Post monitoring system that detects information leakage and the likes from SNS trouble and business mails.
By using “E-Trident”, it is possible to detect slander, information leakage, and others by gathering posts from various medias such as SNS, Web Sites, Blogs, and Business Mails. We implement “Reduction of number of visual contacts” and “Improvement of process speed” at the same time by determining posts in combination with multiple filtering technologies.
System Flow Chart
High-level Filtering Function
Utilizes the analyzation know-how of huge amount of data acquired from SNS post monitoring and screening, and makes high-precision filtering possible by doing machine learning and data mining.
Useful AI Solution for Business
Utilizes database gathered from more than 10,000,000 net post monitoring per month, and quickly detects social risks such as receiving a flood of critical comments. In addition, it is possible to provide a useful AI solution for business by operational strength of 24 hours a day and 365 days a year system.
Image recognition AI that detects inappropriate images such as adult images, imitation product images, and illegal usage of logos and characters.
“ROKA SOLUTION” is an AI-type Image Recognition System that utilized deep learning, developed by E-guardian in cooperation with Tokyo University, that has world-class image recognition machine learning system.
Implements image detection rate with high-accuracy of 99.5% through the data that helps the AI to learn that utilized data acquired from extensive experience in post monitoring. It can detect inappropriate images such as adult images, imitation product images, etc.
System Flow Chart
Teacher data making that enables high detection rate
Our knowledge that have been accumulated years and years through the monitoring enables to make “teacher data” that will be required as a criteria to raise the detection rate for certain images. Images will be justified either “in” or “gray” or “out” and only the gray ones will be manually checked by the operators. In the case the judgement differs between the filtering and the visual checking, teacher data will be auto-corrected that the more we operate this system the more accurate judgement will be.
Filtering that can be used in various scenes such as EC, advertisement distribution, etc.
By filtering adult images and inappropriate images that violate social standards with a detection rate of 99.5%, it can be used not only to support healthy site management, but also in checking of advertisement distribution destination which is becoming a social problem nowadays. Also, in the EC field, the checking of fake products on CtoC flea market application sites, the recommend function which extracts image data that matches the taste of users, the suggestion of recommendation coordinate by AI in cooperation with “face authentication” system, etc. can also be applied.
Image Analysis AI that catches trends of SNS post images, and can support marketing
“Kiducoo AI” is an in-image object detection system that automatically analyzes elements included in an image data and can perform tagging by merging E-guardian AI Technology to the latest object detection algorithm.
By analyzing and tagging the images posted in SNS, it derives the trends and application scenarios, and it can be used in collecting marketing data.
Application example of “Kiducoo AI”
Collection and Analysis of Marketing Data
Kiducoo AI is an in-image object detection system that automatically analyzes elements included in an image data posted in SNS, etc. and can perform tagging. It derives what is the trend in a specific target, the trend of a product used in a specific scene, etc. and it can be used in collecting marketing data.
Flexible analysis function that can be used in various scenes
The analysis function of “Kiducoo AI” is excellent in application. It can be used in various scenes, for example, early detection of copyright infringement due to plagiarism, resolution and AB test of internet ads, Competitive analysis, automatically introduce recipe only by sending picture of the contents of the refrigerator, etc.
AI function that detects copyright infringement of live videos and video ads, and violation of Pharmaceuticals and Medical Devices Law
Currently, with the rapid increase in volume of videos on the internet backed by the popularization of smartphones and video posting sites, compliance violation of transmission and videos to be posted is rapidly increasing.
In “TextVoice”, we monitor video contents to be delivered, we quickly detect copyright infringement and Pharmaceuticals and Medical Devices Law violation, etc., and we support restoration of video market.
System Flow Chart
Makes video’s sounds to text (speech-to-text), and checks inappropriate videos
“TextVoice” can check illegal video transmission such as piracy, and Pharmaceutical and Medical Device Act of video advertisements by separating video footage and sound from a video file, and making word match of text data extracted from the sound.
In addition, it can monitor both images and sounds, and it can gather marketing data by combining existing AI solutions offered by E-guardian, such as AI-type Image Recognition System “ROKA SOLUTION”, In-Image Object Detection System “Kiducoo AI”, etc.
Cost and Labor Reduction through Automation of Video Monitoring
Video monitoring has more information comparing to texts and still images, so extensive labor and time is necessary to check everything. By using “TextVoice”, we can create an environment that can focus on upstream processes such as planning and analysis by automating time-consuming monitoring work.
Thank you for visiting our website. Please complete the form below, so we can provide quick and efficient service.
(02) 8478-7693 or (02) 8478-7674