[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tools-index":3},{"tools":4},[5,11,16,21,26,31,36,41,46,51,56,61,66,71,76,81,86,91,96,101,106,111,116,121,126,131,135,139,143,147,151,155,159,163,167,171,175,179,182,187,191,195,199,203,207,211,215,219,223,227,231,235,239,243,247,251,255,259,263,267,271,275,279,283,287,291,295,300,304,308,312,316,320,324,330,334,338,342,346],{"type":6,"name":7,"category":8,"index":9,"description":10},"clear-text","文本清洗","标准文本处理",1,"按行清洗文本：移除停用词、处理标点、剥离网页噪声，并可按字数窗口分段供后续建模。",{"type":12,"name":13,"category":8,"index":14,"description":15},"evaluate-text-quality","文本质量评估器",2,"从六个维度给文本做一次全面体检，判断它能不能直接用于主题建模、聚类、实体识别等下游任务。",{"type":17,"name":18,"category":8,"index":19,"description":20},"text-normalize","中文文本规范化",3,"把繁简、标点、全半角写法不一的中文统一成出版级样式，并可整篇转写为拼音。",{"type":22,"name":23,"category":8,"index":24,"description":25},"pos-tagging","词性标注",4,"统计名词动词分布、转移矩阵、基准语料对比，看清文本的语法骨架。",{"type":27,"name":28,"category":8,"index":29,"description":30},"extract-keywords","关键词抽取",5,"提取文本核心关键词,TF-IDF 看稀有度、TextRank 看关联强度，交叉对比看清文本核心语义。",{"type":32,"name":33,"category":8,"index":34,"description":35},"high-frequency-words","高频词提取",6,"统计词频和固定词组，包括 2–4 个词组成的搭配，自动归纳焦点说法与多篇间的共性。",{"type":37,"name":38,"category":8,"index":39,"description":40},"entity-recognition","命名实体识别",7,"自动识别文本里的人名地名机构时间，生成可核对实体清单。",{"type":42,"name":43,"category":8,"index":44,"description":45},"style-fingerprint","文体风格指纹",8,"把写作习惯拆成可对比的统计指标，定位风格差异来源。多篇文本可对比风格上是否相近、相近到什么程度。",{"type":47,"name":48,"category":8,"index":49,"description":50},"word-co-occurrence","词语共现分析",9,"找出文本里经常成对出现的词，并用多项统计指标判断这种搭配是否真的稳定。",{"type":52,"name":53,"category":8,"index":54,"description":55},"dependency","依存句法分析",10,"可视化每句话的主干、修饰与依赖关系，并给整段文本打出句法复杂度评分。",{"type":57,"name":58,"category":8,"index":59,"description":60},"text-matrix","文本矩阵分析",11,"找出多份文本里最重要的核心词，用矩阵和网络图展示词与词之间的关联强度。",{"type":62,"name":63,"category":8,"index":64,"description":65},"sentiment-analysis","传统情感分析",12,"识别文本情感倾向，支持自建积极词和消极词。",{"type":67,"name":68,"category":8,"index":69,"description":70},"deep-senti","DeepSentiV2深度学习情感分析",13,"使用深度学习模型判断情感倾向，支持电商、学术、金融等 7 种行业语境，输出关键词和置信度。",{"type":72,"name":73,"category":8,"index":74,"description":75},"deep-keyword","DeepKeyword 深度学习模型关键词发现",14,"综合原文命中、位置与多路证据，为长文筛选核心短语。",{"type":77,"name":78,"category":8,"index":79,"description":80},"simple-cluster","简单文本聚类",15,"按文本相似性自动分组，并用质量指标和原文检查主题边界。",{"type":82,"name":83,"category":8,"index":84,"description":85},"kwic-concordance","KWIC关键词上下文索引",16,"对齐关键词左右语境，比较命中密度、位置分布与同行共现。",{"type":87,"name":88,"category":8,"index":89,"description":90},"keyword-hit-stats","KWIC关键词命中矩阵",17,"按段落统计多组关键词命中、覆盖与共现，定位主题集中分布。",{"type":92,"name":93,"category":8,"index":94,"description":95