DETAILED ACTION
Application No. 19/304,280 filed on 08/19/2025 has been examined. In this Office Action, claims 1-20 are pending.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/19/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP § 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto- processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-8, 10-14, 16, and 18-20 are rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claims 1-8, 10-12, 14-15, and 17-20 of U.S. Patent No. 12,443,637 B1. Although the claims at issue are not identical, they are not patentably distinct from each other because they cover substantially the same recitations and limitations, with certain limitations worded more broadly or slightly differently from the patented claims, but in essence they convey substantially the same subject matter. The instant application is a broader scope of recitation of the claims of the already patented application.
Present Application 19/304280
US PAT. 12443637 B1
1. A non-transitory, computer-readable storage medium comprising instructions recorded thereon, wherein the instructions, when executed by at least one data processor of a system, cause the system to: obtain a hierarchy of web pages including a top level web page and a lower level web page, wherein the hierarchy of web pages is publicly accessible; provide a search interface associated with the hierarchy of webpages; receive at the search interface a natural language search query as input; provide the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limit the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the hierarchy of webpages, thereby excluding the AI tool from accessing extraneous information and improving AI tool response times; and obtain, from the AI tool, a response to the natural language search query.
2. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: augment the natural language search query using a retrieval-augmented generation (RAG) framework before providing the natural language search query to the AI tool, wherein the RAG framework fetches relevant information to the natural language search query from a pre-compiled database of information, and wherein information fetched by the RAG framework directs the AI tool towards generating a response to the natural language search query that is relevant; and provide the augmented natural language search query to the AI tool.
3. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: extract a semantic meaning from the natural language search query; receive information related to the semantic meaning from a pre-compiled database of information; augment the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and provide the augmented natural language search query to the AI tool.
4. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: display, at the search interface, an example search query; wherein the example search query is based on information contained on pages in the hierarchy of webpages; receive a selection of the example search query from a user of a page associated with the hierarchy of webpages; and provide the example search query to the AI tool.
5. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: prompt a user of a page associated with the hierarchy of webpages to submit feedback regarding quality of the response to the natural language search query; receive the feedback regarding quality of the response to the natural language search query; and provide the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
6. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: provide a header bar associated with a page in the hierarchy of webpages; and customize the header bar to include the search interface, thereby allowing natural language search queries to be received and provided to the AI tool via the header bar.
7. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: provide text on a page associated with the hierarchy of webpages which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
8. A method comprising: obtaining a hierarchy of web pages including a top level web page and a lower level web page, wherein the hierarchy of web pages is publicly accessible; providing a search interface associated with the hierarchy of webpages; receiving at the search interface a natural language search query as input; providing the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limiting the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the hierarchy of webpages, thereby excluding the AI tool from accessing extraneous information and improving AI tool response times; and obtaining, from the AI tool, a response to the natural language search query.
10. The method of claim 8, further comprising: extracting a semantic meaning from the natural language search query; receiving information related to the semantic meaning from a pre-compiled database of information; augmenting the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and providing the augmented natural language search query to the AI tool.
11. The method of claim 8, further comprising: displaying, at the search interface, an example search query; wherein the example search query is based on information contained on pages in the hierarchy of webpages; receiving a selection of the example search query from a user of a page associated with the hierarchy of webpages; and providing the example search query to the AI tool.
12. The method of claim 8, further comprising: prompting a user of a page associated with the hierarchy of webpages to submit feedback regarding quality of the response to the natural language search query; receiving the feedback regarding quality of the response to the natural language search query; and providing the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
13. The method of claim 8, further comprising: providing text on a page associated with the hierarchy of webpages which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
14. A system comprising: at least one hardware processor; and at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the system to: obtain a hierarchy of web pages including a top level web page and a lower level web page, wherein the hierarchy of web pages is publicly accessible; provide a search interface associated with the hierarchy of webpages; receive at the search interface a natural language search query as input; provide the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limit the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the hierarchy of webpages, thereby excluding the AI tool from accessing extraneous information and improving AI tool response times; and obtain, from the AI tool, a response to the natural language search query.
