Kohtaroh Miyamoto

The Dialog manager a system for managing procedural knowledge

The Dialog Manager is a conversational web-based tool that helps organizations manage procedural knowledge. In the modern enterprise, procedural knowledge is of particular importance for service delivery organizations. The Dialog Manager helps standardization of operating procedures in order to deliver a consistently high level of service. In turn, it provides a systematic approach to capturing, managing and disseminating procedural knowledge. The Dialog Manager captures procedural knowledge in the form of dialogs that serve as interactive guides by offering a visual knowledge representation and an integrated content management system. It also provides a sophisticated conversation management mechanism that records and manages the activation status of nodes in a conversation. With advanced question selection algorithms, it makes the performance of procedural knowledge effective. The Dialog Manager has been piloted with the Application Management Services practice of IBM Global Business Services. Currently, the Dialog Manager is being used primarily for teams managing and supporting software applications for large enterprise customers in service engagements. We currently have several hundred users and expect the user population to grow to several thousand by the end of the year. The system has been received enthusiastically by users and in a recent survey. We found that over 70% found the tool to be of value to them and that it significantly improves the productivity of the practitioners. While the initial area of deployment has been in the area of IT services, the Dialog Manager is equally well suited to handling all kinds of procedural knowledge in the enterprise.

Document Quality Checking Tool for Global Software Development

Software development projects often utilize global resources to reduce costs. Typically a large volume of unstructured office documents are involved. Unfortunately, in many cases the low quality of unstructured documents due to various location-related barriers (e.g. time zones, languages, and cultures) can cause negative effects on the outcomes of projects. Several approaches have been introduced for document quality checking but they have not generalized well enough to handle various unstructured documents in a broad range of projects. Based on past experience, we have prepared guidelines, templates, rules, and document quality-checking tools for designing and developing global software development projects. In this paper we specifically focus on the effectiveness of our document quality checking tool. The challenges for such a checking tool are that it must be generally adaptive and also highly accurate to be practical for industrial use. Our approach is template-based and consists of an extraction process for the physical-syntactic structure, a transformation process for the logical-semantic structure and an analysis process. Our experiments inspected 66 authentic customer documents, detecting 118 errors. The accuracy as measured by the true-positive ratio (accurately detected true errors) was 98.3% and the true-negative ratio (accurately detected non-errors) was 99.4%.

Improving IT Service Incident Resolution by Using an FAQ System

As the enterprise computing becomes more and more complex, recently, the cost of IT system maintenance in enterprises has become a significant problem from the perspective of technology as well as business operations. One approach to managing the IT system maintenance cost is preparing and leveraging an FAQ (Frequently Asked Questions) system as a way of knowledge management and reuse. However, because the preparation of an FAQ system and data may take significant investment, a cost justification for such a system is essential. In an effort to analyze the cost and effect of the FAQ approach, in this paper, we observed a software maintenance project where 66 FAQs were prepared and monitored for a period of 15 months. We found that 67% of the practitioners resolution time was saved with FAQ references. We also applied our novel Natural Language Processing techniques using conditional branches, sequential analysis and topic detection as domain independent methods. We found that the number of text segments has strong correlation with the time and cost savings. We designed an FAQ system based on these findings and observed that more than 70% of the practitioners who tested the system reported that it is useful and significantly improved their productivity.

Inter-organizational Business Processes Managed by Blockchain

Blockchain technology is highly expected to be a solution to the consistency and trust problems in managing business processes that span across organizational boundaries. However, to execute collaborative business processes, we need a mechanism for enabling entire workflows as a whole, where participants’ private processes must agree on the shared inter-organizational processes realized by Blockchain. To address this, we introduce a set of techniques that take business process models as input and transforms them into statecharts for Blockchain and process participants. We also optimize the size of the statechart in order to reduce the number of communications between Blockchain and participants. The statecharts are then used as a basis for generating software artifacts: smart contracts running on Blockchain and Web applications for process participants. Through the evaluation of our solution, we confirmed that our algorithms produce software artifacts that collaboratively work together. By applying the statechart reduction algorithms, we could reduce the number of sending and receiving events by 74% and 65% in two case studies.

Obtaining Exhaustive Answer Set for Q&A-based Inquiry System using Customer Behavior and Service Function Modeling

Abstract When customers are interested in a service or intend to buy it, they sometimes have questions on that service. In this study, we considered an inquiry system in which customers ask questions on a specific service and obtain correct information on the service. For such an inquiry system, a question-answering (Q&A) technology is needed. Many programming modules for such a technology have been developed and can be easily used for system development. In many Q&A technologies, machine-learning techniques are involved, and we need to prepare training data consisting of pairs of an answer and assumed questions. For training-data preparation, an answer set for a service should be defined as the first step and the answer set should cover all the information on the service that customers may ask about. By using a customer-behavior model and introducing a service-function model, we propose a method of effectively collecting knowledge information for an answer set on a service. Through a case study, we show that we can collect exhaustive knowledge information for an answer set with our method compared to the case in which domain experts collect knowledge information in their own way. For an actual project, we also considered an actual inquiry-system-development project, with training data obtained with the proposed method, and showed that the system covers almost all the information on the service that customers may ask after a user test.

Hierarchical context supplementation for consecutive question answering

Question-answering (QA) systems have recently shown impressive results in terms of accurately answering user questions in such situations as domain specific user questions. However, we have identified many real situations where QA systems must cope with not a single question-answering situation but rather a sequence of consecutive questions. In such cases, users often ask questions on the basis of the previous answer they have received, so the context of the questions changes on a certain level. The commonly used method to handle this problem when using a QA system is to append the current question to the previous question (append method). However, the append method is not designed to detect such context changes. To deal with such context changes, we have designed a hierarchical context supplementation QA System (HCSQ). The HCSQ handles consecutive questions by matching the current question with the hierarchical domain knowledge database structure of the previous answer and then supplements the context of the current question with the required keywords. We also show that our method can be further applied to the initial question to supplement omitted context. Experimental results show that our method substantially outperforms the state-of-the-art methods.

Effective data curation for frequently asked questions

Frequently-asked-question (FAQ) systems are effective in operating and reducing costs of IT services. Basically, FAQ data preparation requires data curation of available heterogeneous question-and-answer (QA) data sets and creating FAQ clusters. We identified that the labor intensiveness of data curation is a major problem and that it strongly affects the final FAQ output quality. To deal with this problem, we designed a FAQ creation system with a strong focus on the effectiveness of its data-curation component. We conducted a field study by inspecting two sources: incident reports and a QA forum. The first source of incident reports showed a high F-score of 89.9% (precision: 82.5%, recall: 100%). We also applied the same set of parameters to 300 entries of the QA forum and achieved an F-score of 94.3% (precision: 94.9%, recall: 93.8%).