Ex Parte Itzhak et alDownload PDFPatent Trial and Appeal BoardNov 14, 201710485108 (P.T.A.B. Nov. 14, 2017) Copy Citation United States Patent and Trademark Office 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 APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO. 10/485,108 02/03/2004 Ilan Itzhak 08011.3056-00000 4142 100692 7590 Oath Inc./Finnegan 901 New York Ave., NW Washington, DC 20001 11/16/2017 EXAMINER PARK, GRACE A ART UNIT PAPER NUMBER 2157 NOTIFICATION DATE DELIVERY MODE 11/16/2017 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): regional-desk @ finnegan. com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE BEFORE THE PATENT TRIAL AND APPEAL BOARD Ex parte ILAN ITZHAK, YARON GALAI, and ODED ITZHAK Appeal 2015-000438 Application 10/485,108 Technology Center 2100 Before MAHSHID D. SAADAT, JOHN A. EVANS, and JASON M. REPKO, Administrative Patent Judges. SAADAT, Administrative Patent Judge. DECISION ON APPEAL Appellants1 appeal under 35 U.S.C. § 134(a) from the Final Rejection of claims 51, 52, 57, 58, 63—82, and 91—98.2 We have jurisdiction under 35 U.S.C. § 6(b). We reverse. 1 According to Appellants, the real party in interest is AOL, Inc. (App. Br. 1). 2 Claims 53—56, 59—62, 83—90 have been canceled (see App. Br. 3). Appeal 2015-000438 Application 10/485,108 STATEMENT OF THE CASE Appellants’ invention is directed to a system and method for automated mapping of keywords and key phrases to documents in order to determine relationships between the content of these different documents, and/or relationships between the Web pages and/or other documents and key words or key phrases (Spec. 4:12—19). Exemplary claim 51 under appeal reads as follows: 51. A system for selecting an advertisement for display with a web page requested by a user through a web browser, the system comprising: at least one server, in communication with said web browser, configured to: receive, as input, a plurality of documents and a plurality of key terms; analyze content of the plurality of documents; automatically generate a key term feature vector for each key term based on the content of the plurality of documents, each key term feature vector comprising elements comprising a plurality of words or phrases that are related to the corresponding key term; analyze at least one of a Universal Resource Locator (“URL”) of said web page and a content of said web page; automatically generate a document feature vector based on the URL or the content of the web page, the document feature vector comprising elements comprising a plurality of words or phrases that are contained in the URL or content of the web page; compare the key term feature vector and the document feature vector; generate a relevance factor based on the similarity of the elements of the key term feature vector and the document feature vector; and 2 Appeal 2015-000438 Application 10/485,108 provide a relevant advertisement for display by said web browser with said web page according to the determined relevance factor. The Examiner rejected claims 51, 52, 57, and 58 under 35 U.S.C. § 103(a) as unpatentable over Graham (US 6,804,659 Bl; Oct. 12, 2004) and Shanahan (US 2003/0078899 Al; Apr. 24, 2003) (see Final Act. 3—5). The Examiner further added Kurtzman (US 6,044,376; Mar. 28, 2000) to reject claims 69—82 and 91—98 (see Final Act. 6—10), and Culliss (US 6,078,916; June 20, 2000) to reject claims 63—68 under 35 U.S.C. § 103(a) (see Final Act. 10-11). ANAFYSIS In rejecting claim 51, the Examiner finds Graham discloses all the recited elements of the claim except for “automatically generate a key term feature vector for each key term based on the content of the plurality of documents,...” and “compare the key term feature vector and the document feature vector,” for which the Examiner relied on Shanahan (see Final Act. 3—5). The Examiner cites paragraphs 4 and 48, which correspond to Figures 3 and 14 of Shanahan, for disclosing “learning class fuzzy sets includes: constructing class fuzzy set (key term feature vector). . . fuzzy set constructing a document fuzzy set with one of the set of features extracted from the text object” as the recited key term feature vector (Final Act. 5). Appellants contend Graham does not disclose “the document feature vector comprising elements