From 28f51a8e25d0b3d9f45a3340ac1e22c5a3efabe0 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Tue, 19 Aug 2025 13:41:20 +0800
Subject: [PATCH] 'commit'

---
 .../Config/__pycache__/Config.cpython-310.pyc | Bin 852 -> 852 bytes
 .../ElasticSearch/Utils/EsSearchUtil.py       | 129 ++++++++++++++
 .../__pycache__/EsSearchUtil.cpython-310.pyc  | Bin 12791 -> 15868 bytes
 dsSchoolBuddy/Start.py                        | 164 ++----------------
 4 files changed, 147 insertions(+), 146 deletions(-)

diff --git a/dsSchoolBuddy/Config/__pycache__/Config.cpython-310.pyc b/dsSchoolBuddy/Config/__pycache__/Config.cpython-310.pyc
index 22c831f6d96cb94f07dd73765e83b5549a1ef46d..e1f95488be20eb743d1e832fbca43079cf56dabd 100644
GIT binary patch
delta 101
zcmcb@c7=^MpO=@50SMxFmt@?W$h(a3*2FC~j8PjuZfA73#qa178Smrc8}At48Sm{H
rc}oB$;N%$W8Xp?ub4v&&;_L6?>J#th=<B+Yp@;)$ViCvW7fd+-o<1O&

delta 101
zcmcb@c7=^MpO=@50SLr-mSh~C$h(X&YT_0f##<XdZfA6e;&=3kjQ8>Jjdu+2jQ4hp
rj1qteI5`Hp#)k&^L<zw}eEnTqed7HbeO*^F6tMzLEMlGff++_8FzOz<

diff --git a/dsSchoolBuddy/ElasticSearch/Utils/EsSearchUtil.py b/dsSchoolBuddy/ElasticSearch/Utils/EsSearchUtil.py
index 77e1e440..1d41639e 100644
--- a/dsSchoolBuddy/ElasticSearch/Utils/EsSearchUtil.py
+++ b/dsSchoolBuddy/ElasticSearch/Utils/EsSearchUtil.py
@@ -4,6 +4,7 @@ import warnings
 import hashlib
 import time
 
+import jieba
 import requests
 
 from ElasticSearch.Utils.ElasticsearchConnectionPool import ElasticsearchConnectionPool
@@ -17,7 +18,32 @@ from typing import List, Tuple, Dict
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
 
+
 class EsSearchUtil:
+    # 存储对话历史的字典，键为会话ID，值为对话历史列表
+    conversation_history = {}
+
+    # 存储学生信息的字典，键为用户ID，值为学生信息
+    student_info = {}
+
+    # 年级关键词词典
+    GRADE_KEYWORDS = {
+        '一年级': ['一年级', '初一'],
+        '二年级': ['二年级', '初二'],
+        '三年级': ['三年级', '初三'],
+        '四年级': ['四年级'],
+        '五年级': ['五年级'],
+        '六年级': ['六年级'],
+        '七年级': ['七年级', '初一'],
+        '八年级': ['八年级', '初二'],
+        '九年级': ['九年级', '初三'],
+        '高一': ['高一'],
+        '高二': ['高二'],
+        '高三': ['高三']
+    }
+
+    # 最大对话历史轮数
+    MAX_HISTORY_ROUNDS = 10
     def __init__(self, es_config):
         """
                 初始化Elasticsearch搜索工具
@@ -527,3 +553,106 @@ class EsSearchUtil:
         sorted_results = sorted(unique_results.values(), key=lambda x: x[1], reverse=True)
         return sorted_results
 
