18038956. DISCRIMINATOR GENERATION DEVICE, DISCRIMINATOR GENERATION METHOD, AND DISCRIMINATOR GENERATION PROGRAM simplified abstract (Nippon Telegraph and Telephone Corporation)
DISCRIMINATOR GENERATION DEVICE, DISCRIMINATOR GENERATION METHOD, AND DISCRIMINATOR GENERATION PROGRAM
Organization Name
Nippon Telegraph and Telephone Corporation
Inventor(s)
DISCRIMINATOR GENERATION DEVICE, DISCRIMINATOR GENERATION METHOD, AND DISCRIMINATOR GENERATION PROGRAM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18038956 titled 'DISCRIMINATOR GENERATION DEVICE, DISCRIMINATOR GENERATION METHOD, AND DISCRIMINATOR GENERATION PROGRAM
Simplified Explanation
The abstract describes an identifier generation device that can analyze flow data of an application and generate identifiers for similar applications. Here is a simplified explanation of the abstract:
- The device analyzes flow data of an application.
- It calculates first feature vectors from the flow data.
- The first feature vectors are converted into second feature vectors that are similar to feature vectors of other applications of the same type.
- The second feature vectors are then clustered and assigned a pseudo-label.
- A learning data set is generated from the second feature vectors with the pseudo-label.
- The learning data set is supplied to an identifier, which is then updated with the new data.
Potential applications of this technology:
- Network traffic analysis: The device can be used to identify and classify different types of network traffic based on their flow data.
- Intrusion detection: By analyzing flow data, the device can help identify potential security threats or unauthorized access attempts.
- Application performance optimization: The device can analyze flow data to identify patterns and optimize the performance of applications.
Problems solved by this technology:
- Efficient identification: The device can quickly generate identifiers for applications based on their flow data, allowing for efficient classification and analysis.
- Similarity detection: By converting feature vectors into similar vectors, the device can identify applications that have similar characteristics or behaviors.
Benefits of this technology:
- Automation: The device automates the process of generating identifiers and updating settings, reducing the need for manual intervention.
- Improved accuracy: By analyzing flow data and generating feature vectors, the device can provide more accurate identification and classification of applications.
- Scalability: The device can handle a large volume of flow data and generate identifiers for a wide range of applications.
Original Abstract Submitted
An identifier generation device includes identifier generation circuitry configured to acquire flow data of an application, calculate first feature vectors from the flow data, convert the first feature vectors into second feature vectors to which feature vectors of an identical type of application are similar, cluster the second feature vectors and add a pseudo-label to the clustered second feature vectors, generate a learning data set from the second feature vectors to which the pseudo-label is added, supply the learning data set to an identifier, and update a setting of the identifier to which the learning data set is supplied.
