# US 10,503,768 B2 · Analogic pattern determination

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

- Number: US 10,503,768 B2
- Document ID: US10503768B2
- Status: Granted
- Kind: B2
- Application number: 15/287,154
- Filed: 2016-10-06
- Published: 2018-04-12
- Granted: 2019-12-10
- Earliest claimed: 2016-10-06
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Corville O. Allen; Andrew R. Freed
- Web page: https://patentgrep.com/patent/US10503768B2

## CPC

- G06F 16/3344: {using natural language analysis}
- G06F 40/30: Semantic analysis
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. An analogy list is obtained, each analogy within the analogy list having a known meaning, and receiving an analogy phrase. A verb is identified within the phrase and a verb definition list is generated. A subject is identified within the phrase and a subject definition list is generated. An adjective is identified within the phrase and an adjective definition list is generated, including filtering adjectives to accept adjective definitions associated with the identified subject. A set of outcomes is identified, incorporating the verb definition, subject definition, and adjective definition, and a corpus is searched for evidentiary use. The outcomes are ranked in accordance to evidentiary use found in the corpus the highest ranked outcome is outputted.

## Claims

### Claim 1

A computer system comprising:
a processing unit operatively coupled to memory;
an artificial intelligence platform, in communication with the processing unit;
a tool in communication with the processing unit to decipher a phrase upon activation by the artificial intelligence platform, including:
obtaining an analogy list, each analogy within the analogy list having a known meaning;
receiving an analogy phrase;
parsing the analogy phrase to identify a term and a structure in the phrase;
generating a definition list for the identified term and structure;
identifying a set of outcomes, each outcome in the outcome set incorporating each identified term and structure and the generated definition list;
for each outcome in the identified outcome set, searching a corpus for evidentiary use;
ranking entries in the outcome set in accordance to an amount of evidentiary use found in the corpus;
outputting at least one outcome from the outcome set with the highest ranking; and
deriving an intended idiomatic meaning of the received analogy phrase from the outputted outcome.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein ranking entries in the outcome set includes applying a high rank for a high amount of evidentiary use found in the corpus.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein ranking entries in the outcome set includes applying a low rank for a low amount of evidentiary use found in the corpus.

### Claim 4

A computer program product for deciphering a phrase, the computer program product comprising a computer readable storage device having program code embodied therewith, the program code executable by a processing unit to:
obtain an analogy list, each analogy within the analogy list having a known meaning;
receive an analogy phrase;
parse the analogy phrase to identify a term and a structure in the phrase;
generate a definition list for the identified term and structure;
identify a set of outcomes, each outcome in the outcome set incorporating each identified term and structure and the generated definition list;
for each outcome in the identified set, search a corpus for evidentiary use;
rank entries in the outcome set in accordance to an amount of evidentiary use found in the corpus;
output at least one outcome from the outcome set with the highest ranking; and
derive an intended idiomatic meaning of the received analogy phrase from the outputted outcome.

### Claim 5 (depends on 4)

The computer program product of claim 4, wherein ranking entries in the outcome set includes applying a high rank for a high amount of evidentiary use found in the corpus.

### Claim 6 (depends on 4)

The computer program product of claim 4, wherein ranking entries in the outcome set includes applying a low rank for a low amount of evidentiary use found in the corpus.

### Claim 7

A method for utilizing an information handling system comprising a processor and memory to decipher a phrase, the method comprising:
obtaining an analogy list, each analogy within the analogy list having a known meaning;
receiving an analogy phrase;
parsing the analogy phrase to identify a term and a structure in the phrase;
generating a definition list for the identified term and structure;
identifying a set of outcomes, each outcome in the outcome set incorporating each identified term and structure and the generated definition list;
for each outcome in the identified outcome set, searching a corpus for evidentiary use;
ranking entries in the outcome set in accordance to an amount of evidentiary use found in the corpus;
outputting at least one outcome from the outcome set with the highest ranking; and
deriving an intended idiomatic meaning of the received analogy phrase from the outputted outcome.

### Claim 8 (depends on 7)

The method of claim 7, wherein ranking entries in the outcome set includes applying a high rank for a high amount of evidentiary use found in the corpus.

### Claim 9 (depends on 7)

The method of claim 7, wherein ranking entries in the outcome set includes applying a low rank for a low amount of evidentiary use found in the corpus.