农产品类京东直播带货违法监测预警数据

对采集的京东平台带货品类为农产品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：100%纯天然，绝对无农药残留，特效治疗，绿色有机，预防疾病，抗癌，抗衰老，政府推荐，无激素，快速生长剂，口感绝佳，品质卓越等）违反的次数和频率，依据触发条件规则提出警告或处理。为诸暨市市场监督局管理区域内规范企业京东直播行为，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 is constructed for the analysis of influencer live streaming videos of promoted agricultural product categories on the JD.com platform. The work involves processing and analyzing the oral language content of the influencers, and issuing warnings or taking regulatory actions in accordance with the preset triggering rules based on the count and frequency of violations of pre-defined sensitive violation-related keywords during the live streaming. The pre-defined sensitive violation-related keywords include but are not limited to: "100% pure natural, absolutely no pesticide residue, special effect treatment, green organic, disease prevention, anti-cancer, anti-aging, government recommendation, hormone-free, rapid growth agent, excellent taste, superior quality, etc.". This dataset provides data support for the Zhuji Municipal Market Supervision Administration to standardize the live streaming behaviors of enterprises within its jurisdiction.

The collected live streaming videos undergo the following five preprocessing steps:
1. Slice the original video files into segments with a maximum duration of 10 minutes per segment;
2. Convert each sliced video segment from video to speech;
3. Transcribe the speech content of the sliced video segments into text;
4. Extract text from images captured in the original videos using Optical Character Recognition (OCR) technology;
5. Match the obtained text content (from speech transcription and image OCR) with the pre-built violation warning keyword database.

Subsequently, a multi-criteria decision analysis model is employed to analyze and calculate the violation statements made by the live stream host during the broadcast, to derive the final violation warning score and the corresponding warning judgment result.
The formula for calculating the violation warning score is as follows:
Violation Warning Score = (Number of hits for single violation warning keywords * 0.25) + (Number of hits for combined violation warning keywords * 0.3) + (Number of combined violation warning keywords identified via image recognition * 0.35) + (Number of historical violation records of the live stream room in the past month * 0.1)
The warning triggering rules are: if the calculated Violation Warning Score is ≤ 1, no warning prompt will be triggered; if the Violation Warning Score is > 1, a violation warning prompt will be issued.

搜集汇总

数据集介绍

特点

该数据集主要用于监测京东平台上农产品类直播带货中的违法行为，包含1734条数据，每季度更新。通过分析直播内容中的违规敏感词，结合算法规则计算违法预警值，为市场监督局提供数据支持。