DETAILED ACTION
Applicant’s arguments, filed on 12/23/2025, have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Applicants have amended their claims, filed on 12/23/2025, and therefore rejections newly made in the instant office action have been necessitated by amendment.
Claims 1-10 are the current claims hereby under examination.
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 Objections
Claims 1-7 are objected to because of the following informalities:
In claim 1, line 11, “a spatial acceleration” should read “the spatial acceleration”
In claim 1, line 11, “a spatial angular velocity” should read “the spatial angular velocity”
In claim 2, line 11, the period after “estimation model” should be replaced by a comma
In claim 3, line 5, the period after “amount data” should be replaced by a comma
In claim 4, line 6, the period after “the second feature amount” should be replaced by a comma
In claim 5, line 8, the period after “estimation model” should be replaced by a comma
In claim 6, line 4, the period after “the left-right axis” should be replaced by a comma
In claim 6, line 9, the period after “estimation model” should be replaced by a comma
In claim 7, lines 3-4, “an estimation target” should read “the estimation target”
In claim 7, line 10, “spatial angular velocity” should read “the spatial angular velocity”
In claim 7, line 14, “the instructions” should read “instructions”, as there is a lack of antecedent basis in the claims for instructions for the second processor
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-10 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1, the claim recites the limitation “a subject” in line 12. It is unclear if this is meant to refer to the subject from line 5, or a different subject. If it is meant to refer to the subject from line 5, it needs to refer back to it. If it is referring to a different subject, it needs to be distinguished from the subject from line 5. For purposes of examination, it is being interpreted as referring to the subject from line 5. Claims 2-8 are also rejected due to their dependence on claim 1.
Further regarding claim 1, the claim recites the limitation “foot movement” in line 29. It is unclear if this limitation is meant to refer to the movement of a foot from line 12, or a different foot movement. If it is meant to refer to the movement of a foot from line 12, it needs to refer back to it. If it is referring to a different foot movement, it needs to be distinguished from the movement of a foot from line 12. For purposes of examination, it is being interpreted as referring to the movement of a foot from line 12. Claims 2-8 are also rejected due to their dependence on claim 1.
Further regarding claim 1, the claim recites the limitation “waist movement” in line 29. It is unclear if this limitation is meant to refer to the movement of a waist from line 6, or a different waist movement. If it is meant to refer to the movement of a waist from line 6, it needs to refer back to it. If it is referring to a different waist movement, it needs to be distinguished from the movement of a waist from line 6. For purposes of examination, it is being interpreted as referring to the movement of a waist from line 6. Claims 2-8 are also rejected due to their dependence on claim 1.
Further regarding claim 1, the claim recites the limitation “feature amounts” in line 32. It is unclear if this limitation is meant to refer to the feature amount from line 9, or different feature amounts. If it is meant to refer to the feature amount from line 9, it needs to refer back to it. If it is meant to refer to different feature amounts, it needs to be distinguished from the feature amount from line 9. For purposes of examination, it is being interpreted as referring to the feature amount from line 9. Claims 2-8 are also rejected due to their dependence on claim 1.
Regarding claim 4, the claim recites the limitation “calculate, as the second feature amount, an average value of the first feature amounts for both feet of the subject and a difference between the first feature amounts for both feet of the subject, and an average value of the gait parameters for both feet of the subject and a difference between the gait parameters for both feet of the subject” in lines 6-10. It is unclear how the second feature amount can be all four of these calculations, as the second feature amount is a singular amount. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as the second feature amount being one of these values, not all four. Claim 5 is also rejected due to its dependence on claim 4.
Regarding claim 7, the claim recites the limitation “sensor data” in line 9. It is unclear if this limitation is meant to refer to the sensor data from claim 1, line 5, or different sensor data. If it is meant to refer to the sensor data from claim 1, it needs to refer back to it. If it is meant to refer to a different sensor data, it needs to be distinguished from the sensor data from claim 1. For purposes of examination, it is being interpreted as referring to the sensor data from claim 1. Claim 8 is also rejected due to their dependence on claim 7.
Further regarding claim 7, the claim recites the limitation “movement of the foot” in line 9. It is unclear if this limitation is meant to refer to the movement of a foot from claim 1, line 12. If it is meant to refer to the movement of a foot from claim 1, it needs to refer back to it. If it is meant to refer to a different movement of the foot, it needs to be distinguished from the movement of a foot from claim 1. For purposes of examination, it is being interpreted as referring to the movement of a foot from claim 1. Claim 8 is also rejected due to its dependence on claim 7.
Regarding claim 9, the claim recites the limitation “sensor data” in line 9. It is unclear if this limitation is meant to refer to the sensor data from line 3, or different sensor data. If it is meant to refer to the sensor data from line 3, it needs to refer back to it. If it is meant to refer to different sensor data, it needs to be distinguished from the sensor data from line 3. For purposes of examination, it is being interpreted as referring to the sensor data from line 3.
Further regarding claim 9, the claim recites the limitation “a subject” in line 9. It is unclear if this limitation is meant to refer to the subject from line 3, or a different subject. If it is meant to refer to the subject from line 3, it needs to refer back to it. If it is meant to refer to a different subject. It needs to be distinguished from the subject from line 3. For purposes of examination, it is being interpreted as referring to the subject from line 3.
Further regarding claim 9, the claim recites the limitation “foot movement” in line 25. It is unclear if this limitation is meant to refer to the movement of a foot from line 9, or a different foot movement. If it is referring to the movement of a foot from line 9, it needs to refer back to it. If it is referring to a different foot movement, it needs to be distinguished from the movement of a foot from line 9. For purposes of examination, it is being interpreted as referring to the movement of a foot from line 9.
Further regarding claim 9, the claim recites the limitation “waist movement” in line 25. It is unclear if this limitation is meant to refer to the movement of a waist from line 4, or a different waist movement. If it is referring to a movement of a waist from line 4, it needs to refer back to it. If it is referring to a different waist movement, it needs to be distinguished from the movement of a waist from line 4. For purposes of examination, it is being interpreted as referring to the movement of a waist from line 4.
Further regarding claim 9, the claim recites the limitation “feature amounts” in line 28. It is unclear if this limitation is meant to refer to the feature amount from line 7, or different feature amounts. If it is meant to refer to the feature amount from line 7, it needs to refer back to it. If it is meant to refer to different feature amounts, it needs to be distinguished from the feature amount from line 7. For purposes of examination, it is being interpreted as referring to the feature amount from line 7.
