DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This non-final office action is in response to the application filed 29 June 2023.
Claims 1-20 are pending. Claims 1 and 11 are independent claims.
Drawings
The examiner accepts the drawings filed 29 June 2023.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4 and 11-14 are rejected under 35 U.S.C. 103 as being unpatentable over Deselaers et al. (US 2018/0188938, published 5 July 2018, hereafter Deselaers) and further in view of Miyabe et al. (US 2023/0408259, filed 6 June 2023, hereafter Miyabe) and further in view of Luo et al. (US 11620019, patented 4 April 2023, hereafter Luo).
As per independent claim 1, Deselaers discloses a device for stylus trajectory prediction, the device comprising:
memory including instructions (Figure 1; paragraph 0062: Here, a machine learning computer system includes a processor and memory)
processing circuitry (Figure 1; paragraph 0062: Here, a machine learning computer system includes a processor and memory) that, when in operation, is configured by the instructions to:
obtain a set of points, the set of points derived from a stylus moving on a surface (paragraph 0002: Here, a stylus is used to enter data on a touch sensitive display. This input is interpreted into touch sensitive points (paragraph 0003))
invoke an artificial neural network on an input set (paragraph 0027: Here, the machine learned touch interpretation prediction model is implemented as an artificial neural network), the input set based on a set of points (paragraph 0003: Here, a set of points is obtained based upon interpreted touch data), the ANN configured to output a next point from the input set, the next point being a prediction of a location of the stylus on the surface (paragraph 0022: Here, a touch interpretation prediction model receives input touch points and outputs a prediction of the future touch point at a next time step), the ANN trained to minimize a weighted function for the next point (paragraph 0112: Here, the ANN is trained to minimize the weighted loss function)
communicate the next point for rendering on a display (paragraph 0005: Here, a touch point prediction includes a next touch point (paragraph 0022)
Deselaers fails to specifically disclose:
the ANN trained to minimize a weighted sum of errors, the weighted sum prioritizing angular error components over other error components
However, Miyabe, which is analogous to the claimed invention because it is directed toward training a neural network, discloses the ANN trained to minimize a weighted sum of errors (paragraph 0077: Here, a neural network is trained using an error function. Weights are adjusted such as to minimize a sum of the error function on the training data). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Miyabe with Deselaers, with a reasonable expectation of success, as it would have allowed for improving the neural network by minimizing the weighted sum of errors and retraining the neural network to improve accuracy of the output (Miyabe: paragraph 0077).
Further, Luo, which is analogous to the claimed invention because it is directed toward determining errors contributing to a weighted sum, discloses the weighted sum prioritizing angular error components over other components (column 10, line 61- column 11, 16: Here, the weighted sum may be calculated including a combination of values including angular error. Further, angle-based filtering may be performed to prioritize angular error based components when calculating the sum (Figure 5; column 12, lines 7-40). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Luo with Deselaers-Miyabe, with a reasonable expectation of success, as it would have allowed for predicting a stylus contact point at a future time based upon angular error components (column 11, lines 28-43).
As per dependent claim 2, Deselaers, Miyabe, and Luo disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Deselaers discloses wherein the processing circuitry is configured by the instructions to create the input set from the set of points (paragraph 0002: Here, a stylus is used to enter data on a touch sensitive display. This input is interpreted into touch sensitive points (paragraph 0003)).
As per dependent claim 3, Deselaers, Miyabe, and Luo disclose the limitations similar to those in claim 2, and the same rejection is incorporated herein. Deselaers discloses wherein, to create the input set from the set of points, the processing circuity is configured by the instructions to interpolate the set of points in time to product uniform time intervals between points (paragraph 0005: Here, touch inputs, including touch points, are received over a time interval. The touch sensor data is provided as a time-stepped sequence (uniform time interval) associated with each touch point (paragraphs 0025 and 0035)).
As per dependent claim 4, Deselaers, Miyabe, and Luo disclose the limitations similar to those in claim 3, wherein the input set is a vector of coordinates, each element of the vector representing an interpolated position at the uniform time interval (paragraph 0102: Here, time information is provided in the form of a time vector).
With respect to independent claim 11, the claim recites the limitations substantially similar to those in claim 1. The rejection of claim 1 is incorporated herein by reference.
Additionally, Deselaers discloses at least one non-transitory machine readable medium including instructions for style trajectory prediction, the instructions, when executed by processing circuitry of a device, cause the processing circuitry to perform operations (paragraph 0006).
With respect to claims 12-14, the claims recite the limitations substantially similar to those in claims 2-4, respectively. Claims 12-14 are rejected under similar rationale.
Claims 5-7 and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Deselaers, Miyabe, and Luo, and further in view of Stepp et al. (US 2021/0287554, published 16 September 2021, hereafter Stepp).
As per dependent claim 5, Deselaers, Miyabe, and Luo disclose the limitations similar to those in claim 4, and the same rejection is incorporated herein. Deselaers fails to specifically disclose wherein to create the input set, the processing circuitry is configured by the instructions to normalize the vector with respect to origin, length, or angle.
However, Stepp, which is analogous to the claimed invention because it is directed toward normalizing vector data, discloses normalize the vector with respect to origin, length, or angle (paragraph 0055: Here, the vector is normalized with respect to trajectory at a time where the trajectory normalizer convers the trajectories into normalized trajectories by setting an initial position as the origin). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Stepp with Deselaers-Miyabe-Luo, with a reasonable expectation of success, as it would have allowed for normalizing data so that it can be properly classified by the neural network (Stepp: paragraphs 0055 and 0067).
