CN118656800A - Electronic cigarette atomizer life prediction method based on big data analysis - Google Patents

Abstract

The present invention relates to the technical field of electronic cigarettes, and discloses a method for predicting the life of an electronic cigarette atomizer based on big data analysis, comprising: recording usage data and usage status data of the electronic cigarette; predicting the future carbon deposit amount of the electronic cigarette atomizer at a future time Q according to a first deep neural network model; obtaining a battery performance coefficient of a battery of the electronic cigarette atomizer, and obtaining the failure probability of the electronic cigarette atomizer at a future time Q according to a third deep neural network model; judging whether the future time Q is a failure time according to the failure probability, and if not, setting T=T+k; if so, calculating the difference between the failure time and the time T, and taking the difference between the failure time and the time T as the remaining use time of the electronic cigarette atomizer; the present invention is conducive to reminding a user to replace the electronic cigarette atomizer on time, avoiding reminding the user to replace too early or too late, and is conducive to ensuring the real-time normal use of the electronic cigarette.

Description

Electronic cigarette atomizer life prediction method based on big data analysis

Technical Field

The present invention relates to the technical field of electronic cigarettes, and more specifically, to a method for predicting the life of an electronic cigarette atomizer based on big data analysis.

Background Art

Among the components of electronic cigarettes, the atomizer is a key part, and its performance and lifespan directly affect the overall user experience and safety of electronic cigarettes; however, different user habits, usage environment and maintenance conditions will affect the actual lifespan of the atomizer; replacing the atomizer too early or too late may have negative effects, such as: replacing it too early will increase the user's usage cost; while replacing it too late may cause the atomizer to fail, affecting the normal use of the electronic cigarette, resulting in a poor user experience, and even causing safety hazards; therefore, a more efficient, accurate and real-time electronic cigarette atomizer life prediction method is needed.

At present, the traditional electronic cigarette atomizer life prediction method mainly relies on laboratory tests, user feedback or empirical formulas, which cannot accurately reflect the actual usage. Of course, there are also some related improved technical documents. For example, the patent with authorization announcement number CN116542161B discloses an electronic cigarette atomizer life analysis method. This method intelligently predicts the service life of the electronic cigarette atomizer based on the configuration data of the electronic cigarette and various usage information of the electronic cigarette before the current time. However, research and practical application of the above method and the prior art found that the above method and the prior art have at least the following defects:

(1) There is a lack of consideration of the battery performance coefficient and carbon deposit amount of the electronic cigarette atomizer, and it is impossible to accurately estimate the battery performance coefficient and carbon deposit amount of the electronic cigarette atomizer;

(2) It is impossible to predict the failure time of the electronic cigarette atomizer battery based on the battery performance coefficient and the amount of carbon deposits, and thus it is impossible to determine the remaining use time of the electronic cigarette atomizer based on the failure time. Furthermore, it is impossible to remind the user to replace the electronic cigarette atomizer on time, which may easily lead to the user being reminded to replace the atomizer too early, resulting in increased user cost; or it may easily lead to the user being reminded to replace the atomizer too late, resulting in the failure of the atomizer and affecting the normal use of the electronic cigarette.

Summary of the invention

In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for predicting the life of an electronic cigarette atomizer based on big data analysis.

To achieve the above object, the present invention provides the following technical solutions:

A method for predicting the life of an electronic cigarette atomizer based on big data analysis, the method comprising:

S101: When a user uses an electronic cigarette, the use status data and the use state data of the electronic cigarette in the use time interval T-N to time T are recorded; the use state data includes the puffing time, puffing pressure, puffing frequency and average operating temperature at each time, and T and N are integers greater than zero;

S102: Inputting the usage status data and the usage state data into a preset first deep neural network model for predicting the carbon deposit amount, so as to predict the future carbon deposit amount of the electronic atomizer at a future time Q, where Q is an integer greater than zero;

S103: Obtaining the battery performance coefficient of the electronic atomizer battery at the future time Q, and inputting the battery performance coefficient of the electronic atomizer and the future carbon deposit amount into a preset third deep neural network model for predicting failure probability, so as to obtain the failure probability of the electronic cigarette atomizer at the future time Q;

S104: Determine whether the future time Q is the failure time according to the failure probability. If not, set T=T+k and return to step S101; if so, calculate the difference between the failure time and the time T, and use the difference between the failure time and the time T as the remaining usage time of the electronic cigarette atomizer, where k is an integer greater than zero.

