openPR Logo
Press release

Agmis launches all-in-one AI platform for automated marketplace content moderation

05-12-2022 04:27 PM CET | IT, New Media & Software

Press release from: Agmis

Leading Baltic technology developer Agmis has launched a new AI powered platform for automated marketplace content moderation. Aimed at marketplaces, ecommerce and classified advert websites, EasyCMT titled platform uses AI to moderate visual, textual and video content. The platform automatically identifies content that goes against the policy guidelines, preventing it from appearing on the site.

EasyCMT platform was developed by Agmis product spinoff EasyFlow, which specializes in retail Computer Vision applications. By using AI for image analysis, the content moderation platform automatically identifies unwanted content in user uploaded pictures or videos, including nudity, weapons, drugs, and hate symbols. The platform can be augmented to detect watermarks, excessive usage of text and other unwanted aspects, further improving marketplace user experience. EasyCMT also comes with inbuilt tools for background removal and image enhancement.

In addition to image and video moderation, the platform analyzes textual content, preventing hate speech, offensive comments or potentially fraudulent postings from making it onto the website. For improved user experience, the platform also scans for ALL CAPS postings or usage of unwanted symbols.

"Marketplaces are the most lively corners of the internet. Think of a real world town market, where sellers are jousting for buyer attention. With fast growth of the user-base, unmoderated marketplaces are quickly overrun by spam and unwanted content. Poor user experience is the main reason why users choose to shop elsewhere" - says head of product development at EasyFlow Simas Jokubauskas.

According to Simas Jokubauskas, the EasyCMT aims to address two main challenges for marketplace owners. Firstly, the platform helps to keep unwanted and harmful content off the site. Secondly, it nudges third-party sellers to adhere to website-wide content policy guidelines for a unified and fluid user experience.

"Marketplace owners are faced with a balancing act between fast-paced growth and over-policing. Serving visual, textual and video mediums, our content moderation platform workflows bring the best of both worlds, with the ability to prevent unwanted content from appearing online, as well as reducing the manual oversight burden from human content moderation" - adds Simas Jokubauskas.

With EasyFlow content moderation platform all user-generated entries are assigned a policy breach probability score. In a fully automated mode, AI prevents all unwanted content from appearing on the site automatically. Human moderators can overrule these decisions later on. Operating in an assisted mode, the platform will only block the content where it is highly certain that it breaches the policy of the marketplace. In the cases where it cannot make a decision with absolute certainty, the platform will prioritize suspicious entries for human moderators to review. In a manual mode of operations, the platform will not prevent any content from appearing. Yet it will prioritize the item review list for human moderators, with the most suspicious postings coming first in line.

"These workflows make a better use of human content moderator resources, shifting their attention to postings where their review is most needed, eliminating the requirement to manually check every content item on the website" - says Simas Jokubauskas.

EasyFlow has already made its mark in the world of 'offline' retail. EasyFlow team are the authors of Computer Vision powered applications for in-store analytics, including apps for shelf-level stock management, planogram compliance, checkout queue management and other tools for 'brick and mortar' retailers to improve their store performance. ScanWatch - an application for unmanned checkout counters - automatically identifies scanned unpackaged products (e.g. vegetables or baked goods) without the need to select them from a self-checkout picklist menu. It also helps to prevent unintentional product misscaning and mitigate checkout fraud.

"It's only natural that with our experience in real-world image recognition, we are bringing this expertise into the digital retail realm" - says Simas Jokubauskas.

www.agmis.com
Savanorių pr. 321C, LT-50120 Kaunas
Lithuania

About Agmis | www.agmis.com
Technology company Agmis creates smart solutions for customers all over the world. The product arm of the company develops AI and Computer Vision applications for retail, industrial and aerodiagnostics applications. Another part in the Agmis group - Bluelark - is the first certified Salesforce partner in the Baltic states. Agmis solutions are employed in more than 30 countries across 4 continents. Agmis employs more than 100 highly skilled specialists.

This release was published on openPR.

Permanent link to this press release:

Copy
Please set a link in the press area of your homepage to this press release on openPR. openPR disclaims liability for any content contained in this release.

