Maternity clinic chatbot NeRo

AI systems > Maternity clinic chatbot NeRo
Social services and health care

Overview

Maternity clinic chatbot NeRo

Tags

chatbot maternity clinic customer service

The chatbot answers the clients of the Helsinki counselling centres’ questions without queuing at all times of the day. In addition to problems related to the child’s growth or development and pregnancy, the customers can also ask questions about dental care, speech development, and nutrition. Service can also connect the client to the nurse as needed, and the client can also tell the chatbot of their willingness to talk to the nurse.

The service is intended for customers of the City of Helsinki’s maternity and child health clinic. The service operates on a rule-based logic based on question-answer pairs and discussion dialogues defined by the clinic’s experts. The service operates as part of the clinic’s chat customer service and extends the service’s availability to 24 hours a day. The service also enables the counselling centre to react faster, to inform proactively, and to develop operations to current issues of concern to customers based on discussion analytics. The service increases efficiency by enabling the automated collection of preliminary data and the automation of frequently asked questions.


Link to service

Contact information


  • Department

  • Counseling and family work
  • Contact team for inquiries

  • Monica Lindberg
  • External suppliers

  • IBM
  • Contact email

  • monica.lindberg@hel.fi
  • Contact phone

  • 09 3105 8352


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.

Frequently asked questions

Experts have taught the service by creating phrases and keywords related to themes based on the clinic’s frequently asked questions. The service is constantly being developed by creating new phrases and keywords based on conversation analytics for themes that the service has not been able to respond to.

Discussion logs

The discussion data includes the questions and phrases entered by the customer, as well as the customer’s answers related to the instructions provided by the service. The conversation data is used to identify customer’s question, and on this basis to provide related instructions during the conversation. The conversation data is analysed to further develop the service on a weekly basis. At the same time, the conversation log is checked for deleting any potential personal information entered into the conversation. 

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

If a client wishes to enter into a conversation with a nurse, they will be asked to provide preliminary information that, upon identification, will become part of the remote healthcare background information in the Genesys Contact Management System.

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 service operates on a rule-basis by using reasoning rules taught by the clinic’s experts. The experts at the clinic define keywords and phrases for the chatbot to identify the topics supported by the service. When the customer enters a keyword or phrase corresponding to a supported topic into the service, the service returns the respective advice or instructions to the customer. The service is developed by teaching it new keywords and phrases based on conversation analytics on the questions that the service has not been able to answer.

Non-discriminationShow More Show Less

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

The service is currently only available in Finnish, and therefore only customers who speak Finnish can benefit from the extended availability of counselling services through the service. The service also does not automatically know how to correct spelling errors, which may limit the use of non-native-speaking customers. The service is not yet planned to be extended to new language versions.

Human oversightShow More Show Less

Human oversight during the use of the service.

The service is constantly monitored and further developed by healthcare experts by using discussion analytics. An expert regularly reads the anonymised discussions, and the chatbot is further trained on the basis of the identified new topics and the corresponding instructions. The customer is clearly informed when he or she is chatting with the chatbot, and he or she always has the option of getting personal service from a nurse during the opening hours of the chat’s personal service.

Risk managementShow More Show Less

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

The service is an application for voluntary health care which also has the potential for false or bad instructions. The service is not a medical device. The customer is informed about the nature of the service and the situations in which the customer should primarily use other service channels. The service provides the client with instructions corresponding to the symptom description and it can, if necessary, transfer the conversation to a nurse within the opening hours of the personal service.

Discussion data from the service is regularly analysed to identify new topics and to improve the coverage of a wide range of topics. Websites and instructions related to the service are monitored by designated experts to ensure that the references and instructions are working and stay up-to-date.

The service also involves a risk related to the processing of personal data if the customer enters unnecessary personal data into the service. To manage the risk, the discussion logs are reviewed on a weekly basis by an expert, at which point all personal information is deleted.

Was this information useful?