DETAILED ACTION
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) 2-3, 5-10, 12-13, 15-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Heywood et al. US 11,706,391 hereinafter referred to as Heywood in view of Aquino et al. US 11,282,367 hereinafter referred to as Aquino.
In regards to claim 2, Heywood teaches:
“A system comprising: a storage device configured to store first instructions and second instructions”
Heywood Figure 2 illustrates memory 240 storing various instructions.
“a wearable device configured to process sensor signals to determine a first physiological value for a person”
Heywood column 2 lines 17-19 teaches the sensor data is indicative of at least one of: a respiratory rate of the person or a pulse rate of the person. Heywood column 4 lines 38-41 teaches in various embodiments, wearable device 102 may also capture health data regarding first responder 104, such as a measured pulse rate, temperature, pulse oximetry, respiratory rate, or the like.
“a microphone”
Heywood Figure 2 teaches microphone 226.
“a camera”
Heywood Figure 2 teaches camera 222.
“and a hardware processor configured to execute the second instructions to: receive, from the wearable device, the first physiological value”
Heywood column 10 lines 31-34 teach In various embodiments, respiratory monitor 304b may be configured to assess audio, video, and/or other sensor information in sensor data 312, to estimate the breathing rate of the person with whom the first responder is interacting.
“determine to begin a monitoring process based on the first physiological value; and in response to determining to begin the monitoring process”
Heywood Figure 4 teaches the policy compliance process begins after the sensor data 312 is received. The Examiner interprets that this process is therefore in response to receiving the sensor data 312. The various process that are performed are based on the physiological values that are received. For example, Heywood column 11 lines 7-11 teach Notably, if the person is being held in a headlock, their respiratory rate begins to drop, and they are at or near unconsciousness, this may be a strong indication that distress detection process 247 should generate and send an alert 314. Therefore, if the physiological value of the respiratory rate drop, the process of detecting unconsciousness occurs based on this value.
“receive, from the camera, image data; receive, from the microphone, audio data”
Heywood column 10 lines 31-34 teach respiratory monitor 304b may be configured to assess audio, video, and/or other sensor information in sensor data 312, to estimate the breathing rate of the person with whom the first responder is interacting
“invoke, on the [processor], a first unconscious detection model based on the image data, wherein the first unconscious detection model outputs a first classification result”
Heywood column 44-51 teaches health analyzer 304 may also include an unconsciousness detector 304c that is configured to identify when the person with whom the first responder is interacting is unconscious. To do so, unconsciousness detector 304c may apply any number of image classifiers to video data in sensor data 312, to apply classification labels to the images, such as “unresponsive,” “seizing,” “fainting,” “normal,” or the like.
“invoke, on the [processor], a second unconscious detection model based on the audio data, wherein the second unconscious detection model outputs a second classification result”
In another embodiment, unconsciousness detector 304c may also take as input other sensor data 312, such as audio data, temperature measurements, or the like, to enhance the accuracy of its classifications. For instance, a sudden stop or change in the utterances by the person interacting with the first responder, coupled with an image of the person falling to the ground, may be a strong indication that the person has become unconscious or worse. The Examiner interprets that the enhanced accuracy of a classification results is a second classification result.
“detect a potential state of unconsciousness based on the first classification result and the second classification result”
Heywood column 10 lines 44-58 teach health analyzer 304 may also include an unconsciousness detector 304c that is configured to identify when the person with whom the first responder is interacting is unconscious. To do so, unconsciousness detector 304c may apply any number of image classifiers to video data in sensor data 312, to apply classification labels to the images, such as “unresponsive,” “seizing,” “fainting,” “normal,” or the like. In another embodiment, unconsciousness detector 304c may also take as input other sensor data 312, such as audio data, temperature measurements, or the like, to enhance the accuracy of its classifications. For instance, a sudden stop or change in the utterances by the person interacting with the first responder, coupled with an image of the person falling to the ground, may be a strong indication that the person has become unconscious or worse.