16. The system of claim 14, further comprising instructions to: extract a semantic meaning from the natural language search query; receive information related to the semantic meaning from a pre-compiled database of information; augment the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and provide the augmented natural language search query to the AI tool.
18. The system of claim 14, further comprising instructions to: prompt a user of a page associated with the hierarchy of webpages to submit feedback regarding quality of the response to the natural language search query; receive the feedback regarding quality of the response to the natural language search query; and provide the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
19. The system of claim 14, further comprising instructions to: provide a header bar associated with a page in the hierarchy of webpages; and customize the header bar to include the search interface, thereby allowing natural language search queries to be received and provided to the AI tool via the header bar.
20. The system of claim 14, further comprising instructions to: provide text on a page associated with the hierarchy of webpages which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
1. A non-transitory, computer-readable storage medium comprising instructions recorded thereon, wherein the instructions, when executed by at least one data processor of a system, cause the system to: generate an internal hierarchy of pages, wherein the internal hierarchy includes a top level page and lower level page, wherein the lower level page is accessible from the top level page; associate access permissions with a page in the internal hierarchy in order to permit access to a restricted group of users; receive an indication designating that a page within the internal hierarchy is publicly accessible and an indication designating a domain associated with the page; upon receiving the indications designating that the page is publicly accessible and designating the domain, create an external hierarchy of pages including an external top level page and an external lower level page, wherein the external lower level page is accessible from the external top level page, wherein the external lower level page is different from the lower level page associated with the internal hierarchy; add the page to the external hierarchy; publish the page to the domain associated with the page; provide a search interface to the published page; receive at the search interface a natural language search query as input; provide the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limit the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the external hierarchy, thereby excluding the AI tool from accessing information contained on pages associated with the internal hierarchy but not the external hierarchy; and obtain, from the AI tool, a response to the natural language search query.
2. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: augment the natural language search query using a retrieval-augmented generation (RAG) framework before providing the natural language search query to the AI tool, wherein the RAG framework fetches relevant information to the natural language search query from a pre-compiled database of information, and wherein information fetched by the RAG framework directs the AI tool towards generating a response to the natural language search query that is relevant; and provide the augmented natural language search query to the AI tool.
3. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: extract a semantic meaning from the natural language search query; receive information related to the semantic meaning from a pre-compiled database of information; augment the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and provide the augmented natural language search query to the AI tool.
4. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: display, at the search interface, an example search query; wherein the example search query is based on information contained on pages in the external hierarchy; receive a selection of the example search query from a user of the page; and provide the example search query to the AI tool.
5. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: prompt a user of the page to submit feedback regarding quality of the response to the natural language search query; receive the feedback regarding quality of the response to the natural language search query; and provide the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
6. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: provide a header bar associated with the page; and customize the header bar to include the search interface, thereby allowing natural language search queries to be received and provided to the AI tool via the header bar.
7. The non-transitory, computer-readable storage medium of claim 1, further comprising instructions to: provide text on a page in the internal hierarchy which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
8. A method, comprising: receiving an indication designating that a page is publicly accessible and an indication designating a domain associated with the page; creating, upon receiving the indications designating that the page is publicly accessible and designating the domain, an external hierarchy of pages including an external top level page and an external lower level page, wherein the external lower level page is accessible from the external top level page; adding the page to the external hierarchy; publishing the page to the domain associated with the page; providing a search interface to the published page; receiving at the search interface a natural language search query as input; providing the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limiting the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the external hierarchy; and obtaining, from the AI tool, a response to the natural language search query.
10. The method of claim 8, further comprising: extracting a semantic meaning from the natural language search query; receiving information related to the semantic meaning from a pre-compiled database of information; augmenting the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and providing the augmented natural language search query to the AI tool.
11. The method of claim 8, further comprising: displaying, at the search interface, an example search query; wherein the example search query is based on information contained on pages in the external hierarchy; receiving a selection of the example search query from a user of the page; and providing the example search query to the AI tool.
