Knowledge management
Allowing employees to share, find, access and update business knowledge is key to allowing companies to run productively and make decisions more effectively and efficiently. Most companies manage this manually. AI can enhance both employees' ability to find the knowledge they are looking for and suggest knowledge that seems relevant to them.
Overview
Improve search results and suggest relevant documents to allow for better sharing of business knowledge.
TARGET
Relevant pages to a user.
Challenge
The primary problem is to create a record for every employee that captures which types of documents that the employee has used in the past. This is similar in scope to building the data for a recommendation engine for an ecommerce company. Further, all the documents will need to be processed by text analytics tools to extract relevant characteristics for the recommendation engine and to support natural language search. All this data needs to be cleaned, joined and transformed into valuable ML features before going into model training. This pre-modeling prep process can be frustrating and time consuming. We are here to help.
Modeling techniques and libraries
Extract text features
Using a natural language processing toolkit, extract the relevant features from the file.
Package:
- NLTK
- CoreNLP
- Gensim
- spaCy
- Polyglot
- Pattern
Content-based filtering
Use the attributes of the products a customer has used/purchased to find other products that have similar attributes.
Package:
- Sklearn
Search
Build a high-quality search engine to enable quick searches of the documents.
Package:
- Scout
- Whoosh
