Electronic cigarette atomizer life analysis method and system

By processing abnormal identification and trust calculation of user data, the problem of abnormal data impact in the life detection of electronic cigarette atomizer is solved, and a more accurate life evaluation is achieved.

CN118410257BActive Publication Date: 2024-11-08GUANGDONG FUWO INTELLIGENT MFG CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410665579.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-27
Publication Date
2024-11-08
Estimated Expiration
2044-05-27

AI Technical Summary

Technical Problem

The failure to effectively process abnormal data in the prior art leads to a decrease in the accuracy and credibility of the life detection of electronic cigarette atomizers.

Method used

By collecting user usage data, performing fitting curve processing, extracting target temperature and airflow data segments, calculating the credibility of smoking time, identifying abnormal data, calculating the trust level, and weighting the sum to obtain the life of the electronic cigarette atomizer.

Benefits of technology

It improves the accuracy and credibility of the life detection of electronic cigarette atomizer, and objectively reflects the true life under different usage conditions and individual differences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118410257B_ABST
    Figure CN118410257B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and more specifically, to a method and system for analyzing the life of an electronic cigarette atomizer, including: collecting operation data of a user using an electronic cigarette atomizer, obtaining a data segment composed of each airflow data point and a temperature data segment composed of each temperature data point, M represents the total number of data segments; performing curve fitting processing on the #imgabs0# segment of temperature data #imgabs1#, and extracting the target temperature data segment #imgabs2# before temperature saturation. The present invention calculates the user's trust in using the electronic cigarette atomizer based on abnormal data, reduces the impact of abnormal data on the detection of the life of the electronic cigarette atomizer, and finally uses the weighted summation of the actual trust of test users of different age groups in using the electronic cigarette atomizer, which can more objectively and accurately reflect the real service life of the atomizer under different use conditions and different individual differences, thereby obtaining a more accurate life of the electronic cigarette atomizer.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a method and system for analyzing the life of an electronic cigarette atomizer. Background Art

[0002] Electronic cigarettes are mainly composed of atomizers, batteries, and cartridges. Among them, the atomizer is the core component of the electronic cigarette, which includes a heating element inside. When the battery is powered on, the heating element will generate heat, causing the tobacco oil next to it to evaporate, thereby forming steam, providing users with a smoking experience similar to that of traditional cigarettes. In order to provide users with a better user experience, it is often necessary to conduct a life analysis of the electronic cigarette atomizer.

[0003] In the related technology, for example, a Chinese patent application document with publication number CN117390972B discloses a method for predicting the life of an electronic cigarette atomizer. The application document discloses: the life of the electronic cigarette atomizer is predicted by using indicators quantified from the temperature clutter characteristics and periodic shape characteristics of the target curve segment, thereby effectively improving the accuracy of the prediction of the life of the electronic cigarette atomizer.

[0004] However, there may be abnormal data in the usage data of different test users, that is, the abnormal data cannot be used as data for life judgment standards. If these abnormal data are not analyzed and processed, the life detection of electronic cigarette atomizer products will be biased, reducing the accuracy and credibility of the life detection. Summary of the invention

[0005] The present invention provides an electronic cigarette atomizer life analysis method and system, aiming to solve the problem in the related art that if these abnormal data are not analyzed and processed, the electronic cigarette atomizer product life detection will be biased, thereby reducing the accuracy and credibility of the life detection.

[0006] In a first aspect, the present invention provides a method for analyzing the life of an electronic cigarette atomizer, comprising: collecting operation data of a user using an electronic cigarette atomizer, obtaining data points of each airflow to form a data segment And the temperature data segment composed of each temperature data point , M represents the total number of data segments; Segment temperature data Perform curve fitting processing to extract the target temperature data segment before temperature saturation , and the target temperature data segment Corresponding target airflow data segment , and calculate the Credibility of smoking duration , the calculation formula is:

[0007] ;

[0008] In the formula, and Respectively and The average value of Indicates the target airflow data segment Middle data points, The target temperature data segment Middle data points, express and The number of internal data points; the average smoking time of the user is obtained by weighted average of the single smoking time and its credibility; the number of anomalies is determined according to the difference between the single smoking time and the average smoking time, and the degree of trust is inversely correlated with the number of anomalies; the life of the electronic cigarette atomizer is obtained by weighted summation of the number of smoking times and the degree of trust of each user.

