In "document intelligence", i have one problem. That is i have a same key in different places in one single image. how to seperate prediction for my requested prompt.

[Dineshkumar-Anandan-ZS0367]

请提出你的问题

city,state,zip. this key present in image both left and right side. left side patient information and right side prescriber informations are available, how to solve this.

[wawltor]

In "document intelligence", the model was a fined-tune model, we can not change the result of the model; You could use the method of fine-tune to impove the result of model, the document as https://github.com/PaddlePaddle/PaddleNLP/tree/develop/applications/information_extraction

[Dineshkumar-Anandan-ZS0367]

Thanks sir, Is there any options to identify which keys are present in particular images.

Say, I had a resume, the resume converted as fax documents. The resume contains my information with key value pair. How to identify which keys are present like, name, dob, address, city, etc.

How to find, is there any pretrained model available for this. I have medical related records.

Get Outlook for Androidhttps://aka.ms/AAb9ysg

---

From: wawltor @.> Sent: Tuesday, February 6, 2024 11:32:30 AM To: PaddlePaddle/PaddleNLP @.> Cc: Dineshkumar Anandan @.>; Author @.> Subject: [EXTERNAL]Re: [PaddlePaddle/PaddleNLP] In "document intelligence", i have one problem. That is i have a same key in different places in one single image. how to seperate prediction for my requested prompt. (Issue #7963)

CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you recognize the sender and know the content is safe.

In "document intelligence", the model was a fined-tune model, we can not change the result of the model; You could use the method of fine-tune to impove the result of model, the document as https://github.com/PaddlePaddle/PaddleNLP/tree/develop/applications/information_extraction

— Reply to this email directly, view it on GitHubhttps://github.com/PaddlePaddle/PaddleNLP/issues/7963#issuecomment-1928841425, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AZCYH33BBHJJ6VKP6NZVO3DYSHBPNAVCNFSM6AAAAABCYXSZP2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSMRYHA2DCNBSGU. You are receiving this because you authored the thread.Message ID: @.***>

Disclaimer: "The contents of this e-mail and any attachments enclosed therein are intended solely for the addressee(s) and may contain confidential and/or privileged information. It may also be the sole intellectual and proprietary resource of Zuci Systems and therefore may be legally protected from disclosure. If you are not the intended recipient of this message, or if this message has been addressed to you by inadvertence, kindly alert the sender by email and then follow with its deletion. If you are not the intended recipient, you are hereby notified that any use, dissemination, copying, or storage of this message or its attachments is strictly prohibited and shall make you liable for consequences under applicable laws."

[github-actions[bot]]

This issue is stale because it has been open for 60 days with no activity. 当前issue 60天内无活动，被标记为stale。

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale. 当前issue 被标记为stale已有14天，即将关闭。