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 .
All amendments to the claims as filed on 12/22/2025 have been entered and the action follows:
Response to Arguments
Applicant’s arguments with respect to claim(s) have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Examiner Note
Upon further consideration and search a new art was found for the amended claim 1 with limitations of claim 7 added. And therefore, the first non-final action (9/29/2025) is vacated and a new non-final is issued.
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.
Claims 1, 3-5, 8-9, 11, 13-15 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Goncharov et al (WO 2021/202276) in view of Seed: Sound event early detection via evidential uncertainty, by Zhao et al (IDS document) and Liu (US Pub. 2024/0046644).
With respect to claim 1, Goncharov discloses A computer-implemented method for event detection, comprising:
training a joint neural network model and an output layer 630 to train the machine learning model(s) or model …determined abnormal event from a captured input data, e.g., audio data, video data …), as claimed.
However, Goncharov fails to explicitly disclose with respective neural networks for audio data and video data relating to a same scene, wherein the joint neural network model is configured to output a belief value, a disbelief value, and an uncertainty value; and determining that an event has occurred based on determining that the belief value is greater than the disbelief value and that the uncertainty value is below a threshold value, (emphasis added), as claimed.
Zhao discloses wherein the joint neural network model is configured to output a belief value, a disbelief value, and an uncertainty value; and determining that an event has occurred based on determining that the belief value is greater than the disbelief value and that the uncertainty value is below a threshold value, (emphasis added, see figure 2, a model outputting three values as belief, disbelief and uncertainty; and in section 2.2 equation (6), gives the outcome as the event occurred if the values of belief is greater than disbelief and the uncertainty value is below a threshold), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the two references as they are analogous because they are solving similar problem of event detection using image analysis. Teaching of Zhao of training a model can be incorporated into Goncharov’s system as suggested in figure 1 numerical 140 machine model, for suggestion, and modifying the system yields a uncertainty aware event prediction, for motivation.
Also, Liu teaches training a joint neural network model with respective neural networks for audio data and video data relating to a same scene, (emphasis added, see figure 1, video and audio inputs are going to their respective neural networks for processing) as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of processing audio and video signals. Teaching of Liu to process audio and video signals can be incorporated into Goncharov and Zhao system as suggested in figure 1 numerical 140 machine model of Goncharov, for suggestion, and modifying the system yields the predictive results as claimed for classification (see Liu Abstract), for suggestion.
With respect to claim 3, combination of Goncharov, Zhao and Liu further discloses collecting operational data of a system that includes audio and video data streams from the same scene, (see Goncharov paragraph 0029, wherein …Referring now to Figure 3, the monitoring data reveals that individual 120 has fallen on the floor…), as claimed.
With respect to claim 4, combination of Goncharov, Zhao and Liu further discloses wherein detecting that the event has occurred includes inputting the audio and video data streams to the respective neural networks of the joint neural network model, (see Liu figure 1, video and audio inputs are going to their respective neural networks for processing), as claimed.
With respect to claim 5, combination of Goncharov, Zhao and Liu further discloses wherein the audio and video data streams are collected from a same location at a same time, (see Goncharov paragraph 0029, wherein …Referring now to Figure 3, the monitoring data reveals that individual 120 has fallen on the floor…), as claimed.
With respect to claim 8, combination of Goncharov, Zhao and Liu further discloses wherein the belief value, the disbelief value, and the uncertainty value sum to 1, (see Zhao section 2.1 first paragraph, wherein, …we have the property b + d + u = 1…), as claimed.
With respect to claim 9, combination of Goncharov, Zhao and Liu further discloses collecting new audio and video data from a new scene, wherein determining that the event has occurred includes inputting the new audio and video data to the trained joint neural network model, (see Goncharov paragraph 0043, wherein …step 710, a data stream, e.g., video stream, audio stream, infrared data, etc., from an input device at a monitored location is received, as described above…), as claimed.
Claims 11, 13-15 and 18-19 are rejected for the same reasons as set forth in the rejections of claims 1, 3-5 and 8-9, because claims 11, 13-15 and 18-19 are claiming subject matter of similar scope as claimed in claims 1, 3-5 and 8-9.
Claims 2 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Goncharov et al (WO 2021/202276) in view of Seed: Sound event early detection via evidential uncertainty, by Zhao et al (IDS document) and Liu (US Pub. 2024/0046644) as applied to claim 1 above, and further in view of Qi et al (CN 111443328 A).
With respect to claim 2, combination of Goncharov, Zhao and Liu discloses all the elements as claimed and as rejected in claim 1 above. Furthermore, combination of Goncharov, Zhao and Liu discloses a first network architecture that includes a transformer for video data, (see Liu paragraph 0049, wherein … In one embodiment, the video classification system also includes a BERT (Bidirectional Encoder Representation from Transformers) network and a comprehensive prediction unit), as claimed.