[0009] The effect is that since each user has different smoking habits, the data generated each time the user uses an electronic cigarette atomizer to smoke is obtained according to the user's smoking habits, and the abnormal data generated by the user in the process of using the electronic cigarette atomizer is found, and the user's trust in the use of the electronic cigarette atomizer is calculated based on the abnormal data, thereby reducing the impact of abnormal data on the detection of the life of the electronic cigarette atomizer. Finally, the weighted summation of the actual trust levels of the test users of different age groups in using the electronic cigarette atomizer can more objectively and accurately reflect the actual service life of the atomizer under different usage conditions and different individual differences, thereby obtaining a more accurate electronic cigarette atomizer life.

[0010] In one embodiment, the temperature data segment before temperature saturation is obtained. , including: using the least squares method to Temperature data segment for the first smoking The data points in the curve are fitted to obtain the slope at each corresponding time point, and the change rate sequence of the temperature data at the corresponding point before the temperature reaches saturation is counted to obtain the target temperature data segment. .

[0011] In one embodiment, the target temperature data segment is obtained. Corresponding target airflow data segment , including: In the air flow data section Intercept the target temperature data segment The data segments with corresponding time and the same length are recorded as target airflow data segments .

[0012] In one embodiment, the average smoking time of the user is obtained, and the calculation formula of the average smoking time is: ; In the formula, represents the average smoking time of users, Indicates How long does it take to smoke each time? Indicates The credibility of the duration of each smoking session, The The weight of the duration of each smoking session, Indicates the total number of times cigarettes are smoked.

[0013] In one embodiment, according to the difference between the duration of a single puff and the average duration of a puff, the number of anomalies is determined, and the degree of trust is calculated, including: calculating the characteristic value ; In the formula, Indicates user The characteristic value of smoking times, Indicates The duration of smoking each time, Indicates the average smoking time of the user.

[0014] The effect is that the difference between a single smoking time and the average smoking time is used to calculate the user's The characteristic value of each smoking simplifies the calculation process and improves the speed of data processing.

[0015] In one embodiment, the feature value is input into a box plot to obtain the abnormal number of the feature value.

[0016] The effect is that the box plot can intuitively display the distribution of data, including the median, upper and lower quartiles, and the range of outliers. Outliers are usually defined as data points that fall a certain distance outside the upper and lower quartiles. The box plot can intuitively identify these outliers and help quickly identify possible abnormal data.

[0017] In one embodiment, the number of anomalies is determined based on the difference between the single smoking duration and the average smoking duration, and the degree of trust is calculated. The degree of trust is inversely correlated with the number of anomalies, including: the degree of trust in the user's use of the electronic cigarette atomizer to run the data ; In the formula, represents the number of times the user smokes, and U represents the number of times the user smokes. The number of abnormal data in the data.

[0018] In one embodiment, the life of the electronic cigarette atomizer is calculated using the following formula: ;in, For the life of the electronic cigarette atomizer product, Indicates The number of cigarettes smoked by the test user, is the number of users, For the The trust level of the test users in the data run by the electronic cigarette atomizer, Indicates normalization processing.

[0019] In one embodiment, a sequence of the rate of change of temperature data at corresponding points before the temperature reaches saturation is statistically calculated, including: if five points with a slope of 0 appear consecutively in the fitting curve, the five points with a slope of 0 appearing consecutively are used as the dividing point, and the data before the dividing point are used as the target temperature data.

[0020] The effect is: it is used to remove the data after the temperature reaches saturation, reduce the amount of data calculation, improve the processing speed, and take the data before 5 points with consecutive zero slopes to avoid local optimality (data fluctuations may cause points with a slope of 0), thereby improving the accuracy of data acquisition.

[0021] In a second aspect of the present invention, there is also provided an electronic cigarette atomizer life analysis system, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the electronic cigarette atomizer life analysis methods described above.

