ELECTRONIC AEROSOL PROVISION SYSTEM

DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Continued Examination A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on September 14, 2026 has been entered. Status of the Claims Claims 1-16, and 18-22 are pending and are subject to this Office Action. This is the first Office Action on the merits of the claims. Claims 20-22 are withdrawn. Claim 1 is amended. Claim 17 is cancelled. Response to Amendments The amendments to the claims filed on September 14, 2026 are acknowledged. The 101 rejections of Claims 1-22 have been withdrawn due to the amendments. Response to Arguments Applicant' s arguments, see pgs 6-9, filed September 14, 2026, with respect to the rejection(s) of claims 1-19 under 35 U.S.C. 103 have been fully considered and they are persuasive. Applicant has amended claim 1 to require an optional limitation of Claim 17 that the previously applied prior art does not disclose: “wherein one or more characters in the alphabet are enabled or disabled for discrimination by the Al model based on the type of cartridge currently included in the electronic aerosol provision system.” Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of newly found prior art references in combination with previously applied prior art. The following is a modified rejection based on amendments made to the claims. The following is a modified rejection based on amendments made to the claims. Claim Rejections - 35 USC § 103 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. Claims 1-2, 5, 7, 9-16, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 2016/0158782 A1, cited on the IDS dated 9/19/2022) in view of Valafar (US 2018/0292910 A1, cited on the IDS dated 9/19/2022) and Thomas (US 2022/0256930 A1). Regarding Claim 1, Henry, directed to aerosol generating devices (), gesture detection for smoking applications ([0001], [0004]), and motion sensors ([0053]), teaches an electronic aerosol provision system ([0026], Fig. 1; Aerosol delivery device 100 is an electronic device forming a system comprising control body 102 and cartridge 104), said system including a motion sensor ([0053], Fig. 1; Aerosol delivery device 100 includes a motion sensor 146), at least one computing device ([0055]-[0056], Fig. 1; Aerosol delivery device 100 includes a control component 108 (e.g., microprocessor). A microprocessor is a computing device), the at least one computing device defining an alphabet of multiple characters ([0055]-[0056], Fig. 1; The motion sensor 146 may be configured to detect a defined motion of the aerosol delivery device caused by user interaction with the housing to perform a gesture. The control component 108 (e.g., microprocessor) of the aerosol delivery device 100 may be configured to receive the electrical signal from the motion sensor, recognize the gesture and an operation associated with the gesture based on the electrical signal, and control at least one functional element of the aerosol delivery device to perform the operation. [0047]-[0048], Examples of suitable gestures include tracing one character within alphabet of multiple character (e.g. an “l” or a “b”) with the housing. [0051], The gestures (characters) may be preset or user-defined. If multiple different alphabetical characters can be traced as gestures, and control component 108 can recognize the gesture based on receive the electrical signal from the motion sensor 146, the control component 108 (computing device) must define an alphabet of multiple characters), each character corresponding to a movement pattern ([0047]-[0048], [0066], Fig. 8); wherein the computing device is further configured to receive data from the motion sensor representing spatial motion of the electronic aerosol provision system ([0055]-[0056], Fig. 1; The motion sensor 146 may be configured to detect a defined spatial motion of the aerosol delivery device caused by user interaction with the housing to perform a gesture. The control component 108 (computing device) of the aerosol delivery device 100 may be configured to receive the electrical signal (data) from the motion sensor), and based on the received data, to discriminate a particular character from the alphabet of multiple characters as user input to the electronic aerosol provision system when the spatial motion of the electronic aerosol provision system matches the movement pattern of the particular character ([0055]-[0056], Fig. 1; The control component 108 (computing device) of the aerosol delivery device 100 may be configured to receive the electrical signal (data) from the motion sensor, recognize the gesture and an operation associated with the gesture based on the electrical signal, and control at least one functional element of the aerosol delivery device to perform the operation. [0047]-[0048], As the gesture may be one of alphabet of multiple characters defined by the computing device, the step of “recogniz[ing] the gesture” must comprise discriminating from the alphabet of multiple characters as user input to the electronic aerosol provision system when the spatial motion of the electronic aerosol provision system matches the movement pattern of the particular character), wherein said alphabet comprises