fix

2025-12-29 20:51:20 +08:00
parent 0d94276a0d
commit b6352d4f6f
12 changed files with 176256 additions and 10 deletions
--- a/WebApi/Resources/char_state_tab.json
+++ b/WebApi/Resources/char_state_tab.json
--- a/WebApi/Resources/dict.txt
+++ b/WebApi/Resources/dict.txt
--- a/WebApi/Resources/idf.txt
+++ b/WebApi/Resources/idf.txt
--- a/WebApi/Resources/pos_prob_emit.json
+++ b/WebApi/Resources/pos_prob_emit.json
--- a/WebApi/Resources/pos_prob_start.json
+++ b/WebApi/Resources/pos_prob_start.json
@@ -0,0 +1,258 @@
+{
+  "E-e": -3.14e+100,
+  "E-d": -3.14e+100,
+  "E-g": -3.14e+100,
+  "E-f": -3.14e+100,
+  "E-a": -3.14e+100,
+  "E-c": -3.14e+100,
+  "E-b": -3.14e+100,
+  "E-m": -3.14e+100,
+  "S-rg": -10.275268591948773,
+  "E-o": -3.14e+100,
+  "E-n": -3.14e+100,
+  "E-i": -3.14e+100,
+  "E-h": -3.14e+100,
+  "E-k": -3.14e+100,
+  "E-j": -3.14e+100,
+  "E-u": -3.14e+100,
+  "E-t": -3.14e+100,
+  "E-w": -3.14e+100,
+  "E-v": -3.14e+100,
+  "E-q": -3.14e+100,
+  "E-p": -3.14e+100,
+  "E-s": -3.14e+100,
+  "M-bg": -3.14e+100,
+  "M-uj": -3.14e+100,
+  "E-y": -3.14e+100,
+  "E-x": -3.14e+100,
+  "E-z": -3.14e+100,
+  "B-uz": -3.14e+100,
+  "S-d": -3.903919764181873,
+  "M-rg": -3.14e+100,
+  "E-nt": -3.14e+100,
+  "B-d": -3.9750475297585357,
+  "B-uv": -3.14e+100,
+  "E-vi": -3.14e+100,
+  "B-mq": -6.78695300139688,
+  "M-rr": -3.14e+100,
+  "S-ag": -6.954113917960154,
+  "M-jn": -3.14e+100,
+  "E-l": -3.14e+100,
+  "M-rz": -3.14e+100,
+  "B-ud": -3.14e+100,
+  "S-an": -12.84021794941031,
+  "B-qg": -3.14e+100,
+  "B-ug": -3.14e+100,
+  "M-y": -3.14e+100,
+  "S-qg": -3.14e+100,
+  "S-z": -3.14e+100,
+  "S-y": -6.1970794699489575,
+  "S-x": -8.427419656069674,
+  "S-w": -3.14e+100,
+  "S-v": -3.053292303412302,
+  "S-u": -6.940320595827818,
+  "S-t": -3.14e+100,
+  "B-nrt": -4.985642733519195,
+  "S-r": -2.7635336784127853,
+  "S-q": -4.888658618255058,
+  "M-zg": -3.14e+100,
+  "S-o": -8.464460927750023,
+  "S-n": -3.8551483897645107,
+  "B-zg": -3.14e+100,
+  "S-l": -3.14e+100,
+  "S-k": -6.940320595827818,
+  "S-in": -3.14e+100,
+  "S-i": -3.14e+100,
+  "S-h": -8.650563207383884,
+  "S-g": -6.507826815331734,
+  "B-f": -5.491630418482717,
+  "S-e": -5.942513006281674,
