[{"data":1,"prerenderedAt":597},["Reactive",2],{"navigation":3,"content-query-QgpOJrl7T5":40,"content-query-s6rkEq2v7j":360},[4,9,37],{"title":5,"_path":6,"children":7},"产品简介","/product-introduce",[8],{"title":5,"_path":6},{"title":10,"_path":11,"children":12},"用户指南","/user-guide",[13,14,17,31,34],{"title":10,"_path":11},{"title":15,"_path":16},"项目背景","/user-guide/project-background",{"title":18,"_path":19,"children":20},"数据源管理","/user-guide/datasource",[21,22,25,28],{"title":18,"_path":19},{"title":23,"_path":24},"数据准备","/user-guide/datasource/datasource-02",{"title":26,"_path":27},"模型配置","/user-guide/datasource/datasource-03",{"title":29,"_path":30},"抽图及抽图结果检测","/user-guide/datasource/datasource-04",{"title":32,"_path":33},"规则发现","/user-guide/rule-discovery",{"title":35,"_path":36},"规则库","/user-guide/rule-base",{"title":38,"_path":39},"附录1：各种数据库支持的数据类型","/appendix1-types-data",[41],{"_path":30,"_dir":42,"_draft":43,"_partial":43,"_locale":44,"_empty":43,"title":29,"description":45,"body":46,"_type":355,"_id":356,"_source":357,"_file":358,"_extension":359},"datasource",false,"","在完成全部数据模型的属性选择后，点击提交按钮，系统开始抽图并检测抽图结果。抽图结果检测是系统依据图的点边数据、抽图过程的丢弃日志等来对图文件做出详细的评价。",{"type":47,"children":48,"toc":345},"root",[49,56,61,66,90,101,106,115,134,143,148,157,163,168,173,178,191,196,201,212,221,226,237,242,247,252,261,266,271,276,332],{"type":50,"tag":51,"props":52,"children":53},"element","h1",{"id":29},[54],{"type":55,"value":29},"text",{"type":50,"tag":57,"props":58,"children":59},"p",{},[60],{"type":55,"value":45},{"type":50,"tag":57,"props":62,"children":63},{},[64],{"type":55,"value":65},"（1）提交配置，弹出“生成图文件”弹窗，如下图所示。",{"type":50,"tag":67,"props":68,"children":69},"blockquote",{},[70],{"type":50,"tag":57,"props":71,"children":72},{},[73,75,81,83,88],{"type":55,"value":74},"生成图文件过程中点击",{"type":50,"tag":76,"props":77,"children":78},"code-inline",{},[79],{"type":55,"value":80},"返回数据源管理",{"type":55,"value":82},"，返回数据源管理界面，本抽图任务仍在后台运行。点击",{"type":50,"tag":76,"props":84,"children":85},{},[86],{"type":55,"value":87},"停止",{"type":55,"value":89},"，抽图任务终止，系统跳转至创建数据源页面。",{"type":50,"tag":57,"props":91,"children":92},{},[93],{"type":50,"tag":94,"props":95,"children":100},"img",{"alt":96,"src":97,"style":98},"image-20230726165539106","/2.user-guide/images/datasource-29.png",{"aspectRatio":99},"1650/897",[],{"type":50,"tag":57,"props":102,"children":103},{},[104],{"type":55,"value":105},"（2）抽图完成，如下图所示。",{"type":50,"tag":57,"props":107,"children":108},{},[109],{"type":50,"tag":94,"props":110,"children":114},{"alt":111,"src":112,"style":113},"image-20230726165842782","/2.user-guide/images/datasource-30.png",{"aspectRatio":99},[],{"type":50,"tag":57,"props":116,"children":117},{},[118,120,125,127,132],{"type":55,"value":119},"（3）点击",{"type":50,"tag":76,"props":121,"children":122},{},[123],{"type":55,"value":124},"查看数据源",{"type":55,"value":126},"按钮进入数据源查看界面，如下图所示。点击实体，可查看到用户配置属性通过模型计算后，产生的衍生属性。点击",{"type":50,"tag":76,"props":128,"children":129},{},[130],{"type":55,"value":131},"已配置模型",{"type":55,"value":133},"按钮，可查看当前数据源使用的模型及模型中已选的属性。",{"type":50,"tag":57,"props":135,"children":136},{},[137],{"type":50,"tag":94,"props":138,"children":142},{"alt":139,"src":140,"style":141},"image-20230726170058445","/2.user-guide/images/datasource-31.png",{"aspectRatio":99},[],{"type":50,"tag":57,"props":144,"children":145},{},[146],{"type":55,"value":147},"（4）点击查看检测结果，出现检测结果的弹窗，如图所示。",{"type":50,"tag":57,"props":149,"children":150},{},[151],{"type":50,"tag":94,"props":152,"children":156},{"alt":153,"src":154,"style":155},"image-20230726170213268","/2.user-guide/images/datasource-32.png",{"aspectRatio":99},[],{"type":50,"tag":158,"props":159,"children":161},"h2",{"id":160},"编码检测",[162],{"type":55,"value":160},{"type":50,"tag":57,"props":164,"children":165},{},[166],{"type":55,"value":167},"检测图文件编码是否正确。