[0022] Beneficial Effects of the Invention

[0023] (I) Based on the data of each user smoking each time, the credibility of the data generated by each smoking is calculated. Based on the credibility, the noise generated by some sensors built into the atomizer when collecting data can be eliminated, so that the final result of calculating the life of the electronic cigarette atomizer is more accurate.

[0024] (ii) Based on the credibility of the data generated by each puff, the characteristic value of each puff of the user is calculated, and based on the establishment of the characteristic value, the box plot can more accurately identify abnormal data, thereby obtaining the degree of trust in the actual data of different users using the electronic cigarette atomizer, improving the accuracy of product life analysis, and finding out the abnormal data generated by users when using the electronic cigarette atomizer.

[0025] (III) The user's trust in the use of the e-cigarette atomizer is calculated based on the abnormal data, which reduces the impact of the abnormal data on the detection of the life of the e-cigarette atomizer. Finally, the weighted summation of the actual trust of the test users of different age groups in the use of the e-cigarette atomizer can more objectively and accurately reflect the actual service life of the atomizer under different usage conditions and different individual differences, thereby obtaining a more accurate e-cigarette atomizer life. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0027] Figure 1 is a schematic diagram showing a flow chart of calculating the life of an electronic cigarette atomizer according to an embodiment of the present invention;

[0028] Figure 2 FIG. 1 is a schematic diagram schematically showing a system structure according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0030] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0031] The present invention is mainly because the test user may make some mistakes in the process of using the electronic cigarette atomizer, such as taking a very short puff. If this kind of data is used to judge the life of the electronic cigarette atomizer, the detected life of the electronic cigarette atomizer will be too high, resulting in a poor user experience. Therefore, it is necessary to identify the anomalies of the operating data generated by each test user using the electronic cigarette atomizer. When using the box plot to detect the anomalies of the electronic cigarette atomizer operating data, since the electronic cigarette atomizer operating data is multi-dimensional data, and the data of each dimension is not a point in the traditional sense, the box plot cannot directly detect anomalies on it. Therefore, this case calculates the characteristic value of each operating data to perform anomaly detection. After the box plot identifies the abnormal data, the ratio of the number of abnormal data to the total number of data becomes the user's trust level in the use of the electronic cigarette atomizer operating data. Finally, the weighted average of the operating data of all users can be used to obtain the life of the electronic cigarette atomizer. The specific process is as follows:

[0032] Step S101: Acquire data.

[0033] In one embodiment, the method for obtaining electronic cigarette atomizer data is as follows: first obtain the data of N different test users, wherein each user's data contains M segments of airflow data and M segments of temperature data (M for each test user may be different). It should be noted that M is the service life of the electronic cigarette atomizer used by a certain user (because the statistics of the service life of the electronic cigarette atomizer are based on the number of puffs, and each puff by the user will generate a segment of airflow data and temperature data).

[0034] For example, the operation data of the user's electronic cigarette atomizer is collected each time, and each airflow data point is obtained to form an airflow data segment. And the temperature data segment composed of each temperature data point ,in , Respectively represent the user The airflow data segment and temperature data segment generated during the first puff of smoke, and and The length of time is consistent.

[0035] It should be noted that M represents the total number of data segments, each of which represents one puff using the electronic cigarette atomizer. In other words, M represents the total number of puffs.

[0036] Since the sensors in the electronic cigarette atomizer may be affected by the surrounding environment of the test user, causing noise to be generated when the built-in sensors in the electronic cigarette atomizer collect data, it is also necessary to judge the credibility of the data collected from each test user each time they smoke (i.e., the credibility of a single smoking duration), so as to take a weighted average of the single smoking duration of a single test user to obtain the user's average smoking duration.

[0037] Step S102: Calculate the credibility of the duration of a single smoking session.

