# US 2026/0228647 A1 · a System and method to plan and book hotels utilizing artificial intelligence

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0228647 A1
- Document ID: US20260228647A1
- Status: Published application
- Kind: A1
- Application number: 19/459,373
- Filed: 2026-01-26
- Published: 2026-08-06
- Earliest claimed: 2025-01-30
- Assignees: Zenvoya, Inc.
- Applicants: Zenvoya, Inc.
- Inventors: Surendra Goel
- Web page: https://patentgrep.com/patent/US20260228647A1

## CPC

- G06Q 10/02: Reservations, e.g. for tickets, services or events
- G06Q 10/0285: {for lodging}
- G06Q 50/12: Hotels or restaurants
- G06Q 50/14: Travel agencies
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A computer-implemented method to plan and book hotels utilizing artificial intelligence from unstructured user input with a language model, the method comprising: receiving, at a computer system, an input hotel query reflecting a user intention; wherein an artificial intelligence model has been trained based on user data of a user’s hotel preferences; analyzing the input hotel query using the trained artificial intelligence model; generating possible hotels in terms of dates, based on the input hotel query, external context, hotel attributes (structured and unstructured; see appendix hotel attributes) and the user’s hotel preferences; wherein the artificial intelligence utilized is either machine learning, deep learning or neural networks; wherein the artificial intelligence model utilizes a probabilistic model; wherein the language model may be either a large language model or a small language model; wherein there are several additional dimensions by which possible hotels are generated.

## Claims

### Claim 1

A computer-implemented method to plan and book hotels utilizing artificial intelligence from structured and unstructured user input with a language model, the method comprising:
receiving, at a computer system, an input hotel query reflecting a user intention;
wherein an artificial intelligence model has been trained based on user data of a user’s hotel preferences, hotel availability and many attributes relating to hotels;
wherein artificial intelligence is used to understand the user intent to find the best semantic matches to the user input, external context, hotel attributes and the available hotel inventory;
analyzing the input hotel query using the trained artificial intelligence model; and
generating possible hotels in terms of dates, based on the input hotel query, external context, hotel attributes (structured and unstructured; see appendix hotel attributes) and the user’s hotel preferences.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
wherein the artificial intelligence utilized is either machine learning, deep learning or neural networks.

### Claim 3 (depends on 1)

The method of claim 1,
wherein the artificial intelligence model utilizes a natural language understanding and probabilistic models.

### Claim 4 (depends on 1)

The method of claim 1,
wherein the language model may be either a large language model or a small language model.

### Claim 5 (depends on 1)

The method of claim 1,
wherein additional dimensions by which possible hotels are generated include Structured Hotel Attributes (see appendix Hotel Attributes) :
guest type, as in adult or child;
number of beds;
room class, as in standard, premium, or luxury class.

### Claim 6 (depends on 1)

The method of claim 1,
wherein additional dimensions by which possible hotels are generated include Structured Hotel Attributes (see appendix Hotel Attributes):
ability to get a partial refund,
ability to get a full refund,
ability to choose a view,
time of check-in,
time of check-out;
whether breakfast is included;
whether the user is paying in cash or using points; and
whether any discounts apply;
unstructured hotel attributes as defined in appendix hotel attributes;
user reviews, floors, location of the rooms within the hotel; and translating user input like kids friendly, family friendly, best for business travel, etc.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
generating at least one additional prompt that differs from the prompt in at least one of the at least one example shot or the query metadata;
inputting at least one additional prompt into the language model;
receiving, from the language model and in response to the at least one additional prompt, at least one respective additional hotel query reflecting the user intention;
scoring the hotel query and the at least one additional hotel query; and
selecting a top scoring hotel query from among the all possibly generated hotels.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
sampling a prior probability distribution of the trained machine learning model to generate sampled prior probability distributions for the prompt and the at least one additional prompt; and
using the sampled prior probability distributions as parameters of the trained machine learning model in generating the query metadata and selecting the example shots for the prompt and the at least one additional prompt.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
wherein the set of possible hotels that is best match to the hotel query includes structured and unstructured hotel attributes defined in Appendix – Hotel Attributes; user data of a user’s hotel preferences, external context, as well as hotel preferences based on metadata of that user, such as location of the user, time of the hotel travel query, income level, hotel location, and hotel availability and many variables relating to hotels.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
wherein synthetic data is generated using a synthesizer build; and
wherein the synthetic data is utilized to train the machine learning model.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
wherein training data is from all available hotels from a city of the hotel query, including but not limited to (see appendix Hotel Attributes for complete list) guest type, as in adult or child; number of beds; nearby airports; room class, as in standard, premium, or luxury class; ability to get a partial refund; ability to get a full refund; ability to choose a view; time of check-in; time of check-out; whether breakfast is included; whether the user is paying in cash or using points; whether any discounts apply; user data of a user’s hotel preferences, as well as hotel preferences based on metadata of that user, such as location of the user, time of the hotel travel query, income level, hotel location, and hotel availability and many variables relating to hotels; and surrounding cities from the city of the hotel query.

