DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 01/22/25 and 02/06/25 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Drawings
The drawings filed on 03/29/24 are accepted.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
With respect to step 1 of the patent subject matter eligibility analysis, the claims are directed to a process, machine, manufacture, or composition of matter. Independent claim 1 is directed to a method for training a trajectory estimation model, which is a process. Independent claim 14 is directed to a trajectory uncertainty determining method, which is a process. Independent claim 18 is directed to a computer program product, comprising computer-executable instructions stored on a non-transitory computer-readable storage medium, which is a manufacture. All other claims depend on independent claims 1, 14, and 18. As such, claims 1-20 are directed to a statutory category.
With respect to step 2A, prong one, the claims recite an abstract idea, law of nature, or natural phenomenon. Specifically, the following limitations recite mathematical concepts and/or mental processes.
Claim 1
in the feature extraction module, extracting a first feature of the first IMU data, and extracting a second feature of the second IMU data (A general extraction of data is a mental process that can be performed in the human mind. For example, if a user reads over a list of data and gives particular attention to a particular data point or feature, that can broadly be construed as “extracting a feature.” At the same time, the applicant’s 02/12/25 substitute specification appears to show that the feature extraction models is represented by specific abstract mathematical concepts. Figure 8B shows a schematic diagram of a structure of an example feature extraction module. Paragraph 00207 states, “This structure uses a residual network as a backbone, extracts the features of the IMU data through one-dimensional convolution, and can represent input IMU data as 512 7-dimensional vectors. A regularization (norm) layer in the structure shown in FIG. 8B may be implemented by using a group normalization operator.” This shows that the feature extraction module is defined by specific mathematical relationships and calculations, such as one-dimensional convolution and 7-dimensional vectors. The limitation therefore recites abstract mental processes and/or mathematical concepts.)
in the label estimation module, determining a first label based on the first feature, and determining a second label based on the second feature, wherein the first label and the second label correspond to a first physical quantity (A general determination of labels is an abstract mental process that can be performed in the human mind, as human minds often attach labels to data, in order to contextualize it. At the same time, the applicant’s 02/12/25 substitute specification appears to show that the label estimation module is defined by specific mathematical relationships and/or calculations. For example, figure 8C shows a schematic diagram of a structure of an example label estimation module. Paragraph 0208 states, “A network structure of the label estimation module includes the one-dimensional convolutional layer and a fully connected layer … The three fully connected layers respectively regress feature vectors into a 512-dimensional vector …and a 3-dimensional vector … As shown in FIG. 8C, the 3-dimensional vector is …” The limitation therefore recites abstract mental processes and/or mathematical concepts.)
determining a first difference between the first label and the second label (A general observation of differences, like “observe how picture A differs from picture B,” is a mental process that can be performed in the human mind. A mathematical calculation of differences, like “subtract X parameters from parameter Y,” is a mathematical equation and/or calculation. The limitation therefore recites abstract mental processes and/or mathematical concepts.)
performing a first update on a parameter of the feature extraction module and a parameter of the label estimation module in a direction of reducing the first difference (Here, the claim does not specify what “performing a first update” entails. At a general level, performing a first update could just be “making a mental note of a change” in the human mind. At the same time, paragraph 00219 of the applicant’s 02/12/25 amended specification states, “Use backward propagation of the total loss L to optimize the trajectory estimation model. That is, the parameter in the trajectory estimation model is updated to reduce the total loss L.” This appears to show that the update is a mathematical relationship between a parameter in a model and a variable, such as total loss. The limitation therefore recites abstract mental processes and/or mathematical concepts.)
Claim 14
determining a first difference between the plurality of estimated results, wherein the first difference represents an uncertainty level of the first physical quantity, and the first difference is represented by a variable or a standard deviation (This limitation recites abstract mathematical concepts. The limitation specifically recites a specific mathematical equation/calculation in the form of a first difference that is represented by a variable or a standard deviation.)
