industry news
Subscribe Now

Open Source Software to realize Conversational AI – COTOBA Agent OSS

COTOBA DESIGN released their core technology as OSS, focused on industry use.

COTOBA DESIGN [https://global.cotobadesign.com/], Tokyo based Conversational AI Product Startup, releases their core technologies as Open Source Software (OSS), entitled “COTOBA Agent OSS.” This allows you to: (a) Embrace industrial conversational AI as a white box: It can utilize sensor information from IoT with external APIs; (b) Utilize its secured and scaling-out capabilities: More than 5,000 tests are conducted for large-scale commercial use; (c) Commercialize the OSS with MIT license: There is no limitation to copy, modify, merge, publish, distribute and sublicense.

“You can develop your own Siri(TM) or Alexa(TM) alternative from scratch with COTOBA Agent OSS for a wide-range of enterprise applications. Those are not chat bots, but voice user interfaces which share your feelings with intelligent real systems such as robots, autonomous vehicles, factory automation controllers, and digital signages.” said Mick Etoh, President and CEO of COTOBA DESIGN. “However, applying such an interactive interface to a full-fledged industrial application is not easy. The dialog engine, which is the core technology of conversational AI, often involves the following problems.”

1. Expandability to industrial applications: Until now, the fundamental functions provided by conversational AI have been input in natural languages such as voice and chat, and it is difficult to integrate with IoT and connect with external APIs, making it difficult to apply in industrial fields.

2. Usability of dialog operation data: The data is not retained by the user companies and cannot be used to improve or market their services.

3.  Transparency of technical specifications: The inside is black boxed, so the user companies don’t know what’s going on, and it’s hard to deal with when problems arise.

“To solve these problems, we have released the core technology of dialog agents as open source software, COTOBA Agent OSS. It is designed to be available in multiple languages and is available in Japanese and English at launch.”

In addition, he said “by using COTOBA Agent OSS, you can freely implement and execute a dialog agent regardless of cloud or on-premise environments. It is also widely available for commercial use under the MIT license.”

The GitHub repository: https://github.com/cotobadesign/cotoba-agent-oss/

Leave a Reply

featured blogs
Nov 5, 2024
Learn about Works With Virtual, the premiere IoT developer event. Specifically for IoT developers, Silicon Labs will help you to accelerate IoT development. ...
Nov 13, 2024
Implementing the classic 'hand coming out of bowl' when you can see there's no one under the table is very tempting'¦...

featured video

Introducing FPGAi – Innovations Unlocked by AI-enabled FPGAs

Sponsored by Intel

Altera Innovators Day presentation by Ilya Ganusov showing the advantages of FPGAs for implementing AI-based Systems. See additional videos on AI and other Altera Innovators Day in Altera’s YouTube channel playlists.

Learn more about FPGAs for Artificial Intelligence here

featured paper

Quantized Neural Networks for FPGA Inference

Sponsored by Intel

Implementing a low precision network in FPGA hardware for efficient inferencing provides numerous advantages when it comes to meeting demanding specifications. The increased flexibility allows optimization of throughput, overall power consumption, resource usage, device size, TOPs/watt, and deterministic latency. These are important benefits where scaling and efficiency are inherent requirements of the application.

Click to read more

featured chalk talk

Ultra-low Power Fuel Gauging for Rechargeable Embedded Devices
Fuel gauging is a critical component of today’s rechargeable embedded devices. In this episode of Chalk Talk, Amelia Dalton and Robin Saltnes of Nordic Semiconductor explore the variety of benefits that Nordic Semiconductor’s nPM1300 PMIC brings to rechargeable embedded devices, the details of the fuel gauge system at the heart of this solution, and the five easy steps that you can take to implement this solution into your next embedded design.
May 8, 2024
39,093 views