International House Helsinki Chatbot Into

AI systems > International House Helsinki Chatbot Into
City Executive office

Overview

International House Helsinki Chatbot Into

International

Tags

International House Helsinki labour migration chatbot

International House Helsinki’s chatbot Into is a 24/7 customer service channel, offering a wide range of information on the official services offered by IHH and advice to support the settlement of those who have moved to the capital region from abroad. With the help of the service, customers have faster access to International House Helsinki’s wide range of services for the city and the authorities. The service is intended for all people who have recently moved to the capital region and for international people who are considering moving to the capital region. The service operates on a rule-based basis based on advice and question-answer pairs defined by experts in the subject areas, as well as discussion dialogues. The service increases efficiency by enabling the automation of frequently asked questions, e.g. inquiries about contact information and making appointments.




Contact information


  • Department

  • City Executive office, Economic development
  • External suppliers

  • IBM
  • Contact email

  • juho-tuomas.jarvikangas@hel.fi
  • Contact phone

  • +358 40 5423051


More detailed information on the system

Here you can get acquainted with the information used by the system, the operating logic, and its governance in the areas that interest you.


DatasetsShow More Show Less

Key data sources utilised in the development and use of the system, their content and utilisation methods. The different data sources are separated by subheadings.

AI training material

AI training material contains sample questions from the content area of the service. The questions have been collected during the development project from City of Helsinki service experts, and they represent the questions asked by citizens in customer service situations. The material is owned by the City of Helsinki, but it has not been licensed. The material does not contain any personal data.

 

The training material is uploaded to the AI, which constructs a model based on the training material. Some of the sample questions are also used to test the model.

Conversation logs

 

The system records the questions asked and the answers given during the chat session in a log file. The log is regularly analysed by the service development team to see how the service has responded to customer questions.

The analysis will identify areas of content where the training material and the answers provided by the service need to be improved. After the analysis, the training material is defined and more sample questions can be added or, for example, new discussion paths can be created to improve the user experience of the service. Customer feedback can also be used to define answers and add more information.

The conversation log will be removed from the system after 30 days after the analysis and changes have been made, but usage-related reporting such as usage rates, response rates and other parameters will be stored to monitor the long-term progress.

The conversation log is owned by the City of Helsinki, but it has not been licensed.

 

Data processingShow More Show Less

The operational logic of the automatic data processing and reasoning performed by the system and the models used.

Model architecture

The Chatbot service is based on the IBM Watson Assistant software product that is offered as an IBM Cloud SaaS application from the Frankfurt data centre in the EU. The service utilises AI and machine learning models to process natural-language questions.

The customer asks questions through a digital interface that works across different devices. If the AI is unable to respond to the questions, or otherwise more suitable, the customer can contact a customer service representative. The service will then connect the customer to a service specialist who can continue the conversation. The customer can also give feedback on the service, which is used for further development of the service.

System architecture description

Chatbot-toteutuksen-looginen-arkkitehtuuri.png

Performance

The development of the use and quality of the service is continuously evaluated. User statistics and quality measures are regularly recorded in reports. Quality measures include the number of correct answers compared to all the questions and direct customer feedback collected on the service.

Non-discriminationShow More Show Less

Promotion and realisation of equality in the use of the service.

The service is currently only available in English.

The service also does not automatically know how to correct spelling errors, which may limit its use by customers who are not native speakers. The service is not yet extended to new language versions.

Human oversightShow More Show Less

Human oversight during the use of the service.

The service automatically identifies and compiles topics that it cannot answer. These are submitted to the City of Helsinki’s experts to develop the conversation paths of the service further.

The service is monitored by reviewing the feedback and conversation logs and by analysing the statistics on the use of the service. Based on this data, experts identify the topics customers find interesting and then they develop discussion paths.

The monitoring experts are tasked to create new discussion paths based on the analysis and to improve the retrievability of recommendations, e.g. by using new keywords.

Risk managementShow More Show Less

Risks related to the system and its use and their management methods.

The service will never ask for personally identifiable information. However, the service involves a risk related to the processing of personal data if the customer enters unnecessary personal data into the service. To manage this risk, the service has an automated function that immediately deletes any social security numbers or email addresses from the conversation logs. The conversation logs are also regularly reviewed by experts, who delete any personal data that may have been overlooked by the automated system.

Was this information useful?