Platform for conversation-based insight search in analytics systems

Patent metadata

Field	Value
Publication number	US-11714807-B2
Application number	US-201916726462-A
Country	US
Kind code	B2
Filing date	Dec 24, 2019
Priority date	Dec 24, 2019
Publication date	Aug 1, 2023
Grant date	Aug 1, 2023

Abstract

Methods, systems, and computer-readable storage media for receiving, by a conversation-based search system (CSS) of an analytics system, verbal input from a user, providing, by the CSS, text input based on the verbal input, processing, by the CSS, the text input to determine a set of contexts, each context in the set of context representing one or more operations of an enterprise, determining, by the CSS, one or more insights based on the set of contexts, each insight representative of a performance of the enterprise, and displaying, by the analytics system, a story comprising one or more visualizations, each visualization depicting at least one insight.

First claim

What is claimed is:

1. A computer-implemented method for providing insights from an analytics system based on verbal input of a user, the method being executed by one or more processors and comprising:
receiving, by a conversation-based search system (CSS) of an analytics system, verbal input from a user during a session between the user and the CSS, the CSS providing a user profile of the user based on interactions of the user with the CSS;
providing, by the CSS, text input based on the verbal input;
processing, by the CSS, the text input to determine a set of contexts, a number of contexts in the set of contexts being limited by a context limit defined in a configuration, each context in the set of contexts representing one or more operations of an enterprise, contexts are provided in the set of contexts based on one or more patterns associated with the user in the user profile;
determining, by the CSS, a set of insights based on the set of contexts, each insight representative of a performance of the enterprise;
receiving, by a smart freeze module of the CSS, user input indicating that a current depth of insight is usable and, in response, storing one or more insights in the set of insights for use in a subsequent session; and
displaying, by the analytics system and during the session, a story comprising one or more visualizations, each visualization depicting at least one insight.

2. The method of claim 1 , wherein the text input is provided by processing the verbal input through one or more natural language system (NLS) libraries.

3. The method of claim 1 , further comprising determining a data fence for the user at least partially based on a role that is assigned to the user, the data fence determining one or more data sources to be accessed to determine the set of contexts.

4. The method of claim 1 , further comprising determining that a configuration setting indicates that the CSS is accessible to the user, and in response, enabling the CSS to receive the verbal input from the user.

5. The method of claim 1 , further comprising providing an intermediate story based on at least one insight of the one or more insights, wherein at least a portion of the intermediate story is included in the story.

6. The method of claim 1 , wherein at least one context is determined as a leading context and at least one context is determined as an intermediate context.

7. The method of claim 1 , wherein contexts in the set of contexts are provided in a rank order.

8. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for providing insights from an analytics system based on verbal input of a user, the operations comprising:
receiving, by a conversation-based search system (CSS) of an analytics system, verbal input from a user during a session between the user and the CSS, the CSS providing a user profile of the user based on interactions of the user with the CSS;
providing, by the CSS, text input based on the verbal input;
processing, by the CSS, the text input to determine a set of contexts, a number of contexts in the set of contexts being limited by a context limit defined in a configuration, each context in the set of contexts representing one or more operations of an enterprise, contexts are provided in the set of contexts based on one or more patterns associated with the user in the user profile;
determining, by the CSS, a set of insights based on the set of contexts, each insight representative of a performance of the enterprise;
receiving, by a smart freeze module of the CSS, user input indicating that a current depth of insight is usable and, in response, storing one or more insights in the set of insights for use in a subsequent session; and
displaying, by the analytics system and during the session, a story comprising one or more visualizations, each visualization depicting at least one insight.

9. The computer-readable storage medium of claim 8 , wherein the text input is provided by processing the verbal input through one or more natural language system (NLS) libraries.

10. The computer-readable storage medium of claim 8 , wherein operations further comprise determining a data fence for the user at least partially based on a role that is assigned to the user, the data fence determining one or more data sources to be accessed to determine the set of contexts.

11. The computer-readable storage medium of claim 8 , wherein operations further comprise determining that a configuration setting indicates that the CSS is accessible to the user, and in response, enabling the CSS to receive the verbal input from the user.

12. The computer-readable storage medium of claim 8 , wherein operations further comprise providing an intermediate story based on at least one insight of the one or more insights, wherein at least a portion of the intermediate story is included in the story.

13. The computer-readable storage medium of claim 8 , wherein at least one context is determined as a leading context and at least one context is determined as an intermediate context.

14. The computer-readable storage medium of claim 8 , wherein contexts in the set of contexts are provided in a rank order.

15. A system, comprising:
a computing device; and
a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for providing insights from an analytics system based on verbal input of a user, the operations comprising:
receiving, by a conversation-based search system (CSS) of an analytics system, verbal input from a user during a session between the user and the CSS, the CSS providing a user profile of the user based on interactions of the user with the CSS;
providing, by the CSS, text input based on the verbal input;
processing, by the CSS, the text input to determine a set of contexts, a number of contexts in the set of contexts being limited by a context limit defined in a configuration, each context in the set of contexts representing one or more operations of an enterprise, contexts are provided in the set of contexts based on one or more patterns associated with the user in the user profile;
determining, by the CSS, a set of insights based on the set of contexts, each insight representative of a performance of the enterprise;
receiving, by a smart freeze module of the CSS, user input indicating that a current depth of insight is usable and, in response, storing one or more insights in the set of insights for use in a subsequent session; and
displaying, by the analytics system and during the session, a story comprising one or more visualizations, each visualization depicting at least one insight.

16. The system of claim 15 , wherein the text input is provided by processing the verbal input through one or more natural language system (NLS) libraries.

17. The system of claim 15 , wherein operations further comprise determining a data fence for the user at least partially based on a role that is assigned to the user, the data fence determining one or more data sources to be accessed to determine the set of contexts.

18. The system of claim 15 , wherein operations further comprise determining that a configuration setting indicates that the CSS is accessible to the user, and in response, enabling the CSS to receive the verbal input from the user.

Assignees

• Sap Se

Inventors

• Amulu James Michael
• Natarajan Ranganathan

Classifications

• G06F16/243 Primary

  Natural language query formulation · CPC title

• G06F16/24553

  of query operations · CPC title

• G10L15/1815

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

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title