电动自行车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电动自行车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：能互认协议，解限速，曾容量，可拆卸电池，续航里程200公里，可进电梯，可换电池，超强大电机等）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 conducts transcription and analysis on livestream video content of influencers promoting electric bicycles on the JD.com platform, and processes and analyzes the spoken content of the influencers. Warnings or penalties will be issued based on the frequency and count of violations of pre-set sensitive violation keywords (e.g., mutual recognition agreement, speed limit unlocking, capacity increase, detachable battery, 200-kilometer cruising range, elevator-accessible, replaceable battery, ultra-high-power motor, etc.) during the livestream, providing data support for standardizing JD.com livestream behaviors within the jurisdiction of the Zhuji City Market Supervision Bureau.

The collected livestream videos are preprocessed via the following steps:
1. Slice the original video files into segments with a maximum duration of 10 minutes.
2. Convert the sliced videos into audio files.
3. Transcribe the audio content of the sliced videos into text.
4. Extract text from images captured from the original videos using OCR technology.
5. Match the obtained text content against the violation warning keyword database.

Finally, a multi-criteria decision analysis model is applied to analyze and calculate the violation statements made by the streamer during the livestream, to derive the violation warning value and the judgment of whether to trigger a warning.

The violation warning value is calculated using the following formula:
Violation Warning Value = (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 livestream room in the past month * 0.1)

If the calculated violation warning value ≤ 1, no warning prompt will be triggered; if the value > 1, a violation warning prompt will be triggered.

搜集汇总

数据集介绍

特点

该数据集用于监测京东平台上电动自行车类直播带货中的违法行为，通过分析直播内容中的违规关键词，计算违法预警值，为市场监督提供数据支持。数据集包含1879条记录，每季度更新一次，适用于公共管理和社会保障领域。