奶粉类小红书直播带货违法监测预警数据

对采集的小红书平台带货品类为奶粉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：母乳、增加抵抗力、促进脑部发育、益智、预防感冒、治疗、强化体质、增强免疫力等）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小红书直播行为，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。

We conduct transcription and analysis on the collected live streaming video content of influencers promoting milk powder products on the Xiaohongshu platform, and process and analyze the oral language content of the influencers. Based on the frequency and count of the use of pre-set sensitive violation keywords (e.g., breast milk, boost immunity, promote brain development, improve intelligence, prevent colds, treat, strengthen physique, enhance immunity, etc.) by the influencers during live streaming, we issue warnings or take corresponding actions in accordance with the trigger condition rules. This dataset provides data support for market supervision bureaus within their respective jurisdictions to standardize the live streaming behaviors of enterprises on the Xiaohongshu platform.

The collected live streaming videos undergo the following preprocessing steps:
Step 1: Slice the original raw video files into segments with a maximum duration of 10 minutes.
Step 2: Perform video-to-speech conversion on the sliced videos.
Step 3: Convert the generated speech content from the previous step into text.
Step 4: Extract text from images captured from the original videos using OCR technology.
Step 5: Match the obtained text content against the violation warning keyword database.

Finally, apply a multi-criteria decision analysis model to analyze and calculate the violation statements made by the influencers during live streaming, and derive the violation warning score and the judgment of whether to trigger a warning.

The Violation Warning Score is calculated using the following formula:
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 warning keywords identified via image recognition * 0.35) + (Number of historical violation records of the live streaming room in the past month * 0.1)

Based on the formula, the final Violation Warning Score is calculated. If the score is ≤ 1, no warning prompt is triggered; if the score is > 1, a violation warning prompt is triggered.

搜集汇总

数据集介绍

特点

该数据集是针对小红书平台奶粉类直播带货的违法监测预警数据，包含1200条记录，每季度更新。通过视频转译、语音转文本和OCR技术，结合违法预警关键词库和多标准决策分析模型，监测直播中的违规语句，为市场监督局提供数据支持。