Systems and methods for computer generation of a modifiable product description

Patent metadata

Field	Value
Publication number	US-2023259692-A1
Application number	US-202217670110-A
Country	US
Kind code	A1
Filing date	Feb 11, 2022
Priority date	Feb 11, 2022
Publication date	Aug 17, 2023
Grant date	—

Abstract

Generative language models are able to generate a sequence of text that may closely mimic a native human speaker's own generated text. However, technical challenges exist when implementing a generative language model for generating product descriptions. The model may output certain inaccuracies due to the predictive nature of generating the output. Further, the model does not have the ability to identify words from the product description that a merchant may want to modify, nor the ability to provide meaningful alternatives to such words. In some embodiments, a natural language processor might be built and/or trained using classification data. The natural language processor may identify one or more words and/or phrases in a product description as a candidate for modification. The product description might then be displayed on a merchant-facing user interface with an indication that the candidate for modification may be modified.

First claim

1 . A computer-implemented method comprising:
generating a product description associated with a product using a generative language model; processing the product description to identify at least a word or phrase in the product description as a candidate for modification; and providing content for presentation, the content including the product description and an alternative word or phrase that may be substituted in place of the candidate for modification.

2 . The computer-implemented method of claim 1 , wherein generating the product description comprises:
receiving a prompt, the prompt including text corresponding to the product; and inputting the prompt into the generative language model.

3 . The computer-implemented method of claim 2 , wherein the prompt further includes one or both of an example product title and an example product description.

4 . The computer-implemented method of claim 1 , wherein the generative language model sequentially outputs segments of the production description, each next segment determined by the generative language model as being associated with a highest probability of being the next segment.

5 . The computer-implemented method of claim 4 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is a particular word or phrase that was determined by the generative language model as being associated with a lower probability of being the next segment and not used to form part of the product description.

6 . The computer-implemented method of claim 1 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is determined based on use of the alternative word or phrase in relation to other products.

7 . The computer-implemented method of claim 1 further comprising:
processing an image depicting the product to obtain an attribute related to the product as depicted in the image; and
including, in the content, a particular word or phrase associated with the attribute.

8 . The computer-implemented method of claim 7 further comprising modifying the product description to include the particular word or phrase associated with the attribute.

9 . The computer-implemented method of claim 7 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is the particular word or phrase associated with the attribute.

10 . A system comprising:
at least one processor; and a memory storing processor-executable instructions that, when executed, cause the at least one processor to: generate a product description associated with a product using a generative language model; process the product description to identify at least a word or phrase in the product description as a candidate for modification; and provide content for presentation, the content including the product description and an alternative word or phrase that may be substituted in place of the candidate for modification.

11 . The system of claim 10 , wherein the at least one processor is further to:
receive a prompt, the prompt including text corresponding to the product; and input the prompt into the generative language model.

12 . The system of claim 10 , wherein the at least one processor is to use the generative language model to sequentially output segments of the product description, and wherein each next segment is associated with a highest probability of being the next segment.

13 . The system of claim 12 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is a particular word or phrase associated with a lower probability of being the next segment and does not form part of the product description.

14 . The system of claim 10 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is determined based on use of the alternative word or phrase in relation to other products.

15 . The system of claim 10 , wherein the at least one processor is further to:
process an image depicting the product to obtain an attribute related to the product as depicted in the image; and include, in the content, a particular word or phrase associated with the attribute.

16 . The system of claim 15 wherein the at least one processor is further to modify the product description to include the particular word or phrase.

17 . The system of claim 15 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is the particular word or phrase associated with the attribute.

18 . A computer readable medium having stored thereon computer-executable instructions that, when executed by a computer, cause the computer to perform operations comprising:
generating a product description associated with a product using a generative language model; processing the product description to identify at least a word or phrase in the product description as a candidate for modification; and providing content for presentation, the content including the product description and an alternative word or phrase that may be substituted in place of the candidate for modification.

19 . The computer readable medium of claim 18 , wherein the generative language model sequentially outputs segments of the production description, each next segment determined by the generative language model as being associated with a highest probability of being the next segment.

20 . The computer readable medium of claim 19 , wherein the alternative word or phrase that may be substituted in place of the candidate for modification is a particular word or phrase that was determined by the generative language model as being associated with a lower probability of being the next segment and not used to form part of the product description.

Assignees

• Shopify Inc

Inventors

• Wright Asher

Classifications

• G06F40/166 Primary

  Editing, e.g. inserting or deleting · CPC title

• G06F40/289

  Phrasal analysis, e.g. finite state techniques or chunking · CPC title

• G06F40/40

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

• G06F40/56 Primary

  Natural language generation · CPC title