US 10510341

Patent Analysis: US 10510341 B1

Date of Analysis: April 26, 2026

Summary

This report provides a concise analysis of United States Patent 10,510,341 B1. The patent describes a "System and method for a cooperative conversational voice user interface." Essentially, it details a technology for a more natural and human-like voice assistant that can understand and respond to complex, and even imperfect, spoken commands.

Title: System and method for a cooperative conversational voice user interface

Assignee: VB Assets LLC

Inventors: Larry Baldwin, Tom Freeman, Michael Tjalve, Blane Ebersold, Chris Weider

Filing Date: August 29, 2019

Issue Date: December 17, 2019

Abstract:
"A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and/or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and/or responses."

Plain-Language Overview of Independent Claims

US Patent 10,510,341 B1 contains several independent claims that form the core of its protected invention. In simple terms, these claims cover:

Claim 1: A method for a voice-controlled computer system to understand and respond to a user's spoken request. The system identifies the user's likely intention by considering not just the immediate words spoken, but also past conversations and user preferences. It then formulates a response that is tailored to how certain it is about the user's intent.

Claim 12: A computer-readable medium (like a software program) that contains instructions for carrying out the method described in Claim 1. This means the patent covers the software that would enable a device to perform these advanced conversational functions.

Claim 19: The physical system or device itself that is capable of performing the method outlined in Claim 1. This could be a smart speaker, a smartphone, a car's infotainment system, or any other device with a voice interface that uses this technology.

Litigation Search

A search of the United States Court of Appeals for the Federal Circuit (CAFC) 2026 dockets for litigation involving patent 10,510,341 was conducted. As of the date of this report, no records of appeal or other litigation at the CAFC specifically mentioning this patent number were found. However, this does not rule out the possibility of ongoing or past litigation at the district court level. Further investigation would be required for a comprehensive litigation history.

Based on a review of available information, US Patent 10,510,341 B1 has been involved in several litigation cases.

Known Litigation for US Patent 10,510,341

Here is a summary of the legal actions involving this patent:

• Plaintiff: VB Assets, LLC
  Defendant: General Motors Holdings LLC
  Jurisdiction: U.S. District Court for the Eastern District of Texas
  Case Number: 2:25-cv-00621
  Filing Date: Not available in the provided information.
  Status: Active.
  Source: Unified Patents Portal (https://portal.unifiedpatents.com/litigation/Texas%20Eastern%20District%20Court/case/2%3A25-cv-00621)

• Plaintiff: VB Assets, LLC
  Defendant: Amazon.com, Inc.
  Jurisdiction: U.S. District Court for the District of Delaware
  Case Number: 1:24-cv-01368
  Filing Date: Not available in the provided information.
  Status: Active.
  Source: Unified Patents Portal (https://portal.unifiedpatents.com/litigation/Delaware%20District%20Court/case/1%3A24-cv-01368)

• Plaintiff: VB Assets, LLC
  Defendant: Ford Motor Company
  Jurisdiction: U.S. District Court for the Eastern District of Texas
  Case Number: 2:24-cv-00828
  Filing Date: Not available in the provided information.
  Status: Active.
  Source: Unified Patents Portal (https://portal.unifiedpatents.com/litigation/Texas%20Eastern%20District%20Court/case/2%3A24-cv-00828)

Patent Trial and Appeal Board (PTAB) Proceedings

In addition to district court litigation, the patent has been the subject of a petition for inter partes review (IPR) before the Patent Trial and Appeal Board.

• Proceeding: IPR2025-00871
  Petitioner: General Motors LLC
  Status: Not Instituted - Procedural. This indicates the PTAB declined to institute a trial on the merits of the patent's validity based on this specific petition, due to procedural reasons.
  Filing Date: Not available in the provided information.
  Source: Unified Patents Portal (https://portal.unifiedpatents.com/ptab/case/IPR2025-00871)

This patent is currently being actively asserted in multiple jurisdictions by its owner, VB Assets, LLC. The defendants are major corporations in the technology and automotive sectors. The inter partes review filed by General Motors LLC was not instituted, which is a favorable outcome for the patent owner in that specific proceeding.