+    # 添加函数：保存学生信息到ES
+    def save_student_info_to_es(self,user_id, info):
+        """将学生信息保存到Elasticsearch"""
+        try:
+            # 使用用户ID作为文档ID
+            doc_id = f"student_{user_id}"
+            # 准备文档内容
+            doc = {
+                "user_id": user_id,
+                "info": info,
+                "update_time": time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+            }
+            # 从连接池获取连接
+            es_conn = self.es_pool.get_connection()
+            try:
+                # 确保索引存在，如果不存在则创建
+                es_conn.index(index="student_info", id=doc_id, document=doc)
+                logger.info(f"学生 {user_id} 的信息已保存到ES: {info}")
+            finally:
+                # 释放连接回连接池
+                self.es_pool.release_connection(es_conn)
+        except Exception as e:
+            logger.error(f"保存学生信息到ES失败: {str(e)}", exc_info=True)
+
+    # 添加函数：从ES获取学生信息
+    def get_student_info_from_es(self,user_id):
+        """从Elasticsearch获取学生信息"""
+        try:
+            doc_id = f"student_{user_id}"
+            # 从连接池获取连接
+            es_conn = self.es_pool.get_connection()
+            try:
+                # 确保索引存在
+                if es_conn.indices.exists(index=Config.ES_CONFIG.get("student_info_index")):
+                    result = es_conn.get(index=Config.ES_CONFIG.get("student_info_index"), id=doc_id)
+                    if result and '_source' in result:
+                        logger.info(f"从ES获取到学生 {user_id} 的信息: {result['_source']['info']}")
+                        return result['_source']['info']
+                    else:
+                        logger.info(f"ES中没有找到学生 {user_id} 的信息")
+                else:
+                    logger.info("student_info索引不存在")
+            finally:
+                # 释放连接回连接池
+                self.es_pool.release_connection(es_conn)
+        except Exception as e:
+            # 如果文档不存在，返回空字典
+            if "not_found" in str(e).lower():
+                logger.info(f"学生 {user_id} 的信息在ES中不存在")
+                return {}
+            logger.error(f"从ES获取学生信息失败: {str(e)}", exc_info=True)
+        return {}
+
+    def extract_student_info(self,text, user_id):
+        """使用jieba分词提取学生信息"""
+        try:
+            # 提取年级信息