Furthermore, the usage status data includes the current carbon deposit amount and e-liquid composition of the electronic cigarette, and the e-liquid composition includes nicotine concentration, propylene glycol ratio and vegetable glycerin ratio.

Furthermore, the generation logic of the preset first deep neural network model is as follows:

Acquire historical carbon deposit amount training data, and divide the historical carbon deposit amount training data into a carbon deposit amount training set and a carbon deposit amount test set, wherein the historical carbon deposit amount training data includes a plurality of carbon deposit amount feature data and their corresponding future carbon deposit amounts;

Wherein, the carbon deposit characteristic data includes usage status data and usage state data;

Constructing a first regression network, taking the carbon deposit amount characteristic data in the carbon deposit amount training set as input data of the first regression network, taking the future carbon deposit amount of the first regression network as output data of the first regression network, training the first regression network, and obtaining an initial first regression network;

The initial first regression network is model verified using the carbon deposit test set, and the initial first regression network that is less than or equal to the preset first test error threshold is output as the preset first deep neural network model.

Further, the obtaining of the battery performance coefficient of the electronic atomizer battery at the future time Q includes:

Obtaining current health characteristic data of a battery in an electronic cigarette atomizer during a usage time interval from T to N to time T; the current health characteristic data includes the battery capacity, current charging efficiency, current discharging efficiency, current battery temperature, current ambient temperature, current maximum discharge current and battery standard voltage value at each time;

Input the current health feature data into a preset second deep neural network model to obtain future health feature data at a future time Q;

The future health characteristic data includes battery capacity, future charging efficiency, future discharging efficiency, future battery temperature, future ambient temperature, future maximum discharge current and battery standard voltage value;

Input the future health characteristic data into the pre-built mathematical calculation model to obtain the battery performance coefficient of the electronic atomizer at the future time Q;

The expression of the pre-built mathematical calculation model is as follows:

;

Where: For the battery performance coefficient of the electronic atomizer Q at a future time, is the battery capacity, For the future charging efficiency at the future time Q, is the future discharge efficiency at the future time Q, is the battery temperature at the future time Q, is the future ambient temperature at the future time Q, is the future maximum discharge current at the future time Q, It is the standard voltage value of the battery.

Furthermore, the generation logic of the preset second deep neural network model is as follows:

Acquire historical health feature training data, and divide the historical health feature training data into a health feature training set and a health feature test set, wherein the historical health feature training data includes a plurality of current health feature data and corresponding future health feature data;

Constructing a second regression network, using current health feature data in the health feature training set as input data of the second regression network, and using future health feature data in the health feature training set as output data of the second regression network, training the second regression network, and obtaining an initial second regression network;

The initial second regression network is model verified using the health feature test set, and the initial second regression network with a preset second test error is output as the preset second deep neural network model.

Furthermore, the generation logic of the preset third deep neural network model is as follows:

Acquire historical failure probability training data, and divide the historical failure probability training data into a failure probability training set and a failure probability test set, wherein the historical failure probability training data includes failure probability influencing feature data and its corresponding failure probability;

Wherein, the failure probability impact characteristic data includes battery performance coefficient and future carbon deposition amount;

Constructing a third regression network, using the failure probability training set in the failure probability training set as input data of the third regression network, and using the failure probability in the failure probability training set as output data of the third regression network, training the third regression network, and obtaining an initial third regression network;

The initial third regression network is model verified using the failure probability test set, and the initial third regression network that is less than or equal to a preset third error threshold is output as the preset third deep neural network model.

Furthermore, judging whether the future time Q is a failure time according to the failure probability includes:

Setting a failure probability threshold, and comparing the failure probability with the failure probability threshold;

If the failure probability is less than or equal to the failure probability threshold, it is determined that the electronic cigarette atomizer will not completely fail at the future time Q, and the future time Q is marked as a non-failure time;

If the failure probability is greater than the failure probability threshold, it is determined that the electronic cigarette atomizer will completely fail at the future time Q, and the future time Q is marked as the failure time.

An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, any of the above-mentioned methods for predicting the life of an electronic cigarette atomizer based on big data analysis is implemented.

A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements any of the above-mentioned methods for predicting the life of an electronic cigarette atomizer based on big data analysis.

