Titulo Estágio
Natural Language search analytics for ASK
Áreas de especialidade
Engenharia de Software
Sistemas Inteligentes
Local do Estágio
Critical Software - Coimbra
Enquadramento
Today’s way to interact between a human and
a computer system is changing. Computer systems are becoming more intelligent
in the way they communicate with humans, with the latest developments in
Natural Language Processing helping a lot the improvement of speech recognition
and conversational interaction, like bots and home appliances (Echo and Google
Home). The days of having computer personal assistants has come, with Siri,
Cortana and others. But the problem is that there are still areas more complex
to be addressed, namely asking for data analysis to a personal assistant. Critical Software is developing the Natural
Language Search Analytics (NLSA) platform, which is a conversational/search
platform that allows the user to do analytical questions and queries in natural
language, like: “what are my top 5 customers in USA?” or “list sales product
TVs in Japan”. Part of the challenging of developing NLSA is dealing with how
to ingest the data that is available for being analysed. Not only this, but
also how the system is used, which can provide hints into how the data can be
better organised. On the other hand, Critical Software has a knowledge
management tool (ASK) which due to the complexity of the data it manages could
be enhanced by adding the possibility of querying the database using natural
language, and at the same time providing an interface to the tool using a
chat-bot. Summarising this internship has a strong
engineering focus and encompasses two main challenges:- Deploy ANSA (CSW’s natural language
search analytics platform) for the ASK tool- Integrate the deployment with CSW’s
virtual assistant Redy (developed on the Lexia platform), enriched with
pro-active functionalities such as alerts.
Objetivo
The main goal of this internship is to
deploy the NLSA platform for the ASK database and integrate it with our virtual
assistant. To achieve this the main objectives are as follows: - Analyse the ask database which represents
a knowledge graph, and its suitability for using as-is on the NLSA platform- Implement a configuration for the
deployment of NLSA on top of this database using the available database
connector if suitable, otherwise develop a graph database connector- Implement an executor for our virtual
assistant that integrates with the NLSA deployment as an external tool.- Enrich the assistant with pro-active
alerts concerning knowledge management
Plano de Trabalhos - Semestre 1
The internship has the following stages:- Analyse the ASK database and the
functionalities in the ASK tool [result: functional requirement list, M1]- Analyse the NLSA platform configurations
and the suitability of the ASK database [result: engineering requirements, M2]- Get acquainted with Lexia and how to
develop executors for this platform [M3]- Write the technical overview of the
systems involved [M1 to M4]- Creating the high-level Architecture and
Technical Specification [result: technical specification, M5 and M6]
- Writing the internship proposal [result:
internship proposal, M5 and M6]
it is mandatory to write a report in the 1st semester, according to the internship plan and respective tasks presented.
Plano de Trabalhos - Semestre 2
The second semester comprises the following
stages:- Setting up the Development Environment
[result: Development Environment, M6]- Development of a graph database connector
for the NLSA platform for ASK [M7]- Deployment of the NLSA platform for ASK
[M8]- Implement the virtual assistant executor
that integrates the previous work [M9]- Implement pro-active alerts for knowledge
management [M10]
- Writing the internship report [result:
internship report, M10 and M11]
it is mandatory to write a report in the 2nd semester, according to the internship plan and respective tasks presented.
Condições
Descrever de forma resumida as condições
oferecidas no estágio (e.g. recursos computacionais).
A computer and work post will be provided.
Orientador
Rui Lopes
rui.lopes@criticalsoftware.com 📩