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 .
Claim Rejections - 35 USC § 112
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.
Claims 4 and 5 are 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.
It is unclear whether the “N reference motion data” of claims 4 and 5 are the same or different as the “N motion data” of claims 1 and 3.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Section 33(a) of the America Invents Act reads as follows:
Notwithstanding any other provision of law, no patent may issue on a claim directed to or encompassing a human organism.
Claims 2 and 16 are rejected under 35 U.S.C. 101 and section 33(a) of the America Invents Act as being directed to or encompassing a human organism. See also Animals - Patentability, 1077 Off. Gaz. Pat. Office 24 (April 21, 1987) (indicating that human organisms are excluded from the scope of patentable subject matter under 35 U.S.C. 101). The limitation “a motion sensor set or worn on a foot” encompasses a human organism. It is recommended to incorporate “configured to” language or similar to overcome this rejection, such as “a motion sensor configured to be set or worn on a foot.”
Claims 1-3, 11-16, 18-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Under the two-step 101 analysis, the claims fail to satisfy the criteria for subject matter eligibility.
Step 1: Claims 1-3, 11-16, 18-20 are within at least one of the four statutory categories.
Claim 1 and dependent claims 2-3 and 11-14 disclose a method.
Claim 15 and dependent claims 16 and 18 disclose an apparatus.
Claim 19 and dependent claim 20 disclose a product of manufacture.
Step 2A, Prong One: The independent claims 1, 15, and 19 recite limitations directed to an abstract idea that is part of the Mathematical Concepts and/or Mental Processes group identified in the 2019 Revised Patent Subject Matter Eligibility Guidance published in the Federal Register (84 FR 50) on January 7, 2019.
Mathematical Concepts: “A mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words ….” October 2019 Update: Subject Matter Eligibility, II. A. i. “[T]here are instances where a formula or equation is written in text format that should also be considered as falling within this grouping.” Id. at II. A. ii. “[A] claim does not have to recite the word “calculating” in order to be considered a mathematical calculation.” Id. at II. A. iii. See for example, SAP Am., Inc. v. InvestPic, LLC, 898 F.3d 1161, 1163-65 (Fed. Cir. 2018) (performing a resampled statistical analysis to generate a resampled distribution).
Mental Processes: Mental Processes can be practically performed in the human mind using mental steps, a pen and paper, or basic critical thinking/judgement -- types of activities that have been found by the courts to represent abstract ideas. See p. 7-8 of October 2019 Update: 2019 Revised Patent Subject Matter Eligibility Guidance published in the Federal Register (84 FR 50) for examples of ineligible claims that recite mental processes.
Claims 1, 15, and 19 recite the follow abstract ideas:
“determin[ing/e] a plurality of probability distributions based on the N motion data, wherein the plurality of probability distributions respectively correspond to a plurality of gait events”
[0038] “Next, in step S220, the processor 104 determines a plurality of probability distributions based on the N motion data, and the plurality of probability distributions respectively correspond to a plurality of gait events. In an embodiment, the plurality of gait events include, for example, initial contact, foot-flat, heel-off and toe-off, but not limited thereto.”
[0039] “In an embodiment, the processor 104 may feed the N motion data into an artificial intelligence model (hereinafter referred to as M1) that has undergone a training process, and the artificial intelligence model M1 generates the plurality of probability distributions in response to the N motion data.”
“determin[ing/e] an event time point of each of the gait events belonging to a specific step according to the plurality of probability distributions”
[0058] “Afterwards, in step S230, the processor 104 determines the event time points of various gait events belonging to a specific step according to the plurality of probability distributions, and the relevant details of step S230 will be described with reference to FIG. 7 and FIG. 8.”
[0088] “Afterwards, the processor 104 takes the time point corresponding to the specific sampling point of the j-th specific sampling point group as the event time point of the j-th gait event belonging to a specific step. For example, the processor 104 takes the time point T1 of the specific sampling point 1012a as the event time point of initial contact of a specific step, takes the time point T2 of the specific sampling point 1013a as the event time point of foot-flat of the specific step, takes the time point T3 of the specific sampling point 1014a as the event time point of heel-off of the specific step, and takes the time point T4 of the specific sampling point 1015a as the event time point of toe-off of the specific step.”
These limitations describe a mathematical calculation and/or a mental process as the skilled artisan is capable of performing the recited limitations and making a mental assessment thereafter. Determining a plurality of probability distributions based on the N motion data, wherein the plurality of probability distributions respectively correspond to a plurality of gait events are mathematical concepts that can be determined mentally or with the aid of pen and paper. Determining an event time point of each of the gait events belonging to a specific step according to the plurality of probability distributions can be performed through an individual’s mental process and judgement based on temporal alignment of the gait event and probability distribution characteristics.
Regarding dependent claims 2-3, 11-14, 16, 18, and 20, they are directed to either 1) steps that are also abstract or 2) additional data output that is well-understood, routine, and previously known to the industry:
Claim 2 and 16 further limit the motion data to have 6 degrees of freedom values.
Claim 3 further limits the artificial intelligence model generating the plurality of probability distributions in response to the N motion data.
Claim 11 and 12 further limit other probability distributions based on the N other motion data and event time points of each of the gait events belonging to another specific step according to the plurality of other probability distributions.
Claim 13, 18, and 20 further limit determining gait asymmetry based on first and second gait indexes.
Claim 14 further limits the plurality of gait events to comprise an initial contact, a foot-flat, a heel-off and a toe-off.