Compared with the prior art, the present invention has the following beneficial effects:

The present application discloses a method for predicting the life of an electronic cigarette atomizer based on big data analysis, including: recording the usage status data and usage state data of the electronic cigarette; predicting the future carbon deposit amount of the electronic cigarette atomizer at a future time Q according to a first deep neural network model; obtaining the battery performance coefficient of the electronic cigarette atomizer battery, and obtaining the failure probability of the electronic cigarette atomizer at a future time Q according to a third deep neural network model; judging whether the future time Q is the failure time according to the failure probability, if not, setting T=T+k; if so, calculating the difference between the failure time and the time T, and taking the difference between the failure time and the time T as the remaining life of the electronic cigarette atomizer. Remaining usage time; Based on the above technical features, the present invention can more accurately estimate the battery performance coefficient and carbon deposit amount of the electronic cigarette atomizer, and by introducing the consideration of the battery performance coefficient and carbon deposit amount of the electronic cigarette atomizer, the present invention can predict the failure time of the electronic cigarette atomizer battery, which is beneficial to determine the remaining usage time of the electronic cigarette atomizer according to the failure time. Further, it is beneficial to remind the user to replace the electronic cigarette atomizer on time, avoid reminding the user to replace too early, resulting in increased user cost; or avoid reminding the user to replace too late, resulting in failure of the atomizer, which is beneficial to ensure the real-time and normal use of the electronic cigarette.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a method for predicting the life of an electronic cigarette atomizer based on big data analysis provided by the present invention;

FIG2 is a schematic structural diagram of an electronic device provided by the present invention;

FIG. 3 is a schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

DETAILED DESCRIPTION

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 only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Example 1

Referring to FIG. 1 , this embodiment discloses a method for predicting the life of an electronic cigarette atomizer based on big data analysis, the method comprising:

S101: When a user uses an electronic cigarette, the use status data and the use state data of the electronic cigarette in the use time interval T-N to time T are recorded; the use state data includes the puffing time, puffing pressure, puffing frequency and average operating temperature at each time, and T and N are integers greater than zero;

Specifically, the usage status data includes the current carbon deposit amount and e-liquid composition of the electronic cigarette, and the e-liquid composition includes nicotine concentration, propylene glycol (PG) ratio and vegetable glycerin (VG) ratio;

It should be understood that the amount of carbon deposits refers to the amount of carbonaceous residues produced on the surface of the heating element, atomizer core or other parts of the electronic cigarette atomizer due to the heating process of the electronic cigarette liquid; these residues are mainly formed by the decomposition or incomplete combustion of the components in the electronic cigarette liquid (such as glycerin and propylene glycol) at high temperatures; and the amount of carbon deposits is an important factor leading to the failure of electronic cigarette atomizers; and the important factors that lead to the continuous accumulation of carbon deposits include the composition of the electronic cigarette oil, the duration of puffing, the puffing pressure, the puffing frequency and the average operating temperature, etc. By monitoring the real-time changes of these parameters, it is helpful to provide an important basis for the subsequent accurate prediction of the future carbon deposits, and then provide support for the subsequent determination of the failure time of the electronic cigarette atomizer;

It should be noted that the usage status data and usage state data are collected using various types of micro sensors, including but not limited to timers, pressure sensors, temperature sensors, etc.

S102: Inputting the usage status data and the usage state data into a preset first deep neural network model for predicting the carbon deposit amount, so as to predict the future carbon deposit amount of the electronic atomizer at a future time Q, where Q is an integer greater than zero;

Specifically, the generation logic of the preset first deep neural network model is as follows:

Acquire historical carbon deposit amount training data, and divide the historical carbon deposit amount training data into a carbon deposit amount training set and a carbon deposit amount test set, wherein the historical carbon deposit amount training data includes a plurality of carbon deposit amount feature data and their corresponding future carbon deposit amounts;

Wherein, the carbon deposit characteristic data includes usage status data and usage state data;

It should be noted that the carbon deposit amount characteristic data in the historical carbon deposit amount training data is obtained through historical records or micro-sensor collection, and the details are referred to above, which will not be repeated here; the future carbon deposit amount in the carbon deposit amount characteristic data is obtained by technicians recording in real time according to experimental conditions;

Constructing a first regression network, taking the carbon deposit amount characteristic data in the carbon deposit amount training set as input data of the first regression network, and taking the future carbon deposit amount of the first regression network as output data of the first regression network, training the first regression network, and obtaining an initial first regression network;

The initial first regression network is model verified using the carbon deposit test set, and the initial first regression network whose error is less than or equal to the preset first test error threshold is output as the preset first deep neural network model;

It should be noted that the first regression network is specifically one of the regression algorithm models such as LSTM neural network, CNN convolutional neural network or RNN recurrent neural network.

