Categorizing concept terms for game-based training in cognitive computing systems

Patent metadata

Field	Value
Publication number	US-10896377-B2
Application number	US-201514919819-A
Country	US
Kind code	B2
Filing date	Oct 22, 2015
Priority date	Sep 10, 2015
Publication date	Jan 19, 2021
Grant date	Jan 19, 2021

Abstract

A first list that includes a first set of one or more concept terms may be obtained. The first set of one or more concept terms may be candidates for being conceptually related to a seed concept term. Prior to the obtaining, a first client computing device may provide a first plurality of individual characters and the seed concept term to a first user using the first client computing device. The first client computing device may prompt the first user to generate the first set of one or more concept terms that are conceptually related to the seed concept term using one or more of the first plurality of individual characters. In response to the obtaining, one or more particular categories to which each of the first set of one or more concept terms belongs to may be determined.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
obtaining, by a cognitive computing system including a natural language processing system, a first list that includes a first set of one or more concept terms from an information corpora of the cognitive computing system, the first set of one or more concept terms are transmitted from a first client computing device to the cognitive computing system, the first set of one or more concept terms are candidates for being conceptually related to a seed concept term, wherein prior to the obtaining, the first client computing device provides a first plurality of individual characters and the seed concept term to a first user using the first client computing device, the first client computing device prompts the first user to generate a second set of one or more concept terms that are conceptually related to the seed concept term using one or more of the first plurality of individual characters;
determining, by the natural language processing system and in response to the obtaining, one or more particular categories to which each of the first set of one or more concept terms belongs, wherein each of the particular categories is a distinct class that includes an identification, the identification describes a specific meaning for each of the first set of one or more concept terms;
associating, in response to the determining that one or more particular categories to which each of the first set of one or more concept terms belongs, at least one of the second set of one or more concept terms with the one or more particular categories of the first set of one or more concept terms;
causing, in response to the associating the second set of one or more concept terms with the one or more particular categories of the first set of one or more concept terms, the client computing device to increase a game score for the first user by a first amount, the game score corresponding to a point total earned by the first user for generating the second set of one or more concept terms;
determining that at least one of the particular categories is a new category that the cognitive computing system has not yet generated;
associating, in response to the determining that at least one of the particular categories is a new category, at least one of the second set of one or more concept terms with the new category;
causing, in response to the associating at least one of the second set of one or more concept terms with the new category, the client computing device to further increase the game score for the first user by a second amount that is different than the first amount; and
training the cognitive computing system by updating the first set of one or more concept terms in the information corpora to include one or more of the second set of one or more concept terms that the cognitive computing system can use for a subsequent execution of the method.

2. The method of claim 1 , wherein the determining one or more particular categories includes:
identifying a first definition for each of the first set of one or more concept terms, the first definition including a first part of speech;
identifying a second definition for the seed concept term, the second definition including a second part of speech;
determining, by at least comparing the first definition with the second definition, a relationship between the seed concept and each of the first set of one or more concepts; and
determining the one or more particular categories based on at least the determining a relationship.

3. The method of claim 1 , further comprising:
causing, by the cognitive computing system, the first client computing device to provide a second plurality of individual characters;
causing, by the cognitive computing system, the first client computing device to provide one of the first set of concept terms; and
causing, by the cognitive computing system, the first client computing device to provide the seed concept term, wherein the first client computing device prompts the first user to generate a second set of one or more concept terms that are within a same category as the one of the first set of concept terms term using one or more of the second plurality of individual characters.

4. The method of claim 3 , further comprising:
obtaining, by the cognitive computing system, a second list from the first client computing device, the second list including the second set of one or more concept terms;
identifying, by the cognitive computing system, a domain associated with the one or more particular categories, the domain corresponding to a field of knowledge;
identifying, by the cognitive computing system, a subject matter expertise of the first user;
comparing, by the cognitive computing system, the subject matter expertise of the first user with the domain; and
providing a validity score for the second set of one or more concept terms based on the comparing the subject matter expertise of the first user with the domain, the validity score corresponding to scoring the second set of one or more concept terms to determine whether the second set of one or more concept terms are utilized by the cognitive computing system for concept expansion, and wherein concept expansion is a process of inputting a set of seed concept terms that are expanded by the cognitive computing system to a more complete set of concept terms.

5. The method of claim 3 , further comprising:
causing, by the cognitive computing system and prior to the causing the first client computing device to provide a second plurality of individual characters, the first client computing device to display the one or more particular categories to which each of the first set of one or more concept terms belongs; and
causing, by the cognitive computing system and prior to the causing the first client computing device to provide a second plurality of individual characters, the first client computing device to display the each of the first set of one or more concept terms.

6. The method of claim 1 , further comprising:
determining that the second set of one or more concept terms does not include all of the first set of one or more concept terms;
causing, in response to the determining that the second set of one or more concept terms does not include all of the first set of one or more concept terms, the client computing device to decrease the game score for the first user.

7. A system comprising:
a computing device having a processor; and
a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the processor to cause the system to:
display a first plurality of individual characters;
display a first seed concept term, the first seed concept term to train a cognitive computing system including a natural language processing system, wherein the cognitive computing system analyzes the first seed concept term to generate a first set of one or more concept terms from an information corpora of the cognitive computing system that are candidates for being conceptually related to the first seed concept term;
display a particular concept term of a second set of one or more concept terms, wherein the particular concept term is generated by a first user, the particular concept term is assigned to a particular category by the natural language processing system, wherein the particular category is a distinct class that includes an identification, the identification describes a specific meaning for the particular concept term;
prompt the first user to generate a third set of one or more concept terms that are within the particular category as the particular concept term using one or more of the first plurality of individual characters;
provide a game score to

Assignees

• IBM

Inventors

• Allen Corville O
• Boinodiris Phaedra
• Kozhaya Joseph N
• Madison Christopher M
• Sudarsan Sridhar

Classifications

• A63F13/79

  involving player-related data, e.g. identities, accounts, preferences or play histories · CPC title

• A63F13/35

  Details of game servers · CPC title

• G06F16/36

  Creation of semantic tools, e.g. ontology or thesauri · CPC title

• A63F13/46

  Computing the game score · CPC title

• G06F16/3344

  using natural language analysis · CPC title