“and in response to detecting the potential state of unconsciousness, provide an alert”
Heywood column 11 lines 7-11 teach Notably, if the person is being held in a headlock, their respiratory rate begins to drop, and they are at or near unconsciousness, this may be a strong indication that distress detection process 247 should generate and send an alert 314. Heywood does not explicitly teach:
“a hardware accelerator configured to execute the first instructions” and “hardware accelerator”
Barash teaches in paragraph [0036] sensing applications range from detecting movement sensing, counting people, and medical applications such as breathing rate, heartbeat, sleep state tracking, presence, and fall detection, etc. Barash also teaches in paragraph [0028] one or more processors of digital signal processor 208 may offload certain processing tasks to these dedicated hardware circuits, which are known as hardware accelerators. Exemplary hardware accelerators can include Fast Fourier Transform (FFT) circuits and encoder/decoder circuits. In some aspects, the processor and hardware accelerator components of digital signal processor 208 may be realized as a coupled integrated circuit. The use of a hardware accelerator would be considered a routine implementation by those of ordinary skill in the art. Its use would be an engineering design choice based on cost and system requirements. This feature is merely a combination of familiar elements (hardware accelerators) using known methods (unconscious detection) and does not provide any unpredictable results in that it merely results in performing the same functionality as provided for in Aquino using a single or multiple processors. It has been held that "[t]he combination of familiar elements according to known methods is likely to be obvious when it does not more than yield predictable results." KSR., 127 S. Ct. at 1739, 82 USPQ2d at 1395 (2007) (Citing Graham, 383 U.S. at 12).
In regards to claim 3, Heywood teaches all the limitations of claim 2 and further teaches:
“wherein the wearable device comprises a pulse oximetry sensor and the first physiological value is for blood oxygen saturation”
Heywood column 4 lines 38041 teach In various embodiments, wearable device 102 may also capture health data regarding first responder 104, such as a measured pulse rate, temperature, pulse oximetry, respiratory rate, or the like. The Examiner interprets that pulse oximetry is used to measure blood oxygen saturation therefore a teach of measuring pulse oximetry is a teaching of measuring blood oxygen saturation.
In regards to claim 5, Heywood teaches all the limitations of claim 2 and further teaches:
“wherein the wearable device comprises a respiration rate sensor and the first physiological value is for respiration rate”
Heywood column 4 lines 38041 teach In various embodiments, wearable device 102 may also capture health data regarding first responder 104, such as a measured pulse rate, temperature, pulse oximetry, respiratory rate, or the like.
In regards to claim 6, Heywood teaches all the limitations of claim 5 and further teaches:
“wherein determining to begin the monitoring process based on the first physiological value further comprises determining that the first physiological value satisfies a threshold alarm level”
Heywood column 11 lines 7-11 teach Notably, if the person is being held in a headlock, their respiratory rate begins to drop, and they are at or near unconsciousness, this may be a strong indication that distress detection process 247 should generate and send an alert 314. The Examiner interprets that the point at which an alert is generated is equivalent to a threshold alarm level.
In regards to claim 7, Heywood teaches all the limitations of claim 2 and further teaches:
“wherein the wearable device comprises a heart rate sensor and the first physiological value is for heart rate”
Heywood column 10 lines 18-20 teach during execution, RPPG module 304a may assess image/video data captured in sensor data 312, to determine a heart/pulse rate
In regards to claim 8, Heywood teaches all the limitations of claim 7 and further teaches:
“wherein determining to begin the monitoring process based on the first physiological value further comprises: receiving, from the wearable device, a plurality of physiological values measuring heart rate over time; and determining that the plurality of physiological values and the first physiological value satisfies a threshold alarm level”
Heywood teaches in column 13 lines 10-19 if the heart rate determined by RPPG module 304a or respiratory rate determined by respiratory monitor 304b is trending downward, the prediction model may predict that the person is about to lose consciousness or experience some other form of medical distress. Likewise, the combination of position analyzer 306a labeling the video data as “chokehold” in combination with a trend downward from respiratory monitor 304b may lead the prediction model of alert generator 308 to predict that medical distress is likely to occur in the near future. The Examiner interprets that “trending” requires a first value measured and a plurality of values measured after the first value to define the trend.
In regards to claim 9, Heywood teaches all the limitations of claim 2 and further teaches:
“wherein the first or second unconscious detection model is a neural network”
Heywood column 7 lines 23-33 teach distress detection process 247, policy compliance process 248, and/or interaction evaluation process 249 may use machine learning to perform the analysis of captured sensor data. Generally, machine learning refers to any form of programmatic technique that can adapt to new forms of input data and produce a corresponding output. For example, in the context of analyzing captured images in a video feed, a machine learning-based process may be able to identify specific conditions, such as a person in medical distress, even though the process was not explicitly programmed to analyze that specific image. Heywood column 10 lines 47-51 teaches To do so, unconsciousness detector 304c may apply any number of image classifiers to video data in sensor data 312, to apply classification labels to the images, such as “unresponsive,” “seizing,” “fainting,” “normal,” or the like.
In regards to claim 10, Heywood teaches all the limitations of claim 9 and further teaches:
“wherein the neural network is trained with consciousness class labels and unconscious class labels”
Heywood column 10 lines 47-51 teaches To do so, unconsciousness detector 304c may apply any number of image classifiers to video data in sensor data 312, to apply classification labels to the images, such as “unresponsive,” “seizing,” “fainting,” “normal,” or the like.