[0038] In one embodiment, the airflow rate directly affects the temperature change rate of the atomizer, because the greater the airflow, the more oxygen enters the atomizer core, which can accelerate the temperature change of the atomizer. Therefore, the larger the airflow data, the faster the temperature data changes. If the relationship between the temperature and airflow data during a user's smoking shows the above relationship, the credibility of the smoking duration is higher. It should be noted that the rate of change of temperature data can be represented by the slope at the corresponding point on the fitting curve. The greater the slope, the greater the rate of change. Its purpose is to calculate the credibility of the data generated by each smoking according to the data used by each user each time. According to the credibility, some data generated by abnormal smoking can be eliminated, so that the final calculation result of the life of the electronic cigarette atomizer is more accurate.

[0039] In one embodiment, calculating the reliability of each smoking duration includes: Segment temperature data Perform curve fitting to obtain the target temperature data segment before temperature saturation , and the target temperature data segment Corresponding target airflow data segment , and calculate the reliability of each smoking duration.

[0040] Specifically, for the operation data of a user using an electronic cigarette atomizer, the user The airflow data segment and temperature data segment generated during the first puff are , , take the calculation of the reliability of the smoking duration as an example. Temperature data segment for the first smoking The data points in the curve are fitted, and then the slope at each corresponding time point is obtained on the fitted curve; it should be noted that when the slope is always 0, it means that the temperature has been saturated (will not rise any further), then no matter how the current data changes, the temperature data will not change, so when the temperature data segment When there are five points with a slope of 0 in a row in the fitting curve, the calculation is stopped to obtain the target temperature data segment before temperature saturation. ,but It represents the change rate sequence of the temperature data at the corresponding point before the temperature reaches saturation; then in the air flow data segment Intercept and target temperature data The data segments with the same time length are recorded as target airflow data (time correspondence), then the target temperature data With target airflow data The correlation can characterize the changing relationship between temperature data and airflow data, thereby calculating the reliability of a single smoking duration.

[0041] In another embodiment, the temperature data segment can also be The calculation stops when 6 or 7 points with a slope of 0 appear in succession in the fitting curve.

[0042] Step S103: Calculate the characteristic value of a single smoking of the user.

[0043] In one embodiment, the average smoking time of the user is obtained based on the weighted average of the single smoking time and its credibility, and the single smoking time and the average smoking time are used to calculate the user's first The characteristic value of each smoking session.

[0044] Specifically, the duration of a single puff of a user can be determined using the airflow data segment The time span is expressed as, and the single smoking duration sequence of a user is recorded as ,in Indicates the air flow data segment The time span is The smoking time of each smoking session is calculated to calculate the average smoking time of the user. If the difference between the test user's single smoking time and his average smoking time is larger, it means that the smoking data information is more abnormal, and the characteristic value is larger, and the characteristic value of the user's single smoking session can be calculated.

[0045] Step S104: Obtain the user's trust level in using the electronic cigarette atomizer operation data.

[0046] In one embodiment, the number of abnormalities is determined based on the characteristic value, and the degree of trust is calculated. The degree of trust is inversely correlated with the number of abnormalities. Specifically, the characteristic value of each puff is calculated as described above, and a box plot is established for the characteristic value of the electronic cigarette atomizer operation data of each user, and the number of abnormal points is counted. The fewer abnormal data in the collected data, the higher the degree of trust. The purpose is to calculate the characteristic value of each puff of the user based on the credibility of the data generated by each puff, and based on the establishment of the characteristic value, the box plot can more accurately identify the abnormal data, thereby obtaining the degree of trust in the actual data of different users using the electronic cigarette atomizer, and improving the accuracy of product life analysis to find out the abnormal data generated by the user in the process of using the electronic cigarette atomizer.

[0047] Step S105: Calculate the life of the electronic cigarette atomizer.

[0048] In one embodiment, the life of the electronic cigarette atomizer product can be comprehensively obtained through the number of times each user smokes the electronic cigarette atomizer (i.e., the life of the electronic cigarette atomizer, one puff equals one puff) and the credibility of each user's usage data.

[0049] In one embodiment, the calculation formula for the reliability of calculating the duration of each puff in step S102 is:

[0050] In the formula, Indicates The credibility of the duration of smoking each time, and Respectively and The average value of the data points in the data segment, Indicates the target airflow data segment Middle data points, The target temperature data segment Middle data points, Indicates the target airflow data segment and target temperature data segment The number of data points inside.

