JOURNAL OF IQRO – ЖУРНАЛ ИҚРО – IQRO JURNALI – volume 15, issue 02, 2025
ISSN: 2181-4341, IMPACT FACTOR ( RESEARCH BIB ) – 7,245, SJIF – 5,431
ILMIY METODIK JURNAL
Tursunbek Sadriddinovich Jalolov
Asia international university pffd .( PhD)
PROCESSING VARIOUS TYPES OF DIAGRAMS THROUGH ARTIFICIAL
INTELLIGENCE USING PYTHON
Abstract:
This in the article artificial Python programming of intelligence language through
graphic and diagram shaped information again at work place is highlighted . Diagrams in the
form of visual information automatic in a way analysis to do and them semantic in terms of
comment current technological development during important importance profession Python is
doing libraries using figurative information again work , they based on concept harvest to do ,
statistical and semantic solutions working exit opportunities seeing In this regard mechanical
learning (Machine Learning), deep learning (Deep Learning) and the image again such as image
processing technologies analysis will be done .
Key words :
Python, artificial intellect , diagram , image again work , mechanical study ,
analysis , semantics interpretation , OpenCV , matplotlib , AI.
Current time technological in the environment visual data — graphs , diagrams , tables —
information important shape as confession Especially in medicine , economics , engineering and
education in the fields diagram and graphs important information source is considered .
Diagrams automatic in a way recognizing to take and them content analysis to do artificial
intellect tools through increasingly becoming popular Python language and this in process main
tool become service is doing . His open source libraries AI models through create , image again
work and semantic to concepts based analysis done increase possible . Current time information
in the century diagrams and graphs complicated information understandable in appearance
presented of reaching important Artificial artificial intelligence (AI) and Python programming
language using diagrams automatic again performance , analysis to do and create processes
noticeable at the level This is easy . in the article Python and AI technologies through diagrams
with of work main advantages and application seeing is released .
Home part
Current on the day information with at work diagrams and graphs important role plays . Artificial
artificial intelligence (AI) and Python programming language using diagrams again work
processes noticeable at the level made easy . Python strong libraries and AI technologies through
diagrams automatic analysis to do , to edit and visualization to do opportunities further is
expanding . First of all , using Python diagrams automatic again work processes noticeable at the
level It is faster than OpenCV , like Pillow (PIL) libraries computer based on computer vision in
the diagrams elements identify , texts reading (OCR – Tesseract such as technologies via ) and
information systematization opportunity This gives at hand diagram to compose process
automate and save time to save take comes . Artificial intelligence , especially machine learning
(ML) and natural the language again performance (NLP) technologies in the diagrams
information more precisely analysis to do opportunity For example , TensorFlow or PyTorch
such as frameworks using in the diagrams trends determine , relationships find or mistakes
correction possible . NLP tools ( spaCy , NLTK ) in the charts textual information understanding
and in the selection help Python 's visualization libraries ( Matplotlib , Seaborn , Plotly )
interactive and dynamic diagrams in creation especially convenient . Real -time renewable
graphics , 3D models or mobile visualizations create possible . Bokeh or like Dash libraries and
to users complicated information simple and understandable in a way see opportunity gives .
JOURNAL OF IQRO – ЖУРНАЛ ИҚРО – IQRO JURNALI – volume 15, issue 02, 2025
ISSN: 2181-4341, IMPACT FACTOR ( RESEARCH BIB ) – 7,245, SJIF – 5,431
ILMIY METODIK JURNAL
Big in size information with Python and AI in performance importance further increases . Pandas,
NumPy such as libraries using millions from the rows consists of information quickly again
work , diagrams convert possible . Dask or like Apache Spark frameworks and big in quantity
data in parallel again work opportunity gives .
Diagrams artificial intellect through analysis to do two main in the direction done increased
1.
Image as again work
is in stages diagram picture in appearance taken , it segmentation to
make , elements identify , texts separate to take done is increased .
2.
Semantic analysis
is in process diagram elements between connections is determined , their
meaning automatic in a way is interpreted .
In Python this the process done increase for following main libraries used :
OpenCV
– image analysis to make , filters , contours identify , elements separation
Tesseract -OCR
– in the diagram textual elements separate to take and to the text convert
matplotlib / seaborn
– charts automatic harvest to do and they with work
TensorFlow / PyTorch
– deep study models diagram to the analysis adaptation .
Example as follows the process imagination we do : user PDF or picture shaped diagram This
loads . diagram OpenCV through segmentation is done , then Tesseract using text elements is
determined . Then this text and graphic components based on model diagram content analysis
This method does medical graphs ( e.g. ECG, blood pressure graph ) or economic indicators in
the graphs use possible .
Another one current direction —
from the diagram information base Create
a diagram . line
or columns studied , they based on numerical values is determined and structured format (CSV,
JSON ) . This information later visualization , statistics analysis or in forecasting is applied .
