Conversational Database Analysis

Patent metadata

Field	Value
Publication number	US-2023177078-A1
Application number	US-202318162321-A
Country	US
Kind code	A1
Filing date	Jan 31, 2023
Priority date	Nov 13, 2018
Publication date	Jun 8, 2023
Grant date	—

Abstract

Systems and methods for conversational user experiences and conversational database analysis disclosed herein improve the efficiency and accessibility of low-latency database analytics. The method may include obtaining data expressing a usage intent with respect to the low-latency database analysis system, wherein the data expressing the usage intent includes a current request string expressed in a natural language, a current context associated with the current request string, and a previously generated context associated with a previously generated resolved-request, identifying, from the current request string, a conversational phrase corresponding to a conversational phrase pattern from a defined set of conversational phrase patterns, generating a resolved-request based on the identified conversational phrase, including the resolved-request in the current context, obtaining results data responsive to the resolved-request from a distributed in-memory database, generating a response including the results data and the current context, and outputting the response.

First claim

What is claimed is:

1 . A method for use in a low-latency database analysis system, the method comprising:
obtaining data expressing a usage intent with respect to the low-latency database analysis system, wherein the data expressing the usage intent includes a current request string expressed in a natural language, a current context associated with the current request string, and a previously generated context associated with a previously generated resolved-request; identifying, from the current request string, a conversational phrase corresponding to a conversational phrase pattern from a defined set of conversational phrase patterns; generating a resolved-request based on the identified conversational phrase; including the resolved-request in the current context; obtaining results data responsive to the resolved-request from a distributed in-memory database; generating a response including the results data and the current context; and outputting the response.

2 . The method of claim 1 , wherein generating the resolved-request comprising:
in response to a determination that the conversational phrase is a data-request phrase, generating the resolved-request based on the data-request phrase, wherein generating the resolved-request omits using the previously generated context.

3 . The method of claim 1 , wherein generating the resolved-request comprising:
in response to a determination that the conversational phrase is a request-transformation phrase, generating the resolved-request by modifying the previously generated resolved-request based on the request-transformation phrase.

4 . The method of claim 3 , wherein the request-transformation phrase includes one or more of remove a column from the previously generated context, add a filter, remove a filter on a column, remove all filters, change a filter value, sort on a set of columns, sort columns in an ascending order, sort columns in a descending order, change date bucketing, limit to top N, exclude one or more value, drill down by an attribute, and drill down on a particular filter value by an attribute.

5 . The method of claim 1 , wherein generating the resolved-request comprising:
in response to a determination that the conversational phrase is a serial-request phrase, generating the resolved-request based on the serial-request phrase such that the resolved-request identifies a result of the previously generated resolved-request as a data-source for the resolved-request.

6 . The method of claim 5 , wherein generating the resolved-request comprising:
obtaining results data responsive to a previously generated resolved-request from a distributed in-memory database.

7 . The method of claim 6 , wherein generating the resolved-request comprising:
locally storing, with respect to a relational search unit, the results data.

8 . The method of claim 1 , wherein generating the resolved-request comprising:
in response to a determination that the conversational phrase is an autonomous-analysis phrase, generating the resolved-request such that the resolved-request indicates a request for autonomous-analysis based on the previously generated resolved-request.

9 . The method of claim 8 , wherein the request for autonomous-analysis identifies one or more insights based on the previously generated resolved-request, where the one or more insights are data other than data expressly requested by a user.

10 . The method of claim 1 , wherein generating the resolved-request comprising:
in response to a determination that the conversational phrase is an action phrase, generating the resolved-request includes identifying the previously generated resolved-request as the resolved request and generating an action-request corresponding to the action phrase, the action-request referring to the previously generated resolved-request.

11 . The method of claim 10 , wherein the action phrase includes one or more of pinning the previously generated context, sharing the previously generated context, or changing a chart type of the previously generated context.

12 . A system comprising:
a low-latency database; and a processor, the processor configured to:
obtain data expressing a usage intent with respect to the low-latency database analysis system, wherein the data expressing the usage intent includes a current request string expressed in a natural language, a current context associated with the current request string, and a previously generated context associated with a previously generated resolved-request;
identify, from the current request string, a conversational phrase corresponding to a conversational phrase pattern from a defined set of conversational phrase patterns;
generate a resolved-request based on the identified conversational phrase;
include the resolved-request in the current context;
obtain results data responsive to the resolved-request from a distributed in-memory database;
generate a response including the results data and the current context; and
output the response.

13 . The system of claim 12 , wherein the processor further configured to:
in response to a determination that the conversational phrase is a data-request phrase, generate the resolved-request based on the data-request phrase, wherein generating the resolved-request omits using the previously generated context.

14 . The system of claim 12 , wherein the processor further configured to:
in response to a determination that the conversational phrase is a request-transformation phrase, generate the resolved-request by modifying the previously generated resolved-request based on the request-transformation phrase.

15 . The system of claim 12 , wherein the processor further configured to:
in response to a determination that the conversational phrase is a serial-request phrase, generate the resolved-request based on the serial-request phrase such that the resolved-request identifies a result of the previously generated resolved-request as a data-source for the resolved-request.

16 . The system of claim 12 , wherein the processor further configured to:
in response to a determination that the conversational phrase is an autonomous-analysis phrase, generate the resolved-request such that the resolved-request indicates a request for autonomous-analysis based on the previously generated resolved-request.

17 . The system of claim 12 , wherein the processor further configured to:
in response to a determination that the conversational phrase is an action phrase, generate the resolved-request includes identifying the previously generated resolved-request as the resolved request and generating an action-request corresponding to the action phrase, the action-request referring to the previously generated resolved-request.

18 . A non-transitory computer-readable storage medium, comprising processor-executable instructions for performing operations in a low-latency database analysis system, the operations performed in response to the instructions comprising:
obtaining data expressing a usage intent with respect to the low-latency database analysis system, wherein the data expressing the usage intent includes a current request string expressed in a natural language, a current context associated with the current request string, and a previously generated context associated with a previously generated resolved-request; identifying, from the current request string, a conversational phrase corresponding to a conversational phrase pattern from a defined set of conversational phrase patterns; generating

Assignees

• Thoughtspot Inc

Inventors

• Balakavi Manikanta Venkata Rahul
• Kothari Rakesh
• Prakash Amit
• Tandon Ravi
• Shubham Ashish

Classifications

• G06F40/253

  Grammatical analysis; Style critique · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F16/3344 Primary

  using natural language analysis · CPC title

• G06F16/24522

  Translation of natural language queries to structured queries · CPC title

• G06F40/205

  Parsing · CPC title