Claim 18
extract a first feature of the first IMU data, and extracting a second feature of the second IMU data (This limitation recites an abstract mental process and/or mathematical concept, for the reasons stated in claim 1 above.)
determine a first label based on the first feature, and determining a second label based on the second feature, wherein the first label and the second label correspond to a first physical quantity (This limitation recites an abstract mental process and/or mathematical concept, for the reasons stated in claim 1 above.)
determine a first difference between the first label and the second label (This limitation recites an abstract mental process and/or mathematical concept, for the reasons stated in claim 1 above.)
perform a first update on a parameter of the feature extraction module and a parameter of the label estimation module in a direction of reducing the first difference (This limitation recites an abstract mental process and/or mathematical concept, for the reasons stated in claim 1 above.)
Dependent claims 2-13, 15-17, and 19-20 depend on independent claims 1, 14, and 18. They recite the independent claims’ abstract limitations, by virtue of their dependence. In addition, some of the claims also recite their own abstract mathematical concepts and/or mental processes.
Claim 3 discloses, “rotating a direction of the first acceleration by a first angle … and rotating a direction of the first angular velocity by the first angle …” This recites specific mathematical relationships. Envisioning a rotation is also an observation, evaluation, judgment, and/or opinion that can be performed in the human mind.
Claim 4 discloses, “rotating a direction of the first initial label by the first angle … rotating a direction of the second initial label by the first angle …” This recites specific mathematical relationships. Envisioning a rotation is also an observation, evaluation, judgment, and/or opinion that can be performed in the human mind.
Claims 5-6 further disclose extracting, determining, and update performing limitations that recite an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 8 further discloses rotating, extracting, determining, and update performing limitations that recite an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 9 further discloses determining a similarity between two features. At a general level, this is an observation, evaluation, judgment, and/or opinion that can be performed in the human mind. A more specific mathematical determination of similarity recites abstract mathematical concepts. Performing an update recites an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 10 further discloses determining and update performing limitations that recite an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 11 further discloses extracting, determining, and update performing limitations that recite an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 12 further discloses determining and update performing limitations that recite an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 13 further discloses extracting and determining limitations that recite an abstract mathematical concept and/or mental process, for reasons similar to those discussed above.
Claim 16 discloses determining a first location corresponding to the estimated result. This is an observation, evaluation, judgment, and/or opinion that can be performed in the human mind. Claim 14 also discloses determining a second difference … the second difference is represented by using a variance or a standard deviation … This is an abstract mathematical calculation.
Claim 17 discloses a three-dimensional space coordinate system, which represents specific mathematical relationships. Claim 17 also discloses determination of change rates. The claim therefore recites specific mathematical relationships and/or calculations.
Claim 20 discloses rotating a direction of acceleration and velocity. This represents specific mathematical relationships and/or calculations.
With respect to step 2A, prong two, the claims do not recite additional elements that integrate the judicial exception into a practical application. The following limitations are considered “additional elements” and explanation will be given as to why these “additional elements” do not integrate the judicial exception into a practical application.
Claim 1
obtaining first inertial measurement unit (IMU) data generated by a first inertial measurement unit (IMU) in a first time period, wherein the first inertial measurement unit moves along a first trajectory in the first time period (This limitation is not indicative of integration into a practical application because gathering data to be processed merely adds insignificant extra-solution activity to the judicial exception (see MPEP 2106.05(g)). The limitation, “wherein the first inertial measurement unit moves along a first trajectory in the first time period” merely serves to generally link the use of the judicial exception to a particular technological environment or field of use (see MPEP 2106.05(h)). The “movement” is presented as context for the type of data that is obtained. The claim does not positively recite the structure of the inertial measurement unit. Contextual data about structure is not the same as positive recitation of structure.)
obtaining second IMU data, wherein the first IMU data and the second IMU data use a same coordinate system, and the second IMU data and the first IMU data have a preset correspondence (This limitation recites routing data gathering, which merely adds insignificant extra-solution activity to the judicial exception.)
Claim 14
obtaining a plurality of estimated results output by a plurality of trajectory estimation models, wherein the plurality of trajectory estimation models are in a one-to-one correspondence with the plurality of estimated results, the plurality of estimated results correspond to a first physical quantity, and different trajectory estimation models in the plurality of trajectory estimation models have independent training processes and a same training method (This limitation is not indicative of integration into a practical application because obtaining data for data processing merely adds insignificant extra-solution activity to the judicial exception. The disclosure of disclosure of the different trajectory estimation models having independent training processes and a same training method merely serve to generally link the use of the judicial exception to a particular technological environment or field of use. The claims do not specify what the training processes are.)
