Translation of artificial intelligence representations

• US 10,235,734 B2
• Filed: 01/27/2017
• Issued: 03/19/2019
• Est. Priority Date: 01/27/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Riabov, Anton V., Sohrabi Araghi, Shirin, Udrea, Octavian
• Primary Examiner(s): Mazumder, Tapas
• Application Number:
  US15/418,418
• Publication Number:
  US 20180218472A1
• Time in Patent Office: 781 Days
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06T 1/20 Processor architectures; Processor configuration, e.g. pipelining

Abstract

Techniques for translating graphical representations of domain knowledge are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, a graphical representation of domain knowledge. The graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept. The computer-implemented method further comprises translating, by the device, the graphical representation into an artificial intelligence planning problem. The artificial intelligence planning problem is expressed in an artificial intelligence description language. The translating comprises parsing the graphical representation into groupings of terms. A first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and a second grouping of terms of the grouping of terms comprises the information indicative of the central concept. The computer-implemented method also comprises validating, by the device, the artificial intelligence planning problem.

Claims

1. A computer program product facilitating translating a graphical representation of domain knowledge, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing unit to cause the processing unit to:

receive, by the processing unit, a graphical representation of domain knowledge, wherein the graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept, and wherein the graphical representation further comprises one or more weights associated with an event of the at least one chain of events; and

translate, by the processing unit, the graphical representation into an artificial intelligence planning problem, wherein the artificial intelligence planning problem is expressed in an artificial intelligence description language, wherein the program instructions further cause the processing unit to;

parse the graphical representation into groupings of terms, wherein a first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and wherein a second grouping of terms of the grouping of terms comprises the information indicative of the central concept;

identify an initial state of the domain knowledge based on the first grouping of terms and the second grouping of terms; and

associate the one or more weights with one or more predicates and one or more actions.

2. The computer program product of claim 1, wherein the program instructions further cause the processing unit to:

identify one or more constants based on the first grouping of terms;

identify the one or more predicates and the one or more actions based on the one or more constants; and

encode the initial state, the one or more constants, the one or more predicates, and the one or more actions into the artificial intelligence description language.

3. The computer program product of claim 2, wherein an action of the one or more predicates and the one or more actions is associated with an action cost.

4. The computer program product of claim 1, wherein the program instructions further cause the processing unit to:

receive a second graphical representation; and

update the initial state of the domain knowledge based on the second graphical representation.

5. The computer program product of claim 1, wherein the artificial intelligence planning problem comprises one or more observations from the graphical representation, and wherein the one or more observations are one or more unreliable observations.

6. The computer program product of claim 1, wherein the artificial intelligence planning problem projects a future state of the domain knowledge.

7. A system, comprising:

a memory that stores computer executable components; and

a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise;

a translation component that;

receives a graphical representation of domain knowledge, wherein the graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept, and wherein the graphical representation further comprises one or more weights associated with an event of the at least one chain of events; and

translates the graphical representation into an artificial intelligence planning problem, wherein the artificial intelligence planning problem is expressed in an artificial intelligence description language, wherein translation comprises;

a parsing of the graphical representation into groupings of terms, wherein a first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and wherein a second grouping of terms of the grouping of terms comprises the information indicative of the central concept;

identification of an initial state of the domain knowledge based on the first grouping of terms and the second grouping of terms; and

association of the one or more weights with one or more predicates and one or more actions.

8. The system of claim 7, wherein the translation component also performs operations comprising:

identification of one or more constants based on the first grouping of terms;

identification of the one or more predicates and the one or more actions based on the one or more constants; and

an encoding of the initial state, the one or more constants, the one or more predicates, and the one or more actions into the artificial intelligence description language.