Artificial intellect using processing given diagrams following to the advantage has :
From the diagram information automatic release ;
User heavy the load relief ;
Diagram content blind and weak seers for to the text to convert ;
Information according to automatic analysis and conclusion release opportunity .
Practical program sample :
import cv2
import pytesseract
image = cv2.imread('diagram.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
ret , thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)
text = pytesseract.image_to_string (thresh)
print( " In the diagram text :", text)
JOURNAL OF IQRO – ЖУРНАЛ ИҚРО – IQRO JURNALI – volume 15, issue 02, 2025
ISSN: 2181-4341, IMPACT FACTOR ( RESEARCH BIB ) – 7,245, SJIF – 5,431
ILMIY METODIK JURNAL
Above code through in the diagram text elements automatic separate is taken . Such approach
develop , texts location , diagram with elements ( row , column ) related automate analyses as
well possible .
Conclusion
Diagrams artificial intellect using analysis to do current at the time wide opportunities Python
programming language this regarding main from tools one is , its using figurative information
effective in a way analysis to do possible . Diagrams automatic learning , semantic analysis to do
them structural to look to bring through many in the fields information flow optimization
possible . In the future this technologies digital analysis , artificial vision , automated information
systems and education in technologies wide is applied .
Used literature
1. Jalolov, T. S. (2024). SUN'IY INTELLEKTNI KIBERXAVFSIZLIK TIZIMLARIDA QO
‘LLASH: TAHDIDLARNI ERTA ANIQLASH USULLARI. Modern digital technologies in
education: problems and prospects, 1(2), 54-59.
2. Jalolov, T. S. (2024). KUCHLI VA ZAIF SUN'IY INTELLEKT MODELLARI:
ULARNING TAQQOSLANISHI VA RIVOJLANISH ISTIQBOLLARI. Modern digital
technologies in education: problems and prospects, 1(2), 91-96.
3. Jalolov,
T.
S.
(2024).
MASHINA
O
‘QITISH
ALGORITMLARINI
OPTIMALLASHTIRISH:
SAMARADORLIK
VA
ANIQLIKNI
OSHIRISH
USULLARI. Modern digital technologies in education: problems and prospects, 1(2), 97-102.
4. Jalolov, T. S. (2024). SUN'IY INTELLEKT YORDAMIDA SOXTA MA'LUMOTLARNI
ANIQLASH USULLARI. Modern digital technologies in education: problems and
prospects, 1(2), 47-53.
5. Jalolov, T. S. (2024). AI ASOSIDA HUJUMLARNI BASHORAT QILISH VA HIMOYA
STRATEGIYALARINI ISHLAB CHIQISH. Modern digital technologies in education:
problems and prospects, 1(2), 66-71.
6. Jalolov, T. S. (2024). KUCHLI AI BILAN JIHOZLANGAN ROBOTOTEXNIKA UCHUN
REJALASHTIRISH VA QAROR QABUL QILISH ALGORITMLARI. Modern digital
technologies in education: problems and prospects, 1(2), 60-65.
7. Jalolov, T. S., & Usmonov, A. U. (2021). “АQLLI ISSIQXONA” BOSHQARISH
TIZIMINI MODELLASHTIRISH VA TADQIQ QILISH. Экономика и социум, (9 (88)), 74-77.
8. Жалолов, Т. (2023). Использование математических методов в психологических
данных (с использованием программного обеспечения SPSS). in Library, 4(4), 359-363.
9. Jalolov, T. S. (2024). ANALYSIS OF PSYCHOLOGICAL DATA USING SPSS
PROGRAM. Multidisciplinary Journal of Science and Technology, 4(4), 477-482.
10. Sadriddinovich, J. T. (2024). BASICS OF PSYCHOLOGICAL SERVICE. PSIXOLOGIYA
VA SOTSIOLOGIYA ILMIY JURNALI, 2(4), 61-67.
11. Jalolov, T. S. (2024). ЭКОЛОГИЧЕСКИЙ СИСТЕМЫ ИСКУССТВЕННЫЙ В
МОНИТОРИНГЕ ИНТЕЛЛЕКТ ТЕХНОЛОГИЙ ПРИЛОЖЕНИЕ. Advanced methods of
ensuring the quality of education: problems and solutions, 1(3), 86-92.
12. Jalolov, T. S. (2024). НА ОСНОВЕ ИИ НАПАДЕНИЯ ПРОРОЧЕСТВО ДЕЛАТЬ И
ЗАЩИЩАТЬ. Advanced methods of ensuring the quality of education: problems and
solutions, 1(3), 60-65.
13. Jalolov, T. S. (2024). ОСНОВО МАШИННОГО ЯЗЫКА. Advanced methods of ensuring
the quality of education: problems and solutions, 1(3), 46-52.
14. Jalolov, T. S. (2024). ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ С ИСПОЛЬЗОВАНИЕМ
ФАЛЬШИВЫЙ ИНФОРМАЦИЯ ОПРЕДЕЛИТЬ МЕТОДЫ. Advanced methods of ensuring
the quality of education: problems and solutions, 1(3), 53-59.