characters used to input one or more operations relating to aerosol provision by the electronic aerosol provision system ([0047]-[0056]), but does not teach the system i) including an artificial intelligence (AI) model configured to run on the at least one computing device, the model defining the alphabet of multiple characters, wherein the AI model is further configured to receive data from the motion sensor representing spatial motion of the electronic aerosol provision system, and based on the received data, to discriminate a particular character from the alphabet of multiple characters as user input to the electronic aerosol provision system when the spatial motion of the electronic aerosol provision system matches the movement pattern of the particular character, wherein the AI model has been trained on an external computing system, and then loaded into the at least one computing device prior to use of the aerosol provision system by the user; and ii) wherein one or more characters in the alphabet are enabled or disabled for discrimination by the Al model based on the type of cartridge currently included in the electronic aerosol provision system. With respect to i), Valafar, directed to gesture detection for smoking applications ([0001], [0004]) and machine learning ([0007]), teaches a system ([0059], Fig. 6; Computing system 100 includes a wearable computing device 102 and a machine learning computing system 130 that are communicatively coupled over a network 180) including a motion sensor ([0023], [0059], Fig. 6; Wearable computing device 102 comprises one or more sensors 104. The one or more sensors 104 can include one or more accelerometers or a gyroscope to provide spatial motion data); at least one computing device ([0059]-[0061], Fig. 6; Wearable computing device 102 includes one or more processors 112. A microprocessor is a computing device); an artificial intelligence (AI) model configured to run on the at least one computing device ([0065]-[0066], Fig. 6; Wearable computing device 102 can store or include one or more machine-learned classifier models 110. The wearable computing device 102 can then use or otherwise implement the one or more machine-learned models 110 (e.g., by processor(s) 112). [0027], The machine-learned classifier models 110 can be a random forest classifier; a logistic regression classifier; a support vector machine; one or more decision trees; a neural network; and/or other types of models including both linear models and non-linear models), wherein the AI model is further configured to receive data from the motion sensor representing spatial motion of the system ([0023]-[0026], Fig. 1; The one or more sensors 104 output sensor (accelerometer) data 106 representing spatial motion of the wearable computing device 102 (system). Smoking gesture detection model 110 (AI model) can receive the sensor data 106), and based on the received data, to discriminate a particular gesture as user input to the system when the spatial motion of the system matches the movement pattern of the particular gesture ([0023]-[0026], Fig. 1; The one or more sensors 104 output sensor (accelerometer) data 106 representing spatial motion of the wearable computing device 102 (system). The smoking gesture detection model 110 can receive the sensor data 106 (e.g., the raw and/or pre-processed sensor data) and, in response, output a gesture classification 112. In particular, the gesture classification 112 can indicate whether the sensor data 106 was indicative of a smoking gesture (particular gesture). If the gesture classification 112 is a system output, the gesture is a user input). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the system of Henry comprising an artificial intelligence (AI) model configured to run on the at least one computing device as taught by Valafar, wherein the model defines the alphabet of multiple characters, wherein the AI model is further configured to receive data from the motion sensor representing spatial motion of the electronic aerosol provision system, and based on the received data, to discriminate a particular character from the alphabet of multiple characters as user input to the electronic aerosol provision system when the spatial motion of the electronic aerosol provision system matches the movement pattern of the particular character, as performed by the computing device of Henry, because Henry and Valafar are directed to gesture detection for smoking applications, Valafar demonstrates that AI models are capable of receiving data from a motion sensor representing spatial motion of the system and discriminate a particular gesture as user input to the system when the spatial motion of the system matches the movement pattern of the particular gesture (Valafar, [0023]-[0026], Fig. 1), and that the AI model can be trained to detect a gesture regardless of the device orientation (Valafar, [0019]), and this involves combining prior art elements according to known methods to yield predictable results. The limitation: “wherein the AI model has been trained on an external computing system, and then loaded into the at least one computing device prior to use of the aerosol provision system by the user” is a