Dependent claims 2-3, 11-14, 16, 18, and 20 further limit the abstract ideas of independent claims 1, 15, and 19 and do not recite significantly more than the abstract ideas.
Step 2A, Prong Two: The judicial exceptions (abstract ideas) in claims 1-3, 11-16, 18-20 are not integrated into a practical application because:
The abstract idea amounts to simply implementing the abstract idea on a computer. For example, the recitations regarding the generic computing components for obtaining motion data and displaying gait analysis results merely invoke a computer as a tool.
The data-gathering step (obtaining motion data data) and the data-output step (displaying gait analysis results) do not add a meaningful limitation to the method as they are insignificant extra-solution activity.
There is no improvement to a computer or other technology. “The McRO court indicated that it was the incorporation of the particular claimed rules in computer animation that "improved [the] existing technological process", unlike cases such as Alice where a computer was merely used as a tool to perform an existing process.” MPEP 2106.05(a) II.
The claims recite a computer/processor that is used as a tool for obtaining motion data and displaying gait analysis results.
The claims do not apply the abstract idea to affect a particular treatment or prophylaxis for a disease or medical condition. Rather, the abstract idea is utilized for obtaining motion data to provide the gait analysis results.
The claims do not apply the abstract idea to a particular machine. “Integral use of a machine to achieve performance of a method may provide significantly more, in contrast to where the machine is merely an object on which the method operates, which does not provide significantly more.” MPEP 2106.05(b). II. “Use of a machine that contributes only nominally or insignificantly to the execution of the claimed method (e.g., in a data gathering step or in a field-of-use limitation) would not provide significantly more.” MPEP 2106.05(b) III. The pending claims utilize a computer/processor for obtaining motion data and outputting gait analysis results.
The additional elements are identified as follows:
Claims 1 and 16 – motion sensor
Claims 15-18 – gait analysis device
Claims 15 – storage circuit
Claims 15 and 17-18 – processor
Claims 18 – display device
Claims 19-20 – computer-readable storage medium
Step 2B: Claims 1-3, 11-16, 18-20 do not include additional elements that are sufficient to provide for an inventive concept nor amount to significantly more than the judicial exception.
Those in the relevant field of art would recognize the above-identified additional elements as being well-understood, routine, and conventional means for obtaining measurement data and outputting results as demonstrated by the specification. The applicant discloses nothing unique about the motion sensor (Specification [0031]), gait analysis device (Specification [0025]), processor (Specification [0028]), display device (Specification [0112]), or storage circuit/computer-readable storage medium (Specification [0027]), configured to perform the generic computer functions (e.g., obtaining measurement data and outputting results) that are well-understood, routine, and conventional activities previously known to the pertinent industry.
Thus, the claimed additional elements “are so well-known that they do not need to be described in detail in a patent application to satisfy 35 U.S.C. § 112(a).” Berkheimer Memorandum, III. A. 3. Furthermore, the court decisions discussed in MPEP § 2106.05(d)(lI) note the well-understood, routine and conventional nature of such additional generic computer components as those claimed. See option III. A. 2. in the Berkheimer memorandum.
When considered in combination, the additional elements (i.e., the generic computer functions and conventional equipment/steps) do not amount to significantly more than the abstract idea. Looking at the claim limitations as a whole adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of the motion sensor, gait analysis device/processor, display device, or storage circuit/computer-readable storage medium, or any other technology. Their collective functions merely provide conventional computer implementation.
Therefore, claims 1-3, 11-16, 18-20 are directed to patent ineligible subject matter.
Examiner’s Note: Dependent claims 4-10 and 17 recite additional limitations that cannot be feasibly determined mentally or with the aid of pen and paper by one of ordinary skill in the art, and therefore, are not directed to abstract ideas without significantly more. Dependent claims 4-10 and 17 are not rejected under 35 USC 101.
Claim Rejections - 35 USC § 102
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3, 11, 13-15, and 18-20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Newton (US 20230329587 A1).
Regarding claim 1, Newton teaches a gait analysis method, adaptable for a gait analysis device ([0017] “FIGS. 4-10 are process flow diagrams that illustrate methods using a mobile device to represent human gait and diagnose health conditions (e.g., detect a neuromuscular disorder, etc.)”), and comprising:
obtaining consecutive N motion data, wherein N is a positive integer ([0092] “In block 404, the mobile computing device may collect gait data. For example, the computing device may commence collecting data from the accelerometer, ensure proper placement of the device on the sternum or other suitable body location, and record raw accelerometer data in 3-axis format (x, y, z).”);
determining a plurality of probability distributions based on the N motion data, wherein the plurality of probability distributions respectively correspond to a plurality of gait events ([0139] In block 918, the processor may use a neural network to identify gait patterns and classify gait abnormalities. For example, the processor may use a CNN to capture spatial patterns in the gait features, and a RNN or a long short-term memory network to model temporal dependencies in the gait data. The processor may train the neural network using a labeled dataset of gait patterns from healthy individuals and individuals with known abnormalities. The processor may use the trained network to classify the user's gait patterns based on the extracted gait features or representation (e.g., BKG waveform, etc.). The neural network may output a probability distribution over the possible gait classes, which may be used by the processor to determine the most likely gait pattern or abnormality for the user. In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).”); and
determining an event time point of each of the gait events belonging to a specific step according to the plurality of probability distributions ([0088] “Each of these events occurs at a certain time (or percent) within the gait cycle.” [0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0139] “block 918… output a probability distribution over the possible gait classes”).