12. The method of claim 8, further comprising: prompting a user of the page to submit feedback regarding quality of the response to the natural language search query; receiving the feedback regarding quality of the response to the natural language search query; and providing the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
14. The method of claim 8, further comprising: providing text on a page in the external hierarchy which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
15. A system comprising: at least one hardware processor; and at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the system to: receive an indication designating that a page is publicly accessible and an indication designating a domain associated with the page; create, upon receiving the indications designating that the page is publicly accessible and designating the domain, an external hierarchy of pages including an external top level page and an external lower level page, wherein the external lower level page is accessible from the external top level page; add the page to the external hierarchy; publish the page to the domain associated with the page; provide a search interface to the published page; receive at the search interface a natural language search query as input; provide the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limit the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the external hierarchy, and obtain, from the AI tool, a response to the natural language search query.
17. The system of claim 15, further comprising instructions causing the system to: extract a semantic meaning from the natural language search query; receive information related to the semantic meaning from a pre-compiled database of information; augment the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and provide the augmented natural language search query to the AI tool.
18. The system of claim 15, further comprising instructions causing the system to: prompt a user of the page to submit feedback regarding quality of the response to the natural language search query; receive the feedback regarding quality of the response to the natural language search query; and provide the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
19. The system of claim 15, further comprising instructions causing the system to: provide a header bar associated with the page; and customize the header bar to include the search interface, thereby allowing natural language search queries to be received and provided to the AI tool via the header bar.
20. The system of claim 15, further comprising instructions causing the system to: provide text on a page in the external hierarchy which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
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.
Claims 1, 8 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Parsana et al (US 10,095,788 B2) in view of Fitzpatrick (US 2020/0257437 A1) further in view of Hagler et al (US 2025/0028747 A1).
As per claim 1, Parsana teaches a non-transitory, computer-readable storage medium comprising instructions recorded thereon, wherein the instructions, when executed by at least one data processor of a system, cause the system to (Figs.1, 5):
provide a search interface associated with the hierarchy of webpages (see description of claim 17, e.g., discloses a user interface component that operates to receive search queries from end users and to return search results in response to the search queries and a deeplink hierarchy analysis component that operates to identify relevant deeplinks for the search results based on the deeplink hierarchies).
Parsana does not explicitly teach obtain a hierarchy of web pages including a top level web page and a lower level web page, wherein the hierarchy of web pages is publicly accessible.
However, Fitzpatrick teaches obtain a hierarchy of web pages including a top level web page and a lower level web page, wherein the hierarchy of web pages is publicly accessible (see paragraphs [0005]-[0006], disclose that a website is “a set of related webpages served from a single web domain,” that “All publicly accessible websites collectively constitute the World Wide Web,” and that “The URLs of the pages organize them into a hierarchy”).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the publicly accessible webpage hierarchy taught by Fitzpatrick to the webpage hierarchy/search system of Parsana in order to organize and search webpages of a publicly accessible website according to their known hierarchical relationship (Fitzpatrick).
Parsana and Fitzpatrick do not explicitly teach receive at the search interface a natural language search query as input; provide the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query; limit the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the hierarchy of webpages, thereby excluding the AI tool from accessing extraneous information and improving AI tool response times; and obtain, from the AI tool, a response to the natural language search query.
