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 .
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 5-11, 14, 16 and 19 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Alcaide et al., US Patent Application (20230214018), hereinafter “Alcaide”
Regarding claim 5 Alcaide teaches a system, comprising: a user-interface device, The platform 100 may communicate with a user device 140 to display output, via a user interface 144 generated by an application engine 142. [Alcaide para 0032] comprising: a housing The headband of the headphones 225, connects to the case of the headphones 228. [Alcaide para 0051]: at least one sensor coupled with the housing and configured to detect physiological signals Head movements may include head tilts, head nods, head shakes, head rotations, or the like, and may be combined with the facial gestures discussed above sequentially or coincidentally to indicate a certain desired interaction. [Alcaide para 0044] associated with an inaudible communication of a user and produce sensor data the headphones also contain an accelerometer and/or a gyroscope which provide movement data to the computing device. The movement data can be combined with the EMG data to determine certain types of head movements, or head movements combined with facial gestures. [Alcaide para 0044]; and a pre-processing module operable to pre-process the sensor data and produce pre-processed sensor data FIG. 6B, a facial gesture architecture implemented by the Analytics Engine receives incoming data that represents voltages and impedances from one or more LSL (lab streaming layer) transmitters from the headphones. [Alcaide para 0075]; and at least one machine learning (ML) model communicatively coupled with the pre-processing module and configured to, at least: receive as input the pre-processed sensor data; and produce an output representation of a content of the inaudible communication of the user. he signal files may further include audio data and movement data, from which audio and movement features may be extracted. For example, the signal files may include audio data based on sound detected by one or more microphones associated with at least one of the electrodes. The signal files may further include movement data based on at least one change in a physical orientation of a motion detector associated with the set of headphones. In various embodiments the audio signal may be associated with a facial gesture, for instance a clicking of the teeth creates an audible “click” sound but also uses muscles to move the jaw and thereby creates EMG signals that can be picked up by the electrodes. In this embodiment, the audio signal may be detected by one or more microphones, converted from analog audio signal to a digital signal, and sent to the analytics engine platform 100 wherein the Feature Extraction Module 108 may extract audio features and send those features to the Machine Learning Network 130 along with the extracted EMG features associated with the facial gesture. [Alcaide para 0059]
Regarding claim 6 Alcaide teaches claim 5 in addition Alcaide teaches wherein: the user-interface device further includes a network interface; and the at least one ML model is disposed on a computing device remote from the user-interface device and communicatively coupled to the user-interface device via the network interface. Cloud computing can be used to provide software-as-a-service, platform-as-a-service, infrastructure-as-a-service, and similar features. In a cloud computing environment, a user may store a file in the “cloud,” which means that the file is stored on a remote network resource though the actual hardware storing the file may be opaque to the user. [Alcaide para 0031] the databases and information maintained in a database may be combined together or further separated in a manner the promotes retrieval and storage efficiency and/or data security. In one or more embodiments, the Analytics Engine Platform 100 the machine learning network 130 and the data 120, 122, 124 may all be implemented within one or more computing devices. [Alcaide para 0039]
Regarding claim 7 Alcaide teaches claim 5 in addition Alcaide teaches wherein the pre-processing module is disposed within the housing of the user-interface device. The headband of the headphones 225, connects to the case of the headphones 228. [Alcaide para 0051]