+            seg_list = jieba.cut(text, cut_all=False)  # 精确模式
+            seg_set = set(seg_list)
+
+            # 检查是否已有学生信息，如果没有则从ES加载
+            if user_id not in student_info:
+                # 从ES加载学生信息
+                info_from_es = self.get_student_info_from_es(user_id)
+                if info_from_es:
+                    student_info[user_id] = info_from_es
+                    logger.info(f"从ES加载用户 {user_id} 的信息: {info_from_es}")
+                else:
+                    student_info[user_id] = {}
+
+            # 提取并更新年级信息
+            grade_found = False
+            for grade, keywords in GRADE_KEYWORDS.items():
+                for keyword in keywords:
+                    if keyword in seg_set:
+                        if 'grade' not in student_info[user_id] or student_info[user_id]['grade'] != grade:
+                            student_info[user_id]['grade'] = grade
+                            logger.info(f"提取到用户 {user_id} 的年级信息: {grade}")
+                            # 保存到ES
+                            self.save_student_info_to_es(user_id, student_info[user_id])
+                        grade_found = True
+                        break
+                if grade_found:
+                    break
+
+            # 如果文本中明确提到年级，但没有匹配到关键词，尝试直接提取数字
+            if not grade_found:
+                import re
+                # 匹配"我是X年级"格式
+                match = re.search(r'我是(\d+)年级', text)
+                if match:
+                    grade_num = match.group(1)
+                    grade = f"{grade_num}年级"
+                    if 'grade' not in student_info[user_id] or student_info[user_id]['grade'] != grade:
+                        student_info[user_id]['grade'] = grade
+                        logger.info(f"通过正则提取到用户 {user_id} 的年级信息: {grade}")
+                        # 保存到ES
+                        self.save_student_info_to_es(user_id, student_info[user_id])
+        except Exception as e:
+            logger.error(f"提取学生信息失败: {str(e)}", exc_info=True)
+
+
+
diff --git a/dsSchoolBuddy/ElasticSearch/Utils/__pycache__/EsSearchUtil.cpython-310.pyc b/dsSchoolBuddy/ElasticSearch/Utils/__pycache__/EsSearchUtil.cpython-310.pyc
index e09d9fc754fdc8343d4c89047cbf3fbb57895eb2..c2e277831a8d13cea18e7eb427ee7a15ca6d5bf2 100644
