Prosecution Insights
Last updated: November 12, 2026
Application No. 19/446,301

METHOD AND SYSTEM FOR INDUSTRIAL ERGONOMICS RISK ROOT-CAUSE ANALYSIS AND MANAGEMENT USING ARTIFICIAL INTELLIGENCE ORIENTED NATURAL LANGUAGE PROCESSING TECHNIQUES

Final Rejection §103§DOUBLEPATENT
Filed
Jan 12, 2026
Priority
Apr 12, 2023 — continuation of 11/763,235 +3 more
Examiner
BROCKINGTON III, WILLIAM S
Art Unit
3623
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Velocityehs Holdings Inc.
OA Round
2 (Final)
42%
Grant Probability
Moderate
3-4
OA Rounds
98%
With Interview

Examiner Intelligence

Grants 42% of resolved cases
42%
Career Allowance Rate
221 granted / 522 resolved
-9.7% vs TC avg
Strong +56% interview lift
Without
With
+55.7%
Interview Lift
resolved cases with interview
Typical timeline
Avg Prosecution
29 currently pending
Career history
563
Total Applications
across all art units

Office Action

§103 §DOUBLEPATENT
DETAILED ACTION The following is a Final Office Action in response to communications filed September 18, 2026. Claims 9–10 are amended. Claims 1–23 are currently pending. Response to Amendment/Argument Applicant’s Response is sufficient to overcome the previous rejections of claims 9–10 under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention. Accordingly, the previous rejections of claims 9–10 under 35 U.S.C. 112(b) are withdrawn. With respect to the previous rejections of claims 1–23 under 35 U.S.C. 103, Applicant’s remarks have been fully considered but are not persuasive. Applicant first asserts that the rejection of record fails to address using ergonomic risks for the one or more body regions as an input to the second deep learning framework. Examiner disagrees. Examiner submits that the argued claim element is rejected over a combination of references. More particularly, the reference to Baek is asserted as disclosing ergonomic risks for the one or more body regions, and the reference to Mukund is asserted as disclosing the concept of utilizing risks determined in a first learning process as inputs to a second learning process that determines risk root-causes. As a result, Applicant’s remarks are not persuasive because, as stated in MPEP 2145(IV), “[o]ne cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., Inc., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).” As a result, Applicant’s remarks are not persuasive. To the extent that Applicant asserts that the rejection of record does not articulate how combining the references to Baek and Mukund would produce the claimed system, Examiner disagrees. Pages 4–6 of the Non-Final Office Action mailed April 20, 2026 articulate the asserted combination of references by addressing the factual inquiries of Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966). More particularly, the rejection (1) determines the scope and content of the prior art through citations and explanatory text, (2) ascertains the differences between the claimed invention and the prior art by mapping references to claimed limitations, as appropriate, and (3) implicitly resolves the level of ordinary skill in the art through discussion of common elements within the field (See, MPEP 2141). Further, the rejection combines the argued references by (1) finding that the prior art contained a “base” device upon which the claimed invention is an “improvement” (Here, the reference to Baek), (2) finding that the prior art contained a known technique that is applicable to the base device (a two-step learning process for determining risks and determining risk root-causes based on the risks, as disclosed by Mukund), and (3) finding that one of ordinary skill in the art would have recognized that applying the known technique would have yielded predictable results and resulted in an improved system (See, MPEP 2143). As a result, Applicant’s remarks are not persuasive. With respect to claim 22, Applicant notes that the ergonomic risks are determined “upon execution of joint location and angle estimation instructions” and asserts that the combination of references do not disclose the features. Examiner disagrees for the same reasons as stated above. More particularly, the rejection of record asserts the reference to Baek as disclosing the concept of using joint locations and angles to determine ergonomic risks for one or more body regions and asserts the reference to Mukund as disclosing the concept of determining risk root-causes based on previously determined risks. As a result, Applicant’s remarks address the references individually and are not persuasive for the same reasons as stated above. Applicant’s remarks with respect to KSR International Co. v. Teleflex Inc. (KSR), 550 U.S. 398, 82 USPQ2d 1385 (2007) have been fully considered but are not persuasive for the same reasons as stated above. However, to the extent that Applicant submits that the rejection does not explain what problem would have motivated the asserted combination, Examiner notes that the rejection indicates that the reference to Baek does not expressly disclose the claim elements that are taught by the remaining references, including