Regarding claim 8 Alcaide teaches claim 5 in addition Alcaide teaches further comprising: a computing device remote from the user-interface device and communicatively coupled to the user-interface device via a network, the client 141 may be a set of headphones that sends biometric or motion sensor data used during execution of the method 200 or other method herein. This may be accomplished via communication over the network 145 between the client 141 and server 150. For example, the client may communicate a request to the server 150 to store a file with a specified file name in the storage 151. The server 150 may respond to the request and store the file with the specified name in the storage 151. The file to be saved may exist on the client 141 or may exist in other storage accessible via the network such as storage 152, or even in storage on the client 142 (e.g., in a peer-to-peer system). [Alcaide para 0029] the computing device including: a processor; and a memory coupled to the processor A computer system may include a processor, a memory [Alcaide para 0024] and storing an artificial intelligence (AI) agent configured to, The memory and non-transitory medium may store instructions for performing methods and steps [Alcaide para 0024] at least: receive the output representation of the content of the inaudible communication from the at least one ML model The Analytics Engine identifies at least one input command that corresponds to the detected relationship between the user's current level of a particular type of mental state and the threshold. For example, the input command may include at least one of: (i) one or more instructions to initiate at least one of a notification and (ii) one or more instructions for one of (a) a reduction, (b) a minimization and (c) an elimination of presentation of one or more notifications on the computing device. [Alcaide para 0060]; determine, based at least in part on the output representation, an action to be performed; and cause the action to be performed. Output from the machine learning network 130 may be sent to the computing device 140 and may represent one or more types of actions to be performed or executed. Output from the machine learning network 130 may be sent to the headphones 202 via the computer device(s) 140 and/or a cloud computing environment 206. Output may represent one or more types of actions to be performed. [Alcaide para 045]
Regarding claim 9 Alcaide teaches claim 5 in addition Alcaide teaches wherein the at least one sensor comprises at least one of: an electromyography (EMG) sensor configured to detect micro-movements of at least one of a jaw or a tongue of the user; a functional near-infrared spectroscopy (fNIR) sensor configured to detect image data of a brain of the user; a sound navigation and ranging (SONAR) sensor configured to detect fine-grained motion in an ear of the user or around the ear of the user; a radio detection and ranging (RADAR) sensor configured to detect micro-deformations inside the ear of the user; an optical motion tracking sensor configured to track movements inside the ear of the user; an interferometry sensor configured to detect micro-deformations based on changes in light wave patterns; an ultrasound sensor configured to capture inner ear movements or apply low-intensity focused ultrasound (LIFU) to a neural region of a brain of the user; an otoacoustic emissions device configured to detect changes in the ear; a microelectromechanical systems (MEMS) microphone configured to capture movements related to jaw and tongue actions; an in-ear electroencephalography (EEG) sensor configured to record electrical activity from a brain of the user; a superconducting quantum interference device (SQUID) configured to detect magnetic signals associated with neural activity; or a magnetoencephalography (MEG) configured to detect magnetic signals associated with neural activity. The headphones 202 may include one or more electrodes that can detect various types of signals, such as EEG and/or EMG signals. [Alcaide para 0054] the neural signals can be recorded through the electrodes in the neural recording device appropriately arranged around the ear and jaw of a user [Alcaide para 0048] one or more electrodes are placed at a location on the headphones 202 that results in a proximate alignment of the one or more electrodes with a location at which the user's jawbone is substantially close to the user's ear when the user wears the headphones 202. [Alcaise para 0049]
Regarding claim 10 Alcaide teaches claim 5 in addition Alcaide teaches, wherein the housing is sized and shaped to be positioned at least partially within an ear canal of the user. The headband of the headphones 225, connects to the case of the headphones 228. [Alcaide para 0051]
Regarding claim 11 Alcaide teaches claim 5 in addition Alcaide teaches wherein the housing is sized and shaped to be positioned at least partially around an outer portion of an ear of the user. The headband of the headphones 225, connects to the case of the headphones 228. [Alcaide para 0051]
Regarding claim 14 Alcaide teaches claim 5 in addition Alcaide teaches further comprising: at least one output device configured to provide feedback to the user, the at least one output device comprising at least one of: a speaker configured to provide audible feedback; a haptic device configured to provide haptic feedback; or a display interface configured to provide visual feedback. there is also a haptic feedback indicator (e.g. a vibrate sensation), that alerts the user of a notification. … the visual indicator is used as a driver of social interaction. For instance, if a user is above a certain threshold of mental fatigue, or has been above a certain level of mental fatigue for a certain level of time, then a haptic notification may be sent to the user (e.g. the headphones vibrate according to a certain pattern), [Alcaide para 0043]
