搞得烦死了,要作个安全的程序

本文介绍了九种安全措施,包括MD5加密、COOKIES加密、SQL注入防护、木马病毒防护等,确保网站安全无忧。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

我想了这么多措施来保安全,不知道能不能挡得住呀
一、 MD5加密用户密码
用户密码采用MD5加密,听说这是一种安全性非常高的加密算法,由于这种加密的不可逆性,在使用10位以上字母加数字组成的随机密码时,几乎没有破解的可能性。
二、 COOKIES加密
保存COOKIES时,对保存于COOKIES中的数据采用了以MD5加密为基础,加入随机加密因子的改进型专用加密算法。由于使用的不是标准MD5加密,因此COOKIES中保存的数据不可能被解密。因此,黑客试图用伪造COOKIES攻击系统变得完全不可能,系统用户资料变得非常安全。
三、 SQL注入防护
系统在防SQL注入方面,设置了四道安全防护:
  第一、 系统级SQL防注入检测,系统会遍历检测所有用GET、POST、COOKIES提交到服务器上的数据,如发现有可能用于构造可注入SQL的异常代码,系统将终止程序运行,并记录日志。这一道安全防护加在连接数据库之前,能在连接数据库前挡处几乎所有的SQL注入和危害网站安全的数据提交。 
  第二、 程序级安全仿SQL注入系统,在应用程序中,在构建SQL查询语句前,系统将对由外部获取数据,并带入组装为SQL的变量进行安全性验证,过滤可能构成注入的字符。
  第三、 禁止外部提交表单,系统禁止从本域名之外的其它域名提交表单,防止从外部跳转传输攻击性代码。
  第四、数据库操作使用存储过程 系统所有的重要数据操作,均使用存储过程完成,避免组装SQL字符串,令即使通过了层层SQL注入过滤的攻击性字符仍然无法发挥作用。
四、 木马和病毒防护
针对可能的木马和病毒问题,系统认为,在服务器设置安全的情况下,外部带来的安全问题,主要是用户可能上传病毒和木马,作了如下四层的防护
第一、 客户端文件检测,在上传之前,对准备上传的文件进行检测,如果发现不是服务器设置的允许上传的文件类型,系统拒绝进行上传。如果客户端屏蔽了检测语句,则上传程序同时被屏蔽,系统无法上传任何文件。
第二、 服务器端文件安全性检测,对上传到服务器的文件,程序在将文件写入磁盘前,检测文件的类型,如发现是可能构成服务器安全问题的文件类型,即所有可以在服务器上执行的程序,系统都拒绝写入磁盘。以此保证不被上传可能在服务器上传播的病毒和木马程序。
第三、对有权限的服务器,系统采用即上传即压缩策略,所有上传的除图片文件、视频文件外,其它各种类型的文件一但上传,立即压缩为RAR,因此,即使包含木马也无法运行。不能对网站安全带来威胁。
第四、底层的文件类型检测系统对文件类型作了底层级检测,由于不仅检测扩展名,而是对文件的实际类型进行检测,所以无法通过改扩展名方式逃过安全性验证。
五、 权限控制系统
系统设置了严格有效的权限控制系统,何人可以发信息,何人能删除信息等权限设置系统一共有数十项详细设置,并且网站不同栏目可以设置完全不同的权限,所有权限均在多个层次上严格控制权限。
六、IP记录
IP地址库 除记录所有重要操作的IP外,还记录了IP所在地区,系统中内置约了17万条IP特征记录。
详细的IP记录所有的创建记录、编辑记录行为(如发文章,发评论,发站内信等),均记录此操作发生的IP,IP所在地区,操作时间,以便日后备查。在发现安全问题时,这些数据会非常关键和必要。
七、隐藏的程序入口,
  有全站生成静态页 系统可以全站生成HTML静态文件,使网站的执行程序不暴露在WEB服务中,HTML页不和服务器端程序交互,黑客很难对HTML页进行攻击,很难找到攻击目标。
八、有限的写文件 
  系统所有的写文件操作只发生于一个UPFILE目录,而此目录下的文件均为只需读写即可,可通过WINDOWS安全性设置,设置此目录下的文件只读写,不执行,而程序所在的其它文件夹只要执行和读权限,从而使破坏性文件无法破坏所有程序执行文件,保证这些文件不被修改。
九、作了MD5校验的订单数据
  在商城订单处理中,对提交的订单信息作了MD5校验,从而保证数据不被非法修改。

代码可压缩不必要的计算么,压缩内存及代码量,在不影响程序稳定的功能上: import os import sys import re import json import gc import time import tempfile import concurrent.futures import difflib import threading import traceback import numpy as np import librosa import torch import psutil import requests import hashlib import shutil from typing import List, Dict, Tuple, Optional, Set from threading import Lock, Semaphore, RLock from datetime import datetime from pydub import AudioSegment from pydub.silence import split_on_silence from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks from transformers import AutoModelForSequenceClassification, AutoTokenizer from torch.utils.data import TensorDataset, DataLoader from PyQt5.QtWidgets import (QApplication, QMainWindow, QWidget, QVBoxLayout, QHBoxLayout, QPushButton, QLabel, QLineEdit, QTextEdit, QFileDialog, QProgressBar, QGroupBox, QMessageBox, QListWidget, QSplitter, QTabWidget, QTableWidget, QTableWidgetItem, QHeaderView, QAction, QMenu, QToolBar, QCheckBox, QComboBox, QSpinBox, QDialog, QDialogButtonBox, QStatusBar) from PyQt5.QtCore import QThread, pyqtSignal, Qt, QTimer, QSize from PyQt5.QtGui import QFont, QTextCursor, QColor, QIcon # ====================== 资源监控器 ====================== class ResourceMonitor: """统一资源监控器(增强版)""" def __init__(self): self.gpu_available = torch.cuda.is_available() def memory_percent(self) -> Dict[str, float]: """获取内存使用百分比,同时返回CPU和GPU信息""" try: result = { "cpu": psutil.virtual_memory().percent } if self.gpu_available: allocated = torch.cuda.memory_allocated() / (1024 ** 3) total = torch.cuda.get_device_properties(0).total_memory / (1024 ** 3) result["gpu"] = (allocated / total) * 100 if total > 0 else 0 return result except Exception as e: print(f"获取内存使用百分比失败: {str(e)}") return {"cpu": 0, "gpu": 0} # ====================== 方言配置中心(优化版) ====================== class DialectConfig: """集中管理方言配置,便于维护和扩展(带缓存)""" # 标准关键词 STANDARD_KEYWORDS = { "opening": ["您好", "很高兴为您服务", "请问有什么可以帮您"], "closing": ["感谢来电", "祝您生活愉快", "再见"], "forbidden": ["不知道", "没办法", "你投诉吧", "随便你"] } # 贵州方言关键词 GUIZHOU_KEYWORDS = { "opening": ["麻烦您喽", "请问搞哪样", "有咋个可以帮您", "多谢喽"], "closing": ["搞归一喽", "麻烦您喽", "再见喽", "慢走喽"], "forbidden": ["搞不成", "没得法", "随便你喽", "你投诉吧喽"] } # 方言到标准表达的映射(扩展更多贵州方言) DIALECT_MAPPING = { "恼火得很": "非常生气", "鬼火戳": "很愤怒", "搞不成": "无法完成", "没得": "没有", "搞哪样嘛": "做什么呢", "归一喽": "完成了", "咋个": "怎么", "克哪点": "去哪里", "麻烦您喽": "麻烦您了", "多谢喽": "多谢了", "憨包": "傻瓜", "归一": "结束", "板扎": "很好", "鬼火冒": "非常生气", "背时": "倒霉", "吃豁皮": "占便宜" } # 类属性缓存 _combined_keywords = None _compiled_opening = None _compiled_closing = None _hotwords = None _dialect_trie = None # 使用Trie树替换正则表达式 class TrieNode: """Trie树节点类""" def __init__(self): self.children = {} self.is_end = False self.value = "" @classmethod def _build_dialect_trie(cls): """构建方言Trie树""" root = cls.TrieNode() # 按长度降序添加关键词 for dialect, standard in sorted(cls.DIALECT_MAPPING.items(), key=lambda x: len(x[0]), reverse=True): node = root for char in dialect: if char not in node.children: node.children[char] = cls.TrieNode() node = node.children[char] node.is_end = True node.value = standard return root @classmethod def get_combined_keywords(cls) -> Dict[str, List[str]]: """获取合并后的关键词集(带缓存)""" if cls._combined_keywords is None: cls._combined_keywords = { "opening": cls.STANDARD_KEYWORDS["opening"] + cls.GUIZHOU_KEYWORDS["opening"], "closing": cls.STANDARD_KEYWORDS["closing"] + cls.GUIZHOU_KEYWORDS["closing"], "forbidden": cls.STANDARD_KEYWORDS["forbidden"] + cls.GUIZHOU_KEYWORDS["forbidden"] } return