Regarding claim 3, Newton teaches the method according to claim 1, wherein determining the plurality of probability distributions based on the N motion data comprises: feeding the N motion data into an artificial intelligence model, wherein the artificial intelligence model generates the plurality of probability distributions in response to the N motion data ([0062] “Once the model is trained, the computing device may apply the model to BKG waveform or to the processed motion sensor data of an individual's gait. The model may then output a predicted label or a probability distribution over potential labels;” [0139] “The neural network may output a probability distribution over the possible gait classes, which may be used by the processor to determine the most likely gait pattern or abnormality for the user. In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).”).
Regarding claim 11, Newton teaches the method according to claim 1, wherein the plurality of gait events comprise a 1-st gait event to a K-th gait event in sequence ([0153] “Each comparison result may be obtained through an automatic comparison of a BKG value to a standard for a corresponding variable linked to one or more specific components of a gait cycle, including left and right heel strikes, toe strikes, and toe lift-offs. BKG values may be determined automatically from a data set consisting of numerous scalar sums of acceleration values in three orthogonal directions, with each sum corresponding to a specific point in time.”), and the method further comprises:
in response to determining that the event time point of each of the gait events corresponding to a specific step has been found based on the N motion data, obtaining the event time point of the K-th gait event corresponding to the specific step ([0148] “As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”);
obtaining other consecutive N motion data from the event time point of the K-th gait event corresponding to the specific step, and determining a plurality of other probability distributions based on the N other motion data, wherein the plurality of other probability distributions respectively correspond to the plurality of gait events ([0139] “The processor may use the trained network to classify the user's gait patterns based on the extracted gait features or representation (e.g., BKG waveform, etc.). The neural network may output a probability distribution over the possible gait classes, which may be used by the processor to determine the most likely gait pattern or abnormality for the user. In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).”); and
determining the event time point of each of the gait events belonging to another specific step according to the plurality of other probability distributions ([0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0139] “block 918… output a probability distribution over the possible gait classes”).
Regarding claim 13, Newton teaches the method according to claim 1, wherein the specific step corresponds to a first foot of a subject under test, and after determining the event time point of each of the gait events belonging to the specific step according to the plurality of probability distributions ([0153] “Each comparison result may be obtained through an automatic comparison of a BKG value to a standard for a corresponding variable linked to one or more specific components of a gait cycle, including left and right heel strikes, toe strikes, and toe lift-offs. BKG values may be determined automatically from a data set consisting of numerous scalar sums of acceleration values in three orthogonal directions, with each sum corresponding to a specific point in time.”), the method further comprises:
determining at least one first gait index corresponding to the first foot according to the event time point of each of the gait events belonging to the specific step; obtaining at least one second gait index of a second foot corresponding to the subject under test ([0148] “As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”);
determining a gait asymmetry between the first foot and the second foot based on the at least one first gait index and the at least one second gait index ([0148] “A high degree of gait symmetry may indicate a healthy walking pattern, whereas a significant asymmetry could suggest an underlying health issue or injury. In some embodiments, the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0153] “The cause of the patient's condition may be identified (e.g., as an orthopedic injury, etc.) when the BKG value for the patient shows asymmetrical cadence with a difference between the first and second double stance time greater than 25 milliseconds.”).
Regarding claim 14, Newton teaches the method according to claim 1, wherein the plurality of gait events comprise an initial contact, a foot-flat, a heel-off and a toe-off ([0088] “In the example illustrated in FIG. 3A, the computing device associates various stages in a single human gait cycle with an event and a time or percentage within the gait cycle. The events include initial contact 302, foot flat 304, mid stance 306, heel off 308, opposite initial contact 310 (or heel strike), toe off 312 (or toe strike), feet adjustment 314, tibia vertical 316, and next cycle initial 318. Each of these events occurs at a certain time (or percent) within the gait cycle.”).
Regarding claim 15, Newton teaches a gait analysis device (computing system 102, system 200), comprising:
a storage circuit, which stores a program code ([0186] “such non-transitory server-readable, computer-readable or processor-readable media may include RAM, ROM, EEPROM, FLASH memory, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a compute”);
a processor, which is coupled to the storage circuit to access the program code ([0185] “ implemented or performed with a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device”) to:
obtain consecutive N motion data, wherein N is a positive integer ([0092] “In block 404, the mobile computing device may collect gait data. For example, the computing device may commence collecting data from the accelerometer, ensure proper placement of the device on the sternum or other suitable body location, and record raw accelerometer data in 3-axis format (x, y, z).”);
determine a plurality of probability distributions based on the N motion data, wherein the plurality of probability distributions respectively correspond to a plurality of gait events ([0139] In block 918, the processor may use a neural network to identify gait patterns and classify gait abnormalities. For example, the processor may use a CNN to capture spatial patterns in the gait features, and a RNN or a long short-term memory network to model temporal dependencies in the gait data. The processor may train the neural network using a labeled dataset of gait patterns from healthy individuals and individuals with known abnormalities. The processor may use the trained network to classify the user's gait patterns based on the extracted gait features or representation (e.g., BKG waveform, etc.). The neural network may output a probability distribution over the possible gait classes, which may be used by the processor to determine the most likely gait pattern or abnormality for the user. In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).”); and
determine an event time point of each of the gait events belonging to a specific step according to the plurality of probability distributions ([0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0139] “block 918… output a probability distribution over the possible gait classes”).
