search

eleow / shopBot

AudioPhil, the shopbot for headphones 🎧
MIT License
2 stars 0 forks source link

Knowledge graph #10

Open Shashankwer opened 4 years ago

Shashankwer commented 4 years ago

We would be recommending the different products to the user based on his/her interest.

This can be done through the intent classification where we can obtain the requirement of the user.

The data needs to be further mapped with the product. The level of mapping also determines how well the recommendation system can be.

A knowledge graph conceptually is an open ended data representation which can allow querying through different dimensions.

Goal for proposing a knowledge graph based approach is

  1. Ease of allowing query based on the product features.
  2. Getting list of products having similar product feature: allowing navigating from one product to another
    1. Efficient data structuring
Shashankwer commented 4 years ago

Based on the preliminary unsupervised aspect mining following aspects could be derived

  1. Appearance (Color/Wiggly wires/cable/cord/port)
  2. ease of use
  3. Service by organisation/ seller
  4. Device connectivity
  5. Cost/Price 6.Game use/Travel Use
  6. Damage (sentiment based): such as crackling, irregularities/ defects
  7. Volume 9 . Battery life
  8. Durability
  9. Application/Boosting
  10. Comfort in use
  11. Discomfort in use
  12. Noise cancellation
  13. Ear cup/tips

This is based on the common sentiment data.

Product description are as well in the form of the same format in most of the cases.

For uniformity in comparison a common data structure can be proposed

as attached Proposed system

The cases can be refined further based on this property and the NLU chatbot can be designed to ask questions considering the aspects in general