However, Hagler teaches receive at the search interface a natural language search query as input (paragraphs [0069]-[0070] disclose a “prompt input interface” through which the user enters textual input for the AI subsystem and expressly disclose that “the prompt can be a natural language input”); provide the natural language search query to an artificial intelligence (AI) tool, wherein the AI tool is configured to receive and process the natural language search query (paragraph [0075] discloses that the search system can use the prompt and optionally the query as input to the AI subsystem and paragraphs [0078] and [0081] further disclose processing the query/user prompt using an AI model, e.g., an LLM. The “AI subsystem” and “AI model, e.g., an LLM” correspond to the claimed “artificial intelligence (AI) tool,” and prompt/query provided as input to the AI subsystem corresponds to the claimed natural language search query being provided to and processed by the AI tool); limit the scope of information the AI tool uses to respond to the natural language search query to information contained on pages in the hierarchy of webpages, thereby excluding the AI tool from accessing extraneous information and improving AI tool response times (paragraph [0013] discloses that rather than processing the query against resources hosted by many different domains, “the AI system can limit the search space to the domain of the resource corresponding to the search result,” and further discloses that doing so “can greatly reduce the amount of computational resources used to process the prompt and the associated latency.” and paragraphs [0076]-[0079] further disclose selecting resources “hosted by the same domain,” wherein the set of resources may comprise “the various webpages of the same website,” and disclose that the AI subsystem can “search the various webpages of the same website” and select webpages satisfying the user’s intent. paragraph [0080] further explains that limiting the resources prevents selection of irrelevant/noneligible resources and reduces the time and computing resources required to generate the conversational response. Wherein the “limit the search space to the domain” corresponds to the claimed “limit the scope of information”; and “various webpages of the same website” correspond to the claimed “pages in the hierarchy of webpages”; limiting processing to same-domain/relevant resources rather than resources from many different domains corresponds to the claimed “excluding the AI tool from accessing extraneous information”; and Hagler’s reduction in “associated latency” and reduction in the time required to generate the conversational response correspond to the claimed “improving AI tool response times”); obtain, from the AI tool, a response to the natural language search query (paragraph [0076] discloses that the AI subsystem uses the user’s prompt/query to select resources relevant to the user’s intent. paragraph [0081] further discloses providing the query/user prompt to the AI model, and paragraphs [0082]-[0083] disclose that “the search system provides a conversational response,” wherein the commentary can include information responsive to the prompt. Wherein the “conversational response” corresponds to the claimed “response to the natural language search query” because the conversational response is generated from processing the user’s prompt/query and contains information responsive to that prompt/query).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Hagler to the combined teachings of Parsana and Fitzpatrick in order to enable the search system to receive a natural-language query, provide the query to an AI subsystem, restrict the AI subsystem to relevant webpages of the selected website, avoid processing extraneous information, reduce processing latency, and provide a conversational response responsive to the natural-language query (Hagler).
Regarding claims 8, 14, claims 8,14 are rejected for substantially the same reason as claim 1 above.
Claims 2-3, 9-10 and 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Parsana et al (US 10,095,788 B2) in view of Fitzpatrick (US 2020/0257437 A1), in view of Hagler et al (US 2025/0028747 A1) and further in view of Huang et al (US 2025/0111159 A1).
As per claim 2, Parsana, Fitzpatrick and Hagler do not explicitly teach augment the natural language search query using a retrieval-augmented generation (RAG) framework before providing the natural language search query to the AI tool,wherein the RAG framework fetches relevant information to the natural language search query from a pre-compiled database of information, and wherein information fetched by the RAG framework directs the AI tool towards generating a response to the natural language search query that is relevant; and provide the augmented natural language search query to the AI tool.