Regarding claim 16 Alcaide teaches an apparatus, comprising: a wearable housing configured to be positioned around, on, or within an ear of a user The headband of the headphones 225, connects to the case of the headphones 228. [Alcaide para 0051]; a plurality of sensors coupled with the wearable housing and configured to generate sensor data corresponding to an inaudible communication generated by the user the movement of those muscles can be detected by the sensors on the headphones. [Alcaide para 0041]; and at least one machine learning (ML) model configured to, at least: receive as input the sensor data The signal files may further include audio data and movement data, from which audio and movement features may be extracted. For example, … The signal files may further include movement data based on at least one change in a physical orientation of a motion detector associated with the set of headphones. … and sent to the analytics engine platform 100 wherein the Feature Extraction Module 108 may extract audio features and send those features to the Machine Learning Network 130 along with the extracted EMG features associated with the facial gesture. [Alcaide para 0059]; and produce an output representation corresponding to a content of the inaudible communication of the user. Output from the machine learning network 130 may be sent to the computing device 140 and may represent one or more types of actions to be performed or executed. Output from the machine learning network 130 may be sent to the headphones 202 via the computer device(s) 140 and/or a cloud computing environment 206. Output may represent one or more types of actions to be performed. [Alcaide para 045]
Regarding claim 19 Alcaide teaches claim 16 in addition Alcaide teaches further comprising: at least one output device coupled with the wearable housing and configured to provide feedback to the user based at least in part on the output representation, the at least one output device comprising at least one of: a speaker configured to provide audible feedback corresponding to the content of the inaudible communication; or a haptic device configured to provide tactile feedback indicating confirmation or rejection of the output representation; and a motion sensor configured to detect a head movement of the user indicating a confirmation or a rejection of the output representation. there is also a haptic feedback indicator (e.g. a vibrate sensation), that alerts the user of a notification. … the visual indicator is used as a driver of social interaction. For instance, if a user is above a certain threshold of mental fatigue, or has been above a certain level of mental fatigue for a certain level of time, then a haptic notification may be sent to the user (e.g. the headphones vibrate according to a certain pattern), [Alcaide para 0043]
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.
Claim(s) 1 and 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alcaide et al., US Patent Application (20230214018), hereinafter “Alcaide” and Lin et al, Chinese Patent Application (CN113314121A), hereinafter “Lin”
Regarding claim 1 Alcaide teaches an apparatus, comprising: a housing The headband of the headphones 225, connects to the case of the headphones 228. [Alcaide para 0051]: an electromyography (EMG) sensor coupled with the housing and configured to, The headphones 202 may include one or more electrodes that can detect various types of signals, such as EEG and/or EMG signals. [Alcaide para 0054] at least: detect micro-movements of at least one of a jaw or a tongue of a user during an inaudible communication of the user; The neural signals can be recorded through the electrodes in the neural recording device appropriately arranged around the ear and jaw of a user [Alcaide para 0048] one or more electrodes are placed at a location on the headphones 202 that results in a proximate alignment of the one or more electrodes with a location at which the user's jawbone is substantially close to the user's ear when the user wears the headphones 202. [Alcaise para 0049] and produce EMG sensor data corresponding to the micro-movements A facial gesture may be, for example, a jaw movement, a jaw clench, a jaw wiggle left and right, a jaw jutting (e.g. jutting jaw forward and backward), a jaw opening, a tooth click, a smile, a cheek puff, a cheek suck, a blink, a wink, a tongue movement, a nose movement, an inhalation or exhalation, an eye movement, a frown, an eyebrow raise, an eyebrow lowering, a mouth movement, a whispered word or phrase, a silent vocalization, and any type of facial muscle movement, head