the elements for determining risk root-causes. As a result, Applicant’s remarks are not persuasive. Finally, with respect to claims 3 and 17, Applicant submits that the reference to Baek does not disclose a three-step post-processing method. Examiner notes that Applicant’s remarks do not comply with the requirements set forth under 37 CFR 1.111(b), which states that “[a] general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references does not comply with the requirements of this section.” Here, Applicant’s remarks do not include any arguments or rationale underpinning in support of Applicant’s position. Instead, Applicant alleges, without any supporting argument, that the asserted citations do not disclose the limitations as presented. As a result, Applicant’s remarks are not persuasive. In view of the above, Applicant’s remarks are not persuasive, and the previous rejections under 35 U.S.C. 103 are maintained. Claim Rejections - 35 USC § 103 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 1–23 are rejected under 35 U.S.C. 103 as being unpatentable over BAEK et al. (U.S. 2020/0327465) in view of Mukund et al. (U.S. 2023/0077338), and in further view of Bourret et al. (U.S. 2023/0177228). Claims 1, 13, and 21–23: Baek discloses a computing server system deployed within a Cloud-based communication network (See FIG. 1, FIG. 12, and paragraph 114), the computing server system comprising: a non-transitory computer-readable storage medium storing machine readable instructions (See paragraph 109); and a processor coupled to the non-transitory computer-readable storage medium and configured to execute the machine readable instructions (See paragraph 109) to: receive, from a computing device of a user, video of an individual performing a task (See FIG. 1 and paragraphs 18 and 40–41, wherein video of worker performing tasks is received, and wherein the imaging sensor is a smartphone camera), process the video of the individual performing the task through a first deep learning framework to determine ergonomic risks for one or more body regions of the individual by identifying at least joint locations and joint angles for the one or more body regions, the first deep learning framework configured to use the joint locations and the joint angles for the one or more body regions to determine the ergonomic risks for the one or more body regions of the individual (See paragraphs 18 and 42–43, in view of paragraph 58, wherein an ergonomic risk assessment based on the processed video is performed using deep machine learning algorithms, and wherein the assessment is generated based on joint positions and angles of a plurality of body regions; see also paragraph 44), determine ergonomic risk control recommendations to mitigate the ergonomic risks (See paragraphs 17–18, wherein a recommended course of action and an assessment report is provided to address identified risks), and transmit, to the computing device, information indicative of the ergonomic risk control recommendations and the ergonomic risk (See paragraphs 17–18, in view of FIG. 12, wherein a recommended course of action output is provided to address identified risks; see also paragraph 132). Although Baek implicitly discloses determining ergonomic root-causes (See paragraphs 40 and 42, wherein metrics identify risk exposure for current activities), Baek does not expressly disclose the remaining claim elements. Mukund discloses functionality to process the information of the event through a first learning framework to determine risks (See FIG. 4 and paragraphs 45–46 and 49–50, in view of paragraphs 31–32, wherein incident descriptions are analyzed and pre-processed for subsequent analysis using NLP/analytic functions, and wherein analytic functions include expert, NLP, and AI functions); and process at least some of the risks through a second learning framework to determine root-causes, the second deep learning framework including an expert or knowledge-based diagnostic or evaluation system that relates the risks to the root-causes (See paragraphs 58–59, wherein subsequent to the initial processing, the incident dataset is processed using an expert function in combination with an AI/machine learning framework to identify causes of incident using risk factors associated with the incident). Baek discloses a system directed to analyzing and mitigating workplace injuries. Mukund discloses a system directed to processing incident data to analyze risks. Each reference discloses a system directed to assessing risks. The technique of first and second framework processing is applicable to the system of Baek as they each share characteristics and capabilities; namely, they are directed to assessing risks. One of ordinary skill in the art would have recognized that applying the known technique of Mukund would have yielded predictable results and resulted in an improved system. It would have been recognized that applying the technique of Mukund to the teachings of Baek would have yielded predictable results because the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate risk