},"doc-term-matrix","文档词项矩阵",18,"逐文档统计高频词，用矩阵比较用词分布与相似度",{"type":97,"name":98,"category":8,"index":99,"description":100},"punctuation-correct","标点纠正",19,"统一并修正中文文本中的已有标点。",{"type":102,"name":103,"category":8,"index":104,"description":105},"text-readability","文本可读性分析",20,"估算中英文本阅读门槛，比较近似阅读年级并定位难句。",{"type":107,"name":108,"category":8,"index":109,"description":110},"similar-sentence-finder","相似句查找",21,"按语义找出含义相近的句段对和聚类，减少同类表达的漏检。",{"type":112,"name":113,"category":8,"index":114,"description":115},"vocab-level","词汇等级评估",22,"对照官方词表逐词估等级并筛超纲，可作新词发现候选与后续主题、关键词任务的自定义词表。",{"type":117,"name":118,"category":8,"index":119,"description":120},"extractive-summary","抽取式摘要（TextRank \u002F LexRank 双引擎）",23,"用 TextRank 与 LexRank 双算法从原文挑出最关键的几句拼成摘要，不改写、可溯源。",{"type":122,"name":123,"category":8,"index":124,"description":125},"pii-redaction","敏感信息脱敏",24,"批量识别并脱敏文本里的身份证、手机号、银行卡等结构化个人信息，占位 \u002F 掩码 \u002F 删除三选一。",{"type":127,"name":128,"category":129,"index":9,"description":130},"markitdown-export","文档转写导出TXT","辅助工具","将 Word\u002FPDF\u002FPPT\u002FExcel 等文档统一转写为 Markdown 和纯文本，同时输出多种格式。",{"type":132,"name":133,"category":129,"index":14,"description":134},"audio-to-text","语音转文字","把录音、会议等语音转成文字，支持多语言，适合记录与字幕。",{"type":136,"name":137,"category":129,"index":19,"description":138},"json-to-csv","JSON 转 CSV","把 JSON 数据转成表格，支持嵌套结构，便于在 Excel 等中分析。",{"type":140,"name":141,"category":129,"index":29,"description":142},"word-to-pdf","Word\u002FExcel\u002FPPT 转 PDF","Office 文档转 PDF，保持排版，支持批量。",{"type":144,"name":145,"category":129,"index":39,"description":146},"excel-to-csv","EXCEL 转 CSV","把 Excel 表另存为 CSV，支持多表、自定义分隔符。",{"type":148,"name":149,"category":129,"index":44,"description":150},"csv-to-excel","CSV 转 EXCEL","把 CSV 转成 Excel，自动识别分隔符与编码。",{"type":152,"name":153,"category":129,"index":49,"description":154},"txt-to-csv","TXT 转 CSV","按分隔符把文本转成表格，便于导入与分析。",{"type":156,"name":157,"category":129,"index":54,"description":158},"ocr","智能OCR","把图片或 PDF 里的文字、公式、表格识别出来，导出为可编辑文档。",{"type":160,"name":161,"category":129,"index":59,"description":162},"word-to-csv","WORD 转 CSV 文件","把 Word 里的表格转成 CSV 文件。",{"type":164,"name":165,"category":129,"index":64,"description":166},"word-to-txt","Word\u002FPDF\u002FExcel\u002FCSV 转 TXT","从各类文档中提取纯文字，去掉格式，便于做文本分析。",{"type":168,"name":169,"category":129,"index":84,"description":170},"extract-audio-from-video","视频提取音频","从视频中导出音频轨道，支持多格式与音质选择。",{"type":172,"name":173,"category":129,"index":89,"description":174},"resize-image","批量转换图片分辨率","",{"type":176,"name":177,"category":129,"index":94,"description":178},"pdf-split","PDF 页面分割","按页码范围从 PDF 