Document Duplicity Check
Document duplicity check finds duplicates by the data on the document — name, date of birth, personal number, document number — rather than by face. It catches people re-registering under the same identity details and provides the text signal that complements face duplicity check.
Document duplicity check requires the Data Storage tier but, unlike face 1:N, does not require the biometric 1:N add-on — it is a text search over existing Customer records.
1:1 Document Compare
In order to decide, whether 2 documents are of a same person, rules for comparison need to be defined. Different countries may have different conventions for giving a name and may have different personal identifiers. Thus, each integration may have different comparison rules.
What is compared
The integrator needs to define, which fields are compared, and how the different comparison scores are weighted to create one matching score that is compared against a threshold.
| Strength | Fields |
|---|---|
| Strong (identity anchors) | Date of birth, personal number |
| Supporting | Full name, given names, surname, document number |
How matching works
- Text cleaning — names are normalized (titles stripped, lower-cased, punctuation removed) so cosmetic differences don't cause misses.
- Similarity scoring — names are compared with a fuzzy string-similarity measure that tolerates typos and minor spelling variation; exact fields like date of birth and personal number act as strong anchors.
- Weighted score — the platform combines the field scores into a single weighted score and compares it against a match and a similar threshold. The comparison fields, their weights, and the thresholds are configurable per tenant.
Outcomes
| Result | Meaning |
|---|---|
| No match | No existing record shares the document data. |
| Similar match | A record is close (e.g. same DOB, near-identical name) — warrants review or cross-checking against the face. |
| Full match | A record shares the strong identity fields. |
1:N Identification
Identification search the new applicant's document data against all existing Customers. First, the search narrows the candidate records, then the shortlist is re-scored using the 1:1 matching rules.
Combining document match with a face match
The real value comes from cross-checking the document signal against the face signal — a full text match with a non-matching face is a classic stolen-ID pattern, while a matching face with different text can indicate a name change or a fabricated document. See the disambiguation matrix in Identity Verification.