assessments into similar systems. Further, applying first and second framework processing to Baek would have been recognized by those of ordinary skill in the art as resulting in an improved system that would allow more detailed analysis and more reliable results. Baek and Mukund do not expressly disclose the remaining claim elements. Bourret discloses functionality to determine ergonomic risk control recommendations to mitigate the ergonomic root-causes from a database of possible ergonomic risk control recommendations (See FIG. 9–10 and paragraph 45, in view of FIG. 11, wherein a risk control suggestion is determined by searching a mapping between risk types, risk locations, and suggestions; see also paragraphs 68–69). As disclosed above, Baek discloses a system directed to analyzing and mitigating workplace injuries, and Mukund discloses a system directed to processing incident data to analyze risks. Bourret discloses a system directed to assessing ergonomic risks. Each reference discloses a system directed to assessing risks. The technique of utilizing a risk control database is applicable to the systems of Baek and Mukund as they each share characteristics and capabilities; namely, they are directed to assessing risks. One of ordinary skill in the art would have recognized that applying the known technique of Bourret would have yielded predictable results and resulted in an improved system. It would have been recognized that applying the technique of Bourret to the teachings of Baek and Mukund would have yielded predictable results because the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate risk assessments into similar systems. Further, applying a risk control database to Baek and Mukund would have been recognized by those of ordinary skill in the art as resulting in an improved system that would allow more detailed analysis and more reliable results. Claims 2 and 14: Baek discloses the computing server system of Claim 1, wherein the first deep learning framework is configured to: process the video to determine the joint locations of the individual (See paragraph 42, wherein the image data is processed to determine joint positions and angles); calculate the joint angles for each of a plurality of body regions of the individual based on the joint locations (See paragraph 42, wherein the image data is processed to determine joint positions and angles, and FIG. 7 and paragraph 58, wherein joint positions and angles are determined for each body region); calculate, based at least upon the joint angles and forces being exerted during the task, a risk score for each of the plurality of body regions of the individual in each of a plurality of risk categories (See paragraphs 42 and 45, in view of paragraph 58, wherein ergonomic metrics are determined for each of the plurality of body regions, and wherein ergonomic metrics are risk scores); and calculate a risk rating for each of the plurality of body regions of the individual based on the risk score for each of the plurality of body regions of the individual in each of the plurality of risk categories (See paragraphs 42–43, in view of FIG. 10, wherein a risk assessment is derived from the ergonomic metrics, and wherein risks are identified with respect to each body region), wherein the deep learning framework is configured to determine the ergonomic risk for each of the plurality of body regions of the individual based at least upon the risk rating (See paragraphs 42–43, in view of FIG. 10, wherein the risk assessment derived from the ergonomic metrics defines the ergonomic risk, and wherein risks are identified with respect to each body region). Baek does not expressly disclose the remaining claim elements. Mukund discloses wherein the second deep learning framework is configured to determine the root-causes of the individual based at least upon the risk (See paragraphs 58–59, wherein subsequent to the initial processing, the incident dataset is processed using an expert function in combination with an AI/machine learning framework to identify causes of incident using risk factors associated with the incident). One of ordinary skill in the art would have recognized that applying the known technique of Mukund would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1. Claims 3 and 17: Baek discloses the computing server system of Claim 2, wherein the first deep learning framework is configured to determine the joint locations of the individual when a view of the joint locations is at least partially blocked in at least one video frame of the video by: determining positions between each of the joint locations from some of the video; detecting video frames from the video where at least one joint location has a confidence value related to blocked viewability; and interpolating a position of the at least one joint location based on an angle and a distance of the at least one joint location from a parent joint (See paragraphs 94 and 89, in view of paragraphs 42 and 81-82, wherein hidden layer outputs are produced in a 3D pose estimation process using joint angles and positions and a