Reimagining the future with the cognitive Internet of Things
The Internet of Things (IoT) is all about creating value by connecting physical devices, then combining data to understand patterns and trends not otherwise obvious. The data-driven decisions made possible in this way have the potential to drive business and industries to new heights, leaving little doubt that IoT applications are delivering value in unprecedented ways. But what’s next for the Internet of Things?
Despite the great strides we have seen in IoT technology and applications, the Internet of Things has much room for growth. Much of the dark data and edge data created by the Internet of Things holds great value—if it can be deciphered and put to use. This otherwise discarded data can help us learn about complex IoT systems, but that’s just the beginning. When we combine it with information from other sources, such as weather and news events, we can use the resulting analysis to drive decisions on everything from predictive maintenance to fleet operations to worker safety.
Bringing cognition to the Internet of Things
Enter cognitive computing. To bring ambitious IoT applications into being, we need powerful, sophisticated ways of processing an increasingly large and varied flow of IoT data. In short, we need the Internet of Things to be smarter than it is, and we need to get ever more value from the data it produces. Using cognitive computing systems that learn at scale, reason purposefully and interact naturally with humans, we can begin exploiting IoT data to an unprecedented degree.
The onset of massive data analytics has prompted efforts to empower the Internet of Things through use of high-level intelligence. In the resulting cognitive Internet of Things, we can expect things to behave as agents, interacting with the physical environment or social networks without the need for human intervention to interpret relationships and data. Indeed, in the cognitive era, human cognition is becoming part of the design of the Internet of Things.
Harnessing data in the Internet of Things
By translating massive amounts of unstructured data into meaningful outputs, IBM Watson Internet of Things helps identify trends, anomalies, probabilities and patterns that otherwise might go unseen. What’s more, by unlocking previously unused data, Watson Internet of Things can help transform business models and sharpen the decision-making process, propelling entire industries forward.
IBM is bringing the power of cognition to the Internet of Things by making available new Watson application programming interfaces (APIs) as part of its new IBM Watson Internet of Things Foundation Analytics offering. In a physical world in which devices and systems are becoming highly digitized, the capabilities provided by these APIs aim to give IBM clients, partners and developers an ever fuller sense of the data on which they rely:
- The Natural Language Processing (NLP) API Family enables users to interact with systems and devices using simple, human language. Natural Language Processing helps solutions understand the intent of human language by correlating it with other sources of data to put it into context in specific situations. For example, a technician working on a machine might notice an unusual vibration. He can ask the system “What is causing that vibration?” Using NLP and other sensor data, the system will automatically link words to meaning and intent, determine the machine he is referencing, and correlate recent maintenance to identify the most likely source of the vibration and then recommend an action to reduce it.
- The Machine Learning Watson API Family automates data processing and continuously monitors new data and user interactions to rank data and results based on learned priorities. Machine Learning can be applied to any data coming from devices and sensors to automatically understand the current conditions, what’s normal, expected trends, properties to monitor, and suggested actions when an issue arises. For example, the platform can monitor incoming data from fleet equipment to learn both normal and abnormal conditions, including environment and production processes, which are often unique to each piece of equipment. Machine Learning helps understand these differences and configures the system to monitor the unique conditions of each asset.
- The Video and Image Analytics API Family enables monitoring of unstructured data from video feeds and image snapshots to identify scenes and patterns. This knowledge can be combined with machine data to gain a greater understanding of past events and emerging situations. For example, video analytics monitoring security cameras might note the presence of a forklift infringing on a restricted area, creating a minor alert in the system; three days later, an asset in that area begins to exhibit decreased performance. The two incidents can be correlated to identify a collision between the forklift and asset that might not have been readily apparent from the video or the data from the machine.
- The Text Analytics API Family enables mining of unstructured textual data including transcripts from customer call centers, maintenance technician logs, blog comments, and tweets to find correlations and patterns in these vast amounts of data. For example, phrases reported through unstructured channels—such as “my brakes make a noise,” ”my car seems to slow to stop,” and “the pedal feels mushy”—can be linked and correlated to identify potential field issues in a particular make and model of car.
Watson Internet of Things gives enterprises a way to tap into the flood of IoT data, then use that data to answer previously unasked questions and make intelligent business decisions. We’d like to help you use the cognitive Internet of Things to heighten your IoT capabilities—join us in exploring the possibilities of a connected world, and learn what the cognitive era can mean for you.