系统在抽图时会以编码/加密的方式对数据进行处理，解决用户数据的安全合规问题。此处是为了检验最终图文件是否按照预期完成编码/加密，并保证后续规则发现能够正常执行。",{"type":50,"tag":158,"props":169,"children":171},{"id":170},"属性类型检测",[172],{"type":55,"value":170},{"type":50,"tag":57,"props":174,"children":175},{},[176],{"type":55,"value":177},"检测图文件属性数据是否符合类型，某一属性列表明为数值类型，则抽图文件中该属性列的属性值都必须为数值类型才能通过。",{"type":50,"tag":67,"props":179,"children":180},{},[181],{"type":50,"tag":182,"props":183,"children":184},"ul",{},[185],{"type":50,"tag":186,"props":187,"children":188},"li",{},[189],{"type":55,"value":190},"若数值型列中的数据一大半填写数值一小半填字符，抽图过程中抽图异常—可修复，其属性类型检测会判定为失败。",{"type":50,"tag":158,"props":192,"children":194},{"id":193},"连通性检测",[195],{"type":55,"value":193},{"type":50,"tag":57,"props":197,"children":198},{},[199],{"type":55,"value":200},"连通性列表5个连通分量分别的点边数量，其最大连通分量实体数为45014，总实体数为孤立点的个数加上连通分量点的个数，一共56033个。最大连通分量的实体数和总实体数的比例大于0.5，为通过，如图所示。",{"type":50,"tag":67,"props":202,"children":203},{},[204],{"type":50,"tag":182,"props":205,"children":206},{},[207],{"type":50,"tag":186,"props":208,"children":209},{},[210],{"type":55,"value":211},"检测图文件的连通性情况，实体/实体关系数量越集中，图文件质量越高，最大连通分量的实体数/总实体数>0.5即为检测通过。",{"type":50,"tag":57,"props":213,"children":214},{},[215],{"type":50,"tag":94,"props":216,"children":220},{"alt":94,"src":217,"style":218},"/2.user-guide/images/048.png",{"aspectRatio":219},"976/486",[],{"type":50,"tag":158,"props":222,"children":224},{"id":223},"信息熵检测",[225],{"type":55,"value":223},{"type":50,"tag":57,"props":227,"children":228},{},[229,231],{"type":55,"value":230},"信息熵是信息论中用于度量信息量的一个概念。 一个系统越是有序，信息熵就越低； 反之，一个系统越是混乱，信息熵就越高。 所以，信息熵也可以说是系统有序化程度的一个度量。 信息熵过低，说明实体与实体关系的属性信息过于单一，可能会挖掘出大量意义不大的规则； 信息熵过高，说明实体与实体关系的属性信息过于随机，可能会导致包含该属性的规则因支持度不足而被抛弃； 公式计算如下所示：",{"type":50,"tag":94,"props":232,"children":236},{"alt":94,"src":233,"style":234},"/2.user-guide/images/formula1.png",{"aspectRatio":235},"958/65",[],{"type":50,"tag":158,"props":238,"children":240},{"id":239},"数值属性内容分布情况",[241],{"type":55,"value":239},{"type":50,"tag":57,"props":243,"children":244},{},[245],{"type":55,"value":246},"显示数值内容的分布的箱型图，包含该属性列数值的上边缘、下边缘、上四分位数、下四分位数、中位数等 显示离群值。",{"type":50,"tag":57,"props":248,"children":249},{},[250],{"type":55,"value":251},"显示标签和数值类型属性名，且显示箱型图和离群点，如图所示。",{"type":50,"tag":57,"props":253,"children":254},{},[255],{"type":50,"tag":94,"props":256,"children":260},{"alt":94,"src":257,"style":258},"/2.user-guide/images/image-20220125103912096.png",{"aspectRatio":259},"1961/768",[],{"type":50,"tag":158,"props":262,"children":264},{"id":263},"丢弃数据日志",[265],{"type":55,"value":263},{"type":50,"tag":57,"props":267,"children":268},{},[269],{"type":55,"value":270},"不符合要求的数据将被丢弃，显示日志序号，丢弃数据原因和对应类型说明的编号。",{"type":50,"tag":57,"props":272,"children":273},{},[274],{"type":55,"value":275},"丢弃类型说明：",{"type":50,"tag":277,"props":278,"children":279},"ol",{},[280,285,290,295,300,327],{"type":50,"tag":186,"props":281,"children":282},{},[283],{"type":55,"value":284},"丢弃类型1:若实体列/关系列有数据内容为空，则该空数据对应的实体/实体关系将会被丢弃",{"type":50,"tag":186,"props":286,"children":287},{},[288],{"type":55,"value":289},"丢弃类型2:若实体关系对应的起点、终点的实体列有数据内容为空，则该空数据对应的实体关系将会被丢弃",{"type":50,"tag":186,"props":291,"children":292},{},[293],{"type":55,"value":294},"丢弃类型3:如果实体关系所对应实体标签在已抽出的实体标签中不存在，则该条实体关系将会被丢弃",{"type":50,"tag":186,"props":296