GIT binary patch
delta 5816
zcma)Adu$v>8Q<C0?Y+;BI8Ndw7dNkq>pW;ln@3I3#<XdQ)5Zy*OUm_fv$oIKyK`sv
zoY<^;EeVMOO-s6I71~6#p@fzaHPnTsrELTPAtXTJC8Xsc5IH9me<4xveth5T*}k|&
zU~7N(%{TLX^UcinnB6~T|MAIKF&YgC@V7qpLf<iZD%L{YI@PwJOiWc*sX#?Dkk@pL
z2tZ3_Fdx!GoR-aSKB7lBt(eh#OpkF|HRJh&p5S!AtjpKwb)44B`h0`lkZ;r*^Yiq1
zL@>x$lQDms=*>p+*aCy}FB~UCxJ#fx8agVdG;~DN7oGaeSISW^ZYw<2Lqre^K_^tu
z#hjo^@W_-<u~(!Ll>rs10tR{s)!+%j6XLyL-W%b)QQ*eliNljP8_^Y72kWe-4Mzn%
zK)2F)wCO0(HM)(?r_DeG%k&PqkS+o;MDL`FjWAteL}(J8rAD+zqpkGDqlz8_(PhxL
z+=v1{-lNhLbS3Z;bQN%Mq)bzE^-)=`<D51=E(+srqV2$~hY8mJZ*5htO4rf#Am2dC
z+bIsd*@)Anv=Ibup&x{fM!Lb6XTS~`%{}4*VSzwzoz-4C)i%OC5{>}b+vrA^YysUw
zH^X`t(k=9M_+3Oh=!f99g*J8zsZKA_X>}VJmhIbX=gjhZLD>8&mmaOW@!Hilzg$wG
zRT(`848P;e$7glC`FK_0#H@}>CwNEYx##?js{HAiR^`(dYFbw=9jUxg##w#APrqE-
z`Np|w3oUy0<uho}6bUv=k(W-SA}j(!7&;P*A;b|92z3bc2n`602=fq{5at6Y?_zjN
zJTG1)@kPjNLAU|HbDx$^kfggrS*YCz?Uw|Wa<?ga$l8f#ln14d7bsZ<OXsNP{!?os
zo|_7;AZy(Fg15J=K^^S?Dai{O`2z-}xk9fO@&yV5C7W$Tjf8D*F9lbT4HLf$S|qs~
zcwVg6u+!OMp<ra~T(Q8Cz+@{BR=RdLr>;UW>Ha>vESW-*!)l<sI5Q5EawbjZGXn!K
zU#Gh=^0=6l+#e~;?oT2|8<RLn$!F|rAKMIcN`m?Oqc@dtVzw1~Rf~HD!v(Xu5bj3c
z^Y1|F9)Og}xE1#!V>iN108eFxRWfbXg`8Qog>B=oo%WTVhJI@?KuDB{ENWz8UhD;u
zn9-I*1s(49<IC>p26Ae;>6sV~^)#4npjd!2m}|ngWtgyo>5OTnX~xc+cW+JXBI_oO
zC*C3IgE+w_+@1A(x1gOV!ZP?Hdg7XOo?;D{IeYd3LR-w7WoL`|fsS9gSL-t^ooIt(
z8iiEA-;H&sw5pjlEKkhZfu^S#n#gzEiw$>?jT3)qsEGVHy7Wk|Q7~A>Oydsy&HZE3
zqQ#zeAY&Qn5;MI(W+0b7XbcT2CA+8nwwFXWvDNdprEWueW$s1%D7~Pa%Nv%R$q%qi
z(DxD?E!s2So}S-IcDk?6zcW02%B;^-nvbb>;($)~RP($}9P6oOF`F^1nPX4I{gvf#
zAUZ57A>d(ix77Vp&GwZF2Q9|jKQy;)z{x#{7PE7nN>dKc%TAlcLN8x%+AgLI>(}m`
z3mzr+yWd&xTY3-_z?LdFNdRFO;gbj$^UMLz!#t?c50?x!1lus<jYpu@i*tT@I`C$n
zWrMqIQ3L6iXj#-Rk<IS$#Xn!Z4CG*QvpB<XgzHa_8OU=VThgJLNZs##cS)w@vq<9B
z=@5FRF_<Z2jkJ|5GJ`$k-jTeo{Yf0~IRqC09e*yxr=aq&r`^lR{HFg?;#n>M>bg>O
z3_X#JxIIhPlOFfX(j93p!7@2;pq?U2gG<;Yi{bisD8u-f-Qo*)2D<d<V8+bRv>(A1
zJBq_`AM`LRCQ~@bV~CwWw(f3i-JIHs<XnLls|r+Ab-ORLeu|u!Sb5{$3HNwCVr5xw
z0FnXUsE@fDmUp#21ll}xAj2|wD<%5zt@`8G12|KMdw%(`nLOot#vu0WLEu}^gVc1+
zN@@N=PayY2glWHJIyU*@=UPF+PgCgwL+L?CAw_l;cH7ztRpR9p_etbo_aCVn!cU=!
zQwS&BWvkl~PXIYAwYRsk$C0_&O|RZYHoD`hH<o9N8^Nw;0X)Sn4VZ?1EYBhLZUmlO
zL%!YIybH+Xhw&w(_@<u+$_qe+u#JLWN9H_-IL$#K%M7J4PeNL@ems$B`<DpjKeVQO
z)x)R`eLO`xa(I?gdfFB<lRrQ+9Vz$gYwj(d#Tiwr$ZUgpDtJoCuu@esCs5IA0D2fx
