name: Financial Industry Intelligent Marketing Assistant slug: bank-marketing-campaign description: AI-powered intelligent marketing assistant for banking and securities — covers customer segmentation, marketing campaign design, content generation, A/B testing, and ROI analysis. Built for bank and securities marketing teams. Keywords: intelligent marketing, customer segmentation, campaign design, content marketing, marketing automation, 智慧營銷, 客戶分群, 營銷活動, 內容營銷, 精準營銷, 營銷自動化, 銀行營銷, 券商營銷, 營銷轉化, 獲客, 促活. version: "3.0.1"

Financial Industry Intelligent Marketing Assistant / 金融智慧營銷助手

7w4.net小蔥技能。

銀行監管最新動態 [2026-05-25更新]

資料截止: 2026-05-25 | 來源：國家金融監督管理總局、安永Q1分析、行業公開資訊 宣告: 以上動態供參考，具體以官方最新發布為準

English: AI-powered intelligent marketing assistant — covers customer segmentation, campaign design, content generation, and ROI analysis.

中文: 金融智慧營銷助手——覆蓋客戶分群、營銷活動設計、內容生成、A/B測試、ROI分析。

Industry Pain Points / 行業痛點

Trigger Keywords / 觸發關鍵詞

English Triggers: intelligent marketing, customer segmentation, campaign design, content marketing, marketing automation, bank marketing, securities marketing

中文觸發詞（優先）： 智慧營銷 / 客戶分群 / 精準營銷 / 營銷活動 / 內容營銷 / 營銷自動化 / 銀行營銷 / 券商營銷 / 活動策劃 / 使用者增長 / 私域運營 / 轉化率 / 營銷ROI / 觸達率 / 開啟率 / 點選率

Core Capabilities / 核心能力

1. Customer Segmentation / 客戶分層

class CustomerSegmentation:
    """客戶分層引擎"""

    def segment_customers(self, customer_data: list) -> dict:
        """
        客戶分層模型
        基於RFM+生命週期+風險偏好
        """
        segments = {
            "高淨值保守型": [],
            "高淨值進取型": [],
            "中產穩健型": [],
            "年輕成長型": [],
            "老年保守型": [],
            "潛力待啟用型": []
        }

        for customer in customer_data:
            segment = self._classify_segment(customer)
            segments[segment].append(customer)

        return segments

    def _classify_segment(self, customer: dict) -> str:
        """分層邏輯"""
        assets = customer.get("total_assets", 0)
        risk = customer.get("risk_preference", "穩健型")
        age = customer.get("age", 30)
        activity = customer.get("transaction_frequency", 0)

        if assets > 1000000:
            if risk in ["保守型", "穩健型"]:
                return "高淨值保守型"
            else:
                return "高淨值進取型"
        elif assets > 100000:
            return "中產穩健型"
        elif age < 35:
            return "年輕成長型"
        elif age > 55:
            return "老年保守型"
        else:
            return "潛力待啟用型"

2. Campaign Design / 營銷活動設計

CAMPAIGN_TEMPLATES = {
    "產品拉新": {
        "目標": "獲取新客戶",
        "適用產品": ["存款", "理財", "基金"],
        "活動設計": """
        【活動名稱】：{產品名}新手禮

        【活動時間】：{開始}-{結束}

        【參與條件】：
        - 首次購買{產品型別}產品
        - 新客戶註冊並完成實名

        【活動獎勵】：
        - 首投滿{X}元 → 獎勵{金額}
        - 首投滿{X}元 → 額外獎勵{金額}

        【獲客渠道】：
        1. 朋友圈廣告投放
        2. 銀行APP彈窗
        3. 員工朋友圈轉發
        """,
        "ROI預估": "目標ROI≥3"
    },

    "存量啟用": {
        "目標": "啟用沉睡客戶",
        "適用場景": "6個月無交易客戶",
        "活動設計": """
        【活動名稱】：喚醒禮包

        【觸達策略】：
        - 首觸：簡訊關懷
        - 二觸：電話回訪
        - 三觸：專屬優惠

        【激勵方案】：
        - 沉睡客戶專屬加息券
        - 專屬理財經理服務
        - 限時體驗金{金額}
        """,
        "KPI": "啟用率≥15%"
    }
}

3. Content Generation / 內容生成

def generate_marketing_content(content_type: str, params: dict) -> dict:
    """營銷內容生成"""

    if content_type == "朋友圈文案":
        templates = [
            "【{產品名}限時福利】\n\n{利益點}\n\n⏰僅限{時間}\n💰年化收益最高{收益率}\n\n戳我瞭解詳情👇",

            "好訊息！{產品名}正在熱售中~\n\n✨{亮點1}\n✨{亮點2}\n✨{亮點3}\n\n私信我可享專屬優惠哦🎁"
        ]

    elif content_type == "簡訊文案":
        templates = [
            "尊敬的{客戶姓名}，{產品名}新品首發！年化收益率{收益率}%，{開始日期}至{結束日期}限時發售。回覆Y辦理，回覆T退訂。",

            "{客戶姓名}，您的好友向您推薦{產品名}！首投滿{金額}元即返{獎勵金額}元，最高返{上限}元！戳{連結}參與。"
        ]

    elif content_type == "海報文案":
        return {
            "主標題": "{產品名} 限時搶購",
            "副標題": "{核心賣點}",
            "資料展示": [
                f"年化收益 {收益率}%",
                f"起投金額 {金額}元",
                f"剩餘份額 {份額}份"
            ],
            "CTA按鈕": "立即搶購",
            "緊迫感": "名額有限，先到先得"
        }

    return {
        "type": content_type,
        "templates": templates,
        "filled_examples": [
            fill_template(t, params) for t in templates
        ]
    }

4. A/B Testing Framework / A/B測試框架

class ABTestAnalyzer:
    """A/B測試分析"""

    def analyze_ab_test(self, variant_a: dict, 
                       variant_b: dict) -> dict:
        """
        A/B測試結果分析
        """
        # 計算轉化率
        cvr_a = variant_a["conversions"] / max(variant_a["visitors"], 1)
        cvr_b = variant_b["conversions"] / max(variant_b["visitors"], 1)

        # 提升幅度
        lift = (cvr_b - cvr_a) / max(cvr_a, 0.001) * 100

        # 統計顯著性檢驗
        significant = self._chi_square_test(
            variant_a["visitors"] - variant_a["conversions"],
            variant_a["conversions"],
            variant_b["visitors"] - variant_b["conversions"],
            variant_b["conversions"]
        )

        return {
            "variant_a": {
                "visitors": variant_a["visitors"],
                "conversions": variant_a["conversions"],
                "cvr": round(cvr_a * 100, 2)
            },
            "variant_b": {
                "visitors": variant_b["visitors"],
                "conversions": variant_b["conversions"],
                "cvr": round(cvr_b * 100, 2)
            },
            "lift": round(lift, 2),
            "statistically_significant": significant,
            "recommendation": "選擇B" if lift > 5 and significant else "繼續測試"
        }

Disclaimer

This skill provides marketing planning tools for educational purposes. All marketing activities must comply with applicable advertising and financial regulations.

這是一個面向銀行和券商營銷團隊的智慧助手工具。整體質量中等偏上：中文支援友好、場景覆蓋較全，包含客戶分層、內容生成、活動設計等實用功能。但實際使用體驗可能受限——缺少對話示例和操作指引，程式碼為主的文件對非技術使用者不夠友好，且沒有完整的營銷案例演示。建議開發方補充更多實戰案例和傻瓜式使用指南，讓非技術人員也能快速上手。適合技術基礎較好的營銷人員使用。