In regards to claim 12, Heywood teaches all the limitations of claim 2 and claim 12 contains similar limitations. Therefore claim 12 is rejected for similar reasoning.
In regards to claim 13, Heywood teaches all the limitations of claim 12 and claim 13 contains similar limitations as in claim 3. Therefore claim 13 is rejected for similar reasoning as applied to claim 3.
In regards to claim 15, Heywood teaches all the limitations of claim 12 and claim 15 contains similar limitations as in claim 5. Therefore claim 15 is rejected for similar reasoning as applied to claim 5.
In regards to claim 16, Heywood teaches all the limitations of claim 15 and claim 16 contains similar limitations as in claim 6. Therefore claim 16 is rejected for similar reasoning as applied to claim 6.
In regards to claim 17, Heywood teaches all the limitations of claim 12 and claim 17 contains similar limitations as in claim 7. Therefore claim 17 is rejected for similar reasoning as applied to claim 7.
In regards to claim 18, Heywood teaches all the limitations of claim 17 and claim 18 contains similar limitations as in claim 8. Therefore claim 18 is rejected for similar reasoning as applied to claim 8.
In regards to claim 19, Heywood teaches all the limitations of claim 12 and claim 19 contains similar limitations as in claim 9. Therefore claim 19 is rejected for similar reasoning as applied to claim 9.
In regards to claim 20, Heywood teaches all the limitations of claim 19 and claim 20 contains similar limitations as in claim 10. Therefore claim 20 is rejected for similar reasoning as applied to claim 10.
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) 4 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Heywood/Aquino in view of Ahmed et al. US 2021/0290184 hereinafter referred to as Ahmed.
In regards to claim 4, Heywood/Aquino teaches all the limitations of claim 2 and further teaches:
“wherein determining to begin the monitoring process based on the first physiological value further comprises determining that the first physiological value is below a threshold level”
Ahmed paragraph [0026] teaches a wearable device worn by the user configured to communicate with the one or more sensors and to process information responsive to output from the one or more sensors. Ahmed paragraph [0262] teaches if the patient's respiratory rate falls below a certain threshold (which can indicate that a patient is having difficulty breathing), the patient's blood oxygen saturation is below a threshold, the patient's temperature is higher than a certain threshold (which can indicate that a patient might have an infection), and/or blood pressure is above a certain threshold, the system 110 may generate and send a notification (or an alert) to a care provider, an emergency contact, and/or to the patient user computing device 102. It would have been obvious for a person with ordinary skill in the art before the invention was effectively filed to have modified Heywood/Aquino in view of Ahmed to have included the features of ““wherein determining to begin the monitoring process based on the first physiological value further comprises determining that the first physiological value is below a threshold level” for allowing patients to receive care while reducing the risk of being infected from or infecting other patients, and/or the risk of infecting the care providers (Ahmed [0007]).
In regards to claim 14, Heywood/Aquino teaches all the limitations of claim 13 and claim 14 contains similar limitations as in claim 4. Therefore claim 14 is rejected for similar reasoning as applied to claim 4.
Claim(s) 11 and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Heywood/Aquino in view of Heng et al. US 2022/0067940 hereinafter referred to as Heng.
In regards to claim 11, Heywood/Aquino teaches all the limitations of claim 10 and further teaches:
“wherein the neural network is configured to go through a series of epochs during training, resulting in further adjusting of neural network weights”
This is a routine implementation in training a neural network. Heng teaches in paragraph [0018] One iteration of the training process or an epoch is complete when the weight values of each layer have been adjusted for the full training input data set. The next iteration of the training process can then be performed with the updated weights, and the training process can be repeated for a number of epochs until a loss objective is achieved, such as minimizing the error or until the error lowers to a certain threshold. It would have been obvious for a person with ordinary skill in the art before the invention was effectively filed to have modified Heywood/Aquino in view of Heng to have included the features of “wherein the neural network is configured to go through a series of epochs during training, resulting in further adjusting of neural network weights” for minimizing the error or until the error lowers to a certain threshold (Heng [0018]).
In regards to claim 21, Heywood/Aquino teaches all the limitations of claim 20 and claim 21 contains similar limitations as in claim 11. Therefore claim 21 is rejected for similar reasoning as applied to claim 11.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL E TEITELBAUM, Ph.D. whose telephone number is (571)270-5996. The examiner can normally be reached 8:30AM-5:00PM EST.
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, John Miller can be reached at 571-272-7353. 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.
/MICHAEL E TEITELBAUM, Ph.D./Primary Examiner, Art Unit 2422