Granted Patent B2

US 12,579,377 · App. 18/467,995 · Granted Mar 17, 2026

Inventors: Chuanye Ouyang (Gaithersburg, MD); Benjamin Lerchin (Victoria, CA); Danica Dillera (Toronto, CA)

Assignee: SHOPIFY INC.

G06F40/40G06F16/345G06F40/166G06F40/284G06N20/00G06Q30/0282G06Q30/0631G06F40/30

Abstract

Claims (67)

1 . A computer-implemented method comprising:

assigning relevancy values to reviews of a plurality of reviews;

automatically aggregating a subset of reviews from the plurality of reviews into an input prompt, the subset of reviews selected based on the relevancy values assigned to reviews in the plurality of reviews and the subset of reviews comprising a defined number of reviews, wherein determining the defined number of reviews comprises:

generating a plurality of subsets of reviews, wherein each subset of reviews of the plurality of subsets of reviews includes a number of reviews;

for each subset of reviews of the plurality of subsets of reviews:

inputting that subset of reviews into a generative language model yielding a summary of that subset of reviews;

generating a semantic embedding of the summary of that subset of reviews; and

determining a distance between the semantic embedding of the summary of that subset of reviews and a corresponding semantic embedding of a preceding summary of a preceding subset of reviews of the plurality of subsets of reviews; and

determining, as the defined number of reviews, a number of reviews in a particular subset of reviews of the plurality of subsets of reviews having the distance below a distance threshold; and

inputting the input prompt into the generative language model yielding a summary review of the subset of reviews generated by the generative language model.

2 . The computer-implemented method of claim 1 , wherein a relevancy value assigned to a particular review of the plurality of reviews is based on at least one of informational density of review content of the particular review or keywords in the review content of the particular review.

3 . The computer-implemented method of claim 1 , wherein a relevancy value assigned to a particular review of the plurality of reviews is based on review metadata associated with the particular review.

4 . The computer-implemented method of claim 1 , wherein inputting the input prompt into the generative language model yielding the summary review comprises:

inputting the input prompt into the generative language model yielding attribute data associated with the subset of reviews generated by the generative language model; and

inputting the attribute data into the generative language model yielding an initial summary generated by the generative language model.

5 . The computer-implemented method of claim 4 , further comprising:

inputting the initial summary and context including one or more example summary reviews into the generative language model yielding a final summary generated by the generative language model, wherein the final summary comprises the summary review.

6 . The computer-implemented method of claim 1 , wherein the subset of reviews comprises reviews of the plurality of reviews having highest relevancy values.

7 . The computer-implemented method of claim 1 , wherein

each subset of reviews of the plurality of subsets of reviews includes a number of reviews selected according to a review number sequence and wherein a subset of reviews in the review number sequence includes all reviews of a preceding subset of reviews in the review number sequence as well as additional reviews.

8 . The computer-implemented method of claim 7 , wherein the preceding subset of reviews in the review number sequence comprises an immediately preceding subset of reviews in the review number sequence.

9 . A non-transitory computer-readable storage medium having stored thereon computer-executable instructions that, when executed, cause at least one processor to perform operations comprising:

assigning relevancy values to reviews of a plurality of reviews;

automatically aggregating a subset of reviews from the plurality of reviews into an input prompt, the subset of reviews selected based on the relevancy values assigned to reviews in the plurality of reviews and the subset of reviews comprising a defined number of reviews, wherein determining the defined number of reviews comprises:

generating a plurality of subsets of reviews, wherein each subset of reviews of the plurality of subsets of reviews includes a number of reviews;

for each subset of reviews of the plurality of subsets of reviews:

inputting that subset of reviews into a generative language model yielding a summary of that subset of reviews;

generating a semantic embedding of the summary of that subset of reviews; and

determining a distance between the semantic embedding of the summary of that subset of reviews and a corresponding semantic embedding of a preceding summary of a preceding subset of reviews of the plurality of subsets of reviews; and

determining, as the defined number of reviews, a number of reviews in a particular subset of reviews of the plurality of subsets of reviews having the distance below a distance threshold; and

inputting the input prompt into a generative language model yielding a summary review of the subset of reviews generated by the generative language model.