cls._combined_keywords @classmethod def get_compiled_opening(cls) -> List[re.Pattern]: """获取预编译的开场关键词正则表达式(带缓存)""" if cls._compiled_opening is None: keywords = cls.get_combined_keywords()["opening"] cls._compiled_opening = [re.compile(re.escape(kw)) for kw in keywords] return cls._compiled_opening @classmethod def get_compiled_closing(cls) -> List[re.Pattern]: """获取预编译的结束关键词正则表达式(带缓存)""" if cls._compiled_closing is None: keywords = cls.get_combined_keywords()["closing"] cls._compiled_closing = [re.compile(re.escape(kw)) for kw in keywords] return cls._compiled_closing @classmethod def get_asr_hotwords(cls) -> List[str]: """获取ASR热词列表(带缓存)""" if cls._hotwords is None: combined = cls.get_combined_keywords() cls._hotwords = sorted(set( combined["opening"] + combined["closing"] )) return cls._hotwords @classmethod def preprocess_text(cls, texts: List[str]) -> List[str]: """将方言文本转换为标准表达(使用Trie树优化)""" if cls._dialect_trie is None: cls._dialect_trie = cls._build_dialect_trie() processed_texts = [] for text in texts: # 使用Trie树进行高效替换 processed = [] i = 0 n = len(text) while i < n: node = cls._dialect_trie j = i found = False # 查找最长匹配 while j < n and text[j] in node.children: node = node.children[text[j]] j += 1 if node.is_end: processed.append(node.value) i = j found = True break if not found: processed.append(text[i]) i += 1 processed_texts.append(''.join(processed)) return processed_texts # ====================== 系统配置管理器 ====================== class ConfigManager: """管理应用程序配置""" _instance = None def __new__(cls): if cls._instance is None: cls._instance = super().__new__(cls) cls._instance._init_config() return cls._instance def _init_config(self): """初始化默认配置""" self.config = { "model_paths": { "asr": "./models/iic-speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn", "sentiment": "./models/IDEA-CCNL-Erlangshen-Roberta-110M-Sentiment" }, "sample_rate": 16000, "silence_thresh": -40, "min_silence_len": 1000, "max_concurrent": 1, "dialect_config": "guizhou", "max_audio_duration": 3600 # 最大音频时长(秒) } self.load_config() def load_config(self): """从文件加载配置""" try: if os.path.exists("config.json"): with open("config.json", "r") as f: self.config.update(json.load(f)) except: pass def save_config(self): """保存配置到文件""" try: with open("config.json", "w") as f: json.dump(self.config, f, indent=2) except: pass def get(self, key: str, default=None): """获取配置值""" return self.config.get(key, default) def set(self, key: str, value): """设置配置值""" self.config[key] = value self.save_config() # ====================== 音频处理工具(优化版) ====================== class AudioProcessor: """处理音频转换和特征提取(避免重复加载)""" SUPPORTED_FORMATS = ('.mp3', '.wav', '.amr', '.m4a') @staticmethod def convert_to_wav(input_path: str, temp_dir: str) -> Optional[List[str]]: """将音频转换为WAV格式(在静音处分割)""" try: os.makedirs(temp_dir, exist_ok=True) # 检查文件格式 if not any(input_path.lower().endswith(ext) for ext in AudioProcessor.SUPPORTED_FORMATS): raise ValueError(f"不支持的音频格式: {os.path.splitext(input_path)[1]}") if input_path.lower().endswith('.wav'): return [input_path] # 已经是WAV格式 # 检查ffmpeg是否可用 try: AudioSegment.converter = "ffmpeg" # 显式指定ffmpeg audio = AudioSegment.from_file(input_path) except FileNotFoundError: print("错误: 未找到ffmpeg,请安装并添加到环境变量") return None # 检查音频时长是否超过限制 max_duration = ConfigManager().get("max_audio_duration", 3600) * 1000 # 毫秒 if len(audio) > max_duration: return AudioProcessor._split_long_audio(audio, input_path, temp_dir) else: return AudioProcessor._convert_single_audio(audio, input_path, temp_dir) except Exception as e: print(f"格式转换失败: {str(e)}") return None @staticmethod def _split_long_audio(audio: AudioSegment, input_path: str, temp_dir: str) -> List[str]: """分割长音频文件""" wav_paths = [] # 在静音处分割音频 chunks = split_on_silence( audio, min_silence_len=ConfigManager().get("min_silence_len", 1000), silence_thresh=ConfigManager().get("silence_thresh", -40), keep_silence=500 ) # 合并小片段,避免分段过多 merged_chunks = [] current_chunk = AudioSegment.empty() for chunk in chunks: if len(current_chunk) + len(chunk) < 5 * 60 * 1000: # 5分钟 current_chunk += chunk else: if len(current_chunk) > 0: merged_chunks.append(current_chunk) current_chunk = chunk if len(current_chunk) > 0: merged_chunks.append(current_chunk) # 导出分段音频 sample_rate = ConfigManager().get("sample_rate", 16000) for i, chunk in enumerate(merged_chunks): chunk = chunk.set_frame_rate(sample_rate).set_channels(1) chunk_path = os.path.join( temp_dir, f"{os.path.splitext(os.path.basename(input_path))[0]}_part{i + 1}.wav" ) chunk.export(chunk_path, format="wav") wav_paths.append(chunk_path) return wav_paths @staticmethod def _convert_single_audio(audio: AudioSegment, input_path: str, temp_dir: str) -> List[str]: """转换单个短音频文件""" sample_rate = ConfigManager().get("sample_rate", 16000) audio = audio.set_frame_rate(sample_rate).set_channels(1) wav_path = os.path.join(temp_dir, os.path.splitext(os.path.basename(input_path))[0] + ".wav") audio.export(wav_path, format="wav") return [wav_path] @staticmethod def extract_features_from_audio(y: np.ndarray, sr: int) -> Dict[str, float]: """从音频据中提取特征(流式处理优化)""" try: duration = librosa.get_duration(y=y, sr=sr) segment_length = 60 # 60秒分段 total_segments = max(1, int(np.ceil(duration / segment_length))) syllable_rates = [] volume_stabilities = [] total_samples = len(y) samples_per_segment = int(segment_length * sr) # 流式处理每个分段 for i in range(total_segments): start = i * samples_per_segment end = min((i + 1) * samples_per_segment, total_samples) y_segment = y[start:end] if len(y_segment) == 0: continue # 语速计算(使用VAD检测语音段) intervals = librosa.effects.split(y_segment, top_db=20) speech_samples = sum(end - start for start, end in intervals) speech_duration = speech_samples / sr if speech_duration > 0.1: syllable_rate = len(intervals) / speech_duration else: syllable_rate = 0 syllable_rates.append(syllable_rate) # 音量稳定性(使用RMS能量) rms = librosa.feature.rms(y=y_segment, frame_length=2048, hop_length=512)[0] if len(rms) > 0 and np.mean(rms) > 0: volume_stability = np.std(rms) / np.mean(rms) volume_stabilities.append(volume_stability) # 计算加权平均值(按时长加权) valid_syllable = [r for r in syllable_rates if r > 0] valid_volume = [v for v in volume_stabilities if v > 0] return { "duration": duration, "syllable_rate": round(np.mean(valid_syllable) if valid_syllable else 0, 2), "volume_stability": round(np.mean(valid_volume) if valid_volume else 0, 4) } except Exception as e: print(f"特征提取错误: {str(e)}") return {"duration": 0, "syllable_rate": 0, "volume_stability": 0} # ====================== 模型加载器(优化版) ====================== class ModelLoader: """加载和管理AI模型(使用RLock)""" asr_pipeline = None sentiment_model = None sentiment_tokenizer = None model_lock = RLock() # 使用RLock代替Lock models_loaded = False # 添加模型加载状态标志 @classmethod def load_models(cls): """加载所有模型""" config = ConfigManager() # 加载ASR模型 if not cls.asr_pipeline: with cls.model_lock: if not cls.asr_pipeline: # 双重检查锁定 cls.load_asr_model(config.get("model_paths")["asr"]) # 加载情感分析模型 if not cls.sentiment_model: with cls.model_lock: if not cls.sentiment_model: # 双重检查锁定 cls.load_sentiment_model(config.get("model_paths")["sentiment"]) cls.models_loaded = True @classmethod def reload_models(cls): """重新加载模型(配置变更后)""" with cls.model_lock: cls.asr_pipeline = None cls.sentiment_model = None cls.sentiment_tokenizer = None gc.collect() if torch.cuda.is_available(): torch.cuda.empty_cache() cls.load_models() @classmethod def load_asr_model(cls, model_path: str): """加载语音识别模型""" try: if not os.path.exists(model_path): raise FileNotFoundError(f"ASR模型路径不存在: {model_path}") asr_kwargs = {} if hasattr(torch, 'quantization'): asr_kwargs['quantize'] = 'int8' print("启用ASR模型量化") cls.asr_pipeline = pipeline( task=Tasks.auto_speech_recognition, model=model_path, device='cuda' if torch.cuda.is_available() else 'cpu', **asr_kwargs ) print("ASR模型加载完成") except Exception as e: print(f"加载ASR模型失败: {str(e)}") raise @classmethod def load_sentiment_model(cls, model_path: str): """加载情感分析模型""" try: if not os.path.exists(model_path): raise FileNotFoundError(f"情感分析模型路径不存在: {model_path}") cls.sentiment_model = AutoModelForSequenceClassification.from_pretrained(model_path) cls.sentiment_tokenizer = AutoTokenizer.from_pretrained(model_path) if torch.cuda.is_available(): cls.sentiment_model = cls.sentiment_model.cuda() print("情感分析模型加载完成") except Exception as e: print(f"加载情感分析模型失败: {str(e)}") raise # ====================== 核心分析线程(优化版) ====================== class AnalysisThread(QThread): progress_updated = pyqtSignal(int, str, str) result_ready = pyqtSignal(dict) finished_all = pyqtSignal() error_occurred = pyqtSignal(str, str) memory_warning = pyqtSignal() resource_cleanup = pyqtSignal() def __init__(self, audio_paths: List[str], temp_dir: str = "temp_wav"): super().__init__() self.audio_paths = audio_paths self.temp_dir = temp_dir self.is_running = True self.current_file = "" self.max_concurrent = min( ConfigManager().get("max_concurrent", 1), self.get_max_concurrent_tasks() ) self.resource_monitor = ResourceMonitor() self.semaphore = Semaphore(self.max_concurrent) os.makedirs(temp_dir, exist_ok=True) def run(self): try: if not ModelLoader.models_loaded: self.error_occurred.emit("模型未加载", "请等待模型加载完成后再开始分析") return self.progress_updated.emit(0, f"最大并行任务: {self.max_concurrent}", "") # 使用线程池并行处理 with concurrent.futures.ThreadPoolExecutor(max_workers=self.max_concurrent) as executor: # 创建任务 future_to_path = {} for path in self.audio_paths: if not self.is_running: break # 使用信号量控制并发 self.semaphore.acquire() batch_size = self.get_available_batch_size() future = executor.submit(self.analyze_audio, path, batch_size) future_to_path[future] = path future.add_done_callback(lambda f: self.semaphore.release()) # 处理完成的任务 for i, future in enumerate(concurrent.futures.as_completed(future_to_path)): if not self.is_running: break path = future_to_path[future] self.current_file = os.path.basename(path) # 内存检查 if self.check_memory_usage(): self.memory_warning.emit() self.is_running = False break try: result = future.result() if result: self.result_ready.emit(result) # 更新进度 progress = int((i + 1) / len(self.audio_paths) * 100) self.progress_updated.emit( progress, f"完成: {self.current_file} ({i + 1}/{len(self.audio_paths)})", self.current_file ) except Exception as e: result = { "file_name": self.current_file, "status": "error", "error": f"分析失败: {str(e)}" } self.result_ready.emit(result) # 分析完成后 if self.is_running: self.finished_all.emit() except Exception as e: self.error_occurred.emit("系统错误", str(e)) traceback.print_exc() finally: # 确保资源清理 self.resource_cleanup.emit() self.cleanup_resources() def analyze_audio(self, audio_path: str, batch_size: int) -> Dict: """分析单个音频文件(整合所有优化)""" result = { "file_name": os.path.basename(audio_path), "status": "processing" } wav_paths = [] try: # 1. 