Regarding claim 10, the claim recites the limitation “sensor data” in line 9. It is unclear if this limitation is meant to refer to the sensor data from line 3, or different sensor data. If it is meant to refer to the sensor data from line 3, it needs to refer back to it. If it is referring to different sensor data, it needs to be distinguished from the sensor data from line 3. For purposes of examination, it is being interpreted as referring to the sensor data from line 3.
Further regarding claim 10, the claim recites the limitation “a subject” in line 9. It is unclear if this is meant to refer to the subject from lines 3-4, or a different subject. If it is meant to refer to the subject from lines 3-4, it needs to refer back to it. If it is meant to refer to a different subject, it needs to be distinguished from the subject from lines 3-4. For purposes of examination, it is being interpreted as referring to the subject from lines 3-4.
Further regarding claim 10, the claim recites the limitation “foot movement” in line 25. It is unclear if this limitation is meant to refer to the movement of a foot from line 9, or a different foot movement. If it is referring to the movement of a foot from line 9, it needs to refer back to it. If it is referring to a different foot movement, it needs to be distinguished from the movement of a foot from line 9. For purposes of examination, it is being interpreted as referring to the movement of a foot from line 9.
Further regarding claim 10, the claim recites the limitation “waist movement” in line 25. It is unclear if this limitation is meant to refer to the movement of a waist from lines 4-5, or a different waist movement. If it is referring to a movement of a waist from lines 4-5, it needs to refer back to it. If it is referring to a different waist movement, it needs to be distinguished from the movement of a waist from lines 4-5. For purposes of examination, it is being interpreted as referring to the movement of a waist from lines 4-5.
Further regarding claim 10, the claim recites the limitation “feature amounts” in line 28. It is unclear if this limitation is meant to refer to the feature amount from line 7, or different feature amounts. If it is meant to refer to the feature amount from line 7, it needs to refer back to it. If it is meant to refer to different feature amounts, it needs to be distinguished from the feature amount from line 7. For purposes of examination, it is being interpreted as referring to the feature amount from line 7.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-10 are rejected under 35 U.S.C. 103 as being unpatentable over Chang (US 20170188894) in view of Kubo (WO 2014181602) and Torres (US 10786192). Citations to WO 2014181602 will refer to the English Machine Translation that accompanies this Office Action.
Regarding independent claim 1, Chang teaches a pelvic inclination estimation device (Abstract: “A system and method for utilizing an activity monitoring device that includes, during a set of initial activity sessions, collecting the kinematic data from an activity monitoring device and generating a temporal record of at least one biomechanical signal that is calculated from the kinematic data”; Claim 1: “the at least one biomechanical signal and the at least one current biomechanical signal includes cadence, braking, pelvic rotation, pelvic tilt, and pelvic drop signals of a running activity.”) comprising:
at least one memory storing instructions; and at least one processor connected to the at least one memory and configured to execute the instructions to ([0129]: “The systems and methods of the embodiments can be embodied and/or implemented at least in part as a machine configured to receive a computer-readable medium storing computer-readable instructions … The instructions can be executed by computer-executable components integrated with apparatuses and networks of the type described above. The computer-readable medium can be stored on any suitable computer readable media such as RAMs, ROMs, flash memory, EEPROMs, optical devices (CD or DVD), hard drives, floppy drives, or any suitable device. The computer-executable component can be a processor but any suitable dedicated hardware device can (alternatively or additionally) execute the instructions”):
receive sensor data from a measurement device installed on footwear of a subject who is an estimation target of a pelvic inclination that is an index related to movement of a waist ([0031]: “The activity monitoring device 110 is preferably small enough to be mounted to a participant in an unobtrusive way and may be integrated into a wearable such as … shoes”; [0032]: “The inertial measurement system 112 of the activity monitoring device 110 functions to measure multiple kinematic properties of an activity. The inertial measurement system 112 preferably includes at least one inertial measurement unit (IMU). An IMU can include at least one accelerometer, gyroscope, magnetometer, or other suitable inertial sensor”) via wireless communication ([0030]: “the activity monitoring device 110 uses wireless communication (e.g., Bluetooth) to connect to the secondary computing device 130, and the secondary computing device communicates with the computing platform 120 for synchronizing data”), the sensor data comprising spatial acceleration and spatial angular velocity ([0055]: “The kinematic measurements collected by the activity monitoring device are preferably along a set of orthonormal axes (e.g., an x, y, z coordinate system) … The kinematic measurements can include acceleration … angular velocity”);
acquire feature amount data including a feature amount to be used for estimation of the pelvic inclination ([0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The feature amount is the motion paths functions created from the acceleration and angular velocity data.).
However, Chang is silent on how the feature amount data is acquired.
Kubo discloses a walking meter and program. Specifically, Kubo teaches the feature amount being extracted from a gait waveform of a spatial acceleration and a spatial angular velocity included in the sensor data related to movement of a foot of a subject (Page 15: “FIG. 6 is a diagram showing the relationship between a human gait and a typical example of the time-varying waveform of vertical axis acceleration (acceleration in the Z-axis direction, with the vertical upward direction being positive) output from acceleration sensor 112 of activity meter 100 worn on the waist during a reference period (T7 (=Step T) in the figure) corresponding to one step in a walking cycle”; Fig. 6; Page 33-34: “the inventors experimentally discovered that the result of weighting and adding one or more feature quantities (feature parameters) that capture the characteristics of the waveform shape of the acceleration change over time output from an acceleration sensor attached to the subject's waist has a good correlation with the tilt angle of the pelvis when the subject is walking”. Walking is a movement of a foot.). Chang and Kubo are analogous arts as they are both relation to devices that measure a user’s gait pattern to analyze the user’s health.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the feature amount being extracted from a gait waveform from Kubo into the device from Chang as Chang is silent on how the feature amount is extracted, and Kubo discloses a suitable process in an analogous device.
The Chang/Kubo combination teaches the step of input the feature amount included in the acquired feature amount data to an estimation model trained by machine learning (Chang, [0044]: “the method can use a machine intelligence approach”; [0097]: “an exemplary set of heuristic-based analyses can include … monitoring changes in sagittal tilt range of motion”).
However, the Chang/Kubo combination is silent on the steps of the machine learning model.
Kubo teaches input the feature amount included in the acquired feature amount data to an estimation model to output an estimation value related to the pelvic inclination according to the input of the feature amount included in the acquired feature amount data; estimate the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the steps of the model from Kubo into the Chang/Kubo combination as the combination is silent on the steps, and Kubo discloses steps of a model in an analogous device.
