نوع مقاله : مقاله پژوهشی
نویسنده
استادیار، گروه مهندسی برق و کامپیوتر، دانشکده فنی و مهندسی، دانشگاه ایوان کی، ایوان کی، سمنان، ایران.نویسنده مسئول ohammad.Rabiei@eyc.ac.ir :
چکیده
تایید نام در فرآیند ﺛﺒﺖ ﺗﺎﺳﻴﺲ ﺷﺮﻛﺖ ﺑﺎﻋﺚ ﻣﻲﺷﻮﺩ ﺍﺯ ﺛﺒﺖ ﺷﺮﻛﺖ ﻫﺎﻳﻲ ﻛﻪ ﻧﺎﻡ ﺁﻥ ﻫﺎ ﺑﺎ ﺯﻣﻴﻨﻪ ﻓﻌﺎﻟﻴﺖ ﻫﻤﺨﻮﺍﻧﻲ ﻧﺪﺍﺭﺩ ﺟﻠﻮﮔﻴﺮﻱﺑﻌﻤﻞ ﺁﻳﺪ. ﺩﺭ ﺍﻳﻦ ﻣﻘﺎﻟﻪ بمنظور بررسی درصد تطبیق ﻧﺎﻡ ﭘﻴﺸﻨﻬﺎﺩﻱ ﻣﺘﻘﺎﺿﻴﺎﻥ ﺛﺒﺖ ﺷﺮﻛﺖ ﺑﺎ ﺯﻣﻴﻨﻪ ﻓﻌﺎﻟﻴﺖ ﺷﺮﻛﺖ روشی نوین بر اساس الگوریتمهای یادگیری عمیق ارائه شده است. داده های این پژوهش از ﺳﺎﺯﻣﺎﻥ ﺛﺒﺖ ﺍﺳﻨﺎﺩ ﻭ ﺍﻣﻼﻙ ﻛﺸﻮﺭ جمع آوری گردیده است. در روش پیاده سازی ابتدا از فیلترهای اولیه نامگذاری شرکت استفاده شده است. سپس با ﺍﺳﺘﻔﺎﺩﻩ ﺍﺯ ﺗﺮﻛﻴﺐﺭﻭﺵ آریا برت به ﻋﻨﻮﺍﻥ ﻳﻚ ﺗﻜﻨﻴﻚ تعبیه کلمات به ﺗﺒﺪﻳﻞ ﻧﺎﻡ پیشنهادی ﺷﺮﻛﺖ به بردار پرداخته می شود. در مرحله ای موازی زمینه فعالیت شرکت را با استفاده از فستتکس به ﺑﺮﺩﺍﺭ ﻋﺪﺩﻱ ﻭ تلفیق بردار بدست آمده با الگوریتمهای یادگیری عمیق حافظه کوتاه و بلند مدت دو طرفه بر اساس یک لایه توجه اضافه می گردد. جهت ارزیابی نتایج از ﻣﻌﻴﺎﺭ ﺷﺒﺎﻫﺖﻛﺴﻴﻨﻮﺳﻲ و معیار روج (1و2و ال) ﺍستفاده ﺷﺪﻩ ﺍﺳﺖ. پس از تایید پذیرش نام شرکت و زمینه فعالیت، از روش خوشه بندی دیبی اسکن برای خوشه بندی نام شرکت در دسته های فعالیت استفاده می شود.
نتایج تحقیق نشان می دهد که مقادیر دقت در بخش بردار سازی زمینه فعالیتهای شرکت برای معیار روج ال مقدار 7982/0 و مقادیر دقت و فراخوانی نهایی مدل به ترتیب 8512/0 ،8317/. محاسبه گردید. ﻫﻤﭽﻨﻴﻦ ﺿﺮﻳﺐ ﻫﻤﺒﺴﺘﮕﻲ ﺑﻴﻦ ﺷﺒﺎﻫﺖ ﻛﺴﻴﻨﻮﺳﻲﻣﺤﺎﺳﺒﻪ ﺷﺪﻩ ﺑﻴﻦ ﻧﺎﻡ ﭘﻴﺸﻨﻬﺎﺩﻱ ﻭ ﺯﻣﻴﻨﻪ ﻓﻌﺎﻟﻴﺖ ﺷﺮﻛﺖ ﺑﺎ ﻣﻘﺪﺍﺭ 93 درصد ﺑﺮ ﺍﺳﺎﺱ معیارهای ﺗﻌﻴﻴﻦ ﻧﺎﻡ ﻧﺸﺎﻥ ﺩﻫﻨﺪﻩ ﻛﺎﺭﻛﺮﺩ ﺩﺭﺳﺖ ﻣﺪﻝ ﻣﻲﺑﺎﺷﺪ.