product-by-process limitation. The patentability of a product or apparatus does not depend on its method of production or formation. If the product in the product-by-process claim is the same as or obvious from a product of the prior art, the claim is unpatentable even if the prior product was made by a different process. In this instance, Henry in view of Valafar discloses a structurally and compositionally equivalent electronic aerosol provision system. With respect to ii), Thomas, directed to aerosol generating devices ([0002]-[0018]), teaches an electronic aerosol provision system ([0363]-[0369], Figs. 2A-2C; Smoking substitute device 110), said system including a main body, and a cartridge configured to couple to the main body ([0363]-[0369], Figs. 2A-2C; Smoking substitute device 110 includes a main body 120 and a consumable 150 (cartridge) configured to couple to the main body 120), wherein certain device functionalities can be enabled or disabled based on the type of cartridge which is coupled to the main body ([0093], The main body further houses a reading device to read a detail of the consumable and to determine whether the consumable is a first type or a second type and to enable or disable an aerosol assembly according to an operation mode determined from the location of the smoking substitute device; and [0553], It will be appreciated that there may be further modes where further functions are enabled and disabled and the modes may include combinations of functions, for instance an age limit restriction on a type of consumable). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the system wherein one or more characters in the alphabet are enabled or disabled for discrimination by the Al model based on the type of cartridge currently included in the electronic aerosol provision system because Henry and Thomas are directed to aerosol generating devices, Thomas demonstrates that certain device functionalities can be enabled or disabled based on the type of cartridge which is currently in use for the purpose of age restriction (Thomas, [0553]), and one of ordinary skill in the art would have understood that enabling/disabling characters in the alphabet would be a method of enabling/disabling device functionalities based on the type of cartridge currently included in the electronic aerosol provision system. As such, the cited disclosures in Thomas would have motivated one of ordinary skill in the art to provide the device wherein one or more characters in the alphabet are enabled or disabled for discrimination by the Al model based on the type of cartridge currently included in the electronic aerosol provision system. Regarding Claim 2, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein the motion sensor is configured to output 3-axis linear motion or acceleration data ([0053]-[0054], Fig. 1; Motion sensor 146 may be implemented as a multi-axis accelerometer. [0058]-[0059], Fig. 2; Multi-axis accelerometer 200 is configured to output 3-axis linear motion or acceleration data). Regarding Claim 5, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein the motion sensor is configured to collect samples of motion data at a rate of at least 10 Hz ([0014], [0058], Figs. 6-7; The motion sensor 146/accelerometer 200 is configured to collect samples of motion data at a rate of 62.5 Hz). Regarding Claim 7, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1, but does not teach the system wherein the motion sensor is configured to assemble multiple samples of motion data occurring during a time window, and for each time window, to send together to the AI model the multiple samples of motion data occurring during that time window. Valafar, directed to gesture detection for smoking applications ([0001], [0004]), teaches a system ([0059], Fig. 6; Computing system 100 includes a wearable computing device 102 and a machine learning computing system 130 that are communicatively coupled over a network 180) including a motion sensor ([0023], [0059], Fig. 6; Wearable computing device 102 comprises one or more sensors 104. The one or more sensors 104 can include one or more accelerometers or a gyroscope to provide spatial motion data); at least one computing device ([0059]-[0061], Fig. 6; Wearable computing device 102 includes one or more processors 112. A microprocessor is a computing device); an artificial intelligence (Al) model configured to run on the at least one computing device ([0065]-[0066], Fig. 6; Wearable computing device 102 can store or include one or more machine-learned classifier models 110. The wearable computing device 102 can then use or otherwise implement the one or more machine-learned models 110 (e.g., by processor(s) 112). [0027], The machine-learned classifier models 110 can be a random forest classifier; a logistic regression classifier; a support vector machine; one or more decision trees; a neural network; and/or other types of models including both linear models and non-linear models), wherein the motion sensor is configured to assemble multiple samples of motion data occurring during a time window, and for each time window, to send together to the AI model the multiple samples of motion data occurring during that time window ([0023]-[0026], Fig. 1; The one or more sensors 104 output sensor (accelerometer) data 106 representing spatial motion of the wearable computing device 102 (system). Smoking gesture detection model 110 (AI model) can receive the sensor data 106. [0028]-[0029], The smoking gesture detection model 110 can receive a plurality of sets of sensor data 106 over a plurality of time periods (time windows) and can output, for each time period, a gesture classification 112). