# US 10,503,829 B2 · Book analysis and recommendation

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

- Number: US 10,503,829 B2
- Document ID: US10503829B2
- Status: Granted
- Kind: B2
- Application number: 15/782,367
- Filed: 2017-10-12
- Published: 2018-04-19
- Granted: 2019-12-10
- Earliest claimed: 2016-10-13
- Assignees: Booxby Inc.; University of Houston System
- Applicants: Booxby Inc.
- Inventors: Holly Lynn Payne; Mark Fielding Bregman; Bogart Vargas; Thamar Solorio; Suraj Maharjan; Sudipta Kar
- Web page: https://patentgrep.com/patent/US10503829B2

## CPC

- G06F 40/253: Grammatical analysis; Style critique
- G06F 16/24578: {using ranking}
- G06F 16/35: Clustering; Classification
- G06F 16/383: using metadata automatically derived from the content
- G06F 16/94: {Hypermedia (Hyperlinking G06F40/134)}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/9536: Search customisation based on social or collaborative filtering
- G06F 40/205: Parsing
- G06F 40/242: Dictionaries
- G06F 40/30: Semantic analysis
- G06F 40/56: Natural language generation
- G06N 3/09: Supervised learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 30/0241: Advertisements
- G06Q 30/0251: Targeted advertisements
- G06Q 30/0631: {Recommending goods or services}
- G06N 3/045: Combinations of networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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 method includes generating style values and experiential language tags (ELTs) for a plurality of books based on retrieved book content and reader reviews, respectively. The method further includes generating an ELT prediction model based on the style values and the ELTs. The ELT prediction model is configured to receive a set of style values for a new book and output a set of predicted ELTs for the new book, the set of predicted ELTs indicating predicted reader experiences with the new book. The method further includes receiving user-submitted book content from a remote user device, determining style values for the user-submitted book content, and determining a list of predicted ELTs for the user-submitted book content using the style values for the user-submitted book content and the ELT prediction model. Additionally, the method includes transmitting, to the user device, the list of predicted ELTs for the user-submitted book content.

## Claims

### Claim 1

A method comprising:
retrieving, at a computing device, book content and reader reviews for a plurality of books, wherein the book content for each book includes an author's written portion of the book;
generating, at the computing device, style values for each of the plurality of books based on the retrieved book content, wherein the style values for each book indicate the author's writing style for the book;
generating, at the computing device, experiential language tags (ELTs) for each of the plurality of books based on the retrieved reader reviews, wherein the ELTs for each book indicate one or more readers' experiences with the book;
generating, at the computing device, an ELT prediction model based on the style values and the ELTs for the plurality of books, wherein the ELT prediction model is configured to receive a set of style values for a new book and output a set of predicted ELTs for the new book, the set of predicted ELTs indicating predicted reader experiences with the new book;
receiving, at the computing device, user-submitted book content from a remote user device;
determining, at the computing device, style values for the user-submitted book content;
determining, at the computing device, a list of predicted ELTs for the user-submitted book content using the style values for the user-submitted book content and the ELT prediction model; and
transmitting, to the user device, the list of predicted ELTs for the user-submitted book content.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
identifying, at the computing device, a list of comparable books from the plurality of books based on the style values associated with the comparable books and the style values associated with the user-submitted book content; and
transmitting, to the user device, the list of comparable books.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
generating, at the computing device, a filtered list of comparable books by removing books from the list of comparable books that are not associated with predicted ELTs of the user-submitted book content; and
transmitting, to the user device, the filtered list of comparable books.

### Claim 4 (depends on 2)

The method of claim 2, further comprising:
arranging, at the computing device, the list of comparable books based on the ELTs associated with the comparable books and the predicted ELTs associated with the user-submitted book content; and
transmitting, to the user device, the arranged list of comparable books.

### Claim 5 (depends on 1)

The method of claim 1, wherein the style values include at least one of a readability style value and a writing density style value.

### Claim 6 (depends on 1)

The method of claim 1, wherein the ELTs include one or more words describing an emotional experience.