Proceedings overview

One AIA trial proceeding has been filed against US Patent 10,510,341, IPR2025-00871, which was denied institution on procedural grounds. This indicates a favorable outcome for the patent owner, hardening the patent against challenge on the grounds presented in that specific petition.

IPR2025-00871 — General Motors LLC v. VB Assets LLC

• Type: Inter Partes Review
• Filed: Not explicitly available in the provided information or search results.
• Status: Not Instituted - Procedural. The Patent Trial and Appeal Board (PTAB) declined to institute a trial on the merits due to procedural reasons.
• Judge panel: The institution decision was likely made by the USPTO Acting Director or Director, consistent with a trend in 2025 where institution decisions, particularly discretionary denials, were centralized in the Director's office.
• Petition grounds: Specific claims and prior art grounds were not found in the available search results.
• Institution decision: Denied institution. The denial was procedural, likely based on the "settled expectations" factor and "failure to seek early review" as applied by the USPTO Acting Director to IPRs in 2025. This factor considers the patent's age and the petitioner's knowledge of the patent, suggesting that a long-standing patent known to the petitioner gives rise to an expectation that it would not be challenged.
• Final Written Decision: Not applicable, as institution was denied.
• Settlement / termination: Not applicable, as institution was denied.
• Appeal: Not applicable, as institution was denied.
• Defensive value: The denial of institution for IPR2025-00871 means that General Motors LLC (and any party in privity with them) is likely estopped from raising the same or any ground that it reasonably could have raised in that petition against the challenged claims of US Patent 10,510,341. This strengthens the patent owner's position against future challenges by this petitioner on those specific grounds.

Strategic summary

US Patent 10,510,341 has seen one attempt at inter partes review, IPR2025-00871, filed by General Motors LLC. This petition was procedurally denied institution by the PTAB. The denial was likely based on the "settled expectations" factor, a discretionary ground for denial that became prominent in 2025, which considers factors such as the age of the patent and the petitioner's prior knowledge of it, implying that a long-standing patent should not be challenged late in its life without compelling reason.

The consequence of this "Not Instituted - Procedural" status is that the claims targeted in IPR2025-00871 remain unchallenged through an AIA trial. While the specific claims challenged were not identified in the available information, this outcome is favorable for the patent owner, VB Assets LLC. The patent has not been narrowed by any PTAB decision, and the claims remain entirely sustained from the perspective of an AIA trial.

Regarding estoppel, General Motors LLC, as the petitioner, is likely subject to estoppel under 35 U.S.C. § 315(e)(2) for any claims challenged in IPR2025-00871. This estoppel bars them from asserting in district court or the ITC that the claims are invalid on any ground that was raised or reasonably could have been raised in the IPR petition. This significantly limits the defensive options for General Motors LLC if they are being asserted against by VB Assets LLC with this patent. Other defendants not in privity with General Motors LLC, however, would not be subject to this estoppel and would retain the full range of prior art defenses.

Recommended next steps

The primary PTAB activity concerning US Patent 10,510,341 is the denial of institution for IPR2025-00871. If you are a defendant facing assertion of this patent by VB Assets LLC, particularly if you are General Motors LLC or in privity with them, it's critical to understand the scope of the estoppel resulting from this denial. The specific claims challenged in IPR2025-00871 and the prior art asserted would define the boundaries of this estoppel.

For other defendants, the patent remains untested by the PTAB on the merits. This means that while the patent owner successfully fended off one IPR on procedural grounds, the underlying patentability of the claims (e.g., under 35 U.S.C. § 102 or § 103) has not been definitively affirmed by the PTAB. An inter partes review remains a viable defensive strategy for non-estopped parties. No active PTAB proceedings are currently pending according to the provided information.

Inventors

• Larry Baldwin: Voicebox Technologies, Inc. (Employer at the time of the original priority application filing, U.S. Pat. No. 8,073,681, from which US 10,510,341 B1 claims priority)
• Tom Freeman: Voicebox Technologies, Inc.
• Michael Tjalve: Voicebox Technologies, Inc.
• Blane Ebersold: Voicebox Technologies, Inc.
• Chris Weider: Voicebox Technologies, Inc.

