Ex Parte Deshpande et alDownload PDFPatent Trial and Appeal BoardFeb 19, 201612111325 (P.T.A.B. Feb. 19, 2016) Copy Citation UNITED STA TES p A TENT AND TRADEMARK OFFICE APPLICATION NO. FILING DATE 12/111,325 04/29/2008 48062 7590 02/23/2016 RYAN, MASON & LEWIS, LLP 1175 Post Road East 2nd Floor Westport, CT 06880 FIRST NAMED INVENTOR Prasad M. Deshpande UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O. Box 1450 Alexandria, Virginia 22313-1450 www .uspto.gov ATTORNEY DOCKET NO. CONFIRMATION NO. IN920080026US 1 7146 EXAMINER GREENE, SABRINA LETICIA ART UNIT PAPER NUMBER 2172 NOTIFICATION DATE DELIVERY MODE 02/23/2016 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address( es): ctoffice@rml-law.com kmm@rml-law.com mjc@rml-law.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE BEFORE THE PATENT TRIAL AND APPEAL BOARD Ex parte PRASAD M. DESHPANDE, RAGHURAM KRISHNAPURAM, DEBAPRIYO MAJUMDAR, and DEEP AK S. PADMANABHAN Appeal2014-002730 1 Application 12/111,325 Technology Center 2100 Before JEAN R. HOMERE, WILLIAM M. FINK, and JOSEPH P. LENTIVECH, Administrative Patent Judges. HOMERE, Administrative Patent Judge. DECISION ON APPEAL STATEMENT OF THE CASE Appellants seek our review under 35 U.S.C. § 134(a) of the Examiner's final rejection of claims 1 and 4--13. App. Br. 1. Claims 2 and 3 have been canceled. Id. at 17. We have jurisdiction under 35 U.S.C. § 6(b ). We reverse. 1 Appellants identify the real party in interest as International Business Machines Corp. App. Br. 1. This appeal is related to Appeal No. 2014- 002739 (SIN 12/111,356). Appeal2014-002730 Application 12/111,325 Appellants 'Invention Appellants invented a system for ascertaining the behavioral pattern of a multitasking user by examining the user's activities recorded in action logs. Spec. 4: 11-19, Fig. 2. In particular, upon determining a task associated with each user's action in the activity logs, a confidence score is computed for the task to thereby compute a first probability distribution for a set of open tasks associated with the user as a normalized weighted average of distributions over a predetermined number of previous actions performed by the user. Id. at 6:25-7:8. Further, upon determining a distribution of recency associated with the set of open tasks, the first probability distribution is combined therewith to compute a second probability distribution for the user. Finally, the task with the highest confidence score is correlated with the maximal probability in the second probability distribution to thereby segregate each activity log on a per-task basis to derive a behavioral pattern of the multitasking user. Id. at 8:19-27. Illustrative Claim Independent claim 1 is illustrative, and reads as follows: 1. A method for segregating multiple action logs of at least one multitasking user to derive at least one behavioral pattern of the at least one multitasking user, comprising the steps of: obtaining multiple action logs for a user from multiple web sites, configuration information, domain knowledge, at least one task history and open task repository information; correlating the multiple action logs, configuration information, domain knowledge, at least one task history and open task repository information to determine a task associated with each of one or more actions in the multiple action logs, where there is no explicit indication of the task associated with 2 Appeal2014-002730 Application 12/111,325 each of the one or more actions performed, wherein said correlating comprises: associating each of one or more actions in the multiple action logs with a task in the open task repository; computing a confidence score for each task in the open task repository associated with the one or more actions, said computing comprising: computing a first probability distribution for a set of tasks associated with the user from the open task repository as a normalized weighted average of distributions over a pre-determined number of previous actions restricted to the set of tasks performed by the user; computing a distribution of recency of tasks opened in the set of tasks; and combining the probability distribution and the distribution of recency of tasks to determine a second probability distribution for the user; and identifying the task with the highest confidence score, wherein the highest confidence score corresponds to the task having the maximal probability in the second probability distribution; automatically segregating the multiple action logs of the at least one multitasking user on a per-task basis based on the identified task; and using the multiple action logs that have been segregated on a per-task basis to derive at least one behavioral