The Chang/Kubo combination teaches the steps of generate recommendation information corresponding to the estimated pelvic inclination used for decision making for the subject to address the pelvic inclination (Chang, [0027]: “the system and method may be applied to activity use-cases such as gait-analysis … The system method can be applied to helping a participant improve performance, track progress, and/or avoid injury in the sporting field, but can similarly be applied to physical rehabilitation and other clinical applications”; [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”); and
output the recommendation information associated to the estimated pelvic inclination of the subject to display the recommendation information on a display of a terminal device used by the subject (Chang, [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”; [0030]: “Alternative implementations implement the method with the activity monitoring device 110 in communication directly with user feedback elements such as tactile feedback elements, an audio system, or a display.”; [0120]: “Analysis can be provided by displaying information, generating a graphical representation (e.g., a chart, a graphical indicator, etc.), playing audio feedback (e.g., making an speech audio announcement concerning the changes), activating a haptic feedback device, or using any suitable mechanism to provide feedback”; [0040]: “Feedback could be in the form of audio cues (e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback.”), the recommendation information including information indicating whether the pelvic inclination is within a normal range, an attention-required range, or an assistance-required range (Chang, [0125]: “One pattern of injury may be detected based on a change in biomechanical signals beyond an expected range”. If the biomechanical signal is the pelvic tilt, the expected range can be a normal range of the pelvic tilt.), and information recommending at least one of a training to be performed by the subject and an examination at a hospital (Chang, [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”),
wherein the feature amount is extracted from gait phase clusters selected by correlation analysis (Chang, [0094]: “A third approach can use an unsupervised clustering algorithm to find groups of data that are most dissimilar. An unsupervised clustering model approach can include k-means, expectation-maximization algorithms, density-based clustering, principal component analysis, and auto-encoding deep learning networks to identify different states”; [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”) based on a phase interlocking relationship between foot movement and waist movement (Chang, [0026]: “The pelvis can have a strong correlation to lower body movements”. The pelvic movements and the lower body movements have a strong correlation, therefore they have a phase interlocking relationship.).
However, the Chang/Kubo combination does not teach using statistical parametric mapping.
Torres discloses systems and methods for medical diagnosis. Specifically, Torres teaches using statistical parametric mapping (Column 10, lines 1-3: “The system may extract displacement and rotation kinematics from raw sensor data using a Statistical Parametric Mapping”). Chang, Kubo, and Torres are analogous arts as they are all related to monitoring a user’s movements for analysis of their health conditions.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use statistical parametric mapping from Torres into the Chang/Kubo combination as it is another known evaluation method, and therefore would be a simple substitution.
The Chang/Kubo/Torres combination teaches wherein the estimation model comprises separate trained models for each of three axes of a traveling axis, a left-right axis, and a vertical axis (Chang, [0066]: “Pelvic dynamics can be represented in several different biomechanical signals including pelvic rotation, pelvic tilt, and pelvic drop. Pelvic rotation (i.e., yaw) can characterize the rotation in the transverse plane (i.e., rotation about a vertical axis). Pelvic tilt (i.e., pitch) can be characterized as rotation in the sagittal plane (i.e., rotation about a lateral axis). Pelvic drop (i.e., roll) can be characterized as rotation in the coronal plane (i.e., rotation about the forward-backward axis)”. The pelvic dynamics are determined for each axis as separate parameters, therefore they are determined through different trained models, as they require different processing steps.), each model using different combinations of feature amounts optimized for the respective axis (Chang, [0067]: “Vertical oscillation of the pelvis is characterization of the up and down bounce during a step (e.g., the bounce of a step).”; [0068]: “Forward velocity properties of the pelvis or the forward oscillation can be one or more signals characterizing the oscillation of distance over a step or stride, velocity, maximum velocity, minimum velocity, average velocity, or any suitable property of forward kinematic properties of the pelvis”; [0072]: “The position can be measured in one, two, or three dimensions. As a feature, the motion path can be characterized by different parameters such as consistency, range of motion in various directions, and other suitable properties”; [0081]: “the normalized kinematic data streams determine a vertical axis and a forward-backward axis. A left-right axis can be determined from these two perpendicular axes. Left and right strides can be determined by monitoring the angular oscillation at a pelvic sensing device during a step segment. Gyroscopic data providing angular velocity around a vertical axis through the sensor towards earth can be used. In one variation, the left foot is determined if the angular velocity at the beginning of the step segment around the vertical direction measured by the gyroscope is less than zero, otherwise the right foot is determined. The angular velocity can be inspected at the beginning of a step segment. The sum of angular velocities over a whole step could alternatively be used for detecting a bias. Once left and right steps are identified the alternating pattern can be assumed to continue during subsequent step segments. However, continuous or periodic left-right detection can be performed to correct or verify accurate classification of steps. Additionally, anomalies in kinematic data or biomechanical signals can trigger an event to perform left-right detection”. These limitations show that each parameter is calculated with different parameters, which shows that each model uses different combinations of feature amounts.).
