Conversational authoring of event processing applications

Patent metadata

Field	Value
Publication number	US-10552543-B2
Application number	US-201715591199-A
Country	US
Kind code	B2
Filing date	May 10, 2017
Priority date	May 10, 2017
Publication date	Feb 4, 2020
Grant date	Feb 4, 2020

Abstract

A computer natural language conversational agent authors an event-processing rule by carrying out a dialog in natural language with a user. A data model that customizes a dialog and building of the event-processing rule is received. A partial tree data structure is constructed based on a rule's grammar, and specialized based on tokens extracted from the data model. An utterance is received from a user and interpreted according to the grammar as specialized to the data model. Based on the interpreting of the utterance, the grammar, the data model, and context of interactions with the user, a natural language prompt is determined for the computer natural language conversational agent to output to the user. The partial tree data structure is filled based on the natural language prompt and the utterance from the user. The event-processing rule is generated based on the partial tree data structure filled during the dialog.

First claim

We claim:

1. A method of providing a computer natural language conversational agent that authors an event-processing rule, the method performed by at least one hardware processor, the method comprising:
receiving a data model that customizes a dialog and building of the event-processing rule, the data model including at least entities and events, fields associated with the entities and events, and relationships associated with the entities and events;
parsing the data model to extract tokens;
constructing a partial tree data structure based on a grammar and specializing the partial tree data structure based on the tokens extracted from the data model, the partial tree data structure including at least nodes and edges representing a syntax tree (AST);
receiving a natural language utterance from a user;
interpreting the natural language utterance according to the grammar as specialized to the data model;
determining based on the interpreting of the natural language utterance, the grammar, the data model, and context of interaction with the user, a natural language prompt for the computer natural language conversational agent to output to the user;
filling the partial tree data structure based on the natural language prompt and the natural language utterance from the user, the filling including at least using separate data structures representing tree transformation including at least a replace instruction and an accept instruction, wherein the replace instruction swaps one subtree with a new subtree and the accept instruction changes a state of the subtree to be accepted;
repeating the receiving of the natural language utterance, the interpreting of the natural language utterance, the determining of the natural language prompt, and the filling of the partial tree data structure until the nodes in the AST are filled and the partial tree data structure represents a rule the user accepts; and
generating the event-processing rule based on the partial tree data structure that is filled, the event-processing rule provided as a controlled natural language (CNL), the event-processing rule comprising a computer language deployable to process an application event specified in the data model,
wherein the computer natural language conversational agent engages the user in the dialog via the natural language prompt, allowing the user to program the event-processing rule via carrying on the dialog with the computer natural language conversational agent, without the user having to know how to program the event-processing rule.

2. The method of claim 1 , further comprising transmitting the event-processing rule to an event-processing system, wherein based on an input event received in the event-processing system, the event-processing rule is triggered.

3. The method of claim 2 , wherein the event-processing rule triggering in the event-processing system generates an event output automatically.

4. The method of claim 1 , further comprising providing finite state machines that control a flow of the dialog in the interpreting of the natural language utterance and the determining of the natural language prompt.

5. The method of claim 1 , wherein the conversational agent generates the event-processing rule in a controlled natural language form.

6. The method of claim 1 , wherein the conversational agent generates the event-processing rule in a query language.

7. The method of claim 1 , wherein the conversational agent further echoes back the event processing rule that is generated based on the partial tree data structure filled during the dialog, and requests confirmation from the user.

8. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
receive a data model that customizes a dialog and building of the event-processing rule, the data model including at least entities and events, fields associated with the entities and events, and relationships associated with the entities and events;
parse the data model to extract tokens;
construct a partial tree data structure based on a grammar and specializing the partial tree data structure based on the tokens extracted from data model, the partial tree data structure including at least nodes and edges representing a syntax tree (AST);
receive a natural language utterance from a user;
interpret the natural language utterance according to the grammar as specialized to the data model;
determine based on the interpreting of the natural language utterance, the grammar, the data model, and context of interaction with the user, a natural language prompt for the computer natural language conversational agent to output to the user;
fill the partial tree data structure based on the natural language prompt and the natural language utterance from the user, the filling including at least using separate data structures representing tree transformation including at least a replace instruction and an accept instruction, wherein the replace instruction swaps one subtree with a new subtree and the accept instruction changes a state of the subtree to be accepted;
repeat receiving of the natural language utterance, interpreting of the natural language utterance, determining of the natural language prompt, and filling of the partial tree data structure until the nodes in the AST are filled and the partial tree data structure represents a rule the user accepts; and
generate the event-processing rule based on the partial tree data structure that is filled, the event-processing rule provided as a controlled natural language (CNL), the event-processing rule comprising a computer language deployable to process an application event specified in the data model,
wherein the computer natural language conversational agent engages the user in the dialog via the natural language prompt, allowing the user to program the event-processing rule via carrying on the dialog with the computer natural language conversational agent, without the user having to know how to program the event-processing rule.

9. The computer readable storage device of claim 8 , further comprising transmitting the event-processing rule to an event-processing system, wherein based on an input event received in the event-processing system, the event-processing rule is triggered.

10. The computer readable storage device of claim 9 , wherein the event-processing rule triggering in the event-processing system generates an event output automatically.

11. The computer readable storage device of claim 8 , further comprising providing finite state machines that control a flow of the dialog in the interpreting of the natural language utterance and the determining of the natural language prompt.

12. The computer readable storage device of claim 8 , wherein the conversational agent generates the event-processing rule in a controlled natural language form.

13. The computer readable storage device of claim 8 , wherein the conversational agent generates the event-processing rule in a query language.

14. The computer readable storage device of claim 8 , wherein the conversational agent further echoes back the event processing rule that is generated based on the partial tree data structure filled during the dialog, and requests confirmation from the user.

15. A natural language conversational agent system, comprising:
a storage devices; and
at least one hardware processor coupled to the storage device,
the at least one hardware processor receiving a data model that customizes a dialog and building of the event-processing rule

Assignees

• IBM

Inventors

• Hirzel Martin J
• Shinnar Avraham E
• Simeon Jerome

Classifications

• G06F16/243 Primary

  Natural language query formulation · CPC title

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title

• G06F16/24522

  Translation of natural language queries to structured queries · CPC title

• G10L15/22

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

• G10L15/18

  using natural language modelling · CPC title