Regarding claim 18, Newton teaches the gait analysis device according to claim 15, further comprising a display device (dashboard 122), wherein the specific step corresponds to a first foot of a subject under test, and after determining the event time point of each of the gait events belonging to the specific step according to the plurality of probability distributions ([0153] “Each comparison result may be obtained through an automatic comparison of a BKG value to a standard for a corresponding variable linked to one or more specific components of a gait cycle, including left and right heel strikes, toe strikes, and toe lift-offs. BKG values may be determined automatically from a data set consisting of numerous scalar sums of acceleration values in three orthogonal directions, with each sum corresponding to a specific point in time.”), the processor is further configured to:
determine at least one first gait index corresponding to the first foot according to the event time point of each of the gait events belonging to the specific step; obtain at least one second gait index of a second foot corresponding to the subject under test ([0148] “As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”);
determine a gait asymmetry between the first foot and the second foot based on the at least one first gait index and the at least one second gait index ([0148] “A high degree of gait symmetry may indicate a healthy walking pattern, whereas a significant asymmetry could suggest an underlying health issue or injury. In some embodiments, the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0153] “The cause of the patient's condition may be identified (e.g., as an orthopedic injury, etc.) when the BKG value for the patient shows asymmetrical cadence with a difference between the first and second double stance time greater than 25 milliseconds.”); control the display device to display the gait asymmetry ([0067] “The dashboard 122 may visualize and present the results on an electronic display. For example, the dashboard 122 may generate graphs and visualizations based on the extracted variables and calculated risk levels, display the results on a user-friendly interface or dashboard, and allow users to interact with the data and visualize their progress over time.”).
Regarding claim 19, Newton teaches a computer-readable storage medium, wherein the computer-readable storage medium records an executable computer program, and the executable computer program is loaded by a gait analysis device to perform ([0186] “The steps of a method or algorithm disclosed herein may be embodied in a processor-executable software module and/or processor-executable instructions, which may reside on a non-transitory computer-readable or non-transitory processor-readable storage medium. Non-transitory server-readable, computer-readable or processor-readable storage media may be any storage media that may be accessed by a computer or a processor.”) the following:
obtaining consecutive N motion data, wherein N is a positive integer ([0092] “In block 404, the mobile computing device may collect gait data. For example, the computing device may commence collecting data from the accelerometer, ensure proper placement of the device on the sternum or other suitable body location, and record raw accelerometer data in 3-axis format (x, y, z).”);
determining a plurality of probability distributions based on the N motion data, wherein the plurality of probability distributions respectively correspond to a plurality of gait events ([0139] In block 918, the processor may use a neural network to identify gait patterns and classify gait abnormalities. For example, the processor may use a CNN to capture spatial patterns in the gait features, and a RNN or a long short-term memory network to model temporal dependencies in the gait data. The processor may train the neural network using a labeled dataset of gait patterns from healthy individuals and individuals with known abnormalities. The processor may use the trained network to classify the user's gait patterns based on the extracted gait features or representation (e.g., BKG waveform, etc.). The neural network may output a probability distribution over the possible gait classes, which may be used by the processor to determine the most likely gait pattern or abnormality for the user. In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).”); and
determining an event time point of each of the gait events belonging to a specific step according to the plurality of probability distributions ([0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0139] “block 918… output a probability distribution over the possible gait classes”).
Regarding claim 20, Newton teaches the computer-readable storage medium according to claim 19, wherein the specific step corresponds to a first foot of a subject under test, and after determining the event time point of each of the gait events belonging to the specific step according to the plurality of probability distributions ([0153] “Each comparison result may be obtained through an automatic comparison of a BKG value to a standard for a corresponding variable linked to one or more specific components of a gait cycle, including left and right heel strikes, toe strikes, and toe lift-offs. BKG values may be determined automatically from a data set consisting of numerous scalar sums of acceleration values in three orthogonal directions, with each sum corresponding to a specific point in time.”), further comprising:
determining at least one first gait index corresponding to the first foot according to the event time point of each of the gait events belonging to the specific step; obtaining at least one second gait index of a second foot corresponding to the subject under test ([0148] “As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”);
determining a gait asymmetry between the first foot and the second foot based on the at least one first gait index and the at least one second gait index ([0148] “A high degree of gait symmetry may indicate a healthy walking pattern, whereas a significant asymmetry could suggest an underlying health issue or injury. In some embodiments, the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0153] “The cause of the patient's condition may be identified (e.g., as an orthopedic injury, etc.) when the BKG value for the patient shows asymmetrical cadence with a difference between the first and second double stance time greater than 25 milliseconds.”).
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.
Claim(s) 2 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Newton (US 20230329587 A1) in view of Chandel (US 20200305763 A1).
Regarding claim 2, Newton teaches the method according to claim 1, wherein the N motion data is derived from a motion sensor set, and each of the motion data comprises 6 degrees of freedom values ([0025] “Some embodiments may include a computing device (e.g., mobile device, etc.) configured to receive data from a motion sensor (e.g., an accelerometer, gyroscope, etc.) while the user holds or wears the device (or another device containing the motion sensor) and walks a designated distance.” [0049] “In some embodiments, any or all of the sensors (e.g., accelerometers, gyroscopes, magnetometers, etc.) may be three-dimensional sensors that may measure and record data in all three dimensions (x, y, and z axes) of physical space and/or detect changes in position, orientation, or motion.”). However, Newton fails to disclose the sensor being worn on a foot.