+  "M-en": -3.14e+100,
+  "S-c": -4.786966795861212,
+  "S-b": -6.472888763970454,
+  "S-a": -3.9025396831295227,
+  "B-g": -3.14e+100,
+  "B-b": -5.018374362109218,
+  "B-c": -3.423880184954888,
+  "M-ug": -3.14e+100,
+  "B-a": -4.762305214596967,
+  "E-qe": -3.14e+100,
+  "M-x": -3.14e+100,
+  "E-nz": -3.14e+100,
+  "M-z": -3.14e+100,
+  "M-u": -3.14e+100,
+  "B-k": -3.14e+100,
+  "M-w": -3.14e+100,
+  "B-jn": -3.14e+100,
+  "S-yg": -13.533365129970255,
+  "B-o": -8.433498702146057,
+  "B-l": -4.905883584659895,
+  "B-m": -3.6524299819046386,
+  "M-m": -3.14e+100,
+  "M-l": -3.14e+100,
+  "M-o": -3.14e+100,
+  "M-n": -3.14e+100,
+  "M-i": -3.14e+100,
+  "M-h": -3.14e+100,
+  "B-t": -3.3647479094528574,
+  "M-ul": -3.14e+100,
+  "B-z": -7.045681111485645,
+  "M-d": -3.14e+100,
+  "M-mg": -3.14e+100,
+  "B-y": -9.844485675856319,
+  "M-a": -3.14e+100,
+  "S-nrt": -3.14e+100,
+  "M-c": -3.14e+100,
+  "M-uz": -3.14e+100,
+  "E-mg": -3.14e+100,
+  "B-i": -6.1157847275557105,
+  "M-b": -3.14e+100,
+  "E-uz": -3.14e+100,
+  "B-n": -1.6966257797548328,
+  "E-uv": -3.14e+100,
+  "M-ud": -3.14e+100,
+  "M-p": -3.14e+100,
+  "E-ul": -3.14e+100,
+  "E-mq": -3.14e+100,
+  "M-s": -3.14e+100,
+  "M-yg": -3.14e+100,
+  "E-uj": -3.14e+100,
+  "E-ud": -3.14e+100,
+  "S-ln": -3.14e+100,
+  "M-r": -3.14e+100,
+  "E-ng": -3.14e+100,
+  "B-r": -3.4098187790818413,
+  "E-en": -3.14e+100,
+  "M-qg": -3.14e+100,
+  "B-s": -5.522673590839954,
+  "S-rr": -3.14e+100,
+  "B-p": -4.200984132085048,
+  "B-dg": -3.14e+100,
+  "M-uv": -3.14e+100,
+  "S-zg": -3.14e+100,
+  "B-v": -2.6740584874265685,
+  "S-tg": -6.272842531880403,
+  "B-w": -3.14e+100,
+  "B-e": -8.563551830394255,
+  "M-k": -3.14e+100,
+  "M-j": -3.14e+100,
+  "B-df": -8.888974230828882,
+  "M-e": -3.14e+100,
+  "E-tg": -3.14e+100,
+  "M-t": -3.14e+100,
+  "E-nr": -3.14e+100,
+  "M-nrfg": -3.14e+100,
+  "B-nr": -2.2310495913769506,
+  "E-df": -3.14e+100,
+  "E-dg": -3.14e+100,
+  "S-jn": -3.14e+100,
+  "M-q": -3.14e+100,
+  "B-mg": -3.14e+100,
+  "B-ln": -3.14e+100,
+  "M-f": -3.14e+100,
+  "E-ln": -3.14e+100,
+  "E-yg": -3.14e+100,
+  "S-bg": -3.14e+100,
+  "E-ns": -3.14e+100,
+  "B-tg": -3.14e+100,
+  "E-qg": -3.14e+100,
+  "S-nr": -4.483663103956885,