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the system of Henry in view of Valafar and Thomas wherein the motion sensor is configured to assemble multiple samples of motion data occurring during a time window, and for each time window, to send together to the AI model the multiple samples of motion data occurring during that time window as disclosed by Valafar because Valafar demonstrates that this configuration provides an additional layer of intelligence beyond the basic detection of a smoking gesture by the gesture detection model 110, thereby reducing false positives (Valafar, [0028]-[0029], Fig. 1), and this involves combining prior art elements according to known methods to yield predictable results. Regarding Claim 9-10, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein said alphabet contains at least 4 characters ([0048], [0058], lowercase “l”, lowercase “b”, uppercase “L”, and uppercase “U” as sample characters), but does not teach the system wherein said alphabet contains 5 or more characters, 10 or more characters, 20 or more characters, 40 or more characters, wherein said alphabet contains between 20 and 60 characters. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the system wherein said alphabet contains between 20 and 60 characters because Henry states that the character may be any letter, number or other shape (Henry, [0048]), that the character may correspond any number of operations that may be performed by at least one functional element of the aerosol delivery device (Henry, [0062]), one of ordinary skill in the art would know that there are 26 letters in the alphabet, and providing additional characters to the alphabet would increase the number of operations which can be performed through motion sensor detection. Regarding Claim 11, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein said characters represent abstract, symbolic user input for the electronic aerosol provision system ([0048], the aerosol delivery device may be configured with an “unlock code” to lock/unlock the device, such as by the user tracing a particular character (e.g., lowercase “l”) with the device. The trace of a distinct particular character (e.g., lowercase “b”) may cause the aerosol delivery device to indicate a charge-level of its battery 112). Regarding Claim 12, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein said characters are used to input one or more of the following operations: sending the electronic aerosol provision system into a low power mode; setting a power level for the electronic aerosol provision system ([0062], [0069], recognizable gestures may be associated with any of a number of operations that may be performed by at least one functional element of the aerosol delivery device 100. For example, the operation may include altering a power state of the aerosol delivery device (e.g., turn on/off, enter standby/low-power mode, enter operational mode)). Regarding Claim 13, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein said characters are used to lock and/or unlock the electronic aerosol provision system, wherein the electronic aerosol provision system must be unlocked to produce vapor ([0048], [0052], on first use, the aerosol delivery device may be configured with an “unlock code” to lock/unlock the device, such as by the user tracing a particular character (e.g., lowercase “l”) with the device. It is reasonably understood that the electronic aerosol provision system must be unlocked to produce vapor). Regarding Claim 14, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Valafar further teaches the system wherein the AI model is configured to determine a string of one or more characters from the motion sensor data ([0023]-[0026], Fig. 1; The one or more sensors 104 output sensor (accelerometer) data 106 representing spatial motion of the wearable computing device 102 (system). The smoking gesture detection model 110 can receive the sensor data 106 (e.g., the raw and/or pre-processed sensor data) and, in response, output a gesture classification 112. In particular, the gesture classification 112 can indicate whether the sensor data 106 was indicative of a smoking gesture (particular gesture). If the gesture classification 112 is a system output, the gesture is a user input. As applied to Claim 1, the gestures may be characters. Therefore, a string of at least one character can be determined from the motion sensor data 106). Regarding Claim 15, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Valafar further teaches the system wherein the AI model runs on the at least one computing device to discriminate characters from the motion sensor data ([0023]-[0026], Fig. 1; The one or more sensors 104 output sensor (accelerometer) data 