Claim 18
A computer program product, comprising computer-executable instructions stored on a non-transitory computer-readable storage medium, wherein the computer- executable instructions, when executed by one or more processors of an apparatus, cause the apparatus to (This limitation is not indicative of integration into a practical application because it merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)).)
obtain first IMU data generated by a first inertial measurement unit in a first time period, wherein the first inertial measurement unit moves along a first trajectory in the first time period (This limitation is not indicative of integration into a practical application because routine data gathering for data processing merely adds insignificant extra-solution activity to the judicial exception.)
obtain second IMU data, wherein the first IMU data and the second IMU data use a same coordinate system, and the second IMU data and the first IMU data have a preset correspondence (This limitation is not indicative of integration into a practical application because routine data gathering for data processing merely adds insignificant extra-solution activity to the judicial exception.)
Dependent claims 2-13, 15-17, and 19-20 depend on independent claims 1, 14, and 18. They recite the independent claims’ limitations that are not indicative of integration into a practical application, by virtue of their dependence. In addition, some of the claims also recite their own limitations that are not indicative of integration into a practical application.
Claim 2 discloses that the first physical quantity comprises a speed, a displacement, a step size, and/or a heading angle. This merely serves to generally link the use of the judicial exception to a particular technological environment or field of use. It is not indicative of integration into a practical application.
Claims 5-6 disclose obtaining device conjugate data. These limitations merely serve to add insignificant extra-solution activity to the judicial exception, in the form of routine data gathering. The disclosure of what the device conjugate data represents merely serves to generally link the judicial exception to a particular technological environment or field of use.
Claim 7 discloses that the second IMU data is generated by a second inertial measurement unit in the first time period, and the second inertial measurement unit moves along the first trajectory in the first time period. This limitation merely serves to generally link the use of the judicial exception to a particular technological environment or field of use.
Claim 10 discloses obtaining an actual label of the first inertial measurement unit when the first inertial measurement unit moves along the first trajectory. This limitation represents routine data gathering that merely adds insignificant extra-solution activity to the judicial exception.
Claim 13 discloses obtaining first measured IMU data of a first object. This limitation represents routine data gathering that merely adds insignificant extra-solution activity to the judicial exception.
Claim 14 discloses obtaining a plurality of estimated results. This limitation merely adds insignificant extra-solution activity to the judicial exception. The disclosure of the different trajectory estimation models, having independent training processes and a same training method, merely serves to generally link the use of the judicial exception to a particular technological environment or field of use.
Claim 15 discloses that the first physical quantity is a speed. This limitation merely serves to generally link the use of the judicial exception to a particular technological environment or field of use.
Claim 19 discloses that the first physical quantity comprises a speed, a displacement, a step size, and/or a heading angle. This limitation merely serves to generally link the use of the judicial exception to a particular technological environment or field of use.
With respect to step 2B, the claims do not recite additional elements that amount to significantly more than the judicial exception. The claimed invention does not add significantly more because, as discussed above in step 2A, prong two, the claims do nothing more than merely use a computer as a tool to perform an abstract idea; add insignificant extra-solution activity to the judicial exception; and/or generally link the use of the judicial exception to a particular technological environment or field of use. The claims are directed to receiving and processing data. This is well-understood, routine, and conventional. Simply appending well-understood, routine, and conventional activities previously known to the industry, and specified at a high level of generality, to the judicial exception is not indicative of an inventive concept (aka “significantly more”) (see MPEP 2106.05(d) and Berkheimer Memo).
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 14-15 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Zhu et al (US Pat 12078510).