z?UV!Y7(z?+SgDYMc%1He2nCMu9$({h&-EeaMe_#hMY#YsKQ6k**WO;vN+3G*7XSjw
zH)b;H8vw(bDRIbi!Z~q7a)=|^!Wi5j0mX4)9PW{4r4iW?`lT^>To_S?Z*Y`;h02cP
z$W%Eg5y4i+0#ro}G~kG!N5)(0K7q?<jxt{6O&ac=VFBlmAPaVINGHOGN`&DCTkQ`~
z%?>;25pE1#dQXa|=mCL-N7P4D)ZkNx$RQyWDJ=)<D;JMdE}Xx5`uQuD$0r|q<;vxA
zl?!JoqZd2PjAiGt=$7SdpQl-NiNe{ZSw9Ft5&r=Eu$2IMxHJI8&PZc1U^gM#0(cMi
z$=94LEd)Aw_1UBT9F^B!otdV4Q?j%Kx~rTTQ_zU+$_rn+R(|bEo05B8BA#X(&ZcvP
zo?;i=zYc*AJB%=dfNSB`3BLxdz$ThE6P#=ZHo3c3tLO9@xNq>>;{^<h--K%XyUd+r
zHAs8&t;`^#+v;ARDSk0&7pvC`Q4EQqB$60W{~1z6k`S9oQi_okM0-^H_wcgXYw()?
zqAUx_rvFqyaDSzQ%3Y8Th6~f4CW3c>pMgh7!}}enU+kA`xnCJmsW?ukbds=Lz*T2>
zj!5N`B6y<AI;rBwgOI@Nz?e4edEkw3<JT4lQyz%^>2tsr%Q#)ok$l(e7Px4TJ8kG3
z=N96e7oK+Bn(;ZI+jr<$JidskR_@QCq4VI+3i$I)Gy=Y?93f+oabZv>vnRRwD4#Os
zPniRyD!O-kM0rF(qxz#X;frBB(mGl{9Rhp|8sd-UA<$52g^j-Q%_nNSJ==HfiPtMn
zK2sYN?Cmm)^XjiV_*{V+huIeBU_}JX!KHZssIR-KWb|S+2HuN6&rA$#N^<WkH3PS^
z`^u#Yldq0Xo;@*n;vI1Nsjvynh?F5VOZcu(Yr@snzEFAV=_{8`V#uC-(F+!eHWc7e
zfwFgCC?7vFC5+%RO^@&L1Fy!~+USG8<8j9>gQ`?HRuf@&0Ec1zt0{@R*v}Pp7;v6q
z77rPWN8r@Wng<`|WcDqD|61Fd@!iBK*M?jVE9T(_*NH)Q3kXBd5ePfdBsP%<Sqx7i
z(D?U=7?b3H_@|g62V#GXK`7Rf1ZgEQhT`9bmtPl(e3Cilm`eS4{(=yL2M>kk{)-rq
zmu#UQvOj(^fasEJ(UFc2h%(WZ1_^6(gfXDU$%x`8Y^9^vk|S;rY>ZQ&Amhu9G8JzH
zIVbr2l#Hn8?c>6B;lVBY#gV{BS#vaKtRD$FK_0w)lq*{x3=(T6ib1GCxH^G@5~EIF
zic_6T<&y=Rz|>@5SP+dwxpAlxRKqG#AP?W_s4UN^^^R&?#42KjMnYvLG!~{|hm4CO
zVJFNcobXtLMqp(TCj#q;LiG#Om~?u|fT~H~c%MnJ|7FrXfrc<`a4gp}pzcM7egSzR
z%IlueAER+Q?nJ9~Pos(Hpbw2iABmy@$|)Z7b)_5O2(P?-`ReHx`*X&DOl9=gwO39~
zKKZ#>QU77Mrv$Pk{ytYO)uRx`O64<S*WP{`geON|PqOa-o81ghN&r-qj9#pEb14i#
z|GR=;|Dc#L@ExJ6REHv?rzX$5vT8qVOZkHs-jn=qBL3$Q{5nv6_t9ssT|Pc};fs~g
z&%bXLtgr94A8RLuuphw*PvNWeBv_IsS%&Qw>+gYV^<5t*FLu}NZQDE3J3AlPw`=$I
zZcoYCM&4rOZ)2wj_iViTdP*-VmInL_<V;zO`L{^^Qi|aXw+5p(jqk8}04bQ$i}0dZ
zjbJ_8%Q6&S8Zc+!E_xcgcpfS;YO%G@WIsZ<57sZ}L4Rzal&`7HGo`r^US(MZ-o9%y
zWCl|Nh(n5q!Arj;;p@Lfnu#XLQUWNAv_QIOg5&_71&H`pSp)pHENdhJ97rqG{=H42
z`kpGQQcS6q@}<}1kGUpKkuG@4#|#fY`|w9(`*A&Z_$jg{b%Q&(c3IhLgnRX%!K@5^
zdr9}fb`{x>e>gvYkzV~rwtXyp_m1v8yLLa2-o0yY*Y<AKhI)1(d=%m12t3nDxq|J<
zxaX`7n4Wx~STxxv_J0Q9%LrdZcojht+`a1>_q~NQ9x>zY@KdDt*3Q6c<b?s6;ITRY
zG(m=4giRqT>>d6iHBJ9XPPnJmHQv0XLtCshM_RaWs)c<4M7@An?Cpi`MQkaw*dqx1
zLic^7o_Bw^?g{v~wSWDF-k%`@>k2xPeXlWSn4Y|&>%+Uay19&mH;H_amQ14q_t|O%
Z&;&eb{tsRd5hHNs{(mDBjtHrj{sSOFJtP1C

