:::

【2020 Solutions】 Driving AI with Chips, Fansi Data Multiplies Computing Power at Low Cost

編輯群2020-05-26

A tiny chip capable of driving AI algorithm speeds by nearly a hundredfold, Fansi Data's team is dedicated to software and hardware integration, providing industries including finance, smart healthcare, and smart manufacturing with a cost-effective, high-efficiency way of introducing AI and rapidly undergoing digital transformation.

In recent years, artificial intelligence has been highly prominent; however, practical applications have been limited by high costs. The enhancement of 'computing power' is crucial for breaking through the bottlenecks in AI applications. Fansi Data's customized chip design and solutions can increase processing performance and effectively reduce costs, making AI applications in finance, healthcare, and manufacturing easy and feasible.

The company's core service is the high-performance hardware acceleration platform (FPGA)

Fansi Data was founded in October 2018 by a founding team from National Tsing Hua University, National Chiao Tung University, and National Taipei University. The company currently has 11 employees, including the chip design director Liu Wenkai from the IC design company Huirong Technology, who leads a 5-person IC design team. They spent over a year developing the high-performance hardware acceleration platform (FPGA), which became the company's core service.

Fansi Data integrates software and hardware to develop a high-performance hardware acceleration platform (FPGA)

▲Fansi Data integrates software and hardware to develop a high-performance hardware acceleration platform (FPGA)

'To bring AI to practical implementation, the challenges are cost and real processing situations. Purchasing a standard set of NIDIA GPUs is expensive. If we can adjust the hardware through customization, producing a setup tailored for use, the costs can be significantly reduced.' Said Liao Yanchin, General Manager of Fansi Data, who additionally pointed out that most AI startups currently only have software engineers and lack hardware engineers. Fansi Data excels in data handling and software/hardware integration, has an excellent team, and can efficiently solve data issues while developing software/hardware solutions tailored to customer needs.

Financial markets are notoriously fickle, as evidenced by the recent COVID-19 pandemic, which triggered a global stock market crash and was reinforced by program trading, leading to the unprecedented implementation of four trading halts in U.S. stock exchanges within a decade. This has significantly raised investors' risk awareness.

Zheng Zongyi, co-founder of Fansi Data, experienced in financial trading, points out that in financial markets such as stocks, futures, and warrants, 'speed' is often the key to victory. Typically, the traditional stock trading process involves financial trading data flowing from the network to the mainframe, processed through combination software, measured in milliseconds (ms, 10^-3 seconds), with an average transaction completed in 20 ms. System transaction processing speed, however, is at the nanosecond level (ns, 10^-9 seconds), and through the high-performance hardware acceleration platform (FPGA), each financial matching transaction can be completed in microseconds, a significant difference that can lead to billions in trading gains or losses, and is a major competitive edge for proprietary traders.

Financial services in the domain of securities firms' proprietary sections, new types of financial product trading departments, and high-frequency traders (or major retail traders). In the securities market, market volatility is the result of a tremendous amount of data. If the system operates at nanosecond speed, allowing you to see transaction information instantaneously, ahead by 0.1 seconds, you can make trading decisions before others even see the market data.

Service areas focus on financial technology and smart manufacturing

The risk control systems of bank credit cards can also utilize AI integration acceleration, similar to regulatory technology domains. Establishing an AI model can effectively identify risky credit card transactions and provide responses in a very short time, enhancing the security and smoothness of online transactions.

In the AI credit card risk control system, AI acceleration is also used through software integration. Transactions are prevalent, and fraud is common, similar to regulatory technology domains. By establishing an AI model, risky credit card transactions can be effectively identified, and responses given in a very short time, enhancing the security and smoothness of online transactions. This includes financial transactions and credit card risk identification, all through chip-based transaction data analysis and risk management system direct acceleration calculations.

Financial transaction information acceleration solution

▲Financial transaction information acceleration solution

Currently, many financial companies have their own IT departments, including data scientists, big data analysts, and AI algorithm engineers. What is Fansi Data's advantage in the financial sector? Zheng Zongyi points out that the IT departments in the financial industry are more 'users' of IT, not 'developers' of IT. Moreover, understanding IC design involves high costs, and the financial industry does not need to maintain their IC design team. The specialization is very clear, as Fansi simply develops models for the financial industry to adopt.

