DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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) 1-16 and 21-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sarferaz (U.S. 2021/0192376 hereinafter Sarferaz) in view of Achin et al. (U.S. 2018/0060738 hereinafter Achin).
As Claim 1, Sarferaz teaches:
A system comprising:
one or more processors (Sarferaz (¶0115 line 7-9), CPU) to:
the impact threshold indicating that the second features modify one or more of the forecast data points (Sarferaz (¶0034 line 3-6), local explanation provides an indication of features that were more or less relevant to a result);
causing a graphical user interface to present the forecast including one or more of the first features having respective first visual properties corresponding to identifiers of respective ones of the first features (Sarferaz (¶0091 line 4-9, fig. 6B), component information 654 allows a user to see how individual features contributed to an overall result);
causing the graphical user interface to present the forecast including one or more of the second features having a second visual property corresponding to an indication that the second features satisfy the impact threshold (Sarferaz (¶0091 line 4-9, fig. 6B), component information 654 allows a user to see how individual features contributed to an overall result. Sarferaz (112 last 4 lines, fig. 20B item 1055, ¶0069 line 3-end), granular local explanation includes contribution scores for two or more features of a plurality of feature. Good scores are highlighted in green. Average scores are highlighted in yellow or orange while bad scores are highlighted in red); and
causing the graphical user interface to modify the forecast including the second features to include an explanation portion including one or more metrics of the second features (Sarferaz (¶0085 line 1-5, fig. 6B), user selects result 630 to view more granular local explanation information), the metrics corresponding to respective time points of the time dependency relationship (Sarferaz (¶0081 last 3 lines), the ranking is based on delivery time).
Sarferaz may not explicitly disclose:
generating, by a first machine learning model receiving as input one or more first features including one or more input data points having a time dependency relationship, a forecast including one or more forecast data points having the time dependency relationship and positions after the one or more data points;
identifying, by a second machine learning model receiving as input the first features, one or more second features having respective impact metrics that satisfy an impact threshold,
Achin teaches:
generating, by a first machine learning model receiving as input one or more first features including one or more input data points having a time dependency relationship (Achin (¶0310 line 4-10, fig. 9 item 910, ¶0273 line 4-9), system fits model based on initial dataset. Initial dataset includes values of at least some of the features. Available data includes the 3 years of previous daily sales data), a forecast including one or more forecast data points having the time dependency relationship and positions after the one or more data points (Achin (¶0273 line 2-4), system predicts the next 6 weeks of daily sales for each of the supermarket’s locations);
identifying, by a second machine learning model receiving as input the first features (Achin (¶0312, fig. 9 item 930), system shuffles the value of particular feature “F”), one or more second features having respective impact metrics that satisfy an impact threshold (Achin (¶0313 line 1-5, fig. 9 item 940, ¶0314 line 3-7, fig. 9 item 950, ¶0319), predictive value of features F is calculated based on teh change in accuracy. Features are categorized based on predictive value),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify feature importance of Sarfeaz instead be a feature detection model taught by Achin, with a reasonable expectation of success. The motivation would be to “provide feature importance values either for a prediction problem in general or for a particular model may have numerous benefits” (Achin (¶¶ 0304-0308)).
As Claim 2, besides Claim 1, Sarferaz in view of Achin teaches wherein the operations further include: causing the graphical user interface to present the forecast including an impact indicator corresponding to a second feature of the second features and that indicates a magnitude of impact of the second feature associated with the explanation portion (Sarferaz (¶0091 line 4-9, fig. 6B), component information 654 allows a user to see how individual features contributed to an overall result).
As Claim 3, besides Claim 1, Sarferaz in view of Achin teaches wherein the operations further include:
causing the graphical user interface to present one or more portions of a selected feature of the second features (Sarferaz (¶0034 line 12-16), user can manually select features), the portions of the selected feature having the second visual property (Sarferaz (112 last 4 lines, fig. 20B item 1055, ¶0069 line 3-end), granular local explanation includes contribution scores for two or more features of a plurality of feature. Good scores are highlighted in green. Average scores are highlighted in yellow or orange while bad scores are highlighted in red).
As Claim 4, besides Claim 1, Sarferaz in view of Achin teaches wherein the operations further include:
causing the graphical user interface to present one or more portions of a selected feature of the second features at one or more time points having a time dependency relationship and corresponding to the forecast (Sarferaz (¶0085 line 1-5, fig. 6B), user selects result 630 to view more granular local explanation formation. Sarferaz (¶0081 last 3 lines), the ranking is based on delivery time).
As Claim 5, besides Claim 1, Sarferaz in view of Achin teaches the first visual properties corresponding to a first brightness, and the second visual property corresponding to a second brightness (Sarferaz (112 last 4 lines, fig. 20B item 1055, ¶0069 line 3-end), granular local explanation includes contribution scores for two or more features of a plurality of feature. Good scores are highlighted in green. Average scores are highlighted in yellow or orange while bad scores are highlighted in red).
As Claim 6, besides Claim 1, Sarferaz in view of Achin teaches the first visual properties corresponding to a first color, and the second visual property corresponding to a second color (Sarferaz (112 last 4 lines, fig. 20B item 1055, ¶0069 line 3-end), granular local explanation includes contribution scores for two or more features of a plurality of feature. Good scores are highlighted in green. Average scores are highlighted in yellow or orange while bad scores are highlighted in red).
As Claim 7, besides Claim 1, Sarferaz in view of Achin teaches wherein the operations further include: causing the graphical user interface to present a highlight cursor including a bar a particular time or times (Sarferaz (¶0091 line 4-9, fig. 6B), component information 654 allows a user to see how individual features contributed to an overall result. Results are displayed in a bar chart).
As Claim 8, besides Claim 1, Sarferaz in view of Achin teaches the impact metrics comprise at least one of a direction of impact, a magnitude of impact, or a type of impact (Sarferaz (¶0091 line 4-9, fig. 6B), component information 654 allows a user to see how individual features contributed to an overall result. Results are displayed in a magnitude of impact or type or impact or direction of impact).
As Claim 9-16, the Claims are rejected for the same reasons as Claims 1-8, respectively.
As Claim 21-24, the Claims are rejected for the same reasons as Claims 1-4, respectively.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Achin (US 2018/0046926) teaches selection of models using the evaluation score of the predictive model.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NHAT HUY T NGUYEN whose telephone number is (571)270-7333. The examiner can normally be reached M-F: 12:00-8:00 EST.
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, Viker Lamardo can be reached at 571-270-5871. 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.
/NHAT HUY T NGUYEN/ Primary Examiner, Art Unit 2147