delta 2660
zcma)8YiwLc6~42NyD#t4yY{ZVsUNWu->jWFf`o?J#-Wcir8rTOC}n7Ld%ZJWZ*w1;
zxp&jVDL4vlM5U-C9Z?}#q?VVcKp?S|`VUd@6Obw-_;G*nrz-s5SA>uNA<mg~>=5|}
zyV~!bIdjgL^O|$_-`D@q%z4>tT7%E0nIEpdwsJRDCm-Bx9NUc8x|5&@qA`s{?WB{U
zDMiQZw3DG3MaS&{Crh)6*6o~=r+Gyu?1EFE1w|+AqEn(JXOIp$Wm+a0C+}AH(0haq
z^Wk@^oV;9nj}Yyo#!@W3rLpukB6Nh2yMOt~Cc3o@KmVTqT%&|(G{OjrY-u#g4zU=E
zZxI?}4VGX@pyF(nrCA0joz1ZvPp~{svI6{yJhhf&B{sMfr)khE!(N4_fS*~@*$^8B
z{s5~27bRn?#zwYcn>4Ffqe?IZf_1iUD@Jp0;3L2r+cvDTaW(-4^6W4}+5J4jiYyB9
zQ*0Xe1$KZJd5I75@>-;()iieSp>^^8nkUwxC;_@NtY*Mr6&5|K8IOhoPx)uLC7SE!
zgSOo(#6BhY9Ari05efiQ>iX-XB=6`W$qKCB*Tks&rGAc7dWpovXqqOvJ{M-2QR$`|
zgv#%x50G*BQF^g4jyA>sjA)qR&MIfD?Y6>nU%~Bk12KcUL`+K~Gef3(&u4rxJ`B7t
z*W!WM^jw!WgSO|2656UF)Z`}vZG8mEl02848XrYcK^>?tFZgP=Z8OucIvqH#A-|Ko
zo%kyjy&08XNL1xgZmW#;!nk7v&2@1IXd?<v{3$o<;pyTq?&`iujKHYHQG{a%%8Ab*
z^%#Jm3+2i(GEN{I2MBe+{jME|1>`*BU?$*K1G8^@qjx#~0Vyn_n9^2p&dQ_3sb{|k
z%=_kdEDID3lVHB%xsdq14#@l5hP0WMZJW#rtlRPj#nWW6cdz&>qCba6eOZ1uxc*u6
z3zB~ZACWL}cs`8#9lISo>~MO)Zu>#gb2>{O$+Kmv{u%TkYID~}^rN3dquZ80E>CA3
zi1^LQDEX<ZS5A_d9;<v3QJG(%11;`yVc8}oV?$o7jy^(@tCr8ruCQss>a@*E{Mtsm
z8?4PeW<;PkZ&gni2hr7->KawGFcq{N?gy6B5eDu-715QizFC_j$L0Ro6PcZQiVN~`
z?bb_2a32GpdDW68^O{|UyMeD%L*4e8mhJBr+{pK1d;t})UxkT)Wma8D`}J(Dcil_A
zxF|1-OddmD!YEkYvpz#@tXyE)p4(FKn}KI?|2Og%BR9yhoFD!3#8<!oBsY$SBoG(^
zN6-=0<dOPdX1DVkdAeSCFzwQ-SIJcGoAsBY<dD2K_Q&ZV(0e~3o=5e|2oDqqm*)Up
zkbfIr(kU*N<&g=i-bE5qO5s}B{EFo^x#>4O!Nsfc=M!h<uA#sN!q*VKj<AQ}R|xPo
zWn<F${Qs$OLur7y6{D!?C0g<ilSjyT8QXu#qy=HMp;^{EVM6(Xt}ie?bwfdZH!&)J
z8?Z&QS1h~D%>Kpng^S{t2bzIkEccSSD&i)xPsyL{f82Ny$-VAZZd+m7)Nxsux=H+=
zocb40-AxDlrf7HIj;lnSl;1zFGI<)Tg?h&lmg7S|FRNu=PCSDr&C1fjTbsM>s>=Qn
z?mU5jEi29=?2IBK*$>o5?p=hPrWB`ese<1tf<k}#n5);!D=;ZMaTBubFKb$Fc;-x$
zyeQWj`!cVhiR%cj$UBWj;VO_D(Yd)faRr%&<Zl}%$c)U+9^c$`u7z7$0AW1nc5L1+
z%WKG0(^JjNbl-2~-dnh(itz?gD(T-s{RB+^0Pbb~&g~UNp0#0KS=US)hcIpZ4|~6#
z{Z9nk|J|c=GcTe!Y(;~F<my9B873EO%UNaCQeIBXKSyp!cYbI=waq)I_dNib!2x=|
zU(}UB$7rtWwl8=2&JI>qbmXt+%VYoB`C-=KqO~LVcOvi2FHRa{1%~btD8b`td_=^T
z&;*nKSm%r(dHwOJO|cJoiwI94Jd1$Y3!`l}2xB;s#RXi)Rz1%a0`~)iI|$!KcpD*!
zkV3#$U>IMsJu47DLdLGUimD?o15nnqCpEtcR8mWl^icYAx>O&lR!i1UrFyD*ba_dM
z8KdGh$b<>oYqj7_D+bZPI)a7py8L+I4fsc3E*{f=jEt&$d$IQP9;ZS%9FKKvzJy8e
W#{ux<?QditGC=Ns%Onk}QslqO>R!G8