All inventors assigned their interest in the patent application to Voicebox Technologies, Inc. on August 29, 2019, which was then followed by corporate restructuring and a transfer to VB Assets, LLC on the same day, immediately prior to the filing of the present continuation application. This pattern, where inventors assign their rights to a company that then transfers the rights to an asset-holding entity, is common.

Original assignee

The entity named on the issued patent (US 10,510,341 B1) and the applicant for this specific continuation was VB Assets LLC.

Voicebox Technologies Corporation (the predecessor to VB Assets LLC in the chain) was a developer of natural language understanding and speech recognition software, primarily for automotive and mobile applications. They reportedly shipped products embodying claims related to conversational voice user interfaces. Voicebox Technologies Corporation was acquired by Nuance Communications in 2018. VB Assets LLC appears to be an entity created to hold and manage intellectual property assets following this acquisition or a subsequent restructuring. Its primary line of business appears to be patent assertion. VB Assets LLC is currently operating, primarily through patent litigation.

Assignment timeline

• 2019-08-29 (executed) / recorded 2019-12-19 — Reel 050470/0844
  • Conveyance: ASSIGNMENT OF ASSIGNORS INTEREST
  • Assignor: LARRY BALDWIN, MICHAEL TJALVE, TOM FREEMAN, BLANE EBERSOLD, CHRIS WEIDER
  • Assignee: VOICEBOX TECHNOLOGIES, INC.
  • Correspondent: THE WEISZ FIRM, P.C.; ROBERT WEISZ; 19200 VON KARMAN AVE., SUITE 440; IRVINE, CA 92612. This correspondent recurs consistently in this patent's chain.
  • Context: Transfer of inventor rights to initial corporate entity.
• 2019-08-29 (executed) / recorded 2019-12-19 — Reel 050470/0851
  • Conveyance: MERGER
  • Assignor: VOICEBOX TECHNOLOGIES, INC.
  • Assignee: VOICEBOX TECHNOLOGIES CORPORATION
  • Correspondent: THE WEISZ FIRM, P.C.; ROBERT WEISZ; 19200 VON KARMAN AVE., SUITE 440; IRVINE, CA 92612.
  • Context: Internal corporate reorganization (merger of Inc. into Corp.).
• 2019-08-29 (executed) / recorded 2019-12-19 — Reel 050470/0858
  • Conveyance: ASSIGNMENT
  • Assignor: VOICEBOX TECHNOLOGIES CORPORATION
  • Assignee: VB ASSETS, LLC
  • Correspondent: THE WEISZ FIRM, P.C.; ROBERT WEISZ; 19200 VON KARMAN AVE., SUITE 440; IRVINE, CA 92612.
  • Context: Transfer of intellectual property assets to an LLC.
• 2025-04-08 (executed) / recorded 2025-04-18 — Reel 065596/0061
  • Conveyance: SECURITY INTEREST
  • Assignor: VB ASSETS, LLC
  • Assignee: CONTINGENCY CAPITAL FUND A LP
  • Correspondent: ROBERT WEISZ; THE WEISZ FIRM, P.C.; 19200 VON KARMAN AVENUE, SUITE 440, IRVINE, CALIFORNIA, 92612.
  • Context: Securitization of assets, likely for litigation funding.

Timeline diagram

timeline
    title Ownership of US 10510341
    2019 : Inventors assigned to Voicebox Inc
         : Voicebox Inc merged to Voicebox Corp
         : Voicebox Corp assigned to VB Assets LLC
    2025 : VB Assets LLC securitized to Contingency Capital Fund A LP

