摘要：【中文】本申请公开了一种违规视频检测方法、装置以及存储介质。其中，违规视频检测方法包括：获取待检测视频；以及对待检测视频执行以下的检测操作，确定待检测视频是否为违规视频：对待检测视频的关键帧中的图像进行违规内容的检测；和/或对待检测视频中的音频信息、标题信息、描述信息和/或从待检测视频关键帧中提取的文本信息进行违规内容的检测。 【EN】The application discloses a violation video detection method and device and a storage medium. The illegal video detection method comprises the following steps: acquiring a video to be detected; and executing the following detection operations on the video to be detected to determine whether the video to be detected is an illegal video: detecting illegal contents of images in a key frame of a video to be detected; and/or detecting the illegal content of the audio information, the title information, the description information and/or the text information extracted from the key frame of the video to be detected in the video to be detected.

摘要：【中文】本申请公开了一种用于舆情分析的文本信息处理的方法、装置以及存储介质。其中，一种用于舆情分析的文本信息处理的方法包括：获取第一文本信息集合，其中第一文本信息集合中包括待筛选的多个文本信息；根据预先设置的文本分类模块，从第一文本信息集合中抽取属于指定舆情类别的第二文本信息集合；根据预先设置的专题预警模块，从第一文本信息集合中抽取属于指定舆情专题的第三文本信息集合；根据预先设置的事件跟踪模块，从第一文本信息集合中抽取与指定事件相关联的第四文本信息集合；以及根据预先设置的多模态融合模型对第二文本信息集合、第三文本信息集合以及第四文本信息集合进行融合，确定用于舆情分析的第五文本信息集合。 【EN】The application discloses a method and a device for processing text information for public opinion analysis and a storage medium. The method for processing the text information for public opinion analysis comprises the following steps: acquiring a first text information set, wherein the first text information set comprises a plurality of text information to be screened; extracting a second text information set belonging to a specified public opinion category from the first text information set according to a preset text classification module; extracting a third text information set belonging to a specified public opinion topic from the first text information set according to a preset topic early warning module; extracting a fourth text information set associated with the specified event from the first text information set according to a preset event tracking module; and fusing the second text information set, the third text information set and the fourth text information set according to a preset multi-mode fusion model to determine a fifth text information set for public opinion analysis.

摘要：【中文】本申请公开了一种信息数据的审核方法、装置和存储介质，其中方法包括：获取待审核信息数据，根据已构建的数据标注预估模型判断所述待审核信息数据是否为需要人工纠偏的偏差信息数据，其中，所述数据标注预估模型是通过有监督机器学习模型训练得出，以及根据预设规则确定所述偏差信息数据的纠偏优先级。通过本实施例，提高了信息数据在审核时的工作效率和正确率。 【EN】The application discloses a method, a device and a storage medium for auditing information data, wherein the method comprises the following steps: acquiring information data to be audited, judging whether the information data to be audited is deviation information data needing manual deviation rectification according to a constructed data labeling estimation model, wherein the data labeling estimation model is obtained through supervised machine learning model training, and determining the deviation rectification priority of the deviation information data according to a preset rule. Through the embodiment, the working efficiency and the accuracy of the information data during auditing are improved.