diff --git a/dsSchoolBuddy/Start.py b/dsSchoolBuddy/Start.py
index 47f80c7f..d2c9d485 100644
--- a/dsSchoolBuddy/Start.py
+++ b/dsSchoolBuddy/Start.py
@@ -29,134 +29,6 @@ client = AsyncOpenAI(
 # 初始化 ElasticSearch 工具
 search_util = EsSearchUtil(Config.ES_CONFIG)
 
-# 存储对话历史的字典，键为会话ID，值为对话历史列表
-conversation_history = {}
-
-# 存储学生信息的字典，键为用户ID，值为学生信息
-student_info = {}
-
-# 年级关键词词典
-GRADE_KEYWORDS = {
-    '一年级': ['一年级', '初一'],
-    '二年级': ['二年级', '初二'],
-    '三年级': ['三年级', '初三'],
-    '四年级': ['四年级'],
-    '五年级': ['五年级'],
-    '六年级': ['六年级'],
-    '七年级': ['七年级', '初一'],
-    '八年级': ['八年级', '初二'],
-    '九年级': ['九年级', '初三'],
-    '高一': ['高一'],
-    '高二': ['高二'],
-    '高三': ['高三']
-}
-
-# 最大对话历史轮数
-MAX_HISTORY_ROUNDS = 10
-
-
-# 添加函数：保存学生信息到ES
-def save_student_info_to_es(user_id, info):
-    """将学生信息保存到Elasticsearch"""
-    try:
-        # 使用用户ID作为文档ID
-        doc_id = f"student_{user_id}"
-        # 准备文档内容
-        doc = {
-            "user_id": user_id,
-            "info": info,
-            "update_time": time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
-        }
-        # 从连接池获取连接
-        es_conn = search_util.es_pool.get_connection()
-        try:
-            # 确保索引存在，如果不存在则创建
-            es_conn.index(index="student_info", id=doc_id, document=doc)
-            logger.info(f"学生 {user_id} 的信息已保存到ES: {info}")
-        finally:
-            # 释放连接回连接池
-            search_util.es_pool.release_connection(es_conn)
-    except Exception as e:
-        logger.error(f"保存学生信息到ES失败: {str(e)}", exc_info=True)
-
-# 添加函数：从ES获取学生信息
-def get_student_info_from_es(user_id):
-    """从Elasticsearch获取学生信息"""
-    try:
-        doc_id = f"student_{user_id}"
-        # 从连接池获取连接
-        es_conn = search_util.es_pool.get_connection()
-        try:
-            # 确保索引存在
-            if es_conn.indices.exists(index=Config.ES_CONFIG.get("student_info_index")):
-                result = es_conn.get(index=Config.ES_CONFIG.get("student_info_index"), id=doc_id)
-                if result and '_source' in result:
-                    logger.info(f"从ES获取到学生 {user_id} 的信息: {result['_source']['info']}")
-                    return result['_source']['info']
-                else:
-                    logger.info(f"ES中没有找到学生 {user_id} 的信息")
-            else:
-                logger.info("student_info索引不存在")
-        finally:
-            # 释放连接回连接池
-            search_util.es_pool.release_connection(es_conn)
-    except Exception as e:
-        # 如果文档不存在，返回空字典
-        if "not_found" in str(e).lower():
-            logger.info(f"学生 {user_id} 的信息在ES中不存在")
-            return {}
-        logger.error(f"从ES获取学生信息失败: {str(e)}", exc_info=True)
-    return {}
-
-
-def extract_student_info(text, user_id):
-    """使用jieba分词提取学生信息"""
-    try:
-        # 提取年级信息
-        seg_list = jieba.cut(text, cut_all=False)  # 精确模式
-        seg_set = set(seg_list)
-
-        # 检查是否已有学生信息，如果没有则从ES加载
-        if user_id not in student_info:
-            # 从ES加载学生信息
-            info_from_es = get_student_info_from_es(user_id)
-            if info_from_es:
-                student_info[user_id] = info_from_es
-                logger.info(f"从ES加载用户 {user_id} 的信息: {info_from_es}")
-            else:
-                student_info[user_id] = {}
-
-        # 提取并更新年级信息
-        grade_found = False
-        for grade, keywords in GRADE_KEYWORDS.items():
-            for keyword in keywords:
-                if keyword in seg_set:
-                    if 'grade' not in student_info[user_id] or student_info[user_id]['grade'] != grade:
-                        student_info[user_id]['grade'] = grade
-                        logger.info(f"提取到用户 {user_id} 的年级信息: {grade}")
-                        # 保存到ES
-                        save_student_info_to_es(user_id, student_info[user_id])
-                    grade_found = True
-                    break
-            if grade_found:
-                break
-
-        # 如果文本中明确提到年级，但没有匹配到关键词，尝试直接提取数字
-        if not grade_found:
-            import re
-            # 匹配"我是X年级"格式
-            match = re.search(r'我是(\d+)年级', text)
-            if match:
-                grade_num = match.group(1)
-                grade = f"{grade_num}年级"
-                if 'grade' not in student_info[user_id] or student_info[user_id]['grade'] != grade:
-                    student_info[user_id]['grade'] = grade
-                    logger.info(f"通过正则提取到用户 {user_id} 的年级信息: {grade}")
-                    # 保存到ES
-                    save_student_info_to_es(user_id, student_info[user_id])
-    except Exception as e:
-        logger.error(f"提取学生信息失败: {str(e)}", exc_info=True)
-
 