Regarding claim 2, the Chang/Kubo/Torres combination teaches the pelvic inclination estimation device according to claim 1, wherein the estimation model is configured to output the estimation value related to the pelvic inclination according to an input of gait parameters included in the feature amount data (Chang, [0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The feature amount is the motion paths functions created from the acceleration and angular velocity data; [0026]: “A biomechanical signal preferably parameterizes a biomechanical-based property of some action by a user. More particularly, a biomechanical signal quantifies at least one aspect of motion that occurs once or repeatedly during a task. For example, in the case of walking or running, how a participant takes each step can be broken into several biomechanical signals. In a preferred implementation, the system and method preferably operate with a set of biomechanical signals that can include ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, and/or foot pronation”. The acceleration and angular velocity are the gait parameters, as they are measured while the user is walking or running for gait analysis.; Kubo, Page 15: “FIG. 6 is a diagram showing the relationship between a human gait and a typical example of the time-varying waveform of vertical axis acceleration (acceleration in the Z-axis direction, with the vertical upward direction being positive) output from acceleration sensor 112 of activity meter 100 worn on the waist during a reference period (T7 (=Step T) in the figure) corresponding to one step in a walking cycle”; Fig. 6; Page 33-34: “the inventors experimentally discovered that the result of weighting and adding one or more feature quantities (feature parameters) that capture the characteristics of the waveform shape of the acceleration change over time output from an acceleration sensor attached to the subject's waist has a good correlation with the tilt angle of the pelvis when the subject is walking”), the at least one processor is configured to execute the instructions to: acquire the feature amount data including the gait parameters extracted from the gait waveform of the spatial acceleration and the spatial angular velocity included in the sensor data (Chang, [0032]: “The inertial measurement system 112 can additionally include an integrated processor that, among other functionality, provides sensor fusion, which effectively provides a separation of forces caused by gravity from forces caused by speed changes on the sensor. The integrated processor may additionally provide post processing of kinematic data”. The processor is used for post processing of the kinematic data, therefore the processor acquires the feature amount data.), input the gait parameters included in the acquired feature amount data to the estimation model (Chang, [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”. The post processing of the kinematic data includes the machine learning model, therefore the gait parameters are input into the estimation model.), and estimate the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Kubo, Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Regarding claim 3, the Chang/Kubo/Torres combination teaches the pelvic inclination device according to claim 2, wherein the estimation model is configured to output the estimation value related to the pelvic inclination according to an input of a first feature amount included in the feature amount data (Chang, [0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The first feature amount is one of the motion paths functions created from the acceleration and angular velocity data.; Kubo, Page 15: “FIG. 6 is a diagram showing the relationship between a human gait and a typical example of the time-varying waveform of vertical axis acceleration (acceleration in the Z-axis direction, with the vertical upward direction being positive) output from acceleration sensor 112 of activity meter 100 worn on the waist during a reference period (T7 (=Step T) in the figure) corresponding to one step in a walking cycle”; Fig. 6; Page 33-34: “the inventors experimentally discovered that the result of weighting and adding one or more feature quantities (feature parameters) that capture the characteristics of the waveform shape of the acceleration change over time output from an acceleration sensor attached to the subject's waist has a good correlation with the tilt angle of the pelvis when the subject is walking”), and the at least one processor is configured to execute the instructions to: acquire the feature amount data including the first feature amount for each gait phase cluster extracted from the gait waveform of the spatial acceleration and the spatial angular velocity included in the sensor data (Chang, [0032]: “The inertial measurement system 112 can additionally include an integrated processor that, among other functionality, provides sensor fusion, which effectively provides a separation of forces caused by gravity from forces caused by speed changes on the sensor. The integrated processor may additionally provide post processing of kinematic data”. The processor is used for post processing of the kinematic data, therefore the processor acquires the first feature amount data.), input the first feature amount included in the acquired feature amount data to the estimation model (Chang, [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”. The post processing of the kinematic data includes the machine learning model, therefore the first feature amount is input into the estimation model.), and estimate the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Kubo, Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Regarding claim 4, the Chang/Kubo/Torres combination teaches the pelvic inclination estimation device according to claim 3, wherein the estimation model is configured to output the estimation value related to the pelvic inclination according to an input of a second feature amount (Chang, [0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The second feature amount is one of the motion paths functions created from the acceleration and angular velocity data.), and the at least one processor is configured to execute the instructions to: calculate, as the second feature amount, an average value of the first feature amounts for both feet of the subject (Chang, [0056]: “The biomechanical signals can reflect ranges in observed metrics and/or maximum, minimum, or average metric values”; [0075]: “the ground contact time can be estimated as a running average for both feet”. The motion path, which is the feature amount, includes the ground contact time, therefore the running average of ground time for both feet is the average value of the first feature amounts for both feet of the subject.) and a difference between the first feature amounts for both feet of the subject (Chang, [0076]: “Determining ground contact time in a first variation includes segmenting the vertical velocity data by steps and taking the difference between the time of the maximum vertical velocity and the time of the minimum vertical velocity within each step cycle”. The motion path, which is the first feature amount, includes the ground contact time, therefore the difference used to determine the ground contact time is the difference between the first feature amounts.), and an average value of the gait parameters for both feet of the subject (Chang, [0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The feature amount is the motion paths functions created from the acceleration and angular velocity data; [0026]: “A biomechanical signal preferably parameterizes a biomechanical-based property of some action by a user. More particularly, a biomechanical signal quantifies at least one aspect of motion that occurs once or repeatedly during a task. For example, in the case of walking or running, how a participant takes each step can be broken into several biomechanical signals. In a preferred implementation, the system and method preferably operate with a set of biomechanical signals that can include ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, and/or foot pronation”. The acceleration and angular velocity are the gait parameters, as they are measured while the user is walking or running for gait analysis; [0056]: “The biomechanical signals can reflect ranges in observed metrics and/or maximum, minimum, or average metric values”. The biomechanical signals include the acceleration and angular velocity, therefore the average of these metric values are the average of the gait parameters.) and a difference between the gait parameters for both feet of the subject (Chang, [0077]: “Determining ground contact time in a second preferred variation can include measuring the time difference between the minimum vertical acceleration and the time of the minimum vertical velocity, adjusted by a linear transformation or other transformation. The minimum vertical velocity will correspond to when an increasing vertical acceleration crosses zero. At lower sampling rates, the time when vertical acceleration crosses zero can be in between sample points. A linear interpolation between negative and positive values of vertical acceleration and identification of a zero point can be used to refine the minimum vertical velocity time”; [0056]: “The biomechanical signals can reflect ranges in observed metrics and/or maximum, minimum, or average metric values”. The difference between the velocities are determined through the acceleration, which is a gait parameter, therefore is the difference between gait parameters.), input the second feature amount to the estimation model (Chang, [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”. The post processing of the kinematic data includes the machine learning model, therefore the second feature amount is input into the estimation model.), and estimate the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Kubo, Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Regarding claim 5, the Chang/Kubo/Torres combination teaches the pelvic inclination estimation device according to claim 4, wherein the estimation model is configured to output the estimation value related to the pelvic inclination according to an input of an attribute of the subject and the second feature amount (Chang, [0103]: “Users could be given initially calibrated thresholds based on demographic information”; [0051]: “a base set of data can be characterized for a set of participants with different demographics and activity experience, and the data can be collected in controlled environments”. The demographic information about the user is the attribute of the subject that is used in the estimation process; [0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The second feature amount is one of the motion paths functions created from the acceleration and angular velocity data.), and the at least one processor is configured to execute the instructions to: input the attribute of the subject and the second feature amount input to the estimation model (Chang, [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”. The post processing of the kinematic data includes the machine learning model, therefore the second feature amount and the attribute of the subject are input into the estimation model.), and estimate the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Kubo, Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Regarding claim 6, the Chang/Kubo/Torres combination teaches the pelvic inclination estimation device according to claim 1, wherein the estimation model is configured to output at least one variation width of the pelvic inclination related to the three axes of the traveling axis, the left-right axis, and the vertical axis in one gait cycle as the estimation value related to the pelvic inclination according to the input of the feature amount included in the feature amount data (Chang, [0106]: “The x-offset and y-offset can relate to the amount of variation (i.e., wiggle) in the motion path”. Fig. 19 shows the x offset and y offset for each plane that show the amount of variation in a range, which is the variation width of each axis.), and the at least one processor is configured to execute the instructions to: input the feature amount included in the acquired feature amount data to the estimation model (Chang, [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”. The post processing of the kinematic data includes the machine learning model, therefore the feature amount is input into the estimation model.), and estimate the pelvic inclination of the subject according to the variation width of at least one of the pelvic inclinations in the three axes of the traveling axis, the left-right axis, and the vertical axis output from the estimation model (Kubo, Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”. The variation of the motion path is included in the motion path (the feature amount), therefore it is used for determination of the pelvic inclination.).