movement, and any type of jaw movement, asymmetric variations of the former, and combinations thereof. [Alcaide para 0048]; and a system coupled with the housing and configured to, at least: detect inside an ear of the user during the inaudible communication of the user the generation and output of meaningful data by electrodes placed solely near, in, and/or around a person's ears, such as substantially near a mastoid area, the occipital area behind the ear, the zygomatic region near the ear, the temporal region, the parotid-masseteric region, the auricular region, the temporomandibular joint area, the temple area, the sphenoid area, in the ear canal, and/or any defined facial region or head region in or around the ear, especially those areas that may be normally touched by a pair of headphones. [Alcaide para 0053]; and produce sensor data corresponding one or more electrodes may detect EMG signals representing a movement of a user's facial muscle(s) when the user wears the set of headphones [Alcaide para 0054]; a pre-processing module coupled with the EMG sensor and the system and operable to, at least: pre-process the EMG sensor data received from the EMG sensor and produce pre-processed EMG sensor data The Analytics Engine extracts EMG features from the received data based on EMG signals detected by the one or more electrodes. The Analytics Engine feeds the extracted EMG features into a facial gesture machine learning model for determining a type of facial gesture from a plurality of types of facial gestures. [Alcaide para 0059]; and pre-process the sensor data and produce pre-processed sensor data The signal files may further include audio data and movement data, from which audio and movement features may be extracted. For example, … The signal files may further include movement data based on at least one change in a physical orientation of a motion detector associated with the set of headphones. … and sent to the analytics engine platform 100 wherein the Feature Extraction Module 108 may extract audio features and send those features to the Machine Learning Network 130 along with the extracted EMG features associated with the facial gesture. [Alcaide para 0059]; and at least one machine learning (ML) model configured to receive as input the pre-processed EMG sensor data and the pre-processed detection-and-ranging sensor data and produce an output representation of a content of the inaudible communication of the user. The signal files may further include audio data and movement data, from which audio and movement features may be extracted. … The signal files may further include movement data based on at least one change in a physical orientation of a motion detector associated with the set of headphones. …. and sent to the analytics engine platform 100 wherein the Feature Extraction Module 108 may extract audio features and send those features to the Machine Learning Network 130 along with the extracted EMG features associated with the facial gesture. [Alcaide para 0059]
Alcaide does not teach but Lin teaches ranging and detection inner ear sensor and detecting micro deformations The silent speech recognition method provided in this application embodiment uses an electronic device 10 as the execution subject. Specifically, through the human-computer interaction between the silent voice input action and the electronic device 10, the electronic device 10 obtains the recognition result corresponding to the silent voice. Taking an electronic device 10 as an earphone as an example, the principle of the silent voice recognition method is as follows: When sound (i.e., the first signal) is played in the earphone, the audio signal propagates in the ear canal. When the audio signal hits the ear wall, the signal is reflected, forming a corresponding reflected signal. At this moment, the user makes a silent gesture, which causes the corresponding oral movement to deform the inside of the ear canal. Because deformation of the ear canal will cause changes in the signal propagation path, the resulting reflected signal will fluctuate accordingly. Based on the fluctuations in the obtained reflected signals, the deformation of the ear canal can be inferred in reverse. [Lin para(s) 0044-045]
Alcaide discloses an apparatus, methods, systems and computer program products described herein are directed to an Analytics Engine that receives one more signal files that include neural signal data of a user based on voltages detected by one or more electrodes on a set of headphones worn by a user. The Analytics Engine preprocesses the data, extracts features from the received data, and feeds the extracted features into one or more machine learning models to generate determined output that corresponds to at least one of a current mental state of the user and a type of facial gesture performed by the user. The Analytics Engine sends the determined output to a computing device to perform an action based on the determined output.
