diff --git a/VERSION_NUMBER b/VERSION_NUMBER
index 834f262953..dbe5900654 100644
--- a/VERSION_NUMBER
+++ b/VERSION_NUMBER
@@ -1 +1 @@
-2.8.0
+2.8.1
diff --git a/paddleocr.py b/paddleocr.py
index d69c8854c1..8b9b017347 100644
--- a/paddleocr.py
+++ b/paddleocr.py
@@ -50,7 +50,6 @@ def _import_file(module_name, file_path, make_importable=False):
 ppstructure = importlib.import_module("ppstructure", "paddleocr")
 from ppocr.utils.logging import get_logger
 
-logger = get_logger()
 from ppocr.utils.utility import (
     check_and_read,
     get_image_file_list,
@@ -68,6 +67,7 @@ def _import_file(module_name, file_path, make_importable=False):
 from ppstructure.predict_system import StructureSystem, save_structure_res, to_excel
 
 logger = get_logger()
+
 __all__ = [
     "PaddleOCR",
     "PPStructure",
diff --git a/ppstructure/predict_system.py b/ppstructure/predict_system.py
index a2d21df79b..69f8e27765 100644
--- a/ppstructure/predict_system.py
+++ b/ppstructure/predict_system.py
@@ -121,7 +121,7 @@ def __call__(self, img, return_ocr_result_in_table=False, img_idx=0):
                 time_dict["layout"] += elapse
             else:
                 h, w = ori_im.shape[:2]
-                layout_res = [dict(bbox=None, label="table")]
+                layout_res = [dict(bbox=None, label="table", score=0.0)]
 
             # As reported in issues such as #10270 and #11665, the old
             # implementation, which recognizes texts from the layout regions,
diff --git a/pyproject.toml b/pyproject.toml
index bc437656a1..6d46c0870b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -58,6 +58,12 @@ dependencies = [
     "fire>=0.3.0",
 ]
 
+[project.urls]
+homepage = "https://github.com/PaddlePaddle/PaddleOCR"
+documentation = "https://github.com/PaddlePaddle/PaddleOCR/blob/main/README.md"
+repository = "https://github.com/PaddlePaddle/PaddleOCR.git"
+issues = "https://github.com/PaddlePaddle/PaddleOCR/issues"
+
 [project.scripts]
 paddleocr = "paddleocr.paddleocr:main"