import re import random def message_probability( user_message, recognised_words, single_response=False, required_words=None ): if required_words is None: required_words = [] message_certainty = 0 has_required_words = True for word in user_message: if word in recognised_words: message_certainty += 1 percentage = float(message_certainty) / float(len(recognised_words)) for word in required_words: if word not in user_message: has_required_words = False break if has_required_words or single_response: return int(percentage * 100) else: return 0 def unknown(): response = ["Could you please re-phrase that? ", "...", "Sounds about right.", "What does that mean?"][ random.randrange(4)] return response def check_all_messages(message): highest_prob_list = {} def response(bot_response, list_of_words, single_response=False, required_words=[]): nonlocal highest_prob_list highest_prob_list[bot_response] = message_probability(message, list_of_words, single_response, required_words) # Responses ------------------------------------------------------------------------------------------------------- response("بله", ["دارد", "نشانه", "علایم", "علائم", "بله"], required_words=["بله"]) response("خیر", ["ندارد", "نشانه‌ای", "علایمی", "خیر"], required_words=["خیر"]) response("L99", ["تمام", "خروج", "پایان", "l99"], required_words=["پایان"]) response("L01", ["اختلالات", "حرکتی", "Movement", "disorders","حرکت"], required_words=["حرکت"]) response("L02", ["تعمیم یافته", "صورت", "گردن", "اندامهای", "رقصاک", "فوقانی", "تحتانی", "تنه"], required_words=["رقصاک"]) response("L03", ["چشمی", "عصبی", "حرکت" ], required_words=["عصبی"]) response("L04", ["بیماری‌", "عصبی", "متا", "بولیکی", "نورومتابولیکی" ], required_words=["عصبی"]) response("L05", ["روان‌پزشکی", "روانپریشی", "روان", "پزشکی", "روانپزشکی" ], required_words=["روانپزشکی"]) response("L06", ["هیپرهموسیستئینمی", "hyperhomocysteinemia","ژنتیکی" ], required_words=["ژنتیکی"]) response("L07", ["درگیری", "طناب", "نخاعی", "spinal", "cord", "نخاعی" ], required_words=["نخاعی"]) response("L08", ["کوبالامین", "داخل", "سلولی", "intracellular", "cobalamin","سلولی" ], required_words=["سلولی"]) response("L09", ["لیپاز", "اسید", "لیزوزومال", "LAL-D", "کمبود" ], required_words=["کمبود"]) response("L10", ["هیدرولیپوآمید", "دهیدروژناز", "کمبود" ], required_words=["کمبود"]) response("L11", ["فسفاتمی","هایپوفسفاتمی", "هیپوفسفاتمی", "hypophosphatemia", "HP", "ژنتیکی" ], required_words=["ژنتیکی"]) response("L12", ["آنسفالوپاتی", "هیپرآمونمیک", "غیر", "کبدی", "جراحی", "چاقی", "Nonhepatic", "hyperammonemic", "encephalopathy", "bariatric", "surgery", "NHE-BS" ], required_words=["کبدی"]) response("L13", ["لرزش", "میتو", "کندری", "میتوکندری", "ژنتیکی" ], required_words=["ژنتیکی"]) response("L14", ["اندام", "لرزش", "ترمور", "Tremor", "TRM" ], required_words=["عصبی"]) best_match = max(highest_prob_list, key=highest_prob_list.get) print(f'Best match = {best_match} | Score: {highest_prob_list[best_match]}') return unknown() if highest_prob_list[best_match] < 1 else best_match def replace_synonyms(sentence): synonyms_dict = { "بله": [ "بله", "بلی", "بلخ", "یله", "پله", "آره", "آری", "آرخ", "yes", "ya", "bale", "ari", "are", "fgi", "hvi", "Hvd", "Hvd", "fgd", "hsj", "isj", "nhvn", "هست", "است", "دارد", "یس", "nhavd", "هست", "احتمال دارد", "امکان دارد", "میتواند", "شاید", "احتمال مثبت", "باشد", "می دهم", "یس", "yes", "yup", "چک کن", "مشکوک", "دارد" ], "خیر": [ "نه", "منفی", "odv", "kodv", "خیر", "no", "ni", "نخیر", "نیست", "نبود", "نمیشود", "نمی شود", "نمی\u200cشود", "نیست", "ندیدم", "دخ", "nist", "nabod", "na", "nah", "noch", "nuch", "nooch", "manfi", "udv" ], } reverse_dict = {} for key, synonyms in synonyms_dict.items(): for synonym in synonyms: reverse_dict[synonym] = key regex_pattern = r'\b(' + '|'.join(map(re.escape, reverse_dict.keys())) + r')\b' def replace(match): return reverse_dict[match.group(0)] result = re.sub(regex_pattern, replace, sentence) print(result) return result # Used to get the response def get_response(user_input): user_input = replace_synonyms(user_input) split_message = re.split(r'\s+|[,;?!.-]\s*', user_input.lower()) response = check_all_messages(split_message) return response