药食同源类淘宝直播带货违法监测预警数据
收藏资源简介：
对采集的淘宝平台带货品类为药食同源类的达人直播视频内容进行转译分析，对达人口播语言内容进行处理、分析，根据达人在直播过程中对预先设置的违规敏感词（比如：彻底根治、绝对安全、无任何副作用、快速见效、立竿见影、包治百病、100%纯天然、预防疾病、抗癌、抗衰老、政府推荐等）违反的次数和频率，依据触发条件规则提出警告或处理。为服务辖区市场监督局管理区域内规范企业淘宝直播行为，提供数据支持。将采集完成的直播视频进行进行预处理，第一步：基于原始视频文件，以最大10分钟单位对原始视频进行切片。第二步：对于已完成的切片视频，进行视频内容转语音操作。第三步：对于已完成视频转语音操作的切片，进行语音转文本操作。第四步：使用OCR技术对原始视频中抓取的图片进行文字提取操作。第五步：将所得到的文字内容与违法预警关键词库进行匹配。最终运用多标准决策分析模型，对主播在直播过程中出现的违规语句进行分析计算，得出违法预警值和是否预警判断。 违法预警值=（违法预警单关键词命中次数*0.25）+（违法预警组合关键词命中次数* 0.3）+（图片识别命中预警组合关键词个数*0.35）+（直播间近一个月历史违规记录数*0.1） 通过公式计算出最终违法预警值，违法预警值 ≤1 时，不触发预警提示，违法预警值 ＞1 时触发违法预警提示。
This dataset performs transcription and analysis on live stream video content from Taobao platform influencers who promote medicinal and edible products. The spoken content of the influencers will be processed and analyzed, and warnings or penalties will be issued in line with the frequency and count of violations against pre-configured sensitive prohibited keywords (e.g., "complete cure", "absolutely safe", "no side effects whatsoever", "quick results", "immediate effects", "cure all diseases", "100% natural", "disease prevention", "anti-cancer", "anti-aging", "government recommendation") during the live broadcast. This work aims to provide data support for local Market Supervision Administrations to standardize the live streaming behaviors of enterprises under their jurisdiction on Taobao. The collected live stream videos undergo the following preprocessing steps: 1. Slice the original video files into segments with a maximum duration of 10 minutes. 2. Convert the sliced video content to audio via video-to-speech conversion. 3. Conduct speech-to-text conversion on the audio files extracted from the sliced videos. 4. Extract text from images captured from the original videos using Optical Character Recognition (OCR) technology. 5. Match the collected text content against the prohibited warning keyword database. Finally, a multi-criteria decision analysis (MCDA) model is employed to analyze and calculate the violating statements made by the live streamer during the broadcast, to obtain the Violation Warning Score and make a warning determination. The Violation Warning Score is calculated using the following formula: Violation Warning Score = (Number of single prohibited keyword hits × 0.25) + (Number of combined prohibited keyword hits × 0.3) + (Number of combined warning keyword hits detected via image recognition × 0.35) + (Number of historical violation records of the live stream room in the past month × 0.1) The final Violation Warning Score is calculated via the aforementioned formula. No warning prompt will be triggered when the score is ≤ 1, while a violation warning prompt will be triggered when the score > 1.
