then, it judges the falling characteristics of the output information at each unit time based on the second identification conditions and the second reference information. When both rising and falling characteristics are detected, a valid smoking behavior is determined. By judging the rising and falling characteristics of the output information at each unit time, the accuracy of valid smoking behavior recognition is improved.

[0081] Based on the above embodiments, optionally, the determination module 220 is configured to: for the current unit time, if the output information of the previous unit time does not meet the first identification condition, determine the first reference information corresponding to the current unit time based on the output information of multiple units of time in the previous historical time period corresponding to the current unit time; if the output information of the previous unit time meets the first identification condition, determine the first reference information corresponding to the previous unit time as the first reference information corresponding to the current unit time.

[0082] Optionally, determining the first reference information corresponding to the current unit time based on the output information of multiple unit times within the previous historical time period corresponding to the current unit time includes: determining the average of the output information of multiple unit times within the previous historical time period corresponding to the current unit time as the first reference information corresponding to the current unit time.

[0083] Optionally, the first identification condition includes the difference between any output information per unit time and the first reference information corresponding to the unit time being greater than a first preset threshold; and / or, the second identification condition includes the output information per unit time being less than the second reference information.

[0084] Optionally, the determination module 220 is further configured to: record the maximum information among multiple output information of the first unit time; determine second reference information based on the maximum information, wherein the second reference information is less than the maximum information and greater than the first preset threshold.

[0085] Optionally, the determination module 220 is further configured to: count a plurality of consecutive first unit times; and, if the number of the plurality of consecutive first unit times meets a number threshold, determine that the plurality of first unit times meets the preset trigger condition, and perform a step of determining the output information of each unit time after the first unit time based on the second reference information to determine the second identification condition.

[0086] Optionally, the determination module 220 is further configured to: reset the count of the first unit time to zero when the output information of any unit time does not meet the first identification condition and the difference between the output information of the unit time and the first reference information corresponding to the unit time is less than a second preset threshold.

[0087] Optionally, the determination module 220 is further configured to: determine the cumulative duration of the plurality of first unit times; and, if the cumulative duration is greater than the preset duration threshold, clear the cumulative duration, the count of the first unit times, and the second reference information to zero respectively.

[0088] Optionally, the energy acquisition module 210 is further configured to: after acquiring the output information of the smoking device at each unit time, filter the output information at each unit time to remove noise information from the output information at multiple units time.

[0089] Optionally, the device further includes a smoking device control module for counting the detected effective smoking behaviors and controlling the working state of the smoking device based on the number of effective smoking behaviors.

[0090] The suction behavior identification device provided in the embodiments of the present invention can execute the suction behavior identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0091] Figure 6 This is a schematic diagram of the structure of a smoking device provided in an embodiment of the present invention. The smoking device 10 is intended to represent various forms of electronic smoking devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0092] like Figure 6 As shown, the smoking device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the smoking device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] Multiple components in the smoking device 10 are connected to the I / O interface 15, including: an input unit 16; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the smoking device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0094] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for recognizing suction behavior.

[0095] In some embodiments, the method for identifying the smoking behavior can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the smoking device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for identifying the smoking behavior described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for identifying the smoking behavior by any other suitable means (e.g., by means of firmware).

[0096] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] Computer programs for implementing the method for identifying suction behavior according to the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0098] This invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for identifying a suction behavior, the method comprising:

[0099] The system acquires the output information of the smoking device at each unit time and determines the first reference information corresponding to each unit time. Based on the first reference information corresponding to each unit time, it determines the output information of each unit time according to a first identification condition. If the output information of multiple consecutive first unit times meets the first identification condition, it determines the second reference information based on the multiple first unit times. If the multiple first unit times meet a preset trigger condition, it continues to determine the second identification condition based on the second reference information. If the cumulative duration of the multiple first unit times is less than a preset duration threshold and the output information of the second unit time is detected to meet the second identification condition, it determines that an effective smoking behavior of the smoking device has been detected.

[0100] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0101] To provide interaction with the user, the systems and techniques described herein can be implemented on a smoking device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the smoking device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0103] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0104] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the method for identifying suction behavior according to any embodiment of the invention.