Considering personal privacy and data security, financial data is sensitive and often not easily accessible. Fansi Data, by joining the financial technology innovation park (FinTechSpace) and with the assistance of the Institute for Information Industry, applies for the real-time transaction data and corporate annual financial statements, historical trading data provided by the digital sandbox, using it to group data, analyze, model, backtest, and propose AI risk warnings and other solutions for abnormal transactions and risk management.

Besides financial technology, Fansi Data also focuses on AI applications in smart manufacturing, such as developing smart image meter reading through image recognition methods, which can help businesses reduce equipment replacement costs and achieve higher accuracy.

In the process of customized chip design, data analysis, and software/hardware integration, Fansi Data encounters difficulties in data and talent acquisition. At this stage, through interfacing with the digital sandbox and utilizing resources provided by the financial technology innovation park, AI models are built; regarding talent, a lean core team is established, continuously accumulating experience and building a robust entrepreneurial culture to face the ever-growing market demands.

From left to right: Co-founder Zheng Zongyi, General Manager Liao Yanchin, and Chip Design Director Liu Wenkai

▲From left to right: Co-founder Zheng Zongyi, General Manager Liao Yanchin, and Chip Design Director Liu Wenkai

「Translated content is generated by ChatGPT and is for reference only. Translation date：2024-05-19」

Recommend Cases

【解決方案】光禾感知科技智慧球場體驗 AR互動讓看球變得更加有趣
OSENSE Technology Qubby AI customer service helps enterprises comprehensively upgrade from customer service to knowledge management

