Enhancing Romi's Conversations: The Role of BigQuery and LLMs - Build What's Next
Blog

Enhancing Romi’s Conversations: The Role of BigQuery and LLMs

900

Of your peers have already read this article.

3:30 Minutes

The most insightful time you'll spend today!

Explore MIXI's journey in refining Romi's dialogue with BigQuery data analysis and the integration of large-scale language models, shaping the future of AI-based communication.

MIXI, Inc. (MIXI) is a social networking organization that provides a diverse range of services for friends and family to enjoy together, such as the social-media platform mixi, a mobile game called Monster Strike, and a family photo and video sharing service known as FamilyAlbum. One of our current projects is Romi, a social robot launched in April 2021 that uses Speech-to-Text by Google Cloud as its speech recognition engine.

Since the late 2010s, the social robot market has been booming, with some models becoming increasingly affordable for consumers, from robotic tutors that promote social and cognitive development for children, to companion robots for elderly care. But with Romi, there is a marked difference in the quality of dialogue that makes Romi distinct from most social robots. 

The biggest feature of Romi is that the AI developed internally by MIXI can generate natural exchange of communication. The size of a hand-held device, Romi can be placed anywhere in a room and has a screen to demonstrate different facial expressions. It responds to conversation within context. Until now, AI has been used to interpret the intentions behind user speech, but Romi is an AI-powered robot that takes it a step further, generating spoken conversations. After all, Romi was created to offer heartwarming communication to those who are looking for it. This form of speech recognition did not exist before Romi was released. We hope users will enjoy conversing with it, including the occasional unexpected response.

https://storage.googleapis.com/gweb-cloudblog-publish/images/1_MIXI.max-1800x1800.jpg

The speech recognition part was one of the most critical aspects of Romi. Most of the infrastructure that makes up Romi uses a main public cloud, which was used for other services then. As for speech recognition, we decided to try out the Speech-to-Text tool by Google Cloud, which was praised for its overwhelmingly high accuracy, and the prototype’s results were very positive. Even though we tried other companies’ services before making the final decision, our conclusion about Speech-to-Text remains the same. 

The accuracy and responsiveness of Speech-to-Text made the tool an effective one for a social robot like Romi. Google Cloud also provided a sense of security with its high reliability that has been demonstrated in enabling Romi’s workloads, and will be able to support continuous development of Romi’s services for the long run.

With the rapid development of speech recognition technology, MIXI decided to re-examine the speech recognition engine for Romi in June 2022, about a year after its release. We eventually decided to continue its use of Speech-to-Text. We reviewed about 10 companies’ Japanese-compatible speech recognition engines, and found that Speech-to-Text offered the best results. In addition, Speech-to-Text has several speech recognition transcription models, but we found that the latest short model, which specializes in short utterances, is more suitable for Romi than the default model.

The cost-savings that Speech-to-Text delivers is also impressive. The billing unit was changed from 15 seconds increments rounded up, to one second in November, and huge cost reductions could be expected with Romi. This is important to us because Romi does not have trigger phrases, such as “OK Google,” so as to achieve more natural conversations. As a result, it can recognize and process more speech as compared to other social robots. While this results in a more user-friendly experience, it also requires greater workloads and can incur a higher cost compared to most speech recognition engines. But with the updated billing system that Speech-to-Text delivers, we are able to continue refining Romi’s speech recognition accuracy while keeping costs low. 

Improving data analysis with BigQuery

Google Cloud was only used for speech recognition initially, but as Romi’s range of service expanded, more aspects of Romi were hosted on Google Cloud. Among these features, the machine learning platform for AI was moved to Google Cloud at an early stage. To be able to make use of a cloud platform at an affordable cost makes Google Cloud very appealing. Premium Support and technical account management helped us with our cost considerations.

Furthermore, MIXI started migrating the data analysis platform for Romi to BigQuery last year. BigQuery was chosen because it excels at bringing together and analyzing big data in various formats, as in-depth data analysis becomes necessary to improve Romi’s services. What also makes BigQuery an attractive choice was the ability to introduce structured query language (SQL) to BigQuery, a language that the development team from MIXI is familiar with. 