Lin discloses a silent speech recognition method and device, a medium, an earphone and electronic equipment, and relates to the field of silent speech recognition. The method comprises the following steps: acquiring a first signal, wherein the first signal is an audio signal before the earphone is used to play; acquiring a mixed signal, wherein the mixed signal comprises a second signal and a reflection signal after the second signal is transmitted through the ear canal, the second signal is an audio signal after the first signal is played through the earphone, and the reflection signal changes along with the deformation of the ear canal corresponding to the silent speech; and determining an identification result corresponding to the silent speech according to the first signal and the mixed signal.
Prior to the effective date of the invention it would have been obvious to one of ordinary skill in the art to combine the teachings of Alcaide and Lin in the art of preprocessing data to extract features from the received data and feeds the extracted features into one or more machine learning models and operating the same, as one of ordinary skill in the art would have recognized that the results of the combination were predictable as the combined teachings and technologies were well known in the art. Lin improves Alcaide’s systems, methods and/or apparatus by using a silent speech recognition method and device, a medium, an earphone and electronic equipment to extract features of facial movement
Regarding claim 3 Alcaide and Lin teaches claim 1 in addition Alcaide teaches wherein the housing is sized and shaped to be positioned at least partially within an ear canal of the user. that the electrodes can be integrated into the ear cup, ear cushion, Ear-Pads, earpads, ear-canal-probe, ear-bud, or other part of the headphones that make contact with a user's skin in or around the user's ear. [Alcaide para 0049]
Claim(s) 1 and 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alcaide and Lin, and further in view of Fleury et al., US Patent Application (20230031613), hereinafter “Fleury”
Regarding claim 2 Alcaide and Lin teaches claim 1 in addition Alcaide and Lin do not teach but Fleury teaches further comprising: a functional near-infrared spectroscopy (fNIR) sensor coupled with the housing and configured to, at least: detect image data of a brain of the user during the inaudible communication of the user The wearable device may include a camera, a display and bio-signal measuring means. At least one of the bio-signal measuring means may employ at least one sensor in order to measure brain activity. [Fleury para 0143]; and produce fNIR sensor data corresponding to the image data measuring relative changes in hemoglobin concentration through the use of near infrared light attenuation. [Fleury Para 0143]; and wherein: the pre-processing module is further operable to pre-process the fNIR sensor data received from the fNIR sensor Brain activity may be measured through electroencephalography (“EEG”) techniques electrically, or through functional near-infrared spectroscopy (fNIR″) technique [Fleury Para 0143]and produce pre-processed fNIR sensor data; and the at least one ML model is further configured to receive as additional input the pre-processed fNIR sensor data. Collected and analyzed data may be used to build a user profile that is specific to a user. The user profile data may be analyzed, such as by machine learning algorithms, either individually or in the aggregate to function as a BCI, or to improve the algorithms used in the analysis. [Fleury para 0151]
Alcaide discloses an apparatus, methods, systems and computer program products described herein are directed to an Analytics Engine that receives one more signal files that include neural signal data of a user based on voltages detected by one or more electrodes on a set of headphones worn by a user. The Analytics Engine preprocesses the data, extracts features from the received data, and feeds the extracted features into one or more machine learning models to generate determined output that corresponds to at least one of a current mental state of the user and a type of facial gesture performed by the user. The Analytics Engine sends the determined output to a computing device to perform an action based on the determined output.
Lin discloses a silent speech recognition method and device, a medium, an earphone and electronic equipment, and relates to the field of silent speech recognition. The method comprises the following steps: acquiring a first signal, wherein the first signal is an audio signal before the earphone is used to play; acquiring a mixed signal, wherein the mixed signal comprises a second signal and a reflection signal after the second signal is transmitted through the ear canal, the second signal is an audio signal after the first signal is played through the earphone, and the reflection signal changes along with the deformation of the ear canal corresponding to the silent speech; and determining an identification result corresponding to the silent speech according to the first signal and the mixed signal.