,"children":297},{},[298],{"type":55,"value":299},"丢弃类型4:如果属性列有为空的数据内容，则为空数据对应的属性将会被丢弃",{"type":50,"tag":186,"props":301,"children":302},{},[303,305],{"type":55,"value":304},"丢弃类型5:属性类型为时间/数值/YM时间/YMD时间且转换失败的属性将会被丢弃",{"type":50,"tag":67,"props":306,"children":307},{},[308],{"type":50,"tag":57,"props":309,"children":310},{},[311,313,318,320,325],{"type":55,"value":312},"对于在数据库中是字符类型但属性类型被选为",{"type":50,"tag":76,"props":314,"children":315},{},[316],{"type":55,"value":317},"时间",{"type":55,"value":319},"/",{"type":50,"tag":76,"props":321,"children":322},{},[323],{"type":55,"value":324},"数值",{"type":55,"value":326},"的数据，系统会尝试将其转为数值类型，但会出现转换失败的情况，例如“180cm”因为其带有非数字的字符导致系统无法完成转换。对于此种情况，系统会将转换失败的属性丢弃。",{"type":50,"tag":186,"props":328,"children":329},{},[330],{"type":55,"value":331},"丢弃类型6:实体/实体关系已有重复记录，合并可能造成属性冲突其属性将会被丢弃",{"type":50,"tag":57,"props":333,"children":334},{},[335,337,343],{"type":55,"value":336},"数据内容判断为空的标准：数据为",{"type":50,"tag":338,"props":339,"children":340},"span",{},[341],{"type":55,"value":342},"\"\",\"none\",\"nan\",\"null\"",{"type":55,"value":344},"其中之一则认为是空数据，如果是组合实体列/关系列,只要有一个实体列/关系列有数据内容为空也会丢弃对应的实体/实体关系",{"title":44,"searchDepth":346,"depth":347,"links":348},2,3,[349,350,351,352,353,354],{"id":160,"depth":346,"text":160},{"id":170,"depth":346,"text":170},{"id":193,"depth":346,"text":193},{"id":223,"depth":346,"text":223},{"id":239,"depth":346,"text":239},{"id":263,"depth":346,"text":263},"markdown","content:2.user-guide:2.datasource:3.datasource-04.md","content","2.user-guide/2.datasource/3.datasource-04.md","md",{"_path":30,"_dir":42,"_draft":43,"_partial":43,"_locale":44,"_empty":43,"title":29,"description":45,"body":361,"_type":355,"_id":356,"_source":357,"_file":358,"_extension":359},{"type":47,"children":362,"toc":589},[363,367,371,375,392,399,403,410,424,431,435,442,446,450,454,458,468,472,476,486,493,497,505,509,513,517,524,528,532,536,580],{"type":50,"tag":51,"props":364,"children":365},{"id":29},[366],{"type":55,"value":29},{"type":50,"tag":57,"props":368,"children":369},{},[370],{"type":55,"value":45},{"type":50,"tag":57,"props":372,"children":373},{},[374],{"type":55,"value":65},{"type":50,"tag":67,"props":376,"children":377},{},[378],{"type":50,"tag":57,"props":379,"children":380},{},[381,382,386,387,391],{"type":55,"value":74},{"type":50,"tag":76,"props":383,"children":384},{},[385],{"type":55,"value":80},{"type":55,"value":82},{"type":50,"tag":76,"props":388,"children":389},{},[390],{"type":55,"value":87},{"type":55,"value":89},{"type":50,"tag":57,"props":393,"children":394},{},[395],{"type":50,"tag":94,"props":396,"children":398},{"alt":96,"src":97,"style":397},{"aspectRatio":99},[],{"type":50,"tag":57,"props":400,"children":401},{},[402],{"type":55,"value":105},{"type":50,"tag":57,"props":404,"children":405},{},[406],{"type":50,"tag":94,"props":407,"children":409},{"alt":111,"src":112,"style":408},{"aspectRatio":99},[],{"type":50,"tag":57,"props":411,"children":412},{},[413,414,418,419,423],{"type":55,"value":119},{"type":50,"tag":76,"props":415,"children":416},{},[417],{"type":55,"value":124},{"type":55,"value":126},{"type":50,"tag":76,"props":420,"children":421},{},[422],{"type":55,"value":131},{"type":55,"value":133},{"type":50,"tag":57,"props":425,"children":426},{},[427],{"type":50,"tag":94,"props":428,"children":430},{"alt":139,"src":140,"style":429},{"aspectRatio":99},[],{"type":50,"tag":57,"props":432,"children":433},{},[434],{"type":55,"value":147},{"type":50,"tag":57,"props":436,"children":437},{},[438],{"type":50,"tag":94