# US 2021/0200954 A1 · Sentence phrase generation

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

- Number: US 2021/0200954 A1
- Document ID: US20210200954A1
- Status: Published application
- Kind: A1
- Application number: 16/730,093
- Filed: 2019-12-30
- Published: 2021-07-01
- Earliest claimed: 2019-12-30
- Assignees: Accenture Global Solutions Limited
- Applicants: Accenture Global Solutions Limited
- Inventors: Shaun DSOUZA; Subhashini LAKSHMINARAYANAN; Gopali RAVAL CONTRACTOR
- Web page: https://patentgrep.com/patent/US20210200954A1

## CPC

- G06F 40/30: Semantic analysis
- G06F 16/2228: {Indexing structures}
- G06F 16/243: {Natural language query formulation}
- G06F 40/279: Recognition of textual entities
- G06N 3/008: based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/04: Inference or reasoning models
- G06N 5/041: {Abduction}
- G06N 20/00: Machine learning
- G06F 40/205: Parsing
- G06F 40/295: Named entity recognition
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Examples of a sentence phrasing system are provided. The system may obtain a user question from a user. The system may obtain question entailment data from a plurality of data sources. The system may implement an artificial intelligence component to identify a word index from the question entailment data and to identify a question premise from the user question. The system may implement a first cognitive learning operation to determine an answer premise corresponding to the question premise comprising a second-word data set. The system may determine a subject component corresponding to the question premise. The system may generate an object component and a predicate component from the second-word data set corresponding to the subject component. The system may generate an integrated answer relevant for resolving the user question and comprising the subject component, the object component, and the predicate component concatenated to form an answer sentence.

## Claims

### Claim 1

A system comprising:
a processor;
a question data organizer coupled to the processor, the question data organizer to:
obtain a query from a user, the query indicating a data entailment requirement comprising a user question; and
obtain question entailment data associated with the user question from a plurality of data sources;
implement an artificial intelligence component to:
identify a word index from the question entailment data, the word index including a plurality of words being associated with the data entailment requirement; and
identify a question premise from the user question, the question premise comprising a first word data set associated with the word index;
an answer creator coupled to the processor, the answer creator to implement a first cognitive learning operation to:
determine an answer premise corresponding to the question premise, the answer premise comprising a second-word data set and indicating an inference associated with the user question, the second-word data set being associated with the word index; and
a modeler coupled to the processor, the modeler to implement a second cognitive learning operation to:
determine a subject component from the second-word data set, the subject component indicating one of a person, a place, a thing, and an idea associated with the question premise;
determine an object component from the second-word data set, the object component indicating one of the person, the place, the thing, and the idea associated with the subject component;
determine a predicate component from the second-word data set, the predicate component indicating an action associated with the subject component; and
generate an integrated answer relevant for resolving the user question, the integrated answer comprising the subject component, the object component, and the predicate component associated with the question premise concatenated to form an answer sentence.

### Claim 2 (depends on 1)

The system as claimed in claim 1, wherein the artificial intelligence component is to map the plurality of words from the user question with a text corpus to identify the word index, the plurality of data sources comprising the text corpus.

### Claim 3 (depends on 1)

The system as claimed in claim 1, wherein the question data organizer implements the artificial intelligence component to assign a numeral symbol to each of the words in the word index.

### Claim 4 (depends on 3)

The system as claimed in claim 3, wherein the modeler implements the second cognitive learning operation to map the numeral symbol for each of the words in the word index with the first word data set to determine a question premise index and with the second-word data set to determine an answer premise index.

### Claim 5 (depends on 1)

The system as claimed in claim 1, wherein the answer creator implements the first cognitive learning operation to create an answer map associated with the question premise by mapping the second-word data set with the first word data set.

### Claim 6 (depends on 1)

The system as claimed in claim 1, wherein the modeler creates a user question library comprising the user question and the answer sentence associated with the user question.

### Claim 7 (depends on 6)

The system as claimed in claim 6, wherein the modeler deploys the user question library for generating an answer for a subsequent query.

