International Business Machines Corporation

Xin Ni

Jun Wei Zhang

Lei Chen

Tao Xie

Zi Ming Huang

Jian Wang

Qi Cheng Li

Jing Li

Jie Ma

Ke Fei Wang

Ching-Yun Chao

Randy Allan Rendahl

Jian Min Jiang

Christopher Jonathan Davis

Rachel Mohammed

Zhuoxuan Jiang

John H Teoh

Frankie Kong

Techniques for generating a natural language question template for an artificial intelligence question and answer (QA) system are disclosed. A graph database query relating to a QA system is parsed using a predefined schema. The parsing includes extracting a first plurality of values from the graph database query relating to a where clause in the graph database query, extracting a second plurality of values from the graph database query relating to a return clause in the graph database query, identifying a QA template rule relating to the graph database query, based on a match clause in the graph database query. A natural language question template is generated based on the first plurality of values, the second plurality of values, and the identified QA template rule. The natural language question template is suitable for use by the QA system as part of generating a response to a natural language question.

Generating question templates in a knowledge-graph based question and answer system

Mechanisms are provided to implement a recurring payment collection system for extending current quick response (QR) code payment methods to collect recurring payments from a customer. The recurring payment collection system sends a notification to the customer that a recurring payment is due in response to a recurring payment event occurring. The recurring payment collection system obtains a QR code for the recurring payment in response to the customer acknowledging the notification. The recurring payment collection system utilizes the QR code to request the recurring payment from a payment system. The recurring payment collection system acknowledges that the recurring payment has been made in responsive to the recurring payment being processed by the payment system.

Using quick response (QR) codes to collect recurring payments

In embodiments, a reusable and adaptive multi-task orchestration dialogue system orchestrates a set of single-task dialogue systems to provide multi-scenario dialogue processing. In embodiments, for each question propounded by a user, using a deep learning predictive model, a best single-task dialogue system is chosen out of the set. In embodiments, multi-task orchestration is done without the need to change, or even understand, the inner workings or mechanisms of the individual single-task dialogue systems in the set. Moreover, the multi-task orchestration is also unconcerned with what rules are set in each individual single-task dialogue system. In embodiments, prior to selection of the best single-task dialogue system to return the best answer, new intents and entities are discovered and used to update an existing dialogue path. In embodiments, additional data is continually collected, and used to retrain model so as to further improve performance.

Cognitive orchestration of multi-task dialogue system

Balancing resource usage for client applications workload and data merge optimization of the backend for both a local merge within one server and a merge across multiple servers is determined based on previous resource usage pattern in a distributed storage system.

Planning of data segment merge for distributed storage system

Growing community of inventors

Shanghai, China

Xin Ni