Natural language eminence based robotic agent control

Patent metadata

Field	Value
Publication number	US-2019005329-A1
Application number	US-201816020611-A
Country	US
Kind code	A1
Filing date	Jun 27, 2018
Priority date	Jun 29, 2017
Publication date	Jan 3, 2019
Grant date	—

Abstract

In some examples, natural language eminence based robotic agent control may include ascertaining, by a robotic agent, an image of an object or an environment, and ascertaining a plurality of natural language insights for the image. For each insight of the plurality of insights, an eminence score may be generated, and each insight of the plurality of insights may be ranked according to the eminence scores. An operation associated with the robotic agent, the object, or the environment may be controlled by the robotic agent and based on a highest ranked insight.

First claim

What is claimed is:

1 . A natural language eminence based robotic agent control apparatus comprising:
an insight analyzer, executed by at least one hardware processor, to
ascertain, by a robotic agent, an image of an object or an environment, and
ascertain a plurality of natural language insights for the image;
an eminence score generator, executed by the at least one hardware processor, to
generate, for each insight of the plurality of insights, an eminence score, and
rank each insight of the plurality of insights according to the eminence scores; and
a robotic agent controller, executed by the at least one hardware processor, to
control, by the robotic agent and based on a highest ranked insight, an operation associated with the robotic agent, the object, or the environment.

2 . The apparatus according to claim 1 , wherein the eminence score generator is to generate, for each insight of the plurality of insights, the eminence score by:
determining, for the eminence score, a reliability score by
determining, by a semantic relatedness analyzer that is executed by the at least one hardware processor, semantic relatedness between each insight of the plurality of insights,
generating, based on the semantic relatedness between each insight of the plurality of insights, a semantic relatedness graph, wherein each node of the semantic relatedness graph represents an insight of the plurality of insights, and
determining, for each node of the semantic relatedness graph, a degree of centrality that represents the reliability score for the corresponding insight.

3 . The apparatus according to claim 2 , further comprising:
an eminence score analyzer that is executed by the at least one hardware processor to:
analyze reliability scores for the plurality of insights to identify at least one reliability score that exceeds a reliability score threshold; and
identify, for determination of the highest ranked insight, at least one insight associated with the identified at least one reliability score that exceeds the reliability score threshold.

4 . The apparatus according to claim 1 , wherein the eminence score generator is to generate, for each insight of the plurality of insights, the eminence score by:
determining, for the eminence score, a degree of atypicalness by
determining, for each insight of the plurality of insights, by a semantic relatedness analyzer that is executed by the at least one hardware processor, semantic relatedness between each pair of words of the insight, and
determining, for each insight of the plurality of insights, the degree of atypicalness as a function of the semantic relatedness between each pair of words of the insight.

5 . The apparatus according to claim 4 , further comprising:
an eminence score analyzer that is executed by the at least one hardware processor to:
analyze degrees of atypicalness for the plurality of insights to identify at least one degree of atypicalness that exceeds a degree of atypicalness threshold; and
identify, for determination of the highest ranked insight, at least one insight associated with the identified at least one degree of atypicalness that exceeds the degree of atypicalness threshold.

6 . The apparatus according to claim 1 , wherein the eminence score generator is to generate, for each insight of the plurality of insights, the eminence score by:
determining, for the eminence score, a conciseness score by
generating a concept graph that includes nodes that represent concepts extracted from the plurality of insights, and edge weights that represent semantic relatedness between the concepts,
retaining, for the concept graph, edges that include an edge weight that exceeds a specified edge weight threshold,
generating groups based on remaining concepts that are connected by edges, and
determining, for a specified insight, the conciseness score as a function of a total number of concepts occurring in the specified insight and a total number of the groups that are spanned by the concepts occurring in the specified insight.

7 . The apparatus according to claim 6 , further comprising:
an eminence score analyzer that is executed by the at least one hardware processor to:
analyze conciseness scores for the plurality of insights to identify at least one conciseness score that exceeds a conciseness score threshold; and
identify, for determination of the highest ranked insight, at least one insight associated with the identified at least one conciseness score that exceeds the conciseness score threshold.

8 . The apparatus according to claim 1 , wherein the eminence score generator is to generate, for each insight of the plurality of insights, the eminence score by:
determining, for the eminence score, an intrinsic succinctness score by
determining, for each insight of the plurality of insights, noun type words,
generating, for each insight of the plurality of insights, a dependency tree,
determining, for each dependency tree, a number of dependent nodes associated with the noun type words, and
determining, for each insight of the plurality of insights, the intrinsic succinctness score as a function of a number of the noun type words and the number of dependent nodes for the associated insight.

9 . The apparatus according to claim 1 , wherein the eminence score generator is to generate, for each insight of the plurality of insights, the eminence score by:
determining, for the eminence score, a relative succinctness score by
determining, for each insight of the plurality of insights, a hierarchy of concepts included in the insight, and
determining a number of concepts included in a first insight of the plurality of insight that are at a higher level than concepts included in a second insight of the plurality of insights.

10 . The apparatus according to claim 9 , further comprising:
an eminence score analyzer that is executed by the at least one hardware processor to:
analyze relative succinctness scores for the plurality of insights to identify at least one relative succinctness score that exceeds a relative succinctness score threshold; and
identify, for determination of the highest ranked insight, at least one insight associated with the identified at least one relative succinctness score that exceeds the relative succinctness score threshold.

11 . The apparatus according to claim 1 , wherein the eminence score generator is to generate, for each insight of the plurality of insights, the eminence score by:
determining, for the eminence score, a naturalness score by
determining, for each insight of the plurality of insights, a semantic relatedness between each pair of words in the insight, and
determining, for each insight of the plurality of insights, an expected semantic relatedness between node pairs in a semantic relatedness graph as an average of semantic relatedness scores across pairs of nodes in the semantic relatedness graph.

12 . The apparatus according to claim 11 , further comprising:
an eminence score analyzer that is executed by the at least one hardware processor to:
analyze naturalness scores for the plurality of insights to identify at least one naturalness score that is less than a naturalness score threshold; and
identify, for determination of the highest ranked insight, at least one remaining insight that is not associated with the identified at least one naturalness score that is less than the naturalness score threshold.

13 . The apparatus according to claim 1 , further comprising:
an eminence score analyzer that is executed by the at least one hardware processor to:
analyze, for each insi

Assignees

• Accenture Global Solutions Ltd

Inventors

• Misra Janardan
• Podder Sanjay
• Rawat Divya
• Ghosh Bhaskar
• DUBASH Neville

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F40/56

  Natural language generation · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06N5/048

  Fuzzy inferencing · CPC title