[0051] in, is the sum of the products of the deviations of the airflow data and temperature data from the mean. This part reflects the coordinated changes between the two. If the two tend to deviate from their respective mean values ​​in the same direction at the same time, then the sum of this value is positive, that is, the higher the correlation, the better. The credibility of the smoking duration during the second smoking is positively correlated with this value; on the contrary, if the two are increasing and decreasing respectively, then the sum is a negative value, that is, the lower the correlation, the more credibility is 0; It is the normalization operation of correlation, where exp is the exponential function, and the normalized value is the credibility.

[0052] In one embodiment, in step S103, in order to calculate the characteristic value of a single smoking of a user, it is first necessary to calculate the average smoking time of the user. The calculation formula of the average smoking time is:

[0053] In the formula, represents the average smoking time of users, Indicates How long does it take to smoke each time? Indicates The credibility of the duration of each smoking session, is the weight of the duration of the i-th smoking session (normalization operation of credibility, and the sum of all weights needs to be kept equal to 1).

[0054] Next, the characteristic value is calculated using the single smoking duration and the average smoking duration. The calculation formula is: In the formula, Indicates user The characteristic value of smoking times, Indicates The duration of smoking each time, Indicates the average smoking time of the user. The user's The difference between the duration of a smoking session and the average duration of a smoking session. So far, the above method can be used to calculate the characteristic value of each user's smoking data each time, and the characteristic value sequence of a user is recorded as ,in Indicates user The characteristic values ​​of the electronic cigarette atomizer operation data during the first puff.

[0055] In another embodiment, the ratio of a single smoking duration to the average smoking duration may be used as the characteristic value.

[0056] In one embodiment, regarding the calculation of the trust level of each test user's operation data of the electronic cigarette atomizer in step 104, the calculation formula is: In the formula, Indicates the degree of trust users have in running data using electronic cigarette atomizers. represents the total number of times the user smokes, and U represents the number of abnormal data in the M data collected. It indicates the credibility of the data. It can be seen that the less abnormal data in the collected data, the higher the degree of trust.

[0057] In one embodiment, regarding the calculation of the life of the electronic cigarette atomizer in step S105, the calculation formula is: ;in, For the life of the electronic cigarette atomizer product, Indicates The number of cigarettes smoked by the test user, is the number of users, For the The trust level of the test users in the data run by the electronic cigarette atomizer, Indicates normalization processing.

[0058] So far, the life of the electronic cigarette atomizer product has been obtained through testing by multiple users and analysis of their usage data. , that is, an electronic cigarette atomizer can inhale mouth.

[0059] Through the above steps, the user's trust level in using the electronic cigarette atomizer is calculated based on the abnormal data, which reduces the impact of the abnormal data on the detection of the life of the electronic cigarette atomizer. Finally, the weighted summation of the actual trust levels of test users of different age groups in using the electronic cigarette atomizer can more objectively and accurately reflect the actual service life of the atomizer under different usage conditions and different individual differences, thereby obtaining a more accurate electronic cigarette atomizer life.

[0060] The present invention also provides an electronic cigarette atomizer life analysis system. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an electronic cigarette atomizer life analysis method according to the first aspect of the present invention is implemented.