[0105] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0106] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying suction behavior, characterized in that, include: Obtain the output information of the smoking device at each unit of time, and determine the first reference information corresponding to each unit of time; Based on the first reference information corresponding to each unit time, the output information of each unit time is determined according to the first identification condition; If the output information of multiple consecutive first unit time periods satisfies the first identification condition, the second reference information is determined based on the multiple first unit time periods of output information. If the multiple first unit time periods meet the preset triggering conditions, the output information of each unit time period is further judged based on the second reference information to determine the second identification conditions. If the cumulative duration of the multiple first unit time periods is less than the preset duration threshold and the output information of the second unit time period is detected to meet the second identification conditions, it is determined that an effective smoking behavior of the smoking device has been detected.

2. The identification method according to claim 1, characterized in that, The determination of the first reference information corresponding to each unit of time includes: For the current unit of time, if the output information of the previous unit of time does not meet the first identification condition, then the first reference information corresponding to the current unit of time is determined based on the output information of multiple units of time in the previous historical time period corresponding to the current unit of time. If the output information of the previous unit of time satisfies the first identification condition, then the first reference information corresponding to the previous unit of time is determined as the first reference information corresponding to the current unit of time.

3. The identification method according to claim 2, characterized in that, The step of determining the first reference information corresponding to the current unit time based on the output information of multiple unit times within the previous historical time period corresponding to the current unit time includes: The average of the output information of multiple units of time in the previous historical time period corresponding to the current unit time is determined as the first reference information corresponding to the current unit time.

4. The identification method according to claim 1, characterized in that, The first identification condition includes a difference between the output information per unit time and the first reference information corresponding to the unit time being greater than a first preset threshold; and / or, The second identification condition includes that the output information per unit time is less than the second reference information.

5. The identification method according to claim 4, characterized in that, The determination of the second reference information based on the output information of the plurality of first unit time includes: Record the maximum value among the multiple output messages from the first unit of time; A second reference information is determined based on the maximum information, wherein the second reference information is less than the maximum information and greater than the first preset threshold.

6. The identification method according to claim 1, characterized in that, The method further includes: Counting multiple consecutive first unit time intervals; If the number of consecutive first unit time intervals meets the quantity threshold, it is determined that the multiple first unit time intervals meet the preset triggering condition, and the step of determining the second identification condition of the output information of each unit time interval after the first unit time interval based on the second reference information is executed.

7. The identification method according to claim 6, characterized in that, The method further includes: If the output information in any unit time does not meet the first identification condition, and the difference between the output information in the unit time and the first reference information corresponding to the unit time is less than the second preset threshold, the count of the first unit time is cleared to zero.

8. The identification method according to claim 6, characterized in that, The method further includes: Determine the cumulative duration of the plurality of first unit times; If the cumulative duration exceeds the preset duration threshold, the cumulative duration, the count of the first unit time, and the second reference information are all cleared to zero.

9. The identification method according to any one of claims 1-8, characterized in that, After acquiring the output information of the smoking device at each unit of time, it also includes: The output information for each unit time is filtered to remove noise from the output information for multiple units time.

10. The identification method according to claim 1, characterized in that, The method further includes: The number of detected effective sucking actions is counted, and the working state of the smoking device is controlled based on the number of effective sucking actions.

11. A device for recognizing suction behavior, characterized in that, include: The energy acquisition module is used to acquire the output information of the smoking device at each unit of time; The determination module is used to determine the first reference information corresponding to each unit time, and to determine the first identification condition for the output information of each unit time based on the first reference information corresponding to each unit time. If the output information of multiple consecutive first unit time periods satisfies the first identification condition, the second reference information is determined based on the multiple first unit time periods of output information. If the multiple first unit time periods meet the preset triggering conditions, the output information of each unit time period is further judged based on the second reference information to determine the second identification conditions. If the cumulative duration of the multiple first unit time periods is less than the preset duration threshold and the output information of the second unit time period is detected to meet the second identification conditions, it is determined that an effective smoking behavior of the smoking device has been detected.

12. A smoking device, characterized in that, The smoking device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the method for recognizing suction behavior according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for recognizing suction behavior as described in any one of claims 1-10.

Images