音频格式转换 wav_paths = AudioProcessor.convert_to_wav(audio_path, self.temp_dir) if not wav_paths: result["error"] = "格式转换失败(请检查ffmpeg是否安装)" result["status"] = "error" return result # 2. 提取音频特征(合并所有分段) audio_features = self._extract_audio_features(wav_paths) result.update(audio_features) result["duration_str"] = self._format_duration(audio_features["duration"]) # 3. 语音识别与处理(使用批处理优化) all_segments, full_text = self._process_asr_segments(wav_paths) # 4. 说话人区分(使用优化后的方法) agent_segments, customer_segments = self.identify_speakers(all_segments) # 5. 生成带说话人标签的文本 labeled_text = self._generate_labeled_text(all_segments, agent_segments, customer_segments) result["asr_text"] = labeled_text.strip() # 6. 文本分析(包含方言预处理) text_analysis = self._analyze_text(agent_segments, customer_segments, batch_size) result.update(text_analysis) # 7. 服务规范检查(使用方言适配的关键词) service_check = self._check_service_rules(agent_segments) result.update(service_check) # 8. 问题解决率(上下文关联) result["issue_resolved"] = self._check_issue_resolution(customer_segments, agent_segments) result["status"] = "success" except Exception as e: result["error"] = f"分析失败: {str(e)}" result["status"] = "error" finally: # 清理临时文件(使用优化后的清理方法) self._cleanup_temp_files(wav_paths) # 显式内存清理 self.cleanup_resources() return result def identify_speakers(self, segments: List[Dict]) -> Tuple[List[Dict], List[Dict]]: """区分客服与客户(增强版)""" if not segments: return [], [] # 1. 基于关键词的识别 agent_id = self._identify_by_keywords(segments) # 2. 基于说话模式的识别(如果关键词识别失败) if agent_id is None and len(segments) >= 4: agent_id = self._identify_by_speech_patterns(segments) # 3. 使用说话频率最高的为客服(最后手段) if agent_id is None: spk_counts = {} for seg in segments: spk_id = seg["spk_id"] spk_counts[spk_id] = spk_counts.get(spk_id, 0) + 1 agent_id = max(spk_counts, key=spk_counts.get) if spk_counts else None if agent_id is None: return [], [] # 使用集合存储agent的spk_id agent_spk_ids = {agent_id} return ( [seg for seg in segments if seg["spk_id"] in agent_spk_ids], [seg for seg in segments if seg["spk_id"] not in agent_spk_ids] ) def _identify_by_keywords(self, segments: List[Dict]) -> Optional[str]: """基于关键词识别客服""" opening_patterns = DialectConfig.get_compiled_opening() closing_patterns = DialectConfig.get_compiled_closing() # 策略1:在前3段中查找开场白关键词 for seg in segments[:3]: text = seg["text"] for pattern in opening_patterns: if pattern.search(text): return seg["spk_id"] # 策略2:在后3段中查找结束语关键词 for seg in reversed(segments[-3:] if len(segments) >= 3 else segments): text = seg["text"] for pattern in closing_patterns: if pattern.search(text): return seg["spk_id"] return None def _identify_by_speech_patterns(self, segments: List[Dict]) -> Optional[str]: """基于说话模式识别客服""" # 分析说话模式特征 speaker_features = {} for seg in segments: spk_id = seg["spk_id"] if spk_id not in speaker_features: speaker_features[spk_id] = { "total_duration": 0.0, "turn_count": 0, "question_count": 0 } features = speaker_features[spk_id] features["total_duration"] += (seg["end"] - seg["start"]) features["turn_count"] += 1 # 检测问题(包含疑问词) if any(q_word in seg["text"] for q_word in ["吗", "呢", "?", "?", "如何", "怎样"]): features["question_count"] += 1 # 客服通常说话时间更长、提问更多 if speaker_features: # 计算说话时间占比 max_duration = max(f["total_duration"] for f in speaker_features.values()) # 计算提问频率 question_rates = { spk_id: features["question_count"] / features["turn_count"] for spk_id, features in speaker_features.items() } # 综合评分 candidates = [] for spk_id, features in speaker_features.items(): score = ( 0.6 * (features["total_duration"] / max_duration) + 0.4 * question_rates[spk_id] ) candidates.append((spk_id, score)) # 返回得分最高的说话人 return max(candidates, key=lambda x: x[1])[0] return None def _analyze_text(self, agent_segments: List[Dict], customer_segments: List[Dict], batch_size: int) -> Dict: """文本情感分析(优化版:向量化批处理)""" def analyze_speaker(segments: List[Dict], speaker_type: str) -> Dict: if not segments: return { f"{speaker_type}_negative": 0.0, f"{speaker_type}_neutral": 1.0, f"{speaker_type}_positive": 0.0, f"{speaker_type}_emotions": "无" } # 方言预处理 - 使用优化的一次性替换 texts = [seg["text"] for seg in segments] processed_texts = DialectConfig.preprocess_text(texts) # 使用DataLoader进行批处理 with ModelLoader.model_lock: inputs = ModelLoader.sentiment_tokenizer( processed_texts, padding=True, truncation=True, max_length=128, return_tensors="pt" ) # 创建TensorDataset和DataLoader dataset = TensorDataset(inputs['input_ids'], inputs['attention_mask']) dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False) device = "cuda" if torch.cuda.is_available() else "cpu" sentiment_dist = [] emotions = [] # 批量处理 for batch in dataloader: input_ids, attention_mask = batch inputs = { 'input_ids': input_ids.to(device), 'attention_mask': attention_mask.to(device) } with torch.no_grad(): outputs = ModelLoader.sentiment_model(**inputs) batch_probs = torch.nn.functional.softmax(outputs.logits, dim=-1) sentiment_dist.append(batch_probs.cpu()) # 情绪识别(批量) emotion_keywords = ["愤怒", "生气", "鬼火", "不耐烦", "搞哪样嘛", "恼火", "背时"] for text in processed_texts: if any(kw in text for kw in emotion_keywords): if