v1.2.3 底部快捷问题AI预测：对话进行中由大模型预测用户可能追问的问题(每个≤30字)，个数后台可配(默认3，1-6)，异步刷新防串扰；初始与开场白一致

admin.py

@@ -52,6 +52,8 @@ DEFAULT_CONFIG = {
     ], ensure_ascii=False),
     "footer_text": "NBA球迷大全 · 数据为模拟演示数据（2025-26 赛季） · LLM: DeepSeek · 向量: Chroma + bge-large-zh",
     "admin_password": "admin123",
+    "entity_mark_mode": "first",   # 实体标记：first=只标记首次出现 / all=全部标记
+    "suggestion_count": "3",       # 对话中底部快捷问题预测个数（默认3）
 }
 
 SEARCHABLE = {  # 每个表可搜索的 TEXT 字段

api.py

@@ -64,6 +64,22 @@ def boot():
     return jsonify(chat.boot_info())
 
 
+@app.route("/api/suggest", methods=["POST"])
+def api_suggest():
+    """基于对话历史预测底部快捷问题（个数后台可配，默认3）"""
+    body = request.get_json(force=True, silent=True) or {}
+    history = body.get("history") or []
+    try:
+        n = int(admin_mod.get_config().get("suggestion_count", "3") or "3")
+    except Exception:
+        n = 3
+    try:
+        return jsonify({"suggestions": chat.predict_suggestions(history, n)})
+    except Exception as e:
+        log.exception("suggest error")
+        return jsonify({"suggestions": chat.suggest_questions()[:n]}), 200
+
+
 # ------------------------------------------------------------------ 对话
 @app.route("/api/chat", methods=["POST"])
 def api_chat():
@@ -78,7 +94,8 @@ def api_chat():
         game_refs = [it for s in sources
                      if s.get("tool") in ("search_games", "get_game_detail")
                      for it in s.get("items", [])]
-        spans, cards = entity_linker.link_entities(reply, game_refs=game_refs)
+        mark_mode = admin_mod.get_config().get("entity_mark_mode", "first")
+        spans, cards = entity_linker.link_entities(reply, game_refs=game_refs, mark_mode=mark_mode)
         return jsonify({"reply": reply, "sources": sources, "used_tools": used_tools,
                         "news_refs": news_refs, "entities": spans, "cards": cards})
     except Exception as e:

chat.py

@@ -272,3 +272,53 @@ def boot_info():
         "suggestions": suggest_questions(),
         "footer_text": cfg.get("footer_text", "NBA球迷大全 · 数据为模拟演示数据（2025-26 赛季）"),
     }
+
+
+def _parse_json_array(text):
+    """从 LLM 输出中解析 JSON 数组（容错：直接 JSON / 提取中括号段）"""
+    if not text:
+        return []
+    text = text.strip()
+    try:
+        arr = json.loads(text)
+        if isinstance(arr, list):
+            return arr
+    except Exception:
+        pass
+    m = re.search(r"\[.*\]", text, re.S)
+    if m:
+        try:
+            arr = json.loads(m.group(0))
+            if isinstance(arr, list):
+                return arr
+        except Exception:
+            pass
+    return []
+
+
+def predict_suggestions(history=None, n=3):
+    """基于对话历史，让大模型预测用户接下来最可能追问的 n 个问题（底部快捷语句）。
+    每个问题不超过 30 字；LLM 异常时回退到默认快捷问题。"""
+    n = max(1, min(int(n or 3), 6))
+    history = history or []
+    msgs = [{"role": "system", "content": (
+        f"你是「NBA球迷大全」智能助手。根据对话历史，站在用户角度预测他接下来最可能追问的{n}个问题。\n"
+        "要求：\n"
+        "1. 每个问题不超过30个汉字，简洁口语化\n"
+        "2. 必须是用户会直接发送的提问，不要编号、不要引号、不要解释\n"
+        "3. 只输出JSON数组，例如：[\"库里今天拿了几分\",\"湖人下一场什么时候\"]，不要输出任何其他内容")}]
+    for h in history[-6:]:
+        msgs.append({"role": "user", "content": h.get("user", "")})
+        if h.get("assistant"):
+            msgs.append({"role": "assistant", "content": str(h["assistant"])[:600]})
+    if len(msgs) == 1:
+        return DEFAULT_SUGGESTIONS[:n]
+    try:
+        resp = llm.chat(msgs, temperature=0.9, max_tokens=200)
+        arr = _parse_json_array(llm.parse_content(resp))
+        out = [str(x).strip()[:30] for x in arr if str(x).strip()][:n]
+        if out:
+            return out
+    except Exception as e:
+        log.warning("快捷问题预测失败(%s)，回退默认", e)
+    return DEFAULT_SUGGESTIONS[:n]

