Online videos have been a challenge on so many fronts – Not only do they consume more bandwidth (and cost more to maintain), they do not monetize well and are not search engine friendly. While there have been reports of companies such as Google working on scanning online videos to understand the context (and thus be able to rank them more appropriately), AOL seems to have an interesting alternate solution.
In a recently filed patent application, AOL describes a way to “study” the instant messages shared by people viewing a video and scanning this text for keywords that may be added as a metadata. This includes splitting the video itself into frames and assigning particular frame IDs. The algorithm will then study the instances of instant messages shared within a particular time since a frame of the video is displayed.
For instance, if several users watching a baseball game video type in praising a “homerun” 25 seconds into the video, the system immediately recognizes that an event associated with a keyword “homerun” has occured at a frame near the 25 second mark and associates this keyword to the video – thus helping in future searches as well as helping it index its videos better on search engines.
You will have to take this with a grain of salt, but it is possible that Hewlett Packard could be working on a search engine. A recent patent filed in the name of ‘Jianwei Dian’ describes a search engine that will understand the “intent” of the user inputting the search query and list results that the user needs; not simply match the query with web pages like Google.
So, how does it work? The inventor explains that the process will involve understanding the query of the user and delivering results of the information and not just the web pages that contain the words from the query (like Google does). So, if you query “Contact Information of Jianwei Dian”, you are likely to see results ranked by those web pages that contain the email, phone number, etc. of Jianwei rather than just web pages that match the query. The inventor writes
“With considering both the relevance and reliability of the matched web pages, the intent match search engine more likely will give high rankings to the web pages that both contain the information the user is looking for and are reliable sources of information. This saves the user’s time, since the few top web pages or even the very first web page may already contain what the user is looking for and is also the most reliable source of information. The user doesn’t need to navigate through a lot of matched web pages before he finds what he is looking for. “
While the patent looks interesting, there is still not enough confirmation about who the patent really belongs to. The patent is filed in the name of ‘Jianwei Dian’ from Plano Texas. A quick search (on Google!) on the inventor gave us the following information:
Name: DIAN Jianwei
Location: Plano, TX
Company: Hewlett-Packard Company
E-mail: [email protected]
Phone: XXX-XXX-XXXX (Home)
What do you think? Is HP indeed working on a search engine? Tell us your thoughts.