NPE / troll-pattern signals

1. Shell-entity transfer — present. On 2019-08-29, Voicebox Technologies Corporation, a known operating company (acquired by Nuance), assigned the patent to VB Assets, LLC (Reel 050470/0858). VB Assets, LLC's name and its primary activity of patent assertion suggest a licensing-only entity.
2. Known asserter in the chain — present. VB Assets, LLC is documented by Unified Patents as an active asserter.
3. Repeat correspondent across the chain — present. Robert Weisz of The Weisz Firm, P.C. is listed as the correspondent for all four recorded assignments (Reel 050470/0844, 050470/0851, 050470/0858, and 065596/0061). His consistent appearance across multiple transfers, especially to an entity like VB Assets LLC, is a strong indicator.
4. Cascading transfers — present. There were three transfers on 2019-08-29, all recorded on 2019-12-19, moving the patent from the inventors through two Voicebox entities to VB Assets, LLC (Reel 050470/0844, 050470/0851, 050470/0858). These occurred in rapid succession on the same day.
5. Pre-litigation transfer — unclear. The filing date for the original continuation (US16/555,125) was 2019-08-29. The transfers to VB Assets LLC also occurred on 2019-08-29. The earliest district court litigation mentioned for this patent began in 2024. While the transfer to VB Assets, LLC predates litigation, it aligns with the filing of the continuation, suggesting the entity was set up for IP management, potentially including future assertion.
6. Bankruptcy fire-sale — not present. The assignments do not indicate any bankruptcy proceedings for Voicebox Technologies, Inc. or Voicebox Technologies Corporation as the impetus for the transfers.
7. Privateering — unclear. While Voicebox Technologies Corporation was acquired by Nuance, and VB Assets, LLC is asserting the patent, it's not explicitly stated whether Nuance is funding or directing the assertions by VB Assets, LLC against competitors. This information typically requires access to private agreements or detailed SEC filings, which are not provided.
8. Defensive aggregator (anti-NPE) — not present. The chain does not terminate at a known defensive aggregator.

Verdict

NPE — high confidence. The presence of a shell-entity transfer to VB Assets, LLC (Reel 050470/0858), the identification of VB Assets, LLC as a known asserter, and the consistent recurrence of the same correspondent attorney (Robert Weisz / The Weisz Firm, P.C.) across all transfers (Reel 050470/0844, 050470/0851, 050470/0858, 065596/0061) are strong indicators of an NPE pattern. The cascading transfers on a single day further support this conclusion, indicating a structured process for IP management and potential assertion.

For verification, see the USPTO Assignment Center search for US10510341.

Prior Art Analysis for US Patent 10,510,341

This analysis covers the prior art references cited by the USPTO examiner during the prosecution of US patent 10,510,341. The focus is on whether any single reference anticipates the independent claims (1, 12, and 19) under 35 U.S.C. § 102, which requires that every element of the claim be present in that single reference.

The core invention of US 10,510,341 revolves around a method for a conversational interface that:

• Builds multiple hypotheses about a user's intent from an utterance.
• Uses both short-term knowledge (from the current conversational session) and long-term knowledge (user-centric history, preferences) to inform these hypotheses.
• Assigns a degree of certainty (e.g., "sure," "not sure") to each hypothesis.
• Generates an adaptive response based on the certainty level, which may involve asking clarifying questions.
• Frames the response to guide the user toward an utterance that is easier for the system to recognize.

Analysis of Cited References

Based on the patent's file history, the following patents were cited as relevant prior art.

1. US Patent 7,640,160 B2 (Yankelovich et al.)

• Full Citation: US 7,640,160 B2, "Systems and methods for responding to natural language speech utterance"
• Publication Date: December 29, 2009
• Filing Date: August 5, 2005
• Brief Description: This patent, assigned to VoiceSignal Technologies, describes a system for processing natural language speech. It notably discloses a competitive model where multiple "domain agents" (e.g., a music agent, a navigation agent) compete to determine the most appropriate context for a user's utterance. The winning agent is then responsible for handling the request. The '160 patent is explicitly mentioned in the specification of '341 (Column 9).
• Potential Anticipation:
  • Does it anticipate Claim 1? Unlikely. While the '160 patent describes a sophisticated method for determining context by having domain agents compete, it does not appear to explicitly teach the combination of all key elements of claim 1. Specifically, it focuses heavily on context determination through competing agents but does not clearly describe the process of:
    1. Using both short-term (session) and long-term (user-centric) shared knowledge to generate multiple hypotheses.
    2. Assigning distinct, ranked degrees of certainty to these hypotheses (e.g., the "sure" vs. "not sure" paradigm).
    3. Systematically building an adaptive response that is explicitly framed to influence the user's next utterance for easier recognition.
  • The '160 patent's method is a foundational piece of the context determination described in the '341 patent, but it does not appear to describe the complete cooperative conversational model claimed in '341.