S103: Obtaining the battery performance coefficient of the electronic atomizer battery at the future time Q, and inputting the battery performance coefficient of the electronic atomizer and the future carbon deposit amount into a preset third deep neural network model for predicting failure probability, so as to obtain the failure probability of the electronic cigarette atomizer at the future time Q;

In implementation, the obtaining of the battery performance coefficient of the electronic atomizer battery at the future time Q includes:

Obtaining current health characteristic data of a battery in an electronic cigarette atomizer during a usage time interval from T to N to time T; the current health characteristic data includes the battery capacity, current charging efficiency, current discharging efficiency, current battery temperature, current ambient temperature, current maximum discharge current and battery standard voltage value at each time;

Input the current health feature data into a preset second deep neural network model to obtain future health feature data at a future time Q;

The future health characteristic data includes battery capacity, future charging efficiency, future discharging efficiency, future battery temperature, future ambient temperature, future maximum discharge current and battery standard voltage value;

Specifically, the generation logic of the preset second deep neural network model is as follows:

Acquire historical health feature training data, and divide the historical health feature training data into a health feature training set and a health feature test set, wherein the historical health feature training data includes a plurality of current health feature data and corresponding future health feature data;

It should be noted that the current health characteristic data in the historical health characteristic training data is obtained by collecting or retrieving records from a database through various sensor devices, and the sensor devices include but are not limited to current sensors, voltage sensors and temperature sensors; and the future health characteristic data is obtained by real-time collection and entry by technicians;

Constructing a second regression network, using current health feature data in the health feature training set as input data of the second regression network, and using future health feature data in the health feature training set as output data of the second regression network, training the second regression network, and obtaining an initial second regression network;

Using the health feature test set to perform model verification on the initial second regression network, and outputting an initial second regression network with a value less than or equal to a preset second test error as a preset second deep neural network model;

It should be noted that, like the first regression network, the second regression network is specifically one of the regression algorithm models such as LSTM neural network, CNN convolutional neural network or RNN recurrent neural network;

Input the future health characteristic data into the pre-built mathematical calculation model to obtain the battery performance coefficient of the electronic atomizer at the future time Q;

The expression of the pre-built mathematical calculation model is as follows:

;

Where: For the battery performance coefficient of the electronic atomizer Q at a future time, is the battery capacity (mAh), is the future charging efficiency (percentage) at the future time Q, is the future discharge efficiency (percentage) at the future time Q, is the battery temperature at the future time Q, is the future ambient temperature at the future time Q (in degrees Celsius), is the future maximum discharge current (A) at the future time Q, is the standard voltage value of the battery (V);

Specifically, the generation logic of the preset third deep neural network model is as follows:

Acquire historical failure probability training data, and divide the historical failure probability training data into a failure probability training set and a failure probability test set, wherein the historical failure probability training data includes failure probability influencing feature data and its corresponding failure probability;

Wherein, the failure probability impact characteristic data includes battery performance coefficient and future carbon deposition amount;

It should be noted that the failure probability influencing characteristic data in the historical failure probability training data is predicted by the above-mentioned preset first deep neural network model and the preset second deep neural network model. Please refer to the description of the above-mentioned relevant parts for details, and no further details will be given here. The failure probability is obtained by technicians based on experimental data records.

Constructing a third regression network, using the failure probability training set in the failure probability training set as input data of the third regression network, and using the failure probability in the failure probability training set as output data of the third regression network, training the third regression network, and obtaining an initial third regression network;

Using the failure probability test set to perform model verification on the initial third regression network, outputting an initial third regression network that is less than or equal to a preset third error threshold as a preset third deep neural network model;

It should be noted that, like the first regression network or the second regression network mentioned above, the third regression network is specifically one of the regression algorithm models such as LSTM neural network, CNN convolutional neural network or RNN recurrent neural network.

