# US 2023/0409872 A1 · Detecting and correcting knowledge base errors

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

- Number: US 2023/0409872 A1
- Document ID: US20230409872A1
- Status: Published application
- Kind: A1
- Application number: 17/807,909
- Filed: 2022-06-21
- Published: 2023-12-21
- Earliest claimed: 2022-06-21
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Ndivhuwo Makondo; Francois Pierre Luus; Naweed Aghmad Khan; Ismail Yunus Akhalwaya; Ryan Nelson Riegel; Oarabile Hope Moloko; Thabang Doreen Lebese
- Web page: https://patentgrep.com/patent/US20230409872A1

## CPC

- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 5/025: Extracting rules from data
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 5/046: Forward inferencing; Production systems
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A computer-implemented method may include processors configured for receiving input data corresponding to a knowledge base comprising a plurality of propositional logic clauses, generating output data corresponding to a first set of logical rules and a first set of facts based on the plurality of propositional logic clauses, accumulating the first set of facts to generate accumulated facts, generating a model graph based on the accumulated facts and the first set of logical rules, alternating reasoning and learning passes at the model graph until convergence to generate a second set of logical rules and a second set of facts, and generating a third set of logical rules and a third set of facts, wherein the third set of logical rules and the third set of facts exceed a first predetermined threshold.

## Claims

### Claim 1

A computer-implemented method, comprising:
receiving, by one or more processors, at a component, input data corresponding to a knowledge base comprising a plurality of propositional logic clauses;
generating, by the component, output data corresponding to a first set of logical rules and a first set of facts based on the plurality of propositional logic clauses;
accumulating, by one or more processors, the first set of facts to generate accumulated facts;
generating, by one or more processors, a model graph based on the accumulated fact sand the first set of logical rules;
alternating, by one or more processors, reasoning and learning passes at the model graph until convergence to generate a second set of logical rules and a second set of facts; and
generating, by one or more processors, a third set of logical rules and a third set of facts, wherein the third set of logical rules and the third set of facts exceed a first predetermined threshold.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the input data corresponding to the knowledge base further comprises an external labeled dataset aligned with the knowledge base.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein generating the output data further comprises:
receiving, at the component, the input data;
processing, by the component, the input data to identify each of the plurality of propositional logic clauses;
extracting, by the component, the first set of logical rules and the first set of facts from the plurality of propositional logic clauses; and
transmitting, by the component, the first set of logical rules and the first set of facts as the output data.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein generating the model graph further comprises:
generating, by one or more processors, a graphical representation of first order logic statements corresponding to syntax trees representing the accumulated facts with the corresponding first set of logical rules; and
displaying, by one or more processors, the graphical representation as the model graph on a user interface of a computing device.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
extracting, by one or more processors, truth values from the knowledge base; and
determining, by one or more processors, truth value bounds based on the truth values.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein alternating the reasoning and learning passes at the model graph until convergence further comprises:
applying, by one or more processors, the truth value bounds to the model graph to allow an open world assumption that some of the second set of logical rules and the second set of facts are true even if the second set of logical rules and the second set of facts are unknown and unprovable.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
updating, by one or more processors, the knowledge base to include the third set of logical rules and the third set of facts; and
generating, by one or more processors, a fourth set of logical rules and a fourth set of facts, wherein the fourth set of logical rules and the fourth set of facts exceed a second predetermined threshold.