any(kw in text for kw in ["愤怒", "生气", "鬼火", "恼火"]): emotions.append("愤怒") elif any(kw in text for kw in ["不耐烦", "搞哪样嘛"]): emotions.append("不耐烦") elif "背时" in text: emotions.append("沮丧") # 合并结果 if sentiment_dist: all_probs = torch.cat(sentiment_dist, dim=0) avg_sentiment = torch.mean(all_probs, dim=0).tolist() else: avg_sentiment = [0.0, 1.0, 0.0] # 默认值 return { f"{speaker_type}_negative": round(avg_sentiment[0], 4), f"{speaker_type}_neutral": round(avg_sentiment[1], 4), f"{speaker_type}_positive": round(avg_sentiment[2], 4), f"{speaker_type}_emotions": ",".join(set(emotions)) if emotions else "无" } return { **analyze_speaker(agent_segments, "agent"), **analyze_speaker(customer_segments, "customer") } # ====================== 辅助方法 ====================== def get_available_batch_size(self) -> int: """根据GPU内存动态调整batch size(考虑并行)""" if not torch.cuda.is_available(): return 4 # CPU默认批次 total_mem = torch.cuda.get_device_properties(0).total_memory / (1024 ** 3) # GB per_task_mem = total_mem / self.max_concurrent # 修正批次大小逻辑:显存越少,批次越小 if per_task_mem < 2: return 2 elif per_task_mem < 4: return 4 else: return 8 def get_max_concurrent_tasks(self) -> int: """根据系统资源计算最大并行任务""" if torch.cuda.is_available(): total_mem = torch.cuda.get_device_properties(0).total_memory / (1024 ** 3) if total_mem < 6: return 1 elif total_mem < 12: return 2 else: return 3 else: # CPU模式下根据核心设置 return max(1, os.cpu_count() // 2) def check_memory_usage(self) -> bool: try: mem_percent = self.resource_monitor.memory_percent() return mem_percent.get("cpu", 0) > 85 or mem_percent.get("gpu", 0) > 85 except: return False def _extract_audio_features(self, wav_paths: List[str]) -> Dict[str, float]: """提取音频特征(合并所有分段)""" combined_y = np.array([], dtype=np.float32) sr = ConfigManager().get("sample_rate", 16000) for path in wav_paths: y, _ = librosa.load(path, sr=sr) combined_y = np.concatenate((combined_y, y)) return AudioProcessor.extract_features_from_audio(combined_y, sr) def _process_asr_segments(self, wav_paths: List[str]) -> Tuple[List[Dict], str]: """处理ASR分段(批处理优化)""" segments = [] full_text = "" # 分批处理(根据GPU内存动态调整批次大小) batch_size = min(4, len(wav_paths), self.get_available_batch_size()) for i in range(0, len(wav_paths), batch_size): if not self.is_running: break batch_paths = wav_paths[i:i + batch_size] try: # 批处理调用ASR模型 results = ModelLoader.asr_pipeline( batch_paths, hotwords=DialectConfig.get_asr_hotwords(), output_dir=None, batch_size=batch_size ) for result in results: for seg in result[0]["sentences"]: segments.append({ "start": seg["start"], "end": seg["end"], "text": seg["text"], "spk_id": seg.get("spk_id", "0") }) full_text += seg["text"] + " " except Exception as e: print(f"ASR批处理错误: {str(e)}") # 失败时回退到单文件处理 for path in batch_paths: try: result = ModelLoader.asr_pipeline( path, hotwords=DialectConfig.get_asr_hotwords(), output_dir=None ) for seg in result[0]["sentences"]: segments.append({ "start": seg["start"], "end": seg["end"], "text": seg["text"], "spk_id": seg.get("spk_id", "0") }) full_text += seg["text"] + " " except: continue return segments, full_text.strip() def _generate_labeled_text(self, all_segments: List[Dict], agent_segments: List[Dict], customer_segments: List[Dict]) -> str: """生成带说话人标签的文本""" agent_spk_id = agent_segments[0]["spk_id"] if agent_segments else None customer_spk_id = customer_segments[0]["spk_id"] if customer_segments else None labeled_text = [] for seg in all_segments: if seg["spk_id"] == agent_spk_id: speaker = "客服" elif seg["spk_id"] == customer_spk_id: speaker = "客户" else: speaker = f"说话人{seg['spk_id']}" labeled_text.append(f"[{speaker}]: {seg['text']}") return "\n".join(labeled_text) def _check_service_rules(self, agent_segments: List[Dict]) -> Dict: """检查服务规范""" forbidden_keywords = DialectConfig.get_combined_keywords()["forbidden"] found_forbidden = [] found_opening = False found_closing = False # 检查开场白(前3段) for seg in agent_segments[:3]: text = seg["text"] if any(kw in text for kw in DialectConfig.get_combined_keywords()["opening"]): found_opening = True break # 检查结束语(后3段) for seg in reversed(agent_segments[-3:] if len(agent_segments) >= 3 else agent_segments): text = seg["text"] if any(kw in text for kw in DialectConfig.get_combined_keywords()["closing"]): found_closing = True break # 检查禁用词 for seg in agent_segments: text = seg["text"] for kw in forbidden_keywords: if kw in text: found_forbidden.append(kw) break return { "opening_found": found_opening, "closing_found": found_closing, "forbidden_words": ", ".join(set(found_forbidden)) if found_forbidden else "无" } def _check_issue_resolution(self, customer_segments: List[Dict], agent_segments: List[Dict]) -> bool: """检查问题是否解决(增强版)""" if not customer_segments or not agent_segments: return False # 提取所有文本 customer_texts = [seg["text"] for seg in customer_segments] agent_texts = [seg["text"] for seg in agent_segments] full_conversation = " ".join(customer_texts + agent_texts) # 问题解决关键词 resolution_keywords = ["解决", "处理", "完成", "已", "好了", "可以了", "没问题"] thank_keywords = ["谢谢", "感谢", "多谢"] negative_keywords = ["没解决", "不行", "不对", "还是", "仍然", "再"] # 检查是否有负面词汇 has_negative = any(kw in full_conversation for kw in negative_keywords) if has_negative: return False # 检查客户最后是否表达感谢 last_customer_text = customer_segments[-1]["text"] if any(kw in