While the expansion of the internet and the advent of digital broadcasting have given us an ever-widening range of content, they have also created an accelerating flood of information. Furthermore, advances in flash memory and other forms of compact, high-capacity storage have made it possible to carry around hundreds, even thousands of tunes via portable music players, such as Walkman. However, faced with the task of sifting through growing masses of data to find the tracks that they want to hear, users are increasingly demanding easier ways to search for tracks and new ways to enjoy content instead of simple shuffle systems.
Since the 1990s, Sony has been working to meet such demands by developing content recommendation & search technology. Some of the resulting advances of this R&D have been used in Sony products and services since 2001. Sony's goal is to provide users with totally new experiences by using recognition technology and AI technology developed over many years to monitor user preferences and content playback on hardware.
Since the 1990s, Sony has been working to meet such demands by developing content recommendation & search technology. Some of the resulting advances of this R&D have been used in Sony products and services since 2001. Sony's goal is to provide users with totally new experiences by using recognition technology and AI technology developed over many years to monitor user preferences and content playback on hardware.
What is Content Recommendation Technology?
Content recommendation technology is a key personalization technology that enables hardware to provide services that complement user attributes and their environment. Specifically, these systems learn to understand the user's preferences and circumstances so that they can filter large volumes of content and recommend the most suitable items. Basically, there are two types of content recommendation.
Figure 2 compares content search and recommendation systems. A content recommendation system is a system in which the hardware automatically carries out filtered searches for content based on assumptions about user preferences and intentions. The content offered will therefore vary over time.
User preference-based search (personalized recommendation)
- as if the device were saying to the user: "This is the content I'd like to recommend to you considering your tastes and present context."
- as if the device were saying to the user: "If you're interested in that, then you'd probably be interested in this as well."
Fig. 1: Five elements of content recommendation technology
Fig. 2: Content searching and recommendation