Chandel teaches a wearable apparatus and method for calculating drift-free plantar pressure parameters for gait monitoring of an individual. Chandel discloses or worn on a foot ([0039 “the 6-Degree Of Freedom (DOF) Inertial Measurement Unit (IMU) (102b of FIG. 1A and FIG. 1B) is placed at bottom of the footwear representing mid foot area of the individual”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newton to include a sensor worn on a foot as disclosed in Chandel to isolate a zero-pressure duration in the acquired dynamic sensor data to prevent the drift and allow for more accurate measures of plantar pressure (Chandel [0040]).
Regarding claim 16, Newton teaches the gait analysis device according to claim 15, wherein the N motion data is derived from a motion sensor set, and each of the motion data comprises 6 degrees of freedom values ([0025] “Some embodiments may include a computing device (e.g., mobile device, etc.) configured to receive data from a motion sensor (e.g., an accelerometer, gyroscope, etc.) while the user holds or wears the device (or another device containing the motion sensor) and walks a designated distance.” [0049] “In some embodiments, any or all of the sensors (e.g., accelerometers, gyroscopes, magnetometers, etc.) may be three-dimensional sensors that may measure and record data in all three dimensions (x, y, and z axes) of physical space and/or detect changes in position, orientation, or motion.”). However, Newton fails to disclose the sensor being worn on a foot.
Chandel teaches a wearable apparatus and method for calculating drift-free plantar pressure parameters for gait monitoring of an individual. Chandel discloses or worn on a foot ([0039 “the 6-Degree Of Freedom (DOF) Inertial Measurement Unit (IMU) (102b of FIG. 1A and FIG. 1B) is placed at bottom of the footwear representing mid foot area of the individual”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newton to include a sensor worn on a foot as disclosed in Chandel to isolate a zero-pressure duration in the acquired dynamic sensor data to prevent the drift and allow for more accurate measures of plantar pressure (Chandel [0040]).
Claim(s) 4-10, 12, and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Newton (US 20230329587 A1) in view of Orlovsky (US 20230181059 A1).
Regarding claim 4, Newton teaches the method according to claim 3, wherein a training process of the artificial intelligence model ([0059] “the pattern analyzer 114 may train supervised and unsupervised machine learning models on the collected data”) comprises:
obtaining consecutive N reference motion data, and obtaining a plurality of data time points corresponding to each of the gait events from the N reference motion data ([0061] “In some embodiments, the computing device may use machine learning algorithms to recognize patterns and classify gait abnormalities by leveraging large datasets containing labeled examples of both healthy and abnormal gaits. In the training phase, the computing device may process the motion sensor data and extract relevant features, such as stride length, cadence, step duration, and foot strike patterns. The computing device may input these extracted features to a neural network or machine learning algorithm that learns to identify patterns associated with specific gait abnormalities by comparing the input data to the labeled examples in the dataset.”).
However, Newton fails to generate a reference probability distribution. Orlovsky teaches systems and methods for monitoring health-related activity parameters using machine learning.
Orlovsky discloses generating a reference probability distribution corresponding to each of the gait events based on the plurality of data time points corresponding to each of the gait events ([0054] “The physical parameters which may be monitored by the telemedical monitoring device 104 include, but are not limited to, the heart rate, heart variability, respiratory rate, sleep scores, gait, postures, etc.” [0113] “The set of standard energy profiles characterize the expected energy distribution associated with a subject in a different pose (standing, sitting, lying, walking, bending over etc.).” [0118] “In an exemplary embodiment, the process of anomaly detection in fall alerts is explained using Kullback-Leibler (KL) Divergence which measures how a probability distribution differs from a reference probability distribution. A metric M.sup.i is defined by the KL Divergence as: where, P.sub.W.sup.i refers to time dependent energy profile distribution of a target segment [reference probability distribution]; and P.sub.D refers to the current energy profile distribution of the target segment.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newton to include a reference probability distribution as disclosed in Orlovsky to detect movement anomalies by comparing the reference probability distribution with a current distribution (Orlovsky [0118]).
The combination of Newton/Orlovsky discloses:
training the artificial intelligence model based on the N reference motion data and the reference probability distribution (Newton [0061] “In the training phase, the computing device may process the motion sensor data and extract relevant features, such as stride length, cadence, step duration, and foot strike patterns. The computing device may input these extracted features to a neural network or machine learning algorithm that learns to identify patterns associated with specific gait abnormalities by comparing the input data to the labeled examples in the dataset.” Orlovsky: [0114] “At step 610, the profile generator selects a closest match for the target segment from the set of standard energy profiles and generates time dependent energy profiles 524 for each segment at step 612. The time dependent energy profiles 524 are stored in the database 520.”),
wherein the artificial intelligence model generates a prediction probability distribution corresponding to each of the gait events in response to the N reference motion data (Newton: [0062] “Once the model is trained, the computing device may apply the model to BKG waveform or to the processed motion sensor data of an individual's gait. The model may then output a predicted label or a probability distribution over potential labels;” [0139] “The neural network may output a probability distribution over the possible gait classes;” Orlovsky [0117] “For each target segment of the target area 102, a current energy profile is generated by the profile generator 514 and sent to the processing unit 526 by the output unit 518 at step 624. “);
updating a plurality of model parameters of the artificial intelligence model based on a comparison result between the reference probability distribution and the prediction probability distribution corresponding to each of the gait events (Newton [0063] “During the training phase, the neural network learns to identify patterns associated with specific gait abnormalities by adjusting the weights and biases of its connections using a labeled dataset containing examples of both healthy and abnormal gaits. The learning process may include iteratively updating the weights and biases to minimize the difference between the predicted labels and the actual labels in the dataset.” Orlovsky: [0118] “Kullback-Leibler (KL) Divergence which measures how a probability distribution differs from a reference probability distribution. A metric M.sup.i is defined by the KL Divergence as: where, P.sub.W.sup.i refers to time dependent energy profile distribution of a target segment; and P.sub.D refers to the current energy profile distribution of the target segment.” [0115] “At step 614, it is determined if all time intervals of the learning period have been completed. It is noted that the system may continue gathering profiles in an ongoing manner during operation even after the learning period is over. Where required older data may be overwritten or purged. In this manner the previous 48 hours may always be divided into a number of time intervals, such as 24 or twelve time intervals as required.”).