S104: judging whether the future time Q is the failure time according to the failure probability, if not, setting T=T+k, and returning to step S101; if yes, calculating the difference between the failure time and the time T, and taking the difference between the failure time and the time T as the remaining use time of the electronic cigarette atomizer, k is an integer greater than zero;

In implementation, judging whether the future time Q is a failure time according to the failure probability includes:

Setting a failure probability threshold, and comparing the failure probability with the failure probability threshold;

If the failure probability is less than or equal to the failure probability threshold, it is determined that the electronic cigarette atomizer will not completely fail at the future time Q, and the future time Q is marked as a non-failure time;

If the failure probability is greater than the failure probability threshold, it is determined that the electronic cigarette atomizer will completely fail at the future time Q, and the future time Q is marked as the failure time;

It should be noted that the present invention will only give an alarm when the service life of the electronic cigarette atomizer is approaching the end. In other words, when the remaining usage time is obtained, it means that the service life of the electronic cigarette atomizer is approaching the end, and the user needs to be reminded to replace the electronic cigarette atomizer in time. Compared with the prior art, the service life alarm of the electronic cigarette atomizer of the present invention is less frequent, but the alarm is accurate, which can avoid the trouble caused to the user by frequent alarms.

It can be understood that: by real-time monitoring of the use status (such as temperature, use frequency, puff time, etc.) and use conditions (such as e-liquid composition, etc.) of the electronic cigarette, the present invention can more accurately and precisely estimate the battery performance coefficient and carbon deposit amount of the electronic cigarette atomizer, and by introducing consideration of the battery performance coefficient and carbon deposit amount of the electronic cigarette atomizer, the present invention can predict the failure time of the electronic cigarette atomizer battery, which is conducive to determining the remaining use time of the electronic cigarette atomizer according to the failure time, and further, it is conducive to reminding the user to replace the electronic cigarette atomizer on time, avoiding reminding the user to replace too early, resulting in increased user cost; or avoiding reminding the user to replace too late, resulting in failure of the atomizer, which is conducive to ensuring the real-time and normal use of the electronic cigarette.

Example 2

Please refer to Figure 2, the present embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements any one of the electronic cigarette atomizer life prediction methods based on big data analysis provided by the above methods.

Since the electronic device introduced in this embodiment is an electronic device used to implement the electronic cigarette atomizer life prediction method based on big data analysis in the embodiment of this application, based on the electronic cigarette atomizer life prediction method based on big data analysis introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not introduced in detail here. As long as the electronic device used by the technical personnel of this field to implement the electronic cigarette atomizer life prediction method based on big data analysis in the embodiment of this application, it belongs to the scope of protection of this application.

Example 3

Please refer to Figure 3, the present embodiment discloses a computer-readable storage medium, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements any one of the electronic cigarette atomizer life prediction methods based on big data analysis provided by the above methods.

The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims (9)