中截取页面，另存为新文档。",{"type":180,"name":181,"category":129,"index":104,"description":174},"image-prompt-reverse","提示词反推",{"type":183,"name":184,"category":185,"index":9,"description":186},"deep-senti-v3","高级情感分析","高级文本处理","逐句解释文本为何偏正负面，给出证据词和推理逻辑。",{"type":188,"name":189,"category":185,"index":9,"description":190},"aigc-detection","AIGC内容检测","不只给整体参考分，还定位逐段逐句风险，并生成可复用改稿提示。",{"type":192,"name":193,"category":185,"index":14,"description":194},"knowledge-extraction","知识图谱","从文本中自动抽取人物、机构、概念及其关系，生成可交互的知识图谱。",{"type":196,"name":197,"category":185,"index":19,"description":198},"stopword-mining","停用词挖掘","自动整理停用词候选，省去反复手写、增补停用词表的精力。",{"type":200,"name":201,"category":185,"index":24,"description":202},"sentence-punctuator","文本结构还原器","把无标点的连续中文恢复成带句读的句子，并给出句长诊断与逐句列表，便于后续文本挖掘。",{"type":204,"name":205,"category":185,"index":24,"description":206},"bertopic","BERTopic 主题聚类","基于语义聚类重建文本主题结构，自动生成抽象标签并解析主题间距离与层级关系。",{"type":208,"name":209,"category":185,"index":29,"description":210},"lda","LDA 主题模型","从文本中发现若干主题，展示主题词、文档分布及主题之间的关系。",{"type":212,"name":213,"category":185,"index":34,"description":214},"vad-senti","VAD 三维情感分析","分析文本情感，除积极\u002F中性\u002F消极外，输出效价（V）、唤醒度（A）、支配度（D）三个维度。",{"type":216,"name":217,"category":185,"index":39,"description":218},"pca","PCA 主成分分析","把高维文本特征压缩成少数主成分，帮助看清差异主要来自哪些方向。",{"type":220,"name":221,"category":185,"index":44,"description":222},"text-cluster","高级文本聚类","对大批量文本做语义聚类，自动发现主题与结构。",{"type":224,"name":225,"category":185,"index":49,"description":226},"lsa","LSA 潜在语义分析","用LSA把分散文本压成几个语义方向，看清主题边界、重叠关系和代表性段落。",{"type":228,"name":229,"category":185,"index":54,"description":230},"find-new-words","智能发现新词","找出常规分词容易切碎的术语、专名和流行表达，补齐领域词表。",{"type":232,"name":233,"category":185,"index":59,"description":234},"lda-perplexity","LDA困惑度计算","对LDA在多个候选主题数下做多指标对照，给出更稳妥的主题数建议。",{"type":236,"name":237,"category":185,"index":64,"description":238},"sentence-info","信息价值评估","逐句评估信息量与表达效率，筛出真正值得保留和引用的内容。",{"type":240,"name":241,"category":185,"index":69,"description":242},"similarity-dedupe-radar","文本相似度去重雷达","对成批文档做相似度分析与聚类，给出去重建议与可视化（矩阵、雷达等）。",{"type":244,"name":245,"category":185,"index":74,"description":246},"collocation","词语搭配强度分析","用关联强度指标筛出材料里稳定的词搭配，可指定中心词专门查它周围的典型搭配伙伴。",{"type":248,"name":249,"category":185,"index":74,"description":250},"duplicate-content-merge","重复内容合并","基于语义相似度将意思接近的句子或段落归组，保留代表句并合并重复表达。",{"type":252,"name":253,"category":185,"index":79,"description":254},"lexical-diversity","词汇多样性分析","标量化文本用词丰富度，并定位哪一段开始变得\"车轱辘话\"。",{"type":256,"name":257,"category":185,"index":79,"description":258},"pca-dimension-reduction","PCA 主成分降维","对表格数值列做主成分分析，输出方差解释、载荷、得分和二维投影散点图。",{"type":260,"name":261,"category":185,"index":84,"description":262},"term-extraction","领域术语抽取","从一批专业文档里自动挑出该领域反复使用的多字术语。",{"type":264,"name":265,"category":185,"index":84,"description":266},"sample-clustering","样本聚类","对表格数值列做 