106 representing spatial motion of the wearable computing device 102 (system). The smoking gesture detection model 110 can receive the sensor data 106 (e.g., the raw and/or pre-processed sensor data) and, in response, output a gesture classification 112. In particular, the gesture classification 112 can indicate whether the sensor data 106 was indicative of a smoking gesture (particular gesture). If the gesture classification 112 is a system output, the gesture is a user input. Henry has been modified in view of Valafar such that the AI model of Valafar runs on the computing device of Henry). Regarding Claim 16, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1, wherein the AI model offloads at least some of the processing onto an external system to discriminate characters from the motion sensor data. Valafar, directed to gesture detection for smoking applications ([0001], [0004]), teaches a system ([0059], Fig. 6; Computing system 100 includes a wearable computing device 102 and a machine learning computing system 130 that are communicatively coupled over a network 180) including a motion sensor ([0023], [0059], Fig. 6; Wearable computing device 102 comprises one or more sensors 104. The one or more sensors 104 can include one or more accelerometers or a gyroscope to provide spatial motion data); at least one computing device ([0059]-[0061], Fig. 6; Wearable computing device 102 includes one or more processors 112. A microprocessor is a computing device); an artificial intelligence (Al) model configured to run on the at least one computing device ([0065]-[0066], Fig. 6; Wearable computing device 102 can store or include one or more machine-learned classifier models 110. The wearable computing device 102 can then use or otherwise implement the one or more machine-learned models 110 (e.g., by processor(s) 112). [0027], The machine-learned classifier models 110 can be a random forest classifier; a logistic regression classifier; a support vector machine; one or more decision trees; a neural network; and/or other types of models including both linear models and non-linear models), wherein the AI model is further configured to receive data from the motion sensor representing spatial motion of the system and based on the received data, to discriminate a particular gesture as user input to the system when the spatial motion of the system matches the movement pattern of the particular gesture ([0023]-[0026], Fig. 1; The one or more sensors 104 output sensor (accelerometer) data 106 representing spatial motion of the wearable computing device 102 (system). The smoking gesture detection model 110 can receive the sensor data 106 (e.g., the raw and/or pre-processed sensor data) and, in response, output a gesture classification 112. In particular, the gesture classification 112 can indicate whether the sensor data 106 was indicative of a smoking gesture (particular gesture). If the gesture classification 112 is a system output, the gesture is a user input), wherein the AI model offloads at least some of the processing onto an external system to discriminate characters from the motion sensor data ([0059], Fig. 6; Computing system 100 includes a wearable computing device 102 and a machine learning computing system 130 (external system) that are communicatively coupled over a network 180. [0072], In addition or alternatively to the model(s) 110 at the wearable computing device 102, the machine learning computing system 130 can include one or more machine-learned models 140. machine-learned models 110 can located and used at the wearable computing device 102 and/or machine-learned models 140 can be located and used at the machine learning computing system 130). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the system of Henry in view of Valafar and Thomas wherein the Al model offloads at least some of the processing onto an external system to discriminate characters from the motion sensor data as taught by Valafar because Valafar demonstrates that the external system provides the additional function of training and storing the AI models before their application with the aerosol generating system (Valafar, [0066]-]0068]), and this involves combining prior art elements according to known methods to yield predictable results. Regarding Claims 18-19, Henry in view of Valafar and Thomas teaches the electronic aerosol provision system of claim 1. Henry further teaches the system wherein the AI model includes a facility to change the alphabet by removing or amending existing and/or by adding new characters, wherein changing the alphabet is performed by interacting with an external system ([0051], The gestures may be preset or user-defined. In some examples, the aerosol delivery device may enable the user to define gestures for various operations. This may be accomplished in a number of different manners, such as through direct interaction with the aerosol delivery device, or interaction with the aforementioned or another software application. [0049] refers to a software application operating on an external system. As the computing device of Henry has been modified such that an AI model performs the functions of the computing device, the AI model of Henry