Invalidity dossier
US 10593330
Added 6/10/2026, 12:00:18 AM
Active provider: Google · gemini-2.5-flash
Auto-generating section 1 of 2: Extensions…
Each section takes ~30-60s with web-search grounding. Keep this tab open — sections will fill in below as they complete.
Patent summary
Title, assignee, inventors, filing/issue dates, abstract, and a plain-language overview of the claims.
Here's a concise summary of US patent 10593330:
Title: Hotword detection on multiple devices
Assignee: Google LLC
Inventors: Matthew Sharifi
Filing Date: October 26, 2018
Issue Date: March 17, 2020
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving, by a first computing device, audio data that corresponds to an utterance. The actions further include determining a first value corresponding to a likelihood that the utterance includes a hotword. The actions further include receiving a second value corresponding to a likelihood that the utterance includes the hotword, the second value being determined by a second computing device. The actions further include comparing the first value and the second value. The actions further include based on comparing the first value to the second value, initiating speech recognition processing on the audio data.
Plain-Language Overview of Independent Claims:
The provided patent text excerpt does not include the full set of claims, only the abstract which summarizes "one aspect" of the method. To provide a plain-language overview of each independent claim, I would need access to the full claims section.
However, based on the provided abstract, the core concept of an independent claim would likely involve:
- Claim 1 (Method-type claim, inferred from abstract): A method for a first computing device to manage hotword detection among multiple devices. This involves the first device:
- Receiving spoken audio (an "utterance").
- Calculating a "first value" (a confidence score) indicating how likely the audio contains a specific "hotword."
- Receiving a "second value" (another confidence score) for the same utterance from a second computing device.
- Comparing its own "first value" to the "second value" from the other device.
- Deciding whether to start full speech recognition on the audio data based on this comparison (e.g., if its own score is highest).
Since the full claims are not provided in the prompt, I cannot definitively detail all independent claims.
CAFC 2026 Dockets:
A review of CAFC dockets for 2026 did not reveal any cases directly listing patent number US10593330. The provided search results primarily show scheduled arguments for June 2026 and a consolidated appeal from May 2025 related to tariffs, none of which appear to involve this specific patent. Therefore, based on the available search results, there is no authoritative information about current CAFC litigation specifically for US10593330 in 2026. However, it's important to note that the Google Patents page for US10593330 states "Family has litigation," referencing several cases in various jurisdictions and a PTAB case (IPR2023-00119) and International Trade Commission (337-TA-1329) cases, as well as several CAFC cases (25-2080, 24-2120). These CAFC cases are from 2024 and 2025, which would not show up in a 2026 dockets search, but indicate prior litigation activity related to the patent family.
Generated 6/10/2026, 12:00:45 AM