In particular, we are grateful for the use of software like Looker. It takes a lot of work, even for engineers, to write complex queries, but with Looker, even non-engineers can intuitively perform fairly complex analysis. About half a year ago, we held regular briefings mainly for employees interested in data analysis, and now they voluntarily conduct analysis, conduct discussions based on the results, and create new projects and ideas. This has become a regular workflow for us.

Currently, what is popular in AI-based communication is the emergence of large-scale language models (LLMs) that learn from huge amounts of data, and generate natural responses on a different level than before. 

To improve the conversational experience with Romi, we have been looking into relevant LLM technologies for a while now. It is important to be able to use high performance GPUs as inexpensively as possible in order to run PoC at high speed. We will continue to focus on Google Cloud services, including Compute Engine and VertexAI.

Trend Analysis

Cloud and AI Paves the Future of Finance: Excerpts from FIA Boca 2022

6611

Of your peers have already read this article.

4:00 Minutes

The most insightful time you'll spend today!

Majority of businesses in the financial markets offer services on cloud. As cloud consumption mostly increases over the next few months, there are new ways technologies can help lay the foundation for the finance industry. Read more!

Financial markets were among the first to adopt new technologies, and that has certainly been true of the derivatives markets, which were early adopters of electronic trading. Going forward, new capabilities will transform the way industry participants communicate, analyze, and trade.

I sat down with Google Cloud’s Phil Moyer and former SEC Commissioner, Troy Paredes, for a fireside chat at FIA Boca 2022 to discuss the future of markets and policy, the new technologies that are already paving the way for greater speed and transparency, and how cloud can help promote greater resiliency, performance, and security to enable the long-term vision for the market. The following is a summary of our discussion.

The current state of cloud technology


When it comes to technology adoption, we’re seeing the market and participants adopt cloud technologies, and increasingly, machine learning (ML) on a wider scale. Cloud technology allows for easier, faster, and much more secure experimentation with large datasets and ML.

A recent Google sponsored study by Coalition Greenwich (September, 2021) showed that more than 93% of trading systems, exchanges, and data providers are in some way providing services on the cloud. The same study, revealed that about 72% of the financial industry across the buy side and sell side, intend to consume public cloud-data based market data within the next 12 months.

Data-driven decision-making and risk management have always been, and continue to remain, the cornerstones of the financial markets. Over time, technology innovation has facilitated access to better insights from data, and therefore, better decision-making and the ability to manage risk. That expectation is now mainstream, and will continue to grow in sophistication.

The multi-phased technology trajectory


The movement of exchanges to the cloud will occur in a “crawl-walk-run” fashion, with low-hanging fruits the first to be picked in the near term while bigger, paradigmatic changes will occur over the medium and long term. Some organizations are starting all three stages simultaneously, understanding that each will move at an independent cadence.

The “crawl” phase is one in which foundations are built, starting with organizations moving data to the cloud and experimenting with some degree of analytics. It’s one of the most important phases because it’s where the opportunity to increase transparency and risk management takes shape.

In moving to the cloud, the infrastructure – which in the past relied on a combination of people, processes, and some technology – becomes the code that runs applications. This early phase is key to empowering organizations to shift to a cloud-based, agile-first operating model that makes it easier and more seamless to launch new products in the future, including by freeing up people and resources from IT management to more mission-focused work.

Establishing the cloud operating model simplifies the “walk” and “run” phases where compliance is more automated, latency-sensitive applications are more readily available, and the next generation of exchanges, market participants, and regulators is better prepared to meet future challenges.

The “walk” phase is where much of the innovation happens. Exchanges are making significant progress in leveraging foundational data decisions in the “crawl” phase and innovations in the cloud to improve settlement, clearing, risk management, collateral management, and compliance, and launch new products.

And finally, the “run” phase is where organizations will start to move the latency-sensitive markets to the cloud, as the markets increasingly will demand low-latency and high performance along with transparency and analytics to solve historical obstacles to market access.

Opportunities for both regulators and market participants


Any time significant technological change takes place, regulators explore its implications, particularly with respect to their ability to meet their regulatory objectives.