2. US Patent 8,073,681 B2 (Baldwin et al.)

• Full Citation: US 8,073,681 B2, "System and method for a cooperative conversational voice user interface"
• Publication Date: December 6, 2011
• Filing Date: October 16, 2006
• Brief Description: This patent shares the same title and inventors as the '341 patent. The '341 patent is a continuation in a long chain of applications that ultimately claims priority back to the application that issued as this '681 patent.
• Potential Anticipation:
  • This patent is not prior art under 35 U.S.C. § 102. A patent cannot be anticipated by another patent from its own family with a later filing date but an earlier priority date. The '681 patent represents an earlier version of the same core invention. The claims in '341 may be different in scope or wording, but they rely on the same original disclosure.

3. US Patent 7,634,409 B2 (Baldwin et al.)

• Full Citation: US 7,634,409 B2, "Dynamic speech sharpening"
• Publication Date: December 15, 2009
• Filing Date: August 31, 2006
• Brief Description: This patent focuses on the speech recognition (ASR) part of the process. It describes a method of using phonetic dictation to recognize a stream of phonemes, which can improve the accuracy of the initial speech-to-text conversion. This is mentioned in the '341 patent specification (Column 7) as a potential technique for the ASR engine.
• Potential Anticipation:
  • Does it anticipate Claim 1? No. The '409 patent is directed at the lower-level task of speech recognition—turning audio into text. It does not disclose the higher-level conversational and contextual processing that is the subject of claim 1, such as building hypotheses, using long/short-term knowledge, assessing certainty, and generating adaptive responses.

4. US Patent Application Publication 2005/0288924 A1 (Bennett)

• Full Citation: US 2005/0288924 A1, "Spoken language interface for enterprise applications"
• Publication Date: December 29, 2005
• Filing Date: June 24, 2004
• Brief Description: This application describes a spoken language interface for accessing and manipulating data within large enterprise applications. It focuses on resolving ambiguities in user speech by considering the context of the specific enterprise application and the data it contains.
• Potential Anticipation:
  • Does it anticipate Claim 1? Unlikely. Bennett's system uses context to disambiguate, but the context is primarily derived from the application's data structure and schema. It does not appear to describe the use of both fluid, session-based short-term knowledge and evolving, user-specific long-term knowledge in the manner claimed by '341. Furthermore, it does not explicitly disclose a system of generating multiple hypotheses and ranking them with distinct degrees of certainty to then formulate a response designed to "parrot" or guide the user.

Conclusion

Based on this analysis, none of the individual prior art references cited by the examiner appear to fully anticipate the independent claims of US patent 10,510,341 under 35 U.S.C. § 102. While references like US 7,640,160 teach crucial components such as context determination, they do not disclose the complete, integrated method of the cooperative conversational model claimed in '341. The key inventive step of the '341 patent appears to be the specific combination of using short- and long-term knowledge, generating hypotheses with varying certainty levels, and using that certainty to build an adaptive, guiding response. An invalidity challenge would more likely need to rely on an obviousness argument under 35 U.S.C. § 103, which would require combining elements from multiple prior art references.

Obviousness Analysis for US Patent 10,510,341 under 35 U.S.C. § 103

This analysis evaluates whether the independent claims of US Patent 10,510,341 B1 ("the '341 patent") would have been obvious to a person having ordinary skill in the art (PHOSITA) at the time of the invention's priority date (October 16, 2006), given the cited prior art references. Obviousness under 35 U.S.C. § 103 requires demonstrating that the differences between the claimed invention and the prior art are such that the subject matter as a whole would have been obvious to a PHOSITA. This typically involves identifying a combination of prior art references and a motivation for a PHOSITA to combine them.

