DETAILED ACTION
This Office Action is in response to communications filed on March 26th, 2026 for Application No. 18/130,992, in which claims 1-10 and 13-15 are presented for examination. The amendments filed on March 26th, 2026 have been entered, where claims 1-2 and 5-10 are amended, claims 11-12 are canceled, and claims 13-15 are newly added.
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.
Claims 2-3, 7-8, and 10 are rejected 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.
Regarding Claim 2, the claim recites the term “biochemically coupled” (ln. 4), which is a relative term that renders the claim indefinite. The term “biochemically coupled” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. As a result, the scope of the claim is indefinite because it is unclear which motion characteristics qualify as “biochemically coupled motion characteristics” (ln. 4). Therefore, Claim 2 is rejected. The claim should be amended to clarify the qualifying criteria for “biochemically coupled motion characteristics” or otherwise modify the scope of the claim to eliminate the aforementioned indefiniteness.
Regarding Claim 3, the claim is rejected because it is dependent on a rejected claim.
Regarding Claim 7, the claim recites the term “biochemically coupled” (ln. 3), which is a relative term that renders the claim indefinite for substantially the same reasons as articulated in regard to the rejection of Claim 2 above. Therefore, it is similarly rejected and should be amended in a similar manner.
Regarding Claim 8, the claim is rejected because it is dependent on a rejected claim.
Regarding Claim 10, the claim recites the term “biochemically coupled” (ln. 3), which is a relative term that renders the claim indefinite for substantially the same reasons as articulated in regard to the rejection of Claim 2 above. Therefore, it is similarly rejected and should be amended in a similar manner.
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.
Claims 1-10 and 13-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more.
Regarding Claim 1:
Step 1: Claim 1 is a machine claim. Therefore, claims 1-4 and 13-14 are directed to a statutory category of eligible subject matter.
Step 2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the "Mental Processes" grouping of abstract ideas. Here, steps performed by the claimed machine are mental processes. Specifically, the claim recites
“the method comprising . . . calculating coordination between parts of the moving body based on correlation between the plurality of motion data items . . . calculated based on the correlation between the plurality of motion data items” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, based on correlations determined from known or observed data items, which may be aided by pen and paper);
“including remaining motion data items obtained by excluding at least one motion data item” (mental process – amounts to exercising judgment to form an opinion on which data items, from an observed or known set, should be included and excluded, which may be aided by pen and paper); and
“output coordination between parts corresponding to the plurality of motion data items of a target moving body, when remaining motion data items obtained by excluding at least one motion data item among a plurality of motion data items measured from the target moving body are input” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, with reference to known or observed input motion information, which may be aided by pen and paper).
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional elements:
“An artificial neural network model training method performed by an artificial neural network model training apparatus for inferring motion coordination . . . training an artificial neural network model using a training dataset . . . wherein the artificial neural network model is configured to . . . to the artificial neural network model” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea);
“acquiring a plurality of motion data items” (receiving data amounts to insignificant extra-solution activity because the transmission of data is incidental to the claimed subject matter); and
“including each motion data item for a plurality of parts of a moving body . . . among the plurality of motion data items as an input data item, and the coordination between the plurality of parts as a target variable” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional elements:
“An artificial neural network model training method performed by an artificial neural network model training apparatus for inferring motion coordination . . . training an artificial neural network model using a training dataset . . . wherein the artificial neural network model is configured to . . . to the artificial neural network model” (mere instructions to apply the exception using generic computer components does not provide an inventive concept);
“acquiring a plurality of motion data items” (transmitting data is well‐understood, routine, and conventional, see generally Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; see also buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014); therefore the limitation, which is recited with a high level of generality, remains insignificant extra-solution activity even upon reconsideration); and
“including each motion data item for a plurality of parts of a moving body . . . including at least one motion data item among the plurality of motion data items as an input data item, and the coordination between the plurality of parts as a target variable” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
For the reasons above, Claim 1 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claims 2-4 and 13-14. The additional limitations of the dependent claims are addressed below.
Regarding Claim 2:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 2 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites:
“wherein the calculating of the coordination between the plurality of parts of the moving body includes calculating a balance scoring result for the plurality of moving parts as the coordination between the plurality of parts” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, using specific calculating techniques, which may be aided by pen and paper).
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional element:
“wherein the plurality of motion data items includes motion data items for a plurality of moving parts having biochemically coupled motion characteristics among the plurality of parts of the moving body” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional element:
“wherein the plurality of motion data items includes motion data items for a plurality of moving parts having biochemically coupled motion characteristics among the plurality of parts of the moving body” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
Accordingly, Claim 2 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 3:
Step 2A Prong 1: See the rejection of Claim 2 above, which Claim 3 depends on.
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional element:
“wherein the motion data item includes a data item measured by inertial sensors mounted on two or more of the plurality of moving parts” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional element:
“wherein the motion data item includes a data item measured by inertial sensors mounted on two or more of the plurality of moving parts” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
Accordingly, Claim 3 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 4:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 4 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites
“wherein the calculating of the coordination between the plurality of parts of the moving body includes determining the correlation between the data items using a cross correlation value or dynamic time warp analysis” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, based on correlations determined from known or observed data items and using specific calculating techniques, which may be aided by pen and paper).
Step 2A Prong 2 & Step 2B: There are no elements left for consideration of implementation within a practical application or for consideration of significantly more.
Accordingly, Claim 4 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 5:
Step 1: Claim 5 is a machine claim. Therefore, claims 5-8 and 15 are directed to a statutory category of eligible subject matter.
Step 2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the "Mental Processes" grouping of abstract ideas. Here, the claim recites limitations that are substantially the same as the limitations of Claim 1. As a result, and as elaborated above, these limitations are abstract ideas because they are mental processes.
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional elements:
“A motion coordination inferring apparatus comprising: a sensor configured to . . . a memory configured to store one or more programs; and a processor configured to execute the one or more stored programs, wherein the processor comprises an artificial neural network model trained using a training dataset . . . and wherein the artificial neural network model is configured to . . . to the artificial neural network model” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea);
“acquire a motion data item . . . the measured motion data item obtained” (receiving data amounts to insignificant extra-solution activity because the transmission of data is incidental to the claimed subject matter); and
“measured for at least one body part among a plurality of measured motion data items that correspond to motion data items for a plurality of parts of a target moving body . . . among a plurality of motion data items that correspond to motion data items for a plurality of parts of a moving body as an input data item and . . . as a target variable” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional elements:
“A motion coordination inferring apparatus comprising: a sensor configured to . . . a memory configured to store one or more programs; and a processor configured to execute the one or more stored programs, wherein the processor comprises an artificial neural network model trained using a training dataset . . . and wherein the artificial neural network model is configured to . . . to the artificial neural network model” (mere instructions to apply the exception using generic computer components does not provide an inventive concept);
“acquire a motion data item . . . the measured motion data item obtained” (transmitting data is well‐understood, routine, and conventional, such as over a network, see generally Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; see also buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014), or from memory, see Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); see also OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93; therefore the limitation, which is recited with a high level of generality, remains insignificant extra-solution activity even upon reconsideration); and
“measured for at least one body part among a plurality of measured motion data items that correspond to motion data items for a plurality of parts of a target moving body . . . among a plurality of motion data items that correspond to motion data items for a plurality of parts of a moving body as an input data item and . . . as a target variable” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
For the reasons above, Claim 5 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claims 6-8 and 15. The additional limitations of the dependent claims are addressed below.
Regarding Claim 6:
Step 2A Prong 1: See the rejection of Claim 5 above, which Claim 6 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites
“generate information representing motion characteristics of the target moving body based on the output coordination between the plurality of parts” (mental process – amounts to exercising judgement to form an opinion on motion characteristics of a moving body, based on known or observed data, which may be aided by pen and paper).