Increasingly, we are seeing technological change driving more opportunities for regulators and market participants alike. Such changes may also allow better protection of the marketplace, with greater integrity and transparency.

Over time, regulatory regimes – rules, regulations, statutes, interpretations, and guidance – will also adjust to new technologies, both benefiting the marketplace and advancing regulatory goals.

As one example, the cloud is increasing the ability to meet compliance obligations by allowing compliance to be built into transactions. Moreover, predicated on the vision of real-time regulatory reporting, and given the pace of technological change in the marketplace over the last several years, various regulators have been using more advanced analytics. This trend will continue to help them more effectively and efficiently meet their objectives, and monitor and meet the expectations they have for the entire market.

Machine learning’s role in the financial markets


Google Cloud’s head of AI and Industry Solutions, Andrew Moore, said that ML will be doing three key things for us in the next 10 years: giving us meaning, providing concierge services, and serving as a guardian. Extracting information that is critical to investor decision-making can be extremely important. With more data than ever, ML can increase the ability to process it while also becoming more accessible in the cloud and better supporting regulatory objectives.

The technology will likely manifest in trading and anti-money laundering activities as they relate market functions, as well as managing a wide variety of risks – supporting the interests of both investors and regulators in terms of decision-making, surveillance, and protections.

Rather than taking individuals out of the equation, the digitization of markets, assets, and guard rails combined with ML will allow people to focus their expertise in different ways to achieve key objectives.

Building the market foundation for the future


The goals of operational resiliency, security, and privacy will continue to be critical for building the market foundation for both participants and regulators. While technology promises to create advantages in concrete, tangible ways, it will be important to scrutinize potential risks and concerns.

Priority one for technology providers is to build an environment of trustless security, including encryption at motion and encryption at rest, ensuring that markets are operationally resilient while instilling confidence for any exchange that runs on top of that infrastructure. Multicloud architectures and approaches are likely also to be part of the solution for operational resilience.

Throughout time, liquidity has been the outcome of improved access, transparency, and security. Technology providers are responding by sharing both the responsibility for, and fate of, the markets of the future to build an efficient, faster, and more transparent and secure financial industry.

You can learn more about our approach in our newest white paper, Building the financial markets foundation for the future.

Blog

Announcing reCAPTCHA Enterprise’s Mobile SDK to Help Protect iOS, Android apps

4209

Of your peers have already read this article.

2:30 Minutes

The most insightful time you'll spend today!

reCAPTCHA Enterprise is Google’s online fraud detection service that leverages more than a decade of experience defending the internet. reCAPTCHA Enterprise can be used to prevent fraud and attacks perpetrated by scripts, bot software, and humans. When installed inside a mobile app at the point of action, such as login, purchase, or account creation, reCAPTCHA Enterprise can block fake users and bots while allowing legitimate users to proceed.

To provide more complete coverage for native mobile iOS and Android applications, we’re announcing the general availability of the reCAPTCHA Enterprise Mobile SDK. Designed with digital-first and mobile-first organizations in mind, the new Mobile SDK fully integrates reCAPTCHA Enterprise’s frictionless experience on end-users’ mobile devices.

Why should I use the Mobile SDK?

Unlike most web applications, iOS and Android apps run on physical devices that can provide a wealth of device telemetry to help identify fraud and bot activity. By combining both device and network signals, the new mobile SDK can better protect native mobile applications from bot attacks while unlocking the full potential of reCAPTCHA Enterprise. It provides:

  • Frictionless customer experience — no picking fire hydrants from a grid
  • Easy integration to your native mobile app with support for popular frameworks like Cocoa Pods and Swift Package Manager
  • A regularly-updated device threat model to help stay ahead of attack evolution

Protecting against fraud across all your channels

Customers will be able to leverage the new mobile SDK to implement native iOS and Android protection against the OWASP Top 10 automated attacks common on the internet, which include fraudulent account creation, financial hijacking, and credential stuffing. This is particularly important for mobile workforces and end users who use a mobile app to access products and services. Since mobile traffic surpasses web traffic in many industries, it’s even more important to implement a comprehensive mobile app protection strategy to protect against the most prevalent attacks.