"What are your business hours" "What are the functions and features of the product" "What discounts are available now" "Does the product have a warranty" "Does the manufacturer cooperate with the product for repair" From the perspective of consumers, every inquiry is a unique customer experience, but from the perspective of companies, 90 or more of these questions are repeatedly asked every day OSENSE Technology's Qubby AI customer service can help companies seize the opportunity to continue to provide high-quality customer services every time they come in contact with customers, and optimize service processes through AI to create an efficient service team Taiwanrsquos first IMSNS virtual human real-time interactive voice AI customer service Qubby AI The information age has caused changes in consumer behavior Companies have deployed online and offline platforms, such as official website apps for their brands, physical stores, distribution channels, and third-party e-commerce, to increase channels for contact with consumers However, this has created a greater workload for customer service personnel, who need to monitor even more channels to provide timely services OSENSE Technology's Qubby AI customer service helps enterprises integrate and manage multiple platforms, such as websites, LINE, Facebook Messenger, WhatsApp, and multimedia interactive machines, with a single account The service supports 29 languages and serves domestic and overseas customers 247, building good relationships by meeting customer needs and creating an endless stream of important and valuable customers Qubby AI customer service features Saves training time, standardized AI response, supports IMSNS, improves customer service efficiency, optimizes the service experience, and the web page is applicable everywhere Efficiently create enterprise-specific AI customer service in 3 steps, eliminating the need for design QA OSENSE Technology has condensed the establishment of Qubby AI customer service into three steps based on its years of experience with domestic and overseas projects and strong technical capabilities, so as to help enterprises build efficient teams The first step is to create an image and personify the corporate image Upload a profile photo, create a realistic or anime-style 3D virtual person, or customize a real person image, transforming the one-way corporate communication model in the past into a two-way interactive service model It not only improves brand favorability among customers, but is also an indispensable part of creating warm services The second step is to select the voice Qubby AI customer service can interact with customers through text, preset QampA, and voice For voice, users can choose the system's preset AI voice, or use AI to clone a real person's voice It supports the conversion of 29 languages, and is like customer service personnel providing services in person, increasing customersrsquo trust in the brand The third step is to establish a knowledge base An AI brain knowledge base can be created by simply uploading a PDF file For languages supported by AI translation for Chinese text, there is no need to design questions and answers one by one The AI machine trains and learns corporate and product knowledge, automatically extracts knowledge related to user questions, and integrates knowledge for responses, greatly shortening the development and training time Another feature of Qubby AI customer service is that it can incorporate "personality," such as liveliness, confidence, and gentleness, into the character, and give it "ambition" and "mission," making the customer service more flexible and closer to the corporate brand image Combined with industry Know-How, it can also become an industry-specific AI customer service application For example, Qubby AI DentalGPT, Taiwan's first AI customer service specifically developed for dentists, has been trained into an exclusive AI model and database of dental knowledge, health education information, and common issues of clinics, and was integrated into a convenient and easy-to-use package Companies only need to follow 3 steps Create an image, choose a voice, and build a knowledge base to quickly create an exclusive Qubby AI customer service Qubby AI's diverse applications help enterprises comprehensively upgrade from customer service to knowledge management Qubby AI customer service has been used a wide range of industries, such as the healthcare industry, financial industry, electronics industry, conference and exhibition industry, education industry, department store retail industry, public relations service industry, and celebrities The services range from external product sales, event promotion, and customer service to internal HR assistant, knowledge management, compliance, technical maintenance and applications It has become the most intelligent, efficient, and direct business partner for enterprises In addition to helping optimize the service process, allowing personnel to focus on solving truly difficult and valuable problems, Qubby AIrsquos back-end data records the number of times, the time, platform, device, and conversation history of customers using AI customer services, and can export the data Insights into customers can be further discovered from the conversations, and create new types of services to seize business opportunities The Qubby AI customer service back-end completely records user information and data A free 14-day trial offered to find distribution agents to jointly expand domestic and overseas markets To assist enterprises with digital transformation, OSENSE Technologyrsquos Qubby AI customer service offers a free 14-day trial, which provides AI text and expected voice customer services, AI knowledge base construction, a limit of 6,000 messages per month, and 3D virtual human default character to reduce enterprisesrsquo doubts about the AI solution Aside from its efforts to further develop Taiwanrsquos market, OSENSE Technology is actively expanding into international markets, such as the United States, Japan, and Southeast Asia In January 2024, it has signed a contract with the largest clinic management system developer in Southeast Asia to bring Qubby AI customer service southward, hoping to provide comprehensive AI digital services and solutions to medical institutions and people ofnbsp Southeast Asia, creating better healthcare experiences and expanding the smart healthcare ecosystem AI is ushering in a new industrial revolution According to Gartnerrsquos estimates, there are approximately 17 million customer service personnel working in customer service centers around the world 95 of the cost of a customer service center is from personnel Even if 10 of the service volume is automated, tens of billions of US dollars can be saved every year Based on the 2023 Taiwan Industrial AI Survey released by the Artificial Intelligence Foundation, nearly half of Taiwanrsquos companies still have not used AI services This shows the huge AI business opportunities OSENSE Technology is thus actively seeking distributors and agents to jointly expand domestic and overseas markets

這是一張圖片。 This is a picture.
Make Meeting Records Efficient and Time-Saving with DeepWave's Smart Meeting Ink AI

