System And Method For Delivering Targeted Advertisements And/Or Providing Natural Language Processing Based On Advertisements

Patent No. US12236456 (titled "System And Method For Delivering Targeted Advertisements And/Or Providing Natural Language Processing Based On Advertisements") was filed by Contingency Capital Fund A Lp on Aug 2, 2021.

What is this patent about?

’456 is related to the field of targeted advertising and natural language processing. Existing voice user interfaces often require users to memorize specific syntaxes or keywords, hindering intuitive interaction. This leads to missed opportunities for providing relevant information and fulfilling consumer demand, especially in voice-based interactions, which are a natural method of human communication. The patent addresses the problem of ineffective voice user interfaces in delivering targeted advertisements.

The underlying idea behind ’456 is to leverage natural language processing of voice-based inputs to deliver targeted advertisements and track user interactions to refine future ad selections. The system analyzes a user's spoken request, determines its context, and then selects a relevant purchase opportunity (advertisement). Crucially, the system learns from the user's interaction with the ad, updating the user's profile to improve the relevance of subsequent ad selections.

The claims of ’456 focus on a method and system for processing voice-based natural language utterances to select and present purchase opportunities. The independent claims cover receiving a user's spoken request, recognizing words and phrases, determining the context of the utterance, selecting a purchase opportunity based on the context, delivering the opportunity to the user's device, tracking the user's interaction with the opportunity, building a user-specific profile based on that interaction, and using the profile to interpret subsequent utterances and select further purchase opportunities.

In practice, the system works by first converting speech to text using a speech recognition engine. Then, a conversational language processor analyzes the text to determine the user's intent and context. Based on this context, the system selects a relevant advertisement from a repository. The selected advertisement is then presented to the user, and the system monitors whether the user clicks on the ad, makes a purchase, or otherwise interacts with it. This interaction data is then used to update the user's profile, which helps the system to better target future advertisements.

The key differentiation from prior approaches lies in the closed-loop feedback mechanism . Instead of simply displaying ads based on keywords or demographics, this system actively learns from user behavior to improve ad relevance over time. By tracking user interactions and updating user profiles, the system can deliver more personalized and effective advertisements, leading to increased engagement and conversion rates. This adaptive approach contrasts with static or rule-based ad selection methods.

How does this patent fit in bigger picture?

Technical landscape at the time

In the mid-2000s when ’456 was filed, voice recognition technology was emerging as a viable interface for electronic devices, at a time when systems commonly relied on keyword spotting and rule-based grammars rather than statistical language models for natural language understanding. At that time, targeted advertising was typically implemented using web-based cookies and user profiling, when hardware or software constraints made real-time analysis of voice-based input for ad selection non-trivial.

Novelty and Inventive Step

The examiner allowed the claims because the invention overrides the routine and conventional use of selecting and presenting purchase opportunities based on speech recognition and user context tracking. The examiner withdrew the rejection under 35 U.S.C. 101, finding that the amended claims do not recite an abstract idea or, if they do, they improve the functioning of a computer or other technology. The examiner also stated that the closest prior art barely reads on or teaches the claimed invention, particularly the combination of limitations in the independent claims.

Claims

This patent contains 56 claims, with independent claims 1 and 11. The independent claims focus on a method and a system for processing voice-based natural language utterances to select and present purchase opportunities. The dependent claims generally elaborate on and refine the features of the independent claims.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Natural language utterance
(Claim 1, Claim 11)
“According to various aspects of the invention, a system and method for selecting and presenting advertisements based on natural language processing of voice-based inputs is provided. A natural language voice-based input may be received by a voice user interface. The voice-based input may include a user utterance, and a request may be identified from the utterance.”A spoken input from a user that is processed using natural language processing techniques.
Purchase opportunity
(Claim 1, Claim 11)
“For example, advertisements may include sponsored messages, calls to action, purchase opportunities, trial downloads, or any other marketing communication, as would be apparent to those skilled in the art.”An offer or advertisement presented to the user, allowing them to make a purchase or complete a transaction.
Selection criteria
(Claim 1, Claim 11)
“Advertisements may be selected based on various criteria, including content of the input (e.g., concepts, semantic indicators, etc.), an activity related to the input (e.g., a relation to a request, a requested application, etc.), user profiles (e.g., demographics, preferences, location, etc.), or in other ways.”Factors used to determine which purchase opportunity is presented to the user, including the determined context of the utterance.
Speech recognition engine
(Claim 1, Claim 11)
“According to various aspects of the invention, a system and method for selecting and presenting advertisements based on natural language processing of voice-based inputs is provided. A natural language voice-based input may be received by a voice user interface. The voice-based input may include a user utterance, and a request may be identified from the utterance.”A component that converts a natural language utterance into recognized words and/or phrases.
User-specific profile
(Claim 1, Claim 11)
“A user may subsequently interact with the advertisement (e.g., via a voice-based input), and action may be taken in response to the interaction. Furthermore, the interaction may be tracked to build statistical profiles of user behavior based on affinities or clusters among advertisements, user profiles, contexts, topics, semantic indicators, concepts, or other criteria.”A record of a user's tracked interactions with purchase opportunities, used to interpret subsequent utterances and select future purchase opportunities.

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Date

    Description

  • Get instant alerts for new documents

US12236456

CONTINGENCY CAPITAL FUND A LP
Application Number
US17391388
Filing Date
Aug 2, 2021
Status
Granted
Expiry Date
Feb 6, 2027
External Links
Slate, USPTO, Google Patents