+  "S-ns": -3.14e+100,
+  "M-vn": -3.14e+100,
+  "S-nt": -12.147070768850364,
+  "S-nz": -3.14e+100,
+  "S-ad": -11.048458480182255,
+  "B-yg": -3.14e+100,
+  "M-v": -3.14e+100,
+  "E-vn": -3.14e+100,
+  "S-ng": -4.913434861102905,
+  "M-g": -3.14e+100,
+  "M-nt": -3.14e+100,
+  "S-en": -3.14e+100,
+  "M-nr": -3.14e+100,
+  "M-ns": -3.14e+100,
+  "S-vq": -3.14e+100,
+  "B-uj": -3.14e+100,
+  "M-nz": -3.14e+100,
+  "B-qe": -3.14e+100,
+  "M-in": -3.14e+100,
+  "M-ng": -3.14e+100,
+  "S-vn": -11.453923588290419,
+  "E-zg": -3.14e+100,
+  "S-vi": -3.14e+100,
+  "S-vg": -5.9430181843676895,
+  "S-vd": -3.14e+100,
+  "B-ad": -6.680066036784177,
+  "E-rz": -3.14e+100,
+  "B-ag": -3.14e+100,
+  "B-vd": -9.044728760238115,
+  "S-mq": -3.14e+100,
+  "B-vi": -12.434752841302146,
+  "E-rr": -3.14e+100,
+  "B-rr": -12.434752841302146,
+  "M-vq": -3.14e+100,
+  "E-jn": -3.14e+100,
+  "B-vn": -4.3315610890163585,
+  "S-mg": -10.825314928868044,
+  "B-in": -3.14e+100,
+  "M-vi": -3.14e+100,
+  "M-an": -3.14e+100,
+  "M-vd": -3.14e+100,
+  "B-rg": -3.14e+100,
+  "M-vg": -3.14e+100,
+  "M-ad": -3.14e+100,
+  "M-ag": -3.14e+100,
+  "E-rg": -3.14e+100,
+  "S-uz": -9.299258625372996,
+  "B-en": -3.14e+100,
+  "S-uv": -8.15808672228609,
+  "S-df": -3.14e+100,
+  "S-dg": -8.948397651299683,
+  "M-qe": -3.14e+100,
+  "B-ng": -3.14e+100,
+  "E-bg": -3.14e+100,
+  "S-ul": -8.4153713175535,
+  "S-uj": -6.85251045118004,
+  "S-ug": -7.5394037026636855,
+  "B-ns": -2.8228438314969213,
+  "S-ud": -7.728230161053767,
+  "B-nt": -4.846091668182416,
+  "B-ul": -3.14e+100,
+  "E-in": -3.14e+100,
+  "B-bg": -3.14e+100,
+  "M-df": -3.14e+100,
+  "M-dg": -3.14e+100,
+  "M-nrt": -3.14e+100,
+  "B-j": -5.0576191284681915,
+  "E-ug": -3.14e+100,
+  "E-vq": -3.14e+100,
+  "B-vg": -3.14e+100,
+  "B-nz": -3.94698846057672,
+  "S-qe": -3.14e+100,
+  "B-rz": -7.946116471570005,
+  "B-nrfg": -5.873722175405573,
+  "E-ad": -3.14e+100,
+  "E-ag": -3.14e+100,
+  "B-u": -9.163917277503234,
+  "M-ln": -3.14e+100,
+  "B-an": -8.697083223018778,
+  "M-mq": -3.14e+100,
+  "E-an": -3.14e+100,
+  "S-s": -3.14e+100,
+  "B-q": -6.998123858956596,
+  "E-nrt": -3.14e+100,
+  "B-h": -13.533365129970255,
+  "E-r": -3.14e+100,