Integrating the new Mobile SDK

If you’re interested in learning more about how to integrate the new Mobile SDK, check out the documentation for iOS and Android. Mobile and Web integrations leverage the same easy to understand pricing for Assessments, found here.

Blog

Google’s Default Messaging Apps for AT&T Android Users Ensure Richer Conversations

5552

Of your peers have already read this article.

1:30 Minutes

The most insightful time you'll spend today!

Google and AT&T announce collaboration to make Google Messaging apps the default feature for AT&T customers with Android devices for consistent, secure and enhanced messaging experience. Read to explore more features in Messaging.

Today, we’re announcing that we’re working with AT&T to establish Messages by Google as the default messaging application for all AT&T customers in the United States using Android phones. The collaboration aims to help accelerate the industry toward global Rich Communication Services (RCS) coverage and interoperability to offer a consistent, secure, and enhanced messaging experience for all Android users around the world.

“Many AT&T customers have enjoyed the advantages of RCS for years when texting with friends and family,” said David Christopher, executive vice president and general manager – AT&T Mobility. “We look forward to working closely with Google to extend these benefits to even more of our customers as they enjoy richer conversations with others around the world.”

Working together, AT&T and Google will continue the momentum to upgrade SMS with enhanced messaging features offered in Messages, which includes the support of chat features based on the open RCS standard. With Messages as the default messaging application, all AT&T customers using Android devices will get enhanced features so they can:

  • Share full-resolution pictures from a recent event or vacation 
  • Send a higher-quality video of that soccer goal and the celebration that followed
  • Know when someone is replying to a text
  • Send and receive messages over Wi-Fi or data
  • Participate in group chats where it’s easy to add someone else to the conversation, or let someone leave, without starting a brand new thread
RCS-AT&T 3.gif

In addition to these features, we’re also rolling out end-to-end encryption for one-on-one RCS conversations between people using Messages and people who have chat features enabled.

E2EE - AT&T.jpg

For years, we’ve been working with the mobile industry and device makers to bring enhanced and secure messaging to everyone on Android. Today’s announcement—that AT&T customers using Android devices will soon be able to enjoy these features by default—is a major step forward.

4581

Of your peers have already watched this video.

1:30 Minutes

The most insightful time you'll spend today!

Blog

Introduction to Cloud Shell Editor

Watch the video to understand how Google’s Cloud Shell Editor and its powerful features-packed environment can streamline your development workflows.

Blog

Beyond Traditional Learning: AI-based Online Learning Platform and Google Cloud Solutions Push Learners to Get Ahead

10342

Of your peers have already read this article.

1:30 Minutes

The most insightful time you'll spend today!

Poorly designed and time consuming content detracts from online learning and course completion. KIMO.ai and Google Cloud solutions bring forth an AI-based learning platform to generate individual learning paths. Learn how it's different!

The combination of a vital need for IT experts among businesses and a digital skills gap is making lifelong learning increasingly critical. Beyond professional development, learning new skills offers additional rewards from building peer connections to boosting your creativity. That’s why in 2020 Krishna Deepak Nallamilli and I launched KIMO.ai to reimagine how people approach learning, especially in developing markets. Our team is building the artificial intelligence needed to generate individual learning paths through a wide range of quality digital learning content.

Google Cloud and its Startup Program have been instrumental in connecting our team with the tools, people, processes, and best practices to grow our business. 

Existing learning platforms lack engagement

Outside of traditional education settings, massive open online learning courses (MOOCs)—often modeled after university courses—can provide a flexible and affordable way to upskill or reskill. But the vast majority of people who participate in MOOC programs fail to complete courses. Based on our research, the challenge with existing learning platforms is a lack of engagement, primarily caused by limited direction on which skills to learn, whether AI, fintech, blockchain, or other in-demand disciplines.   

We’ve also received feedback that many corporate learning management systems–developed as online training systems to upskill employees–tend to be poorly designed and time-consuming to use. 