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional element:
“an output unit configured to” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional element:
“an output unit configured to” (mere instructions to apply the exception using generic computer components does not provide an inventive concept).
Accordingly, Claim 6 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 7:
Step 2A Prong 1: See the rejection of Claim 5 above, which Claim 7 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites:
“wherein a balance scoring result for the plurality of moving parts is used as the coordination between the parts” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, using specific calculating techniques, which may be aided by pen and paper).
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional element:
“wherein the plurality of motion data items includes motion data items for a plurality of moving parts having biochemically coupled motion characteristics of the learning motion body or the target moving body” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional element:
“wherein the plurality of motion data items includes motion data items for a plurality of moving parts having biochemically coupled motion characteristics of the learning motion body or the target moving body” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
Accordingly, Claim 7 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 8:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 8 depends on.
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional element:
“wherein the measured motion data item is measured by an inertial sensor” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea) and
“mounted on at least one moving part among the plurality of moving parts of the target moving body” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional element:
“wherein the measured motion data item is measured by an inertial sensor” (mere instructions to apply the exception using generic computer components does not provide an inventive concept) and
“mounted on at least one moving part among the plurality of moving parts of the target moving body” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
Accordingly, Claim 8 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 9:
Step 1: Claim 9 is a machine claim. Therefore, claims 9-10 are directed to a statutory category of eligible subject matter.
Step 2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the "Mental Processes" grouping of abstract ideas. Here, the claim recites limitations that are substantially the same as the limitations of Claim 1. As a result, and as elaborated above, these limitations are abstract ideas because they are mental processes.
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional elements:
“A non-transitory computer-readable recording medium storing a computer program thereon for executing an artificial neural network model training method for inferring motion coordination on a computer, the method comprising . . . training an artificial neural network model using a training dataset . . . wherein the artificial neural network model is configured to . . . to the artificial neural network model” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea);
“acquiring a plurality of motion data items” (receiving data amounts to insignificant extra-solution activity because the transmission of data is incidental to the claimed subject matter); and
“items including each motion data items for a plurality of parts of a moving body . . . among the plurality of motion data items as an input data item, and the coordination between the plurality of parts . . . as a target variable” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional elements:
“A non-transitory computer-readable recording medium storing a computer program thereon for executing an artificial neural network model training method for inferring motion coordination on a computer, the method comprising . . . training an artificial neural network model using a training dataset . . . wherein the artificial neural network model is configured to . . . to the artificial neural network model” (mere instructions to apply the exception using generic computer components does not provide an inventive concept);
“acquiring a plurality of motion data items” (transmitting data is well‐understood, routine, and conventional, see generally Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; see also buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014); therefore the limitation, which is recited with a high level of generality, remains insignificant extra-solution activity even upon reconsideration); and
“items including each motion data items for a plurality of parts of a moving body . . . among the plurality of motion data items as an input data item, and the coordination between the plurality of parts . . . as a target variable” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
For the reasons above, Claim 9 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claim 10. The additional limitations of the dependent claim are addressed below.
Regarding Claim 10, the claim recites limitations that are all substantially the same as limitations of Claim 2, in the form of a computer readable recording medium. The claim is also directed to performing mental processes without integration into a practical component or significantly more.
Accordingly, Claim 10 is rejected under the same rationale.
Regarding Claim 13:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 13 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites
“and wherein inferring coordination . . . includes inputting motion data for fewer than N moving parts and inferring coordination between the N moving parts” (mental process – amounts to exercising judgment to form an opinion on coordination between the N moving parts, with reference to known or observed input motion information with fewer than N body parts, which may be aided by pen and paper).
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional elements:
“using the trained artificial neural network model” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea);
“wherein the acquiring of the plurality of motion data items includes acquiring motion data items for N moving parts” (receiving data amounts to insignificant extra-solution activity because the transmission of data is incidental to the claimed subject matter); and
“during training of the artificial neural network model” (amounts to merely generally linking the use of the judicial exception to a particular technological environment or field of use, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional elements:
“using the trained artificial neural network model” (mere instructions to apply the exception using generic computer components does not provide an inventive concept);
“wherein the acquiring of the plurality of motion data items includes acquiring motion data items for N moving parts” (transmitting data is well‐understood, routine, and conventional, see generally Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; see also buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014); therefore the limitation, which is recited with a high level of generality, remains insignificant extra-solution activity even upon reconsideration); and
“during training of the artificial neural network model” (merely generally linking the use of the judicial exception to a particular technological environment or field of use does not provide an inventive concept).
Accordingly, Claim 13 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 14:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 14 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites:
“wherein the calculating of the coordination between the parts of the moving body includes determining a cross-correlation value between motion data items for a first moving part and motion data items for a second moving part” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, based on correlations determined from known or observed data items, which may be aided by pen and paper to determine the specific cross-correlation value).
Step 2A Prong 2 & Step 2B: There are no elements left for consideration of implementation within a practical application or for consideration of significantly more.
Accordingly, Claim 14 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 15:
Step 2A Prong 1: See the rejection of Claim 5 above, which Claim 15 depends on. Here, the claim recites additional elements that are mental processes. Specifically, the claim recites
“output the coordination between the plurality of parts as the target variable rather than to output predicted motion data for a specific body part” (mental process – amounts to exercising judgment to form an opinion on coordination between body parts, with reference to known or observed input motion information, as opposed to other mental process outputs, which may be aided by pen and paper).
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
The claim recites the additional element:
“wherein the artificial neural network model comprises a multi-layer neural network trained to output” (amounts to mere instructions to apply the judicial exception on generic and unspecialized computer components, which do not impose any meaningful limits on practicing the abstract idea).
Step 2B: The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
The claim recites the additional element:
“wherein the artificial neural network model comprises a multi-layer neural network trained to output” (mere instructions to apply the exception using generic computer components does not provide an inventive concept).
Accordingly, Claim 15 is rejected as being directed to an abstract idea without significantly more.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 5, 9, 13, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al. (hereinafter Liu) (“A wearable motion capture device able to detect dynamic motion of human limbs”) in view of Park et al. (hereinafter Park) (“3D Human Pose Estimation with Relational Networks”).