pattern of the at least one multitasking user and a sequence of one or more additional actions based on the identified task and the at least one behavioral pattern. Prior Art Relied Upon Tamir US 6,957 ,390 B2 Oct. 18, 2005 3 Appeal2014-002730 Application 12/111,325 Rejection on Appeal Appellants request review of the Examiner's rejection of claims 1 and 4--13 under 35 U.S.C. § 102(b) as being anticipated by Tamir. ANALYSIS Dispositive Issue: Under 35 U.S.C. § 102, did the Examiner err in finding Tamir describes "computing a first probability distribution for a set of tasks associated with the user from the open task repository as a normalized weighted average of distributions over a pre-determined number of previous actions restricted to the set of tasks performed by the user," as recited in independent claim 1? Appellants argue Tamir does not describe the disputed limitations emphasized above. App. Br. 7-12. In particular, Appellants argue Tamir's disclosure of multiplying "running total results" by an unspecified "numerical \x1eighting factor" to generate "a plurality of total rttnning scores" does not describe computing the first probability distribution. App. Br. 8-9 (citing Tamir 19: 14--22). According to Appellants, the "running totals" refer to "URL totals or counts" that are "counted by domain name only," and do not constitute the claimed "normalized weighted average" that makes up the first probability distribution. Id. In response, the Examiner finds Tamir's disclosure of assigning an identifier to a user and webpages visited by the user to track the user's activities thereon according to the user's preferred layout view describes recording the user's activities. Ans. 14 (citing Tamir 1 :50-67, 2: 1---6). Further, the Examiner finds Tamir's disclosure of assigning a numerical weighting factor to each running total to thereby adjust the relevance of a 4 Appeal2014-002730 Application 12/111,325 particular running total result, which can be further adjusted according to the amount of time the user spends at each domain/webpage as a way to generate a plurality of running total scores, describes the first and second probability distributions of the user. Id. at 15-16 (citing Tamir 19:1-53). We do not agree with the Examiner. Tamir discloses a server for tracking a running total for a user's current and prior sessions including web pages visited by the user, a preferred view/layout, as well as the amount of time spent by the user visiting each webpage. Tamir 19:1-13. The server adjusts the relevance of the running total by multiplying it with a weighing factor. The server further adjusts the running total according to the amount of time the user spends on each webpage to thereby generate a plurality of running total scores. Id. at 19: 14--22. Finally, the server compares the user's highest running total score (indicating the top weighted and adjusted web site) with database records to thereby determine the user's behavior (e.g., preferred style). Id. at 19:23-31. As correctly argued by Appellants, Tamir's "running total" does not describe a first probability distribution for a set of tasks associated with the user. Further, although the adjusted "running total" does indicate the weighted summation of a set of activities or tasks performed by the user including total number of websites visited, we agree with Appellants such weighted values do not describe a first probability distribution as a normalized weighted average therefor. See, e.g., Spec. 8:19-27. We recognize nonetheless that one of ordinary skill in the art, given the cited user's set of tasks/activities disclosed by Tamir, would have readily known how to compute a normalized weighted average therefor. However, under 5 Appeal2014-002730 Application 12/111,325 an anticipation standard, the disclosure of computation of the normalized weighted average associated with the user's set of tasks is not readily ascertainable from the cited portions of Tamir. 2 Because Appellants have shown at least one reversible error in the Examiner's rejection, we need not reach Appellants' remaining arguments. Accordingly, Appellants have shown the Examiner erred in finding Tamir anticipates claim 1. Because claims 4--13 also recite commensurate limitations to those of claim 1 discussed above, we similarly find error in the rejection of those claims. DECISION We reverse the Examiner's anticipation rejection under 35 U.S.C. § 102(b) of claims 1 and 4--13 as set forth above. REVERSED 2 In the event of further prosecution, the Examiner should instead consider rejecting these claims under 35 U.S.C. § 103(a) as being unpatentable over Tamir. 6 Copy with citationCopy as parenthetical citation