酒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酒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：不宿醉，喝不醉，不上头，醒酒快，温肾，除积冷，消除紧张、消除焦虑，增加体力，改善疲劳感，再喝一杯，千杯不醉等）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。

This dataset is developed for transcription and analysis of livestream videos of influencers promoting alcoholic products on the Xiaohongshu platform. It processes and analyzes the oral speech content of the influencers, and generates warnings or corresponding actions based on the number and frequency of violations of pre-set sensitive violation keywords (including but not limited to: no hangover, not get drunk, no head rush, quick sober-up, nourish kidneys, dispel accumulated cold, relieve stress, alleviate anxiety, enhance physical stamina, relieve fatigue, have another drink, never get drunk no matter how much one drinks) by the influencers during their livestreams, in accordance with predefined trigger rules. This dataset provides data support for standardizing the livestream behaviors of enterprises on Xiaohongshu within the regulatory jurisdiction of Zhuji Municipal Market Supervision Administration.

The collected livestream videos undergo the following preprocessing workflows:
1. Slice the original video files into segments with a maximum duration of 10 minutes.
2. Convert the content of each sliced video into audio via video-to-audio conversion.
3. Convert the extracted audio from the sliced videos into text via speech-to-text conversion.
4. Extract text from images captured in the original videos using Optical Character Recognition (OCR) technology.
5. Match all collected text content against the pre-built illegal warning keyword database.

Subsequently, a multi-criteria decision analysis (MCDA) model is applied to analyze and calculate the violating statements made by the livestream host during the broadcast, so as to derive the illegal warning score and the judgment on whether to trigger a warning prompt.
The illegal warning score is calculated using the following formula:
Illegal Warning Score = (Number of hits for single illegal warning keywords × 0.25) + (Number of hits for combined illegal warning keywords × 0.3) + (Number of combined warning keywords identified via image recognition × 0.35) + (Number of historical violation records of the livestream room in the past 30 days × 0.1)

The final illegal warning score is computed via the above formula. No warning prompt will be triggered if the score ≤ 1, while an illegal warning prompt will be activated if the score > 1.

原始信息汇总

数据集概述

数据集名称

浙江省数据知识产权登记平台

数据集描述

浙江省数据知识产权登记平台是由浙江知识产权研究与服务中心推出的区块链数据知识产权登记系统。该平台支持数据知识产权登记、知识产权证书申请、原创作品登记确权、维权服务申请、维权证据出具、知识产权转让等多种场景。通过区块链技术，平台从登记、确权、维权、交易等多个维度为创作者的知识产权提供保护。

关键词

区块链、知识产权、数据存证、知识产权存证、知识产权研究与服务中心、数据知识产权登记、浙江省数据知识产权登记平台