,"props":439,"children":441},{"alt":153,"src":154,"style":440},{"aspectRatio":99},[],{"type":50,"tag":158,"props":443,"children":444},{"id":160},[445],{"type":55,"value":160},{"type":50,"tag":57,"props":447,"children":448},{},[449],{"type":55,"value":167},{"type":50,"tag":158,"props":451,"children":452},{"id":170},[453],{"type":55,"value":170},{"type":50,"tag":57,"props":455,"children":456},{},[457],{"type":55,"value":177},{"type":50,"tag":67,"props":459,"children":460},{},[461],{"type":50,"tag":182,"props":462,"children":463},{},[464],{"type":50,"tag":186,"props":465,"children":466},{},[467],{"type":55,"value":190},{"type":50,"tag":158,"props":469,"children":470},{"id":193},[471],{"type":55,"value":193},{"type":50,"tag":57,"props":473,"children":474},{},[475],{"type":55,"value":200},{"type":50,"tag":67,"props":477,"children":478},{},[479],{"type":50,"tag":182,"props":480,"children":481},{},[482],{"type":50,"tag":186,"props":483,"children":484},{},[485],{"type":55,"value":211},{"type":50,"tag":57,"props":487,"children":488},{},[489],{"type":50,"tag":94,"props":490,"children":492},{"alt":94,"src":217,"style":491},{"aspectRatio":219},[],{"type":50,"tag":158,"props":494,"children":495},{"id":223},[496],{"type":55,"value":223},{"type":50,"tag":57,"props":498,"children":499},{},[500,501],{"type":55,"value":230},{"type":50,"tag":94,"props":502,"children":504},{"alt":94,"src":233,"style":503},{"aspectRatio":235},[],{"type":50,"tag":158,"props":506,"children":507},{"id":239},[508],{"type":55,"value":239},{"type":50,"tag":57,"props":510,"children":511},{},[512],{"type":55,"value":246},{"type":50,"tag":57,"props":514,"children":515},{},[516],{"type":55,"value":251},{"type":50,"tag":57,"props":518,"children":519},{},[520],{"type":50,"tag":94,"props":521,"children":523},{"alt":94,"src":257,"style":522},{"aspectRatio":259},[],{"type":50,"tag":158,"props":525,"children":526},{"id":263},[527],{"type":55,"value":263},{"type":50,"tag":57,"props":529,"children":530},{},[531],{"type":55,"value":270},{"type":50,"tag":57,"props":533,"children":534},{},[535],{"type":55,"value":275},{"type":50,"tag":277,"props":537,"children":538},{},[539,543,547,551,555,576],{"type":50,"tag":186,"props":540,"children":541},{},[542],{"type":55,"value":284},{"type":50,"tag":186,"props":544,"children":545},{},[546],{"type":55,"value":289},{"type":50,"tag":186,"props":548,"children":549},{},[550],{"type":55,"value":294},{"type":50,"tag":186,"props":552,"children":553},{},[554],{"type":55,"value":299},{"type":50,"tag":186,"props":556,"children":557},{},[558,559],{"type":55,"value":304},{"type":50,"tag":67,"props":560,"children":561},{},[562],{"type":50,"tag":57,"props":563,"children":564},{},[565,566,570,571,575],{"type":55,"value":312},{"type":50,"tag":76,"props":567,"children":568},{},[569],{"type":55,"value":317},{"type":55,"value":319},{"type":50,"tag":76,"props":572,"children":573},{},[574],{"type":55,"value":324},{"type":55,"value":326},{"type":50,"tag":186,"props":577,"children":578},{},[579],{"type":55,"value":331},{"type":50,"tag":57,"props":581,"children":582},{},[583,584,588],{"type":55,"value":336},{"type":50,"tag":338,"props":585,"children":586},{},[587],{"type":55,"value":342},{"type":55,"value":344},{"title":44,"searchDepth":346,"depth":347,"links":590},[591,592,593,594,595,596],{"id":160,"depth":346,"text":160},{"id":170,"depth":346,"text":170},{"id":193,"depth":346,"text":193},{"id":223,"depth":346,"text":223},{"id":239,"depth":346,"text":239},{"id":263,"depth":346,"text":263},1698718464925]