Adverse information based ontology reinforcement

Patent metadata

Field	Value
Publication number	US-10824663-B2
Application number	US-201815922619-A
Country	US
Kind code	B2
Filing date	Mar 15, 2018
Priority date	Mar 15, 2018
Publication date	Nov 3, 2020
Grant date	Nov 3, 2020

Abstract

According to an example, with respect to adverse information based ontology reinforcement, adverse information related to a product or a process may be ascertained and analyzed to further identify and ascertain a relevant ontology of a plurality of ontologies. A determination may be made as to whether the adverse information is present in the ascertained ontology, and if not, the adverse information may be integrated into the ascertained ontology to generate an updated ontology. Similar existing information corresponding to the ascertained adverse information may be identified in the updated ontology to determine an inconsistency between the identified similar existing information and the ascertained adverse information. The determined inconsistency may be used to modify the updated ontology to generate a reinforced ontology.

First claim

What is claimed is:

1. A system comprising:
an adverse information identifier, executed by at least one hardware processor, to ascertain, over a network, adverse information related to a product or a process;
an ontology instantiator, executed by the at least one hardware processor, to
analyze the adverse information related to the product or the process,
identify, based on the adverse information related to the product or the process, a relevant ontology of a plurality of ontologies,
ascertain, over the network, the relevant ontology of the plurality of ontologies, wherein the relevant ontology is designated an ascertained ontology,
determine whether the adverse information is present in the ascertained ontology,
integrate, based on a determination that the adverse information is not present in the ascertained ontology, the adverse information into the ascertained ontology, and
generate, based on the integrated adverse information, an updated ontology;

an inconsistency analyzer, executed by the at least one hardware processor, to
identify, in the updated ontology, similar existing information corresponding to the ascertained adverse information, and
determine, based on an analysis of the identified similar existing information and the ascertained adverse information, an inconsistency between the identified similar existing information and the ascertained adverse information; and

an ontology reinforcer, executed by the at least one hardware processor, to
modify, based on the determined inconsistency between the identified similar existing information and the ascertained adverse information, the updated ontology to generate a reinforced ontology.

2. The system according to claim 1 , wherein the adverse information includes an adverse effect related to a product that includes a medical drug.

3. The system according to claim 1 , wherein the ontology instantiator is to identify, based on the adverse information related to the product or the process, the relevant ontology of the plurality of ontologies by:
receiving the plurality of ontologies; and
identifying, based on the adverse information related to the product or the process, the relevant ontology of the received plurality of ontologies.

4. The system according to claim 1 , wherein the inconsistency analyzer is to determine, based on the analysis of the identified similar existing information and the ascertained adverse information, the inconsistency between the identified similar existing information and the ascertained adverse information by:
identifying, based on the identified similar existing information and the ascertained adverse information, cohorts that are affected by the product or the process related to the ascertained adverse information;
determining, based on the identified cohorts, a pair of cohorts that are inconsistent with each other;
determining, based on the pair of cohorts that are inconsistent with each other, whether the inconsistency exists between the identified similar existing information and the ascertained adverse information; and
based on a determination that the inconsistency exists between the identified similar existing information and the ascertained adverse information, identifying a root cause of the determined inconsistency.

5. The system according to claim 1 , wherein the ontology reinforcer is to modify, based on the determined inconsistency between the identified similar existing information and the ascertained adverse information, the updated ontology to generate the reinforced ontology by:
generating an inquiry that includes the determined inconsistency;
receiving, based on the inquiry, a response that includes a confirmation of whether the determined inconsistency is correct or incorrect; and
based on the confirmation that the determined inconsistency is incorrect, removing the determined inconsistency between the identified similar existing information and the ascertained adverse information to generate the reinforced ontology.

6. The system according to claim 1 , wherein the ontology reinforcer is to modify, based on the determined inconsistency between the identified similar existing information and the ascertained adverse information, the updated ontology to generate the reinforced ontology by:
generating an inquiry that includes the determined inconsistency;
receiving, based on the inquiry, a response that includes a confirmation of whether the determined inconsistency is correct or incorrect;
based on the confirmation that the determined inconsistency is correct, generating a further inquiry that includes an explanation for the determined inconsistency;
receiving, based on the further inquiry, a further response that includes a further confirmation of disagreement with the explanation for the determined inconsistency; and
based on the further confirmation of the disagreement with the explanation for the determined inconsistency, removing the determined inconsistency between the identified similar existing information and the ascertained adverse information to generate the reinforced ontology.

7. The system according to claim 1 , wherein the ontology reinforcer is to modify, based on the determined inconsistency between the identified similar existing information and the ascertained adverse information, the updated ontology to generate the reinforced ontology by:
generating an inquiry that includes the determined inconsistency;
receiving, based on the inquiry, a response that includes a confirmation of whether the determined inconsistency is correct or incorrect;
based on the confirmation that the determined inconsistency is correct, generating a further inquiry that includes an explanation for the determined inconsistency;
receiving, based on the further inquiry, a further response that includes a further confirmation of agreement with the explanation for the determined inconsistency; and
based on the further confirmation of the agreement with the explanation for the determined inconsistency, generating the reinforced ontology.

8. The system according to claim 7 , wherein the ontology reinforcer is to generate, based on the further confirmation of the agreement with the explanation for the determined inconsistency, the reinforced ontology by:
ascertaining, for the updated ontology, a link between a condition and a trigger related to the determined inconsistency;
ascertaining a policy that is used to correct the link;
assigning a weight to each link of the updated ontology according to the ascertained policy; and
determining, based on the assigned weight to each link of the updated ontology according to the ascertained policy, the reinforced ontology.

9. The system according to claim 8 , wherein the ontology reinforcer is to determine, based on the assigned weight to each link of the updated ontology according to the ascertained policy, the reinforced ontology by:
identifying a path between nodes associated with the determined inconsistency, wherein the path includes a plurality of links;
selecting, from the path, a link for removal based on the ascertained policy;
utilizing the assigned weight for each link to determine an overall score based on the removal of the selected link;
determining whether the removal of the selected link results in a lowest overall score compared to removal of another link of the path;
based on a determination that the removal of the selected link results in the lowest overall score, removing the selected link; and
determining the reinforced ontology by removing the determined inconsistency based on the removal of the selected link that results in the lowest overall score.

10. The system according to claim 9 , wherein the ascertai

Assignees

• Accenture Global Solutions Ltd

Inventors

• Lecue Freddy
• Zaman Md Faisal

Classifications

• G06F16/367 Primary

  Ontology · CPC title

• G16H70/40

  relating to drugs, e.g. their side effects or intended usage · CPC title

• G06F16/335

  Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536) · CPC title