However, combination of Goncharov, Zhao and Liu fails to explicitly disclose network architecture that includes a convolutional neural network (CNN) and a recurrent neural network (RNN) for audio data, as claimed.
Qi teaches network architecture that includes a convolutional neural network (CNN) and a recurrent neural network (RNN) for audio data, (see background second paragraph, wherein Sound detection and location (sound event location and detection) is a combination task that determines each active sound event and estimates their respective spatial positions. 2017 years Sharath adavanne et al. using RNN (cyclic neural network) and CNN combined to CRNN (convolutional cyclic neural network) to realize DOA estimation, the neural network based on CRNN the multi-channel audio as input), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of processing signals for event detection. Teaching of Qi to process signals using a neural network architecture that includes CNN and RNN can be incorporated into Goncharov, Zhao and Lui system as suggested in figure 1 numerical 140 machine model of Goncharov, for suggestion, and modifying the system yields the predictive results as claimed for event detection (see Qi Abstract), for suggestion.
Claim 12 is rejected for the same reasons as set forth in the rejections of claim 2, because claim 12 is claiming subject matter of similar scope as claimed in claim 2.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Goncharov et al (WO 2021/202276) in view of Seed: Sound event early detection via evidential uncertainty, by Zhao et al (IDS document) and Liu (US Pub. 2024/0046644) as applied to claim 1 above, and further in view of Pardeshi et al (US Pub. 2021/0334645).
With respect to claim 6, combination of Goncharov, Zhao and Liu discloses all the elements as claimed and as rejected in claim 1 above.
However, combination of Goncharov, Zhao and Liu fails to explicitly disclose wherein training the joint neural network model includes minimizing a loss function that includes respective cross-entropy losses for the different data types, as claimed.
Pardeshi teaches training the joint neural network model includes minimizing a loss function that includes respective cross-entropy losses for the different data types, (see paragraph 0059, wherein …one embodiment, an auto-encoder trained …to detect “abnormal” events …as well as training this auto-encoder using a binary cross-entropy loss calculated for an output of this discriminator…), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of processing signals for event detection. Teaching of Pardeshi to use a cross entropy for training a machine learning model can be incorporated into Goncharov, Zhao and Lui system as suggested in figure 1 numerical 140 machine model of Goncharov, for suggestion, and modifying the system yields the predictive results as claimed for event detection (see Pardeshi paragraph 0059), for suggestion.
Claim 16 is rejected for the same reasons as set forth in the rejections of claim 6, because claim 16 is claiming subject matter of similar scope as claimed in claim 6.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Goncharov et al (WO 2021/202276) in view of Seed: Sound event early detection via evidential uncertainty, by Zhao et al (IDS document) and Liu (US Pub. 2024/0046644) as applied to claim 1 above, and further in view of Majumdar et al (US Pub. 2014/0100835).
With respect to claim 10, combination of Goncharov, Zhao and Liu discloses all the elements as claimed and as rejected in claim 1 above.
However, combination of Goncharov, Zhao and Liu fails to explicitly disclose performing an action responsive to the event, selected from the group consisting of changing a security setting for an application or hardware component, changing an operational parameter of an application or hardware component, halting an application, restarting an application, halting a hardware component, rebooting a hardware component, changing an environmental condition, and changing a network interface’s status or settings, as claimed.
Majumdar teaches performing an action responsive to the event, selected from the group consisting of changing a security setting for an application or hardware component, changing an operational parameter of an application or hardware component, halting an application, restarting an application, halting a hardware component, rebooting a hardware component, changing an environmental condition, and changing a network interface’s status or settings, (see paragraph 0033, wherein …for example, the action may include a contextual power management scheme, during which the device (1) disables, closes, deactivates, and/or powers-down certain software or hardware applications…), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of processing signals for event detection. Teaching of Majumdar to perform an action can be incorporated into Goncharov, Zhao and Lui system as suggested in figure 7 numerical 780 …data associated with user actions in response…, of Goncharov, for suggestion, and modifying the system yields the predictive results as claimed for modeling user behavior (see Majumdar Abstract), for suggestion.
Claim 20 is rejected for the same reasons as set forth in the rejections of claim 10, because claim 20 is claiming subject matter of similar scope as claimed in claim 10.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VIKKRAM BALI whose telephone number is (571)272-7415. The examiner can normally be reached Monday-Friday 7:00AM-3:00PM.
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, Gregory Morse can be reached at 571-272-3838. 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.
/VIKKRAM BALI/Primary Examiner, Art Unit 2663