Obviousness

Obviousness Analysis of U.S. Patent 12,236,456 under 35 U.S.C. § 103

Under 35 U.S.C. § 103, a patent claim is invalid as obvious "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" (PHOSITA). This analysis considers whether a PHOSITA, at the time of the invention (priority date of February 6, 2007), would have been motivated to combine existing prior art references to arrive at the invention claimed in U.S. Patent 12,236,456, with a reasonable expectation of success.

The core inventive concept of claims 1 and 11 is a specific feedback loop in a voice-operated system: (1) a purchase opportunity is selected based on a user's utterance, (2) the user's interaction with that purchase opportunity is tracked, (3) a user-specific profile is built or updated based on this interaction, and, critically, (4) this updated profile is then used to interpret a subsequent natural language utterance from the same user.

Based on the provided prior art, the claims of U.S. Patent 12,236,456 would have been obvious by combining the teachings of U.S. Patent Application Publication No. 2005/0144068 A1 (Kopra) and U.S. Patent No. 7,069,219 B2 (Drucker).

---

Combination of Kopra and Drucker

1. What Kopra Teaches:
Kopra discloses a comprehensive voice-based advertising system. It teaches:

• Receiving a user's spoken request (a natural language utterance).
• Selecting targeted advertisements based on the utterance, user location, and demographic data.
• Delivering the advertisement to the user.
• Tracking the user's interaction with the advertisement (e.g., requesting more information).
• Using this tracked interaction data to "compile a history of the user's preferences" (i.e., build or update a user-specific profile).
• Using this preference history to select more relevant advertisements in the future.

Kopra teaches nearly every element of the claimed invention. The single element it fails to explicitly disclose is using the ad-interaction-based user profile to interpret the meaning of a subsequent utterance. Kopra uses the profile to select a better advertisement after the subsequent utterance has already been interpreted by the system.

2. What Drucker Teaches:
Drucker teaches the precise element missing from Kopra, albeit outside of an advertising context. It discloses a natural language processing (NLP) system that improves its own accuracy over time. It teaches:

• Using a statistical model to interpret user utterances.
• Tracking user interactions and feedback (such as when a user clarifies an ambiguous request).
• Using this feedback to update or retrain the underlying statistical model.
• Using the updated model to more accurately interpret subsequent user utterances.

Drucker's core teaching is a feedback loop for improving the fundamental natural language understanding (NLU) capability of a system based on user behavior.

3. Motivation to Combine Kopra and Drucker:
A person of ordinary skill in the art in 2007, working to improve a voice-based services platform like the one described by Kopra, would have been highly motivated to combine it with the NLU improvement techniques taught by Drucker. The motivation is to enhance the overall performance, personalization, and perceived intelligence of the voice assistant.

• Problem Faced by the PHOSITA: The PHOSITA working with Kopra's system would have a rich source of user preference data derived from ad interactions. This data provides strong, implicit signals about a user's interests (e.g., a user who interacts with ads for Italian restaurants is likely interested in Italian food). The PHOSITA's goal is to make the entire system, not just the advertising component, more useful and accurate for the user.
• Solution Provided by Drucker: Drucker provides an explicit method for improving NLU accuracy by feeding user interaction data back into the interpretation model.
• Obvious Combination: A PHOSITA would recognize that the user preference data being collected in Kopra's system for ad selection could also be used to resolve ambiguity and improve the core interpretation of user speech, as taught by Drucker. For example, if a user's profile in the Kopra system shows a history of interacting with ads for "Marriott" hotels, and the user later issues the ambiguous utterance "Book me a room at the hotel near the airport," the PHOSITA would be motivated to apply Drucker's method. They would use the profile data to update the NLU model to interpret "the hotel" as more likely referring to "Marriott."

This combination would not just result in a better-selected advertisement, but a better, more accurate fulfillment of the user's primary request. The motivation is to leverage a valuable, already-collected data source (ad interactions) to improve the core functionality (NLU) of the system, creating a more seamless and personalized user experience. A PHOSITA would have had a reasonable expectation of success, as Drucker teaches how statistical models can be updated with new data, and the ad interaction history from Kopra is simply another stream of user behavioral data.