With respect to claim 14, Zhu et al discloses:
A trajectory uncertainty determining method (“Uncertainty” is not defined here. Column 18, lines 26-43 discuss time differences, which can broadly be construed as one type of uncertainty. Column 40, lines 31-34 disclose differences between a local maximum and a local minimum, which can broadly be construed as another type of uncertainty. Column 42, line 50 discloses loss function, which can broadly be construed as another type of uncertainty. Column 43, lines 30-38 disclose errors and differences between errors, which can broadly be construed as another type of uncertainty. Column 54, lines 53-60 disclose distance and angle difference, which can broadly be construed as another type of uncertainty.)
obtaining a plurality of estimated results output by a plurality of trajectory estimation models, wherein the plurality of trajectory estimation models are in a one-to-one correspondence with the plurality of estimated results, the plurality of estimated results correspond to a first physical quantity, and different trajectory estimation models in the plurality of trajectory estimation models have independent training processes and a same training method (abstract states, “a sensor configured to collect sensing data in a venue and obtain a plurality of trajectories … Each trajectory is a time series of spatial coordinates (TSSC) representing a path traversed by a respective object in the venue.” The examiner broadly construes each TSSC representing a trajectory path to serve as a claimed estimation model. Column 18, lines 26-27 state, “The mapping may be one-to-one …” Column 16, lines 37-39 state, “In one embodiment, a wireless monitoring system may comprise training a classifier of multiple events …”)
determining a first difference between a plurality of estimated results, wherein the first difference represents an uncertainty level of the first physical quantity, and the first difference is represented by a variance or a standard deviation (Various sections that teach “difference” were disclosed above. Variance and standard deviation are disclosed in column 37, lines 31-32 and 55; column 40, line 8; and column 77, line 23)
With respect to claim 15, Zhu et al discloses:
wherein the first physical quantity is a speed (column 11, line 12; column 25, lines 42-43; column 27, line 54; column 32, lines 31-32; column 38, line 43; and column 40, line 17 discloses speed)
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-3, 7, 9, 13, 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Gu et al (US PgPub 20190108651).
With respect to claim 1, Gu et al discloses:
A method for training a trajectory estimation model, wherein the trajectory estimation model comprises a feature extraction module and a label estimation module (abstract; figure 1C, reference 135 states, “Train a deep neural network (DNN) by determining weights using a labeled training dataset including images and corresponding absolute camera poses and relative camera poses, where the weights define a map representation of an environment.”; paragraph 0023 states, “Each DNN 110 receives an image … The DNNs 110 are trained to learn the map representation … the input images may correspond to a path through the environment …”)
obtaining first inertial measurement unit (IMU) data generated by a first inertial measurement unit (IMU) in a first time period, wherein the first inertial measurement unit moves along a first trajectory in the first time period (Paragraph 0039 states, “the training loss unit 115 receives geometric constraints in the form of sensor data. The geometric constraints can come from a variety of sources … rotation constraint from two inertial measurement unit (IMU) readings … Furthermore, IMU and GPS provide measurements about camera pose …” Paragraph 0054 states, “FIG. 2C illustrates camera localization results, in accordance with an embodiment. Plot 240 includes a ground truth camera trajectory (path) 242 … The Plot 240 also includes a trajectory of estimated camera poses 244 …”)
obtaining second IMU data (suggested by the disclosure of “two inertial measurement unit (IMU) readings” discussed in paragraphs 0039 and 0057)
in the feature extraction module, extracting a first feature of the first IMU data, and extracting a second feature of the second IMU data (The claims do not define what extraction entails, nor do they define what constitutes “features.” The examiner broadly construes “reading” IMU measurements to serve as the claimed extracting. The examiner broadly construes the measurements themselves to serve as the claimed features.)
in the label estimation module, determining a first label based on the first feature, and determining a second label based on the second feature, wherein the first label and the second label correspond to a first physical quantity (The claims do not define what constitutes “feature” or “physical quantity.” Paragraph 0005 states, “Weights of a DNN are determined during training using a labeled training dataset including images and corresponding absolute camera poses and relative camera poses, where the weighs define a map representation of an environment.” This disclosure is broadly construed to anticipate the broad claimed limitation.)