Regarding claim 5, the combination of Newton/Orlovsky discloses the method according to claim 4, wherein the plurality of gait events comprise a j-th gait event, and generating the reference probability distribution corresponding to each of the gait events based on the plurality of data time points corresponding to each of the gait events (Orlovsky: [0114] “At step 610, the profile generator selects a closest match for the target segment from the set of standard energy profiles and generates time dependent energy profiles 524 for each segment at step 612. The time dependent energy profiles 524 are stored in the database 520.”) comprises:
finding out at least one specific data time point corresponding to the j-th gait event in the N reference motion data (Newton: “The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”);
copying a preset probability distribution template to each of the specific data time points corresponding to the j-th gait event, generating the reference probability distribution corresponding to the j-th gait event (Orlovsky: [0113] “The set of standard energy profiles [preset probability distribution] characterize the expected energy distribution associated with a subject in a different pose (standing, sitting, lying, walking, bending over etc.).” [0114] “At step 610, the profile generator selects a closest match for the target segment from the set of standard energy profiles and generates time dependent energy profiles 524 for each segment [reference probability distribution] at step 612. The time dependent energy profiles 524 are stored in the database 520.” [0118] “P.sub.W.sup.i refers to time dependent energy profile distribution of a target segment;”).
Regarding claim 6, Newton teaches the method according to claim 1, wherein the plurality of probability distributions comprise an i-th probability distribution, and determining the event time point of each of the gait events belonging to the specific step according to the plurality of probability distributions ([0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0139] “block 918… output a probability distribution over the possible gait classes;” [0088] “Each of these events occurs at a certain time (or percent) within the gait cycle.”).
However, Newton fails to explicitly disclose a preset probability distribution template with a plurality of segments.
Orlovsky discloses comprises:
determining a preset probability distribution template ([0113] “The set of standard energy profiles characterize the expected energy distribution associated with a subject in a different pose (standing, sitting, lying, walking, bending over etc.).” [0114] “At step 610, the profile generator selects a closest match for the target segment from the set of standard energy profiles and generates time dependent energy profiles 524 for each segment at step 612. The time dependent energy profiles 524 are stored in the database 520.”);
determining a plurality of probability distribution segments on the i-th probability distribution according to the preset probability distribution template, wherein i is an index value ([0117] “For each target segment of the target area 102, a current energy profile is generated by the profile generator 514 and sent to the processing unit 526 by the output unit 518 at step 624.”);
determining an intersection over union (IoU) between the preset probability distribution template and each of the probability distribution segments on the i-th probability distribution ([0118] “In an exemplary embodiment, the process of anomaly detection in fall alerts is explained using Kullback-Leibler (KL) Divergence which measures how a probability distribution differs from a reference probability distribution. A metric M.sup.i is defined by the KL Divergence as: where, P.sub.W.sup.i refers to time dependent energy profile distribution of a target segment; and P.sub.D refers to the current energy profile distribution of the target segment.” [0121] “using Kullback-Leibler (KL) Divergence is exemplary in nature and should not limit the scope of the invention. Any other suitable probability distribution function can be used for the purpose without limiting the scope of the invention.” KL divergence is a fundamental information-theoretic measure that quantifies how one probability distribution differs from a second, reference probability distribution, and therefore under BRI reads on an IoU.),
and generating an IoU variation diagram corresponding to the i-th probability distribution accordingly ([0122] “FIGS. 16A, 17A and 18A illustrate KL Divergence values over all time windows in case of normal behavior in exemplary embodiments of the invention.” [0123] “FIGS. 16B, 17B and 18B illustrate KL Divergence values over all time windows in case of actual falls in exemplary embodiments of the invention.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newton to include a reference probability distribution as disclosed in Orlovsky to detect movement anomalies by comparing a preset probability distribution with a current distribution (Orlovsky [0118]).
The combination of Newton/Orlovsky discloses determining the event time point of each of the gait events belonging to the specific step based on the IoU variation diagram corresponding to each of the probability distributions (Newton: [0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” Orlovsky: [0118] “A metric M.sup.i is defined by the KL Divergence” [0119] “A threshold T is defined such that if M.sup.i<T there is no anomaly … if M.sup.i≥T an anomaly is detected”).
Regarding claim 7, the combination of Newton/Orlovsky discloses the method according to claim 6, wherein the preset probability distribution template is intercepted from a normal distribution with a specific standard deviation and a specific mean value (Orlovsky: [0113] “A set of 32 standard energy profiles of an exemplary subject are shown in FIG. 7. These standard energy profiles are generated from large sample of data collected over a large period of time.” [0114] “At step 610, the profile generator selects a closest match for the target segment from the set of standard energy profiles and generates time dependent energy profiles 524 for each segment at step 612. The time dependent energy profiles 524 are stored in the database 520.”).