### Claim 8

A computer program product, comprising:
one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media, the stored program instructions comprising:
program instructions to receive at a component, input data corresponding to a knowledge base comprising a plurality of propositional logic clauses;
program instructions to generate, by the component, output data corresponding to a first set of logical rules and a first set of facts based on the plurality of propositional logic clauses;
program instructions to accumulate the first set of facts to generate accumulated facts;
program instructions to generate a model graph based on the accumulated facts and the first set of logical rules;
program instructions to alternate reasoning and learning passes at the model graph until convergence to generate a second set of logical rules and a second set of facts; and
program instructions to generate a third set of logical rules and a third set of facts, wherein the third set of logical rules and the third set of facts exceed a first predetermined threshold.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the input data corresponding to the knowledge base further comprises an external labeled data set aligned with the knowledge base.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein program instructions to generate the output data further comprises:
program instructions to receive, at the component, the input data;
program instructions to process, by the component, the input data to identify each of the plurality of propositional logic clauses;
program instructions to extract, by the component, the first set of logical rules and the first set of facts from the plurality of propositional logic clauses; and
program instructions to transmit, by the component, the first set of logical rules and the first set of facts as the output data.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein program instructions to generate the model graph further comprises:
program instructions to generate a graphical representation of first order logic statements corresponding to syntax trees representing the accumulated facts with the corresponding first set of logical rules; and
program instructions to display the graphical representation as the model graph on a user interface of a computing device.

### Claim 12 (depends on 8)

The computer program product of claim 8, further comprising:
program instructions to extract truth values from the knowledge base; and
program instructions to determine truth value bounds based on the truth values.

### Claim 13 (depends on 12)

The computer program product of claim 12, wherein program instructions to alternate the reasoning and learning passes at the model graph until convergence further comprises:
program instructions to apply the truth value bounds to the model graph to allow an open world assumption that some of the second set of logical rules and the second set of facts are true even if the second set of logical rules and the second set of facts are unknown and unprovable.

### Claim 14 (depends on 8)

The computer program product of claim 8, further comprising:
program instructions to update the knowledge base to include the third set of logical rules and the third set of facts; and
program instructions to generate a fourth set of logical rules and a fourth set of facts, wherein the fourth set of logical rules and the fourth set of facts exceed a second predetermined threshold.

### Claim 15

A computer system, comprising:
one or more computer processors;
one or more computer readable storage media;
program instructions collectively stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to receive at a component, input data corresponding to a knowledge base comprising a plurality of propositional logic clauses;
program instructions to generate, by the component, output data corresponding to a first set of logical rules and a first set of facts based on the plurality of propositional logic clauses;
program instructions to accumulate the first set of facts to generate accumulated facts;
program instructions to generate a model graph based on the accumulated facts and the first set of logical rules;
program instructions to alternate reasoning and learning passes at the model graph until convergence to generate a second set of logical rules and a second set of facts; and
program instructions to generate a third set of logical rules and a third set of facts, wherein the third set of logical rules and the third set of facts exceed a first predetermined threshold.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein the input data corresponding to the knowledge base further comprises an external labeled dataset aligned with the knowledge base.

### Claim 17 (depends on 15)

The computer system of claim 15, wherein program instructions to generate the output data further comprises:
program instructions to receive, at the component, the input data;
program instructions to process, by the component, the input data to identify each of the plurality of propositional logic clauses;
program instructions to extract, by the component, the first set of logical rules and the first set of facts from the plurality of propositional logic clauses; and
program instructions to transmit, by the component, the first set of logical rules and the first set of facts as the output data.

### Claim 18 (depends on 15)

The computer system of claim 15, wherein program instructions to generate the model graph further comprises:
program instructions to generate a graphical representation of first order logic statements corresponding to syntax trees representing the accumulated facts with the corresponding first set of logical rules; and
program instructions to display the graphical representation as the model graph on a user interface of a computing device.

### Claim 19 (depends on 15)

The computer system of claim 15, further comprising:
program instructions to extract truth values from the knowledge base; and
program instructions to determine truth value bounds based on the truth values, wherein the program instructions to alternate the reasoning and learning passes at the model graph until convergence further comprises:
program instructions to apply the truth value bounds to the model graph to allow an open world assumption that some of the second set of logical rules and the second set of facts are true even if the second set of logical rules and the second set of facts are not known or provable.

### Claim 20 (depends on 15)

The computer system of claim 15, further comprising:
program instructions to update the knowledge base to include the third set of logical rules and the third set of facts; and
program instructions to generate a fourth set of logical rules and a fourth set of facts, wherein the fourth set of logical rules and the fourth set of facts exceed a second predetermined threshold.