Advanced Technologies Supporting Big Data Utilization
NEC has been engaged in research and development of Artificial Intelligence (AI) technologies for many years. Our advanced technologies identify new patterns in big data and enable accurate predictions for the real world.
- System Invariant Analysis Technology
- Heterogeneous Mixture Learning Technology
- Recognizing Textual Entailment Technology
- RAPID Machine Learning
System Invariant Analysis Technology
Automatic modeling of correlations between sensors to enable early detection of anomalies
This technology automatically extracts and creates invariant relationships that represent the characteristics of facilities or systems based on massive quantities of sensor data. By comparing the values predicted by the invariant model with real-time data, "not usual" behaviors can be detected.
Since the relationships among the sensor data can be extracted and profiled automatically by machine learning, this technology can identify relationships that cannot be discovered even by experts. All invariant relationship formulas are simplified so that they can be calculated at high speed. In addition, all relationships among the sensors can be visualized comprehensively, allowing facilities and systems to be monitored without any oversights.
Technical introduction by video
Related solutions
Plant Failure Sign Detection Solution––detects signs of failure in a plant before an incident occurs.
Click here to learn more about NEC's Plant Failure Sign Detection Solution.
Related cases
Chugoku Electric Power Company
NEC works with Chugoku Electric Power Company to demonstrate that early signs of failure can be detected from big data related to power plant information such as vibrations and temperature, thereby preventing the failure from occurring.
Potential applications
Preventive maintenance of transportation equipment, production quality control, anomaly detection in buildings and other infrastructure
Heterogeneous Mixture Learning Technology
Discovery of specific regularities in a variety of different data
Heterogeneous Mixture Learning Technology learns multiple relationships hidden in big data, discovers useful patterns and regularities, and selects the appropriate one depending on the situation.
This enables higher-precision prediction in dynamically changing environments than existing machine learning technologies, which often take just a single pattern into account.
Related solutions
Predictive Analytics Solution for Fresh Food Demand––precisely forecasts perishable food demand to reduce food disposal rates.
Click here to learn more about NEC's Predictive Analytics Solution for Fresh Food Demand.
Electric Power Demand Forecasting Solution––generates highly accurate power demand forecasts to facilitate more efficient use of power.
Click here to learn more about the Electric Power Demand Forecasting Solution.
Predictive Analytics Solution for Demand of Repair Parts––enables precision forecasts of spare parts demand to optimize inventory management.
Click here to learn more about the Predictive Analytics Solution for Demand of Repair Parts.
Related cases
Obayashi Corporation
NEC helps Obayashi Corporation generate precise power demand forecasts using big data related to human activity and weather conditions, leading to improvements in energy usage efficiency.
Potential applications
Contract cancellation prediction, market price prediction, facility aging and deterioration prediction
Related links
Recognizing Textual Entailment Technology
Rapidly searching for text containing similar meanings in vast amounts of data
Recognizing Textual Entailment Technology judges whether two sentences have the same meaning by identifying key words and analyzing subject-predicate relationships. Unlike conventional technologies which mainly analyze the consistency/inconsistency of words contained in different sentences, Recognizing Textual Entailment Technology can produce correct results even if sentences contain different words that have the same meaning or use the same words to express different meanings.
Related solutions
Compliance Enhancement––identifies the documents that require strict management from among a large volume of documents such as emails and sales reports.
Click here to learn more about NEC's Compliance Enhancement solution.
Voice of Customer (VoC) Analysis––automatically classifies and organizes customer feedback to enable better customer service and promote new service creation.
Click here to learn more about NEC's Voice of Customer (VoC) Analysis solution.
Related cases
Sumitomo Mitsui Banking Corporation
This solution instantaneously analyzes and visually represents a huge amount of customer feedback, allowing the bank to implement activities to improve customer satisfaction that exceed expectations.
Potential applications
Public risk management, product and service risk management, urban surveillance
Related links
RAPID Machine Learning
Fast and lightweight machine learning software
RAPID Machine Learning is a deep learning technology that learns and recognizes big data, including video, audio and text data without complicated processing involving human labor. It supports operations that necessitate human judgments and inferences. As this technology is capable of fast, highly accurate matching without the need to set rules, it is useful for example when selecting job applicants that match the employment information.
Related solutions
Human Resources Matching––aids in selecting applicants that match job requirements.
Click here to learn more about NEC's Human Resources Matching solution.
Potential applications
Product matching, tourist destination matching, customer behavior analysis, traffic monitoring
- Big Data
- NEC's Big Data
- Solutions / Platform Products
- Case Studies
- Search by Industry Type
- Advanced Technologies Supporting Big Data Utilization
- Special Contents
- Gartner Data & Analytics Summit
- Addressing Social Issues
- Press Releases
- Events & Seminars