K-Means 聚类，自动选 K 并输出分群画像和二维投影图。",{"type":268,"name":269,"category":185,"index":89,"description":270},"keyness-analysis","语料对比关键词分析","用 keyness 关键性统计对比两组语料，找出目标里反复强调的特征词与相对回避的话题。",{"type":272,"name":273,"category":185,"index":89,"description":274},"trend-analysis","趋势分析","对日期指标序列做聚合、移动平均、环比同比分析，自动识别峰谷和异常。",{"type":276,"name":277,"category":185,"index":94,"description":278},"corpus-search","语料检索","在一批文档里按相关度检索段落、句子或整篇文档，关键词与意思接近的内容都能找到。",{"type":280,"name":281,"category":185,"index":99,"description":282},"vocab-growth","词汇增长曲线分析","拟合词汇增长曲线与 Zipf 分布，给出用词开放度、词频陡峭度，并预测再读多少文本能新增多少词。",{"type":284,"name":285,"category":185,"index":104,"description":286},"dependency-pattern-mining","依存句法模式挖掘","从大批句子中归纳反复出现的依存关系、词性骨架、动词论元与修饰搭配，补足单句句法树看不到的整体规律。",{"type":288,"name":289,"category":185,"index":109,"description":290},"discourse-marker","话语标记词分析","总结「所以、然而、总之」这类衔接词的用量与位置，看懂文章怎么讲道理、哪里转折和收束最集中。",{"type":292,"name":293,"category":185,"index":114,"description":294},"deep-style-analysis","写作风格判定","基于多种统计风格特征，量化每篇文档的写作风格。",{"type":296,"name":297,"category":298,"index":9,"description":299},"image-classification","图像识别与分类","图像分析","快速判断图片属于哪一类，并给出置信度。",{"type":301,"name":302,"category":298,"index":14,"description":303},"image-segment-v2","图像语义分割与实例分割","自动识别图中物体并按类别\u002F实例圈出、打标签。",{"type":305,"name":306,"category":298,"index":19,"description":307},"shot-type","景别判断","判断照片是特写、近景、中景还是远景，适合批量分析取景。",{"type":309,"name":310,"category":298,"index":29,"description":311},"semantic-segment","图像语义分割","按物体类别对整张图做像素级分区标注。",{"type":313,"name":314,"category":298,"index":34,"description":315},"color-extract","图像颜色分布","提取图片主色、生成配色方案并展示颜色分布。",{"type":317,"name":318,"category":298,"index":39,"description":319},"instance-segment","实例分割图像","圈出图中每一个独立物体并区分不同实例。",{"type":321,"name":322,"category":298,"index":44,"description":323},"image-classification-predefined","预设分类图像分类","按你设定的类别给图片打标签，适合固定场景。",{"type":325,"name":326,"category":327,"index":328,"description":329},"causal-extraction","因果关系推断","智能分析",0,"从文本中识别「因为—所以」等因果关系，适合政策与社科分析。",{"type":331,"name":332,"category":327,"index":9,"description":333},"position-analysis","立场分析","识别文本中的利益相关方、立场态度与利益动因。",{"type":335,"name":336,"category":327,"index":9,"description":337},"expecta-scope","期待挖掘","从反馈与政策文本中挖出具体期待，判断大家最想要什么、急不急、情绪如何。",{"type":339,"name":340,"category":327,"index":19,"description":341},"implicit-sentiment-analysis","隐含情感识别","逐句检测中文文本中的阴阳怪气、过度捧杀和隐含负面情绪，揭示字面之外的真实态度。",{"type":343,"name":344,"category":327,"index":29,"description":345},"event-timeline","事件时间线抽取","从长文中抽取时间、事件、主体、地点并归一化日期，输出可排序的时间线。",{"type":347,"name":348,"category":327,"index":34,"description":349},"rhetoric-detection","修辞手法检测","逐句标注比喻、排比、反问等修辞手法，输出分布统计和密度指标。"]