Meeting Ink Enterprise Edition is now being launched Studies show that around 50 of content is forgotten within two hours after a meeting if not tracked and reviewed immediately multiple reports and transmissions can result in losing over one-third of key information Precise meeting records are crucial for organizations with strict operational protocols and public sectors However, with extensive meeting demands, recording can lead to losses in meeting outcomes and increase team burdens Spotting this market pain point, Taiwanese AI startup DeepWave has introduced 'Meeting Ink'—a new solution for meeting records that integrates voice, text, and automated AI technologies Meeting Ink supports voice-to-text transcription, speaker recognition, verbatim translation, and automated meeting summary highlights, offering flexible services for consumers and enterprises This year, it has added real-time verbatim scripting and translation, creating a new paradigm in meeting management AI Technology Solves Meeting Recording Pain Points in One Go Since its launch at the end of 2023, 'Meeting Ink' has become a high-efficiency and accurate meeting record management solution on the market DeepWave combines its proprietary technology, third-party tools, and Microsoft Azure's voice recognition technology to create the best voice-to-text experience Furthermore, this includes speaker recognition and segmenting, multiple language translation, and meeting summary functionalities across various scenarios To achieve broader applications, Meeting Ink also provides real-time application solutions, making it suitable not just for regular meetings but also for events, forums, and educational sessions Currently, Meeting Ink supports both app and web platforms, offering enterprise customization options to expand its applications further Excellent Voice Recognition Technology and Optimal User Experience Meeting Ink stands out in the market due to its precise voice recognition technology and user-centered application design Relying on DeepWave's proprietary technology, Meeting Ink can convert audio signals into text representing each speaker, distinguishing each participant's voice to ensure information is clearly differentiated Additionally, meeting content can be further summarized according to the speaker and, with DeepWave's optimized system, generate exclusive summary templates for various scenes and roles Whether for executive meetings, academic forums, personal interviews, or learning sessions, Meeting Ink produces tailored summaries for different contexts, bringing higher efficiency and flexibility to meeting recording experiences Precisely Targeting Enterprise Needs, Providing Comprehensive Enterprise Applications Anticipating the shifting market demands, DeepWave has launched a customized service plan tailored for B2B frameworks, further optimizing Meeting Ink's application on the enterprise side Enterprise clients can use the professional edition and enjoy exclusive customized summary modules tailored to specific industry needs DeepWave commits to regularly updating AI modules to ensure the most advanced technological support Additionally, Meeting Ink's enterprise service plan emphasizes data security, account permission management, unlimited storage space, and multi-device compatibility supporting all recording scenarios Offered at the lowest market rates, this provides an economical and efficient solution for enterprises, allowing them to focus on core tasks and enhancing overall meeting efficiency Embracing the Pulse of the AI Era, Leading Market Applications According to a 2023 market report, the global market for AI application tools is expected to grow from nearly 7 billion to 50 billion over the next decade, with business and learning tools playing key roles Facing the rapid progression of AI technology, DeepWave leverages its technical prowess and innovative capacity to penetrate international markets with Meeting Ink, continually bringing revolutionary changes to meeting records for both businesses and individuals Going forward, DeepWave will continuously optimize Meeting Ink, committed to promoting the close integration of AI technology with everyday work and learning scenarios, creating more convenient and efficient working environments for users 「Translated content is generated by ChatGPT and is for reference only Translation date：2024-11-15」

【解決方案】讓硬碟裡的音樂重生 愛飛媒平運用AI為影像找到最佳拍檔
Rebirth the music on the hard drive. Aifei Matchmaking uses AI to find the best partner for the image.