degree of body point associations; see also FIG. 7 and paragraph 58). Claims 4 and 18: Baek discloses the computing server system of Claim 2, wherein the first deep learning framework is configured to use a convolutional neural network (“CNN”) to determine the joint locations of the individual (See paragraphs 51–52 and 88, wherein joint positions are determined using a CNN; see also FIG. 7 and paragraphs 57–58). Claim 5: Baek discloses the computing server system of Claim 2, wherein the plurality of body regions includes a neck region, a back region, a hand/wrist region, a shoulder region including a left shoulder and a right shoulder, an elbow region including a left elbow and a right elbow, and a leg region including a left knee and a right knee (See paragraph 58, wherein “the following joints and landmarks may be tracked: left hip; right hip; chest; neck; left shoulder; right shoulder; left elbow; right elbow; left wrist; right wrist; left knee; right knee; left ankle; right ankle; nose; left ear; right ear; left eye; and right eye”). Claims 6 and 16: Baek discloses the computing server system of Claim 2, wherein the plurality of risk categories includes an awkward posture category, a duration category, a frequency category, and a force category (See paragraph 42, wherein ergonomic metrics include posture, duration, repetition, and force). Claims 7 and 15: Baek discloses the computing server system of Claim 6, wherein the first deep learning framework is configured to calculate the risk score by comparing the joint angles with a plurality of threshold values determined for each body region in each risk category (See paragraphs 42–43, in view of paragraphs 96–97, wherein body region assessment scores are determined by comparing monitored joint postures to thresholds). Claim 8: Baek discloses the computing server system of Claim 7, wherein the first deep learning framework is configured to determine a first portion of the plurality of threshold values for each body region in the awkward posture category based upon a range of motion for a body joint, wherein the joint angles near an upper limit of the range of motion are determined to have higher risks (See paragraphs 42–43, in view of paragraphs 96–97, wherein body region assessment scores are determined by comparing monitored joint postures to neutral posture thresholds, and wherein risk implicitly increases when joint postures exceed neutral posture thresholds). Claim 9: Baek discloses the computing server system of Claim 7, wherein the first deep learning framework is configured to: determine a second portion of the plurality of threshold values for each body region in the duration category; determine a percentage of time of the one or more body regions maintained in an identified posture based on a frame-by-frame analysis of the video; and compare the percentage of time of the one or more body regions with the second portion of the plurality of threshold values (See paragraphs 40 and 42–43, in view of paragraphs 96–97, wherein body region assessment scores are determined according to extreme posture duration proportions derived from the joint time series data; see also paragraph 51, wherein frame-by-frame analysis is performed). Claim 10: Baek discloses the computing server system of Claim 7, wherein the first deep learning framework is configured to: determine a third portion of the plurality of threshold values for each body region in the frequency category; identify a frequency of occurrence of the one or more body regions during a selected period of time based on the video; and compare the frequency of occurrence with the third portion of the plurality of threshold values (See paragraph 11, wherein posture exposure event frequency is disclosed; see also paragraphs 96–97, wherein a number of posture events are tracked within the time series data, and paragraph 40, wherein repetitions are monitored). Claims 11 and 19: Baek discloses the computing server system of Claim 1, further comprising a database that relates ergonomic risk control recommendation to corresponding ergonomic risk (See paragraph 101, in view of paragraphs 17–18, wherein worker profiles are stored in a database, and wherein assessments are performed with respect to each worker), wherein the processor is configured to: receive the ergonomic root-causes from the deep learning framework (See paragraphs 17–18 and 42, wherein ergonomic risks are identified using a deep machine learning algorithm), and determine the ergonomic risk control recommendations that match the ergonomic risk (See paragraphs 17–18, wherein a recommended course of action and an assessment report is provided to address identified risks). Baek does not expressly disclose the remaining claim elements. Mukund discloses functionality to receive the root-causes from the second deep learning framework (See paragraphs 58–59, wherein subsequent to the initial processing, the incident dataset is processed using an expert function in combination with an AI/machine learning framework to identify causes of incident using risk factors associated with the