determining a first difference between the first label and the second label (figure 1A discloses a “Training Loss Unit”; paragraph 0024 states, “The training loss unit 105 computes a loss function and updates the weights used by the DNNs 110.” Please note that paragraph 0015 of the applicant’s 02/12/25 substitute specification states, “the label based on the first IMU data can be rotated and compared with the label based on the second IMU data, to obtain a loss function.” The examiner broadly understands “determining a first difference” to be suggestive of computing a loss function, which Gu et al discloses.)
performing a first update on a parameter of the feature extraction module and a parameter of the label estimation module in a direction of reducing the first difference (The claims do not define the nature of the update. However, Gu et al paragraph 0024 states, “The training loss unit 105 computes a loss function and updates the weights used by the DNNs 110. In an embodiment, the weights are modified to simultaneously reduce differences between the relative estimated camera poses and the ground truth relative camera poses and differences between the estimated camera poses generated by the DNN 110 and the ground truth camera poses.”)
With respect to claim 1, Gu et al differs from the claimed invention in that is does not explicitly disclose:
wherein the first IMU data and the second IMU data use a same coordinate system, and the second IMU data and the first IMU data have a preset correspondence
With respect to claim 1, the following limitation(s) is/are obvious in view of the total teachings of Gu et al.
wherein the first IMU data and the second IMU data use a same coordinate system, and the second IMU data and the first IMU data have a preset correspondence (As discussed above, paragraphs 0039 and 0057 disclose two IMU readings. Gu et al does not explicitly disclose that the two readings share the same coordinate system, but it is implied and would be obvious to one of ordinary skill in the art. Two readings in different coordinate systems would involve complex processing that would be explained by the art (if present). One of ordinary skill in the art would understand the general teaching of two IMU readings to imply, by default, that the readings are in the same coordinate system. The claims do not define what constitutes “preset correspondence,” but it is inherent for the two readings to have a preset correspondence, in that they occupy the same space and would therefore have a spatial and/or rotational data relationship, relative to one another. Please note that as discussed above, Gu et al further discloses calculation of loss functions, which would further imply that the rotational measurements belong to the same coordinate system, in order to allow the loss function(s) to be properly calculated.)
With respect to claim 1, it would have been obvious to one having ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Gu et al. The motivation for the skilled artisan in doing so is to gain the benefit of processing rotation measurements from multiple IMU readings.
Claim 18 represents a computer program product variation of independent claim 1. It is rejected for similar reasons as claim 1 above. Please note that Gu et al does disclose a computer and computer readable medium (paragraph 0005).
With respect to claim 2, Gu et al, as modified, discloses:
wherein the first physical quantity comprises any one or more of a speed, a displacement, a step size, and/or a heading angle (figure 1C, reference 135 states, “Train a deep neural network (DNN) by determining weights using a labeled training dataset including images and corresponding absolute camera poses and relative poses, where the weights define a map representation of an environment.” A map inherently comprises elements, such as displacement of some objects relative to another. Paragraph 0003 of Gu et al discloses, “A map is an abstract summary of the input data that establishes geometric constraints between observations and can be used to establish correspondences between consecutive image frames. A map can be queried to obtain the camera pose for correcting drift in relative pose estimation and reinitialize the camera pose if the tracking is lost. Maps, however, are usually defined in an application-specific manner with hand-crafted features. Examples include 3D landmarks, 3D points, line/edge structure for indoor/man-made scenes, groups of pixels with depth, or object-level context …”)
Claim 19 represents a computer program product variation of dependent claim 2. It is rejected for similar reasons as claim 2 above.
With respect to claim 3, Gu et al, as modified, discloses:
wherein the first IMU data comprises a first acceleration and a first angular velocity, and the obtaining of the second IMU data comprises: rotating a direction of the first acceleration by a first angle along a first direction, and rotating a direction of the first angular velocity by the first angle along the first direction, to obtain the second IMU data (This limitation describes general and generic information of what IMU data comprises and how it is measured. Such information would be obvious to one of ordinary skill in the art, in view of the art’s disclosure that IMU readings (relative rotation measurements) are present. Please also note paragraph 0034, which states, “the camera orientation is parameterized as the logarithm of a unit quaternion to represent rotation, and is better suited for regression of a DNN.”)
Claim 20 represents a computer program product variation of dependent claim 3. It is rejected for similar reasons as claim 3 above.