+  "S-p": -2.9868401813596317,
+  "M-tg": -3.14e+100,
+  "S-rz": -3.14e+100,
+  "S-nrfg": -3.14e+100,
+  "B-vq": -12.147070768850364,
+  "B-x": -3.14e+100,
+  "E-vd": -3.14e+100,
+  "E-nrfg": -3.14e+100,
+  "S-m": -3.269200652116097,
+  "E-vg": -3.14e+100,
+  "S-f": -5.194820249981676,
+  "S-j": -4.911992119644354
+}
--- a/WebApi/Resources/pos_prob_trans.json
+++ b/WebApi/Resources/pos_prob_trans.json
--- a/WebApi/Resources/prob_emit.json
+++ b/WebApi/Resources/prob_emit.json
--- a/WebApi/Resources/prob_trans.json
+++ b/WebApi/Resources/prob_trans.json
@@ -0,0 +1,18 @@
+{
+  "M": {
+    "M": -1.2603623820268226,
+    "E": -0.33344856811948514
+  },
+  "S": {
+    "S": -0.6658631448798212,
+    "B": -0.7211965654669841
+  },
+  "B": {
+    "M": -0.916290731874155,
+    "E": -0.51082562376599
+  },
+  "E": {
+    "S": -0.8085250474669937,
+    "B": -0.5897149736854513
+  }
+}
--- a/WebApi/Resources/stopwords.txt
+++ b/WebApi/Resources/stopwords.txt
@@ -0,0 +1,330 @@
+的
+了
+在
+是
+我
+有
+和
+就
+不
+人
+都
+一
+一个
+上
+也
+很
+到
+说
+要
+去
+你
+会
+着
+没有
+看
+好
+自己
+这
+那
+与
+或
+等
+及
+而
+为
+之
+于
+对
+从
+中
+可以
+但
+因为
+所以
+如果
+已经
+还
+又
+再
+更
+最
+元
+块
+角
+分
+笔
+条
+张
+个
+次
+回
+天
+月
+年
+来
+给
+把
+被
+让
+向
+往
+跟
+比
+将
+以
+用
+由
+她
+他
+它
+们
+您
+咱
+啥
+哪
+什么
+怎么
+为什么
+多少
+几
+每
+各
+某
+此
+彼
+其
+该
+这个
+那个
+这些
+那些
+哪些
+什么样
+怎样
+如何
+多么
+何等
+若干
+左右
+前后
+上下
+东西
+南北
+里外
+内外
+大小
+高低
+长短
+多少
+好坏
+新旧
+早晚
+前面
+后面
+上面
+下面
+左边
+右边
+里面
+外面
+中间
+旁边
+附近
+周围
+全部
+所有
+一切
+任何
+每个
+各自
+彼此
+相互
+互相
+共同
+一起
+同时
+当时
+平时
+随时
+及时
+准时
+按时
+到时
+届时
+临时
+暂时
+长期
+短期
+永远
+从来
+向来
+素来
+一向
+历来
+总是
+常常
+往往
+通常
+一般
+大概
+大约
+左右
+上下
+几乎
+差不多
+可能
+也许
+大概
+或许
+恐怕
+难道
+岂
+究竟
+到底
+果然
+居然
+竟然
+偏偏
+简直
+实在
+的确
+确实
+真正
+真是
+果真
+当真
+委实
+着实
+十分
+非常
+很
+挺
+最
+更
+极
+太
+甚
+颇
+稍
+略
+稍微
+些
+点
+一点
+有点
+一些
+若干
+许多
+很多
+好多
+大量
+少量
+大批
+成批
+整个
+全部
+部分
+半
+多半
+大半
+少半
+绝大部分
+绝大多数
+极少数
+等等
+之类
+以及
+及其
+乃至
+甚至
+甚而
+进而
+从而
+因而
+所以
+因此
+于是
+然后
+接着
+随后
+继而
+终于
+最后
+最终
+结果
+总之
+综上所述
+由此可见
+显而易见
+众所周知
+不言而喭
+毫无疑问
+毋庸置疑
+无可置疑
+不容置疑
+无庸讳言
+何必
+何况
+何妨
+反正
+不过
+只是
+但是
+然而
+可是
+只不过
+不外
+无非
+虽然
+尽管
+即使
+就算
+哪怕
+纵使
+纵然
+既然
+假如
+如果
+倘若
+要是
+万一
+除非
+不管
+无论
+不论
+任凭
+只要
+只有
+除了
+除去
+除开
+撇开
+此外
+另外
+以外
+之外
+不仅
+不但
+不只
+不光
+而且
+并且
+况且
+何况
+甚至
+以至
+乃至
+与其
+宁可
+宁愿
+还是
+或者
+抑或
+要么
+不是
+就是
+是否
+难道
+莫非
+岂