Regarding claim 8, the combination of Newton/Orlovsky discloses the method according to claim 6, wherein determining the event time point of each of the gait events belonging to the specific step based on the IoU variation diagram corresponding to each of the probability distributions (Newton: [0148] “the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” Orlovsky: [0118] “A metric M.sup.i is defined by the KL Divergence” [0119] “A threshold T is defined such that if M.sup.i<T there is no anomaly … if M.sup.i≥T an anomaly is detected;” FIGS. 16A/B, 17A/B and 18A/B) comprises:
combining the IoU variation diagram corresponding to each of the probability distributions into a reference IoU variation diagram, wherein the reference IoU variation diagram comprises a plurality of IoU sampling points (Orlovsky: [0122] “FIGS. 16A, 17A and 18A illustrate KL Divergence values over all time windows in case of normal behavior in exemplary embodiments of the invention.” [0123] “FIGS. 16B, 17B and 18B illustrate KL Divergence values over all time windows in case of actual falls in exemplary embodiments of the invention.”);
finding out a plurality of sampling point groups from the reference IoU variation diagram, wherein the IoU corresponding to the plurality of IoU sampling points in each of the sampling point groups is higher than a preset threshold (Newton: [0139] “In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).” Orlovsky: [0118] “A metric M.sup.i is defined by the KL Divergence” [0119] “A threshold T is defined such that if M.sup.i<T there is no anomaly … if M.sup.i≥T an anomaly is detected”);
determining the gait event corresponding to each of the sampling point groups (Newton: [0148] “the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application);
in response to determining that there are a plurality of specific sampling point groups satisfying a preset condition in the plurality of sampling point groups (Newton: [0139] “In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).” Orlovsky: [0118] “A metric M.sup.i is defined by the KL Divergence” [0119] “A threshold T is defined such that if M.sup.i<T there is no anomaly … if M.sup.i≥T an anomaly is detected”), determining the event time point of each of the gait events belonging to the specific step based on the plurality of specific sampling point groups (Newton: [0088] “Each of these events occurs at a certain time (or percent) within the gait cycle.” [0148] “A high degree of gait symmetry may indicate a healthy walking pattern, whereas a significant asymmetry could suggest an underlying health issue or injury. In some embodiments, the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0153] “The cause of the patient's condition may be identified (e.g., as an orthopedic injury, etc.) when the BKG value for the patient shows asymmetrical cadence with a difference between the first and second double stance time greater than 25 milliseconds.”).
Regarding claim 9, the combination of Newton/Orlovsky discloses the method according to claim 8, wherein the plurality of gait events comprise a 1-st gait event to a K-th gait event in sequence (Newton: [0148] “As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”), and the method comprises:
in response to determining that consecutive K sampling point groups in the plurality of sampling point groups correspond to the 1-st gait event to the K-th gait event in sequence, determining that the consecutive K sampling point groups are the specific sampling point groups satisfying the preset condition (Newton: [0148] “the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0153] “The cause of the patient's condition may be identified (e.g., as an orthopedic injury, etc.) when the BKG value for the patient shows asymmetrical cadence with a difference between the first and second double stance time greater than 25 milliseconds.” [0139] “In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).”).
Regarding claim 10, the combination of Newton/Orlovsky discloses the method according to claim 8, wherein the plurality of specific sampling point groups comprise a j-th specific sampling point group, and determining the event time point of each of the gait events based on the plurality of specific sampling point groups (Newton: [0148] “As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg.”) comprises:
determining that the plurality of specific sampling point groups belong to the specific step;
finding out a specific sampling point from the j-th specific sampling point group, wherein the j-th specific sampling point group corresponds to a j-th gait event in the plurality of gait events, and j is an index value (Newton: [0148] “gait symmetry indices … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0153] “The cause of the patient's condition may be identified (e.g., as an orthopedic injury, etc.) when the BKG value for the patient shows asymmetrical cadence with a difference between the first and second double stance time greater than 25 milliseconds.”);
taking a time point corresponding to the specific sampling point of the j-th specific sampling point group as the event time point of the j-th gait event belonging to the specific step (Newton: [0148] “The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events” [0156] “BKG values may be determined from a data set containing scalar sums of acceleration values in three orthogonal directions, with each sum corresponding to a specific point in time. The BKG data set may be obtained, and for each variable, a value may be determined from the data set and compared to a standard for the corresponding variable.”).
Regarding claim 12, Newton teaches the method according to claim 1. However, Newton fails to disclose when an event time point is not found.
Orlovsky discloses, further comprising:
in response to determining that the event time point of each of the gait events corresponding to the specific step is not found based on the N motion data (Orlovsky: [0118] “A metric M.sup.i is defined by the KL Divergence” [0119] “A threshold T is defined such that if M.sup.i<T there is no anomaly … if M.sup.i≥T an anomaly is detected”),
obtaining other consecutive N motion data (Orlovsky: [0115] “At step 614, it is determined if all time intervals of the learning period have been completed. It is noted that the system may continue gathering profiles in an ongoing manner during operation even after the learning period is over.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newton to include an event time point not being found as disclosed in Orlovsky to avoid false positives in motion analysis (Orlovsky [0129]).
