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 .
Response to Arguments
Applicant's arguments filed 7/24/2026 have been fully considered but they are not persuasive.
The applicant contends Bathwal et al fails to disclose the limitation “obtain one or more first data objects each having a first structure in a first format identifying fields of the one or more document objects …”.
The examiner disagrees. As indicated in the applicant’s remarks, label 606 of Fig. 6 states a summary of search result documents is generated. A summary of a document indicates “a short, clear description that gives the main facts or ideas about” the document is generated. (SUMMARY | English meaning - Cambridge Dictionary) A field is defined as “an area of activity or interest” (FIELD | English meaning - Cambridge Dictionary). Based on such definition, a summary providing a short and clear description of main facts or ideas would provide information, found in the document, regarding an areas of activity or interests or fields, depending on the contents of the document being summarized. For these reasons, the examiner believes the recited claimed language is disclosed by Bathwal et al. The rejection below reflects consideration of the amended limitation indicated above.
The applicant contends Bathwal et al fails to disclose the limitation “provide input to a large language model (LLM) including the query, the first data objects and one or more second data objects generated based on the first data objects, the second data objects each having a second structure in a second format that is compatible with the LLM and different from the first format …”.
The examiner disagrees. The recited limitation does not recite limitations specify what is constituted as a “first data object”, “second data object”, “a first format” and “a second format”, hence leaving such limitations interpreted in the broadest reasonable interpretation without reading the specification into the claim. Furthermore, the claimed language does not specify boundaries to the limitation compatible for the LLM. What format is not compatible to the LLM? Due to the breath of the claimed language, the examiner interprets “first data object” as summary or search result documents, “second data object” as citations such as hyperlinks, “a first format” as the format of the summary and “a second format” as the format of the hyperlink. The examiner interprets a format compatible with the LLM as a format the LLM uses to generate an output. Based on such interpretation, the office action, presented previous and indicated below, describes the correlation between Bathwal et al’s disclosure and the recited limitation. Please see the office action below.
The applicant contends Bathwal et al fails to teach “provide input to a large language model (LLM) including the query, the first data objects and one or more second data objects”.
The examiner disagrees. Fig. 2, label 220 as the generative LLM. Fig. 2 shows 220 receiving the outputs from label 224 via label 226 and input query via label 236. This indicates the query (label 236) and first data object (output from label 224, received at label 226 which is part of label 220) is received by the LLM 220. The following sections of Bathwal et al discloses citations are received by the LLM:
[0037] “ … returned search results such as number of results to be returned, citation options, thresholds for classification or other determines, or the like …”.
[0039] “As utilized herein, a single best answer includes a search result that is constructed to be responsive to the user search and may include elements from multiple source documents, with citations within the single best answer to the multiple source documents utilized to construct the answer”.
[0043] “The example result construction component 130 includes a citation processor 138 component that incorporates citations into the constructed answer, for example using linked text (e.g., text elements from the source that are hyperlinked to the source), footnotes, or the like.”
[0066] “The user select source types, source trust values (e.g., including quantitative values, such as a trust index value on a slider bar, and/or qualitative values such as categories of sources to include or exclude), or the like, where the single answer may be updated, for example, by refreshing the answer and/or modifying the answer in real time.”
Such paragraphs indicate the citations used to generate the output from label 226 is received by the LLM, such as label 226, in order to incorporate citations into the final summarization, wherein the final summarization is outputted to the user.
For the reasons indicated above and amendments, the office action below considers the amendments in view of the reference. Please see the office action below.
Claim Rejections - 35 USC § 102
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.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-2,4-19 is/are rejected under 35 U.S.C. 102a1 as being anticipated by Bathwal et al (US Publication No.: 20240281487).
Claim 1, Bathwal et al discloses
One or more processors (Paragraphs 91,103 discloses one or more processors), coupled with memory (Paragraph 103), to:
Receive a query (Fig. 6, label 602) indicating a request for one or more document objects (label 602 indicates a search query is requested. Documents are retrieved at label 604 (one or more document objects).) and including one or more criteria for selection of the one or more document objects (Paragraph 106 discloses selection of documents from the plurality of search result documents pertinent to a subject of the search query (one or more criteria).);
Obtain one or more first data objects (Fig. 6, label 606 discloses generation of a summary of search result documents. Paragraph 93 discloses “generates a summary of each of the plurality of search result documents …”.) each having a first structure in a first format identifying fields of the one or more document objects (label 606 where summary of the search result documents indicates a synopisis or overview of the content of the document. Depending on the content of the document, the summary identifies the fields of the document when the document includes content regarding fields.), the first data objects searchable according to the one or more criteria via the first structure (Fig. 6, label 610 indicates citations are included in the reply to query indicating such summaries or first data objects are searchable according to the document search results at label 604.);
Provide input to a large language model (LLM) (Fig. 2, label 220 LLM) including the query (Fig. 2, label input query), the first data objects (Fig. 2, label 224 summaries of each of the plurality of search result documents or first data objects), and one or more second data objects (Fig. 2, label 226 similarly found in Fig. 6, label 608. Per-document summaries output by label 224 are input into 226 to output a compiled summary with citations (second data objects).) generated based on the first data objects (Fig. 2, label 226 is generated based on 224 (first data objects).), the second data objects each having a second structure in a second format that is compatible with the LLM (Fig. 2, label 226 includes citations or second data objects in the format of hyperlinks or citations for reference, which are compatible for the LLM since the LLM uses such citations to generate the final summary. The citations or second data objects are used to generate the final summary, output 238.) and different from the first format (Fig. 2, label 224 first data objects are summaries, while label 226, second data objects are citations or hyperlinks. Hyperlinks or citations have a different format to summaries. For example, Fig. 3, label 308 as generated summary with format of text, Fig. 3, label 310,324 as citation with a format of image.); and
Generate, by the LLM according to the input, a reply to the query identifying a set of the one or more document objects that satisfies the one or more criteria for selection (Fig. 2, label 238, wherein the reply includes a summary with citations of document objects (search result documents) relevant to the query. Fig. 6, label 610).