Regarding Claim 1, Liu teaches an artificial neural network model training method performed by an artificial neural network model training apparatus for inferring motion coordination, the method comprising (Sec. “Methods”, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained . . . The model training is carried out using iterative least square method in MATLAB software”, where the “neural network model” is “trained [using] . . . MATLAB software”, which requires a computer apparatus to carry out the “training”; see also Pg. 4, Col. 1, Para. 2, “we use a three layer back propagation (BP) neural network to model intra-limb coordination between shank and thigh motions in walking and running”, where the “model” has an artificial structure of “a three layer back propagation (BP) neural network”; Pg. 2, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination for human lower limb”, where “characterizing the intra-limb coordination” is inferring motion coordination; and Pg. 10, Col. 1, Para. 6, “The filtered data are transmitted wirelessly to a host computer through a Bluetooth at a frequency of 100Hz and used to implement data fusion to figure out three-dimensional motion velocity, acceleration and attitude in real time. The reference motion data acquired by VICON system is collected by the host computer as well . . . The intra-limb coordination model is trained off line”, where the “host computer”, which is the apparatus, is used to “train” “[t]he intra-limb coordination model . . . off line”):
acquiring a plurality of motion data items including each motion data item for a plurality of parts of a moving body (Pg. 10, Col. 1, Para. 7, “The training datasets are collected from a training experiment when the subject is walking and running on a treadmill with a velocity increasing from 0 to 10 km/h at an interval of 1 km/h. The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where “shank motion data”, which is acquired , “collected”, as input and “thigh motion data”, is acquired as output, which in combination, “shank” and “thigh” are a plurality of moving body parts; see also Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, where the “Motion data”, which as discussed above is for a plurality of body parts, includes a plurality of motion data items, “motion velocity, motion acceleration, and attitude angles”; see generally Pg. 3, Col. 2, Para. 2, “Lower limb motion capture accounts for a high level importance in diagnose [including acquiring data] . . . on thigh and shank to measure the motion of lower limb”)
calculating coordination between parts of the moving body based on correlation between the plurality of motion data items (Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb. Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank) are used as inputs of the network, and attitude angles of the proximal segment (thigh) are used as outputs”, where coordination between parts of the moving body is calculated, “characterize the intra-limb coordination of human lower limb”, is based on a correlative relationship between the plurality of motion data items used as inputs, “Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank)”, and the plurality of motion data items used as outputs, “attitude angles of the proximal segment (thigh)”; see generally Pg. 4, Col. 1, Para. 1, “In our study, we validate a natural intra-limb coordination relationship generally exists between thigh and shank in human walking and running” and Pg. 9, Col. 1, Para. 2, “Preliminary experiments demonstrate that characteristic indicators of knee flexion and shank deflection in human walking and running can be potentially used for health assessment or motion function evaluation”); and
training an artificial neural network model using a training dataset including . . . motion data items obtained by . . . [the] at least one motion data item among the plurality of motion data items as an input data item (Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained for each subject by using training datasets . . . The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where, as discussed above, the “shank motion data”, which is “used as the inputs”, includes the plurality of data motion items, see Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”),
and the coordination between the plurality of parts, calculated based on the correlation between the plurality of motion data items, as a target variable (Pg. 4, Col. 1, Para. 2, “Here, we use a three-layer back propagation (BP) neural network to model intra-limb coordination between shank and thigh motions . . . Attitude angle (elevation angle), motion velocity, angular rate and motion acceleration of the shank are designated as inputs of the network. And the attitude angles of the thigh are as outputs of the network”, where “back propagation” is used to train the “neural network” to generate a target “intra-limb coordination between shanks and thigh motions”; see also Pg. 10, Col. 1, Para. 7, “The trained intra-limb coordination model is validated by determining the thigh motion from the shank motion data detected by our device worn on the subject who conducts walking and running experiments similar with the training experiment”, where the “model is validated” to determine whether the variable output of the “intra-limb coordination” of the plurality of parts, “high motion from the shank motion”, conforms with the expected target output; Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb. Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank) are used as inputs of the network, and attitude angles of the proximal segment (thigh) are used as outputs”, where coordination between parts of the moving body is calculated, “characterize the intra-limb coordination of human lower limb”, is based on a correlative relationship between the plurality of motion data items used as inputs, “Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank)”, and the plurality of motion data items used as outputs, “attitude angles of the proximal segment (thigh)”; see generally Pg. 4, Col. 1, Para. 1, “In our study, we validate a natural intra-limb coordination relationship generally exists between thigh and shank in human walking and running” and Pg. 9, Col. 1, Para. 2, “Preliminary experiments demonstrate that characteristic indicators of knee flexion and shank deflection in human walking and running can be potentially used for health assessment or motion function evaluation”),
wherein the artificial neural network model is configured to output coordination between parts corresponding to the plurality of motion data items of a target moving body (Pg. 9, Fig. 7, “Results of lower limb motion capture in the sagittal plane by using single device worn on the shank and determining the thigh motion from the shank motion by the trained neural network model of intra-limb coordination”, where the artificial “trained neural network model” is configured to output the “intra-limb coordination” between “the thigh motion from the shank motion” parts, which corresponds to motion data items for a plurality of parts of a target moving body, see Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . use motion information of shank as the inputs of the network (including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt) as the outputs”, where the sensor “device”, see Pg. 8, Col. 1, Para. 2, “our device measures the motion velocity and motion acceleration by using the flow sensors”, acquires “motion of shank is directly measured”, which includes motion data items, for example “shark attitude angles”, from a plurality of motion data items, “including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt)”, corresponding to a plurality of parts of a target moving body, “shank” and “thigh”; see also Pg. 5, Col. 2, Para. 5, “A subject wears a device on his wrist and shank”, where a plurality of sensor “device[s]” can be used to measure a plurality of parts of a target moving body, “wrist and shank”),
when . . . motion data items obtained by . . . [the] at least one motion data item among a plurality of motion data items measured from the target moving body are input to the artificial neural network model (Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . The neural network model of intra-limb coordination between shank and thigh has 30 hidden neurons and use motion information of shank as the inputs of the network”; see also Pg. 9, Fig. 7, “Results of lower limb motion capture in the sagittal plane by using single device worn on the shank and determining . . . by the trained neural network model of intra-limb coordination”, where a “the trained neural network model of intra-limb coordination” is used; and Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, where the “motion information” includes a plurality of data; see also Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained for each subject by using training datasets . . . The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where, as discussed above, the “shank motion data”, which is “used as the inputs”, includes the plurality of data motion items, see Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”).
Liu does not explicitly disclose . . . remaining . . . excluding . . . remaining . . . excluding . . . (where the training of the neural network and outputting using the neural network is not specifically discussed in regard to remaining motion data items obtained through a process that excludes some motion data items).
However, Park teaches . . . [a method for processing body part data using neural networks] (Pg. 1, Abstract, “In this paper, we propose a novel 3D human pose estimation algorithm from a single image based on neural networks. We adopted the structure of the relational networks
in order to capture the relations among different body parts”), [comprising] . . .
[training the neural networks using] remaining [data items obtained by] . . . excluding [at least one data item] . . . (Pg. 1-2, Para. 3-1, “we propose a method that can impose robustness to the missing points during the training. The proposed method, named as relational dropout, randomly drops one of the pair features when they are averaged, which simulates the case that certain groups of joints are missing during the training”, where “relational dropout” excludes at least one data item, “randomly drops one of the pair features” in order to obtain remaining data items for training, “simulates the case that certain groups of joints are missing during the training”; see also Pg. 5, Para. 1, “Dropping features of a certain group simulates the case that the 2D points belonging to the dropping group are missing” and Pg. 5, Para. 3, “We used stacked hourglass network [22] to infer 2D joint positions from training and test images”)
remaining [data items obtained by] . . . excluding [at least one data item are input to the neural network to generate an output] . . . (Pg. 5, Para. 1, “At test time, we simply apply relational dropout to the groups that contain missing points” and Pg. 1-2, Para. 3-1, “we propose a method that can impose robustness to the missing points during the training. The proposed method, named as relational dropout, randomly drops one of the pair features when they are averaged, which simulates the case that certain groups of joints are missing during the training”, where “relational dropout” excludes at least one data item, “randomly drops one of the pair features” in order to obtain remaining data items for output “test[ing]”, “At test time, we simply apply relational dropout to the groups that contain missing points”; see also Pg. 5, Para. 1, “Dropping features of a certain group simulates the case that the 2D points belonging to the dropping group are missing” and Pg. 5, Para. 3, “We used stacked hourglass network [22] to infer 2D joint positions from training and test images”).