With respect to claim 7, Gu et al, as modified, discloses:
wherein the second IMU data is generated by a second inertial measurement unit in the first time period, and the second inertial measurement unit moves along the first trajectory in the first time period (obvious in view of the teachings of two inertial measurement unit (IMU) readings; The claims do not specify the nature of the “second inertial measurement unit”. The examiner broadly interprets the first inertial measurement unit reading, as prepared by the first inertial measurement unit, and the second inertial measurement unit reading to be provided by the second inertial measurement unit.)
With respect to claim 9, Gu et al, as modified, discloses:
determining a similarity between the first feature and the second feature (paragraph 0044 states, “similar loss terms … may be defined and computed by the training loss unit 115 to minimize the difference between such measurements and the estimates (predictions) generated by the DNN 110.”)
performing a second update on the parameter of the feature extraction module in a direction of improving the similarity between the first feature and the second feature (paragraph 0022 states, “During supervised and/or self-supervised training, parameters … of the DNNs 110 are updated …”)
With respect to claim 13, Gu et al, as modified, discloses:
A method for performing trajectory estimation by using a trajectory estimation model, wherein the trajectory estimation model is obtained through training according to the method according to claim 1 (as applied to claim 1 above), the trajectory estimation model comprises a feature extraction module and a label estimation module, and the method comprises:
obtaining first measured IMU data of a first object, wherein the first measured IMU data is generated by an inertial measurement unit on the first object in a first time period (paragraphs 0039, 0044, and 0057)
extracting, in the feature extraction module, a first feature of the first measured IMU data (The claims do not define what extraction entails, nor do they define what constitutes “features.” The examiner broadly construes “reading” IMU measurements to serve as the claimed extracting. The examiner broadly construes the measurements themselves to serve as the claimed features.)
determining, in the label estimation module based on the first feature of the first measured IMU data, a first measured label corresponding to the first object, wherein the first measured label corresponds to a first physical quantity (The claims do not define what constitutes “feature” or “physical quantity.” Paragraph 0005 states, “Weights of a DNN are determined during training using a labeled training dataset including images and corresponding absolute camera poses and relative camera poses, where the weighs define a map representation of an environment.” This disclosure is broadly construed to anticipate the broad claimed limitation.)
determining a trajectory of the first object in the first time period based on the first measured label (paragraphs 0023 and 0054-0057 disclose trajectory)
Claim(s) 16-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al (US Pat 12078510).
With respect to claim 16, Zhu et al discloses:
The method according to claim 15 (as applied to claim 15 above)
determining a first location corresponding to the estimated result (Column 6, lines 55-56 state, “The expression may comprise placement, placement of moveable parts, location, position …” Column 10, lines 12-19 state, “The processing may be based on locations …” Column 17, lines 19-23 state, “The classifier may partition TSCI … into clusters and associate the clusters to specific events/objects/subjects/locations/movements/activities.” Column 25, lines 38-43 state, “The characteristics and/or STI (e.g. motion information) may comprise: location, location coordinate, change in location, position … rotational speed …”)
With respect to claim 16, Zhu et al differs from the claimed invention in that is does not explicitly disclose:
determining a second difference between a plurality of first locations corresponding to the plurality of estimated results, wherein the plurality of first locations are in a one-to-one correspondence with the plurality of estimated results, the second difference represents an uncertainty level of the first location, and the second difference is represented by using a variance or a standard deviation
With respect to claim 16, the following limitation(s) is/are obvious in view of the total teachings of Zhu et al:
determining a second difference between a plurality of first locations corresponding to the plurality of estimated results, wherein the plurality of first locations are in a one-to-one correspondence with the plurality of estimated results, the second difference represents an uncertainty level of the first location, and the second difference is represented by using a variance or a standard deviation (The claimed limitation is obvious in view of the vast and total disclosure of Zhu et al. At a high level, Zhu describes a way to build an indoor map by gathering multiple trajectories, where each trajectory is a path that is represented as time-ordered spatial coordinates. With different trajectories on a map inherently comes different locations. Finding the difference between different locations (which broadly represents the claimed uncertainty) is an obvious mathematical operation to one of ordinary skill in the art that has access to the map data. As discussed above, concepts, such as one-to-one correspondence and variance/standard deviation are disclosed by Zhu et al.)