incident). One of ordinary skill in the art would have recognized that applying the known technique of Mukund would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1. Baek and Mukund do not expressly disclose the remaining claim elements. Bourret discloses a database of controls that relates each ergonomic risk control recommendation to corresponding ergonomic risk root-causes (See FIG. 9–10 and paragraph 45, in view of FIG. 11, wherein a risk control suggestion is determined by searching a mapping between risk types, risk locations, and suggestions; see also paragraphs 68–69), and determine the ergonomic risk control recommendations in the database of controls that match the ergonomic root-causes (See FIG. 9–10 and paragraph 45, in view of FIG. 11, wherein a risk control suggestion is determined by searching a mapping between risk types, risk locations, and suggestions; see also paragraphs 68–69). One of ordinary skill in the art would have recognized that applying the known technique of Bourret would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1. Claims 12 and 20: Baek discloses the computing server system of Claim 1, wherein the information indicative of the ergonomic risk control recommendations includes at least one of text, audio, video, or other rich media explanations (See FIG. 10 and paragraphs 17–18, wherein corrective action and suggestion outputs and reports are disclosed; see also paragraph 132). Double Patenting The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969). A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b). The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13. The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer. Claims 1–4, 6, 11–14, and 16–23 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 4–7, 9–11, 14–17, and 19–20 of U.S. Patent No. 12,524,724. Although the claims at issue are not identical, they are not patentably distinct from each other because claims 1, 4–7, 9–11, 14–17, and 19–20 of U.S. Patent No. 12,524,724 anticipate every element of pending claims 1–4, 6, 11–14, and 16–23. More particularly, claims 1 and 11 of U.S. Patent No. 12,524,724 disclose every element of pending claims 1, 13, and 21–23; claims 4 and 14 of U.S. Patent No. 12,524,724 disclose every element of pending claims 2 and 14; claims 6 and 16 of U.S. Patent No. 12,524,724 disclose every element of pending claims 3 and 17; claims 7 and 17 of U.S. Patent No. 12,524,724 disclose every element of pending claims 4 and 18; claims 5 and 15 of U.S. Patent No. 12,524,724 disclose every element of pending claims 6 and 16; claims 9 and 19 disclose every element of pending claims 11 and 19; and claims 10 and 20 of U.S. Patent No. 12,524,724 disclose every element of pending claims 12 and 20. Accordingly, claims 1, 4–7, 9–11, 14–17, and 19–20 of U.S. Patent No. 12,524,724 anticipate every element of pending claims 1–4, 6, 11–14, and 16–20. Claims 5, 7–10, and 15 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 4–5, 11, and 14 of U.S. Patent No. 12,524,724 in view of BAEK et al. (U.S. 2020/0327465). Claim 5: As noted above, claim 1 of U.S. Patent No. 12,524,724 discloses every element of pending claim 1, and claim 4 of U.S. Patent No. 12,524,724 discloses every element of pending claim 2. U.S. Patent No. 12,524,724 does not, however, disclose the elements of claim 5. Baek discloses wherein the plurality of body regions includes a neck region, a back region, a hand/wrist region, a shoulder region including a left shoulder and a right shoulder, an elbow region including a left elbow and a right elbow, and a leg region including a left knee and a right knee (See paragraph 58, wherein “the following joints and landmarks may be tracked: left hip; right hip; chest; neck; left shoulder; right shoulder; left elbow; right elbow; left wrist; right wrist; left knee; right knee; left ankle; right ankle; nose; left ear; right ear; left eye; and right eye”). U.S. Patent No. 12,524,724 discloses a system directed to analyzing video and textual information to identify ergonomic risks and risk root-causes. Baek discloses a system directed to analyzing and mitigating workplace injuries. Each reference discloses a system directed to assessing ergonomic risks. The technique of identifying the claimed body regions is applicable to the system of U.S. Patent No. 12,524,724as they each share characteristics and capabilities; namely, they are directed to assessing ergonomic risks. One of ordinary skill in the art would have recognized that applying the known technique of Baek would have yielded predictable results and resulted in an improved system. It would have been recognized that applying the technique of Baek to the teachings of U.S. Patent No. 12,524,724would have yielded predictable results because the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate ergonomic risk assessments into similar systems. Further, applying body region identifications to U.S. Patent No. 12,524,724would have been recognized by those of ordinary skill in the art as resulting in an improved system that would allow more detailed analysis