US 12,333,256 B2
Authoring a conversation service module from relational data
Tin Kam Ho, Millburn, NJ (US); Vadim Sheinin, Yorktown Heights, NY (US); and Elahe Khorasani, Yorktown Heights, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on May 17, 2021, as Appl. No. 17/322,796.
Prior Publication US 2022/0366147 A1, Nov. 17, 2022
Int. Cl. G06F 40/35 (2020.01); G06F 16/22 (2019.01); G06F 16/242 (2019.01); G06F 16/2452 (2019.01); G06F 16/3329 (2025.01); G06F 40/56 (2020.01); H04L 51/02 (2022.01)
CPC G06F 40/35 (2020.01) [G06F 16/221 (2019.01); G06F 16/2423 (2019.01); G06F 16/243 (2019.01); G06F 16/2448 (2019.01); G06F 16/24522 (2019.01); G06F 16/3329 (2019.01); H04L 51/02 (2013.01); G06F 40/56 (2020.01)] 13 Claims
OG exemplary drawing
 
1. A method of authoring a conversation service for an existing chatbot and a database, comprising:
receiving, from a user though an interface of the chatbot, a selection of a database, and connecting an authoring service of the chatbot to a table in the database, wherein the table comprises a plurality of rows and a plurality of columns;
outputting, from the authoring service through the chatbot's interface to the user, a question requesting a description of a subject matter of the table;
receiving, by the authoring service from the chatbot's interface, the description of the subject matter of the table, wherein the description includes single words or lists of grammatically unrelated words;
outputting, from the authoring service through the chatbot's interface to the user, a question requesting an identification of a key column of the table that contains values that represent the subject matter of the table;
receiving, by the authoring service from the chatbot's interface, the identification of the key column of the table;
outputting, from the authoring service through the chatbot's interface to the user, a question requesting a semantic type of a subject matter of the table;
receiving, by the authoring service from the chatbot's interface, the description of the semantic type of the subject matter of the table;
outputting, from the authoring service through the chatbot's interface to the user, a question requesting which values of the table that are calculable;
receiving, by the authoring service from the chatbot's interface, which of the values of the table that are calculable;
outputting, from the authoring service through the chatbot's interface to the user, a question requesting a description of another column of the table;
receiving, by the authoring service from the chatbot's interface, a description of another column in the table, wherein the description of another column in the table includes single words or lists of grammatically unrelated words and is translated by the natural language query service into the conversation service;
translating, by a natural language query service, the single words or lists of grammatically unrelated words of the description of the subject matter of the table, the key column of the table, the semantic type of the subject matter, the calculable values, and the description of another column into the conversation service, wherein the conversation service includes SQL statements suitable for querying the database table; and
outputting, from the authoring service through the chatbot's interface to the user, feedback that summarizes the description of the subject matter of the table, the identification of the key column of the table, and a natural language description of another column in the table.