With respect to claim 16, it would have been obvious to one having ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Zhu et al. The motivation for the skilled artisan in doing so is to gain the benefit of accurately analyzing data relevant to the different trajectories that are created and tracked.
With respect to claim 17, Zhu et al discloses:
The method according to claim 15 (as applied to claim 15 above)
wherein the estimated result is represented by using a three-dimensional space coordinate system (column 39, line 5 discloses 3-dimensional; Column 29 states, “The venue may be a space such as a sensing area, room, house …” These are three-dimensional spaces.)
and the estimated result comprises a first speed in a direction of a first coordinate axis of the three-dimensional space coordinate system and a second speed in a direction of a second coordinate axis of the three-dimensional space coordinate system (suggested by STI motion information discussed in column 11, lines 10-12. People walk in multiple dimensions in a building.)
With respect to claim 17, Zhu et al differs from the claimed invention in that is does not explicitly disclose:
determining a first change rate of a first heading angle at the first speed, and determining a second change rate of the first heading angle at the second speed, wherein the first heading angle is an angle on a plane on which the first coordinate axis and the second coordinate axis are located (column 53, lines 36-37 state, “while using inertial sensors to measure the turning angles and heading information, which together shape the geometric properties.” Although Zhu et al does not use the same language as the claimed limitation, the claimed limitation represents an obvious mathematical calculation, given that Zhu et al discloses all the necessary data to make the calculation (i.e. speed, heading angles).)
determining an uncertainty level of the first heading angle based on the first change rate, the second change rate, an uncertainty level of the first speed, and an uncertainty level of the second speed (obvious in view of total teachings of Zhu et al. Zhu et al discloses all of the variables needed to make the claimed determination. The determination of the variables result from obvious mathematical calculation.)
With respect to claim 17, it would have been obvious to one having ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Zhu et al. The motivation for the skilled artisan in doing so is to gain the benefit of enhanced analysis of the various data variables discussed by Zhu et al.
Examiner’s Note - Allowable Subject Matter
Claims 4-6, 8, and 10-12 are objected to as being dependent upon a rejected base claim, but would be potentially allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Please note that no claims can be allowed until the above 35 U.S.C. 101 rejection is overcome.
Claim 4 discloses the following limitation(s), which was/were not found, taught, disclosed, or suggested in the prior art:
wherein the determining of the first label based on the first feature, and the determining of the second label based on the second feature comprise:
determining a first initial label based on the first feature, and rotating a direction of the first initial label by the first angle along the first direction to obtain the first label
determining a second initial label based on the second feature, and rotating a direction of the second initial label by the first angle along a second direction to obtain the second label, wherein the second direction is opposite to the first direction
Although Gu et al generally discloses labeling and rotations, it does not appear to disclose the connection between rotations and labels, in the detailed manner provided.
Claim 5 discloses the following limitation(s), which was/were not found, taught, disclosed, or suggested in the prior art:
obtaining device conjugate data of the first IMU data, wherein the device conjugate data is IMU data generated by a second inertial measurement unit in the first time period, and the second inertial measurement unit moves along the first trajectory in the first time period
extracting, in the feature extraction module, a feature of the device conjugate data
determining, in the label estimation module based on the feature of the device conjugate data, a label corresponding to the device conjugate data
determining a device conjugate difference between the first label and the label corresponding to the device conjugate data; and
the performing of the first update on the parameter of the feature extraction module and the parameter of the label estimation module in the direction of reducing the first difference comprises:
performing the first update on the parameter of the feature extraction module and the parameter of the label estimation module in the direction of reducing the first difference and in a direction of reducing the device conjugate difference
Although Gu et al discloses using two inertial measurement unit (IMU) readings, it does not appear to disclose the details of deriving and using the claimed device conjugate data.
