DETAILED ACTION
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/21/2026 was filed after the mailing date of the Non-Final Rejection on 06/02/2026. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Amendment
This communication is responsive to the applicant’s amendment dated 06/10/2026.
Response to Arguments
Applicant's arguments filed 06/10/2026. have been fully considered but they are not persuasive.
Regarding the independent claims 1 and 11, the Applicant’s Representative argues, “Specifically, none of the cited references disclose or suggest "determining a similarity score for each response by comparing the response with at least the context for the corresponding sub-query.” (Remarks: pg. 7) Specifically, they argue that “ordering results based on relevance scores of corresponding micro- queries (as taught by Tumuluri) is not the same as determining similarity scores for the responses themselves, let alone determining a similarity score for each response by comparing the response with at least the context for the corresponding sub-query (as recited in claim 1).” “Moreover, while Applicant's claim 1 determines a similarity score for each response, Tumuluri describes relevance scores for the microqueries - not the responses - and teaches that the results are ordered based on the relevance scores for the microqueries.” (Remarks: pg. 8) The Examiner respectfully disagrees.
Considering the prior art as a whole, Tumuluri teaches calculating relevance scores of micro-queries results. (par. 0035; ‘The outputted results may be ordered, for example, based on the relevance scores of the micro-queries results with respect to soft-query.’) There is a context tied to the micro-queries stemming from the soft-query. (par. 0038; ‘The soft-query may be divided into multiple micro-queries based on the context, intent, modality entities, objects and also previous responses in the same conversation.’). The relevance/relatedness of the results to the micro-queries are a result of comparing each result/response with the context for the micro-queries. Therefore, the arguments are not persuasive. The combination of Tumuluri in view of Ramachandra Iyer teaches the claims as a whole.
Claim Rejections - 35 USC § 103
Claim(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Tumuluri (US 20220114463 A1) in view of Ramachandra Iyer et al. (US 10885119 B2).
Regarding claims 1 and 11, Tumuluri teaches:
“A method for assisting a user of an online resource, the method performed by one or more processors of a computing system associated with the online resource” (par. 0022; ‘An embodiment describes a method of soft-query population for a virtual assistant tool. A user provides (210) a set of inputs. These inputs may be provided by the user through a multi-modal interface based computer implemented tool.’) and comprising:
“receiving, from the user over a communications network coupled to the computing system, a query including a plurality of sub-queries” (par. 0028; ‘For example, the user requests (i.e., queries) may include one, two, or more input modalities obtained from different sensors such as a hand gesture and speech.’; par. 0033; ‘The method 300 includes generating 360 micro-queries. The micro-queries may be specific to individual applications or data stores to access and retrieve the relevant information.’);
“determining a context for each of the sub-queries” (par. 0063; ‘One or more modality-event-context patterns and embeddings may be determined for a micro-query.’);
“obtaining responses to the sub-queries from a plurality of selected agents” (par. 0033; ‘Thus, the soft-query in the invention is divided into a set of micro-queries, which are used to retrieve the information from multiple sources.’; par. 0035; ‘The method 300 includes executing 370 the micro-queries by the soft-agent on processor 220 of FIG. 2 and received micro-query results at least in part on the multi-modality query.’);
“determining a similarity score for each response by comparing the response with at least the context for the corresponding sub-query” (par. 0035; ‘The outputted results may be ordered, for example, based on the relevance scores of the micro-queries results with respect to soft-query.’; par. 0038; ‘The relevance score is based on the closeness between the generated micro-query and the intended outcome, which may be determined based on the learning patterns discovered using ML algorithms on historical data and domain-specific and/or application details.’); and
“summarizing the responses [[based at least in part on the similarity scores]]” (par. 0054; ‘The results dashboard 642 may be configured to summarize and annotate the results. For example, the text results may be summarized using text summarization techniques and send an email to a specified user.’); and
“generating an answer to the query [[by combining the response summaries based at least in part on an alignment between the response summaries and their corresponding sub-queries]]” (par. 0060; ‘The method 700 includes executing 710 the selected soft-query against the respective data store and the respective application to generate a response.’).
However, Tumuluri does not expressly teach:
“determining a context for each of the sub-queries”;
“summarizing the responses based at least in part on the similarity scores”; and
“generating an answer to the query by combining the response summaries based at least in part on an alignment between the response summaries and their corresponding sub-queries” (emphasis added).
