IP Library › Granted Patent US 12,620,009
Granted Patent B2
US 12,620,009 · App. 18/424,210 · Granted May 5, 2026

Method and system for artificial intelligence-based generation of travel and dining reviews

Inventors: Christopher Stang (Malibu, CA); Jessica Staddon (Redwood City, CA); Jonathan Lalima (Manalapan, NJ); Hillary Reinsberg (Brooklyn, NY); Janko Bazhdavela (Mamaroneck, NY); Ricardo Mela (Hartsdale, NY); Vineeth Ravi (Jersey City, NJ); Simran Lamba (Manhattan, NY); Katie Hainsey (New York, NY); Kevin Bichoupan (Great Neck, NY); Allison Beer (Bronxville, NY)
Assignee: JPMORGAN CHASE BANK, N.A.
G06Q30/0282G06Q50/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,620,009
App. No.
18/424,210
Granted
May 5, 2026
Kind
B2
Abstract

Systems and methods for using an artificial intelligence-based technique for automatic generation of travel and dining reviews are provided. The method includes: receiving a request for a review of an entity that provides a service to a user; applying a first artificial intelligence (AI) algorithm to the received request in order to generate the review of the entity; and outputting the review of the entity. The entity provides either or both of a travel-related service and a dining-related service, and as such, the entity may include a restaurant or a hotel. The AI algorithm may use a large language model and/or may be trained such that the review has a style and a tone of a Zagat review.

Claims (49)

1 . A method for generating a review, the method being implemented by at least one processor, the method comprising:

receiving, by the at least one processor, a request for a review of an entity that provides a service to a user;

soliciting a user device, by the at least one processor and in response to the receiving of the request for the review, at least user submission data that relates to an aspect of service provided by the entity, wherein the soliciting is performed by automated transmission of at least one message to the user device in order to prompt the user device to provide the at least user submission data;

applying, by the at least one processor, a first artificial intelligence (AI) algorithm to the received request and the at least user submission data in order to generate the review of the entity;

automatically generating, via the first AI algorithm, the review of the entity, wherein the automatically generating includes determining of an intent in the at least user submission data utilized by the first AI algorithm and creating synthetic embeddings verbatims for the determined intent;

checking, by the at least one processor, the automatically generated review of the entity to detect presence of a hallucination by validating the automatically generated review of the entity using one or more transaction data related to the entity;

modifying the automatically generated review of the entity by removing the detected hallucination for improved accuracy of the automatically generated review of the entity; and

outputting the modified review of the entity that is absent of the detected hallucination,

wherein the entity provides at least one from among a travel-related service and a dining-related service.

2 . The method of claim 1 , wherein the entity includes at least one from among a restaurant and a hotel.

3 . The method of claim 1 , wherein the first AI algorithm is configured to use at least one from among a sentiment analysis technique, a parts-of-speech (POS) tagging technique, and an extractive summarization and ranking technique to generate the review.

4 . The method of claim 1 , wherein the first AI algorithm is trained to generate the review conforming to a target style and a target tone.

5 . The method of claim 4 , wherein the first AI algorithm is trained by using historical data that includes previously published reviews conforming to the target style and the target tone.

6 . The method of claim 4 , wherein the first AI algorithm is configured to use a large language model (LLM) to generate the review.

7 . The method of claim 1 ,

wherein the automated transmission includes:

transmitting at least one message to the user device in order to prompt the user to provide a first submission that relates to a first aspect of the at least one from among the travel-related service and the dining-related service.

8 . The method of claim 7 , wherein the at least one message comprises at least one from among a first message that relates to providing a name and a location of the at least one from among the travel-related service and the dining-related service, a second message that relates to providing at least one stylistic constraint, and a third message that relates to providing at least one example of a review of a different entity to be used as a model.

9 . A computing apparatus for generating a review, the computing apparatus comprising:

a processor;

a memory; and

a communication interface coupled to each of the processor and the memory,

wherein the processor is configured to:

receive, via the communication interface, a request for a review of an entity that provides a service to a user;

solicit a user device, in response to the request for the review received, at least user submission data that relates to an aspect of service provided by the entity, wherein the user device is solicited by automated transmission of at least one message to the user device in order to prompt the user device to provide the at least user submission data;

apply a first artificial intelligence (AI) algorithm to the received request and the at least user submission data in order to generate the review of the entity;

automatically generate, via the first AI algorithm, the review of the entity, wherein the review of the entity is automatically generated by determining of an intent in the at least user submission data utilized by the first AI algorithm and creating synthetic embeddings verbatims for the determined intent;

check the automatically generated review of the entity to detect presence of a hallucination by validating the automatically generated review of the entity using one or more transaction data related to the entity;

modify the automatically generated review of the entity by removing the detected hallucination for improved accuracy of the automatically generated review of the entity; and

output the modified review of the entity that is absent of the detected hallucination,

wherein the entity provides at least one from among a travel-related service and a dining-related service.