Claim 6 discloses the following limitation(s), which was/were not found, taught, disclosed, or suggested in the prior art:
obtaining device conjugate data of the first IMU data, wherein the device conjugate data is IMU data generated by a second inertial measurement unit in the first time period, and the second inertial measurement unit moves along the first trajectory in the first time period
extracting, in the feature extraction module, a feature of the device conjugate data
determining a conjugate feature similarity between the first feature and the feature of the device conjugate data
performing a second update on the parameter of the feature extraction module in a direction of improving the conjugate feature similarity
Although Gu et al discloses using two inertial measurement unit (IMU) readings, it does not appear to disclose the details of deriving and using the claimed device conjugate data.
Claim 8 discloses the following limitation(s), which was/were not found, taught, disclosed, or suggested in the prior art:
rotating a direction of the first acceleration by a first angle along a first direction, and rotating a direction of the first angular velocity by the first angle along the first direction, to obtain rotation conjugate IMU data of first IMU data
extracting, in the feature extraction module, a feature of the rotation conjugate IMU data
determining, in the label estimation module, a rotation conjugate label based on the feature of the rotation conjugate IMU data
determining a rotation conjugate difference between the first label and the rotation conjugate label
the performing of the first update on the parameter of the feature extraction module and the parameter of the label estimation module in the direction of reducing the first difference comprises:
performing the first update on the parameter of the feature extraction module and the parameter of the label estimation module in the direction of reducing the first difference and in a direction of reducing the rotation conjugate difference
Although Gu et al discloses rotation, it does not explicitly disclose the claimed specifics of obtaining and applying rotation conjugate IMU data.
Claim 10 discloses the following limitation(s), which was/were not found, taught, disclosed, or suggested in the prior art:
obtaining an actual label of the first inertial measurement unit when the first inertial measurement unit moves along the first trajectory
determining a label difference between the first label and the actual label
the performing of the first update on the parameter of the feature extraction module and the parameter of the label estimation module in the direction of reducing the first difference comprises:
performing the first update on the parameter of the feature extraction module and the parameter of the label estimation module in the direction of reducing the first difference and in a direction of reducing the label difference
Paragraph 0041 of Gu et al states, “In order to update the defined map representation … weights … of the camera pose estimation system 125 are fine-tuned by minimizing a loss function that consists of the original loss from the labelled dataset … and the loss from the unlabeled data …” It would appear that Gu et al determines the difference between labeled data and unlabeled data, as opposed to the difference between a first label and an actual label.
Claim 11 discloses the following limitation(s), which was/were not found, taught, disclosed, or suggested in the prior art:
determining, in the label estimation module after the first update, a third label based on the third feature, wherein the third label comprises an estimated speed
determining a first estimated trajectory of the first inertial measurement unit in the first time period based on a duration of the first time period and the third label
determining a trajectory difference between the first estimated trajectory and the first trajectory
performing a third update on the parameter of the feature extraction module and the parameter of the label estimation module in a direction of reducing the trajectory difference
Gu et al appears to be silent about determining a third label, wherein the third label comprises an estimated speed. Although a secondary reference that teaches the general principle of estimated speed could be applied, the examiner could not find proper motivation to incorporate a secondary reference that teaches the detailed whole of all of the above claimed limitations.
Claim 12 depends on claim 11 and also includes the above limitations that were not found, taught, disclosed, or suggested in the prior art, as a result of its dependency.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Dugne-Hennequin, Q; Uchiyama, H.; and Lima, J. – “Understanding the Behavior of Data-Driven Inertial Odometry with Kinematics-Mimicking Deep Neural Network”; IEEE Access; Volume 9, 2021, pages 36589-36619
Wang, Yingying and Wang Chaoqun – “Pose-Invariant Inertial Odometry for Pedestrian Localization”; IEEE Transactions on Instrumentation and Measurement, Vol. 70, 2021
Wu et al (US Pat 11639981) discloses a method, apparatus, and system for movement tracking.
Wu et al (US Pat 10866302) discloses a method, apparatus, and system for wireless inertial measurement.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEONARD S LIANG whose telephone number is (571)272-2148. The examiner can normally be reached M-F 10:00 AM - 7 PM.
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, ARLEEN M VAZQUEZ can be reached at (571)272-2619. 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.
/LEONARD S LIANG/ Examiner, Art Unit 2857 07/11/26
Prosecution Insights