Zhihu has become the largest content Q&A community in the bulk sms service Chinese Internet world. After ten years of sharpening a sword, Zhihu has accumulated a large amount of high-value content that is its widest moat. But precisely because of its mass, how to efficiently distribute content to those who need it has become a key issue. The traditional solution is to search. Correlate content with user intent through explicit user search terms. This is the age of people bulk sms service looking for content. The content distribution strategy of Zhihu is not only search, but also recommendations, ideas and hot lists. Why does Zhihu use them as a content distribution strategy? What are the operating mechanisms behind these strategies? 1. Algorithm-based distribution—recommendation
The recommendation system must be familiar to bulk sms service everyone. Now whether you are doing e-commerce, social networking, or content, if you don’t get a personalized recommendation, you are embarrassed to go out. But to build a recommendation system, three steps are necessary: understand the content, understand the user, and build the rules. Zhihu is the same. Whether it is a search system or a recommendation system, the purpose is the same, that is, to complete the efficient and accurate matching of people and content. In order to achieve this, bulk sms service understanding the content and users is the only way to go. So, how should we understand the content in the first place? 1. Understand the content The more common way to understand content is by categorization. For example, when uploading a video at station B, the up master needs to fill in the classification of the submitted content, which is the most basic classification of content.
So how to continue to understand the specific bulk sms service content at the end of the classification? The most common way is to stick a label. For example, label a song with genre, duration, album, artist, etc. These labels are not in a containment relationship, but an equality relationship. Aggregate them together to understand content from multiple dimensions. 2. Understand the user Similarly, since you can tag content, you can also tag people. There is also a professional name for tagging users, called user portraits. Let’s start with user-based collaborative filtering. In bulk sms service addition to listening to music, programmer Xiao Li also likes drinking. He feels that writing code after drinking is more inspirational, so he likes to study various flavors of wine. As a result, the recommendation system will find users who like to study various flavors of wine like Xiao Li, and then recommend the wine-related content that these users pay attention to to Xiao Li.