IP Library › Granted Patent US 12,555,006
Granted Patent B2
US 12,555,006 · App. 17/812,757 · Granted Feb 17, 2026

Extracting enriched target-oriented common sense from grounded graphs to support next step decision making

Inventors: Tsunehiko Tanaka (Chuo-ku, JP); Daiki Kimura (Midori-ku, JP); Michiaki Tatsubori (Oiso, JP)
Assignee: International Business Machines Corporation
G06N5/04G06N5/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,555,006
App. No.
17/812,757
Granted
Feb 17, 2026
Kind
B2
Abstract

Aspects of the invention include systems and methods configured to extract enriched target-oriented common sense from grounded graphs to support efficient next step decision making of an autonomous agent. A non-limiting example computer-implemented method includes extracting common sense from a source. The extracted common sense can include a first knowledge graph. An environment state can be extracted from an observation. The extracted environment state can include a second knowledge graph. The second knowledge graph can include an interactive object and a state of the interactive object. A difference graph including the extracted common sense and the extracted environment state can be generated. A next action is selected based on the difference graph and the next action is taken by an autonomous agent.

Claims (35)

1 . A computer-implemented method comprising:

extracting, by an autonomous agent, common sense from a source, the extracted common sense comprising a first knowledge graph;

extracting, by the autonomous agent, an environment state from an observation, the extracted environment state comprising a second knowledge graph, the second knowledge graph comprising an interactive object and a state of the interactive object;

generating, by the autonomous agent, a difference graph comprising the extracted common sense and the extracted environment state, the difference graph encoding the extracted common sense and the extracted environment state in a single connected graph;

selecting, by the autonomous agent and based on the difference graph, a next action; and

taking, by the autonomous agent, the next action.

2 . The computer-implemented method of claim 1 , wherein the first knowledge graph of the extracted common sense is represented as a triplet of {subject, relationship, object}.

3 . The computer-implemented method of claim 1 , wherein extracting the common sense comprises extracting by meaning, wherein extracting by meaning comprises extracting a knowledge graph from the source when both a similarity of a subject in a respective common sense graph of the source and a similarity of an object in the respective common sense graph of the source to an entity exceeds a threshold.

4 . The computer-implemented method of claim 3 , wherein extracting the common sense further comprises narrowing by circumstances, wherein narrowing by circumstances comprises retaining only those knowledge graphs from the extracted common sense that represent valid actions.

5 . The computer-implemented method of claim 3 , wherein extracting the common sense further comprises transforming into a grounded representation, wherein transforming into a grounded representation comprises transforming the subject in the respective common sense graph of the source to the respective entity.

6 . The computer-implemented method of claim 1 , wherein generating the difference graph comprises organizing the extracted common sense and the extracted environment states by interactive objects.

7 . The computer-implemented method of claim 6 , wherein the difference graph comprises a plurality of current state nodes, a plurality of common sense nodes, and a single interactive object node, and wherein the difference graph comprises interactive object-current state edges and interactive object-common sense edges.

8 . The computer-implemented method of claim 1 , further comprising encoding the difference graph, wherein encoding the difference graph comprises converting one or more words in a node of the difference graph into a series of vectors by word embedding.

9 . A system comprising an autonomous agent having a memory, computer readable instructions, and one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:

extracting common sense from a source, the extracted common sense comprising a first knowledge graph;

extracting an environment state from an observation, the extracted environment state comprising a second knowledge graph, the second knowledge graph comprising an interactive object and a state of the interactive object;

generating a difference graph comprising the extracted common sense and the extracted environment state, the difference graph encoding the extracted common sense and the extracted environment state in a single connected graph;

selecting, based on the difference graph, a next action; and

taking, by the autonomous agent, the next action.

10 . The system of claim 9 , wherein the first knowledge graph of the extracted common sense is represented as a triplet of {subject, relationship, object}.

11 . The system of claim 9 , wherein extracting the common sense comprises extracting by meaning, wherein extracting by meaning comprises extracting a knowledge graph from the source when both a similarity of a subject in a respective common sense graph of the source and a similarity of an object in the respective common sense graph of the source to an entity exceeds a threshold.

