US 11,868,907 B2
Updating chatbot workspaces
Piotr Kalandyk, Zielonki (PL); Piotr P. Godowski, Cracow (PL); Pawel Tadeusz Januszek, Cracow (PL); and Hubert Kompanowski, Izbica Kujawska (PL)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Mar. 22, 2021, as Appl. No. 17/207,880.
Prior Publication US 2022/0300830 A1, Sep. 22, 2022
Int. Cl. G06N 5/022 (2023.01); G06N 5/01 (2023.01); G06F 40/205 (2020.01); G06F 40/35 (2020.01); G06F 40/30 (2020.01); H04L 51/02 (2022.01); G06F 9/455 (2018.01); G06F 40/14 (2020.01)
CPC G06N 5/022 (2013.01) [G06F 40/14 (2020.01); G06F 40/205 (2020.01); G06F 40/30 (2020.01); G06F 40/35 (2020.01); G06N 5/01 (2023.01); H04L 51/02 (2013.01); G06F 9/45529 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for updating chatbot workspaces, the computer-implemented method comprising:
determining a chatbot knowledge base contains a set of updated information;
adding chatbot metadata from the set of updated information to a documentation source, wherein the chatbot metadata is consumable by an automation script;
responsive to identifying new data in the documentation source, generating one or more chatbot skills from the identified new data in the document source;
updating a chatbot dialog decision tree based on the one or more identified new topics in the set of updated information, wherein updating the chatbot dialogue decision tree comprises using natural language processing techniques to determine a set of intents, a set of entities, and a set of keywords;
responsive to identifying new data by a script, updating the one or more correspondent chatbot skills using a chatbot workspace application program interface (API) based on the documentation pages from the chatbot metadata;
creating the automation script to identify input data;
synchronizing, by the automation script, the chatbot skills by utilizing a knowledge center product's documentation stored on a database;
searching, by the automation script, hypertext markup language (HTML) documentation for new topics with chatbot specific data using HTML tags and documentation structure;
responsive to identifying new pages, updating, by the API, the chatbot skills;
creating new entities and skill dialogs that represent HTML pages in the chatbot dialog decision trees; and
identifying a starting decision for traversing the chatbot dialogue decision tree based on the updated set of entities and the updated set of keywords, wherein the execution of the identified starting decision comprises interacting with an end user and based on the interactions traversing the chatbot dialogue tree for a response.