Before the effective filing date of the invention, it would have been obvious to one of ordinary skill in the art to combine the training of an artificial neural network model using a training dataset including at least one motion data item among a plurality of motion data items and wherein the artificial neural network model is configured to output coordination between parts corresponding to the plurality of motion data items of a target moving body when using at least one motion data item among a plurality of motion data items measured from the target moving body as input to the artificial neural network model of Liu with the processing of body part data using neural networks, wherein a neural networks is trained using remaining data items obtained by excluding at least one data item and remaining data items obtained by excluding at least one data item are input to the neural network to generate an output of Park in order to simulate missing body part information, which will allow the network to estimate body coordination when only some body part data is visible (Park, Pg. 5, Para. 1, “Dropping features of a certain group simulates the case that the 2D points belonging to the dropping group are missing. Hence, the network learns to estimate the 3D pose not only when all the 2D joints are visible but also when some of them are invisible”; see also Liu, Pg. 10, Col. 1, Para. 7, “The trained intra-limb coordination model is validated by determining the thigh motion from the shank motion data detected by our device worn on the subject who conducts walking and running experiments similar with the training experiment”), which allows for meaningful estimations of the entire body with broad applicability across computer vision tasks (Park, Pg. 1, Para. 2, “Human pose estimation (HPE) is a fundamental task in computer vision, which can be adopted to many applications such as action recognition, human behavior analysis, virtual reality and so on. Estimating 3D pose of human body joints from 2D joint locations is an under-constrained problem. However, since human joints are connected by rigid bodies, the search space of 3D pose is limited to the range of joints. Therefore, it is able to learn 3D structures from 2D positions, and numerous studies on 2D-to-3D mapping of human body have been conducted”; Park, Pg. 4, Para. 1, “For 2D inputs, we used (x,y) coordinates of detected joints in RGB images whereas relative positions of (x,y, z) coordinates from the root joint are estimated for 3D pose estimation”) and contributes to improved model performance (Park, Pg. 6, Para. 3, “The proposed relational network (RN) gains 0.7 mm improvements over the baseline on average, and it is further improved when the network is finetuned on each sequence (RN-FT), which achieves state-of-the-art performance. Therefore, it is verified that capturing relations between different groups of joints improves the pose estimation performance despite its simpler structure and training procedures than the compared methods”).
Regarding Claim 5, Liu teaches a motion coordination inferring apparatus comprising (Pg. 10, Col. 1, Para. 6, “the host computer . . . [a]nd the trained intra-limb coordination model is used to determine thigh motion from shank motion in real time”, where “the host computer”, which in combination with the “wear[able]” “device[s]” the form the apparatus, see Pg. 5, Col. 2, Para. 5, “A subject wears a device on his wrist and shank”, uses the “intra-limb coordination model” to “determine” inferences “in real time”):
a sensor configured to acquire a motion data item measured for at least one body part among a plurality of measured motion data items that correspond to motion data items for a plurality of parts of a target moving body (Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . use motion information of shank as the inputs of the network (including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt) as the outputs”, where the sensor “device”, see Pg. 8, Col. 1, Para. 2, “our device measures the motion velocity and motion acceleration by using the flow sensors”, acquires “motion of shank is directly measured”, which includes motion data items, for example “shark attitude angles”, from a plurality of motion data items, “including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt)”, corresponding to a plurality of parts of a target moving body, “shank” and “thigh”; see also Pg. 5, Col. 2, Para. 5, “A subject wears a device on his wrist and shank”, where a plurality of sensor “device[s]” can be used to measure a plurality of parts of a target moving body, “wrist and shank”);
a memory configured to store one or more programs; and a processor configured to execute the one or more stored programs, wherein the processor comprises an artificial neural network model trained using a training dataset . . . (Sec. “Methods”, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained for each subject by using training datasets . . . The model training is carried out using iterative least square method in MATLAB software”, where the “neural network model” is “trained [using] . . . MATLAB software [and a] training dataset”, which requires a memory to store the “MATLAB” program instructions, which must be executed by a processor to perform the “training” and to manage and utilize the “trained . . . model” for “real time” inference, see Pg. 10, Col. 1, Para. 6, “the host computer . . . [a]nd the trained intra-limb coordination model is used to determine thigh motion from shank motion in real time”; see also Pg. 4, Col. 1, Para. 2, “we use a three layer back propagation (BP) neural network to model intra-limb coordination between shank and thigh motions in walking and running”, where the “model” has an artificial structure of “a three layer back propagation (BP) neural network”).
The remaining limitations are substantially the same as limitations of Claim 1, therefore it is rejected under the same rationale.
Regarding Claim 9, Liu teaches a non-transitory computer-readable recording medium storing a computer program for executing an artificial neural network model training method for inferring motion coordination on a computer, the method comprising . . . (Sec. “Methods”, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained . . . The model training is carried out using iterative least square method in MATLAB software”, where the “neural network model” is “trained [using] . . . MATLAB software”, which requires a non-transitory computer-readable medium to record and store the “MATLAB” program instructions, which must be executed to perform the “training”; see also Pg. 4, Col. 1, Para. 2, “we use a three layer back propagation (BP) neural network to model intra-limb coordination between shank and thigh motions in walking and running”, where the “model” has an artificial structure of “a three layer back propagation (BP) neural network”; Pg. 2, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination for human lower limb”, where “characterizing the intra-limb coordination” is inferring motion coordination; and Pg. 10, Col. 1, Para. 6, “The filtered data are transmitted wirelessly to a host computer through a Bluetooth at a frequency of 100Hz and used to implement data fusion to figure out three-dimensional motion velocity, acceleration and attitude in real time. The reference motion data acquired by VICON system is collected by the host computer as well . . . The intra-limb coordination model is trained off line”, where the “host computer”, which includes the computer-readable recording medium and processor, is used to “train” “[t]he intra-limb coordination model . . . off line”).
The remaining limitations are substantially the same as limitations of Claim 1, therefore it is rejected under the same rationale.
Regarding Claim 13, Liu in view of Park teach the method of claim 1, wherein the acquiring of the plurality of motion data items includes acquiring motion data items for N moving parts during training of the artificial neural network model (Liu, Pg. 10, Col. 1, Para. 7, “The training datasets are collected from a training experiment when the subject is walking and running on a treadmill with a velocity increasing from 0 to 10 km/h at an interval of 1 km/h. The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where “shank motion data”, which is acquired , “collected”, as input and “thigh motion data”, is acquired as output, which in combination, “shank” and “thigh” are a plurality of moving body parts, which, in view of Park can be referred to as comprising N moving parts, see Park, Pg. 5, Para. 1, “Dropping features of a certain group simulates the case that the 2D points belonging to the dropping group are missing. Hence, the network learns to estimate the 3D pose not only when all the 2D joints are visible but also when some of them are invisible”; see also Liu, Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, where the “Motion data”, which as discussed above is for a plurality of body parts, includes a plurality of motion data items, “motion velocity, motion acceleration, and attitude angles”, which occurs during the “training” of the artificial neural network, see Liu, Sec. “Methods”, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained”; see generally Liu, Pg. 3, Col. 2, Para. 2, “Lower limb motion capture accounts for a high level importance in diagnose [including acquiring data] . . . on thigh and shank to measure the motion of lower limb”),
and wherein inferring coordination using the trained artificial neural network model includes inputting motion data for fewer than N moving parts and inferring coordination between the N moving parts (Liu, Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . The neural network model of intra-limb coordination between shank and thigh has 30 hidden neurons and use motion information of shank as the inputs of the network”; see also Liu, Pg. 9, Fig. 7, “Results of lower limb motion capture in the sagittal plane by using single device worn on the shank and determining . . . by the trained neural network model of intra-limb coordination”, where a “the trained neural network model of intra-limb coordination” is used; and Liu, Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, where the “motion information” includes a plurality of data; see also Liu, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained for each subject by using training datasets . . . The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where, as discussed above, the “shank motion data”, which is “used as the inputs”, includes the plurality of data motion items, see Liu, Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, which in view of Park, the motion data is for fewer than N moving parts, “apply relational dropout to the groups that contain missing points” “when . . . [some] 2D joints are . . . invisible”, to infer coordination between the N moving parts, “the network learns to estimate the 3D pose not only when all the 2D joints are visible”, see Park, Pg. 5, Para. 1, “At test time, we simply apply relational dropout to the groups that contain missing points” and Park, Pg. 5, Para. 1, “Dropping features of a certain group simulates the case that the 2D points belonging to the dropping group are missing. Hence, the network learns to estimate the 3D pose not only when all the 2D joints are visible but also when some of them are invisible”; see also Liu, Pg. 2, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination for human lower limb”, where “characterizing the intra-limb coordination” is inferring motion coordination).
