From 84262e888aebbb313c45ab77e165ac6cbbcaf858 Mon Sep 17 00:00:00 2001
From: Arjun <93950622+Arjun-A-I@users.noreply.github.com>
Date: Sat, 18 Nov 2023 12:42:41 +0530
Subject: [PATCH] Create arjunai@mulearn.md

---
 DoppelDoc/arjunai@mulearn.md | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100644 DoppelDoc/arjunai@mulearn.md

diff --git a/DoppelDoc/arjunai@mulearn.md b/DoppelDoc/arjunai@mulearn.md
new file mode 100644
index 00000000..8293dd25
--- /dev/null
+++ b/DoppelDoc/arjunai@mulearn.md
@@ -0,0 +1,19 @@
+# Project- DoppelDoc
+
+GitHub- https://github.com/aditramdas/DoppelDoc
+
+# Description- Resume duplication had become a huge problem in the HR field and with the rise of chatbots and automated systems the submission of multiple resumes have skyrocketed. Duplicate resume submission for referrels by changing and rephrasing basic data has become a new world problem causing large loss for companies.
+DoppelDoc addresses this issue by incorporating Open API together with embedding vectors and prioritising strategies to sort out bulk resumes and produce only legitimate resumes for evaluation.
+
+# Conrtibution-
+>Algorithm selection for Vector embeddings.
+>Vector comparison method
+>Data search optimisation through psql Flask connectivity using psycopg2
+
+# Challenges-
+>Finding an accurate ocr parsing library and standardisation using 
+>Algorith identification,tried numerous hashing and ebedding methods.
+>DB manipulation
+>Rendering output page in flask environment
+>Maintaining code flow
+