### Claim 8

A method comprising:
obtaining, by a processor, a query from a user, the query indicating a data entailment requirement comprising a user question;
obtaining, by the processor, question entailment data associated with the user question from a plurality of data sources;
implementing, by the processor, an artificial intelligence component to:
identify a word index from the question entailment data, the word index including a plurality of words being associated with the data entailment requirement; and
identify a question premise from the user question, the question premise comprising a first word data set associated with the word index;
implementing, by the processor, a first cognitive learning operation to determine an answer premise corresponding to the question premise, the answer premise comprising a second-word data set and indicating an inference associated with the user question, the second-word data set being associated with the word index; and
implementing, by the processor, a second cognitive learning operation to:
determine a subject component from the second-word data set, the subject component indicating one of a person, a place, a thing, and an idea associated with the question premise;
determine an object component from the second-word data set, the object component indicating one of the person, the place, the thing, and the idea associated with the subject component;
determine a predicate component from the second-word data set, the predicate component indicating an action associated with the subject component; and
generate an integrated answer relevant for resolving the user question, the integrated answer comprising the subject component, the object component, and the predicate component associated with the question premise concatenated to form an answer sentence.

### Claim 9 (depends on 8)

The method as claimed in claim 8, wherein identifying the word index further comprises mapping the plurality of words from the user question with a text corpus to identify the word index, the plurality of data sources comprising the text corpus.

### Claim 10 (depends on 8)

The method as claimed in claim 8, wherein the method further comprises implementing, by the processor, the artificial intelligence component to assign a numeral symbol to each of the words in the word index.

### Claim 11 (depends on 10)

The method as claimed in claim 10, wherein the method further comprises implementing, by the processor, the second cognitive learning operation to map the numeral symbol for each of the words in the word index with the first word data set to determine a question premise index and with the second-word data set to determine an answer premise index.

### Claim 12 (depends on 8)

The method as claimed in claim 8, wherein the method further comprises implementing, by the processor, the first cognitive learning operation to create an answer map associated with the question premise by mapping the second-word data set with the first word data set.

### Claim 13 (depends on 8)

The method as claimed in claim 8, wherein the method further comprises creating, by the processor, a user question library comprising the user question and the answer sentence associated with the user question.

### Claim 14 (depends on 13)

The method as claimed in claim 13, wherein the method further comprises deploying, by the processor, the user question library for generating an answer for a subsequent query.

### Claim 15

A non-transitory computer readable medium including machine readable instructions that are executable by a processor to:
obtaining a query from a user, the query indicating a data entailment requirement comprising a user question;
obtain question entailment data associated with the user question from a plurality of data sources;
implement an artificial intelligence component to:
identify a word index from the question entailment data, the word index including a plurality of words being associated with the data entailment requirement; and
identify a question premise from the user question, the question premise comprising a first word data set associated with the word index;
implement a first cognitive learning operation to determine an answer premise corresponding to the question premise, the answer premise comprising a second-word data set and indicating an inference associated with the user question, the second-word data set being associated with the word index; and
implement a second cognitive learning operation to:
determine a subject component from the second-word data set, the subject component indicating one a person, a place, a thing, and an idea associated with the question premise;
determine an object component from the second-word data set, the object component indicating one of the person, the place, the thing, and the idea associated with the subject component;
determine a predicate component from the second-word data set, the predicate component indicating an action associated with the subject component; and
generate an integrated answer relevant for resolving the user question, the integrated answer comprising the subject component, the object component, and the predicate component associated with the question premise concatenated to form an answer sentence.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein identifying the word index further comprises mapping the plurality of words from the user question with a text corpus to identify the word index, the plurality of data sources comprising the text corpus.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the processor is to implement the artificial intelligence component to assign a numeral symbol to each of the words in the word index.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the processor is to implement the second cognitive learning operation to map the numeral symbol for each of the words in the word index with the first word data set to determine a question premise index and with the second-word data set to determine an answer premise index.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the processor is to implement the first cognitive learning operation to create an answer map associated with the question premise by mapping the second-word data set with the first word data set.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the processor is to create a user question library comprising the user question and the answer sentence associated with the user question and deploy the user question library for generating an answer for a subsequent query.
