# Manual Keying Correction Log Worksheet

> Source: https://netray.co/tools/manual-keying-correction-log-worksheet
> Publisher: Netray (netray.co), AI and integration engineering for ERP and manufacturing systems.
> Section: Free Tools

## Short answer

Record which extracted fields reviewers correct, how often, and why, so you can retrain or reconfigure where errors cluster.

## Category

ai-automation

## Industry

Discrete Manufacturing

## Audience

- AP analyst
- Capture administrator
- Process improvement lead

## Tool

**Kind:** worksheet

**Mode:** editable

**Columns:**

#### Field

**Key:** field

**Type:** select

**Options:**

- Vendor
- Invoice number
- Invoice date
- PO number
- PO line
- Quantity
- Unit price
- Net amount
- Tax amount
- Total
- Currency
- Part number
- Heat or lot number

#### Documents checked

**Key:** checked

**Type:** number

#### Corrections made

**Key:** corrected

**Type:** number

#### Correction rate

**Key:** err_rate

**Type:** number

**Expr:** if(gt(checked,0), corrected / checked * 100, 0)

**Format:** percent

#### Typical error

**Key:** error_type

**Type:** select

**Options:**

- Wrong character
- Missed field
- Wrong field picked
- Wrong format
- Split across lines
- Unit mismatch

#### Impact

**Key:** severity

**Type:** select

**Options:**

- Blocks posting
- Causes wrong payment
- Cosmetic

#### Planned action

**Key:** action

**Type:** text

**Rows:**

**Field:** PO number

**Checked:** 400

**Corrected:** 38

**Error type:** Wrong character

**Severity:** Blocks posting

**Action:** Add check digit validation against open POs

**Field:** Total

**Checked:** 400

**Corrected:** 6

**Error type:** Wrong field picked

**Severity:** Causes wrong payment

**Action:** Compare to sum of lines before posting

**Field:** Unit price

**Checked:** 400

**Corrected:** 29

**Error type:** Wrong format

**Severity:** Causes wrong payment

**Action:** Normalize decimal separators by vendor country

**Field:** Invoice date

**Checked:** 400

**Corrected:** 17

**Error type:** Wrong format

**Severity:** Cosmetic

**Action:** Set date order per vendor

**Field:** Heat or lot number

**Checked:** 150

**Corrected:** 21

**Error type:** Wrong character

**Severity:** Blocks posting

**Action:** Retrain on stamped numbers

**Totals:**

#### Total corrections

**Key:** corrected

**Agg:** sum

**Format:** integer

#### Worst field correction rate

**Key:** err_rate

**Agg:** max

**Format:** percent

**Summary:**

#### Corrections per 100 documents checked, all fields

**Key:** mix

**Expr:** if(gt(sum_checked,0), sum_corrected / sum_checked * 100, 0)

**Format:** decimal

**Primary:** true

**Notes:** Count a correction when a person changes the value the system proposed. Do not count fields the system left blank and a person filled, unless you add a Missed field row.

## Content

**Intro:** Overall accuracy hides which fields cause the work. This log tracks corrections per field so you can see where the engine struggles and fix that field first.

**Sections:**

#### How to use the log

**Body:** Pick a review period, such as a week, and a sample of documents that reviewers touched. For each field, enter how many documents were checked and how many times the proposed value had to be changed. The sheet computes the correction rate for each field. Add a typical error type and an impact rating so you can compare a cosmetic date error against a wrong unit price that could cause a wrong payment.

#### Reading the results

**Body:** Sort by correction rate, then by impact. A field with a moderate rate but a blocking or payment impact deserves attention before a high-rate cosmetic field. The summary shows corrections per hundred documents across all fields, a simple trend number you can track week by week. Watch for a field that suddenly worsens, which often means a supplier changed layout or a scan source degraded.

#### Turning corrections into fixes

**Body:** Wrong characters point to image quality or model confidence. Wrong format errors usually have a rule-based fix, such as a decimal separator or date order per country. Wrong field picked suggests a layout issue that needs a template or more training samples. Add validation rules that use ERP data, like checking a PO number against open orders, to catch errors before a person must.

#### Common mistakes

**Body:** Do not count only the documents that failed, because that overstates error rates. Do not mix invoice fields and quality fields in one period without a separate row for each. Finally, retain old logs. When you change a configuration, the previous period is your baseline.

**Cta:** Netray can capture reviewer corrections automatically and feed them back to an on-prem model, so accuracy improves without separate logging work.

**Faq:**

#### What is a correction rate?

**Answer:** It is the number of times reviewers changed a field value divided by the documents checked for that field, shown as a percent. It is a practical measure of how often the engine was wrong on a field in daily use.

#### Is this the same as OCR accuracy?

**Answer:** It is closely related but based on real review behavior rather than a test set. It captures only errors that reviewers noticed, so it can understate true errors if review is shallow.

#### How big a sample should I use?

**Answer:** A few hundred documents per period gives a stable view for common fields. Rare fields, like heat numbers, need their own count of documents where the field appears, which is why checked is entered per row.

#### Which fields should I track first?

**Answer:** Start with the fields that block posting or affect payment: vendor, PO number and line, quantity, unit price, tax and total. Add descriptive or quality fields once those are under control.

## Search terms

ocr correction log, invoice capture field error rate, ocr field accuracy tracking excel, document ai error log, ocr feedback log, extraction correction tracking

---
Talk to an engineer: https://netray.co/contact?intent=erp_ai | Machine catalog: https://netray.co/agent/catalog.json