### Claim 7 (depends on 1)

The method of claim 1, wherein the ELTs include one or more words describing qualities of the book that create an experience for the readers.

### Claim 8 (depends on 1)

The method of claim 1, wherein generating the ELTs for each of the plurality of books comprises:
identifying words included in the reader reviews for the book that match words included in an ELT dictionary; and
assigning the matching words in the ELT dictionary to the book.

### Claim 9 (depends on 8)

The method of claim 8, wherein the ELT dictionary includes a set of assignable ELTs, wherein each of the assignable ELTs maps to a plurality of additional ELTs, and wherein assigning the matching words to the book comprises:
mapping a subset of the matching words in the ELT dictionary to a single assignable ELT; and
assigning the single assignable ELT to the book.

### Claim 10 (depends on 1)

The method of claim 1, wherein generating the ELT prediction model comprises generating a supervised machine learning model using the style values and the ELTs generated from the retrieved book content and reader reviews.

### Claim 11

A system comprising:
a book data store configured to store a plurality of book records for a plurality of books; and
one or more computing devices configured to:
retrieve book content and reader reviews for the plurality of books, wherein the book content for each book includes an author's written portion of the book;
generate style values for each of the plurality of books based on the retrieved book content, wherein the style values for each book indicate the author's writing style for the book;
generate experiential language tags (ELTs) for each of the plurality of books based on the retrieved reader reviews, wherein the ELTs for each book indicate one or more readers' experiences with the book;
store the generated style values and generated ELTs in the book records;
generate an ELT prediction model based on the style values and ELTs for the plurality of books, wherein the ELT prediction model is configured to receive a set of style values for a new book and output a set of predicted ELTs for the new book, the set of predicted ELTs indicating predicted reader experiences with the new book;
receive user-submitted book content from a remote user device;
determine style values for the user-submitted book content;
determine a list of predicted ELTs for the user-submitted book content using the style values for the user-submitted book content and the ELT prediction model; and
transmit, to the user device, the list of predicted ELTs for the user-submitted book content.

### Claim 12 (depends on 11)

The system of claim 11, wherein the one or more computing devices are configured to:
identify a list of comparable books from the plurality of books based on the style values associated with the comparable books and the style values associated with the user-submitted book content; and
transmit, to the user device, the list of comparable books.

### Claim 13 (depends on 12)

The system of claim 12, wherein the one or more computing devices are configured to:
generate a filtered list of comparable books by removing books from the list of comparable books that are not associated with predicted ELTs of the user-submitted book content; and
transmit, to the user device, the filtered list of comparable books.

### Claim 14 (depends on 12)

The system of claim 12, wherein the one or more computing devices are configured to:
arrange the list of comparable books based on the ELTs associated with the comparable books and the predicted ELTs associated with the user-submitted book content; and
transmit, to the user device, the arranged list of comparable books.

### Claim 15 (depends on 11)

The system of claim 11, wherein the style values include at least one of a readability style value and a writing density style value.

### Claim 16 (depends on 11)

The system of claim 11, wherein the ELTs include one or more words describing an emotional experience.

### Claim 17 (depends on 11)

The system of claim 11, wherein the ELTs include one or more words describing qualities of the book that create an experience for the readers.

### Claim 18 (depends on 11)

The system of claim 11, wherein the one or more computing devices are configured to generate the ELTs for each of the plurality of books by:
identifying words included in the reader reviews for the book that match words included in an ELT dictionary; and
assigning the matching words in the ELT dictionary to the book.

### Claim 19 (depends on 18)

The system of claim 18, wherein the ELT dictionary includes a set of assignable ELTs, wherein each of the assignable ELTs maps to a plurality of additional ELTs, and wherein the one or more computing devices are configured to assign the matching words to the book by:
mapping a subset of the matching words in the ELT dictionary to a single assignable ELT; and
assigning the single assignable ELT to the book.

### Claim 20 (depends on 11)

The system of claim 11, wherein the one or more computing devices are configured to generate the ELT prediction model by generating a supervised machine learning model using the style values and the ELTs generated from the retrieved book content and reader reviews.