However, Huang teaches augment the natural language search query using a retrieval-augmented generation (RAG) framework before providing the natural language search query to the AI tool ([0015]-[0016], [0044]-[0049], Fig. 4, e.g., discloses a retrieval augmentation generator 120 including a search module 124 and prompt augmenter 126; receiving a prompt; converting the prompt to embeddings; performing a search based on the embeddings; and “augment[ing] the prompt with search results” before generating a response. The process shown in Fig. 4 expressly proceeds from “Receive prompt” → “Convert Prompt to Embedding(s)” → “Perform Search based on Embeddings” → “Augment Prompt with Search Results” → “Generate Response”), wherein the RAG framework fetches relevant information to the natural language search query from a pre-compiled database of information ([0015]-[0016], [0042]-[0047], e.g., discloses an embedding database containing embeddings generated from a corpus of data, searching the database based on an embedding generated for the received prompt, and retrieving relevant embeddings/search results. Wherein the “embedding database” corresponds to the claimed “pre-compiled database of information,” because the database is populated beforehand from a corpus of data and subsequently searched when the user prompt is received. Fig. 4 expressly shows “Receive Corpus of Data,” “Generate Embeddings for Chunks,” “Populate Database with Embeddings,” followed subsequently by receipt and processing of the user's prompt), wherein information fetched by the RAG framework directs the AI tool towards generating a response to the natural language search query that is relevant ([0047]-[0049], e.g., discloses augmenting the prompt with retrieved search results and then providing the augmented prompt to the language model to generate a response, thereby providing the language model with relevant contextual information for generating the response. The abstract likewise explains that the augmented prompt is input into a machine learning model and that retrieved embeddings provide context usable to improve the generated response),
provide the augmented natural language search query to the AI tool ([0047]-[0049], e.g., discloses that after the prompt is augmented using the search results, the augmented prompt is provided to a language model for generation of a response. Wherein the “augmented prompt” corresponds to the claimed “augmented natural language search query,” and “language model” corresponds to the claimed “AI tool”)
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Huang with the teachings of Parsana, Fitzpatrick and Hagler in order to augment a natural language query with relevant information retrieved from a previously populated database before providing the augmented query to a language model, thereby providing relevant contextual information for generating a more relevant response (Huang).
As per claim 3, Parsana, Fitzpatrick and Hagler do not explicitly teach extract a semantic meaning from the natural language search query; receive information related to the semantic meaning from a pre-compiled database of information; augment the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool; and provide the augmented natural language search query to the AI tool.
However, Huang teaches extract a semantic meaning from the natural language search query ([0016], [0045]-[0046], e.g., discloses converting a received prompt into one or more embeddings and using the embeddings to perform a similarity/semantic search). Wherein the embedding generated from the prompt corresponds to the claimed “semantic meaning” because the embedding represents the semantic content of the received prompt for use in identifying related stored information. Fig. 4 expressly identifies the operation “Convert Prompt to Embedding(s)”), receive information related to the semantic meaning from a pre-compiled database of information ([0045]-[0047], e.g., discloses performing a search of the embedding database based on the prompt embedding and retrieving search results having embeddings related to the prompt embedding. Wherein the embedding database corresponds to the claimed “pre-compiled database of information,” and search results identified based on similarity to the prompt embedding correspond to information “related to the semantic meaning”), augment the natural language search query with the information received from the pre-compiled database before providing the natural language search query to the AI tool ([0047]-[0048], e.g., discloses “augment[ing] the prompt with search results” retrieved using the embeddings before the prompt is supplied for response generation), provide the augmented natural language search query to the AI tool ([0048]-[0049], e.g., discloses providing the augmented prompt to the language model to generate the response. Wherein the “augmented prompt” corresponds to the claimed “augmented natural language search query,” and Huang's language model corresponds to the claimed “AI tool”).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Huang with the teachings of Parsana, Hagler, and Fitzpatrick in order to represent the semantic content of a user's natural language query using an embedding, retrieve semantically related information from a previously populated database, augment the query with the retrieved information, and provide the augmented query to the language model for response generation (Huang).
Regarding claims 9-10, 15-16, claims 9-10, 15-16 are rejected for substantially the same reason as claims 2-3 above.
Claims 4, 11 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Parsana et al (US 10,095,788 B2) in view of Fitzpatrick (US 2020/0257437 A1), in view of Hagler et al (US 2025/0028747 A1) and further in view of Berkowitz et al (US 2009/0094227 A1).
As per claim 4, Parsana, Fitzpatrick and Hagler do not explicitly teach display, at the search interface, an example search query; wherein the example search query is based on information contained on pages in the hierarchy of webpages;receive a selection of the example search query from a user of a page associated with the hierarchy of webpages; and provide the example search query to the AI tool.