Fleury discloses a wearable device has a flexible and extendable body configured to encircle a portion of a body of a user, an electronics module with a concave space between two ends, each end attachable to the flexible and extendable body with a flexible retention mount to allow rotation of the flexible and extendable body relative to the electronics module and to transfer tension force from the flexible and extendable body to the electronics module, and a bio-signal sensor disposed on the flexible and extendable body to contact at least part of the body of the user and to receive bio-signals from the user.
Prior to the effective date of the invention it would have been obvious to one of ordinary skill in the art to combine the teachings of Alcaide, Lin and Fleury in the art of preprocessing data to extract features from the received data and feeds the extracted features into one or more machine learning models and operating the same, as one of ordinary skill in the art would have recognized that the results of the combination were predictable as the combined teachings and technologies were well known in the art. Lin improves Alcaide’s systems, methods and/or apparatus by using a silent speech recognition method and device, a medium, an earphone and electronic equipment to extract features of facial movement. Fleury improves Alcaide’s systems, methods and/or apparatus by using through functional near-infrared spectroscopy (fNIR″) technique to measure Brain activity may be measured through electroencephalography (“EEG”) techniques to produce clear output images of the Brain
Regarding claim 18 Alcaide teaches claim 16 in addition Alcaide does not teach but Fleury teaches wherein the plurality of sensors further comprises: a functional near-infrared spectroscopy (fNIR) sensor Brain activity may be measured through electroencephalography (“EEG”) techniques electrically, or through functional near-infrared spectroscopy (fNIR″) technique [Fleury Para 0143] configured to produce image data of a brain of the user during the inaudible communication. Collected and analyzed data may be used to build a user profile that is specific to a user. The user profile data may be analyzed, such as by machine learning algorithms, either individually or in the aggregate to function as a BCI, or to improve the algorithms used in the analysis. [Fleury para 0151]
Claim(s) 4 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alcaide and Lin, and further in view of Brunner et al., US Patent Application (20250062040), hereinafter “Brunner”
Regarding claim 4 Alcaide teaches claim 1 in addition Alcaide does not teach but Brunner teaches wherein the detection-and-ranging system comprises at least one of: a sound navigation and ranging (SONAR) component configured to detect micro-deformations by reflecting acoustic signals off at least one of a jaw, a tongue, or an inner ear of the user; a radio detection and ranging (RADAR) component configured to detect micro-deformations using electromagnetic signals; or an ultrasound component configured to capture detailed movements related to the inaudible communication. stereovision may be used to create 2D or 3D models. The system may use one or more of a number of technologies available to acquire 3D images of a scene. These may include sonar, millimeter wave radar, scanning lasers, structured light, and stereovision. A number of novel technologies that can be available for the embodiments disclosed herein are shown in Table I. As described herein, sensors, and sensor configurations capable of generating 3D data, may be referred to as 3D-sensors. [Brunner para 0171]
Alcaide discloses an apparatus, methods, systems and computer program products described herein are directed to an Analytics Engine that receives one more signal files that include neural signal data of a user based on voltages detected by one or more electrodes on a set of headphones worn by a user. The Analytics Engine preprocesses the data, extracts features from the received data, and feeds the extracted features into one or more machine learning models to generate determined output that corresponds to at least one of a current mental state of the user and a type of facial gesture performed by the user. The Analytics Engine sends the determined output to a computing device to perform an action based on the determined output.
Lin discloses a silent speech recognition method and device, a medium, an earphone and electronic equipment, and relates to the field of silent speech recognition. The method comprises the following steps: acquiring a first signal, wherein the first signal is an audio signal before the earphone is used to play; acquiring a mixed signal, wherein the mixed signal comprises a second signal and a reflection signal after the second signal is transmitted through the ear canal, the second signal is an audio signal after the first signal is played through the earphone, and the reflection signal changes along with the deformation of the ear canal corresponding to the silent speech; and determining an identification result corresponding to the silent speech according to the first signal and the mixed signal.
