Determining whether to take an action by applying a metric calculated using natural language processing tokens

Patent metadata

Field	Value
Publication number	US-11042540-B2
Application number	US-201715701704-A
Country	US
Kind code	B2
Filing date	Sep 12, 2017
Priority date	Sep 12, 2017
Publication date	Jun 22, 2021
Grant date	Jun 22, 2021

Abstract

Embodiments described herein are directed to computer-implemented methods, systems, and computer program products for calculating a metric using natural language processing tokens. A non-limiting example of the computer-implemented method includes parsing, by a processing device, user content using a natural language processing technique to extract tokens. The method further includes filtering, by the processing device, the tokens relating to a natural language processing criterion. The method further includes calculating, by the processing device, a metric based at least in part on the filtered tokens. The method further includes determining, by the processing device, whether to take an action by applying the metric to a set of rules. The method further includes taking the action responsive to determining to take the action.

First claim

What is claimed:

1. A system comprising:
a memory comprising computer readable instructions; and
a processing device for executing the computer readable instructions for performing a method, the method comprising:
parsing, by the processing device, user content using a natural language processing technique to extract tokens;
filtering, by the processing device, the tokens relating to a natural language processing criterion relating to product safety for a product of interest;
determining, by the processing device, a severity for the user content, the severity being based on an incident associated with the product of interest, the incident being indicated in the user content;
simultaneously performing in parallel, by the processing device:
calculating a safety metric for the product of interest based at least in part on the filtered tokens and based at least in part on the severity; and
calculating a reputation factor for an author of the user content based at least in part on a determination of whether the author is a verified expert;

recalculating, by the processing device, the safety metric by multiplying the safety metric and the reputation factor for the author of the user content to generate an updated metric;
determining, by the processing device, whether to take an action by applying the updated metric to a set of rules; and
taking the action responsive to determining to take the action.

2. The system of claim 1 , wherein the user content relates to the product of interest.

3. The system of claim 2 , wherein the action comprises initiating a product recall for the product of interest.

4. The system of claim 2 , wherein the action comprises recommending a different product similar to the product of interest.

5. The system of claim 4 , wherein the safety metric is a first safety metric, wherein the first safety metric is associated with the product of interest, and wherein a second safety metric is associated with the different product.

6. The system of claim 5 , wherein the second safety metric is greater than the first safety metric.

7. The system of claim 1 , wherein the set of rules utilizes a plurality of thresholds to determine whether to take the action.

8. A computer program product comprising:
a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processing device to cause the processing device to perform operations comprising:
parsing, by the processing device, user content using a natural language processing technique to extract tokens;
filtering, by the processing device, the tokens relating to a natural language processing criterion relating to product safety for a product of interest;
determining, by the processing device, a severity for the user content, the severity being based on an incident associated with the product of interest, the incident being indicated in the user content;
simultaneously performing in parallel, by the processing device:
calculating a safety metric for the product of interest based at least in part on the filtered tokens and based at least in part on the severity; and
calculating a reputation factor for an author of the user content based at least in part on a determination of whether the author is a verified expert; and

recalculating, by the processing device, the safety metric by multiplying the safety metric and the reputation factor for the author of the user content to generate an updated metric;
determining, by the processing device, whether to take an action by applying the updated metric to a set of rules; and
taking the action responsive to determining to take the action.

Assignees

• IBM

Inventors

• Danyluk Nicholas
• Dow Eli M
• Sehgal Kavita
• Stamboni Diane
• Varghese Sneha
• Werner John
• Wu Sarah

Classifications

• G06Q30/0625 Primary

  by formulating product or service queries, e.g. using keywords or predefined options · CPC title

• G06F16/24564

  Applying rules; Deductive queries · CPC title

• G06F40/205

  Parsing · CPC title

• G06Q30/0631

  Recommending goods or services · CPC title

• G06F16/243 Primary

  Natural language query formulation · CPC title