CTNF 18/361,915 CTNF 88349 DETAILED ACTION This communication is responsive to the application # 18/361,915 filed on July 31, 2023. Claims 1-21 are pending and are directed toward COMPUTER-IMPLEMENTED METHOD FOR LEARNING MOVEMENT MODEL, NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM AND HUMAN MOVEMENT ANALYZING SYSTEM. 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. 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 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. Claim Rejections - 35 USC § 112 07-30-02 AIA The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claim 21 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Limitation of claim 21 “A human movement analyzing system, comprising: a human movement analyzing system” is a circular definition, and thus indefinite. Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-21-aia AIA Claim s 1-3, 10, 12, 13, 15-18, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (US 2017/0087416, Mar. 30, 2017), in view of Alcock et al. (US 2020/0082212, Mar. 12, 2020), in view of Drouin et al. (Semi-supervised clustering of quaternion time series: Application to gait analysis in multiple sclerosis using motion sensor data, SiM, 2022, 24 pages), hereinafter referred to as Hu, Alcock and Drouin . As per claim 1, Hu teaches a computer-implemented method for learning a movement model of a person ( the gait parameters are estimated and the gait cycles are segmented by examining the changing points of the sensor signals. Hu, [0074] ), the method comprising steps of: obtaining a data stream comprising a time series of measured movement data of the person from at least one sensor ( The thermal imaging device 104 can be configured to capture images of the subject. The thermal imaging device 104 can obtain a thermal video stream of the subject. Hu, [0061] ); segmenting the obtained data stream into time segments ( the computing device 200 can be configured to segment and recognize similar motions ( e.g., normal and/or abnormal walking cycles) within the image data as shown by box 152 of FIG. lA. Hu, [0063] ), wherein each time segment corresponds to one movement step ( The skeleton origin is set to the posture of normal standing case, and an Euclidean distance is calculated between the skeleton origin and the skeleton data in each frame of the motion series. Hu, [0150] ); storing each time segment into a first storage section with a predetermined memory size ( As shown by dotted box 150 of FIG. lA, the computing device 200 can be configured to process image data (e.g., thermal images), which was captured by the thermal imaging device 104. For example, as described below, the thermal images can be converted to black and white (B&W) images, the background can be subtracted, and the skeleton model of the subject's lower limbs can then be extracted out from the B& W images for later use. Hu, [0062] ); performing clustering of the time segments stored in the first storage section into specific time intervals by computing distances between the time segments stored in the first storage section using a dynamic time warping algorithm ( known method to calculate the similarity between two series with different lengths is DTW. Using DTW, it is possible to calculate a similarity matrix for the two series, and then search for an optimal warping path with the maximal cumulative similarity, Hu, [0092] ), learning a two-dimensional non-linear topology (In some implementations, a motion series defines the movement of the subject's limb motion (e.g., a particular joint) in two dimensions (e.g., two of the x-, y-, and z-dimensions). Hu, [0091] ) preserving embedded feature vector based on the computed distances ( FIG. 9 illustrates examples of the feature vector for a number of time series in the 3-dimensional (3D) space, Hu, [0103] ) using a uniform manifold approximation and projection algorithm to reduce the time segments stored in the first data storage section to n feature vectors in two-dimensional space ( Takens Embedding Theorem states that a manifold Mc Rd can be embedded by the time-delay coordinates with lag -i: in a k-dimensional space, if-i: does not conflict with the period of o, and k>2 m, as shown in Eq. 5. Hu, [0123] ), Hu does not teach affinity. Alcock however teaches clustering the n feature vectors using an affinity propagation algorithm that determines a number of clusters automatically ( Other clustering techniques may be used, including k-means clustering, affinity propagation, and mean shift clustering. Alcock, [0073] ). Hu in view of Alcock are analogous art to the claimed invention, because they are from a similar field of endeavor of systems, components and methodologies for providing communication between computer systems. