一个通过用户上传的待分词文本
及分词配置文件
进行文本分词,生成词云图的后端api接口。
可通过配置oss存储,将分词结果、词云图保存到oss中。
-
安装依赖
pipenv shell ... pipenv install
-
运行项目
配置文件 配置文件里需要配置oss存储的相关信息,以及词云图的相关参数。
本地运行
uvicorn main:app --reload --port 8000
服务器运行
uvicorn main:app --host 0.0.0.0 --port 8000
-
测试
本地部署后,可通过http://localhost:8000/docs
访问接口文档,使用单词云、多词云和用户设置的xlsx模版进行测试
```json
{
"code": 0,
"msg": "success",
"data": {
"cut_setting": {
"stop_words": [
"方面"
],
"similar_words": {
"AI": "ai|人工智能|小度同?学?",
"昆仑芯片": "昆仑"
},
"user_words": [
"小度同学",
"昆仑芯片",
"AI",
"百度智能云",
"百度Apollo"
]
},
"cut_result": [
{
"word_data": {
"百度": {
"count": 25,
"flag": "n",
"weight": 0.6084701009874303
},
"AI": {
"count": 23,
"flag": "nz",
"weight": 0.7680437222533519
},
"**": {
"count": 11,
"flag": "ns",
"weight": 0.09301823338899441
},
"公司": {
"count": 10,
"flag": "n",
"weight": 0.09786228892681563
},
"全球": {
"count": 10,
"flag": "n",
"weight": 0.13692867189078212
},
"智能": {
"count": 10,
"flag": "n",
"weight": 0.20000442157458104
},
"技术": {
"count": 9,
"flag": "n",
"weight": 0.11864557152829609
},
"领先": {
"count": 6,
"flag": "n",
"weight": 0.11845216624340782
},
"自动": {
"count": 6,
"flag": "vn",
"weight": 0.10862509054290503
},
"领域": {
"count": 6,
"flag": "n",
"weight": 0.09070886383927375
},
"互联网": {
"count": 5,
"flag": "n",
"weight": 0.09946777589790504
},
"芯片": {
"count": 4,
"flag": "n",
"weight": 0.10059036706167598
},
"服务": {
"count": 4,
"flag": "vn",
"weight": 0.05968883348681564
},
"语音": {
"count": 4,
"flag": "n",
"weight": 0.09445743329955307
},
"生态": {
"count": 4,
"flag": "n",
"weight": 0.08272516940547486
},
"交通": {
"count": 4,
"flag": "n",
"weight": 0.06642740293921788
},
"智慧": {
"count": 4,
"flag": "nr",
"weight": 0.08259115659217876
},
"汽车": {
"count": 4,
"flag": "n",
"weight": 0.057864941841675975
},
"社会": {
"count": 4,
"flag": "n",
"weight": 0.05016224738067039
},
"强大": {
"count": 3,
"flag": "a",
"weight": 0.05283762882502793
},
"科技": {
"count": 3,
"flag": "n",
"weight": 0.04887381027997206
},
"用户": {
"count": 3,
"flag": "n",
"weight": 0.057170414014692736
},
"搜索引擎": {
"count": 3,
"flag": "n",
"weight": 0.08150522666547487
},
"深度": {
"count": 3,
"flag": "ns",
"weight": 0.05830353543988827
},
"对话": {
"count": 3,
"flag": "n",
"weight": 0.062485025658770954
},
"昆仑芯片": {
"count": 3,
"flag": "nz",
"weight": 0.10017961594608937
},
"百度智能云": {
"count": 3,
"flag": "nz",
"weight": 0.10017961594608937
},
"解决方案": {
"count": 3,
"flag": "n",
"weight": 0.07179853792215084
},
"助手": {
"count": 3,
"flag": "n",
"weight": 0.06828020960740223
},
"基础": {
"count": 2,
"flag": "n",
"weight": 0.02661022684648045
},
"全栈": {
"count": 2,
"flag": "n",
"weight": 0.06678641063072625
},
"机构": {
"count": 2,
"flag": "n",
"weight": 0.02599034122452514
},
"美国": {
"count": 2,
"flag": "ns",
"weight": 0.023221207998100558
},
"国家": {
"count": 2,
"flag": "n",
"weight": 0.022348856939441337
},
"图谱": {
"count": 2,
"flag": "n",
"weight": 0.054973377885083795
},
"能力": {
"count": 2,
"flag": "n",
"weight": 0.027571749040055864
},
"突破": {
"count": 2,
"flag": "vn",
"weight": 0.031420575123519555
},
"算力": {
"count": 2,
"flag": "n",
"weight": 0.06678641063072625
},
"算法": {
"count": 2,
"flag": "n",
"weight": 0.04855414245324022
},
"开发者": {
"count": 2,
"flag": "n",
"weight": 0.06151008879385475
},
"企业": {
"count": 2,
"flag": "n",
"weight": 0.023585319468994413
},
"专利申请": {
"count": 2,
"flag": "n",
"weight": 0.06151008879385475
},
"融合": {
"count": 2,
"flag": "vn",
"weight": 0.040033999955307265
},
"发展": {
"count": 2,
"flag": "vn",
"weight": 0.019972427656089385
},
"布局": {
"count": 2,
"flag": "n",
"weight": 0.03580153413050279
},
"引擎": {
"count": 2,
"flag": "n",
"weight": 0.04592460917854748
},
"开放平台": {
"count": 2,