Overall, a significant challenge with most existing learning platforms is that they’re generic. For example, suppose you’re interested in learning about AI. In that case, you need AI-related coursework that applies to your industry and the job you want because AI in medicine is vastly different from AI in financial services. Today’s online learning options typically take a one-size-fits-all approach and fail to capture the nuances of what learners really need to get ahead. 

Building a future-proof learning platform 

The commitment to highly personalized, accessible learning inspired KIMO.ai, a platform that we believe is the future of education. Depending on your goals, current skills, location, and other factors, our AI-based platform will identify which coursework (and where to find those classes) to build the skills you need. The more personalized, relevant learning recommendations even take into account people’s preferences for podcasts, MOOCs, books, articles, videos, courses, publications, and more.  

In a mix of cooperation and competition we call “coopetition,” KIMO.ai will regularly recommend courses from other established online learning systems if, based on our automated assessment, it’s the best option for a learner. There’s also the option to access free content only. 

Google cultural alignment fosters trust

Our platform started with one developer exploring NLP models and Google APIs. As we’ve grown our team and launched our beta to 110,000 users in developing markets, we discovered there is a lot of interest in our platform, and we believe we can make a significant impact. In feedback forums, we also learned that we need to focus our efforts on the mobile experience to improve engagement since 99% of the beta testers use mobile devices. 

Beyond our team’s high level of trust in Google Cloud solutions, our team also appreciates the cultural alignment with Google. We value Google’s developer-centric approach and rely on tools like Dataflow for batch data processing and Cloud TPU to reliably run machine learning models with AI services on Google Cloud. We also build all of our deployments on Google Kubernetes Engine (GKE), which makes it easy to manage all our containerized workloads 

On the front end, Google App Engine makes it easy to deploy apps and experiment, and it integrates seamlessly with Firebase for authentication and more. BigQuery is our serverless data warehouse that efficiently scales to support the millions of articles, videos, and other learning resources we need to analyze to provide the targeted coursework recommendations our learners require.

As we grow our business having a network of trusted advisors is also extremely valuable. By working closely with DoIT International, the 2020 Google Cloud Global Reseller Partner of the Year, our team has access to their cloud, Kubernetes, and machine learning expertise. DoIT has already helped us quickly resolve IT issues and create analytics dashboards that give us insights to continually enhance our services. 

Building for a growing industry

The dynamic edtech market is growing rapidly and estimated to become an $11B industry by 2025. We’re proud to be part of the next wave of personalized education that has the potential to empower people in developing markets and beyond to grow their skills with coursework tailored to their exact needs and how they like to learn. This year, we will deliver our platform to at least 400,000 more people. We’re excited to see how they use it and where it takes them. 

If you want to learn more about how Google Cloud can help your startup, visit our Startup Program application page here to get more information about our program, and sign up for our communications to get a look at our community activities, digital events, special offers, and more.

More Relevant Stories for Your Company

Blog

Google Cloud’s Transfer Services Helps Move Nuro’s Petabytes of Data from Edge to the Cloud

Engineers that build last-mile delivery services belong to an elite order, a hallowed subcategory. Delivery customers are incredibly demanding when it comes to speed and convenience, and the services they use must take variables like increased traffic, road conditions, human error, and even driver availability into account every day. Nuro

Blog

New to Cloud Functions? Here’s What You Need to Learn

Cloud Functions is a fully managed event-driven serverless function-as-a-service (FaaS). It is a small piece of code that runs in response to an event. Because it is fully managed, developers can just write the code and deploy it without worrying about managing the servers or scaling up/down with traffic spikes.

Blog

The Evolving Landscape of Multicloud: A Journey, Not a Destination

Editor's note: This post is part of an ongoing series on IT predictions from Google Cloud experts. Check out the full list of our predictions on how IT will change in the coming years. Prediction: Over half of all organizations using public cloud will freely switch their primary cloud provider

Case Study

Google Cloud’s Suite of DevOps Speeds Up ForgeRock’s Development

Editor’s note: Today we hear from ForgeRock, a multinational identity and access management software company with more than 1,100 enterprise customers, including a major public broadcaster. In total, customers use the ForgeRock Identity Platform to authenticate and log in over 45 million users daily, helping them manage identity, governance, and access management across

SHOW MORE STORIES