Claim 2, Bathwal et al discloses generate, by the LLM (Fig. 2, label 220) according to a second input including the one or more document objects (Fig. 2, label 212, paragraph 88 discloses retrieving documents associated with the input query, label 236.) and one or more third data objects (Fig. 2, label 228), one or more summary objects (Fig. 2, label 224 generates summary objects) each respectively including object text descriptive of each of the document objects (label 224 outputs summaries of each of the document objects or search result documents.).
Claim 4, Bathwal et al discloses the third data objects each have the second structure in the machine-readable format that is compatible with the LLM (Fig. 2, label 228 indicates the third data objects having format as dialogues or question+answer used by the LLM, indicating such format is compatible with the LLM.).
Claim 5, Bathwal et al discloses generate the second data objects based on the first data objects to indicate common data according toa first format of the first structure and a second format for the second structure (Fig. 2, label 226, citations or second data objects are generated based on the first data objects (summaries output by label 224) to indicate common data (citations found in the document objects) according to the first format of the first data objects (summaries output by label 224) and second format of the second data object (citations).).
Claim 6, Bathwal et al discloses the first format corresponding to a text-based format (Fig. 2, label 224 outputs summaries of the search result documents, wherein summaries are text based format) and the second format corresponding to a machine readable format (Fig. 2, label 226, citations are a machine readable format).
Claim 7, Bathwal et al discloses the second structure corresponds to at least one or an embedding compatible with the LLM or a vector compatible with the LLM (Paragraph 85 discloses cross-document citations for summarization information that involve unique identifiers of each source document or search result documents or document objects. Such identifiers can be considered a vector or embedding compatible with the LLM since such citations are used to generate the final output in Fig. 2, label 238,226.).
Claim 8, Bathwal et al discloses
Determine, by the LLM according to the input, a natural language corresponding to the content of the query (Paragraph 40 discloses natural language processor to parse the search query into specific terms, indicated intents, etc. Fig. 2, label 238 as the output to the user, natural language corresponding to the query, label 236.); and
Modifying, by the LLM according to the input, at least one portion of at least one of the documents to the natural language (paragraph 30 discloses “natural language processor that refines the summaries to ensure they are written in clear, natural language.” Paragraph 49 discloses using the natural language processor to build out the final answer for presentation to the user. Paragraph 52 discloses 220 includes multi-turn disambiguation personalization to determine system’s understanding of the user’s intent.).
Claim 9, Bathwal et al discloses determine the natural language according to a plurality of queries including the query, the plurality of queries corresponding to a chat history of a plurality of inputs for the LLM (Paragraph 57 discloses a final output is generated reflecting an interpretation of the user’s input 236 based on iterative dialogues with the user, label 228.).
Claim 10 recites similar limitations as claim 1 and rejected on the same grounds as claim 1.
Claim 11 recites similar limitations as claim 2 and rejected on the same grounds as claim 2.
Claim 12 recites similar limitations as claim 3 and rejected on the same grounds as claim 3.
Claim 13 recites similar limitations as claim 4 and rejected on the same grounds as claim 4.
Claim 14 recites similar limitations as claim 5 and rejected on the same grounds as claim 5.
Claim 15 recites similar limitations as claim 6 and rejected on the same grounds as claim 6.
Claim 16 recites similar limitations as claim 7 and rejected on the same grounds as claim 7.
Claim 17 recites similar limitations as claim 8 and rejected on the same grounds as claim 8.
Claim 18 recites similar limitations as claim 9 and rejected on the same grounds as claim 9.
Claim 19 recites similar limitations as claim 1 and rejected on the same grounds as claim 1.
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.
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) 3,20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bathwal et al (US Publication No.: 20240281487) in view of Sasha et al (US Publication No.: 20190034882).
Claim 3, Bathwal et al discloses modify the one or more first data objects to include the object text for respective instances of the one or more document objects (Fig. 2, label 226 includes citations from the references for the compiled summaries from 224), but fails to disclose wherein the object text is descriptive of at least one of a job description or one or more skills corresponding to the job description.
Sasha et al discloses search result documents such as job positing results (Fig. 3, label job posting results) determined for a user input query (Fig. 3, label user input), wherein the search result documents includes description of at least one job description or one or more skills corresponding to the job description (Fig. 3, label ranked job posting results, wherein the job posting results includes description of the job.).
It would be obvious to one skilled in the art before the effective filing date of the application to modify Bathwal et al’s search result documents with job posting as search results as disclosed by Sasha et al so to provide the user with information as per the user’s request or query when the user desires information on job postings.
Claim 20 recites similar limitations as claim 2,3 and rejected on the same grounds as claim 2,3.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LINDA WONG whose telephone number is (571)272-6044. The examiner can normally be reached 9-5.
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, Andrew C Flanders can be reached at 571-272-7516. 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.
/LINDA WONG/Primary Examiner, Art Unit 2655
Prosecution Insights