entity_linker.py

@@ -164,13 +164,23 @@ def _match_games(text, game_refs):
     return cards
 
 
-def link_entities(text, game_refs=None):
+def link_entities(text, game_refs=None, mark_mode="first"):
     """主入口：扫描回答文本。
     返回 (spans, cards)
       spans: 实体命中区间（前端高亮标记用），按 start 升序、互不重叠
+             mark_mode="first" 时同一实体(type,id)只保留首次出现；"all" 时全部标记
       cards: 快速查看卡片数据（每类限量，避免刷屏）
     """
     spans = _find_spans(text or "")
+    if mark_mode == "first":
+        seen, kept = set(), []
+        for sp in spans:          # spans 已按 start 升序 → 保留首次
+            key = (sp["type"], sp["id"])
+            if key in seen:
+                continue
+            seen.add(key)
+            kept.append(sp)
+        spans = kept
     cards = []
     seen_cards = set()
     for sp in spans:

static/admin.html

@@ -157,8 +157,17 @@ td.num { text-align:center; }
           <textarea id="cfg-suggestions" style="min-height:160px"></textarea>
           <div class="tip">💡 一行一个问题。保存后刷新前台页面即可看到新的快捷问题。</div>
         </div>
+        <div class="row2">
+          <div><label>对话中底部快捷问题预测个数（默认3，范围1-6）</label><input type="number" id="cfg-suggestion_count" min="1" max="6">
+          <div class="tip">对话进行中，大模型根据上下文预测用户可能追问的问题数量（每个≤30字）</div></div>
+        </div>
         <div class="row2">
           <div><label>管理员密码（留空则不修改）</label><input type="password" id="cfg-admin_password" placeholder="••••••"></div>
+          <div><label>实体标记模式</label><select id="cfg-entity_mark_mode">
+            <option value="first">只标记首次出现（推荐）</option>
+            <option value="all">全部标记</option>
+          </select>
+          <div class="tip">对话回答中球队/球员/人物等特殊标记策略</div></div>
         </div>
         <div class="form-actions">
           <button class="btn" id="cfg-save">💾 保存配置</button>

static/admin.js

@@ -207,6 +207,8 @@ async function loadConfig() {
   $("#cfg-welcome_hint").value = d.welcome_hint || "";
   $("#cfg-footer_text").value = d.footer_text || "";
   $("#cfg-admin_password").value = "";
+  $("#cfg-entity_mark_mode").value = d.entity_mark_mode === "all" ? "all" : "first";
+  $("#cfg-suggestion_count").value = d.suggestion_count || "3";
   try { $("#cfg-suggestions").value = JSON.parse(d.suggestions || "[]").join("\n"); }
   catch (e) { $("#cfg-suggestions").value = ""; }
   $("#cfg-msg").textContent = "";
@@ -222,6 +224,8 @@ $("#cfg-save").addEventListener("click", async () => {
   };
   const pw = $("#cfg-admin_password").value;
   if (pw) payload.admin_password = pw;
+  payload.entity_mark_mode = $("#cfg-entity_mark_mode").value;
+  payload.suggestion_count = String(Math.min(6, Math.max(1, parseInt($("#cfg-suggestion_count").value || "3"))));
   try {
     await api("/api/admin/config", { method: "PUT", body: JSON.stringify(payload) });
     $("#cfg-msg").textContent = "✅ 保存成功，前台刷新后生效";

static/app.js

@@ -122,6 +122,9 @@ async function sendChat(text) {
     addMsg("bot", html);
     chatHistory.push({ user: text, assistant: d.reply });
     if (chatHistory.length > 20) chatHistory.splice(0, chatHistory.length - 20);
+    // 大模型预测下一轮快捷问题（异步刷新底部 chips）
+    const mark = chatHistory.length;
+    refreshChips(mark);
   } catch (e) {
     typing.remove();
     addMsg("bot", "⚠️ 网络异常，请稍后再试。");
@@ -139,6 +142,19 @@ function askQuick(q) {
   sendChat(q);
 }
 
+/* 底部快捷问题：对话进行中由大模型预测用户可能追问的问题（异步刷新） */
+async function refreshChips(mark) {
+  try {
+    const r = await fetch("/api/suggest", { method: "POST", headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ history: chatHistory.slice(-6) }) });
+    const d = await r.json();
+    if (!d.suggestions || !d.suggestions.length) return;
+    if (mark !== chatHistory.length) return;   // 期间用户又发了新消息 → 丢弃过期预测
+    $("#chips").innerHTML = d.suggestions.map((q) => `<button>${esc(q)}</button>`).join("");
+    $$("#chips button").forEach((b) => b.addEventListener("click", () => askQuick(b.textContent)));
+  } catch (e) {}
+}
+
 /* 聊天区事件委托：快捷语句 / 实体标记 / 新闻链接 / 卡片 */
 $("#chat-list").addEventListener("click", (e) => {
   const q = e.target.closest(".quick-q");

static/index.html

@@ -25,7 +25,6 @@
     <button class="tab" data-view="persons">👥 人物</button>
     <button class="tab" data-view="standings">🏆 排名</button>
   </nav>
-  <a class="admin-link" href="/admin" title="管理后台">⚙️</a>
 </header>
 
 <main>