last_customer_text for kw in thank_keywords): return True # 检查是否有解决关键词 if any(kw in full_conversation for kw in resolution_keywords): return True # 检查客服是否确认解决 for agent_text in reversed(agent_texts[-3:]): # 检查最后3段 if any(kw in agent_text for kw in resolution_keywords): return True return False def _cleanup_temp_files(self, paths: List[str]): """清理临时文件(增强兼容性)""" def safe_remove(path): """安全删除文件(多平台兼容)""" try: if os.path.exists(path): if sys.platform == 'win32': # Windows系统需要特殊处理 os.chmod(path, 0o777) # 确保有权限 for _ in range(5): # 最多尝试5次 try: os.remove(path) break except PermissionError: time.sleep(0.2) else: os.remove(path) except Exception: pass # 使用线程池并行删除 with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor: executor.map(safe_remove, paths) # 额外清理:删除超过1小时的临时文件 now = time.time() for file in os.listdir(self.temp_dir): file_path = os.path.join(self.temp_dir, file) if os.path.isfile(file_path): file_age = now - os.path.getmtime(file_path) if file_age > 3600: # 1小时 safe_remove(file_path) def _format_duration(self, seconds: float) -> str: """将秒转换为时分秒格式""" minutes, seconds = divmod(int(seconds), 60) hours, minutes = divmod(minutes, 60) return f"{hours:02d}:{minutes:02d}:{seconds:02d}" def cleanup_resources(self): """显式清理资源""" gc.collect() if torch.cuda.is_available(): torch.cuda.empty_cache() def stop(self): """停止分析""" self.is_running = False # ====================== 模型加载线程 ====================== class ModelLoadThread(QThread): progress_updated = pyqtSignal(int, str) finished = pyqtSignal(bool, str) def run(self): try: # 检查模型路径 config = ConfigManager().get("model_paths") if not os.path.exists(config["asr"]): self.finished.emit(False, "ASR模型路径不存在") return if not os.path.exists(config["sentiment"]): self.finished.emit(False, "情感分析模型路径不存在") return self.progress_updated.emit(20, "加载语音识别模型...") ModelLoader.load_asr_model(config["asr"]) self.progress_updated.emit(60, "加载情感分析模型...") ModelLoader.load_sentiment_model(config["sentiment"]) self.progress_updated.emit(100, "模型加载完成") self.finished.emit(True, "模型加载成功。建议:可通过设置界面修改模型路径") except Exception as e: self.finished.emit(False, f"模型加载失败: {str(e)}。建议:检查模型路径是否正确,或重新下载模型文件") # ====================== GUI主界面 ====================== class MainWindow(QMainWindow): def __init__(self): super().__init__() self.setWindowTitle("贵州方言客服质检系统") self.setGeometry(100, 100, 1200, 800) self.setup_ui() self.setup_menu() self.analysis_thread = None self.model_load_thread = None self.temp_dir = "temp_wav" os.makedirs(self.temp_dir, exist_ok=True) self.model_loaded = False def setup_ui(self): """设置用户界面""" # 主布局 main_widget = QWidget() main_layout = QVBoxLayout() main_widget.setLayout(main_layout) self.setCentralWidget(main_widget) # 工具栏 toolbar = QToolBar("主工具栏") toolbar.setIconSize(QSize(24, 24)) self.addToolBar(toolbar) # 添加文件按钮 add_file_action = QAction(QIcon("icons/add.png"), "添加文件", self) add_file_action.triggered.connect(self.add_files) toolbar.addAction(add_file_action) # 开始分析按钮 analyze_action = QAction(QIcon("icons/start.png"), "开始分析", self) analyze_action.triggered.connect(self.start_analysis) toolbar.addAction(analyze_action) # 停止按钮 stop_action = QAction(QIcon("icons/stop.png"), "停止分析", self) stop_action.triggered.connect(self.stop_analysis) toolbar.addAction(stop_action) # 设置按钮 settings_action = QAction(QIcon("icons/settings.png"), "设置", self) settings_action.triggered.connect(self.open_settings) toolbar.addAction(settings_action) # 分割布局 splitter = QSplitter(Qt.Horizontal) main_layout.addWidget(splitter) # 左侧文件列表 left_widget = QWidget() left_layout = QVBoxLayout() left_widget.setLayout(left_layout) file_list_label = QLabel("待分析文件列表") file_list_label.setFont(QFont("Arial", 12, QFont.Bold)) left_layout.addWidget(file_list_label) self.file_list = QListWidget() self.file_list.setSelectionMode(QListWidget.ExtendedSelection) left_layout.addWidget(self.file_list) # 右侧结果区域 right_widget = QWidget() right_layout = QVBoxLayout() right_widget.setLayout(right_layout) # 进度条 progress_label = QLabel("分析进度") progress_label.setFont(QFont("Arial", 12, QFont.Bold)) right_layout.addWidget(progress_label) self.progress_bar = QProgressBar() self.progress_bar.setRange(0, 100) self.progress_bar.setTextVisible(True) right_layout.addWidget(self.progress_bar) # 当前文件标签 self.current_file_label = QLabel("当前文件: 无") right_layout.addWidget(self.current_file_label) # 结果标签页 self.tab_widget = QTabWidget() right_layout.addWidget(self.tab_widget, 1) # 文本结果标签页 text_tab = QWidget() text_layout = QVBoxLayout() text_tab.setLayout(text_layout) self.text_result = QTextEdit() self.text_result.setReadOnly(True) text_layout.addWidget(self.text_result) self.tab_widget.addTab(text_tab, "文本结果") # 详细结果标签页 detail_tab = QWidget() detail_layout = QVBoxLayout() detail_tab.setLayout(detail_layout) self.result_table = QTableWidget() self.result_table.setColumnCount(10) self.result_table.setHorizontalHeaderLabels([ "文件名", "时长", "语速", "音量稳定性", "客服情感", "客户情感", "开场白", "结束语", "禁用词", "问题解决" ]) self.result_table.horizontalHeader().setSectionResizeMode(QHeaderView.Stretch) detail_layout.addWidget(self.result_table) self.tab_widget.addTab(detail_tab, "详细结果") # 添加左右部件到分割器 splitter.addWidget(left_widget) splitter.addWidget(right_widget) splitter.setSizes([300, 900]) def setup_menu(self): """设置菜单栏""" menu_bar = self.menuBar() # 