10 . The non-transitory computer-readable storage medium of claim 9 , wherein a relevancy value assigned to a particular review of the plurality of reviews is based on at least one of:

informational density of review content of the particular review;

keywords in the review content of the particular review; or

review metadata associated with the particular review.

11 . The non-transitory computer-readable storage medium of claim 9 , wherein the computer-executable instructions which cause the at least one processor to perform operations comprising inputting the input prompt into the generative language model yielding the summary review comprises instructions which cause the at least one processor to perform operations comprising:

inputting the input prompt into the generative language model yielding attribute data associated with the subset of reviews generated by the generative language model; and

inputting the attribute data into the generative language model yielding an initial summary generated by the generative language model.

12 . The non-transitory computer-readable storage medium of claim 11 , further comprising computer-executable instructions which cause the at least one processor to perform operations comprising:

inputting the initial summary and context including one or more example summary reviews into the generative language model yielding a final summary generated by the generative language model, wherein the final summary comprises the summary review.

13 . The non-transitory computer-readable storage medium of claim 9 , wherein the subset of reviews comprises reviews of the plurality of reviews having highest relevancy values.

14 . The non-transitory computer-readable storage medium of claim 9 , wherein

each subset of reviews of the plurality of subsets of reviews includes a number of reviews selected according to a review number sequence and wherein a subset of reviews in the review number sequence includes all reviews of a preceding subset of reviews in the review number sequence as well as additional reviews.

15 . The non-transitory computer-readable storage medium of claim 14 , wherein the preceding subset of reviews in the review number sequence comprises an immediately preceding subset of reviews in the review number sequence.

16 . A system comprising:

at least one processor; and

a non-transitory computer-readable storage medium having stored thereon computer-executable instructions that, when executed, cause the at least one processor to at least:

assign relevancy values to reviews of a plurality of reviews;

automatically aggregate a subset of reviews from the plurality of reviews into an input prompt, the subset of reviews selected based on the relevancy values assigned to reviews in the plurality of reviews and the subset of reviews comprising a defined number of reviews, wherein the computer-executable instructions further comprise computer-executable instructions that cause the at least one processor to determine the defined number of reviews by at least:

generating a plurality of subsets of reviews, wherein each subset of reviews of the plurality of subsets of reviews includes a number of reviews;

for each subset of reviews of the plurality of subsets of reviews:

inputting that subset of reviews into a generative language model yielding a summary of that subset of reviews;

generating a semantic embedding of the summary of that subset of reviews; and

determining a distance between the semantic embedding of the summary of that subset of reviews and a corresponding semantic embedding of a preceding summary of a preceding subset of reviews of the plurality of subsets of reviews; and

determining, as the defined number of reviews, a number of reviews in a particular subset of reviews of the plurality of subsets of reviews having the distance below a distance threshold; and

input the input prompt into a generative language model yielding a summary review of the subset of reviews generated by the generative language model.

17 . The system of claim 16 , wherein a relevancy values assigned to a particular review of the plurality of reviews is based on at least one of:

informational density of review content of that review;

keywords in the review content of the particular review; or

review metadata associated with that review.

18 . The system of claim 16 , wherein the computer-executable instructions which cause the at least one processor to input the input prompt into the generative language model yielding the summary review comprises computer-executable instructions which cause the at least one processor to at least:

input the input prompt into the generative language model yielding attribute data associated with the subset of reviews generated by the generative language model;

input the attribute data into the generative language model yielding an initial summary generated by the generative language model; and

input the initial summary and context including one or more example summary reviews into the generative language model yielding a final summary generated by the generative language model, wherein the final summary comprises the summary review.

19 . The system of claim 16 , wherein the subset of reviews comprises reviews of the plurality of reviews having highest relevancy values.

20 . The system of claim 16 , wherein

each subset of reviews of the plurality of subsets of reviews includes a number of reviews selected according to a review number sequence and wherein a subset of reviews in the review number sequence includes all reviews of a preceding subset of reviews in the review number sequence as well as additional reviews.

Assignments (3)

Continuity (1)

References Cited (15)