The combination of Newton/Orlovsky discloses:
wherein a first other motion data among the N other motion data has a time difference with a first motion data among the N motion data (Newton: [0088] “In the example illustrated in FIG. 3A, the computing device associates various stages in a single human gait cycle with an event and a time or percentage within the gait cycle. The events include initial contact 302, foot flat 304, mid stance 306, heel off 308, opposite initial contact 310 (or heel strike), toe off 312 (or toe strike), feet adjustment 314, tibia vertical 316, and next cycle initial 318. Each of these events occurs at a certain time (or percent) within the gait cycle.” [0094] “The computing device may determine gait phases such as the stance phase, swing phase, and double stance phase. The computing device may isolate specific events, such as the turnaround in the test and steps before and after the turnaround.”);
determining a plurality of other probability distributions based on the N other motion data, wherein the other probability distributions respectively correspond to the plurality of gait events (Newton: [0139] “The processor may use the trained network to classify the user's gait patterns based on the extracted gait features or representation (e.g., BKG waveform, etc.). The neural network may output a probability distribution over the possible gait classes”); and determining the event time point of each of the gait events belonging to another specific step according to the plurality of other probability distributions (Newton: [0139] “a probability distribution over the possible gait classes, which may be used by the processor to determine the most likely gait pattern or abnormality for the user. In block 920, the processor may determine a diagnosis based on the identified gait patterns and classify gait abnormalities (or based on whether probabilities associated with the gait pattern or abnormality for the user exceed a threshold value).” [0088] “Each of these events occurs at a certain time (or percent) within the gait cycle.”).
Regarding claim 17, Newton teaches the gait analysis device according to claim 15, wherein the plurality of probability distributions comprise an i-th probability distribution and the processor (Newton: [0148] “The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” [0139] “block 918… output a probability distribution over the possible gait classes”).
However, Newton fails to explicitly disclose a preset probability distribution template with a plurality of segments.
Orlovsky discloses is configured to:
determine a preset probability distribution template ([0113] “The set of standard energy profiles characterize the expected energy distribution associated with a subject in a different pose (standing, sitting, lying, walking, bending over etc.).” [0114] “At step 610, the profile generator selects a closest match for the target segment from the set of standard energy profiles and generates time dependent energy profiles 524 for each segment at step 612. The time dependent energy profiles 524 are stored in the database 520.”);
determine a plurality of probability distribution segments on the i-th probability distribution according to the preset probability distribution template, wherein i is an index value ([0117] “For each target segment of the target area 102, a current energy profile is generated by the profile generator 514 and sent to the processing unit 526 by the output unit 518 at step 624.”);
determine an intersection over union (IoU) between the preset probability distribution template and each of the probability distribution segments on the i-th probability distribution ([0118] “In an exemplary embodiment, the process of anomaly detection in fall alerts is explained using Kullback-Leibler (KL) Divergence which measures how a probability distribution differs from a reference probability distribution. A metric M.sup.i is defined by the KL Divergence as: where, P.sub.W.sup.i refers to time dependent energy profile distribution of a target segment; and P.sub.D refers to the current energy profile distribution of the target segment.” [0121] “using Kullback-Leibler (KL) Divergence is exemplary in nature and should not limit the scope of the invention. Any other suitable probability distribution function can be used for the purpose without limiting the scope of the invention.” KL divergence is a fundamental information-theoretic measure that quantifies how one probability distribution differs from a second, reference probability distribution, and therefore under BRI reads on an IoU.),
and generating an IoU variation diagram corresponding to the i-th probability distribution accordingly ([0122] “FIGS. 16A, 17A and 18A illustrate KL Divergence values over all time windows in case of normal behavior in exemplary embodiments of the invention.” [0123] “FIGS. 16B, 17B and 18B illustrate KL Divergence values over all time windows in case of actual falls in exemplary embodiments of the invention.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Newton to include a preset probability distribution template with a plurality of segments as disclosed in Orlovsky to detect movement anomalies by comparing a preset probability distribution with a current distribution (Orlovsky [0118]).
The combination of Newton/Orlovsky disclose and determine the event time point of each of the gait events belonging to the specific step based on the IoU variation diagram corresponding to each of the probability distributions (Newton: [0148] “In block 1010, the processor may extract gait biomarkers based on the identified gait events. For example, the processor may analyze the relationships between gait events and determine various quantitative measures that describe the user's walking patterns and biomechanics. The processor may determine gait biomarkers (e.g., stride length, step length, cadence, stance time, swing time, double support time, gait symmetry, etc.) based on the temporal and spatial relationships between the identified gait events, such as the time intervals between successive heel strikes or the distances between consecutive toe strikes. As an example, the processor may determine gait symmetry indices by comparing the gait parameters of the left and right limbs, such as the stride length or stance time of each leg. … the processor may use a neural network to identify gait patterns and classify gait abnormalities (e.g., by performing the operations of block 918 or any of the techniques discussed in this application).” Orlovsky: [0118] “A metric M.sup.i is defined by the KL Divergence” [0119] “A threshold T is defined such that if M.sup.i<T there is no anomaly … if M.sup.i≥T an anomaly is detected”).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOLLY HALPRIN whose telephone number is (703)756-1520. The examiner can normally be reached 12PM-8PM ET.
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, Robert (Tse) Chen can be reached at (571) 272-3672. 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.
/M.H./Examiner, Art Unit 3791
/DEVIN B HENSON/Primary Examiner, Art Unit 3791