The reasons for obviousness were discussed in regard to the rejection of Claim 1 above and remain applicable here.
Regarding Claim 15, Liu in view of Park teach the apparatus of claim 5, wherein the artificial neural network model comprises a multi-layer neural network trained to output the coordination between the plurality of parts as the target variable rather than to output predicted motion data for a specific body part (Liu, Sec. “Methods”, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained . . . The model training is carried out using iterative least square method in MATLAB software”, where the “neural network model” is “trained [using] . . . MATLAB software”; see also Liu, Pg. 4, Col. 1, Para. 2, “we use a three layer back propagation (BP) neural network to model intra-limb coordination between shank and thigh motions in walking and running”, where the “model” has an artificial multi-layer structure of “a three layer back propagation (BP) neural network”; see also Liu, Pg. 2, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination for human lower limb”, where “characterizing the intra-limb coordination” is inferring motion coordination, which, is within the broadest reasonable interpretation of coordination between the plurality of parts as the target variable, see Liu, Pg. 4, Col. 1, Para. 2, “Here, we use a three-layer back propagation (BP) neural network to model intra-limb coordination between shank and thigh motions . . . Attitude angle (elevation angle), motion velocity, angular rate and motion acceleration of the shank are designated as inputs of the network. And the attitude angles of the thigh are as outputs of the network”, where the “neural network” to generate a target “intra-limb coordination between shanks and thigh motions”; see also Park, Pg. 4, Para. 1, “For 2D inputs, we used (x,y) coordinates of detected joints in RGB images whereas relative positions of (x,y, z) coordinates from the root joint are estimated for 3D pose estimation”, where, as emphasized by Park, the target is for coordination between the plurality of parts as the target variable, “estimated for 3D pose estimation”, rather than to output predicted motion data for a specific body part, a particular “(x,y) coordinate[] of [a] detected joint[]”).
The reasons for obviousness were discussed in regard to the rejection of Claim 1 above and remain applicable here.
Claims 2 and 6-8, and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Liu in view of Park and Virkar et al. (hereinafter Virkar) (Pat. Pub. No. US 2021/0322856 A1).
Regarding Claim 2, Liu in view of Park teach the artificial neural network model training method of claim 1, wherein the plurality of motion data items includes motion data items for a plurality of moving parts having biochemically coupled motion characteristics among the plurality of parts of the moving body (Pg. 10, Col. 1, Para. 7, “The training datasets are collected from a training experiment when the subject is walking and running on a treadmill with a velocity increasing from 0 to 10 km/h at an interval of 1 km/h. The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where “shank motion data” and “thigh motion data”, in combination, are a plurality of moving body parts; see also Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, where the “Motion data”, which as discussed above is for a plurality of body parts, includes a plurality of motion data items, “motion velocity, motion acceleration, and attitude angles”; and where the moving body parts have biochemically coupled, “natural”, motion characteristics, see Pg. 2, Col. 2, Para. 2, “In addition, we study the intra-limb coordination relationship between shank and thigh in human walking and running, and find the natural coordination model for human lower limb”), and
wherein the calculating of the coordination between the plurality of parts of the moving body includes calculating a [correlative relationship] . . . result for the plurality of moving parts as the coordination between the plurality of parts (Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb. Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank) are used as inputs of the network, and attitude angles of the proximal segment (thigh) are used as outputs”, where coordination between parts of the moving body is calculated, “characterize the intra-limb coordination of human lower limb”, is based on a correlative relationship between the plurality of motion data items used as inputs, “Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank)”, and the plurality of motion data items used as outputs, “attitude angles of the proximal segment (thigh)”; see generally Pg. 4, Col. 1, Para. 1, “In our study, we validate a natural intra-limb coordination relationship generally exists between thigh and shank in human walking and running” and Pg. 9, Col. 1, Para. 2, “Preliminary experiments demonstrate that characteristic indicators of knee flexion and shank deflection in human walking and running can be potentially used for health assessment or motion function evaluation”).
Liu in view of Park does not explicitly disclose . . . a balance scoring . . . .
However, Virkar teaches . . . [calculating a coordination between a plurality of parts of the moving body includes calculating] a balance scoring [result for the plurality of moving parts] . . . (Para. [0021], “The processor may be configured to estimate a position of a plurality of joints of the body by applying a second trained learning machine to the isolated and identified part of the body within the images. The processor may be configured to determine a center of mass of the user based on the position of the plurality of joints . . . . The processor may be configured to calculate a balance score based on the changes in the center of mass, wherein the balance score is indicative of deviations of the center of mass”, where the “balance score based on the changes in the center of mass” is a balancing score result for a plurality of moving parts, “a plurality of joints of the body” experiencing “changes in the center of mass”, and where “estimate a position of a plurality of joints of the body” is calculating a coordination between a plurality of parts of a moving body).
Before the effective filing date of the invention, it would have been obvious to one of ordinary skill in the art to combine the calculation of a motion coordination of a plurality of moving body parts, including calculating a correlative relationship between the plurality of moving body parts as the movement coordination of Liu in view of Park with the calculating of a coordination between a plurality of parts of the moving body, including calculating a balance scoring result for the plurality of moving parts of Virkar in order to display a motion coordination result that includes information relevant to the safety of the participant engaging in the motion (Virkar, Para. [0094], “the system can generate an alert that the patient is likely to lose balance and fall”), which will augment the utility of the motion coordination result by users in clinical settings (Virkar, Para. [0027], “in response to determining that the balance score is less than a threshold balance score, generate an alert on the user interface”), where the subjects of motion coordination inferencing may be prone to losing balance because of an injury (compare Liu, Pg. 7-8, Col. 2-1, Para. 2-1, “People with knee injury suffer from weakened knee flexion ability and thus exhibit smaller maximum knee angles than healthy people in walking and running due to pain or pathological knee constraints” with Virkar, Para. [0092], “For example, a physical therapist may wish to monitor a patient's reflexes or equilibrium. When performing various poses, a patient may lose balance and may or may not correct himself/herself without falling”).