comprising a plurality of words or phrases that are contained in the URF or content of the web page” (App. Br. 8). With respect to the teachings of Shanahan, Appellants contend the Examiner erred in characterizing the disclosed “class fuzzy set” and “document fuzzy set” as the claimed “key term feature vector” and “document feature vector” 3 Appeal 2015-000438 Application 10/485,108 because the fuzzy set generator defines a fuzzy set, such as a document fuzzy set or a class fuzzy set, based on the features produced by the feature extractor {id.). Lastly, Appellants contend Shanahan’s disclosure of “measuring a degree of match between each of the plurality of class fuzzy sets and the document fuzzy set” does not meet the claimed “compar[ing] the key term feature vector and the document feature vector” (App. Br. 9). The Examiner responds by pointing out the relevant portions of Graham and Shanahan which were outlined in the rejection (Ans. 2—6). With respect to the teachings of Shanahan, the Examiner explains: Shanahan teaches key term feature vector as “constructing a fuzzy set”, see Shanahan at Fig. 3, par. [0048]. Shanahan further teaches as “the fuzzy set generator 121 uses the feature vector 116 produced by feature reducer 117” see Shanahan at par. [0056]. Therefore, the class fuzzy set is generated from feature vector. Shanahan also further teaches a class fuzzy set with filters and rules for the class (see Shanahan at pr. [0004], [0046-0048], [0101-0111], [0131-0139], and Figures 3, 17). . . . Shanahan was added to show this concept of a class with the terms that indicate the inclusion in the class. In Shanahan, the class fuzzy set is created for a category key term. The class fuzzy set creates a vector of features (words) (See e.g. Shanahan para [0043-0044], [0058-0059], [0064]). These have been pulled from the training documents (See e.g. Shanahan para [0048-0058]). The features that are extracted and represented in the fuzzy set are words. The class or category is the key term and the related terms are the other features in the set. (Ans. 6—7). The Examiner further finds that “Additionally, Shanahan also teaches document feature vector (See e.g. Shanahan para [0005-0006], [0043-0044], [0073], and [0112]) that are created much like the class fuzzy sets described above” (Ans. 8). 4 Appeal 2015-000438 Application 10/485,108 Based on a review of Graham and Shanahan, we are persuaded by Appellants’ contention that the Examiner has not explained how Shanahan’s “class fuzzy set” and “document fuzzy set” meet the claimed “key term feature vector” and “document feature vector,” respectively. As further pointed out by Appellants (Reply Br. 3—4), the cited portions of Shanahan do not describe “what is included in the fuzzy sets or, in particular, that the fuzzy sets contain ‘words or phrases,’ as required by claim 51.” We also agree with Appellants that paragraph 44 of Shanahan defines a fuzzy set as a mapping from a universe of values to a unit interval (e.g., unit interval [0, 1]) (i.e., each element in the universe over which a variable is defined is assigned a membership value, which can be interpreted as the degree of prototypicality of this value to the concept being represented by the fuzzy set). (Reply Br. 4). In other words, the Examiner has not explained how the teachings of Shanahan with respect to a fuzzy set relates to the recited “key term feature vector comprising elements comprising a plurality of words or phrases that are related to the corresponding key term.”3 Therefore, Appellants’ arguments have persuaded us of error in the Examiner’s position with respect to the rejection of independent claim 51 and independent claim 57, which recites similar limitations. The Examiner has not identified any teachings in the other applied prior art that would make up for the above —mentioned deficiencies. We therefore do not sustain the rejection of claims 51 and 57, as well as claims 52, 58, 63—82, and 91—98 dependent therefrom. 3 We do not address Appellants’ other contentions because this contention is dispositive of the issue on appeal. 5 Appeal 2015-000438 Application 10/485,108 DECISION We reverse the Examiner’s decision to reject claims 51, 52, 57, 58, 63-82, and 91-98. REVERSED 6 Copy with citationCopy as parenthetical citation