Prior art

To identify the most relevant prior art for US patent 8073681, I will focus on the references explicitly cited within the detailed description of US8073681 itself, as these are the ones the patent directly references as foundational or related technology. These citations typically indicate a direct relationship to the invention's components or methods.

The detailed description of US8073681 references the following three U.S. patent documents:

1. U.S. Pat. No. 7,634,409

   • Full Citation: U.S. Pat. No. 7,634,409 B2, titled "Dynamic Speech Sharpening", issued December 15, 2009. The inventors are Michael Tjalve, Blane Ebersold, Chris Weider, Tom Freeman, and Larry Baldwin.
   • Publication/Filing Date: Filed August 31, 2006, and issued December 15, 2009.
   • Brief Description: This patent describes techniques for phonetic dictation to recognize a phoneme stream, which is used by the speech recognition engine (ASR 110) within the system of US8073681. It focuses on the underlying technology for converting spoken audio into preliminary textual interpretations.
   • Potential Anticipation (35 U.S.C. § 102): US7634409 potentially anticipates the "speech recognition engine" component of US8073681's claims (e.g., in claims 1, 10, and 19), particularly the aspect of generating "preliminary interpretations of the utterance." However, US8073681's claims generally cover a broader system and method for a cooperative conversational interface that utilizes such a speech recognition engine, rather than inventing the engine itself. Therefore, while the mechanism for speech recognition may be anticipated, the novel combination of elements and the cooperative conversational aspects claimed in US8073681 are likely not fully anticipated by this reference.

2. U.S. Pat. No. 7,640,160

   • Full Citation: U.S. Pat. No. 7,640,160 B2, titled "Systems and Methods for Responding to Natural Language Speech Utterance", issued December 29, 2009. The inventors are Thomas K. Freeman, Michael S. Tjalve, and Larry E. Baldwin.
   • Publication/Filing Date: Filed August 5, 2005, and issued December 29, 2009.
   • Brief Description: This patent details systems and methods for responding to natural language speech utterances, specifically concerning how "one or more context domain agents compete to determine a most appropriate domain for a given utterance" to establish meaning within a conversation. US8073681 explicitly states that its context determination process (255) is "as described in" this patent.
   • Potential Anticipation (35 U.S.C. § 102): Given the explicit reference in US8073681, US7640160 very likely anticipates the "context determination process" element found in claims 1, 10, and 19 of US8073681, particularly the mechanism involving "competing context domain agents." The core method for identifying and disambiguating conversational context appears to be established by this prior art. However, US8073681 differentiates itself by building upon this context determination within a larger cooperative conversational model that incorporates short-term and long-term shared knowledge, intelligent hypothesis building, and adaptive responses to create a more human-like interaction experience.

3. U.S. patent application Ser. No. 11/212,693 (issued as U.S. Pat. No. 7,774,204)

   • Full Citation: U.S. Pat. No. 7,774,204 B2, titled "Mobile Systems and Methods of Supporting Natural Language Human-Machine Interactions", issued August 10, 2010. The inventors are Thomas K. Freeman, Michael S. Tjalve, and Larry E. Baldwin.
   • Publication/Filing Date: Filed August 26, 2005, and issued August 10, 2010.
   • Brief Description: US8073681 cites this application in conjunction with U.S. Pat. No. 7,640,160, indicating its relevance to the "context determination process." Its title suggests a focus on natural language human-machine interactions specifically tailored for mobile systems. This likely involves methods for understanding and responding to natural language, with potential considerations for the constraints or capabilities inherent in mobile environments.
   • Potential Anticipation (35 U.S.C. § 102): Similar to US7640160, this patent application (now issued patent) also appears to anticipate aspects of US8073681's "context determination process." The emphasis on "mobile systems" suggests it could detail specific approaches for context management or natural language processing in portable devices, which could be relevant to how US8073681 gathers and uses environmental or user profile information as part of its shared knowledge. However, as with the other cited prior art, the broader scope of US8073681's claims, particularly its comprehensive cooperative conversational model that actively builds and leverages shared knowledge for adaptive responses and conversational flow correction, goes beyond the specific focus of this reference.

General Assessment of Anticipation:
A definitive determination of anticipation under 35 U.S.C. § 102 would require a detailed, element-by-element comparison of each claim in US8073681 against the complete disclosure (specification, claims, and drawings) of each prior art reference. Based on the titles, descriptions, and the context in which these patents/applications are cited within US8073681, these references primarily establish prior art for fundamental components like speech recognition and natural language context determination. US8073681 builds upon these foundations by integrating them into a more sophisticated "cooperative conversational model" that explicitly includes features such as:

• Leveraging both short-term and long-term shared knowledge.
• Generating intelligent hypotheses about user intent with varying degrees of certainty.
• Building adaptive responses that not only fulfill requests but also frame subsequent interactions to guide the user and correct conversational missteps.
• Modeling human-to-human conversational behavior, including tolerating imperfect speech and adapting to user expression variations.

Therefore, while individual elements or sub-processes described in US8073681 may find their roots in these cited prior art documents, the combination and synergistic operation of these features to achieve a "cooperative conversational voice user interface" (as claimed in US8073681) may represent a non-anticipated advancement.