Regarding Claim 6, Liu in view of Park and Virkar teach the motion coordination inferring apparatus of claim 5, further comprising: an output unit configured to generate information representing motion characteristics of the target moving body (Liu, Pg. 10, Col. 1, Para. 6, “the host computer . . . [a]nd the trained intra-limb coordination model is used to determine thigh motion from shank motion in real time”, where “the host computer”, which in combination with the “wear[able]” “device[s]” the form the apparatus, and, in view of Virkar, includes an output unit, “user interface”, which generates information, “an alert”, which represents motion characteristics that the target body is likely to fall, see Virkar, Para. [0027], “in response to determining that the balance score is less than a threshold balance score, generate an alert on the user interface”; see also Virkar, Abstract, “The processor may estimate a position of a plurality of joints of the body”)
based on the output coordination between the plurality of parts (Liu, Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb”, where, in view of Virkar, the “the intra-limb coordination” further includes “balance score based on the changes in the center of mass”, see Virkar, Para. [0021], “The processor may be configured to estimate a position of a plurality of joints of the body by applying a second trained learning machine to the isolated and identified part of the body within the images. The processor may be configured to determine a center of mass of the user based on the position of the plurality of joints . . . . The processor may be configured to calculate a balance score based on the changes in the center of mass, wherein the balance score is indicative of deviations of the center of mass”, where the “balance score based on the changes in the center of mass” is information representing motion characteristics of the target body, which is based on the output coordination between the plurality of parts of the target moving body, “a plurality of joints of the body” experiencing “changes in the center of mass”, and where “estimate a position of a plurality of joints of the body” is calculating a coordination between a plurality of parts of a moving body; see Liu, Pg. 9, Fig. 7, “Results of lower limb motion capture in the sagittal plane by using single device worn on the shank and determining the thigh motion from the shank motion by the trained neural network model of intra-limb coordination”, where the artificial “trained neural network model” is configured to output the “intra-limb coordination” between “the thigh motion from the shank motion” parts, which corresponds to motion data items for a plurality of parts of a target moving body, see Liu, Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . use motion information of shank as the inputs of the network (including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt) as the outputs”, where the sensor “device”, see Liu, Pg. 8, Col. 1, Para. 2, “our device measures the motion velocity and motion acceleration by using the flow sensors”, acquires “motion of shank is directly measured”, which includes motion data items, for example “shark attitude angles”, from a plurality of motion data items, “including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt)”, corresponding to a plurality of parts of a target moving body, “shank” and “thigh”; see also Liu, Pg. 5, Col. 2, Para. 5, “A subject wears a device on his wrist and shank”, where a plurality of sensor “device[s]” can be used to measure a plurality of parts of a target moving body, “wrist and shank”).
The reasons for obviousness were discussed in regard to the rejection of Claim 2 above and remain applicable here.
Regarding Claim 7, Liu in view of Park and Virkar teach the motion coordination inferring apparatus of claim 5, wherein the plurality of motion data items includes motion data items for a plurality of moving parts having biochemically coupled motion characteristics of the learning motion body or the target moving body (Liu, Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . use motion information of shank as the inputs of the network (including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt) as the outputs”, where the sensor “device”, see Liu, Pg. 8, Col. 1, Para. 2, “our device measures the motion velocity and motion acceleration by using the flow sensors”, acquires “motion of shank is directly measured”, which includes motion data items, for example “shark attitude angles”, from a plurality of motion data items, “including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt)”, corresponding to a plurality of parts of a target moving body, “shank” and “thigh”; see also Liu, Pg. 5, Col. 2, Para. 5, “A subject wears a device on his wrist and shank”, where a plurality of sensor “device[s]” can be used to measure a plurality of parts of a target moving body, “wrist and shank”; and where the moving body parts have biochemically coupled, “natural”, motion characteristics, see Liu, Pg. 2, Col. 2, Para. 2, “In addition, we study the intra-limb coordination relationship between shank and thigh in human walking and running, and find the natural coordination model for human lower limb”),
and wherein a balance scoring result for the plurality of moving parts is used as the coordination between the parts (Liu, Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb. Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank) are used as inputs of the network, and attitude angles of the proximal segment (thigh) are used as outputs”, where coordination between parts of the moving body is calculated, “characterize the intra-limb coordination of human lower limb”, “in real time” for deployment, see Liu, Pg. 10, Col. 1, Para. 6, “the host computer . . . [a]nd the trained intra-limb coordination model is used to determine thigh motion from shank motion in real time”, and where, in view of Virkar, the coordination comprises “a balance score”, see Virkar, Para. [0021], “The processor may be configured to estimate a position of a plurality of joints of the body by applying a second trained learning machine to the isolated and identified part of the body within the images. The processor may be configured to determine a center of mass of the user based on the position of the plurality of joints . . . . The processor may be configured to calculate a balance score based on the changes in the center of mass, wherein the balance score is indicative of deviations of the center of mass”).
The reasons for obviousness were discussed in regard to the rejection of Claim 2 above and remain applicable here.
Regarding Claim 8, Liu in view of Park and Virkar teach the motion coordination inferring apparatus of claim 7, wherein the measured motion data item is measured by an inertial sensor mounted on at least one moving part among the plurality of moving parts of the target moving body (Liu, Pg. 3, Fig. 2, “The motion of shank is directly measured by the device worn on the shank . . . use motion information of shank as the inputs of the network (including shank attitude angles γt, θt, motion velocity vb, and the corresponding derivatives angular rate ωb and motion acceleration ab) and use attitude angles of thigh (γt, θt) as the outputs”, where the measured motion data item, such as “shank attitude angles”, “is directly measured by the device worn on the shank”, which is one of the plurality of moving parts, “shank . . . [and] thigh”, of the target moving body; see also Liu, Pg. 1, Abstract, “Here, a motion capture method with integral-free velocity detection is proposed and a wearable device is developed by incorporating micro tri-axis flow sensors with micro tri-axis inertial sensors”, where the “wearable device” includes “inertial sensors”).
Regarding Claim 10, the additional elements of the dependent claim are substantially the same as limitations of Claim 2, therefore it is rejected under the same rationale.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Liu in view of Park, Virkar, and Solinsky et al. (hereinafter Solinsky) (Pat. Pub. No. US 2011/0208444 A1).
Regarding Claim 3, Liu in view of Park and Virkar teach the artificial neural network model training method of claim 2, wherein the motion data item includes a data item (Liu, Pg. 10, Col. 1, Para. 7, “The neural network model representing intra-limb coordination relationship of human lower limb is trained for each subject by using training datasets . . . The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where, as discussed above, the “shank motion data”, which is “used as the inputs”, includes the plurality of data motion items, see Liu, Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”) . . . .
Liu in view of Park and Virkar do not explicitly disclose . . . measured by inertial sensors mounted on two or more of the plurality of moving parts.
However, Solinsky teaches . . . [body part data items] measured by inertial sensors mounted on two or more of the plurality of moving parts (Para. [0003], “This application describes example systems and methods for placing onto a mammal's lower body, leg and thigh limbs, a set of paired bands to measure the lower body locomotion (for bipedalism, upright locomotion) and, if desired, additional arm strapped forearm and arm paired bands on the upper body (for complex motion[)] . . . that measure [data for] . . . On-band data processing and networked, intra-band RF connectivity from multiple limbs”, where the sensor “bands” may be mounted on both the “leg” and “arm” and where the bands include “inertial” “sensors”, see Para. [0321], “gyro inertial motion sensing can be used to monitor angular motion”).
Before the effective filing date of the invention, it would have been obvious to one of ordinary skill in the art to combine the artificial neural network training method using body part motion data items of Liu in view of Park and Virkar with the measurement of body part data items by inertial sensors mounted on two or more of the plurality of moving parts of Solinsky in order to evaluation movement patterns associated with multiple body part inputs (Solinsky, Para. [0302] – [0313], “the calibrated data has been stored in the included band controller and processing unit and is used to . . . intra-band data processing, for . . . cross-correlation time and spatial data analysis (labeled "CrossCorr"), using the temporal data sets and process spatiotemporal data sets”, where “cross-correlation time and spatial data analysis” is used to generate “intra-band data processing” metrics of data collected across multiple bands “from multiple limbs”, see generally Solinsky, Para. [0003], “This application describes example systems and methods for placing onto a mammal's lower body, leg and thigh limbs, a set of paired bands to measure the lower body locomotion (for bipedalism, upright locomotion) and, if desired, additional arm strapped forearm and arm paired bands on the upper body (for complex motion, crawling, and in other applications, or four calf limb quadrupedalism locomotion) . . . [which allows for] networked, intra-band RF connectivity from multiple limbs”), which is useful for evaluating movement patterns of injured participants (compare Solinsky, Para. [0003], “networked, intra-band RF connectivity from multiple limbs, can be used to produce simple, energy-optimized, least-action metrics of mammal locomotion . . . These technology metrics include assessment of locomotion related neurological functionality of body, limbs, and muscle disorders” with Liu, Pg. 7-8, Col. 2-1, Para. 2-1, “People with knee injury suffer from weakened knee flexion ability and thus exhibit smaller maximum knee angles than healthy people in walking and running due to pain or pathological knee constraints”).
