Semantic-free text analysis for identifying traits

Patent metadata

Field	Value
Publication number	US-9508360-B2
Application number	US-201414288751-A
Country	US
Kind code	B2
Filing date	May 28, 2014
Priority date	May 28, 2014
Publication date	Nov 29, 2016
Grant date	Nov 29, 2016

Abstract

A method, system, and/or computer program product uses speech traits of an entity to predict a future state of the entity. Units of speech are collected from a stream of speech that is generated by a first entity. Tokens from the stream of speech are identified, where each token identifies a particular unit of speech from the stream of speech, and where identification of the tokens is semantic-free. Nodes in a first speech graph are populated with the tokens, and a first shape of the first speech graph is identified. The first shape is matched to a second shape, where the second shape is of a second speech graph from a second entity in a known category. The first entity is assigned to the known category, and a future state of the first entity is predicted based on the first entity being assigned to the known category.

First claim

What is claimed is:

1. A method of predicting a future state of an entity, the method comprising:
collecting, by one or more processors, units of speech from a stream of speech, wherein the stream of speech is generated by a first entity;
identifying, by one or more processors, tokens from the stream of speech, wherein each token identifies a particular unit of speech from the stream of speech, and wherein identification of the tokens is semantic-free such that the tokens are identified independently of a semantic meaning of a respective unit of speech;
populating, by one or more processors, nodes in a first speech graph with the tokens;
identifying, by one or more processors, a first shape of the first speech graph;
matching, by one or more processors, the first shape to a second shape, wherein the second shape is of a second speech graph from a second entity in a known category;
assigning, by one or more processors, the first entity to the known category in response to the first shape matching the second shape; and
predicting, by one or more processors, a future state of the first entity based on the first entity being assigned to the known category.

2. The method of claim 1 , further comprising:
assigning, by one or more processors, the future state to a future state node for use in an activity graph;
identifying, by one or more processors, a cohort whose members are in the known category;
identifying, by one or more processors, activity graphs for the members of the cohort, wherein each of the activity graphs includes the future state node and a subsequent node that describes a mitigation action to mitigate the future state; and
transmitting, by one or more processors, a recommendation to the first entity to implement the mitigation action.

3. The method of claim 1 , wherein the entity is a person, wherein the future state is a future action performed by the person, and wherein the method further comprises:
determining, by one or more processors, an efficacy of a particular action in reaching a predetermined desired state by members of a cohort, wherein the particular action is from a group of actions performed by one or more members of the cohort;
identifying, by one or more processors, a preferred action that has a highest efficacy compared to other actions from the group of actions; and
transmitting, by one or more processors, a recommendation to perform the preferred action as the future action performed by the person.

4. The method of claim 3 , further comprising:
comparing, by one or more processors, a pre-action speech graph for members of the cohort to a post-action speech graph, wherein the pre-action speech graph is based on non-contextual speech patterns of the members of the cohort before taking the particular action, and wherein the post-action speech graph is based on non-contextual speech patterns of the members of the cohort after taking the particular action; and
identifying, by one or more processors, the preferred action based on a change in a shape of the pre-action speech graph and a shape of the post-action speech graph.

5. The method of claim 1 , further comprising:
defining, by one or more processors, the first shape of the first speech graph according to a size of the first speech graph, a quantity of loops in the first speech graph, sizes of the loops in the first speech graph, distances between nodes in the first speech graph, and a level of branching between the nodes in the first speech graph.

6. The method of claim 1 , wherein the first entity is a person, wherein the stream of speech is a stream of spoken words from the person, and wherein the method further comprises:
receiving, by one or more processors, a physiological measurement of the person from a sensor, wherein the physiological measurement is taken while the person is speaking the spoken words;
analyzing, by one or more processors, the physiological measurement of the person to identify a current emotional state of the person; and
modifying, by one or more processors, the first shape of the first speech graph according to the current emotional state of the person.

7. The method of claim 1 , wherein the first entity is a group of persons, wherein the stream of speech is a stream of written texts from the group of persons, and wherein the method further comprises:
analyzing, by one or more processors, the written texts from the group of persons to identify a current emotional state of the group of persons;
modifying, by one or more processors, the first shape of the first speech graph according to the current emotional state of the group of persons; and
adjusting, by one or more processors, a predicted future state of the group of persons based on a modified first shape of the first speech graph of the group of persons.

8. The method of claim 1 , wherein the first entity is a person, wherein the stream of speech is composed of words spoken by the person, and wherein the method further comprises:
generating, by one or more processors, a syntactic vector ({right arrow over (w)} syn ) of the words, wherein the syntactic vector describes a lexical class of each of the words;
creating, by one or processors, a hybrid graph (G) by combining the first speech graph and a semantic graph of the words spoken by the person, wherein the hybrid graph is created by:
converting, by one or more processors operating as a semantic analyzer, the words into semantic vectors, wherein a semantic similarity (sim(a,b)) between two words a and b are estimated by a scalar product (•) of their respective semantic vectors ({right arrow over (w)} a ·{right arrow over (w)} b ), such that:
sim ( a,b )= {right arrow over (w)} a ·{right arrow over (w)} b ; and

creating, by one or more processors, the hybrid graph (G) of the first speech graph and the semantic graph, where:
G={N,E,{right arrow over (W)}}

wherein N are nodes, in the hybrid graph, that represent words, E represents edges that represent temporal precedence in the stream of speech, and {right arrow over (W)} is a feature vector, for each node in the hybrid graph, and wherein {right arrow over (W)} is defined as a direct sum of the syntactic vector ({right arrow over (w)} syn ) and semantic vectors ({right arrow over (w)} sem ), plus an additional direct sum of non-textual features ({right arrow over (w)} ntxt ) of the person speaking the words, such that:
{right arrow over (W)}={right arrow over (w)} syn ⊕{right arrow over (w)} sem ⊕{right arrow over (w)} ntxt .

9. The method of claim 1 , wherein the stream of speech comprises spoken non-language gestures from the first entity.

10. A computer program product for predicting a future state of an entity, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code readable and executable by a processor to perform a method comprising:
collecting units of speech from a stream of speech, wherein the stream of speech is generated by a first entity;
identifying tokens from the stream of speech, wherein each token identifies a particular unit of speech from the stream of speech, and wherein identification of the tokens is semantic-free such that the tokens are identified independently of a semantic meaning of a respective unit of speech;
populating nodes in a first speech graph with the tokens;
identifying a first shape of the first speech graph;
matching the first shape to a second shape, wherein the second shape is of a second speech graph from a second entity in a known category;
assigning the first entity to the known category in response to the first shape matching the second shape; and
predicting a

Assignees

• IBM

Inventors

• Allam Sushmita L
• Cecchi Guillermo A
• Gundugola Srinivas
• Kozloski James R
• Pickover Clifford A
• Rish Irina

Classifications

• G10L25/63 Primary

  for estimating an emotional state · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L25/48 Primary

  specially adapted for particular use · CPC title

• G10L25/27

  characterised by the analysis technique · CPC title