The AOC carries out a process mining pilot in the support service and file management of the Girona Provincial Council

In recent months, the AOC has carried out a process mining pilot in the user support service. Process mining is a discipline that aims to discover, monitor and improve processes through the extraction of knowledge from the event log of information systems. This discipline goes beyond simple data processing and incorporates in-depth knowledge of the process from which it comes. That is, to WHAT (the data) is added the HOW (the process). So, once you've loaded up enough data and learned about the process, you can start asking questions. 

In the case of the AOC we discovered such surprising things as that our support process, for us linear and simple, had more than 3.400 variants or that we were more efficient during the pandemic, with more loads of support requests, than before. It is also an open door to simulations with the question "What if…?" , for example, “What if the second level of support responds directly to the user instead of moving the answer to the first level?”, the answer: up to 16.000 hours of annual processing could be saved.

In parallel, in the previous case a pilot was carried out with the electronic file management service offered by the Diputació de Girona to about 150 municipalities in the province. Given the limitations of the budget, this second pilot was more limited. We are grateful to the Electronic Administration Support Office of the Girona Provincial Council for their collaboration.

In short, a very positive experience that we want to continue exploring. We believe that it will help us to improve the management processes of the AOC and that we will value extrapolating to the local administrations.

This initiative is part of the set of innovative initiatives being promoted by the AOC to explore the opportunities offered by advanced analytics and artificial intelligence technologies to improve the delivery of public services.

Video presentation of the works

Pilot file for user support service


How can we quickly identify the points for improvement in the operation of the support service and determine which action will have the best impact on the satisfaction of the people and entities using the service?

Current issue

The AOC Consortium provides support through the Customer Service Center (CAU) from where administrations, citizens and companies can address requests and queries related to the services of the AOC Consortium. The growth in the last years of the activity of the AOC's own services, accentuated by the widespread increase in digital procedures due to the COVID-19 pandemic, has also caused this support to grow continuously since its inception. start, both in volume of requests and in actors involved.

Currently, the service now exceeds 60.000 requests for support, and includes the participation of different units of the AOC Consortium, technical offices and external suppliers.. This diverse participation, multiplied by the volume of service types, generates a wide variety of possible flows of support request processing, as well as a complex verification of compliance with response and resolution times.

The need arises to analyze the operation of the support service processes in order to:

  1. measure performance times for people and entities using the service
  2. identify possible areas for improvement (in relation to organizational changes or technological support of the process)
  3. be able to measure the impact of the proposed actions in relation to the areas for improvement
  4. be able to assess the future impact of changes in demand (what was the effect of the pandemic)

Applied solution: advanced analysis with process mining

The management of the different requests and queries of the CAU of the AOC Consortium is carried out with a tool of ticketing which is a specific platform for managing service requests. This ticketing tool allows you to keep a detailed record of:

  • registered requests
  • its categorization (by registration, by priority, by service,)
  • its assignment to the different actors involved in its resolution
  • the timestamp for recording each request and the timestamps for assignment changes until they are resolved.

Having this detailed record that allows you to reproduce the execution of each request from the beginning (from the record of the request itself) to the end (at its resolution and acceptance by the person who registered it) was presented as a opportunity to be able to run an advanced analysis of the support service processes with process mining.

Thus, the AOC has promoted a pilot or value test project to demonstrate the applicability and benefits of process mining in a practical environment, based on the AOC's own support processes, of which was awarded iterem with the platform Approve.

This is a pilot project limited to a short period of time (approximately 3 months), in which to carry out an advanced analysis of the support processes that responds to the challenge posed.

What is process mining?

Process mining is a set of methods that allow you to analyze the records of the execution of a process (in this case the support service process) using different types of visualizations to identify bottlenecks, deviations and at the same time discover opportunities. to optimize performance and maximize results.

Process mining, like data mining, is based on data analysis as a fundamental pillar of analytical capabilities; but process mining incorporates process maps with measures of case frequency and performance that in addition to obtaining measures (WHAT) allow us to identify causes and dependencies (COM), allowing to understand how the REAL operation is developed (real effort , actual cost, actual response time,…).

What have we discovered?

1.324.963 activity records were analyzed corresponding to 306.181 requests for support for a period of activity 01/01/2017 to 11/11/2021.

Applying process mining in a short period of time, we have obtained the following key information for process improvement:

  1. The discovery of processes: the starting point of how the processes are executed allows better decisions to be made in their redesign. The support process, although from a theoretical starting point it is linear and limited, in the analyzed period has more than 23855 variants; which allows a starting point for reviewing and standardizing processes.
  • Yield: in a pre (2017 to 2019) and post (2020 and 2021) pandemic comparison; It has been found that with more loads of support requests in the post-pandemic period, the service has been more efficient:
    • Pre-pandemic: Approximately 50.000 requests for support were handled annually.
    • Post-pandemic: there have been more than 60.000 requests for support each year; reducing by up to 42,5% the average duration of requests from registration to response and closing.
  • Analysis of variants: Request times (total time from start to finish) and processing time (time in which the request is not pending from third parties) have been measured, making a comparison between different services. In this way, it has made it possible to identify differences and how the response to requests varies depending on the different services.

It has also been compared based on the scaling levels of requests, identifying behaviors and being able to measure the impact of changes in the process. For example, “What impact does user response time have if the second level of support responds directly to the user instead of moving the response to the first level?”; and to determine the objective savings in a potential redesign of the process that would allow this change.

  • Simulation: Not only has it been possible to analyze the history to draw valuable conclusions, but it has also been possible to assess the potential of process mining to check the impact of possible changes or improvements. In one simulation, variations were made on the number of people assigned to certain tasks and their impact on resolution times.

It allows us to answer the different scenarios "What if…?" with simulations based on objective service data.

The project has been developed applying the following techniques, and with a joint and guided evaluation of the results:

  • Automatic discovery of process maps and comparison between models.
  • Data visualization dashboards, statistics and analytical capabilities of the Apromore platform.
  • Simulation skills (What if…?) To set different scenarios, assess the impact on the process and identify the most appropriate process improvement option.

Mining processes in the Public Administration

The applicability and benefits of process mining have been demonstrated in a practical setting and have enabled:

  • A complete view of the process and its actual execution that cannot be analyzed with other techniques.
  • Only with a load of data, complex analytical calculations have been obtained that would have been costly to obtain otherwise.
  • Ability to simulate to assess the impact of changes on process performance, allowing you to focus on specific modifications to maximize process improvement.

In public entities, process mining can allow us to verify and make transparent metrics and process performance, reduce waiting times, eliminate cases that do not comply with regulations, and at the organizational level, a saving of time in the identification and definition of processes. .

One of the most common challenges is the availability and quality of data. In this case they were available and easy to extract in the tool ticketing.  It is very important that the tool or platforms used to run the operations, make this record and allow this information to be extracted if you want to minimize the effort of data preparation when tackling a process mining project.

Status of the project

· Pilot project: Advanced analysis with process mining completed.

More information

·       Iterem

·       Apromore platform