Generation of a chatbot interface for an application programming interface

Patent metadata

Field	Value
Publication number	US-10951552-B2
Application number	US-201715797670-A
Country	US
Kind code	B2
Filing date	Oct 30, 2017
Priority date	Oct 30, 2017
Publication date	Mar 16, 2021
Grant date	Mar 16, 2021

Abstract

Method and system are provided for generating a chatbot interface for an application programming interface (API) that interacts with networked applications. The method may include: receiving as an input a definition document for an API that interacts with networked applications and parsing the definition document to identify intents and entities and obtain examples of the identified intents and entities. The method may convert the definition document to a chatbot data structure including: extracting the intents and entities and their relationship to objects and fields in the API from the definition document; and training the chatbot data structure with the example intents and entities to generate a conversation specification in the chatbot data structure. The method may then generate a chatbot interface for the API.

First claim

What is claimed is:

1. A computer-implemented method for generating a chatbot interface for an application programming interface (API) that interacts with networked applications, comprising:
receiving as an input a definition document for the API that interacts with cloud-based networked applications;
parsing the definition document to identify intents and entities and obtain examples of the identified intents and entities;
converting the definition document to a chatbot data structure including:
extracting the intents and entities and their relationship to objects and fields in the API from the definition document, wherein the objects and fields in the API include (i) API Uniform Resource Locators, (ii) names of the cloud-based networked applications the API interacts with, and (iii) request parameters for user input information;
training the chatbot data structure with the example intents and entities to generate a conversation specification in the chatbot data structure, wherein the conversation specification is a conversation tree storing the extracted intents and entities and their relationship to the objects and fields in the API; and
generating a chatbot interface for the API.

2. The method as claimed in claim 1 , wherein multiple APIs that interact with networked application are input for generation of a chatbot interface for the multiple APIs.

3. The method as claimed in claim 1 , wherein parsing the definition document includes automatically identifying intents and entities and receiving user inputs of examples of the identified intents and entities.

4. The method as claimed in claim 1 , wherein extracting the intents and entities includes extracting intents from paths and entities from parameters in the description document.

5. The method as claimed in claim 4 , including looking up entities from definitions of parameters in an associated schema.

6. The method as claimed in claim 1 , including deploying the chatbot interface to a user selected chatbot platform.

7. The method as claimed in claim 1 , wherein the API is a Representational State Transfer (RESTful) API and the description document is selected from the group consisting of: OpenAPI file (Swagger file), RESTful API Modeling Language (RAML), Web Application Description Language (WADL), and Simple Object Access Protocol (SOAP) APIs described using Web Services Description Language (WSDL).

8. A system for generating a chatbot interface for an application programming interface (API) that interacts with networked applications, comprising:
a processor and a memory configured to provide computer program instructions to the processor to execute the function of the components;
an API definition receiving component for receiving as an input a definition document for the API that interacts with cloud-based networked applications;
a parsing component for parsing the definition document to identify intents and entities and obtain examples of the identified intents and entities;
a converting component for converting the definition document to a chatbot data structure including:
an extracting component for extracting the intents and entities and their relationship to objects and fields in the API from the definition document, wherein the objects and fields in the API include (i) API Uniform Resource Locators, (ii) names of the cloud-based networked applications the API interacts with, and (iii) request parameters for user input information;
a training component for training the chatbot data structure with the example intents and entities to generate a conversation specification in the chatbot data structure, wherein the conversation specification is a conversation tree storing the extracted intents and entities and their relationship to the objects and fields in the API; and
a chatbot interface providing component for generating a chatbot interface for the API.

9. The system as claimed in claim 8 , wherein the API definition receiving component receive document definitions for multiple APIs that interact with networked applications for generation of a chatbot interface for the multiple APIs.

10. The system as claimed in claim 8 , wherein the parsing component automatically identifies intents and entities and receives user inputs of examples of the identified intents and entities.

11. The system as claimed in claim 8 , wherein the chatbot data structure generating component uses a Natural Language Processing service.

12. The system as claimed in claim 8 , including a deploying component for deploying the chatbot interface to a user selected chatbot platform.

13. The system as claimed in claim 8 , wherein the API is a Representational State Transfer (RESTful) API and the description document is selected from the group consisting of: OpenAPI file (Swagger file), RESTful API Modeling Language (RAML), Web Application Description Language (WADL), and Simple Object Access Protocol (SOAP) APIs described using Web Services Description Language (WSDL).

14. The system as claimed in claim 8 , wherein the API is an integration flow API and the system is provided for an integration tool.

15. The system as claimed in claim 8 , wherein the API is provided on-premise, cloud based, or as a hybrid implementation.

16. A computer program product for generating a chatbot interface for an application programming interface (API) that interacts with networked applications, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
receive as an input a definition document for the API that interacts with cloud-based networked applications;
parse the definition document to identify intents and entities and obtain examples of the identified intents and entities;
convert the definition document to a chatbot data structure including:
extract the intents and entities and their relationship to objects and fields in the API from the definition document, wherein the objects and fields in the API include (i) API Uniform Resource Locators, (ii) names of the cloud-based networked applications the API interacts with, and (iii) request parameters for user input information;
train the chatbot data structure with the example intents and entities to generate a conversation specification in the chatbot data structure, wherein the conversation specification is a conversation tree storing the extracted intents and entities and their relationship to the objects and fields in the API; and
generate a chatbot interface for the API.

Assignees

• IBM

Inventors

• Jafar Ali Hisham
• Kempa Matthew J
• Naved Aaquib
• Nicholson Robert B
• Shah Vivek R
• Thorpe Paul S M
• Wasti Syed Akhass Adnan

Classifications

• G06F9/547

  Remote procedure calls [RPC]; Web services · CPC title

• H04L51/046

  Interoperability with other network applications or services · CPC title

• G06F40/56

  Natural language generation · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title