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Liu in view of Park and Solinsky.
Regarding Claim 4, Liu in view of Park and Solinsky teach the artificial neural network model training method of claim 1, wherein the calculating of the coordination between the plurality of parts of the moving body includes determining the correlation between the data items (Liu, Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb. Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank) are used as inputs of the network, and attitude angles of the proximal segment (thigh) are used as outputs”, where coordination between parts of the moving body is calculated, “characterize the intra-limb coordination of human lower limb”, is based on a correlative relationship between the plurality of motion data items used as inputs, “Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank)”, and the plurality of motion data items used as outputs, “attitude angles of the proximal segment (thigh)”; see generally Liu, Pg. 4, Col. 1, Para. 1, “In our study, we validate a natural intra-limb coordination relationship generally exists between thigh and shank in human walking and running” and Liu, Pg. 9, Col. 1, Para. 2, “Preliminary experiments demonstrate that characteristic indicators of knee flexion and shank deflection in human walking and running can be potentially used for health assessment or motion function evaluation”)
using a cross correlation value or dynamic time warp analysis (Liu, Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb”, where, in view of Solinsky, the “characterization” includes “intra-band data processing” through “cross-correlation time and spatial data analysis”, see Solinsky, Para. [0302] – [0313], “the calibrated data has been stored in the included band controller and processing unit and is used to . . . 3) . . . a. the detection of TD and TO in order to locate the periodic and aperiodic points in the gait cycle data for a single limb . . . 4) The intra-band data processing, for a. combining L/R limb gait and Balance & Track metrics, and b. calf/thigh (U/L) Q-angle metrics, and c. cross-correlation time and spatial data analysis (labeled "CrossCorr"), using the temporal data sets and process spatiotemporal data sets output of 3) above”, where the “cross-correlation time and spatial data analysis (labeled "CrossCorr")” is the cross correlation value, which is used to conduct analysis of body part data items, such as “periodic and aperiodic points in the gait cycle data for a single limb”; see generally Solinsky, Abstract, “An example sensor band configured for attachment to a calf of a mammal and used in measuring track and balance motion of the mammal includes one or more first sensors for sensing muscle circumferential pressure at multiple positions”).
The reasons for obviousness were discussed in regard to the rejection of Claim 3 above and remain applicable here.
Regarding Claim 14, Liu in view of Park and Solinsky teach the method of claim 1, wherein the calculating of the coordination between the parts of the moving body includes (Liu, Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb. Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank) are used as inputs of the network, and attitude angles of the proximal segment (thigh) are used as outputs”, where coordination between parts of the moving body is calculated, “characterize the intra-limb coordination of human lower limb”, is based on a correlative relationship between the plurality of motion data items used as inputs, “Attitude angles, angular rate, motion velocity and acceleration of distal segment (shank)”, and the plurality of motion data items used as outputs, “attitude angles of the proximal segment (thigh)”; see generally Liu, Pg. 4, Col. 1, Para. 1, “In our study, we validate a natural intra-limb coordination relationship generally exists between thigh and shank in human walking and running” and Liu, Pg. 9, Col. 1, Para. 2, “Preliminary experiments demonstrate that characteristic indicators of knee flexion and shank deflection in human walking and running can be potentially used for health assessment or motion function evaluation”)
determining a cross-correlation value between motion data items for a first moving part and motion data items for a second moving part (Liu, Pg. 10, Col. 1, Para. 7, “The training datasets are collected from a training experiment when the subject is walking and running on a treadmill with a velocity increasing from 0 to 10 km/h at an interval of 1 km/h. The shank motion data are used as the inputs and the thigh motion data are used as outputs of the neural network”, where “shank motion data”, which is acquired , “collected”, as input and “thigh motion data”, is acquired as output, which in combination, “shank” and “thigh” are a plurality of moving body parts, wherein , “shank” is the first moving part and “thigh” is the second moving part; Liu, Pg. 3, Fig. 1, “Motion data including three-dimensional motion velocity, motion acceleration, and attitude angles can be measured by our device”, where the “Motion data”, which as discussed above is for a plurality of body parts, includes a plurality of motion data items, “motion velocity, motion acceleration, and attitude angles”; see also Park, Pg. 4, Para. 1, “For 2D inputs, we used (x,y) coordinates of detected joints in RGB images whereas relative positions of (x,y, z) coordinates from the root joint are estimated for 3D pose estimation”, where, as emphasized by Park, the target is for coordination between the plurality of parts as the target variable, “estimated for 3D pose estimation”; Liu, Pg. 8, Col. 2, Para. 2, “We establish a neural network model to characterize the intra-limb coordination of human lower limb”, where, in view of Solinsky, the “characterization” includes “intra-band data processing” through “cross-correlation time and spatial data analysis”, see Solinsky, Para. [0302] – [0313], “the calibrated data has been stored in the included band controller and processing unit and is used to . . . 3) . . . a. the detection of TD and TO in order to locate the periodic and aperiodic points in the gait cycle data for a single limb . . . 4) The intra-band data processing, for a. combining L/R limb gait and Balance & Track metrics, and b. calf/thigh (U/L) Q-angle metrics, and c. cross-correlation time and spatial data analysis (labeled "CrossCorr"), using the temporal data sets and process spatiotemporal data sets output of 3) above”, where the “cross-correlation time and spatial data analysis (labeled "CrossCorr")” is the cross correlation value, which is used to conduct analysis of body part data items, such as “periodic and aperiodic points in the gait cycle data for a single limb”; see generally Solinsky, Abstract, “An example sensor band configured for attachment to a calf of a mammal and used in measuring track and balance motion of the mammal includes one or more first sensors for sensing muscle circumferential pressure at multiple positions”).
The reasons for obviousness were discussed in regard to the rejection of Claim 1, for the combination with Park, and the rejection of Claim 3, for the combination with Solinsky, above and remain applicable here.
Response to Arguments
Applicant's arguments filed on March 26th, 2026 have been fully considered. Each argument is
addressed in detail below.
I. Applicant argues the objections to the drawings should be withdrawn (Applicant’s Remarks, 03/26/2026, Pg. 8, Section “Drawings”).
Applicant’s amendments to the specification have overcome each and every objection to the drawings, as previously set forth in the November 26th, 2025 Office Action. As a result, these objections have been withdrawn.
II. Applicant argues the rejections of the claims, under 35 USC § 112, should be withdrawn (Applicant’s Remarks, 03/26/2026, Pg. 8, Section “Section 112”).
Applicant’s amendments to the claims have overcome some, but not all, of the rejections to the claims, under 35 USC § 112, as previously set forth in the November 26th, 2025 Office Action.
As a result, rejections based on indefiniteness caused by use of terms with insufficient antecedent bases have been withdrawn. Whereas, as discussed in detail above, Applicant’s amendments to the claims due not overcome the rejections based on indefiniteness caused by use of relative terms.
III. Applicant argues the rejections of the claims, under 35 USC § 102 and 35 USC § 103, should be withdrawn (Applicant’s Remarks, 03/26/2026, Pg. 8-9, Section “Sections 102 and 103”).
In response to Applicant’s amendments, the previously communicated rejections under 35 U.S.C. § 102 and 35 U.S.C. § 103, have been withdrawn. However, Applicants arguments are not persuasive in light of the new grounds for rejection, under 35 U.S.C. § 103, discussed in detail above. The new grounds of rejection rely on new prior art of record to teach the new combination of elements in the amended independent claims, which were not presented in this arrangement in any of the previously presented claims. As a result, Applicant’s arguments are rendered moot.