12 . The system of claim 11 , wherein extracting the common sense further comprises narrowing by circumstances, wherein narrowing by circumstances comprises retaining only those knowledge graphs from the extracted common sense that represent valid actions.

13 . The system of claim 11 , wherein extracting the common sense further comprises transforming into a grounded representation, wherein transforming into a grounded representation comprises transforming the subject in the respective common sense graph of the source to the respective entity.

14 . The system of claim 9 , wherein generating the difference graph comprises organizing the extracted common sense and the extracted environment states by interactive objects.

15 . The system of claim 14 , wherein the difference graph comprises a plurality of current state nodes, a plurality of common sense nodes, and a single interactive object node, and wherein the difference graph comprises interactive object-current state edges and interactive object-common sense edges.

16 . The system of claim 9 , further comprising encoding the difference graph, wherein encoding the difference graph comprises converting one or more words in a node of the difference graph into a series of vectors by word embedding.

17 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

extracting, by an autonomous agent, common sense from a source, the extracted common sense comprising a first knowledge graph;

extracting, by the autonomous agent, an environment state from an observation, the extracted environment state comprising a second knowledge graph, the second knowledge graph comprising an interactive object and a state of the interactive object;

generating, by the autonomous agent, a difference graph comprising the extracted common sense and the extracted environment state, the difference graph encoding the extracted common sense and the extracted environment state in a single connected graph;

selecting, by the autonomous agent and based on the difference graph, a next action; and

taking, by the autonomous agent, the next action.

18 . The computer program product of claim 17 , wherein the first knowledge graph of the extracted common sense is represented as a triplet of {subject, relationship, object}.

19 . The computer program product of claim 17 , wherein extracting the common sense comprises extracting by meaning, wherein extracting by meaning comprises extracting a knowledge graph from the source when both a similarity of a subject in a respective common sense graph of the source and a similarity of an object in the respective common sense graph of the source to an entity exceeds a threshold.

20 . The computer program product of claim 19 , wherein extracting the common sense further comprises narrowing by circumstances, wherein narrowing by circumstances comprises retaining only those knowledge graphs from the extracted common sense that represent valid actions.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2022
From: TANAKA, TSUNEHIKO; KIMURA, DAIKI; TATSUBORI, MICHIAKI
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 060516/0625 →
Continuity (1)
Related Publication 20240028923A1 · Jan 25, 2024
References Cited (19)
US 6032142A · Wavish · 2000 [cited by examiner]
US 6636781B1 · Shen · 2003 [cited by examiner]
US 10254759B1 · Faust · 2019 [cited by examiner]
US 20020156932A1 · Schneiderman · 2002 [cited by examiner]
US 20170171684A1 · Badler · 2017 [cited by examiner]
US 20180357083A1 · Chauhan · 2018 [cited by examiner]
US 20200033868A1 · Palanisamy · 2020 [cited by examiner]
US 20200033869A1 · Palanisamy · 2020 [cited by examiner]
US 20200034362A1 · Galitsky · 2020 [cited by examiner]
US 20200356855A1 · Yeh · 2020 [cited by examiner]
US 20220011776A1 · Narang · 2022 [cited by examiner]
KR 20210065066A · 2021 [cited by applicant]
Chen, et al., “Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources,” Coling (Year:2020) 12 pages. [cited by applicant]
Murugesan et al., “Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations” Association for Computational Linguistics, (Year: 2021): pp. 719-725. [cited by applicant]
Murugesan et al., “Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge” cs.AI, (Year: 2020), 10 pages. [cited by applicant]
Murugesan et al., “Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines,” AAAI (Year: 2021), 14 pages. [cited by applicant]
Murugesan, et al., “Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents,” AAAI, (Year: 2021) pp. 1-22. [cited by applicant]
Xu et al., “Automatic Extraction of Commonsense LocatedNear Knowledge” Association for Computational Linguistics, (Year: 2018): pp. 96-101. [cited by applicant]
Maheshwari, et al, “Scene Graph Embeddings Using Relative Similarity Supervision”, arXiv preprint, 2021, 9 pages. [cited by applicant]