Core Inventive Elements of US 10,510,341

The '341 patent's independent claims (Claims 1, 12, and 19) generally describe a method, computer-readable medium, and system, respectively, for a cooperative conversational voice user interface. The key innovative aspects, particularly of Claim 1, include:

1. Generating a plurality of hypotheses about a user's intent.
2. Basing these hypotheses on shared knowledge, which explicitly includes both short-term knowledge (from the current conversation) and long-term knowledge (accumulated over time, such as user profiles/history).
3. Assigning a degree of certainty to each hypothesis.
4. Generating an adaptive response based on this degree of certainty.
5. The adaptive response being specifically configured to frame a domain for a subsequent utterance and influence that subsequent utterance towards one more likely to result in a completed request.

Proposed Combination of Prior Art for Obviousness

A PHOSITA, seeking to improve the robustness and cooperativeness of voice user interfaces, would have been motivated to combine elements from the following prior art references and common general knowledge:

1. US 7,640,160 B2 (Yankelovich et al.): "Systems and methods for responding to natural language speech utterance."
2. US 2005/0288924 A1 (Bennett): "Spoken language interface for enterprise applications."
3. Common general knowledge in the fields of Automatic Speech Recognition (ASR), Natural Language Understanding (NLU), and dialogue management systems, prevalent around the 2006 priority date.

Note: US 8,073,681 B2 and US 7,634,409 B2 are considered family members or related patents with the same inventors and priority claims, and thus are not considered prior art for an obviousness analysis against US 10,510,341.

Motivation to Combine

At the time of the invention (priority date 2006), a known challenge in voice user interfaces was the difficulty in accurately interpreting ambiguous or incomplete natural language utterances. Existing systems often failed on "average conversational missteps" and struggled to maintain context across a conversation, as acknowledged by the '341 patent itself.

A PHOSITA would be motivated to combine the context determination and disambiguation techniques from Yankelovich and Bennett with well-known principles of NLU and dialogue management to address these challenges and create a more intuitive and cooperative human-to-machine interface. The goal would be to build systems that better infer user intent, reduce recognition errors, and guide users towards successful task completion, mirroring human conversational behavior.

Specifically:

• Improving Contextual Understanding: A PHOSITA would recognize that Yankelovich's competitive domain agents provide a strong mechanism for determining context, especially when a single utterance might have multiple meanings (e.g., "traffic" in music vs. navigation). However, to further refine this, they would look to incorporate more explicit forms of knowledge, such as those described by Bennett.
• Leveraging Short-term and Long-term Knowledge: Bennett explicitly teaches using "dialog history" (akin to short-term knowledge) and "user preferences" (akin to long-term knowledge) to resolve ambiguities in spoken language. The '341 patent itself, when describing its context determination process, links directly to the methods in Yankelovich and states that the "winning agent may be responsible for... updating short-term and long-term shared knowledge." This indicates that the concept of accumulating different types of knowledge was already implicit or explicitly present in the relevant art or the context in which Yankelovich was understood. A PHOSITA would naturally combine these sources of knowledge to generate more robust interpretations.
• Handling Uncertainty and Disambiguation: Faced with inherent ambiguities in natural language, a PHOSITA would know that ASR and NLU systems often generate multiple potential interpretations (N-best lists), each with an associated confidence score or probability. When the system's confidence is low or when multiple interpretations are plausible (e.g., a "deadlock" between Yankelovich's competing agents), the known solution in dialogue management is to seek clarification from the user. The '341 patent explicitly describes this scenario: "If there is a deadlock between context domain agents, an adaptive conversational response may prompt the user to assist in disambiguating between the deadlocked agents." This directly suggests an obvious solution to a problem existing in systems like Yankelovich.
• Guiding User Interaction: It would be obvious to a PHOSITA that a clarifying question or a response that narrows down options (e.g., "Did you mean Portland, Maine or Portland, Oregon?") serves to "frame a domain" for the user's next response and "influence" the user to provide more structured or easily recognizable input. This is a fundamental principle in designing effective interactive systems to reduce errors and facilitate task completion. The '341 patent mentions that responses "may be modeled to illicit utterances from the user that may be more likely to result in a completed request" and conform to a "natural human tendency to 'parrot' what was just heard." This describes a desirable outcome of well-designed clarifying prompts.