### Claim 12 (depends on 1)

The method of claim 1, further comprising:
wherein training data is from all available searches of hotels conducted by the user.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
wherein training data is from synthetic data that is based on:
wherein training data is from all available hotels from a city of the hotel query, including surrounding cities from the city of the hotel query; and
all available searches of hotels conducted by the user.

### Claim 14

A computer-implemented method to plan to book hotels utilizing artificial intelligence from unstructured user input with a large language model (LLM), the method comprising:
receiving, at a computer system, an input hotel query reflecting a user intention;
wherein a machine learning model has been trained based on user data of a user’s hotel preferences, as well as hotel preferences based on metadata of that user, such as location of the user, time of the hotel query, income level, location of the hotel, and many variables relating to hotels;
analyzing the input hotel query using the trained machine learning model;
generating possible hotels in terms of dates, guest type, as in adult or child; number of beds; nearby airports; room class, as in standard, premium, or luxury class; ability to get a partial refund; ability to get a full refund; ability to choose a view; time of check-in; time of check-out; whether breakfast is included; whether the user is paying in cash or using points; whether any discounts apply; user data of a user’s hotel preferences, as well as hotel preferences based on metadata of that user, such as location of the user, time of the hotel travel query, income level, hotel location, and hotel availability and many variables relating to hotels; based on the input hotel query and the user’s hotel preferences; wherein the machine learning model utilizes a natural language understanding and probabilistic model;
wherein artificial intelligence to understand the user intent is to find the best semantic matches to the user input, external context, hotel attributes and the available hotel inventory; and
wherein training data is from all available hotels from a city of the hotel query, including surrounding cities from the city of the hotel query and from all available searches of hotels conducted by the user.

### Claim 15 (depends on 14)

The method of claim 14,
wherein additional dimensions by which possible hotels are generated include:
guest type, as in adult or child;
number of beds;
room class, as in standard, premium, or luxury class.

### Claim 16 (depends on 14)

The method of claim 14,
wherein additional dimensions by which possible hotels are generated include:
ability to get a partial refund,
ability to get a full refund,
ability to choose a view,
time of check-in,
time of check-out;
whether breakfast is included;
whether the user is paying in cash or using points; and
whether any discounts apply;
amenities and other semantic similarities to the user request;
user reviews, floors, location of the rooms within the hotel; and translating user input like kids friendly, family friendly, best for business travel, etc. (see complete list in Unstructured Hotel Attributes in appendix hotel attributes).

### Claim 17

A computer-implemented system to plan to book hotels utilizing artificial intelligence from unstructured user input with a small language model (“SLM”), the method comprising:
receiving, at a computer system, an input hotel query reflecting a user intention;
wherein a machine learning model has been trained based on user data of a user’s hotel preferences, as well as hotel preferences based on metadata of that user, such as location of the user, time of the hotel query, income level, hotel location, and hotel availability and many variables relating to hotels;
analyzing the input hotel query using the trained machine learning model;
generating possible hotels in terms of dates, based on the input hotel query, external context, hotel attributes and the user’s hotel preferences; and
wherein the machine learning model utilizes a natural language understanding and probabilistic model.

### Claim 18 (depends on 17)

The system of claim 17,
wherein additional dimensions by which possible hotels are generated include:
guest type, as in adult or child;
number of beds;
room class, as in standard, premium, or luxury class.

### Claim 19 (depends on 17)

The system of claim 17,
wherein additional dimensions by which possible hotels are generated include:
ability to get a partial refund,
ability to get a full refund,
ability to choose a view,
time of check-in,
time of check-out;
whether breakfast is included;
whether the user is paying in cash or using points; and
whether any discounts apply;
amenities and other semantic similarities to the user request;
user reviews, floors, location of the rooms within the hotel; and
translating user input like kids friendly, family friendly, best for business travel, etc. (see complete list in Unstructured Hotel Attributes in appendix hotel attributes).

### Claim 20 (depends on 17)

The system of claim 17, further comprising:
wherein training data is from synthetic data that is based on:
all available hotels from a city of the hotel query, including surrounding cities from the city of the hotel query; and
all available searches of hotels conducted by the user.