Regarding claim 7, the Chang/Kubo/Torres combination teaches an estimation system (Chang, Abstract: “A system and method for utilizing an activity monitoring device that includes, during a set of initial activity sessions, collecting the kinematic data from an activity monitoring device and generating a temporal record of at least one biomechanical signal that is calculated from the kinematic data”; Claim 1: “the at least one biomechanical signal and the at least one current biomechanical signal includes cadence, braking, pelvic rotation, pelvic tilt, and pelvic drop signals of a running activity.”)comprising: the pelvic inclination estimation device according to claim 1 (see the rejection of claim 1 above); and the measurement device installed on the footwear of the subject who is an estimation target of pelvic inclination, the pelvic inclination is corresponding to the index related to movement of the waist (Chang, [0031]: “The activity monitoring device 110 is preferably small enough to be mounted to a participant in an unobtrusive way and may be integrated into a wearable such as … shoes”; [0032]: “The inertial measurement system 112 of the activity monitoring device 110 functions to measure multiple kinematic properties of an activity. The inertial measurement system 112 preferably includes at least one inertial measurement unit (IMU). An IMU can include at least one accelerometer, gyroscope, magnetometer, or other suitable inertial sensor”), wherein the measurement device includes: a sensor configured to: measure the spatial acceleration and the spatial angular velocity (Chang, [0032]: “The inertial measurement system 112 of the activity monitoring device 110 functions to measure multiple kinematic properties of an activity. The inertial measurement system 112 preferably includes at least one inertial measurement unit (IMU). An IMU can include at least one accelerometer, gyroscope, magnetometer, or other suitable inertial sensor”; [0055]: “a sensing device provides acceleration as detected by an accelerometer and angular velocity as detected by a gyroscope along three orthonormal axes.”), generate sensor data related to movement of the foot using the measured spatial acceleration and spatial angular velocity (Chang, [0026]: “the system and method preferably operate with a set of biomechanical signals that can include ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, and/or foot pronation. Additionally, the biomechanical signals can include left/right foot detection”), and output the generated sensor data (Chang, [0041]: “A processor system preferably includes multiple processors: a processor at the activity monitoring device no, a processor at the computing platform 120, and/or a processor at the secondary computing device 130”. If there are multiple processors, it is clear that the sensor data would be output between them for processing.); and a second memory storing instructions (Chang, [0041]: “A processor system preferably includes multiple processors: a processor at the activity monitoring device no, a processor at the computing platform 120, and/or a processor at the secondary computing device 130”; [0129]: “The instructions can be executed by computer-executable components integrated with apparatuses and networks of the type described above. The computer-readable medium can be stored on any suitable computer readable media such as RAMs, ROMs, flash memory, EEPROMs, optical devices (CD or DVD), hard drives, floppy drives, or any suitable device. The computer-executable component can be a processor but any suitable dedicated hardware device can (alternatively or additionally) execute the instructions”. If there are multiple processors, it is obvious that each processor can have a memory attached to it.); and a second processor connected to the second memory and configured to execute the instructions to (Chang, [0041]: “A processor system preferably includes multiple processors: a processor at the activity monitoring device no, a processor at the computing platform 120, and/or a processor at the secondary computing device 130”): acquire time-series data of the sensor data including features of a gait (Chang, [0056]: “Generating a set of biomechanical signals based on the kinematic data functions to process and/or parameterize a set of characterizations of motion properties of an activity. The biomechanical signals for an activity are preferably a substantially real-time assessment of the biomechanical properties during the activity, and, as such, the biomechanical signal can be a time series data set (i.e., a temporal record)”; [0026]: “A biomechanical signal preferably parameterizes a biomechanical-based property of some action by a user. More particularly, a biomechanical signal quantifies at least one aspect of motion that occurs once or repeatedly during a task. For example, in the case of walking or running, how a participant takes each step can be broken into several biomechanical signals. In a preferred implementation, the system and method preferably operate with a set of biomechanical signals that can include ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, and/or foot pronation”. The acceleration and angular velocity are the gait parameters, as they are measured while the user is walking or running for gait analysis.); extract gait waveform data from one gait cycle from the time-series data of the sensor data (Kubo, Page 15: “FIG. 6 is a diagram showing the relationship between a human gait and a typical example of the time-varying waveform of vertical axis acceleration (acceleration in the Z-axis direction, with the vertical upward direction being positive) output from acceleration sensor 112 of activity meter 100 worn on the waist during a reference period (T7 (=Step T) in the figure) corresponding to one step in a walking cycle”; Fig. 6; Page 33-34: “the inventors experimentally discovered that the result of weighting and adding one or more feature quantities (feature parameters) that capture the characteristics of the waveform shape of the acceleration change over time output from an acceleration sensor attached to the subject's waist has a good correlation with the tilt angle of the pelvis when the subject is walking”), normalize the extracted gait waveform data (Chang, [0056]: “Generating a set of biomechanical signals can include normalizing kinematic data or otherwise preparing the kinematic data for processing. Normalizing can involve standardizing the kinematic data and calibrating the kinematic data to a coordinate system of the participant or a piece of equipment”), extract the feature amount data to be used for estimation of the pelvic inclination from the normalized gait waveform data from a gait phase cluster including at least one gait phase, generate the feature amount data including the extracted feature amount (Chang, [0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The feature amount is the motion paths functions created from the acceleration and angular velocity data.; Kubo, Page 15: “FIG. 6 is a diagram showing the relationship between a human gait and a typical example of the time-varying waveform of vertical axis acceleration (acceleration in the Z-axis direction, with the vertical upward direction being positive) output from acceleration sensor 112 of activity meter 100 worn on the waist during a reference period (T7 (=Step T) in the figure) corresponding to one step in a walking cycle”; Fig. 6; Page 33-34: “the inventors experimentally discovered that the result of weighting and adding one or more feature quantities (feature parameters) that capture the characteristics of the waveform shape of the acceleration change over time output from an acceleration sensor attached to the subject's waist has a good correlation with the tilt angle of the pelvis when the subject is walking”), and output the generated feature amount data to the pelvic inclination estimation device (Chang, [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”. The post processing of the kinematic data includes the machine learning model, therefore the generated feature amount is input into the estimation model.).