A young girl, alone in Los Angeles, USA, is looking for a dream, a dream that allows the music creator to find her soulmate again with the music she buried deep in the hard drive Li Zihui, the founder of iFeiMedia, has a background in science and engineering, but she has a strong gene for musicians In order to help global musicians create music and find the "best partner" who can successfully match them, she founded iFeiMedia Ping Company provides a one-stop AI video and music matching platform AV Mapping to help video creators quickly find copyrighted original music One-stop AI image music matching solution to find innovative business opportunities for music creators Generally speaking, in the past, video creators had to work on video music, including composing lyrics, music, and finding copyrights It usually took two weeks Through the AV Mapping video and music matching platform, it can be instantly matched to a suitable video in 10 seconds Music, musicians can also remarket their creations to gain profit sharing, creating a win-win situation This new, decentralized operating model is also favored by the descendants of the late Taiwanese music master Li Taixiang On the platform, you can relive a time when music creation was free to fly Li Zihui has practiced piano since she was a child, participated in choirs and wind bands, and composed her own music Although she studied science and engineering in college - the Department of Surveying and Spatial Information at Cheng Kung University, she joined the imaging team to work on soundtracks from her junior year , and went to the Applied Music Department of Nanyit University to audit After graduating from college, Li Zihui decided to obey the voice in her heart and become a music dreamer Aifei Matching provides a one-stop AI image and music matching solution Aifei Matching provides a one-stop AI image and music matching solution, which mainly uses artificial intelligence image recognition and music analysis Image creators can search and match suitable music by themselves on the platform, and use the system to It can shorten the duration of the soundtrack from 8 hours to a few seconds, a significant reduction of nearly 2,000 times Li Zihui said that in addition to creating suitable soundtracks, traditional video scoring projects also require a lot of time and cost in communication and search, including subsequent post-production processing such as arrangement and recording, and music licensing, which are even more time-consuming and labor-intensive With the assistance of AI, creators can focus all their efforts on creation without worrying about finding suitable music or having their music copyright stolen Integrated virtual and real marketing, from transaction to contract signing with one click At present, AifeiMeiping's music database has a total of 60,000 tracks in more than 60 categories, covering music from Europe, America, Asia and other parts of the world, including pop, EDM, rock, Irish music, etc The original decentralized concept of iFlyMediaPing further protects the rights and interests of musicians Musicians on the platform can set their own prices and track the transaction process, achieving open, transparent and decentralized features There are currently more than 7,000 video and music creators on the platform Music creators who successfully trade on the platform can share profits of more than 40, up to 50 The two parties transact and complete the contract on the platform, and the procedure is very simple AVMapping has a total of 14 AI models, making it easy to find speed dating music Li Zihui said that the AI image music matching solution has a total of 14 AI models The method is to disassemble all elements, conduct music analysis through image recognition and text recognition, and then use machine learning algorithms to train extensively The characteristics of images and music are listed, which can quickly match the soundtrack that suits the image situation, atmosphere, and rhythm In addition to online matchmaking transactions, Aifei Matchmaking also holds physical concert events, inviting music and video creators to participate The content of the event revolves around the display of AI video soundtracks, and a video directed by the director is used on-site to allow music creators to participate PK soundtrack or take out a demonstration video and let AI match it It only takes 10 seconds The images and music matched by AI are very accurate in terms of mood and atmosphere, which amazed the participants Three years of research and development won the Red Dot Design Award, using technology to support the development of music and art Aifei MatchPing spent three years of research and development, and the platform was officially launched in August 2021 In January 2022, it participated in the CES event in Las Vegas, USA, which attracted great attention from reporters present and received more than 100 awards in total media reports, the number of uses in a month has exceeded 1,000 times, attracting 7,000 video and music creators to join the matchmaking platform According to statistics, in the initial stage, the proportion of matchmaking transactions between the United States and Taiwan is evenly divided Li Zihui said that the licensing methods of traditional music are very complex, including types of works, types of copyright property rights, etc To obtain authorization for a song, one must go through a songwriting agency, a collective management group, a production company, a record company, or even a composer , lyricists, it is very cumbersome, and musicians may not necessarily get profit sharing Through the AI image music matching platform, all transaction contracts are completed online, music creators can gain profits, and their creative enthusiasm is constantly stimulated Three steps to help video creators easily complete the soundtrack work It is worth mentioning that NFT Non-fungible token, also known as non-fungible token is currently very popular in the art and cultural market What is the possibility of introducing it into the field of video and music Li Zihui said that the current transaction fees gas fees of Ethereum remain high, and coupled with the conclusions she obtained from attending many gatherings in Los Angeles, the acceptance of NFT is still in the process of brewing However, Aifei Matching is still optimistic about the future of NFT Trend, in the foreseeable future, relevant technologies will still be introduced into the AV Mapping platform to provide more diversified trading methods In order to rapidly expand overseas markets, Li Zihui continues to seek funding from international strategic investors in San Francisco At the same time, due to the appropriate control of the epidemic in Los Angeles, the industry is gradually recovering, and Li Zihui also participates in many offline creative gatherings Aifei Media hopes to become a bridge connecting images and music, introduce well-known user cases in the international market, and let more creators see the power of the platform Aifei Media Ping also frequently reports good news After winning the DSA Digital Advertising Singularity Silver Award and the AWE Female Entrepreneurship Best Potential Award co-organized by the American Institute in Taiwan and META, the one-stop AI video and music matchmaking company founded by Li Zihui The platform AV Mapping also won the Best of the best in the Design Concept of the German Red Dot Award in 2020 We hope to continue to be based on technology and nourished by art Support music creators to create better works Li Zihui, the founder of Aifei Matchping, has won many international awards and is a female entrepreneur with great potential「Translated content is generated by ChatGPT and is for reference only Translation date：2024-05-19」

PopularTags