10 . The computing apparatus of claim 9 , wherein the entity includes at least one from among a restaurant and a hotel.

11 . The computing apparatus of claim 9 , wherein the first AI algorithm is configured to use at least one from among a sentiment analysis technique, a parts-of-speech (POS) tagging technique, and an extractive summarization and ranking technique to generate the review.

12 . The computing apparatus of claim 9 , wherein the first AI algorithm is trained to generate the review conforming to a target style and a target tone.

13 . The computing apparatus of claim 12 , wherein the first AI algorithm is trained by using historical data that includes previously published reviews conforming to the target style and the target tone.

14 . The computing apparatus of claim 9 , wherein the first AI algorithm is configured to use a large language model (LLM) to generate the review.

15 . The computing apparatus of claim 9 , wherein the automated transmission includes:

transmitting, via the communication interface, at least one message to the user device in order to prompt the user to provide a first submission that relates to a first aspect of the at least one from among the travel-related service and the dining-related service.

16 . The computing apparatus of claim 15 , wherein the at least one message comprises at least one from among a first message that relates to providing a name and a location of the at least one from among the travel-related service and the dining-related service, a second message that relates to providing at least one stylistic constraint, and a third message that relates to providing at least one example of a review of a different entity to be used as a model.

17 . A non-transitory computer readable storage medium storing instructions for generating a review, the storage medium comprising executable code which, when executed by a processor, causes the processor to:

receive a request for a review of an entity that provides a service to a user;

solicit a user device, in response to the request for the review received, at least user submission data that relates to an aspect of service provided by the entity, wherein the user device is solicited by automated transmission of at least one message to the user device in order to prompt the user device to provide the at least user submission data;

apply a first artificial intelligence (AI) algorithm to the received request and the at least user submission data in order to generate the review of the entity;

automatically generate, via the first AI algorithm, the review of the entity, wherein the review of the entity is automatically generated by determining of an intent in the at least user submission data utilized by the first AI algorithm and creating synthetic embeddings verbatims for the determined intent;

check the automatically generated review of the entity to detect presence of a hallucination by validating the automatically generated review of the entity using one or more transaction data related to the entity; and

modify the automatically generated review of the entity by removing the detected hallucination for improved accuracy of the automatically generated review of the entity; and

output the modified review of the entity that is absent of the detected hallucination,

wherein the entity provides at least one from among a travel-related service and a dining-related service.

18 . The storage medium of claim 17 , wherein the entity includes at least one from among a restaurant and a hotel.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 13, 2024
From: STANG, CHRISTOPHER; MELA, RICARDO
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 068581/0192 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 14, 2024
From: STADDON, JESSICA; LALIMA, JONATHAN; REINSBERG, HILLARY; BAZHDAVELA, JANKO; RAVI, VINEETH; LAMBA, SIMRAN; HAINSEY, KATIE; BICHOUPAN, KEVIN; BEER, ALLISON
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 067407/0979 →
Continuity (2)
Provisional Application 63457950 · Apr 7, 2023
Related Publication 20240338737A1 · Oct 10, 2024
References Cited (8)
US 20080154883A1 · Chowdhury · 2008 [cited by examiner]
US 20100050118A1 · Chowdhury · 2010 [cited by examiner]
US 20150112981A1 · Conti · 2015 [cited by examiner]
US 20150161686A1 · Williams · 2015 [cited by examiner]
US 20150235281A1 · Jain · 2015 [cited by examiner]
US 20160267377A1 · Pan · 2016 [cited by examiner]
US 20230086653A1 · Zykh · 2023 [cited by examiner]
D. S. Susanto, E. Halim, Richard, A. Gui and Nelly, “Resolving Artificial Intelligence Hallucination in Personalized Adaptive Learning System,” 2023 Eighth International Conference on Informatics and Computing (ICIC), M… [cited by examiner]