As per dependent claim 6, Deselaers, Miyabe, Luo, and Stepp disclose the limitations similar to those in claim 5, and the same rejection is incorporated herein. Deselaers discloses identifying the latest detected coordinate of the stylus (paragraph 0002: Here, a stylus is used to enter data on a touch sensitive display. This input is interpreted into touch sensitive points (paragraph 0003)).
Deselaers fails to specifically disclose shift an origin of the vector to a coordinate. However, Stepp discloses shifting an origin of the vector to a coordinate (paragraph 0055: Here, the vector is normalized with respect to trajectory at a time where the trajectory normalizer convers the trajectories into normalized trajectories by setting an initial position as the origin coordinate). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Stepp with Deselaers-Miyabe-Luo, with a reasonable expectation of success, as it would have allowed for normalizing data so that it can be properly classified by the neural network (Stepp: paragraphs 0055 and 0067).
As per dependent claim 7, Deselaers, Miyabe, Luo, and Stepp disclose the limitations similar to those in claim 5, and the same rejection is incorporated herein. Stepp discloses wherein to normalize the vector with respect to origin, the processing circuity is configured by the instructions to rotate the vector to a predefined angle (paragraph 0055: Here, the transformed coordinate system is mathematically rotated such that the object always remails on the first axis). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Stepp with Deselaers-Miyabe-Luo, with a reasonable expectation of success, as it would have allowed for normalizing data so that it can be properly classified by the neural network (Stepp: paragraphs 0055 and 0067).
With respect to claims 15-17, the claims recite the limitations substantially similar to those in claims 5-7, respectively. Claims 15-17 are rejected under similar rationale.
Claims 8-10 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Deselaers, Miyabe, and Luo, and further in view of Suitoh et al. (US 2018/0270417, published 20 September 2018, hereafter Suitoh).
As per dependent claim 8, Deselaers, Miyabe, and Luo disclose the limitations similar to those in claim 2, and the same rejection is incorporated herein. Deselaers fails to specifically disclose wherein to create the input set from the set of points, the processing circuity is configured by the instructions to convert the set of points into polar coordinates, wherein each coordinate is defined by a pair that includes a radius and an angle.
However, Suitoh, which is analogous to the claimed invention because it is directed toward converting pixel points to polar coordinates, discloses wherein to create the input set from the set of points, the processing circuity is configured by the instructions to convert the set of points into polar coordinates, wherein each coordinate is defined by a pair that includes a radius and an angle (paragraph 0167: Here, a point is expressed by 2D polar coordinates including a radius vector and an angle). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Suitoh with Deselaers-Miyabe-Luo, with a reasonable expectation of success, as it would have allowed for improved processing of captured coordinate data (Suitoh: paragraph 0169).
As per dependent claim 9, Deselaers, Miyabe, Luo, and Suitoh disclose the limitations similar to those in claim 8, and the same rejection is incorporated herein. Deselaers discloses wherein the ANN is trained on the input set to reduce error (paragraph 0022: Here, a touch interpretation prediction model receives input touch points and outputs a prediction of the future touch point at a next time step. Further, the ANN is trained to minimize the weighted loss function (paragraph 0112)).
Deselaers fails to specifically disclose the input set including the angle. However, However, Suitoh, discloses wherein the input set of points is defined by a pair that includes a radius and an angle (paragraph 0167: Here, a point is expressed by 2D polar coordinates including a radius vector and an angle). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Suitoh with Deselaers-Miyabe-Luo, with a reasonable expectation of success, as it would have allowed for improved processing of captured coordinate data (Suitoh: paragraph 0169).
As per dependent claim 10, Deselaers, Miyabe, Luo, and Suitoh disclose the limitations similar to those in claim 8, and the same rejection is incorporated herein. Deselaers discloses wherein the ANN is trained on the input set to predict and reduce error (paragraph 0022: Here, a touch interpretation prediction model receives input touch points and outputs a prediction of the future touch point at a next time step. Further, the ANN is trained to minimize the weighted loss function (paragraph 0112)).
Deselaers fails to specifically disclose the input set includes the radius and angle independently. However, However, Suitoh, discloses wherein the input set of points is defined by a pair that includes a radius and an angle independently (paragraph 0167: Here, a point is expressed by 2D polar coordinates including a radius vector and an angle. These two parameters are independent parameters). It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Suitoh with Deselaers-Miyabe-Luo, with a reasonable expectation of success, as it would have allowed for improved processing of captured coordinate data (Suitoh: paragraph 0169).
With respect to claims 18-20, the claims recite the limitations substantially similar to those in claims 8-10, respectively. Claims 18-20 are rejected under similar rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Katz et al. (US 2020/0103980): Discloses a machine learning technique using deep learning to predict anticipated movement of a location at which a finger will arrive (paragraph 0039)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYLE R STORK whose telephone number is (571)272-4130. The examiner can normally be reached 8am - 2pm; 4pm - 6pm.
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, Omar Fernandez Rivas can be reached at 571/272-2589. 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.
/KYLE R STORK/Primary Examiner, Art Unit 2128