> ## Documentation Index
> Fetch the complete documentation index at: https://help.dingtalk.io/llms.txt
> Use this file to discover all available pages before exploring further.

# AI attendance photo error detection

> DingTalk's AI-powered detection for photo clock-in errors uses large models and image understanding to automatically flag invalid photos, missing faces, dress code violations, and other non-compliant clock-ins, helping managers supervise remotely with speed and accuracy.

In daily attendance management, more organizations rely on photo clock-in to verify that employees actually arrive on site or complete store-visit tasks. In practice, however, common issues occur:

* Employees upload invalid images such as ceilings, floors, black screens, or blank walls.
* Photos do not include a face, making it impossible to prove the employee was present.
* Store-visit photos of shelves or displays are blurry or taken from the wrong angle, failing to reflect the actual situation.
* Special role requirements (such as wearing a safety helmet, reflective vest, or compliant makeup) lack effective inspection methods.
* Admins must manually review hundreds or thousands of photos one by one, which is time-consuming and inefficient.

## Product solution

To tackle these management challenges, DingTalk offers AI-powered detection for photo clock-in errors. By combining large models with image understanding, it automatically identifies non-compliant clock-in behavior, enabling Organization managers to supervise remotely with efficiency and precision.

## Key feature highlights

<CardGroup cols={2}>
  <Card title="Invalid image detection">Automatically detects abnormal photos such as black screens, blank screens, ceilings, and floors.</Card>
  <Card title="Facial recognition check">Determines whether the photo contains a face.</Card>
  <Card title="Error notification mechanism">Automatically generates Error reports and pushes them to Admins for handling.</Card>
  <Card title="Statistics visualization Kanban">Provides an overview of photo quality Data in the attendance Admin Console.</Card>
</CardGroup>

## Feature details and access path

<div style={{display:'flex', flexWrap:'wrap', gap:'16px', justifyContent:'center', margin:'16px 0'}}>
  <img src="https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/res/YdgOk2bv3LgBgq4B/img/d49dd7ba-40bb-4c67-968d-6649677ac213.png" alt="Clock-in photo statistics example" style={{width:'48%', minWidth:'240px', borderRadius:'8px', boxShadow:'0 2px 12px rgba(0,0,0,0.08)', margin:0}} />

  <img src="https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/res/YdgOk2bv3LgBgq4B/img/3776f58a-30d7-4c9b-8d22-89cb005849ab.png" alt="Error detection results example" style={{width:'48%', minWidth:'240px', borderRadius:'8px', boxShadow:'0 2px 12px rgba(0,0,0,0.08)', margin:0}} />
</div>

**Access path**: Attendance App > Statistics > More statistics > Clock-in photo statistics.

**Page content**: On this page, you can review analysis results for clock-in photos from today or previous days, including the total number of clock-in photos, the counts of compliant versus non-compliant photos, and Error type categories. Click any item to view details and inspect the photos one by one.

**Generation time**: The system currently runs in asynchronous, post-event detection mode. Analysis usually completes and results appear the morning after the clock-in.

## Core value

* **HR / Admins**: Cut manual review workload by more than 90% and quickly surface violations.
* **Business managers**: Achieve standardized process control over store visits, field work, and on-site operations.
* **Organization-wide**: Strengthen policy enforcement, organizational discipline, and safety management Standards.

## Typical use cases

| Scenario                                  | Description                                                                                         | Representative industries             |
| ----------------------------------------- | --------------------------------------------------------------------------------------------------- | ------------------------------------- |
| Safety helmet check on construction sites | Automatically detects whether a safety helmet is worn during field clock-in                         | Construction, engineering supervision |
| Hygiene cap compliance check in kitchens  | Detects whether kitchen staff wear a hygiene cap when clocking in for work                          | Catering, food processing             |
| Store Employee makeup check               | Employees take a photo before starting a sales shift, and the system helps assess makeup compliance | Beauty, chain stores                  |
| Merchandise display compliance check      | Photos of shelves are taken during store visits to check whether the display meets Standards        | Retail, fast-moving consumer goods    |