[0061] In one embodiment, the present invention provides a computer device whose internal structure can be as follows: Figure 2As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities, and various varieties such as CPU, single-chip microcomputer, DSP or FPGA can be selected. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. When the computer program is executed, the steps described in the above method embodiment can be completed, such as S101-step S105. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for analyzing the life of an electronic cigarette atomizer is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0062] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the computer device of the present invention. The specific computer device may include more or less components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0063] The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0064] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0065] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0066] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for analyzing the life of an electronic cigarette atomizer, It is characterized in that include: Collect the operation data of the user using the electronic cigarette atomizer to obtain the data segment composed of each airflow data point And the temperature data segment composed of each temperature data point , Indicates the number of times you smoked; For Segment temperature data Perform curve fitting processing to extract the target temperature data segment before temperature saturation , and the target temperature data segment Corresponding target airflow data segment , and calculate the Credibility of smoking duration , the calculation formula is: ; In the formula, and Respectively and The average value of Indicates the target airflow data segment Middle data points, The target temperature data segment Middle data points, express and The number of internal data points; The average smoking time of the user is obtained by taking a weighted average of the single smoking time and its credibility. The number of anomalies is determined based on the difference between the single smoking time and the average smoking time, and the degree of trust is calculated. The degree of trust is inversely correlated with the number of anomalies. The life of the electronic cigarette atomizer is obtained by taking a weighted sum of the number of smoking times and the degree of trust of each user. Get the temperature data segment before temperature saturation ,include: Using the least squares method, Temperature data segment for the first smoking The data points in the curve are fitted to obtain the slope at each corresponding time point, and the change rate sequence of the temperature data at the corresponding point before the temperature reaches saturation is counted to obtain the target temperature data segment. .

2. The electronic cigarette atomizer life analysis method according to claim 1, It is characterized in that Get the target temperature data segment Corresponding target airflow data segment ,include: In the air flow data section Intercept the target temperature data segment The data segments with corresponding time and the same length are recorded as target airflow data segments .

3. The electronic cigarette atomizer life analysis method according to claim 1, It is characterized in that Get the average smoking time of the user. The calculation formula for the average smoking time is: ; In the formula, represents the average smoking time of users, Indicates How long does it take to smoke each time? Indicates The credibility of the duration of each smoking session, The The weight of the duration of each smoking session, Indicates the total number of times cigarettes are smoked.

4. The electronic cigarette atomizer life analysis method according to claim 3, It is characterized in that According to the difference between the duration of a single cigarette and the average duration of a cigarette, the number of anomalies is determined and the degree of confidence is calculated, including: Calculate eigenvalues ; In the formula, Indicates user The characteristic value of smoking times, Indicates The duration of smoking each time, Indicates the average smoking time of the user.

5. The electronic cigarette atomizer life analysis method according to claim 4, It is characterized in that Determine the number of anomalies that occurred, including: The characteristic value is input into the box plot, and the abnormal number U of the characteristic value is obtained to determine the number of abnormalities.

6. The electronic cigarette atomizer life analysis method according to claim 5, It is characterized in that According to the difference between the single smoking duration and the average smoking duration, the number of anomalies is determined, and the degree of confidence is calculated, wherein the degree of confidence is inversely correlated with the number of anomalies, including: The degree of trust users have in the data from running e-cigarette atomizers ; In the formula, represents the number of times the user smokes, and U represents the number of times the user smokes. The number of abnormal data in the data.

7. The electronic cigarette atomizer life analysis method according to claim 6, It is characterized in that Calculate the life of the electronic cigarette atomizer, the calculation formula is: ; in, For the life of the electronic cigarette atomizer product, Indicates The number of cigarettes smoked by the test user, is the number of users, For the The trust level of the test users in the data run by the electronic cigarette atomizer, Indicates normalization processing.

8. The electronic cigarette atomizer life analysis method according to claim 1, It is characterized in that The change rate sequence of the temperature data at the corresponding point before the temperature reaches saturation is statistically analyzed, including: If five points with a slope of 0 appear continuously in the fitting curve, the five points with a slope of 0 appear continuously are taken as the dividing point, and the data before the dividing point are taken as the target temperature data.

9. An electronic cigarette atomizer life analysis system, comprising a processor and a memory, wherein the memory stores a computer program. It is characterized in that The processor executes the computer program to implement the electronic cigarette atomizer life analysis method according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • A method for predicting the life of an electronic cigarette atomizer

    CN117390972B

  • Burning prediction and communications for an electronic cigarette

    CN105473011A

  • Smoking puff number detecting method for electronic cigarette and electronic cigarette

    CN109998178A

  • Thermal performance analysis device and method for electronic cigarette atomization core

    CN114098173A

  • Electronic cigarette atomizer service life analysis method

    CN116542161A