IV. Applicant argues the rejections of the claims, under 35 USC § 101, should be withdrawn (Applicant’s Remarks, 03/26/2026, Pg. 9-12, Section “Section 101”).
1) First, Applicant references MPEP sections, USPTO memoranda, and USPTO PTAB precedential decisions which were updated or issued after the mailing date of the November 26th, 2025 Office Action. (Pg. 10, Para. 2-3, Section “Critical Binding Authority”). As discussed above and further discussed below, this Office Action is consistent with the requirements and guidelines contained in these authoritative materials.
2) Second, Applicant argues the November 26th, 2025 Office Action is internally inconsistent because “[i]n the Section 101 rejection, the Examiner characterizes the claimed operations as a mental process that may be aided by pen and paper. Yet in the Section 102 rejection of the same claims, the Examiner requires Liu's specific computational implementation: a neural network model...trained...using iterative least square method in MATLAB software that requires a computer-readable medium to record and store the MATLAB program instructions, which must be executed by a processor” (Pg. 10, Para. 4, Section “Internal Inconsistency”) (internal quotation marks omitted).
According to MPEP 2106.04, “As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind." Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015)”.
Here, the November 26th, 2025 Office Action characterizes operations, which could arguably require a computer, as mental processes that may be aided by pen and paper. However, this is not inconsistent because the courts have found that claims requiring a computer could be performed mentally with the aid of pen and paper (MPEP 2106.04). Furthermore, it is worth point out the Liu’s specific computational implementation contains additional implementation details, such as the iterative least squared method in MATLAB software referred to by the Applicant, which are not positively recited in the claims. As a result, reaching different conclusions as to what each system requires is not internally inconsistent.
As a result, the argument is not persuasive.
3) Third, Applicant argues the November 26th, 2025 Office Action is inconsistent with the December 2025 MPEP revisions (Pg. 10-11, Para. 5-3, Section “December 2025 MPEP”).
Specifically, Applicant argues the Office Action “analyzes individual limitations in isolation without considering how the ordered combination achieves a technical result”, which “enables coordination inference from reduced sensor measurements” (Pg. 10-11, Para. 6-1).
According to MPEP 2106.05, “the Supreme Court has noted that "it is consistent with the general rule that patent claims ‘must be considered as a whole.’" Alice Corp., 573 U.S. at 218 n.3, 110 USPQ2d at 1981 (quoting Diamond v. Diehr, 450 U.S. 175, 188, 209 USPQ 1, 8-9 (1981)) . . . The Court then walked through part two of the Alice/Mayo test, in which . . . The Court considered the additional elements "as an ordered combination," and determined that "the computer components … ‘[a]dd nothing … that is not already present when the steps are considered separately’" and simply recite intermediated settlement as performed by a generic computer." 573 U.S. at 225 (citing Mayo, 566 U.S. at 79, 101 USPQ2d at 1972).”
Additionally, according to MPEP 2106.05, “A claim having broad applicability across many fields of endeavor may not provide meaningful limitations that integrate a judicial exception into a practical application or amount to significantly more”.
Here, as discussed in detail above, the claims do not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception. Specifically, similar to the claims at issue in the Alice decision, consideration of the ordered combination of additional elements simply recites intermediate settlements as performed by a generic computer and insignificant extra-solution activity, which are merely generally linked to a field of use or technological environment (MPEP 2106.05). Additionally, the parts for motion detection and neural network training have broad applicability beyond coordination inference from reduced sensor measurements (MPEP 2106.05).
As a result, the argument is not persuasive.
Additionally, Applicant argues the Office Action engages in oversimplification by characterizing “a complex AI/ML system involving neural network training, multidimensional data processing, and correlation-based computation” as “exercising judgment to form an opinion” (Pg. 11, Para. 2).
According to MPEP 2106.05(a), “When performing this evaluation, examiners should be "careful to avoid oversimplifying the claims" by looking at them generally and failing to account for the specific requirements of the claims. McRO, 837 F.3d at 1313, 120 USPQ2d at 1100”.
Here, as elaborated on in detail above, the specific requirements of the claims have been evaluated, and the additional elements relating to the AI/ML system for neural network training, data processing, and computation have been found to amount to mere instructions to apply the abstract ideas on generic computer components, insignificant extra-solution activity, and merely generally linking the abstract ideas to a particular technological environment. Therefore, these elements have not been oversimplified as exercising judgment to form an opinion.
As a result, the argument is not persuasive.
Furthermore, Applicant argues the “Office Action dismisses computer components as "generic" without analyzing the technological improvements they provide: sensor reduction (fewer sensors needed for coordination measurement), storage efficiency (trained model vs. continuous multi-sensor data streams), and computational efficiency (fewer inputs to process during inference). This violates the requirement to analyze technological improvements even when components might be considered generic in isolation” (Pg. 11, Para. 3).
According to MPEP § 2106.05(a), “In determining patent eligibility, examiners should consider whether the claim "purport(s) to improve the functioning of the computer itself" or "any other technology or technical field." Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 225, 110 USPQ2d 1976, 1984 (2014).”
Here, as discussed in detail above, the claims were analyzed to determine whether they amounted to technological improvements, but were ultimately found insufficient.
As a result, the argument is not persuasive.
4) Fourth, Applicant argues the claims reflect a “trained neural network model [that] stores learned coordination patterns, enabling inference without requiring continuous storage of multiple sensor data streams”, which “processes fewer sensor inputs during inference (fewer than N sensors for N body parts) while maintaining coordination measurement capability”, and thus the “present claims provide the same types of technological improvements recognized in Desjardins” because the claims parallel “Desjardins's recognition of ways to store knowledge more efficiently . . . maintaining a single model rather than multiple models” (Pg. 11-12, Para. 4-3, Section “Ex parte Desjardins”) (internal quotation marks omitted).
According to MPEP 2106.05(a), “An important consideration in determining whether a claim improves technology is the extent to which the claim covers a particular solution to a problem or a particular way to achieve a desired outcome, as opposed to merely claiming the idea of a solution or outcome” (see also McRO, 837 F.3d at 1314-15, 120 USPQ2d at 1102-03; DDR Holdings, 773 F.3d at 1259, 113 USPQ2d at 1107).
Additionally, according to MPEP 2106.05, “A claim having broad applicability across many fields of endeavor may not provide meaningful limitations that integrate a judicial exception into a practical application or amount to significantly more”.
Here, the asserted improvements of enabling inference without requiring continuous storage of multiple sensor data streams and processing fewer sensor inputs during inference while maintaining coordination measurement capability, at most, merely claim the idea of a solution or outcome. Specifically, the asserted improvements are recited as outcomes, without sufficient particularity of achieving the outcome or of the solution itself (MPEP 2106.05(a)). Furthermore, as discussed in detail above, the parts for motion detection and neural network training have broad applicability beyond coordination inference from reduced sensor measurements (MPEP 2106.05). This meaningfully distinguished the claims from the subject matter at issue in Desjardins, where the claims recited a particular way to achieve storage efficiency, reduced computational complexity, and solutions to technical problems in machine learning systems.
As a result, the argument is not persuasive.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 MATTHEW BRYCE GOLAN whose telephone number is (571)272-5159. The examiner can normally be reached Monday through Friday, 8:00 AM to 5:00 PM 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, Alexey Shmatov can be reached at (571) 270-3428. 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.
/MATTHEW BRYCE GOLAN/Examiner, Art Unit 2123
/ALEXEY SHMATOV/Supervisory Patent Examiner, Art Unit 2123
Prosecution Insights