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Hu in view of Alcock. This would have been desirable because Feature vectors are obtained 610 for each of the N images selected by the user, to establish a search set of N feature vectors. The search set of N feature vectors is then clustered 620, for example, using k-medoid clustering to divide the search set into a number of clusters, each cluster containing at least one feature vector, and the number of clusters being less than or equal to M (Alcock, [0073]). Hu in view of Alcock further teaches aligning time segments of each cluster using a dynamic time warping algorithm and averaging the aligned time segments of each cluster for generating a prototype time segment for each cluster ( First, amplitude smoothing includes detecting all the peaks (including the noise) in the motion series. Second, if the amplitude of a peak is under a threshold, its amplitude is replaced by the average of its neighboring two peaks. The averaging operation is implemented iteratively until the amplitudes of all peaks are above the threshold, Hu, [0095] ); generating and storing in a memory a movement model by comparing the determined number of clusters of a current clustering with the determined number of clusters from the previous clustering stored in a second storage section ( A motion series (e.g., including a normal and/or abnormal walking cycles) can be recognized through the analysis of peaks of the motion series using the PMTW method described herein. To achieve a more convenient observation of the human motion series, a feature space can be constructed based on the peak pattern of time series. The peak pattern can include an amplitude, order, or speed of peaks. Hu, [0098] ), and Hu in view of Alcock teaches merging ( The system 100 thus can take the user's feedback to refine the search results (by merging the result of multiple reference images). In such examples the user interface 402 can allow for collecting the feedback of the user for the purpose of collecting data that can be used to refine the learning engine (or to train a new learning engine). This feedback mechanism can be used to create a system 100 that evolves by continuously and automatically learning from users. Alcock, [0066] ). Drouin further teaches in case the determined number of clusters of the current clustering is equal the determined number of clusters from the previous clustering, merging individually the prototype time segments of the current clustering with the corresponding prototype time segments of the previous clustering, in case of the determined number of clusters of the current clustering exceeding the determined number of clusters from the previous clustering, merging individually the prototype time segments of the current clustering with the corresponding prototype time segments of the previous clustering, and adding the current prototype time segments of the current clustering that have no corresponding prototype time segments in the previous clustering, and in case the determined number of clusters of a current clustering is smaller than the determined number of clusters from the previous clustering, merging individually the prototype time segments of the current clustering with the corresponding prototype time segments of the previous clustering, and retaining the previous prototype time segments of the previous clustering that have no corresponding prototype time segments in the current clustering ( The agglomerative approach pertains to considering that each observation is in its own cluster at the initial state. At each iteration, the two closest clusters are merged together. This iterative process stops when all observations end up into the same cluster. Hierarchical divisive clustering requires more input choices than its agglomerative counterpart. In effect, in addition to the dissimilarity (which is the only ingredient that HAC requires), in a divisive strategy, one needs to define a criterion to select at each iteration which cluster will be further splitted. In the following, we will therefore focus on hierarchical agglomerative clustering (HAC). Let then set up the initial state in which each observation is its own cluster all clusters contains a single observation: Ci = {Qi}, ∀ i ∈ {1, … , n}. The first step for building the dendrogram is to determine the two closest clusters Ci and Cj of the set that will be merged into a single cluster Cij. This is achieved by Cij = Ci ∪ Cj, with (Ci, Cj) = argminCk,ClD(Ck, Cl). The next step is to update the matrix D with the new dissimilarity value between the new cluster Cij and every other cluster Ck, ∀ k ∈ {1, … , n} ⧵ {i, j}. Drouin, page 435 ). Hu in view of Alcock in view of Drouin are analogous art to the claimed invention, because they are from a similar field of endeavor of systems, components and methodologies for providing communication between computer systems. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Hu in view of Alcock in view of Drouin. This would have been desirable because Clustering relates to the process of building a partition of a set of n observations Q1, … ,Qn such that similar observations ends up into the same cluster while observations too far from each other are assigned to separate clusters (Drouin, page 435). As per claim 2, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 1, wherein the step of generating and storing further comprises interpolating each prototype time segment and resampling the interpolated prototype time segment to a predetermined data size (Hu, [0035]-[0036]). As per claim 3, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 2, wherein the predetermined data size exceeds a value that results from a slow human walk sampled at a characteristic sampling frequency of an IMU sensor (Hu, [0122]). As per claim 10, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 1, wherein the method further comprises: storing and outputting, by a data interface, the prototype time segments stored in the memory after a predefined time interval has elapsed (Hu, [0066], [0071]). As per claim 12, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 10, wherein the method further comprises: storing and outputting, by the data interface, meta information for the current predefined time interval of each or all movements associated with the prototype time segments stored in the memory after a predefined time interval has elapsed (Hu, [0118]). As per claim 13, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 12, wherein the meta information comprises at least one of number of movements and duration of movements (Hu, [0118]). As per claim 15, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 1, wherein the method is performed online during movement of the person (Hu, [0075], [0057], [0059]). As per claim 16, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 1, wherein the at least one sensor includes an IMU sensor array (Hu, [0059]). As per claim 17, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 1, wherein the method comprises: estimating a velocity of the movement by counting a number of the movement measurements of each time segment for a constant sampling rate of the at least one sensor (Hu, [0098]-[0102]). Claims 18 and 21 have limitations similar to those treated in the above rejection, and are met by the references as discussed above, and are rejected for the same reasons of obviousness as used above . 07-21-aia AIA Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (US 2017/0087416, Mar. 30, 2017), in view of Alcock et al. (US 2020/0082212, Mar. 12, 2020), in view of Drouin et al. (Semi-supervised clustering of quaternion time series: Application to gait analysis in multiple sclerosis using motion sensor data, SiM, 2022, 24 pages), in view of Li et al. (Evaluation of Postural Sway in Post-stroke Patients by Dynamic Time Warping Clustering, FiHN, 2021, 13 pages), hereinafter referred to as Hu, Alcock, Drouin and Li . As per claim 5, Hu in view of Alcock in view of Drouin teaches the computer-implemented method according to claim 1, but does not teach 60 Hz, Li however teaches wherein a characteristic sampling frequency of the at least one sensor at 60 Hz ( The measurement sampling frequency was 60 Hz for 30 s. Li, page 2 ). Hu in view of Alcock in view of Drouin in view of Li are analogous art to the claimed invention, because they are from a similar field of endeavor of systems, components and methodologies for providing communication between computer systems. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Hu in view of Alcock in view of Drouin in view of Li. This would have been desirable because the measurement sampling frequency was 60 Hz for 30 s, for 5 s data, the number of columns is 60 Hz × 5 s (300). The DTW clustering compared each vector of one data slot and its corresponding vector of another (LI, page 6) . Allowable Subject Matter Claims 4, 6-9, 11, 14, 19, and 20 are indicated as allowable over prior art. 13-03-01 AIA The following is a statement of reasons for the indication of allowable subject matter: Cited by examiner prior art does not teach limitations of claims 4, 6-9, 11, 14, 19, and 20 as currently presented . 07-43-03 AIA As allowable subject matter has been indicated, applicant's reply must either comply with all formal requirements or specifically traverse each requirement not complied with. See 37 CFR 1.111(b) and MPEP § 707.07(a). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to OLEG KORSAK whose telephone number is (571)270-1938. The examiner can normally be reached on Monday-Friday 7:30am - 5:00pm EST. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Rupal Dharia can be reached on (571) 272-3880. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /OLEG KORSAK/ Primary Examiner, Art Unit 2492 Application/Control Number: 18/361,915 Page 2 Art Unit: 2492 Application/Control Number: 18/361,915 Page 3 Art Unit: 2492 Application/Control Number: 18/361,915 Page 4 Art Unit: 2492 Application/Control Number: 18/361,915 Page 5 Art Unit: 2492 Application/Control Number: 18/361,915 Page 6 Art Unit: 2492 Application/Control Number: 18/361,915 Page 7 Art Unit: 2492 Application/Control Number: 18/361,915 Page 8 Art Unit: 2492 Application/Control Number: 18/361,915 Page 9 Art Unit: 2492 Application/Control Number: 18/361,915 Page 10 Art Unit: 2492