User interface for chat-guided searches

Patent metadata

Field	Value
Publication number	US-12511679-B2
Application number	US-202318315792-A
Country	US
Kind code	B2
Filing date	May 11, 2023
Priority date	Feb 28, 2023
Publication date	Dec 30, 2025
Grant date	Dec 30, 2025

Abstract

A computer-implemented method is disclosed. The method includes: receiving, via a first user interface, a selection associated with an object; determining a first set of object attributes based on the selection; presenting, via a second user interface, a text prompt for a user to identify a subset of the first set of object attributes; receiving, via the second user interface, an indication of one or more preferred object attributes of the identified subset; and updating the first user interface to display content relating to objects associated with the one or more preferred object attributes.

First claim

The invention claimed is:

1 . A computer-implemented method for performing a chat-guided search, comprising:
receiving user input of a search query; performing a search of a defined search space of objects using the search query; presenting, via a first user interface, an initial set of user interface elements associated with results of the search, the initial set corresponding to a subset of all searchable objects; receiving, via the first user interface, a selection of a user interface element from the initial set; determining a first set of object attributes based on extracting object attributes from metadata associated with a first object corresponding to the selected user interface element; providing, to a large language model (LLM), an input comprising the first set of object attributes and an indication of the first object and instructions to generate user prompt data for soliciting user selection of a subset of the first set; presenting the user prompt data as chat outputs in a second user interface; receiving, via the second user interface, an indication of one or more preferred object attributes of the identified subset; and updating the first user interface in real-time based on user interaction with the second user interface to display user interface elements corresponding to a progressively reduced set of searchable objects associated with the one or more preferred object attributes.

2 . The method of claim 1 , wherein the first user interface and the second user interface are each a portion of a single user interface.

3 . The method of claim 1 , wherein the selection comprises a selected product image depicting a product.

4 . The method of claim 1 , wherein the displayed content comprises images of the objects.

5 . The method of claim 1 , wherein the first user interface comprises an image canvas interface for displaying images corresponding to results of a further search based on the one or more preferred object attributes.

6 . The method of claim 1 , wherein the second user interface comprises a chatbot interface.

7 . The method of claim 1 , further comprising:
responsive to receiving the selection, initiating a similarity search based on the selection, wherein the first set of object attributes is determined based on identifying object attributes that are commonly associated with results of the similarity search.

8 . The method of claim 7 , wherein the first set of object attributes comprises object attributes that are determined to be relevant for an object category associated with an object corresponding to the selection.

9 . The method of claim 7 , further comprising updating the first user interface to display object images associated with results of the similarity search.

10 . The method of claim 1 , wherein the indication of the one or more preferred object attributes comprises a user response, inputted via the second user interface, to the user prompt data presented as chat outputs.

11 . The method of claim 1 , wherein the search is a vector search and wherein the initial set of user interface elements correspond to objects of the search space that are identified as being similar to a query object of the search query based on the vector search.

12 . The method of claim 1 , wherein the user prompt data comprises text of question prompts that are outputted by the LLM.

13 . The method of claim 12 , further comprising:
providing, to the LLM, the indication of the one or more preferred object attributes and instructions to generate further follow-up question prompts; and presenting, via the second user interface, the further follow-up question prompts.

14 . The method of claim 1 , wherein each of the searchable objects is associated with at least one of tags or metadata indicating object attributes of the object.

15 . A computing system, comprising:
a processor; and a memory coupled to the processor, the memory storing computer-executable instructions that, when executed by the processor, configure the processor to:
receive user input of a search query;
perform a search of a defined search space of objects using the search query;
present, via a first user interface, an initial set of user interface elements associated with results of the search, the initial set corresponding to a subset of all searchable objects;
receive, via the first user interface, a selection of a user interface element from the initial set;
determine a first set of object attributes based on extracting object attributes from metadata associated with a first object corresponding to the selected user interface element;
provide, to a large language model (LLM), an input comprising the first set of object attributes and an indication of the first object and instructions to generate user prompt data for soliciting user selection of a subset of the first set;
present the user prompt data as chat outputs in a second user interface;
receive, via the second user interface, an indication of one or more preferred object attributes of the identified subset; and
update the first user interface in real-time based on user interaction with the second user interface to display user interface elements corresponding to a progressively reduced set of searchable objects associated with the one or more preferred object attributes.

16 . The computing system of claim 15 , wherein the first user interface and the second user interface are each a portion of a single user interface.

17 . The computing system of claim 15 , wherein the instructions, when executed, are to further cause the processor to:
responsive to receiving the selection, initiate a similarity search based on the selection, wherein the first set of object attributes is determined based on identifying object attributes that are commonly associated with results of the similarity search.

18 . The computing system of claim 17 , wherein the first set of object attributes comprises object attributes that are determined to be relevant for an object category associated with an object corresponding to the selection.

19 . The computing system of claim 17 , wherein the instructions, when executed, are to further cause the processor to update the first user interface to display object images associated with results of the similarity search.

20 . A non-transitory processor-readable medium storing processor-executable instructions that, when executed by a processor, are to cause the processor to:
receive user input of a search query; perform a search of a defined search space of objects using the search query; present, via a first user interface, an initial set of user interface elements associated with results of the search, the initial set corresponding to a subset of all searchable objects; receive, via the first user interface, a selection of a user interface element from the initial set; determine a first set of object attributes based on extracting object attributes from metadata associated with a first object corresponding to the selected user interface element; provide, to a large language model (LLM), an input comprising the first set of object attributes and an indication of the first object and instructions to generate user prompt data for soliciting user selection of a subset of the first set; present the user prompt data as chat outputs in a second user interface; receive, via the second user interface, an indication of one or more preferred object attributes of the identified subset; and update the fir

Assignees

• Shopify Inc

Inventors

• Batina Katarina
• Cohen Kenneth

Classifications

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F40/40 Primary

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F16/3328

  using graphical result space presentation or visualisation · CPC title

• G06Q30/0627 Primary

  by specifying product or service characteristics, e.g. product dimensions · CPC title