Update README.md

README.md

@@ -18,38 +18,68 @@ To construct a comprehensive dataset for document parsing, we integrate both rea
 
 # Data Statistics
 
-| Document Type | Samples Number |
-| --- | --- |
-| Synthetic Documents | 6546 |
-| Financial Reports | 14207 |
-| Medical Reports | 5000 |
-| Academic Papers | 8856 |
-| Books | 12488 |
-| Magazines | 2969 |
-| Web Pages | 5000 |
-| All | 55066 |
+Due to company policy constraints, we can only open-source a portion of the training data. We appreciate your understanding. The statistics are as follows:
+
+| Document Type | Samples Number | BBox and Reading Order | 
+| :---: | :---: | :---: |
+| Synthetic Documents | 6546 | ✓ |
+| Financial Reports | 2000 ||
+| Medical Reports | 2000 ||
+| Academic Papers | 5979 ||
+| Books | 1749 ||
+| Magazines | 1688 ||
+| Web Pages | 2000 ||
+| All | 21962 ||
 
 # Data Format
 
+Full-page document parsing format:
+
 ```json
-{
+[
+  {
     "images": ["path/to/image"],
     "conversations": [
       {
         "from": "human",
-        "value": "Please transform the document's contents into Markdown format."
+        "value": "prompt"
       },
       {
         "from": "gpt",
         "value": "ground_truth"
+      }
     ],
     "attributes": {
-        "document_type": "document_type",
-        "task": "task"
+      "document_type": "document_type",
+      "task": "task"
     }
-}
+  },
+  ...
+]
+```
+
+Layout analysis and reading order format:
+
+```json
+[
+  {
+    "images": ["path/to/image"],
+    "form": [
+      {
+        "category": "The category is in [\"title\", \"plain_text\", \"table\", \"table_caption\", \"figure\", \"figure_caption\", \"header\", \"footer\"]"
+        "bbox": [x1, y1, x2, y2],
+        "text": "text content of title, plain_text, table_caption, figure_caption, header or footer",
+        "html": "table html"
+      },
+      ...
+    ]
+  },
+  ...
+]
 ```
 
+Note that the elements in 'form' are sorted in reading order.
+
 # License
 
 This dataset is licensed under cc-by-nc-sa-4.0.