30 окт 2020 30.10.2020

Опрос. Кто часто сталкивается с файлами PDF?

Коллеги добрый вечер, я программист, который хочет сделать масштабный проект, нужна ваша критика и обратная связь.

Идея. Возникла идея сделать сервис по распознаванию pdf документов и агрегирования информации в табличный вид Эксель.

Проблема. Проблема заключается в том, что у всех документов PDF своя разметка, которые нельзя сделать универсальной.

Реализация. Если пользователь научит нейронную сеть распознавать документы так, как ему нужно, у него (у пользователя) будет "свой универсальный распознавательOCR"

Обратная связь. Прошу дать критику или же написать сферу применения данного алгоритма.

Всех благ.

29 показов

64 открытия

0

2 комментария

Олег Погребной

30.10.2020

?

PDF.io – Essential Online PDF Tools

Free set of online tools for handling PDF files. Convert and edit your PDF files with incredible…

Ответить

Развернуть ветку

Ilya Esin

30.10.2020 Автор

Он не оптимизирует рарзметку на вашем PDF, он просто делает excel таблицу

Ответить

Развернуть ветку

Написать комментарий...

-1 комментариев

Раскрывать всегда

[{"id":1,"label":"Header, 100%x250: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","auto_reload":true,"adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"ezfl"}},"distribution":"top-desktop"},{"id":2,"label":"Header, 1200x400\/600: M","provider":"adfox","adaptive":["phone"],"adfox_method":"createAdaptive","auto_reload":true,"adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"ezfn"}},"distribution":"top-mobile"},{"id":4,"label":"Article Branding top","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"p1":"cfovx","p2":"glug"}}},{"id":5,"label":"300x600: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"ezfk"}},"distribution":"right-sidebar"},{"id":6,"label":"Above the Comments: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"h","ps":"bugf","p2":"ffyh"}},"distribution":"before-comments-desktop","analytics":"AdfoxRecount \u2014 1020 \u2014 Show"},{"id":7,"label":"Above the Comments: M","provider":"adfox","adaptive":["tablet","phone"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"p1":"bwkpg","p2":"fjxb"}},"distribution":"before-comments-mobile"},{"id":12,"label":"Topbar button: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"p1":"bscsh","p2":"fdhx"}}},{"id":13,"label":"In Article: M","provider":"adfox","adaptive":["phone"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"h","ps":"bugf","p2":"flvn"}},"analytics":"AdfoxRecount \u2014 300 \u2014 Show"},{"id":15,"label":"In-Feed Teaser: DM","provider":"adfox","adaptive":["desktop","tablet","phone"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"p1":"byudx","p2":"ftjf"}}},{"id":16,"label":"Topbar button: M","provider":"adfox","adaptive":["tablet","phone"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"p1":"byzqf","p2":"ftwx"}}},{"id":17,"label":"Stratum: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","auto_reload":true,"adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"fzvb"}}},{"id":18,"label":"Stratum: M","provider":"adfox","adaptive":["tablet","phone"],"adfox_method":"createAdaptive","auto_reload":true,"adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"fzvc"}}},{"id":19,"label":"Under the News Teaser: DM","provider":"adfox","adaptive":["desktop","tablet","phone"],"adfox_method":"createAdaptive","auto_reload":true,"adfox":{"ownerId":228129,"params":{"p1":"cbltd","p2":"gazs"}}},{"id":20,"label":"Leftbar button: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"p1":"cgxmr","p2":"gnwc"}}},{"id":21,"label":"Header Microteaser: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"gtjk"}}},{"id":23,"label":"In Article: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"hiig"}}},{"id":26,"label":"For test: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"icbj"}}},{"id":27,"label":"For test: M","provider":"adfox","adaptive":["tablet","phone"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"icbn"}}},{"id":28,"label":"For test: DM","provider":"adfox","adaptive":["desktop","tablet","phone"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"icbo"}}},{"id":31,"label":"300x600 screen 2: D","provider":"adfox","adaptive":["desktop"],"adfox_method":"createAdaptive","adfox":{"ownerId":228129,"params":{"pp":"g","ps":"bugf","p2":"fizc"}}}]