Mapping Claim 1 Elements to the Combination

Let's examine how each element of Claim 1 of US 10,510,341 is rendered obvious by the proposed combination:

• "receiving, by at least one processor, an utterance from a user;"

  • Both Yankelovich and Bennett clearly teach receiving spoken utterances from a user in a voice user interface context.

• "generating, by the at least one processor, a plurality of hypotheses about an intent of the user, based on the utterance and a shared knowledge, wherein the shared knowledge includes short-term knowledge associated with a current conversation and long-term knowledge accumulated over time;"

  • Plurality of Hypotheses: Yankelovich's system, with its "one or more context domain agents compete to determine a most appropriate domain for a given utterance," inherently involves considering multiple potential interpretations (hypotheses) of the user's intent.
  • Shared Knowledge (Short-term & Long-term): The '341 patent itself states that when a domain agent "wins" in a system like Yankelovich's, it "may be responsible for... updating short-term and long-term shared knowledge." Furthermore, Bennett explicitly uses "dialog history" (short-term knowledge) and "user preferences" (long-term knowledge) to improve disambiguation. A PHOSITA would be motivated to integrate and leverage these different types of accumulated knowledge (conversational history, user habits/preferences) to inform the generation and evaluation of multiple hypotheses about user intent.

• "assigning, by the at least one processor, a degree of certainty to each hypothesis of the plurality of hypotheses;"

  • Yankelovich's "competition" among agents implies a ranking and selection of a "most appropriate" domain, suggesting varying levels of confidence or certainty. A "deadlock" between agents explicitly represents a low degree of certainty. Furthermore, it was common general knowledge in ASR and NLU fields at the time to associate confidence scores, probabilities, or rankings with N-best hypotheses generated during speech and language processing. A PHOSITA would routinely assign a degree of certainty (e.g., derived from confidence scores or the outcome of agent competition) to each of the competing hypotheses.

• "generating, by the at least one processor, an adaptive response to the user based on the degree of certainty of at least one hypothesis of the plurality of hypotheses, wherein the adaptive response is configured to: frame a domain for a subsequent utterance from the user; and influence the subsequent utterance from the user toward one or more utterances that are more likely to result in a completed request."

  • Given the problem of ambiguity in systems like Yankelovich and Bennett, and the common knowledge of N-best lists and confidence scores, a PHOSITA would find it obvious to use the "degree of certainty" to determine the type of response. When certainty is low (e.g., in a "deadlock" between Yankelovich's agents), an "adaptive response" in the form of a clarifying question is a standard dialogue management technique. The '341 patent itself explicitly states that in such a deadlock, "an adaptive conversational response may prompt the user to assist in disambiguating." Such clarifying prompts inherently:
    • Frame a domain: By offering specific choices or asking for particular information, the system defines the scope for the user's next input (e.g., "Did you mean 'traffic' the band or 'traffic' the road conditions?").
    • Influence the subsequent utterance: The structured nature of the clarifying question guides the user to respond in a way that is easier for the system to process, making it "more likely to result in a completed request." The concept of "parroting" as described in '341 for easier recognition is an advanced manifestation of this fundamental guidance.

Conclusion

Based on this analysis, the independent claims of US Patent 10,510,341 B1 would have been obvious to a person having ordinary skill in the art at the time of the invention. The combination of Yankelovich's competitive domain agents for context, Bennett's use of dialogue history and user preferences for disambiguation, and the well-established practices of generating N-best hypotheses with confidence scores and employing clarifying dialogue strategies, provides all the elements of Claim 1 with a clear motivation for their combination. A PHOSITA would have been driven by the need to create more robust and user-friendly voice interfaces capable of handling the inherent ambiguities of natural language by inferring intent more accurately and guiding users efficiently towards task completion.