However, Berkowitz teaches display, at the search interface, an example search query ([0040]-[0042], [0095]-[0102], [0114], e.g., discloses displaying a list of terms to a user, a Search Assistant interface that recommends words by listing them in a select box, and a screen that allows the user to select one or more Assist-suggested terms);
wherein the example search query is based on information contained on pages in the hierarchy of webpages ([0020]-[0023], [0130]-[0138], e.g., discloses an adaptive artificial-intelligence algorithm that extracts and rank-orders possible search terms from candidate vendor catalog pages, and further discloses extracting keywords/text from found pages and presenting the resulting terms to the user); receive a selection of the example search query from a user of a page associated with the hierarchy of webpages ([0031], [0114], [0117], [0192]-[0193], e.g., discloses that the user selects “finepoint” from the Search Assistant box; the Search Assistant presents a list of suggested terms from which the user selects one or more terms; and the selected terms are added to the current term expression).
provide the example search query to the AI tool ([0193], e.g., user selects from the words suggested by the Search Assistant via the artificial intelligence component).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Parsana, Fitzpatrick and Hagler with Berkowitz’s AI-generated suggested-query functionality such that an example search query derived from page content is displayed to the user, selected by the user, and provided for AI-based query processing, in order to assist the user in refining a search using contextually relevant terms automatically generated from webpage content (Berkowitz’s).
Regarding claims 11, 17, claims 11, 17 are rejected for substantially the same reason as claim 4 above.
Claims 5, 12 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Parsana et al (US 10,095,788 B2) in view of Fitzpatrick (US 2020/0257437 A1), in view of Hagler et al (US 2025/0028747 A1) and further in view of Kissane (US 2025/0190872 A1).
As per claim 5, Parsana, Fitzpatrick and Hagler do not explicitly teach prompt a user of a page associated with the hierarchy of webpages to submit feedback regarding quality of the response to the natural language search query, receive the feedback regarding quality of the response to the natural language search query; and provide the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback.
However, Kissane teaches prompt a user of a page associated with the hierarchy of webpages to submit feedback regarding quality of the response to the natural language search query ([0016]-[0017], [0020], [0024], e.g., discloses enabling users to provide explicit or implicit feedback regarding the “quality, desirability, appropriateness, accuracy, etc.” of generative AI-produced content included in a response received by the user), receive the feedback regarding quality of the response to the natural language search query ([0024], [0034], Fig. 3B, e.g., discloses receiving feedback associated with AI-generated content/result and a response identifier identifying the response to which the feedback pertains and Fig. 3B expressly shows “Receive user feedback and associated response identifier”), provide the feedback to the AI tool, wherein the AI tool is configured to process natural language search queries differently in response to the feedback ([0024]-[0031], [0034], e.g., discloses sending feedback regarding an AI-generated result to the generative AI system, using that feedback to update a reward model, and subsequently using the reward model to fine-tune the private language model and Fig. 2B expressly illustrates “Feedback” from the user being supplied to a “Private Reward Model,” which in turn “Fine Tune[s]” the private LLM).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the feedback-based AI improvement teachings of Kissane with the teachings of Parsana, Fitzpatrick and Hagler in order to solicit and receive user feedback concerning the quality of AI-generated responses and use that feedback to fine-tune the AI model, thereby improving the model's processing and subsequently generated responses (Kissane).
Regarding claims 12, 18, claims 12, 18 are rejected for substantially the same reason as claim 5 above.
Claims 6 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Parsana et al (US 10,095,788 B2) in view of Fitzpatrick (US 2020/0257437 A1), in view of Hagler et al (US 2025/0028747 A1) and further in view of Stellhorn et al (US 2009/0157675 A1).
As per claim 6, Hagler teaches thereby allowing natural language search queries to be received and provided to the AI tool via the header bar (paragraphs [0069]-[0070], [0078]-[0081, Hagler).