文件菜单 file_menu = menu_bar.addMenu("文件") add_file_action = QAction("添加文件", self) add_file_action.triggered.connect(self.add_files) file_menu.addAction(add_file_action) export_action = QAction("导出结果", self) export_action.triggered.connect(self.export_results) file_menu.addAction(export_action) exit_action = QAction("退出", self) exit_action.triggered.connect(self.close) file_menu.addAction(exit_action) # 分析菜单 analysis_menu = menu_bar.addMenu("分析") start_action = QAction("开始分析", self) start_action.triggered.connect(self.start_analysis) analysis_menu.addAction(start_action) stop_action = QAction("停止分析", self) stop_action.triggered.connect(self.stop_analysis) analysis_menu.addAction(stop_action) # 设置菜单 settings_menu = menu_bar.addMenu("设置") config_action = QAction("系统配置", self) config_action.triggered.connect(self.open_settings) settings_menu.addAction(config_action) model_action = QAction("加载模型", self) model_action.triggered.connect(self.load_models) settings_menu.addAction(model_action) def add_files(self): """添加文件到分析列表""" files, _ = QFileDialog.getOpenFileNames( self, "选择音频文件", "", "音频文件 (*.mp3 *.wav *.amr *.m4a)" ) if files: for file in files: self.file_list.addItem(file) def start_analysis(self): """开始分析""" if self.file_list.count() == 0: QMessageBox.warning(self, "警告", "请先添加要分析的音频文件") return if not self.model_loaded: QMessageBox.warning(self, "警告", "模型未加载,请先加载模型") return # 获取文件路径 audio_paths = [self.file_list.item(i).text() for i in range(self.file_list.count())] # 清空结果 self.text_result.clear() self.result_table.setRowCount(0) # 创建分析线程 self.analysis_thread = AnalysisThread(audio_paths, self.temp_dir) # 连接信号 self.analysis_thread.progress_updated.connect(self.update_progress) self.analysis_thread.result_ready.connect(self.handle_result) self.analysis_thread.finished_all.connect(self.analysis_finished) self.analysis_thread.error_occurred.connect(self.show_error) self.analysis_thread.memory_warning.connect(self.handle_memory_warning) self.analysis_thread.resource_cleanup.connect(self.cleanup_resources) # 启动线程 self.analysis_thread.start() def stop_analysis(self): """停止分析""" if self.analysis_thread and self.analysis_thread.isRunning(): self.analysis_thread.stop() self.analysis_thread.wait() QMessageBox.information(self, "信息", "分析已停止") def load_models(self): """加载模型""" if self.model_load_thread and self.model_load_thread.isRunning(): return self.model_load_thread = ModelLoadThread() self.model_load_thread.progress_updated.connect( lambda value, msg: self.progress_bar.setValue(value) ) self.model_load_thread.finished.connect(self.handle_model_load_result) self.model_load_thread.start() def update_progress(self, progress: int, message: str, current_file: str): """更新进度""" self.progress_bar.setValue(progress) self.current_file_label.setText(f"当前文件: {current_file}") def handle_result(self, result: Dict): """处理分析结果""" # 添加到文本结果 self.text_result.append(f"文件: {result['file_name']}") self.text_result.append(f"状态: {result['status']}") if result["status"] == "success": self.text_result.append(f"时长: {result['duration_str']}") self.text_result.append(f"语速: {result['syllable_rate']} 音节/秒") self.text_result.append(f"音量稳定性: {result['volume_stability']}") self.text_result.append(f"客服情感: 负面({result['agent_negative']:.2%}) " f"中性({result['agent_neutral']:.2%}) " f"正面({result['agent_positive']:.2%})") self.text_result.append(f"客服情绪: {result['agent_emotions']}") self.text_result.append(f"客户情感: 负面({result['customer_negative']:.2%}) " f"中性({result['customer_neutral']:.2%}) " f"正面({result['customer_positive']:.2%})") self.text_result.append(f"客户情绪: {result['customer_emotions']}") self.text_result.append(f"开场白: {'有' if result['opening_found'] else '无'}") self.text_result.append(f"结束语: {'有' if result['closing_found'] else '无'}") self.text_result.append(f"禁用词: {result['forbidden_words']}") self.text_result.append(f"问题解决: {'是' if result['issue_resolved'] else '否'}") self.text_result.append("\n=== 对话文本 ===\n") self.text_result.append(result["asr_text"]) self.text_result.append("\n" + "=" * 50 + "\n") # 添加到结果表格 row = self.result_table.rowCount() self.result_table.insertRow(row) self.result_table.setItem(row, 0, QTableWidgetItem(result["file_name"])) self.result_table.setItem(row, 1, QTableWidgetItem(result["duration_str"])) self.result_table.setItem(row, 2, QTableWidgetItem(str(result["syllable_rate"]))) self.result_table.setItem(row, 3, QTableWidgetItem(str(result["volume_stability"]))) self.result_table.setItem(row, 4, QTableWidgetItem( f"负:{result['agent_negative']:.2f} 中:{result['agent_neutral']:.2f} 正:{result['agent_positive']:.2f}" )) self.result_table.setItem(row, 5, QTableWidgetItem( f"负:{result['customer_negative']:.2f} 中:{result['customer_neutral']:.2f} 正:{result['customer_positive']:.2f}" )) self.result_table.setItem(row, 6, QTableWidgetItem("是" if result["opening_found"] else "否")) self.result_table.setItem(row, 7, QTableWidgetItem("是" if result["closing_found"] else "否")) self.result_table.setItem(row, 8, QTableWidgetItem(result["forbidden_words"])) self.result_table.setItem(row, 9, QTableWidgetItem("是" if result["issue_resolved"] else "否")) # 根据结果着色 if not result["opening_found"]: self.result_table.item(row, 6).setBackground(QColor(255, 200, 200)) if not result["closing_found"]: self.result_table.item(row, 7).setBackground(QColor(255, 200, 200)) if result["forbidden_words"] != "无": self.result_table.item(row, 8).setBackground(QColor(255, 200, 200)) if not result["issue_resolved"]: self.result_table.item(row, 9).setBackground(QColor(255, 200, 200)) def analysis_finished(self): """分析完成""" QMessageBox.information(self, "完成", "所有音频分析完成") self.progress_bar.setValue(100) def show_error(self, title: str, message: str): """显示错误信息""" QMessageBox.critical(self, title, message) def handle_memory_warning(self): """处理内存警告""" QMessageBox.warning(self, "内存警告", "内存使用过高,分析已停止。