Automatic seeding of an application programming interface (api) into a conversational interface

Patent metadata

Field	Value
Publication number	US-2019188317-A1
Application number	US-201715843119-A
Country	US
Kind code	A1
Filing date	Dec 15, 2017
Priority date	Dec 15, 2017
Publication date	Jun 20, 2019
Grant date	—

Abstract

Systems, methods, and computer-readable media for automatically seeding an API into a natural language conversational interface are described herein. An API is automatically seeded into a natural language conversational interface by mapping a set of API calls to a set of intents, mapping the set of intents to a collection of example utterances, and using the collection of example utterances as input training data to train a natural language classifier. The trained classifier may then be used to determine an intent associated with a received query such that an action associated with the determined intent can then be performed.

First claim

What is claimed is:

1 . A computer-implemented method for automatically seeding an application programming interface (API) into a natural language conversational interface, the method comprising:
utilizing a knowledge base to automatically map API calls to a set of intents; automatically mapping the set of intents to example utterances; and training a natural language classifier using the example utterances as input training data.

2 . The computer-implemented method of claim 1 , wherein the knowledge base comprises at least one of documentation associated with the API, code examples, or actual code stored in code repositories.

3 . The computer-implemented method of claim 1 , further comprising:
receiving a natural language query; determining, using the natural language classifier, a particular intent in the set of intents that maps to the natural language query; determining a particular API call associated with the particular intent; and executing the particular API call to perform an action corresponding to the particular intent.

4 . The computer-implemented method of claim 1 , wherein utilizing the knowledge base to automatically map the API calls to the set of intents comprises:
classifying the API calls into a set of functional classes, wherein each functional class is associated with a template; executing one or more commands to identify a particular intent and a corresponding natural language description associated with a particular API call; and mapping the particular intent to a particular functional class in the set of functional classes.

5 . The computer-implemented method of claim 4 , wherein automatically mapping the set of intents to the example utterances comprises determining, utilizing i) a particular template associated with the particular functional class, ii) the natural language description, and iii) a synonym database, a subset of the example utterances used to train the natural language classifier, wherein the subset of the example utterances corresponds to the particular intent.

6 . The computer-implemented method of claim 5 , wherein the natural language description is an initial example utterance in the subset of the example utterances corresponding to the particular intent, and wherein determining the subset of the example utterances comprises performing a synonym expansion of the initial example utterance using the synonym database to identify additional example utterances in the subset.

7 . The computer-implemented method of claim 1 , further comprising identifying, from the knowledge base, one or more respective parameters associated with each intent in the set of intents.

8 . A system for automatically seeding an application programming interface (API) into a natural language conversational interface, the system comprising:
at least one memory storing computer-executable instructions; and at least one processor configured to access the at least one memory and execute the computer-executable instructions to:
utilize a knowledge base to automatically map API calls to a set of intents;
automatically map the set of intents to example utterances; and
train a natural language classifier using the example utterances as input training data.

9 . The system of claim 8 , wherein the knowledge base comprises at least one of documentation associated with the API, code examples, or actual code stored in code repositories.

10 . The system of claim 8 , wherein the at least one processor is further configured to execute the computer-executable instructions to:
receive a natural language query; determine, using the natural language classifier, a particular intent in the set of intents that maps to the natural language query; determine a particular API call associated with the particular intent; and execute the particular API call to perform an action corresponding to the particular intent.

11 . The system of claim 8 , wherein the at least one processor is configured to utilize the knowledge base to automatically map the API calls to the set of intents by executing the computer-executable instructions to:
classify the API calls into a set of functional classes, wherein each functional class is associated with a template; execute one or more commands to identify a particular intent and a corresponding natural language description associated with a particular API call; and map the particular intent to a particular functional class in the set of functional classes.

12 . The system of claim 11 , wherein the at least one processor is configured to automatically map the set of intents to the example utterances by executing the computer-executable instructions to determine, utilizing i) a particular template associated with the particular functional class, ii) the natural language description, and iii) a synonym database, a subset of the example utterances used to train the natural language classifier, wherein the subset of the example utterances corresponds to the particular intent.

13 . The system of claim 12 , wherein the natural language description is an initial example utterance in the subset of the example utterances corresponding to the particular intent, and wherein the at least one processor is configured to determine the subset of the example utterances by executing the computer-executable instructions to perform a synonym expansion of the initial example utterance using the synonym database to identify additional example utterances in the subset.

14 . The system of claim 8 , wherein the at least one processor is further configured to execute the computer-executable instruction to identify, from the knowledge base, one or more respective parameters associated with each intent in the set of intents.

15 . A computer program product for automatically seeding an application programming interface (API) into a natural language conversational interface, the computer program product comprising a storage medium readable by a processing circuit, the storage medium storing instructions executable by the processing circuit to cause a method to be performed, the method comprising:
utilizing a knowledge base to automatically map API calls to a set of intents; automatically mapping the set of intents to example utterances; and training a natural language classifier using the example utterances as input training data.

16 . The computer program product of claim 15 , wherein the knowledge base comprises at least one of documentation associated with the API, code examples, or actual code stored in code repositories.

17 . The computer program product of claim 15 , the method further comprising:
receiving a natural language query; determining, using the natural language classifier, a particular intent in the set of intents that maps to the natural language query; determining a particular API call associated with the particular intent; and executing the particular API call to perform an action corresponding to the particular intent.

18 . The computer program product of claim 15 , wherein utilizing the knowledge base to automatically map the API calls to the set of intents comprises:
classifying the API calls into a set of functional classes, wherein each functional class is associated with a template; executing one or more commands to identify a particular intent and a corresponding natural language description associated with a particular API call; and mapping the particular intent to a particular functional class in the set of functional classes.

19 . The comput

Assignees

• IBM

Inventors

• Kashyap Sujatha
• Rellermeyer Jan Simon
• Rozner Eric
• Schaub Jeremy D

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/3344 Primary

  using natural language analysis · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N99/005

  Physics · mapped topic

• G06F17/30684 Primary

  Physics · mapped topic