and more reliable results. Claims 7 and 15: As noted above, claims 1 and 11 of U.S. Patent No. 12,524,724 disclose every element of pending claims 1 and 13, claims 4 and 14 of U.S. Patent No. 12,524,724 disclose every element of pending claims 2 and 14, and claims 5 and 15 of U.S. Patent No. 12,524,724 disclose every element of pending claims 6 and 16. U.S. Patent No. 12,524,724 does not, however, disclose the elements of claims 7 and 15. Baek discloses wherein the first deep learning framework is configured to calculate the risk score by comparing the joint angles with a plurality of threshold values determined for each body region in each risk category (See paragraphs 42–43, in view of paragraphs 96–97, wherein body region assessment scores are determined by comparing monitored joint postures to thresholds). One of ordinary skill in the art would have recognized that applying the known technique of Baek would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 5. Claim 8: U.S. Patent No. 12,524,724 does not expressly disclose the elements of claim 8. Baek discloses wherein the first deep learning framework is configured to determine a first portion of the plurality of threshold values for each body region in the awkward posture category based upon a range of motion for a body joint, wherein the joint angles near an upper limit of the range of motion are determined to have higher risks (See paragraphs 42–43, in view of paragraphs 96–97, wherein body region assessment scores are determined by comparing monitored joint postures to neutral posture thresholds, and wherein risk implicitly increases when joint postures exceed neutral posture thresholds). One of ordinary skill in the art would have recognized that applying the known technique of Baek would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 5. Claim 9: U.S. Patent No. 12,524,724 does not expressly disclose the elements of claim 9. Baek discloses wherein the first deep learning framework is configured to: determine a second portion of the plurality of threshold values for each body region in the duration category; determine a percentage of time of one or more body regions maintained in an identified posture based on a frame-by-frame analysis of the video; and compare the percentage of time of the one or more body regions with the second portion of the plurality of threshold values (See paragraphs 40 and 42–43, in view of paragraphs 96–97, wherein body region assessment scores are determined according to extreme posture duration proportions derived from the joint time series data; see also paragraph 51, wherein frame-by-frame analysis is performed). One of ordinary skill in the art would have recognized that applying the known technique of Baek would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 5. Claim 10: U.S. Patent No. 12,524,724 does not expressly disclose the elements of claim 10. Baek discloses wherein the first deep learning framework is configured to: determine a third portion of the plurality of threshold values for each body region in the frequency category; identify a frequency of occurrence of one or more body regions during a selected period of time based on the video; and compare the frequency of occurrence with the third portion of the plurality of threshold values (See paragraph 11, wherein posture exposure event frequency is disclosed; see also paragraphs 96–97, wherein a number of posture events are tracked within the time series data, and paragraph 40, wherein repetitions are monitored). One of ordinary skill in the art would have recognized that applying the known technique of Baek would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 5. Conclusion THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM S BROCKINGTON III whose telephone number is (571)270-3400. The examiner can normally be reached M-F, 8am-5pm, 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, Rutao Wu can be reached at 571-272-6045. 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. /WILLIAM S BROCKINGTON III/Primary Examiner, Art Unit 3623
Read full office action

Prosecution Timeline

Jan 12, 2026
Application Filed
Apr 20, 2026
Non-Final Rejection mailed — §103, §DOUBLEPATENT
Sep 18, 2026
Response Filed
Oct 15, 2026
Final Rejection mailed — §103, §DOUBLEPATENT (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12793001
CENTRALIZED MILESTONE RECORDATION FOR ROBOTIC PROCESS AUTOMATION SYSTEMS
3y 1m to grant Granted Nov 10, 2026
Patent 12784066
DYNAMIC ACTION CLASSIFICATION USING MACHINE LEARNING TECHNIQUES
3y 5m to grant Granted Nov 03, 2026
Patent 12775897
SYSTEMS AND METHODS FOR GENERATING DYNAMIC REAL-TIME ANALYSIS OF CARBON CREDITS AND OFFSETS
1y 9m to grant Granted Oct 27, 2026
Patent 12762488
ARRANGING A STORE IN ACCORDANCE WITH DATA ANALYTICS
2y 2m to grant Granted Oct 13, 2026
Patent 12749038
DIGITAL WORKER SKILL OVERLAP MITIGATION
2y 9m to grant Granted Sep 29, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
42%
Grant Probability
98%
With Interview (+55.7%)
Moderate
PTA Risk
Based on 522 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month