 def get_system_prompt():
     """获取系统提示"""
@@ -195,24 +67,24 @@ async def chat(request: fastapi.Request):
             raise HTTPException(status_code=400, detail="查询内容不能为空")
 
         # 1. 初始化会话历史和学生信息
-        if session_id not in conversation_history:
-            conversation_history[session_id] = []
+        if session_id not in search_util.conversation_history:
+            search_util.conversation_history[session_id] = []
 
         # 检查是否已有学生信息，如果没有则从ES加载
-        if user_id not in student_info:
+        if user_id not in search_util.student_info:
             # 从ES加载学生信息
-            info_from_es = get_student_info_from_es(user_id)
+            info_from_es = search_util.get_student_info_from_es(user_id)
             if info_from_es:
-                student_info[user_id] = info_from_es
+                search_util.student_info[user_id] = info_from_es
                 logger.info(f"从ES加载用户 {user_id} 的信息: {info_from_es}")
             else:
-                student_info[user_id] = {}
+                search_util.student_info[user_id] = {}
 
         # 2. 使用jieba分词提取学生信息
-        extract_student_info(query, user_id)
+        search_util.extract_student_info(query, user_id)
 
         # 输出调试信息
-        logger.info(f"当前学生信息: {student_info.get(user_id, {})}")
+        logger.info(f"当前学生信息: {search_util.student_info.get(user_id, {})}")
 
         # 为用户查询生成标签并存储到ES
         current_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
@@ -239,9 +111,9 @@ async def chat(request: fastapi.Request):
 
         # 3. 构建对话历史上下文
         history_context = ""
-        if include_history and session_id in conversation_history:
+        if include_history and session_id in search_util.conversation_history:
             # 获取最近的几次对话历史
-            recent_history = conversation_history[session_id][-MAX_HISTORY_ROUNDS:]
+            recent_history = search_util.conversation_history[session_id][-search_util.MAX_HISTORY_ROUNDS:]
             if recent_history:
                 history_context = "\n\n以下是最近的对话历史，可供参考：\n"
                 for i, (user_msg, ai_msg) in enumerate(recent_history, 1):
@@ -250,9 +122,9 @@ async def chat(request: fastapi.Request):
 
         # 4. 构建学生信息上下文
         student_context = ""
-        if user_id in student_info and student_info[user_id]:
+        if user_id in search_util.student_info and search_util.student_info[user_id]:
             student_context = "\n\n学生基础信息：\n"
-            for key, value in student_info[user_id].items():
+            for key, value in search_util.student_info[user_id].items():
                 if key == 'grade':
                     student_context += f"- 年级: {value}\n"
                 else:
@@ -262,9 +134,9 @@ async def chat(request: fastapi.Request):
         system_prompt = get_system_prompt()
 
         # 添加学生信息到系统提示词
-        if user_id in student_info and student_info[user_id]:
+        if user_id in search_util.student_info and search_util.student_info[user_id]:
             student_info_str = "\n\n学生基础信息:\n"
-            for key, value in student_info[user_id].items():
+            for key, value in search_util.student_info[user_id].items():
                 if key == 'grade':
                     student_info_str += f"- 年级: {value}\n"
                 else:
@@ -305,7 +177,7 @@ async def chat(request: fastapi.Request):
                 # 保存回答到ES和对话历史
                 if full_answer:
                     answer_text = ''.join(full_answer)
-                    extract_student_info(answer_text, user_id)
+                    search_util.extract_student_info(answer_text, user_id)
                     try:
                         # 为回答添加标签
                         answer_tags = [f"{user_id}_answer", f"time:{current_time.split()[0]}", f"session:{session_id}"]
@@ -321,10 +193,10 @@ async def chat(request: fastapi.Request):
                         logger.info(f"用户 {user_id} 的回答已存储到ES")
 
                         # 更新对话历史
-                        conversation_history[session_id].append((query, answer_text))
+                        search_util.conversation_history[session_id].append((query, answer_text))
                         # 保持历史记录不超过最大轮数
-                        if len(conversation_history[session_id]) > MAX_HISTORY_ROUNDS:
-                            conversation_history[session_id].pop(0)
+                        if len(search_util.conversation_history[session_id]) > search_util.MAX_HISTORY_ROUNDS:
+                            search_util.conversation_history[session_id].pop(0)
 
                     except Exception as e:
                         logger.error(f"存储回答到ES失败: {str(e)}")