Using unstructured input to update heterogeneous data stores

Patent metadata

Field	Value
Publication number	US-11544465-B2
Application number	US-202117211162-A
Country	US
Kind code	B2
Filing date	Mar 24, 2021
Priority date	Sep 18, 2018
Publication date	Jan 3, 2023
Grant date	Jan 3, 2023

Abstract

Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.

First claim

What is claimed is:

1. A method for natural language processing, the method comprising:
receiving, by one or more processors of a server, an unstructured text input;
receiving, by the one or more processors, a template for interpreting the unstructured text input;
identifying, using an entity classifier, a plurality of entities in the unstructured text input and a respective set of characteristics relating to each entity from the plurality of entities;
determining a parent entity and a child entity from the plurality of entities based on respective sets of characteristics relating to the plurality of entities and a user selection;
identifying an action item in the unstructured text input based on the plurality of entities and the template;
determining, using an intent classifier, an intent of the action item;
matching the plurality of entities and the intent of the action item based on the template;
generating, upon user confirmation, a structured database query based on the action item and matched entities; and
updating a data store based on the structured database query.

2. The method of claim 1 , wherein the respective set of characteristics relating to the each entity includes:
a type of each of the plurality of entities,
a value of each of the plurality of entities, and
a confidence level in the identifying.

3. The method of claim 2 , wherein the type of each of the plurality of entities is selected from a group consisting of an organization, a person, a date, a time, a percentage, a monetary value, and a pick list type.

4. The method of claim 1 , wherein the parent entity and the child entity are determined by:
identifying, by the one or more processors, one or more potential parent entities from the identified plurality of entities based on the template;
receiving, by the one or more processors, a selection of the parent entity from the one or more potential parent entities;
identifying, by the one or more processors, one or more potential child entities from the identified plurality of entities based on the template and the selected parent entity;
receiving, by the one or more processors, a selection of the child entity from the one or more potential child entities.

5. The method of claim 4 , wherein the identifying the one or more potential parent entities comprises searching in records of one or more parent tables in the data store for values matching one or more of the identified plurality of entities having a type matching a type of the one or more parent tables; and
the one or more parent tables are identified in the template.

6. The method of claim 4 , wherein the identifying the one or more potential child entities comprises searching in records of one or more child tables in the data store for values matching one or more of the identified plurality of entities having a type matching a type of the one or more child tables;
the one or more child tables are identified in the template; and
the records are associated with a record corresponding to the selected parent entity.

7. The method of claim 4 , wherein the identifying the one or more potential child entities further comprises one or more of:
filtering records based on a filter in the template; or
ordering the one or more potential child entities based on an ordering specified by the template.

8. The method of claim 1 , further comprising publishing changes to the data store based on the updating.

9. The method of claim 1 , wherein the unstructured text input is received as audio input; and the method further comprises performing speech recognition on the audio input.

10. A computing device comprising:
a memory storing a plurality of processor-executable instructions for natural language processing; and
one or more processors coupled to the memory and executing the plurality of processor-executable instructions from the memory to:
receive an unstructured text input;
receive a template for interpreting the unstructured text input;
identify, using an entity classifier, a plurality of entities in the unstructured text input and a respective set of characteristics relating to each entity from the plurality of entities;
determine a parent entity and a child entity from the plurality of entities based on respective sets of characteristics relating to the plurality of entities and a user selection;
identify an action item in the unstructured text input based on the plurality of entities and the template;
determine, using an intent classifier, an intent of the action item;
match the plurality of entities and the intent of the action item based on the template;
generate, upon user confirmation, a structured database query based on the action item and matched entities; and
update a data store based on the structured database query.

11. The computing device of claim 10 , wherein the respective set of characteristics relating to the each entity includes:
a type of each of the plurality of entities,
a value of each of the plurality of entities, and
a confidence level in the identifying.

12. The computing device of claim 10 , wherein the type of each of the plurality of entities is selected from a group consisting of an organization, a person, a date, a time, a percentage, a monetary value, and a pick list type.

13. The computing device of claim 10 , wherein the parent entity and the child entity are determined by:
identifying, by the one or more processors, one or more potential parent entities from the identified plurality of entities based on the template;
receiving, by the one or more processors, a selection of the parent entity from the one or more potential parent entities;
identifying, by the one or more processors, one or more potential child entities from the identified entities based on the template and the selected parent entity;
receiving, by the one or more processors, a selection of the child entity from the one or more potential child entities.

14. The computing device of claim 10 , wherein the one or more processors execute the plurality of processor-executable instructions from the memory to identify one or more potential parent entities by searching in records of one or more parent tables in the data store for values matching one or more of the identified plurality of entities having a type matching a type of the one or more parent tables; and
wherein the one or more parent tables are identified in the template.

15. The computing device of claim 10 , wherein the one or more processors execute the plurality of processor-executable instructions from the memory to identify one or more potential child entities by:
searching in records of one or more child tables in the data store for values matching one or more of the identified plurality of entities having a type matching a type of the one or more child tables;
wherein the one or more child tables are identified in the template; and
the records are associated with a record corresponding to a selected parent entity.

16. The computing device of claim 10 , wherein the one or more processors execute the plurality of processor-executable instructions from the memory to identify one or more potential child entities by performing one or more of:
filtering records based on a filter in the template; or
ordering the one or more potential child entities based on an ordering specified by the template.

17. The computing device of claim 10 , wherein the one or more processors execute the plurality of processor-executable instructions from the memory to:
publish changes to the data store based on the

Assignees

• Salesforce Com Inc

Inventors

• Machado Michael
• Ball John
• Cook Jr Thomas Archie
• Harinath Shashank
• Lalani Roojuta
• Laraki Zineb
• Liu Qingqing
• Rosenbaum Mike
• Skucha Karl Ryszard
• Soumet Jean-Marc
• Vijayakumar Manju

Classifications

• G06F16/35 Primary

  Clustering; Classification · CPC title

• G06F40/205

  Parsing · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F40/30

  Semantic analysis · CPC title