کلیدواژهها
موضوعات
عنوان مقاله [English]
Designing a system for matching the name and field of activity of companies based on artificial intelligence
نویسنده [English]
- mohammad rabiei
Associate Professor, Department of Electrical and Computer Engineering, Faculty of Engineering, Eyvanekey University, Eyvanekey, Semnan, Iran.Corresponding Author: Mohammad.Rabiei@eyc.ac. ir
چکیده [English]
Semantic similarity is used in applications such as information retrieval, text summarization and sentiment analysis. In this article, a new method based on deep learning has been presented in order to check the matching percentage of the proposed name of the company registration applicants with the time of the company's activity. The key innovation lies in the use of a combined Aria BERT model for word embedding to convert registered company names into vectors. Additionally, the company's field of activity is converted into numerical vectors using the FastText model, which are then processed through deep learning algorithms, specifically bidirectional long short-term memory (Bi-LSTM) networks with an additional attention layer. The results were evaluated using cosine similarity and ROUGE criteria. Following the approval of the company name and activity field, the DBSCAN clustering method is employed to categorize the company names based on their activities.
The results demonstrate that the ROUGE-1, ROUGE-2, and ROUGE-L scores for company activity vectorization are 0/7623, 0/7413, and 0/7982, respectively. The overall model accuracy and recall were 0/8512 and 0/8317, respectively. Moreover, the correlation coefficient between the cosine similarity of the proposed names and the company's activity time, as calculated by the model, was 93%, confirming the model's effectiveness.
This method effectively preventing the registration of names that do not meaningfully relate to the company's operations. By clustering company names, the method facilitates the suggestion of related names based on the company's field of activity.
کلیدواژهها [English]
- Company registration
- Cosine similarity
- Deep learning
- Semantic relation
- Text mining
- Abdous, M., Piroozfar, P., & Minaei Bidgoli, B. (2024). PESTS: Persian–English cross-lingual corpus for semantic textual similarity. Language Resources & Evaluation. https://doi.org/10.1007/s10579-024-09759-3
- Baigi, S. F. M., Sarbaz, M., Sobhani-Rad, D., & Kimiafar, K. (2023). A comparative study of rehabilitation information systems in 8 countries: A literature review. Iranian Rehabilitation Journal, 21(1), 1–16. https://doi.org/10.32598/irj.21.1.1766.1
- Barbella, M., & Tortora, G. (2022). Rouge metric evaluation for text summarization techniques. SSRN. https://doi.org/10.2139/ssrn.4120317
- Dogan, M. E., Dogan, T. G., & Bozkurt, A. (2023). The use of artificial intelligence (AI) in online learning and distance education processes: A systematic review of empirical studies. Applied Sciences, 13(5). https://doi.org/10.3390/app13053056
- Ghafouri, A., Abbasi, M. A., & Naderi, H. (2023). AriaBERT: A pre-trained Persian BERT model for natural language understanding. arXiv. https://arxiv.org/abs/2304.04632
- Hosseini, Z. S. M. E., Izadi, M., Tavakoli, M., et al. (2021). Designing a deep neural network model for finding semantic similarity between short Persian texts using a parallel corpus.
- Khan, S., & Anjum, M. A. I. (2023). Words in mental lexicon: A comparative analysis of word association (WA) responses of Pakistani L1 and Afghan L2 speakers of Urdu. Journal of Communication and Cultural Trends, 5(1), 86–105. https://doi.org/10.32350/jcct.51.05
- Masumi, M., Majd, S. S., Shamsfard, M., & Beigy, H. (2024). FaBERT: Pre-training BERT on Persian blogs. arXiv. https://doi.org/10.48550/arXiv.2402.06617
- Mehrban, A., & Ahadian, P. (2023). Evaluating BERT and ParsBERT for analyzing Persian advertisement data. arXiv. https://arxiv.org/abs/2305.02426
- Moniri, S., Schlosser, T., & Kowerko, D. (2024). Investigating the challenges and opportunities in Persian language information retrieval through standardized data collections and deep learning. Computers. https://doi.org/10.3390/computers13020045
- Ros, F., Riad, R., & Guillaume, S. (2023). PDBI: A partitioning Davies–Bouldin index for clustering evaluation. Neurocomputing, 528, 125–139. https://doi.org/10.1016/j.neucom.2023.01.043
- Sadidpour, S. S., Haji Gholamreza, M., Mohammadzadeh, M. R., Mohammadi, M. R., & Keivanrad, M. A. (2022). Investigation of the semantic similarity of Persian sentences using vector space adaptation and deep learning.
- Sadjadi, S. M., Rajabi, Z., Rabiei, L., & Moin, M.-S. (2024). FarSSiBERT: A novel transformer-based model for semantic similarity measurement of Persian social networks informal texts. arXiv. https://arxiv.org/abs/2407.19173
- Zareshahi, A., Javadzade, M. A., & Bastami, E. (2024). Measuring semantic similarity of Persian sentences using ParsBERT model. In 2024 10th International Conference on Artificial Intelligence and Robotics (QICAR) (pp. 316–321). https://doi.org/10.1109/QICAR61538.2024.10496609
استناد به این مقاله: ربیعی، محمد. (1405). طراحی سیستم سنجش تطابق نام و حوزه فعالیت شرکتها بر اساس هوش مصنوعی، مطالعات مدیریت کسب وکار هوشمند، 15(55)، 299-328. DOI: 10.22054/ims.2026.83957.2573
Journal of Business Intelligence Management Studies is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License..
)