# US 2020/0401910 A1 · Intelligent causal knowledge extraction from data sources

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0401910 A1
- Document ID: US20200401910A1
- Status: Published application
- Kind: A1
- Application number: 16/445,061
- Filed: 2019-06-18
- Published: 2020-12-24
- Earliest claimed: 2019-06-18
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Oktie HASSANZADEH; Michael PERRONE; Shirin SOHRABI ARAGHI; Mark FEBLOWITZ; Debarun BHATTACHARJYA; Michael KATZ; Kavitha SRINIVAS
- Web page: https://patentgrep.com/patent/US20200401910A1

## CPC

- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 16/36: Creation of semantic tools, e.g. ontology or thesauri
- G06F 16/903: Querying (for retrieval from the web G06F16/953)
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 40/30: Semantic analysis
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/025: Extracting rules from data
- G06N 20/00: Machine learning
- G06N 5/04: Inference or reasoning models
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Embodiments are provided for intelligent causal knowledge analysis from data sources in a computing system by a processor. Multiple communications may be identified from one or more data sources. One or more causal statements having a cause-effect relationship may be extracted from the plurality of communications.

## Claims

### Claim 1

A method for intelligent causal knowledge analysis from a data source in a computing system by a processor, comprising:
identifying a plurality of communications from one or more data sources; and
extracting one or more causal statements having a cause-effect relationship from the plurality of communications.

### Claim 2 (depends on 1)

The method of claim 1, further including classifying each of the plurality of communications as being the one or more causal statements or non-causal statements.

### Claim 3 (depends on 1)

The method of claim 1, further including performing a natural language processing (“NLP”) operation on the plurality of communications to identify the one or more causal statements, wherein the one or more data sources include a corpus of text data.

### Claim 4 (depends on 1)

The method of claim 1, further including:
creating an index of a list of a plurality of causal statements collected of a selected period of time, wherein the index is enabled to perform a search operation for a defined query; or
creating a cause-effect relationship graphs having a plurality of nodes and edges representing the one or more causal statements having the cause-effect relationship.

### Claim 5 (depends on 1)

The method of claim 1, further including:
identifying a frequency of occurrence of each of the one or more causal statements; or
assigning a confidence score to the one or more causal statements indicating a degree of accuracy for the cause-effect relationship.

### Claim 6 (depends on 1)

The method of claim 1, further including providing the one or more causal statements to a received cause-effect relationship query void of semantic constraints.

### Claim 7 (depends on 1)

The method of claim 1, further including initiating a machine learning mechanism to:
training a cause-effect relationship model for learning the cause-effect relationship to identify the one or more causal statements;
identifying one or more semantic similarities between the plurality of communications; and
identifying one or more paths in a cause-effect relationship graph representing the one or more causal statements having the cause-effect relationship relating to a received cause-effect relationship query.

### Claim 8

A system for intelligent causal knowledge analysis from a data source in a computing system, comprising:
one or more computers with executable instructions that when executed cause the system to:
identify a plurality of communications from one or more data sources; and
extract one or more causal statements having a cause-effect relationship from the plurality of communications.

### Claim 9 (depends on 8)

The system of claim 8, wherein the executable instructions further classify each of the plurality of communications as being the one or more causal statements or non-causal statements.

### Claim 10 (depends on 8)

The system of claim 8, wherein the executable instructions further perform a natural language processing (“NLP”) operation on the plurality of communications to identify the one or more causal statements, wherein the one or more data sources include a corpus of text data.

### Claim 11 (depends on 8)

The system of claim 8, wherein the executable instructions further:
create an index of a list of a plurality of causal statements collected of a selected period of time, wherein the index is enabled to perform a search operation for a defined query; or
creates cause-effect relationship graphs having a plurality of nodes and edges representing the one or more causal statements having the cause-effect relationship.

### Claim 12 (depends on 8)

The system of claim 8, wherein the executable instructions further:
identify a frequency of occurrence of each of the one or more causal statements; or
assign a confidence score to the one or more causal statements indicating a degree of accuracy for the cause-effect relationship.

### Claim 13 (depends on 8)

The system of claim 8, wherein the executable instructions further provide the one or more causal statements to a received cause-effect relationship query void of semantic constraints.

### Claim 14 (depends on 8)

The system of claim 8, wherein the executable instructions further initiate a machine learning mechanism to:
train a cause-effect relationship model for learning the cause-effect relationship to identify the one or more causal statements;
identify one or more semantic similarities between the plurality of communications; and
identify one or more paths in a cause-effect relationship graph representing the one or more causal statements having the cause-effect relationship relating to a received cause-effect relationship query.

### Claim 15

A computer program product for intelligent causal knowledge analysis from a data source by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that identifies a plurality of communications from one or more data sources; and
an executable portion that extracts one or more causal statements having a cause-effect relationship from the plurality of communications.

### Claim 16 (depends on 15)

The computer program product of claim 15, further including an executable portion that classifies each of the plurality of communications as being the one or more causal statements or non-causal statements.

### Claim 17 (depends on 15)

The computer program product of claim 15, further including an executable portion that performs a natural language processing (“NLP”) operation on the plurality of communications to identify the one or more causal statements, wherein the one or more data sources include a corpus of text data.

### Claim 18 (depends on 15)

The computer program product of claim 15, further including an executable portion:
creates an index of a list of a plurality of causal statements collected of a selected period of time, wherein the index is enabled to perform a search operation for a defined query; or
creates a cause-effect relationship graphs having a plurality of nodes and edges representing the one or more causal statements having the cause-effect relationship.

### Claim 19 (depends on 15)

The computer program product of claim 15, further including an executable portion:
identifies a frequency of occurrence of each of the one or more causal statements;
assigns a confidence score to the one or more causal statements indicating a degree of accuracy for the cause-effect relationship; or
provides the one or more causal statements to a received cause-effect relationship query void of semantic constraints.

### Claim 20 (depends on 15)

The computer program product of claim 15, further including an executable portion initiate a machine learning mechanism to:
trains a cause-effect relationship model for learning the cause-effect relationship to identify the one or more causal statements;
identifies one or more semantic similarities between the plurality of communications; and
identifies one or more paths in a cause-effect relationship graph representing the one or more causal statements having the cause-effect relationship relating to a received cause-effect relationship query.