Brunner discloses devices, systems, and methods for capturing and analyzing behavioral and physiological data of subjects for treatment, modification, and manipulation discovery. In some embodiments, a method for classifying a drug is provided. The method includes obtaining observational data concerning an animal subject to which the drug is administered, the observational data acquired using an enclosure for the animal subject, the enclosure instrumented with at least one sensing device. The method also includes extracting features by applying the observational data to a machine-learning feature-extraction component. The method further includes predicting a class label of the drug by applying the features to a machine-learning classifier component, the machine-learning classifier component trained to predict the class label of the drug from, at least in part, the features. The method further includes providing an indication of the class label.
Prior to the effective date of the invention it would have been obvious to one of ordinary skill in the art to combine the teachings of Alcaide, Lin and Brunner in the art of preprocessing data to extract features from the received data and feeds the extracted features into one or more machine learning models and operating the same, as one of ordinary skill in the art would have recognized that the results of the combination were predictable as the combined teachings and technologies were well known in the art. Lin improves Alcaide’s systems, methods and/or apparatus by using a silent speech recognition method and device, a medium, an earphone and electronic equipment to extract features of facial movement. Brunner improves Alcaide’s systems, methods and/or apparatus by using sensors, and sensor configurations capable of generating 3D data.
Regarding claim 17 Alcaide teaches claim 16 in addition Alcaide does not teach but Brunner teaches wherein the plurality of sensors comprises: an electromyography (EMG) sensor configured to detect micro-movements of at least one of a jaw, a tongue, or vocal tract muscles of the user during the inaudible communication; and a sound navigation and ranging (SONAR) sensor configured to detect fine-grained motion in an ear of the user or around the ear of the user; a radio detection and ranging (RADAR) sensor configured to detect micro-deformations inside the ear of the user during the inaudible communication; or an optical sensor configured to capture optical data to detect movements in the ear of the user or around the ear of the user during the inaudible communication. stereovision may be used to create 2D or 3D models. The system may use one or more of a number of technologies available to acquire 3D images of a scene. These may include sonar, millimeter wave radar, scanning lasers, structured light, and stereovision. A number of novel technologies that can be available for the embodiments disclosed herein are shown in Table I. As described herein, sensors, and sensor configurations capable of generating 3D data, may be referred to as 3D-sensors. [Brunner para 0171]
Claim(s) 12, 13, 15 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alcaide and Lin, and further in view of Lui et al., US Patent Application (20240104183), hereinafter “Lui”
Regarding claim 12 Alcaide teaches claim 5 in addition Alcaide does not teach but Lin teaches further comprising: an identity authenticator agent configured to, at least: compare at least a portion of the pre-processed sensor data with stored user profile data associated with the user to authenticate an identity of the user the computer-implemented method can include performing a multi-factor authentication process, where the multi-factor authentication process uses the machine-learning classifier output to authenticate a user. [Lui para 0012];; and generate an authentication result indicating that the user is authenticated. the memory can further store instructions configured to cause the processor to perform a multi-factor authentication process, where the multi-factor authentication process uses the machine-learning classifier output to authenticate a user. [Lui para 0030];
Alcaide discloses an apparatus, methods, systems and computer program products described herein are directed to an Analytics Engine that receives one more signal files that include neural signal data of a user based on voltages detected by one or more electrodes on a set of headphones worn by a user. The Analytics Engine preprocesses the data, extracts features from the received data, and feeds the extracted features into one or more machine learning models to generate determined output that corresponds to at least one of a current mental state of the user and a type of facial gesture performed by the user. The Analytics Engine sends the determined output to a computing device to perform an action based on the determined output.