1. A method for predicting the life of an electronic cigarette atomizer based on big data analysis, characterized in that the method comprises: S101: When a user uses an electronic cigarette, the use status data and the use state data of the electronic cigarette in the use time interval T-N to time T are recorded; the use state data includes the puffing time, puffing pressure, puffing frequency and average operating temperature at each time, and T and N are integers greater than zero; S102: Inputting the usage status data and the usage state data into a preset first deep neural network model for predicting the carbon deposit amount, so as to predict the future carbon deposit amount of the electronic atomizer at a future time Q, where Q is an integer greater than zero; S103: Obtaining the battery performance coefficient of the electronic atomizer battery at the future time Q, and inputting the battery performance coefficient of the electronic atomizer and the future carbon deposit amount into a preset third deep neural network model for predicting failure probability, so as to obtain the failure probability of the electronic cigarette atomizer at the future time Q; S104: Determine whether the future time Q is the failure time according to the failure probability. If not, set T=T+k and return to step S101; if so, calculate the difference between the failure time and the time T, and use the difference between the failure time and the time T as the remaining usage time of the electronic cigarette atomizer, where k is an integer greater than zero. 2. The method for predicting the life of an electronic cigarette atomizer based on big data analysis according to claim 1, characterized in that the usage status data includes the current carbon deposit amount and the smoke oil composition of the electronic cigarette, and the smoke oil composition includes nicotine concentration, propylene glycol ratio and vegetable glycerin ratio. 3. The method for predicting the life of an electronic cigarette atomizer based on big data analysis according to claim 2, characterized in that the generation logic of the preset first deep neural network model is as follows: Acquire historical carbon deposit amount training data, and divide the historical carbon deposit amount training data into a carbon deposit amount training set and a carbon deposit amount test set, wherein the historical carbon deposit amount training data includes a plurality of carbon deposit amount feature data and their corresponding future carbon deposit amounts; Wherein, the carbon deposit characteristic data includes usage status data and usage state data; Constructing a first regression network, taking the carbon deposit amount characteristic data in the carbon deposit amount training set as input data of the first regression network, taking the future carbon deposit amount of the first regression network as output data of the first regression network, training the first regression network, and obtaining an initial first regression network; The initial first regression network is model verified using the carbon deposit test set, and the initial first regression network that is less than or equal to the preset first test error threshold is output as the preset first deep neural network model. 4. The electronic cigarette atomizer life prediction method based on big data analysis according to claim 3, characterized in that the obtaining of the battery performance coefficient of the electronic cigarette atomizer battery at the future time Q comprises: Obtaining current health characteristic data of a battery in an electronic cigarette atomizer during a usage time interval from T to N to time T; the current health characteristic data includes the battery capacity, current charging efficiency, current discharging efficiency, current battery temperature, current ambient temperature, current maximum discharge current and battery standard voltage value at each time; Input the current health feature data into a preset second deep neural network model to obtain future health feature data at a future time Q; The future health characteristic data includes battery capacity, future charging efficiency, future discharging efficiency, future battery temperature, future ambient temperature, future maximum discharge current and battery standard voltage value; Input the future health characteristic data into the pre-built mathematical calculation model to obtain the battery performance coefficient of the electronic atomizer at the future time Q; The expression of the pre-built mathematical calculation model is as follows: ; Where: For the battery performance coefficient of the electronic atomizer Q at a future time, is the battery capacity, For the future charging efficiency at the future time Q, is the future discharge efficiency at the future time Q, is the battery temperature at the future time Q, is the future ambient temperature at the future time Q, is the future maximum discharge current at the future time Q, It is the standard voltage value of the battery. 5. The method for predicting the life of an electronic cigarette atomizer based on big data analysis according to claim 4, characterized in that the generation logic of the preset second deep neural network model is as follows: Acquire historical health feature training data, and divide the historical health feature training data into a health feature training set and a health feature test set, wherein the historical health feature training data includes a plurality of current health feature data and corresponding future health feature data; Constructing a second regression network, using current health feature data in the health feature training set as input data of the second regression network, and using future health feature data in the health feature training set as output data of the second regression network, training the second regression network, and obtaining an initial second regression network; The initial second regression network is model verified using the health feature test set, and the initial second regression network with a preset second test error is output as the preset second deep neural network model. 6. The method for predicting the life of an electronic cigarette atomizer based on big data analysis according to claim 5, characterized in that the generation logic of the preset third deep neural network model is as follows: Acquire historical failure probability training data, and divide the historical failure probability training data into a failure probability training set and a failure probability test set, wherein the historical failure probability training data includes failure probability influencing feature data and its corresponding failure probability; Wherein, the failure probability impact characteristic data includes battery performance coefficient and future carbon deposition amount; Constructing a third regression network, using the failure probability training set in the failure probability training set as input data of the third regression network, and using the failure probability in the failure probability training set as output data of the third regression network, training the third regression network, and obtaining an initial third regression network; The initial third regression network is model verified using the failure probability test set, and the initial third regression network that is less than or equal to a preset third error threshold is output as the preset third deep neural network model. 7. The method for predicting the life of an electronic cigarette atomizer based on big data analysis according to claim 6, characterized in that the step of judging whether the future time Q is the failure time according to the failure probability comprises: Setting a failure probability threshold, and comparing the failure probability with the failure probability threshold; If the failure probability is less than or equal to the failure probability threshold, it is determined that the electronic cigarette atomizer will not completely fail at the future time Q, and the future time Q is marked as a non-failure time; If the failure probability is greater than the failure probability threshold, it is determined that the electronic cigarette atomizer will completely fail at the future time Q, and the future time Q is marked as the failure time. 8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that when the processor executes the computer program, the method for predicting the life of an electronic cigarette atomizer based on big data analysis as described in any one of claims 1 to 7 is implemented. 9. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the method for predicting the life of an electronic cigarette atomizer based on big data analysis according to any one of claims 1 to 7 is implemented.