Regarding claim 8, the Chang/Kubo/Torres combination teaches the estimation system according to claim 7, wherein the pelvic inclination estimation device is mounted on the terminal device having a screen visually recognizable by the subject (Chang, [0030]: “Alternative implementations implement the method with the activity monitoring device 110 in communication directly with user feedback elements such as tactile feedback elements, an audio system, or a display.”; [0040]: “Feedback could be in the form of audio cues (e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback.”; [0031]: “The activity monitoring device 110 can additionally include any suitable components to support computational operation such as a processor, RAM, Flash memory, battery, user input elements (e.g., buttons, switches, capacitive sensors, touch screens, and the like), user output elements (e.g., status indicator lights, graphical display, speaker, audio jack, vibrational motor, and the like)”), and the second processor of the pelvic inclination estimation device is configured to execute the instructions to display information related to the pelvic inclination estimated according to the movement of the foot of the subject on the screen of the terminal device (Chang, [0120]: “Analysis can be provided by displaying information, generating a graphical representation (e.g., a chart, a graphical indicator, etc.)”).
Regarding independent claim 9, Chang teaches a pelvic inclination estimation method for causing a computer to execute (Abstract: “A system and method for utilizing an activity monitoring device that includes, during a set of initial activity sessions, collecting the kinematic data from an activity monitoring device and generating a temporal record of at least one biomechanical signal that is calculated from the kinematic data”; Claim 1: “the at least one biomechanical signal and the at least one current biomechanical signal includes cadence, braking, pelvic rotation, pelvic tilt, and pelvic drop signals of a running activity.”):
receiving sensor data from a measurement device installed on footwear of a subject who is an estimation target of a pelvic inclination that is an index related to movement of a waist ([0031]: “The activity monitoring device 110 is preferably small enough to be mounted to a participant in an unobtrusive way and may be integrated into a wearable such as … shoes”; [0032]: “The inertial measurement system 112 of the activity monitoring device 110 functions to measure multiple kinematic properties of an activity. The inertial measurement system 112 preferably includes at least one inertial measurement unit (IMU). An IMU can include at least one accelerometer, gyroscope, magnetometer, or other suitable inertial sensor”) via wireless communication ([0030]: “the activity monitoring device 110 uses wireless communication (e.g., Bluetooth) to connect to the secondary computing device 130, and the secondary computing device communicates with the computing platform 120 for synchronizing data”), the sensor data comprising spatial acceleration and spatial angular velocity ([0055]: “The kinematic measurements collected by the activity monitoring device are preferably along a set of orthonormal axes (e.g., an x, y, z coordinate system) … The kinematic measurements can include acceleration … angular velocity”);
acquiring feature amount data including a feature amount to be used for estimation of the pelvic inclination, the feature amount being extracted from sensor data related to movement of a foot of a subject ([0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The feature amount is the motion paths functions created from the acceleration and angular velocity data; [0026]: “the system and method preferably operate with a set of biomechanical signals that can include ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, and/or foot pronation. Additionally, the biomechanical signals can include left/right foot detection”);
inputting the acquired feature amount data to an estimation model trained by machine learning ([0044]: “the method can use a machine intelligence approach”; [0097]: “an exemplary set of heuristic-based analyses can include … monitoring changes in sagittal tilt range of motion”).
However, Chang is silent on the steps of the machine learning model.
Kubo teaches inputting the acquired feature amount data to an estimation model to output an estimation value related to the pelvic inclination according to the input of the feature amount included in the acquired feature amount data; estimating the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the steps of the model from Kubo into the Chang/Kubo combination as the combination is silent on the steps, and Kubo discloses steps of a model in an analogous device.
The Chang/Kubo combination teaches the steps of generating recommendation information corresponding to the estimated pelvic inclination used for decision making for the subject to address the pelvic inclination (Chang, [0027]: “the system and method may be applied to activity use-cases such as gait-analysis … The system method can be applied to helping a participant improve performance, track progress, and/or avoid injury in the sporting field, but can similarly be applied to physical rehabilitation and other clinical applications”; [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”); and
outputting the recommendation information associated to the estimated pelvic inclination of the subject to display the recommendation information on a display of a terminal device used by the subject (Chang, [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”; [0030]: “Alternative implementations implement the method with the activity monitoring device 110 in communication directly with user feedback elements such as tactile feedback elements, an audio system, or a display.”; [0120]: “Analysis can be provided by displaying information, generating a graphical representation (e.g., a chart, a graphical indicator, etc.), playing audio feedback (e.g., making an speech audio announcement concerning the changes), activating a haptic feedback device, or using any suitable mechanism to provide feedback”; [0040]: “Feedback could be in the form of audio cues (e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback.”), the recommendation information including information indicating whether the pelvic inclination is within a normal range, an attention-required range, or an assistance-required range (Chang, [0125]: “One pattern of injury may be detected based on a change in biomechanical signals beyond an expected range”. If the biomechanical signal is the pelvic tilt, the expected range can be a normal range of the pelvic tilt.), and information recommending at least one of a training to be performed by the subject and an examination at a hospital (Chang, [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”),
wherein the feature amount is extracted from gait phase clusters selected by correlation analysis (Chang, [0094]: “A third approach can use an unsupervised clustering algorithm to find groups of data that are most dissimilar. An unsupervised clustering model approach can include k-means, expectation-maximization algorithms, density-based clustering, principal component analysis, and auto-encoding deep learning networks to identify different states”; [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”) based on a phase interlocking relationship between foot movement and waist movement (Chang, [0026]: “The pelvis can have a strong correlation to lower body movements”. The pelvic movements and the lower body movements have a strong correlation, therefore they have a phase interlocking relationship.).
However, the Chang/Kubo combination does not teach using statistical parametric mapping.