in view of Valafar and Thomas would necessarily include a facility to change the alphabet by adding new gestures (characters)). Claims 3-4, and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 2016/0158782 A1, cited on the IDS dated 9/19/2022) in view of Valafar (US 2018/0292910 A1, cited on the IDS dated 9/19/2022) and Thomas (US 2022/0256930 A1) as applied to Claims 1 and 5, and further in view of Veneshetty (US 2020/0256038 A1). Regarding Claim 3-4, and 6, Henry in view of Valafar and Thomas does not teach the system wherein the motion sensor is configured to output 3-axis angular motion or acceleration data, wherein the motion sensor is configured to output 3-axis absolute spatial orientation data, wherein the motion sensor is configured to collect samples of motion data at an interval in the range 0.001 ~ 0.01 seconds. Veneshetty, directed to motion sensors ([0026]), teaches a motion sensor ([0026], Fig. 2; Movement characteristic sensor 32 may embody or comprise a six-axis or a nine-axis inertial motion sensor), wherein the motion sensor is configured to output 3-axis linear motion or acceleration data, wherein the motion sensor is configured to output 3-axis angular motion or acceleration data, wherein the motion sensor is configured to output 3-axis absolute spatial orientation data ([0026], Fig. 2; Movement characteristic sensor 32 may embody or comprise a six-axis or a nine-axis inertial motion sensor. A nine-axis inertial motion sensor may combine a three-axis accelerometer with a three-axis gyroscope and a three-axis compass or magnetometer. It is reasonably understood that the three-axis accelerometer is configured to output 3-axis linear motion or acceleration data, the three-axis gyroscope is configured to output 3-axis angular motion or acceleration data, and the three-axis compass or magnetometer is configured to output 3-axis absolute spatial orientation data), wherein the motion sensor is configured to collect samples of motion data at an interval in the range 0.001 ~ 0.01 seconds ([0042]-[0043], the measurement intervals may be two milliseconds in length (0.002 seconds)). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to replace the motion sensor of Henry with the nine-axis inertial motion sensor of Veneshetty such that the motion sensor is configured to output 3-axis angular motion or acceleration data and 3-axis absolute spatial orientation data and to collect samples of motion data at an interval in the range 0.001 ~ 0.01 seconds, because Henry and Veneshetty are directed to motion sensors, Henry demonstrates that the motion sensor is only configured to output 3-axis linear motion or acceleration data (Henry, [0053]-[0059], Fig. 1-2; Motion sensor 146 may be a multi-axis accelerometer 200 configured to output 3-axis linear motion or acceleration data), outputting 3-axis angular motion or acceleration data and 3-axis absolute spatial orientation data would increase the accuracy of the motion sensor, and thereby increase the efficacy of the character discrimination performed by the AI model. Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 2016/0158782 A1, cited on the IDS dated 9/19/2022) in view of Valafar (US 2018/0292910 A1, cited on the IDS dated 9/19/2022) and Thomas (US 2022/0256930 A1), and further in view of Chai (US 2022/0091837 A1). Regarding Claim 8, Henry in view of Valafar and Thomas does not teach the electronic aerosol provision system wherein the AI model is provided as a flat buffer file. Chai, directed to machine learning ([0002]), teaches an AI model ([0034]-[0038], Machine-learned models), wherein the AI model is provided as a flat buffer file ([0037]-[0038], The platform can use a conversion tool known as TensorFlow Lite Optimizing Converter (“TOCO”) to convert a standard TensorFlow graph of a model into a TensorFlow Lite graph, where TensorFlow Lite is a lightweight machine learning library designed for mobile applications. Converting an AI model using the TensorFlow Light Converter program generates a flat buffer file; see instant specification, pg 17, ln 21-23). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the AI model as a flat butter file because Valafar and Chai are directed to machine learning, Chai demonstrates that a mobile optimized version of an AI model can be generated by converting an AI model to a flat buffer file using the TensorFlow Lite Converter (Chai, [0038]), Henry demonstrates that the AI model is implemented on a mobile aerosol provision system (Henry, [0055]-[0056], Fig. 1; The control component 108 (computing device) of the aerosol delivery device 100 has been modified in view of Valafar such that the AI model of Valafar runs on the control component 108 of Henry), and this involves combining prior art elements according to known methods to yield predictable results. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN M. MARTIN whose telephone number is (703)756-1270. The examiner can normally be reached M-F 8:00-5:00. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Philip Louie can be reached on (571) 270-1241. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /J.M.M./ Examiner, Art Unit 1755 /PHILIP Y LOUIE/Supervisory Patent Examiner, Art Unit 1755