"flag": "nz",
"weight": 0.06678641063072625
},
"医疗": {
"count": 2,
"flag": "n",
"weight": 0.0367421624903352
},
"产品": {
"count": 2,
"flag": "n",
"weight": 0.025457295467206705
},
"百度Apollo": {
"count": 2,
"flag": "nz",
"weight": 0.06678641063072625
},
"测试": {
"count": 2,
"flag": "vn",
"weight": 0.039928713594301675
},
"智能化": {
"count": 2,
"flag": "nr",
"weight": 0.04951801703664804
},
"Apollo": {
"count": 2,
"flag": "eng",
"weight": 0.06678641063072625
},
"次数": {
"count": 2,
"flag": "n",
"weight": 0.042109774013631286
},
"责任": {
"count": 2,
"flag": "n",
"weight": 0.033789042271620114
},
"应用程序": {
"count": 1,
"flag": "n",
"weight": 0.029328157179608936
},
"国际": {
"count": 1,
"flag": "n",
"weight": 0.012495005030754189
},
"复杂": {
"count": 1,
"flag": "a",
"weight": 0.016311470090167597
},
"世界": {
"count": 1,
"flag": "n",
"weight": 0.012199802808854748
},
"简单": {
"count": 1,
"flag": "a",
"weight": 0.01569328114036313
},
"致力于": {
"count": 1,
"flag": "n",
"weight": 0.020132273697513966
},
"人们": {
"count": 1,
"flag": "n",
"weight": 0.013076750423379888
},
"顶级": {
"count": 1,
"flag": "n",
"weight": 0.0239193842800838
},
"高科技": {
"count": 1,
"flag": "nz",
"weight": 0.022664190700027936
},
"中关村": {
"count": 1,
"flag": "ns",
"weight": 0.026485578335698326
},
"创始人": {
"count": 1,
"flag": "n",
"weight": 0.020447034957234638
},
"李彦宏": {
"count": 1,
"flag": "nr",
"weight": 0.034333071898044694
},
"专利": {
"count": 1,
"flag": "n",
"weight": 0.02210677554941341
},
"俄罗斯": {
"count": 1,
"flag": "ns",
"weight": 0.017421230148798882
},
"韩国": {
"count": 1,
"flag": "ns",
"weight": 0.019394358327094973
},
"核心技术": {
"count": 1,
"flag": "n",
"weight": 0.024617545577486032
},
"地区": {
"count": 1,
"flag": "n",
"weight": 0.01245084309
},
"网民": {
"count": 1,
"flag": "n",
"weight": 0.022804763560055865
},
"中文信息": {
"count": 1,
"flag": "nt",
"weight": 0.038828708525139664
},
"入口": {
"count": 1,
"flag": "ns",
"weight": 0.02274239072094972
},
"演化出": {
"count": 1,
"flag": "n",
"weight": 0.031457040006703914
},
"图像": {
"count": 1,
"flag": "n",
"weight": 0.021666178820810057
},
"投资": {
"count": 1,
"flag": "vn",
"weight": 0.010866413273156425
},
"大脑": {
"count": 1,
"flag": "n",
"weight": 0.022127910299078214
},
"集大成": {
"count": 1,
"flag": "nz",
"weight": 0.03091470477067039
},
"调用": {
"count": 1,
"flag": "vn",
"weight": 0.02356660851103352
},
"云端": {
"count": 1,
"flag": "n",
"weight": 0.027255706496033517
},
"伙伴": {
"count": 1,
"flag": "n",
"weight": 0.021386901539972067
},
"场景": {
"count": 1,
"flag": "n",
"weight": 0.022698676274944134
},
"广泛": {
"count": 1,
"flag": "a",
"weight": 0.015606342214134079
},
"部署": {
"count": 1,
"flag": "n",
"weight": 0.018743021278324022
},
"高性能": {
"count": 1,
"flag": "n",
"weight": 0.024851204877178772
},
"量产": {
"count": 1,
"flag": "n",
"weight": 0.026419068143826815
},
"性能比": {
"count": 1,
"flag": "n",
"weight": 0.031457040006703914
},
"飞桨": {
"count": 1,
"flag": "n",
"weight": 0.03339320531536313
},
"框架": {
"count": 1,
"flag": "n",
"weight": 0.020230912307569834
},
"时代": {
"count": 1,
"flag": "n",
"weight": 0.015380810867486034
},
"趋势": {
"count": 1,
"flag": "n",
"weight": 0.014836692629189943
},
"移动": {
"count": 1,
"flag": "vn",
"weight": 0.018246754094022346
},
"新格局": {
"count": 1,
"flag": "nt",
"weight": 0.027901269962430166
},
"积蓄": {
"count": 1,
"flag": "n",
"weight": 0.023129264766089386
},
"势能": {
"count": 1,
"flag": "n",
"weight": 0.027901269962430166
},
"优势": {
"count": 1,
"flag": "n",
"weight": 0.015769912707318437
},
"云智": {
"count": 1,
"flag": "nr",
"weight": 0.03339320531536313
},
"一体": {
"count": 1,
"flag": "n",
"weight": 0.020606467446452514
}
},
"word_cloud_img_url": "oss_url"
}
]
}
}
```