Torres discloses systems and methods for medical diagnosis. Specifically, Torres teaches using statistical parametric mapping (Column 10, lines 1-3: “The system may extract displacement and rotation kinematics from raw sensor data using a Statistical Parametric Mapping”). Chang, Kubo, and Torres are analogous arts as they are all related to monitoring a user’s movements for analysis of their health conditions.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use statistical parametric mapping from Torres into the Chang/Kubo combination as it is another known evaluation method, and therefore would be a simple substitution.
The Chang/Kubo/Torres combination teaches wherein the estimation model comprises separate trained models for each of three axes of a traveling axis, a left-right axis, and a vertical axis (Chang, [0066]: “Pelvic dynamics can be represented in several different biomechanical signals including pelvic rotation, pelvic tilt, and pelvic drop. Pelvic rotation (i.e., yaw) can characterize the rotation in the transverse plane (i.e., rotation about a vertical axis). Pelvic tilt (i.e., pitch) can be characterized as rotation in the sagittal plane (i.e., rotation about a lateral axis). Pelvic drop (i.e., roll) can be characterized as rotation in the coronal plane (i.e., rotation about the forward-backward axis)”. The pelvic dynamics are determined for each axis as separate parameters, therefore they are determined through different trained models, as they require different processing steps.), each model using different combinations of feature amounts optimized for the respective axis (Chang, [0067]: “Vertical oscillation of the pelvis is characterization of the up and down bounce during a step (e.g., the bounce of a step).”; [0068]: “Forward velocity properties of the pelvis or the forward oscillation can be one or more signals characterizing the oscillation of distance over a step or stride, velocity, maximum velocity, minimum velocity, average velocity, or any suitable property of forward kinematic properties of the pelvis”; [0072]: “The position can be measured in one, two, or three dimensions. As a feature, the motion path can be characterized by different parameters such as consistency, range of motion in various directions, and other suitable properties”; [0081]: “the normalized kinematic data streams determine a vertical axis and a forward-backward axis. A left-right axis can be determined from these two perpendicular axes. Left and right strides can be determined by monitoring the angular oscillation at a pelvic sensing device during a step segment. Gyroscopic data providing angular velocity around a vertical axis through the sensor towards earth can be used. In one variation, the left foot is determined if the angular velocity at the beginning of the step segment around the vertical direction measured by the gyroscope is less than zero, otherwise the right foot is determined. The angular velocity can be inspected at the beginning of a step segment. The sum of angular velocities over a whole step could alternatively be used for detecting a bias. Once left and right steps are identified the alternating pattern can be assumed to continue during subsequent step segments. However, continuous or periodic left-right detection can be performed to correct or verify accurate classification of steps. Additionally, anomalies in kinematic data or biomechanical signals can trigger an event to perform left-right detection”. These limitations show that each parameter is calculated with different parameters, which shows that each model uses different combinations of feature amounts.).
Regarding independent claim 10, Chang teaches a non-transitory program having a program recorded therein for causing a computer to execute ([0129]: “The systems and methods of the embodiments can be embodied and/or implemented at least in part as a machine configured to receive a computer-readable medium storing computer-readable instructions … The instructions can be executed by computer-executable components integrated with apparatuses and networks of the type described above. The computer-readable medium can be stored on any suitable computer readable media such as RAMs, ROMs, flash memory, EEPROMs, optical devices (CD or DVD), hard drives, floppy drives, or any suitable device. The computer-executable component can be a processor but any suitable dedicated hardware device can (alternatively or additionally) execute the instructions”):
processing of receiving sensor data from a measurement device installed on footwear of a subject who is an estimation target of a pelvic inclination that is an index related to movement of a waist ([0031]: “The activity monitoring device 110 is preferably small enough to be mounted to a participant in an unobtrusive way and may be integrated into a wearable such as … shoes”; [0032]: “The inertial measurement system 112 of the activity monitoring device 110 functions to measure multiple kinematic properties of an activity. The inertial measurement system 112 preferably includes at least one inertial measurement unit (IMU). An IMU can include at least one accelerometer, gyroscope, magnetometer, or other suitable inertial sensor”) via wireless communication ([0030]: “the activity monitoring device 110 uses wireless communication (e.g., Bluetooth) to connect to the secondary computing device 130, and the secondary computing device communicates with the computing platform 120 for synchronizing data”), the sensor data comprising spatial acceleration and spatial angular velocity ([0055]: “The kinematic measurements collected by the activity monitoring device are preferably along a set of orthonormal axes (e.g., an x, y, z coordinate system) … The kinematic measurements can include acceleration … angular velocity”);
processing of acquiring feature amount data including a feature amount to be used for estimation of the pelvic inclination, the feature amount being extracted from sensor data related to movement of a foot of a subject ([0084]: “a process for generating at least one set of motion paths functions to create a dimensional map of movement of at least one point of the body. The kinematic data can include multi-dimensional linear acceleration and angular velocity data, which can be converted to relative displacement or velocity for one to three dimensions as a function of time”. The feature amount is the motion paths functions created from the acceleration and angular velocity data; [0026]: “the system and method preferably operate with a set of biomechanical signals that can include ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, and/or foot pronation. Additionally, the biomechanical signals can include left/right foot detection”);
processing of inputting the acquired feature amount data to an estimation model trained by machine learning ([0044]: “the method can use a machine intelligence approach”; [0097]: “an exemplary set of heuristic-based analyses can include … monitoring changes in sagittal tilt range of motion”).
However, Chang is silent on the steps of the machine learning model.
Kubo teaches inputting the acquired feature amount data to an estimation model to output an estimation value related to the pelvic inclination according to the input of the feature amount included in the acquired feature amount data; processing of estimating the pelvic inclination of the subject according to the estimation value related to the pelvic inclination output from the estimation model (Page 13-14: “FIG. 12 shows an operation flow of the control unit 110 of the activity meter 100. When the power is turned on, the control unit 110 of the activity meter 100 waits for an instruction to start measurement from the smartphone 200, as shown in step S1. When an instruction to start measurement is received from the smartphone 200 (YES in step S1), the control unit 110 acquires the output of the acceleration in the three-axis directions from the acceleration sensor 112, as shown in step S2. The output of the acceleration sensor 112 is acquired for a predetermined period (for example, 14 seconds) which is a period including acceleration timeseries data for 10 steps in this example. The acquired time series data of acceleration is temporarily stored in memory 120 . Next, the control unit 110 waits for an instruction to start measurement from the smartphone 200, as shown in step S3. When a calculation instruction is received from smartphone 200 (YES in step S3), control unit 110 calculates the amount corresponding to the tilt angle of the pelvis, as shown in step S4. Then, as shown in step S5, the control unit 110 functions as an evaluation unit and uses the calculation result (pelvic tilt angle estimation result) to evaluate the degree of forward/backward tilt of the subject's posture while walking in multiple stages. Thereafter, as shown in step S6, the evaluation result is output (transmitted) to the smartphone 200. Note that the control unit 110 may execute the process of step S4 as soon as acceleration time-series data for at least one step is obtained”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the steps of the model from Kubo into the Chang/Kubo combination as the combination is silent on the steps, and Kubo discloses steps of a model in an analogous device.
