Tokyo, September 28, 2017

Hitachi today announced the development of active-learning dialogue data-based AI technology to enable EMIEW3, Hitachi's human symbiotic service robot, to spontaneously "learn" how to respond to questions that it could not previously answer. EMIEW3 clarifies the meaning of enquiries with related staff through dialogue interaction, and in the process, automatically increases its dialogue contents to increase "comprehension" for appropriate responses. Hitachi is currently developing EMIEW3 with view to use in customer service and guidance settings. Using this technology, EMIEW3's dialogue contents can be enhanced by staff without specialist training, simply by responding to queries posed by EMIEW3, and was found to reduce labor-hours for this process to about one-tenth the time previously needed. Further, this technology allows EMIEW3 to learn more quickly about products or facilities which may change daily, as well as increase comprehension and correctly respond to customer enquiries. Hitachi is aiming to provide even higher quality dialogue data-based solutions by using this technology.

In recent years, in light of companies facing labor-shortage for customer service desks, there is an increasing anticipation for advanced robot-based voice-dialogue solutions. Hitachi has conducted several field-tests for customer service and guidance solutions with EMIEW3 through which it has found that due to wide variation in how a customer query might be posed, that in some cases EMIEW3 is unable to comprehend the nature of the question, and thus unable to answer the question. To address this issue, conventionally, a system administrator would need to continuously analyze interaction logs even after commencement of the service, and regularly expand the dialogue contents. Recognizing the importance of being able to efficiently expand the dialogue contents after the service has been initiated, Hitachi developed active-learning AI technology that investigates questions which EMIEW3 was unable to answer, identifies the causes and clarifies questions that it did not previously understand, to enable EMIEW3 to "learn and grow" through voice-based dialogue with staff. The technology developed consists of the following two points:

  1. Active-learning technology
    Machine learning was applied to identify and spontaneously learn about components of the dialogue that could not be understood. The technology analyzes the causes of unanswerable questions, and classifies them into two patterns: one where the answer is not registered, and the other, where the intention of the query was not understood due to the question being expressed in an unfamiliar form. In the first case of where the question was understood but the answer is not registered, EMIEW3 will ask a staff member for the appropriate information. In the second case where the question could not be understood due to the way it was expressed, a similar question registered in the question-answer database will be sought, and EMIEW3 will confirms with a staff member if the similar question has the same intent as the query which could not be understood. The new "response" and "query expression" learned from the staff response is then automatically registered in the question-answer database.
  2. Technology to efficiently use newly learned query expressions
    Natural language processing techniques such as morphological analysis and syntax analysis were used to develop technology to efficiently learn new forms of expressing the query. The technology uses morphological analysis and difference detection to find interchangeable components from two different ways of asking the same question, and learns rules about diverse forms of how the same question might be posed (hereafter referred to as rephrasing). Further, syntax analysis and machine learning are used to check if incorrect rephrasing is remembered. Through this, more correct rephrasing rules are formed, and by applying this to other questions, increases the pattern of expressions which have the same meaning.

As a result, log analysis by system administrators become unnecessary, and enables daily enhancement of the dialogue contents by simple on-site dialogue between staff with appropriate business knowledge and EMIEW3.

Using this technology, Hitachi aims to provide higher quality correct response voice-dialogue solutions to businesses with customer service desks. This technology will be demonstrated with EMIEW3 in the showcase at the Hitachi Social Innovation Forum 2017 TOKYO, to be held from 1-2 November at the Tokyo International Forum in Yurakucho, Tokyo. Demonstration field-tests will also be conducted in collaboration with the Haneda Robotics Lab at as part of the Haneda Airport Robot Experiment Project.

Figure: Learning process (credit: Hitachi)

Figure: Overview of this technology (credit: Hitachi)

Source: Hitachi

Read more

Comments

No comments to display.

Related posts

EU's Call for Proposals: An empowering, inclusive Next Generation Internet

The objective is to support actions on smarter, open, trusted and personalised learning solutions to optimise digital learning and to allow learners to engage and interact with content and with peers.
Application Deadline in 5 months

Singapore to establish Additive Manufacturing Facility and Applications in Maritime Sector

The facility’s location also leverages PSA’s parts supplier base and facility operations to support just-in-time inventory. This move towards digitised inventories reduces the need to hold excess inventory, which lowers storage costs, while shortening turnaround time from weeks to days due to improved availability of spare parts. In the long run, PSA will expand the scope of these services to the wider maritime industry, including ship owners, to help build its business adjacencies.

EU's Call for Proposals: The AQUAEXCEL2020 twelfth call for access

The facilities available cover the entire range of production systems (cage, pond, recirculation, flowthrough, hatchery and disease challenge); environments (freshwater, marine, cold, temperate and warm water); scales (small, medium and industrial scale); fish species (salmonids, cold and warm water marine fish, freshwater fish and artemia); and fields of expertise (nutrition, physiology, health & welfare, genetics, engineering, monitoring & management technologies).
Application Deadline in a month

Environment and Big Data: Role in Smart Cities of India

This study identifies six environmental factors, which should be integrated in the development of smart cities. These environmental factors include indicators of landscape and geography, climate, atmospheric pollution, water resources, energy resources, and urban green space as a major component of the environment.

Corteva Agriscience and IRRI Ink Partnership to Develop Advanced Rice Technologies and Programs

The partnership seeks to improve the genetic outcomes of breeding programs, encourage sustainable rice cultivation, and develop new rice varieties which deliver higher yields and are more resilient against biotic and abiotic stresses.

Call for Applications: Communication projects which mitigate anthropogenic climate change

The Minor Foundation for Major Challenges (MFMC) is inviting applications from all over the world to fund communication projects which mitigate anthropogenic climate change.
Application Deadline in a month

EU's Call for Proposals: Digital technologies for improved performance in cognitive production plants

Proposals need to develop new technologies to realise cognitive production plants, with improved efficiency and sustainability, by use of smart and networked sensor technologies, intelligent handling and online evaluation of various forms of data streams as well as new methods for self-organizing processes and process chains.
Application Deadline in 4 months

Study reveals best use of wildflowers to benefit crops on farms

For the first time, a Cornell University study of strawberry crops on New York farms tested this theory and found that wildflower strips on farms added pollinators when the farm lay within a "Goldilocks zone," where 25 to 55 percent of the surrounding area contained natural lands.

EU's Call for Proposals: Reinforcing the EU agricultural knowledge base

Activities shall analyse and compare the approaches taken on their performance and impact for farmers/foresters as well as effectivity of the communication and information channels used for dissemination in countries and regions.
Application Deadline in 3 months

The Bali Fintech Agenda: A Blueprint for Successfully Harnessing Fintech’s Opportunities

In response to the Bali Fintech Agenda, the World Bank will focus on using fintech to deepen financial markets, enhance responsible access to financial services, and improve cross-border payments and remittance transfer systems.