请关闭其他应用程序后重试") def cleanup_resources(self): """清理资源""" gc.collect() if torch.cuda.is_available(): torch.cuda.empty_cache() def handle_model_load_result(self, success: bool, message: str): """处理模型加载结果""" if success: self.model_loaded = True QMessageBox.information(self, "成功", message) else: QMessageBox.critical(self, "错误", message) def open_settings(self): """打开设置对话框""" settings_dialog = QDialog(self) settings_dialog.setWindowTitle("系统设置") settings_dialog.setFixedSize(500, 400) layout = QVBoxLayout() # ASR模型路径 asr_layout = QHBoxLayout() asr_label = QLabel("ASR模型路径:") asr_line = QLineEdit(ConfigManager().get("model_paths")["asr"]) asr_browse = QPushButton("浏览...") def browse_asr(): path = QFileDialog.getExistingDirectory(self, "选择ASR模型目录") if path: asr_line.setText(path) asr_browse.clicked.connect(browse_asr) asr_layout.addWidget(asr_label) asr_layout.addWidget(asr_line) asr_layout.addWidget(asr_browse) layout.addLayout(asr_layout) # 情感分析模型路径 sentiment_layout = QHBoxLayout() sentiment_label = QLabel("情感模型路径:") sentiment_line = QLineEdit(ConfigManager().get("model_paths")["sentiment"]) sentiment_browse = QPushButton("浏览...") def browse_sentiment(): path = QFileDialog.getExistingDirectory(self, "选择情感模型目录") if path: sentiment_line.setText(path) sentiment_browse.clicked.connect(browse_sentiment) sentiment_layout.addWidget(sentiment_label) sentiment_layout.addWidget(sentiment_line) sentiment_layout.addWidget(sentiment_browse) layout.addLayout(sentiment_layout) # 并发设置 concurrent_layout = QHBoxLayout() concurrent_label = QLabel("最大并发任务:") concurrent_spin = QSpinBox() concurrent_spin.setRange(1, 8) concurrent_spin.setValue(ConfigManager().get("max_concurrent", 1)) concurrent_layout.addWidget(concurrent_label) concurrent_layout.addWidget(concurrent_spin) layout.addLayout(concurrent_layout) # 方言设置 dialect_layout = QHBoxLayout() dialect_label = QLabel("方言设置:") dialect_combo = QComboBox() dialect_combo.addItems(["标准普通话", "贵州方言"]) dialect_combo.setCurrentIndex(1 if ConfigManager().get("dialect_config") == "guizhou" else 0) dialect_layout.addWidget(dialect_label) dialect_layout.addWidget(dialect_combo) layout.addLayout(dialect_layout) # 音频时长限制 duration_layout = QHBoxLayout() duration_label = QLabel("最大音频时长(秒):") duration_spin = QSpinBox() duration_spin.setRange(60, 86400) # 1分钟到24小时 duration_spin.setValue(ConfigManager().get("max_audio_duration", 3600)) duration_layout.addWidget(duration_label) duration_layout.addWidget(duration_spin) layout.addLayout(duration_layout) # 按钮 button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel) button_box.accepted.connect(settings_dialog.accept) button_box.rejected.connect(settings_dialog.reject) layout.addWidget(button_box) settings_dialog.setLayout(layout) if settings_dialog.exec_() == QDialog.Accepted: # 保存设置 ConfigManager().set("model_paths", { "asr": asr_line.text(), "sentiment": sentiment_line.text() }) ConfigManager().set("max_concurrent", concurrent_spin.value()) ConfigManager().set("dialect_config", "guizhou" if dialect_combo.currentIndex() == 1 else "standard") ConfigManager().set("max_audio_duration", duration_spin.value()) # 重新加载模型 ModelLoader.reload_models() def export_results(self): """导出结果""" if self.result_table.rowCount() == 0: QMessageBox.warning(self, "警告", "没有可导出的结果") return path, _ = QFileDialog.getSaveFileName( self, "保存结果", "", "CSV文件 (*.csv)" ) if path: try: with open(path, "w", encoding="utf-8") as f: # 写入表头 headers = [] for col in range(self.result_table.columnCount()): headers.append(self.result_table.horizontalHeaderItem(col).text()) f.write(",".join(headers) + "\n") # 写入据 for row in range(self.result_table.rowCount()): row_data = [] for col in range(self.result_table.columnCount()): item = self.result_table.item(row, col) row_data.append(item.text() if item else "") f.write(",".join(row_data) + "\n") QMessageBox.information(self, "成功", f"结果已导出到: {path}") except Exception as e: QMessageBox.critical(self, "错误", f"导出失败: {str(e)}") def closeEvent(self, event): """关闭事件处理""" if self.analysis_thread and self.analysis_thread.isRunning(): self.analysis_thread.stop() self.analysis_thread.wait() # 清理临时目录(增强兼容性) try: for file in os.listdir(self.temp_dir): file_path = os.path.join(self.temp_dir, file) if os.path.isfile(file_path): # Windows系统可能需要多次尝试 for _ in range(3): try: os.remove(file_path) break except PermissionError: time.sleep(0.1) os.rmdir(self.temp_dir) except: pass event.accept() # ====================== 程序入口 ====================== if __name__ == "__main__": torch.set_num_threads(4) # 限制CPU线程 app = QApplication(sys.argv) # 设置应用样式 app.setStyle('Fusion') window = MainWindow() window.show() sys.exit(app.exec_())
最新发布
08-05
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值