Home / FAQs / Enterprise context engineering, model migration and process intelligence
QUESTION & ANSWER

AI Process Mining Data Requirements

At a minimum, one needs a business object identifier, a group of activity names and corresponding time, such as the order number, order status and time of occurrence. To analyse organization, waiting, back-to-work and cross-system collaboration, it also requires user roles, departments, amounts, channels and associated objects. Data need not be initially perfect, but they must be able to sample back to the source system to check. In the absence of an event log, the first phase can be filled with a site or task observation.

Answer the question.

First, give conclusions that can be used for decision-making

The core fields are case identification, activity and time: for example, changes in the status of each order from creation, audit, delivery to receipt. To explain the bottlenecks, you can also add implementers, departments, clients, products, amounts, channels, unusual causes and system sources. Cross-system scenes require the creation of stable connecting keys and the harmonization of time zones, status meanings and repeat event processing. Mail, tables and lower steps cannot be detected automatically from the system log, and need to be linked to interviews, missions or new record points.

DECISION FACTORS

What conditions need to be identified before judgement is made?

The same question may have different answers under different business, data and project phases. It is suggested that the following conditions be checked and that the common findings on the web be incorporated into their own projects.

Identification of business objects and process starting and ending pointsWhether the change in status is credible and operatorCross-system recording of business identification linkagesWhether historical data contain deletions, additions and batch changes
ACTION STEPS

Suggested order of advance

01

First, we'll be clear about the target and the border.

Select a process that is of high business value and more complete data.

02

Validation Key Dependence

Defines the case identifier, activity, time and analytical dimensions.

03

Development of assessable outcomes

Take small samples and check them with source systems and operators.

04

Make sure you decide the next step with the real results.

Enlarge data and analyse process variations after calibration.

PRACTICAL EXAMPLE

How do you understand it in the actual business?

Example used to illustrate the method of judgement

When analysing the procurement approval, only the application form is in its current state and cannot be restored; the application number, each time it is submitted, returned, forwarded and approved in the approval record is required. If a financial payment is made using another system, it is also connected through a purchase order or contract number.

COMMON RISKS

The easiest pit to step on.

Misperformed current status table as full event history

Different systems match with vague names, causing an error connection

Individual efficiency is evaluated on log basis without operational reconciliation

ACCEPTANCE

How should we end up receiving and confirming?

Event data should be accompanied by field calibre, source, cleansing rules and coverage. The extraction of a number of real business objects allows for the gradual recurrence of major events and time from the source system; the number, cycle and status of major processes should be broadly consistent with the statement of operations. Underline activities that cannot be covered must be clearly stated and cannot be completed by the model itself.

When preparing to communicate with suppliers or internal teams, it is recommended that current processes, representative samples, existing systems, planning time and budget levels be brought. First, the unknown items are clearly marked, and then the decision is made to use diagnostics, PoC, fixed-range projects or ongoing research and development, which is usually more reliable than a direct demand for a price and duration without borders.

Your project conditions are different from the examples above?

Operational objectives, existing systems, sample and planned time could be collated before consultants could make preliminary judgements in relation to actual boundaries.

Associate project consultants