Lui Discloses methods, apparatus, systems, and computer-readable media for processing biosensor information to produce multi-dimensional images of facial movement, produce multi-dimensional images of expressions of a human user, perform biosensor-based user identification, perform biosensor-based user authentication, and combinations thereof. Other methods, apparatus, systems, and computer-readable media are also disclosed
Prior to the effective date of the invention it would have been obvious to one of ordinary skill in the art to combine the teachings of Alcaide and Lui in the art of preprocessing data to extract features from the received data and feeds the extracted features into one or more machine learning models and operating the same, as one of ordinary skill in the art would have recognized that the results of the combination were predictable as the combined teachings and technologies were well known in the art. Lui improves Alcaide’s systems, methods and/or apparatus by using multi-factor authentication process and a machine-learning classifier output to authenticate a user.
Regarding claim 13 Alcaide teaches claim 5 in addition Alcaide does not teach but Lin teaches further comprising: a translation agent configured to, at least: receive at least a portion of the output representation; and generate a translated output in a different language than a language of the output representation. The system platform may also support headsets from a variety of vendors; the user-specific biosignal information can be received from: a helmet, a hat, a headset, a virtual reality headset, an augmented reality headset, earbuds, smart glasses, a wireless device, a computer monitor, or a combination thereof. [Lui para 0036];
Regarding claim 15 Alcaide teaches claim 5 in addition Alcaide does not teach but Lin teaches wherein the at least one ML model comprises: a plurality of sensor-specific ML models, each configured to process pre-processed sensor data from a corresponding sensor type; and a synthesis ML model configured to, at least: receive outputs from each of the plurality of sensor-specific ML models; and produce, based at least in part on the outputs received from each of the plurality of sensor-specific ML models, the output representation. Biosignal Stream in Testing to Continuously Reconstruct 3D Faces. During testing, the biosignal stream first passes through the same pre-processing procedures in training. Then the fine-tuned biosignal network can continuously reconstruct 2D facial landmarks from the biosignal stream, without any visual input. To ensure a fluent 3D avatar animation, the provided apparatus and methods can then apply Landmark Smoothing via Kalman Filter to stabilize the facial landmark movement across successive frames. Next, the provided apparatus and methods can generate 3D facial animation from the stabilized landmarks using a FLAME (Faces Learned with an Articulated Model and Expressions) model. The generated sequence of fitted head models can then be used for rendering a 3D facial animation that recovers the user's facial movements. [Lui para 0080]
Regarding claim 20 Alcaide teaches claim 16 in addition Alcaide does not teach but Lin teaches further comprising: an identity authenticator component configured to, at least: analyze patterns within the sensor data corresponding to characteristics unique to the user; compare the patterns with stored profile data associated with the user FIG. 28 depicts example confusion matrices of user identification 2800 based upon a single gesture, three gestures, and five gestures. Part (a) of FIG. 28 depicts a confusion matrix for a single gesture, with an overall accuracy of 93.89%. Part (b) of FIG. 28 depicts a confusion matrix for a three gestures, with an overall accuracy of 99.65%. Part (c) of FIG. 28 depicts a confusion matrix for five gestures, with an overall accuracy of 99.80%. As the series of gestures and a soft majority vote method is used, the accuracy of identifying each user increases significantly. These promising results demonstrate capability of the provided systems and methods for user identification. [Lui para 0202]; and generate, based at least in part on the comparison, an authentication result indicating whether the user is authenticated the computer-implemented method can include performing a multi-factor authentication process, where the multi-factor authentication process uses the machine-learning classifier output to authenticate a user. [Lui para 0012]; wherein the at least one ML model is configured to produce the output representation the output of the CNN can describe, using three-dimensional morphable model coefficients, a three-dimensional face mesh. [Lui para 0022] only when the authentication result indicates that the user is authenticated. that biosignals can be used to distinguish between users, authenticate a user, or both, as it is evident that when performing identical gestures, EMG signals of different users displayed distinct patterns, whereas biosignals of the same user remain remarkably consistent. [Lui para 0191]
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT J MICHAUD whose telephone number is (571)270-3981. The examiner can normally be reached 8:30 - 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, Patrick Edouard can be reached on 571-272-7603. 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.
/ROBERT J MICHAUD/Examiner, Art Unit 2622
Prosecution Insights