Parsana, Fitzpatrick and Hagler do not explicitly teach provide a header bar associated with a page in the hierarchy of webpages and customize the header bar to include the search interface.However, Stellhorn teaches provide a header bar associated with a page in the hierarchy of webpages and customize the header bar to include the search interface (paragraphs [0044]-[0045], Figs. 4-5, e.g., discloses a toolbar 415 associated with a displayed webpage/interface, wherein the toolbar may be customized by adding or removing selectable interface elements, and further discloses a search box 510 through which a user may perform a search, Wherein the toolbar 415 corresponds to the claimed header bar, and the disclosed customizable toolbar together with the disclosed search box 510 teaches or suggests customize the header bar to include the search interface).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the customizable toolbar/header interface of Stellhorn to include the natural-language AI search interface taught by Hagler, thereby allowing natural language search queries to be received and provided to the AI tool via the header bar, in order to provide convenient and customizable access to AI-assisted search functionality directly from the webpage interface (Stellhorn).
Regarding claim 19, claim 19 is rejected for substantially the same reason as claim 6 above.
Claims 7, 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Parsana et al (US 10,095,788 B2) in view of Fitzpatrick (US 2020/0257437 A1), in view of Hagler et al (US 2025/0028747 A1) and further in view of Li et al (US 11,429,779 B2).
As per claim 7, Parsana, Fitzpatrick and Hagler do not explicitly teach provide text on a page associated with the hierarchy of webpages which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text.
However, Li teaches provide text on a page associated with the hierarchy of webpages which is highlighted by a user to the AI tool (col. 6, lines 40–65; col. 7, lines 1–18, e.g., discloses a graphical user interface allowing a user to request and receive suggested replacement text segments for a selected text segment, wherein the user may use an input/output device such as a mouse to select a portion of the contents pane, and a UI element is displayed for invoking suggested replacement text segments), wherein the AI tool is configured to receive and process the highlighted text (col. 5, lines 28–40; col. 7, line 63–col. 8, line 5, e.g., discloses a rephrasing service 114 that examines a selected text segment, remaining content of the document, context, and non-linguistic features to intelligently suggest replacement text segment options, wherein the rephrasing service may be provided by one or more rephrasing ML models; and once a text segment has been selected, the application may run a local rephrasing engine or send a request to the rephrasing service for suggested replacement text segments), wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text (col. 7, lines 5–18; col. 8, lines 30–39 and 47–60, e.g., discloses that a user selects the text and invokes a UI element requesting suggested replacement text segments; the menu includes an option for replacing the selected text segment with the suggested replacement text segment, which may result in permanent replacement of the selected text segment and after selecting a suggested replacement text segment, the user may permanently replace the selected text segment with the selected suggestion), wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text (col. 6, lines 40–65; col. 7, lines 20–39 and 63–67; col. 8, lines 1–10, e.g., discloses graphical user interfaces allowing a user to request and receive suggested replacement text segments for a selected text segment; a menu option for invoking display of suggested replacement text segments; a rewrite pane providing suggested rewrites for the selected text segment; and, after receiving the request, providing a list of suggested replacement text segments for display to the user).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the webpage-based AI system of Parsana, Fitzpatrick and Hagler with the intelligent rephrasing functionality of Li so as to provide text on a page associated with the hierarchy of webpages which is highlighted by a user to the AI tool, wherein the AI tool is configured to receive and process the highlighted text, wherein the AI tool is configured to, upon receiving an improvement request from the user, replace the highlighted text with an improved version of the text, and wherein the AI tool is configured to, upon receiving a suggestion request from the user, provide a suggestion for an improved version of the text, in order to enable a user to select displayed text, obtain intelligent replacement suggestions generated by a machine-learning rephrasing system, and replace the selected text with an improved version.
Regarding claims 13, 20, claims 13, 20 are rejected for substantially the same reason as claim 7 above.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to
applicant's disclosure.
Tyrrell et al US 20260141466 A1 discloses Computing System And Method For Controlling A Construction Management Software Application Via Natural-Language Requests.
Chen et al US 20260100921 A1 discloses ARTIFICIAL INTELLIGENCE (AI)-BASED USER INTERFACES.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Mohammad A Sana whose telephone number is (571)270-1753. The examiner can normally be reached Monday-Friday 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, Sanjiv Shah can be reached at 5712724098. 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.
/Mohammad A Sana/Primary Examiner, Art Unit 2166