The Chang/Kubo combination teaches the steps of processing of generating recommendation information corresponding to the estimated pelvic inclination used for decision making for the subject to address the pelvic inclination (Chang, [0027]: “the system and method may be applied to activity use-cases such as gait-analysis … The system method can be applied to helping a participant improve performance, track progress, and/or avoid injury in the sporting field, but can similarly be applied to physical rehabilitation and other clinical applications”; [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”); and
processing of outputting the recommendation information associated to the estimated pelvic inclination of the subject to display the recommendation information on a display of a terminal device used by the subject (Chang, [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”; [0030]: “Alternative implementations implement the method with the activity monitoring device 110 in communication directly with user feedback elements such as tactile feedback elements, an audio system, or a display.”; [0120]: “Analysis can be provided by displaying information, generating a graphical representation (e.g., a chart, a graphical indicator, etc.), playing audio feedback (e.g., making an speech audio announcement concerning the changes), activating a haptic feedback device, or using any suitable mechanism to provide feedback”; [0040]: “Feedback could be in the form of audio cues (e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback.”), the recommendation information including information indicating whether the pelvic inclination is within a normal range, an attention-required range, or an assistance-required range (Chang, [0125]: “One pattern of injury may be detected based on a change in biomechanical signals beyond an expected range”. If the biomechanical signal is the pelvic tilt, the expected range can be a normal range of the pelvic tilt.), and information recommending at least one of a training to be performed by the subject and an examination at a hospital (Chang, [0127]: “Biomechanical properties that are identified as a challenge may be prioritized for training recommendations”),
wherein the feature amount is extracted from gait phase clusters selected by correlation analysis (Chang, [0094]: “A third approach can use an unsupervised clustering algorithm to find groups of data that are most dissimilar. An unsupervised clustering model approach can include k-means, expectation-maximization algorithms, density-based clustering, principal component analysis, and auto-encoding deep learning networks to identify different states”; [0059]: “Detecting an action pattern can additionally or alternatively use machine intelligence such as deep learning, machine learning, statistical methods, and/or other suitable algorithmic approaches to detecting an action”) based on a phase interlocking relationship between foot movement and waist movement (Chang, [0026]: “The pelvis can have a strong correlation to lower body movements”. The pelvic movements and the lower body movements have a strong correlation, therefore they have a phase interlocking relationship.).
However, the Chang/Kubo combination does not teach using statistical parametric mapping.
Torres discloses systems and methods for medical diagnosis. Specifically, Torres teaches using statistical parametric mapping (Column 10, lines 1-3: “The system may extract displacement and rotation kinematics from raw sensor data using a Statistical Parametric Mapping”). Chang, Kubo, and Torres are analogous arts as they are all related to monitoring a user’s movements for analysis of their health conditions.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use statistical parametric mapping from Torres into the Chang/Kubo combination as it is another known evaluation method, and therefore would be a simple substitution.
The Chang/Kubo/Torres combination teaches wherein the estimation model comprises separate trained models for each of three axes of a traveling axis, a left-right axis, and a vertical axis (Chang, [0066]: “Pelvic dynamics can be represented in several different biomechanical signals including pelvic rotation, pelvic tilt, and pelvic drop. Pelvic rotation (i.e., yaw) can characterize the rotation in the transverse plane (i.e., rotation about a vertical axis). Pelvic tilt (i.e., pitch) can be characterized as rotation in the sagittal plane (i.e., rotation about a lateral axis). Pelvic drop (i.e., roll) can be characterized as rotation in the coronal plane (i.e., rotation about the forward-backward axis)”. The pelvic dynamics are determined for each axis as separate parameters, therefore they are determined through different trained models, as they require different processing steps.), each model using different combinations of feature amounts optimized for the respective axis (Chang, [0067]: “Vertical oscillation of the pelvis is characterization of the up and down bounce during a step (e.g., the bounce of a step).”; [0068]: “Forward velocity properties of the pelvis or the forward oscillation can be one or more signals characterizing the oscillation of distance over a step or stride, velocity, maximum velocity, minimum velocity, average velocity, or any suitable property of forward kinematic properties of the pelvis”; [0072]: “The position can be measured in one, two, or three dimensions. As a feature, the motion path can be characterized by different parameters such as consistency, range of motion in various directions, and other suitable properties”; [0081]: “the normalized kinematic data streams determine a vertical axis and a forward-backward axis. A left-right axis can be determined from these two perpendicular axes. Left and right strides can be determined by monitoring the angular oscillation at a pelvic sensing device during a step segment. Gyroscopic data providing angular velocity around a vertical axis through the sensor towards earth can be used. In one variation, the left foot is determined if the angular velocity at the beginning of the step segment around the vertical direction measured by the gyroscope is less than zero, otherwise the right foot is determined. The angular velocity can be inspected at the beginning of a step segment. The sum of angular velocities over a whole step could alternatively be used for detecting a bias. Once left and right steps are identified the alternating pattern can be assumed to continue during subsequent step segments. However, continuous or periodic left-right detection can be performed to correct or verify accurate classification of steps. Additionally, anomalies in kinematic data or biomechanical signals can trigger an event to perform left-right detection”. These limitations show that each parameter is calculated with different parameters, which shows that each model uses different combinations of feature amounts.).
Response to Arguments
All of applicant’s argument regarding the rejections and objections previously set forth have been fully considered and are persuasive unless directly addressed subsequently.
Applicant has amended the claims to overcome the claim objections and 112(b) rejections, however the amendments have introduced new claim objections and 112(b) rejections.
Applicant’s arguments with respect to claims 1-10 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. That is, there are new grounds of rejection that were necessitated by the claim amendments filed on 12/23/2025.
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 ERIN K MCCORMACK whose telephone number is (703)756-1886. The examiner can normally be reached Mon-Fri 7:30-5.
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, Jason Sims can be reached at 5712727540. 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.
/E.K.M./Examiner, Art Unit 3791
/MATTHEW KREMER/Primary Examiner, Art Unit 3791