Get the newsletter
Google · AI / ML · Filed Jul 29, 2025 · USPTO published Aug 13, 2026 · Aug 13 release

Google Patents AI That Recommends Products Through Natural Conversational Dialogue

Google has patented a system where a large language model tracks the flow of a conversation in real time and uses that understanding to decide what to recommend to you, not just answer your question.

User interacting with a conversational video recommendation system via a laptop display interface. Drawing from patent filing US 2026/0236544 A1.
User interacting with a conversational video recommendation system via a laptop display interface.All 20 drawings ↓
Publication number
US 2026/0236544 A1(US20260236544A1)
Applicant
Google LLC
Filed · Published
Jul 29, 2025 · Aug 13, 2026
Inventors
Zhenning Tan, Luke Beck Friedman, Manoj Tiwari, Sameer Ahuja
Status when we published
Examiner raised objections; the company can respond
Document
21 claims
US classification
707/706
Examiner
CHBOUKI, TAREK (Art Unit 2165)
Parent application
National Stage Entry of PCT/US2023/012758 (filed Feb 10, 2023)(PCTUS2023012758)

What Google's conversational recommendation system actually does

A shopper types into a chat window: "I want something comfortable for a long flight, not too expensive, and I hate overhead bins." A search box has no idea what to do with that. This is the kind of problem Google's new patent is designed to solve.

The system uses an AI language model to follow the conversation like a human assistant would. As you add details, change your mind, or ask follow-up questions, the model tracks what you want, picks relevant items from a database, and shows them to you alongside a plain-language explanation of why they were chosen.

The result is a recommender that behaves less like a search engine and more like a knowledgeable store clerk who actually listened to what you said.

From the filing · CLAIM 1
… the dialogue manager is further configured to present the recommendation slate and an explanation about the recommendation slate to a user of the client device along with the response to the received user input.

Translation: The system provides product suggestions and explains why it chose them during your chat.

How the dialogue manager and recommendation engine work together

At the center of the system is a dialogue manager, a software layer that uses a trained large language model to interpret incoming messages. Rather than just parsing keywords, the model predicts what the patent calls a dialogue state, essentially a running summary of what the user wants, what constraints they've expressed, and where the conversation currently stands.

That dialogue state is handed to a separate recommendation engine, which queries a candidate corpus (a large pool of items, products, or content). The engine filters that pool down to a ranked set of relevant results called a recommendation slate.

The dialogue manager then takes that slate and wraps it in a natural-language response, including an explanation of why those items were surfaced. The key steps in order are:

  • User sends a message during a live chat session
  • LLM predicts the current dialogue state from that message
  • Recommendation engine queries the item database based on that state
  • A ranked slate of items is assembled
  • The dialogue manager returns the slate plus a response and an explanation to the user

The architecture keeps the language model and the recommendation engine as distinct but connected components, which means each can be updated or swapped independently.

From the filing · THE ABSTRACT
The technology relates to conversational recommender systems ( 100 ) that employ a large language model ( 402 ) which can function as part of a dialogue manager ( 326 ).

Translation: This patent describes using a large language model to manage how a computer talks to you while suggesting products.

What this means for Google's AI-powered shopping and search tools

For Google, this sits squarely at the intersection of two things the company is already pushing hard: conversational AI through Gemini and product discovery through Google Shopping. A system that can sustain a multi-turn conversation while simultaneously surfacing ranked results would be a meaningful step up from the current experience, where chat and search still feel like separate tools bolted together.

For you as a user, the pitch is that you stop having to translate what you actually want into search-box language. The dialogue state tracking means the system remembers that you said "not too formal" two messages ago, even when you've since moved on to asking about colors. Google's work in this area is part of a broader push across AI-powered search and discovery tools covered in the latest Big Tech patents, where conversational recommendation is emerging as one of the more contested spaces.

Source: US 2026/0236544 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Google patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 20 sheets

20 drawing sheets from US 2026/0236544 A1 · click any drawing to enlarge

Chat interface and video recommendations, drawing sheet 1 from US 2026/0236544 A1
Sheet 1 Chat interface and video recommendations
Conversational history and system updates, drawing sheet 2 from US 2026/0236544 A1
Sheet 2 Conversational history and system updates
Dialogue continuation and general knowledge, drawing sheet 3 from US 2026/0236544 A1
Sheet 3 Dialogue continuation and general knowledge
Transformer encoder and decoder architecture, drawing sheet 4 from US 2026/0236544 A1
Sheet 4 Transformer encoder and decoder architecture
Recommendation retrieval and generation pipeline, drawing sheet 5 from US 2026/0236544 A1
Sheet 5 Recommendation retrieval and generation pipeline
Dialogue manager and user memory components, drawing sheet 6 from US 2026/0236544 A1
Sheet 6 Dialogue manager and user memory components
Auxiliary context processing neural network, drawing sheet 7 from US 2026/0236544 A1
Sheet 7 Auxiliary context processing neural network
NLU query extraction and recommendation engine, drawing sheet 8 from US 2026/0236544 A1
Sheet 8 NLU query extraction and recommendation engine
Show the other 12 sheets
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 9
Sheet 9
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 10
Sheet 10
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 11
Sheet 11
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 12
Sheet 12
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 13
Sheet 13
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 14
Sheet 14
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 15
Sheet 15
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 16
Sheet 16
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 17
Sheet 17
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 18
Sheet 18
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 19
Sheet 19
Google Patents AI That Recommends Products Through Natural Conversational Dialogue patent drawing, sheet 20
Sheet 20
Patent filing page

Watchlists this filing belongs to

All watchlists →