You can edit or delete your press release Agmis launches all-in-one AI platform for automated marketplace content moderation here

News-ID: 2622898 • Views:

More Releases from Agmis

AI as EAS: ScanWatch Introduces AI-Powered Article Protection
AI as EAS: ScanWatch Introduces AI-Powered Article Protection
ScanWatch - the creator of AI-powered Crime Predictor loss prevention software for self-checkouts - is introducing AI software for full store security monitoring. Instead of focusing solely on the checkout area, the software can identify what items a particular shopper has picked up from the store shelf. The new software is currently being tested in a semi-autonomous store setting. In the initial trial the software had managed to cut the
Shoplifters Target Self-Checkout Registers Amid Soaring Inflation
Shoplifters Target Self-Checkout Registers Amid Soaring Inflation
With skyrocketing daily product prices, retailers all over the world are recording an increase in shoplifting incidents. Over the second half of 2022, retailers in the UK reported an increase of 18% in thefts, while according to the US National Retail Federation, the amount of organized shoplifting increased by 26.5%. In nine-out-of-ten incidents, shoplifters were targeting self-checkout registers. In addition to alcoholic beverages and other premium goods, shoplifters went after butter,
09-15-2022 | Health & Medicine
Agmis
Record Salesforce project in the Baltic States: Limedika picks Salesforce to str …
Pharmaceutical company Limedika chooses Salesforce to create an internal employee service center and streamline employee experience across group companies. With nearly 2000 employees, this is one of the largest Salesforce platform deployments in the Baltics. Platform deployment was carried out by specialized full-service Salesforce consultancy Bluelark. Limedika is one of the largest pharmaceutical distributors in the Baltic region, providing services to more than 1500 pharmacies and hospitals. The company distributes more
Bluelark launches Salesforce suite for NGO digital transformation
Leading Baltic full-service Salesforce consultancy debuts an all-in-one product suite, aimed at non-profit and non-governmental organizations. The NGO toolkit covers all key NGO operational areas, including online and offline donation collection, volunteer relationship management platform, event and volunteer resource management and volunteer intranet for online NGO member communication. The suite is available for worldwide deployment, with special focus on nonprofits in the US and the UK. The toolkit is built on

All 5 Releases


More Releases for EasyFlow

AI RetailTech Startup ScanWatch Closes €0.5M Seed Round To Transform Store Che …
AI retail technology startup ScanWatch attracted €0.5M in investments, with technology company Agmis and smart retail security solutions provider Neto Baltic leading the round. ScanWatch reduces the time spent at self-service checkout counters. The product automatically identifies scanned fruit, vegetables and other unpackaged goods, helping retailers to mitigate checkout fraud, as well as reduce unintentional scanning errors. “More than 60% of shopping baskets include at least one unpacked item. Selecting
Mantinga Introduces a PPE AI Assistant for Worksite Safety
A leading Baltic frozen and convenience food producer Mantinga introduced Computer Vision powered solution to ensure PPE compliance. During a three month pilot project, the AI PPE detection product was installed at the company’s logistics centre and a manufacturing plant which is currently being built. The PPE detection solution was tasked with monitoring whether employees are wearing the required protection equipment, including hardhats, high visibility vests and face masks. The
EasyFlow AI Retail Queue Management Unlocks 5 Man Hours per Day in Lost Checkout …
The platform helped to reduce cashier idle time by 57.66% when measuring against the baseline, equaling to more than 2.5 man hours per store per day. The software also prevented 237 queue forming incidents, saving an average of 2.25 hours in customer wait time per day. The experiment was conducted for two months at two store locations of one of the largest retailers in Central and Eastern Europe with 18
EasyFlow AI Service for Retailers Aims to Limit Checkout Fraud
According to Leicester University research, in 2.88% of self-checkout transactions at least one of the items is mis-scanned. In total approx. 0.52% of all items are mis-scanned via self-checkout resulting in heavy losses for retailers. The research analyzed 140 million self-checkout transactions. 17 million post checkout audits were performed finding 486.000 items not being scanned at all. Shopping bags, loose fruit, alcoholic and soft drinks were among the most popular mis-scanned
‘RoboCop’ for worker safety: AI to prevent workplace accidents
Imagine a perfect workplace safety officer. He never sleeps, he never tires, he even does not take coffee breaks. Computer Vision (CV) technologies are bringing science-fiction vision closer to reality. By utilizing AI and machine learning technologies and employing on site security monitoring video cameras, the software can identify personal protective equipment and detect and notify about PPE infringements in real time. And it is less expensive than you think. “PPE
Tech Trends to Watch: Computer Vision makes Construction Smarter, Safer and more …
Being too expensive to deploy or simply unpractical, Computer Vision (CV) solutions were out of reach of most but the largest construction companies. With the growth of cloud computing resources and drop in their prices, as well as with increase of CV solution providers, the technology will make strong inroads into construction sector mainstream in 2019. Computer Vision analyses video footage from security or specialized video monitoring cameras. From this data,