Ramachandra Iyer teaches:
“determining a context for each of the sub-queries” (col. 7, lines 10-14; ‘Each of the one or more sub-queries 106 may belong to one or more domains such as banking, insurance, healthcare, telecom, education, and the like.’);
“summarizing the responses based at least in part on the similarity scores” (col. 11, lines 18-24; ‘In an embodiment, the summarized content generation module 215 may be configured to summarize the one or more sub-queries 106 based on context of the one or more sub-queries 106 and based on historical conversation data associated with the one or more sub-queries 106.’); and
“generating an answer to the query by combining the response summaries based at least in part on an alignment between the response summaries and their corresponding sub-queries” (col. 11, lines 18-24; ‘In an embodiment, the summarized content generation module 215 may be configured to summarize the one or more sub-queries 106 based on context of the one or more sub-queries 106 and based on historical conversation data associated with the one or more sub-queries 106.’; col. 12, lines 35-41; ‘In an embodiment, the collation module 219 may be configured to collate the one or more responses 110 in the output frame and provide the one or more responses 110 to the user 103.’).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Tumuluri’s micro-query responses and their respective scores (i.e., relevance scores based on context) by incorporating Ramachandra Iyer’s sub-query and summarization methods (e.g., collating the responses to the sub-queries) in order to summarize responses based on similarity scores and generate an answer to the query by combining response summaries. The modification would determine most relevant responses to user queries. (Ramachandra Iyer: col. 1, lines 58-62)
Regarding claims 2 (dep. on claim 1) and 12 (dep. on claim 11), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“wherein the response summaries are combined without changing the contexts for any of the sub-queries” (T: par. 0054; ‘The results dashboard 642 may be configured to summarize and annotate the results. For example, the text results may be summarized using text summarization techniques and send an email to a specified user.’).
Regarding claims 3 (dep. on claim 1) and 13 (dep. on claim 11), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“wherein the alignment is based at least in part on the similarity scores” (T: par. 0038; ‘The relevance score is based on the closeness between the generated micro-query and the intended outcome, which may be determined based on the learning patterns discovered using ML algorithms on historical data and domain-specific and/or application details.’).
Regarding claims 4 (dep. on claim 1) and 14 (dep. on claim 11), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“wherein the similarity score for a respective response is further based on a comparison between the respective response and the corresponding sub-query” (T: par. 0038; ‘The relevance score is based on the closeness between the generated micro-query and the intended outcome, which may be determined based on the learning patterns discovered using ML algorithms on historical data and domain-specific and/or application details.’).
Regarding claims 5 (dep. on claim 1) and 15 (dep. on claim 11), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“wherein the query is received during a conversation between the user and an automated assistant associated with the online resource, and the context is based at least in part on one or more previous portions of the conversation” (T: par. 0033; ‘In the case of multi-modality conversational queries, the system may retrieve information from one or more data sources, and a query may be generated for each such data source.’).
Regarding claims 6 (dep. on claim 5) and 16 (dep. on claim 15), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“transmitting the answer to the user over the communications network” (T: par. 0021; ‘A cloud service provider 122 and mobile devices 124 provides data store and transfer services to other devices through internet 108.’); and
“presenting the answer to the user as part of the conversation between the automated assistant and the user” (T: par. 0034; ‘Generating 360 the micro-queries may include considering responses from a previous multi-modality query in the same conversation, for example a lot of previous responses with multi-modality objects, entities, intents, context, or any combination thereof.’; par. 0035; ‘The method 300 includes outputting 380 the results. Outputting 380 the results may include providing text output, speech output, visual output, or any combination thereof, of the results.’).
Regarding claims 7 (dep. on claim 6) and 17 (dep. on claim 16), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“obtaining a confidence score for each of the responses” (T: par. 0038; ‘When the results are received, the results may be sorted, for example, based on the relevance scores of the micro-queries results with respect to soft-query). The micro-query score is a relevance score.’); and
“determining a confidence score for the answer by combining the confidence scores for all of the responses” (T: par. 0038; ‘When the results are received, the results may be sorted, for example, based on the relevance scores of the micro-queries results with respect to soft-query). The micro-query score is a relevance score.’).
Regarding claims 8 (dep. on claim 7) and 18 (dep. on claim 17), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“presenting the confidence score to the user as part of the conversation between the automated assistant and the user” (T: par. 0054; ‘The results dashboard 642 may include a ranking aggregator (not shown) that is configured to consolidate the results (e.g., for presentation to a user) and assign scores as per the relevance to the soft-query or adjusts scores if default scores are provided.’).
Regarding claims 9 (dep. on claim 1) and 19 (dep. on claim 11), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“wherein the context includes one or more of tax preparation, user account maintenance, invoice preparation, bill paying, fraud prevention, or assistance with a product or service associated with the online resource” (T: par. 0001; ‘Enterprises have multiple applications such as customer relationship management (CRM), learning management systems (LMS), human-resource (HR), email and financial applications, and stored data in a variety of data stores. Each application permits the user to access the data and application services and respond to user requests or queries.’).
Regarding claims 10 (dep. on claim 1) and 20 (dep. on claim 11), the combination of Tumuluri (T) in view of Ramachandra Iyer further teaches:
“wherein the context includes a browsing history of the user within a user assistance page or web site associated with the online resource” (T: par. 0038; ‘The relevance score is based on the closeness between the generated micro-query and the intended outcome, which may be determined based on the learning patterns discovered using ML algorithms on historical data and domain-specific and/or application details.’).
Conclusion
THIS ACTION IS MADE FINAL. 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 MARK VILLENA whose telephone number is (571)270-3191. The examiner can normally be reached 10 am - 6pm EST Monday through Friday.
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, Richemond Dorvil can be reached at (571) 272-7602. 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.
MARK . VILLENA
Examiner
Art Unit 2658
/MARK VILLENA/Examiner, Art Unit 2658
Prosecution Insights