Subscribe to DSC Newsletter
Kate Shao
  • Female
  • Shanghai
  • China, mainland
Share on Facebook
Share

Gifts Received

Gift

Kate Shao has not received any gifts yet

Give a Gift

 

Kate Shao's Page

Latest Activity

Kate Shao posted a blog post

Vector Similarity Search Engine

Milvus aims to achieve efficient similarity search and analytics for massive-scale vectors. A standalone Milvus instance can easily handle vector search for billion-scale vectors. However, for 10 billion, 100 billion, or even larger datasets, a Milvus cluster is needed. The cluster can be used as a standalone instance for upper-level applications and can meet the business needs of low latency, high concurrency for massive-scale data. A Milvus cluster can resend requests, separate reading from…See More
Oct 4
Kate Shao's blog post was featured

4 Steps to Building a Video Search System

As its name suggests, searching for videos by image is the process of retrieving from the repository videos containing similar frames to the input image. One of the key steps is to turn videos into embeddings, which is to say, extract the keyframes and convert their features to vectors. Now, some curious readers might wonder what the difference is between searching for video by image and searching for an image by image? In fact, searching for the keyframes in videos is equivalent to searching…See More
Sep 12
Kate Shao posted a blog post

Smarter Housing Search and Recommendation Powered by Milvus

Project BackgroundIn recent years, Proptech has seen huge momentum and Artificial Intelligence especially is now playing a major role in people’s buying/selling decisions on real estate transactions.For housing platforms and their agents, selecting the houses that can be sold quickly from a massive number of houses is often crucial and challenging. So, how can we search for a series of unstructured data such as house plans and house information…See More
Sep 6
Kate Shao posted a blog post

The Journey to Optimizing Billion-scale Image Search

Yupoo Picture Manager serves tens of millions of users and manages tens of billions of pictures. As its user gallery is growing larger, Yupoo has an urgent business need for a solution that can quickly locate the image. In other words, when a user inputs an image, the system should find its original image and similar images in the gallery. The development of the search by image service provides an effective approach to this problem.The search by image service has undergone two evolutions:Began…See More
Aug 13
Kate Shao posted a blog post

How Milvus Implements Dynamic Data Update and Query

Milvus is an open-source vector similarity search engine powered by approximate nearest neighbor search (ANNS) algorithms such as Faiss, NMSLIB, and Annoy. To make a vector search more intuitive and easy to use, we introduced TableFile and metadata in Milvus.In this article, we will mainly describe how vector data are recorded in the memory of Milvus, and how these records are maintained.Below are our main design goals:The efficiency of data import should be high.Data can be seen as soon as…See More
Aug 2
Derek Christensen liked Kate Shao's blog post The Easiest Way to Search Among 1 Billion Image Vectors And Why Vector Search Is Important?
Jul 20
Kate Shao posted a blog post

Building an Intelligent QA System With NLP and Milvus

Milvus Project: github.com/milvus-io/milvusThe question answering system is commonly used in the field of natural language processing. It is used to answer questions in the form of natural language and has a wide range of applications. Typical applications include intelligent voice interaction, online customer service, knowledge acquisition, personalized emotional chatting, and more. Most question…See More
Jul 16
Kate Shao posted a blog post

Building a Deep-Learning-Based Movie Recommender System

With the continuous development of network technology and the ever-expanding scale of e-commerce, the number and variety of goods grow rapidly and users need to spend a lot of time to find the goods they want to buy. This is information overload. To solve this problem, the recommendation system came into being.The recommendation system is a subset of the Information…See More
Jul 9
Kate Shao's blog post was featured

Building a Deep-Learning-Based Movie Recommender System

With the continuous development of network technology and the ever-expanding scale of e-commerce, the number and variety of goods grow rapidly and users need to spend a lot of time to find the goods they want to buy. This is information overload. To solve this problem, the recommendation system came into being.The recommendation system is a subset of the Information…See More
Jul 9
Kate Shao posted a blog post

Milvus × VGG: Building a Content-based Image Retrieval System

IntroductionWhen you heard “Search by Image”, did you first think of the reverse image search function by search engines such as Baidu and Google? In fact, you can build your own image search system: build your own picture library; select a picture to search in the library yourself, and get several pictures similar to it.As a similarity search engine for massive feature vectors, Milvus aims to help analyze increasingly large unstructured data and discover the great value behind it. In order to…See More
Jun 18
Kate Shao posted a blog post

Managing Data in Massive-Scale Vector Search Engine

How data management is done in MilvusFirst of all, some basic concepts of Milvus:Table: Table is a data set of vectors, with each vector having a unique ID. Each vector and its ID represent a row of the table. All vectors in a table must have the same dimensions. Below is an example of a table with 10-dimensional vectors:…See More
Jun 11
Kate Shao posted a blog post

The Easiest Way to Search Among 1 Billion Image Vectors And Why Vector Search Is Important?

That’s correct. 1 server and 10 lines of code are all you need to search among 1 billion images in a few hundred milliseconds. Its ease of use a few lines of code to handle massive-scale reverse image search. Its superior standalone performance satisfies your need for low-latency, real-time searches. Its support for distributed systems and cloud-native extensions can always deal with 10-billion or 100-billion scale searches. It is Milvus, a fantastic vector search engine with high performance.…See More
May 28
Kate Shao posted a blog post

Milvus: A big leap to scalable AI search engine

The challenge with data searchThe explosion in unstructured data, such as images, videos, sound records, and text, requires an effective solution for computer vision, voice recognition, and natural language processing. How to extract value from unstructured data poses as a big challenge for many enterprises.AI, especially deep learning, has been proved as an effective…See More
May 24
Kate Shao updated their profile
May 22

Profile Information

Company:
ZILLIZ
Job Title:
Community Manager
Seniority:
Manager
Job Function:
Marketing
Number of employees:
50 to 99
Industry:
Technology
Short Bio:
Currently building an open-source AI community. Come check out our awesome project: https://www.milvus.io/
Interests:
Contributing

Kate Shao's Blog

4 Steps to Building a Video Search System

Posted on September 11, 2020 at 10:30pm 0 Comments

Image for post

As its name suggests, searching for videos by image is the process of retrieving from the repository videos containing similar frames to the input image. One of the key steps is to turn…

Continue

Smarter Housing Search and Recommendation Powered by Milvus

Posted on August 25, 2020 at 9:21pm 0 Comments

Image for post

Project Background…

Continue

The Journey to Optimizing Billion-scale Image Search

Posted on August 12, 2020 at 11:00pm 0 Comments



Yupoo Picture Manager serves tens of millions of users and manages tens of billions of pictures. As its user gallery is growing larger, Yupoo has an urgent business need for a solution that can quickly locate the image. In other words, when a user inputs an image, the system should find its original…

Continue

How Milvus Implements Dynamic Data Update and Query

Posted on July 29, 2020 at 10:32pm 0 Comments

Milvus is an open-source vector similarity search engine powered by approximate nearest neighbor search (ANNS) algorithms such as Faiss, NMSLIB, and Annoy. 

To make a vector search more intuitive and easy to use, we introduced TableFile and metadata in Milvus.

In this article, we will mainly describe how vector data are recorded in the memory of Milvus, and how these records are maintained.

Below are our main design goals:

  1. The efficiency of data…
Continue

Comment Wall

You need to be a member of Data Science Central to add comments!

Join Data Science Central

  • No comments yet!
 
 
 

Videos

  • Add Videos
  • View All

© 2020   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service