Skip to content

C
ciecc-agent
Commit 6c04f4ff authored by wangning's avatar wangning
Browse files
Options

fix 智能体知识库 问题

parent 2c8526bc
Hide whitespace changes
Inline Side-by-side
Showing with 183 additions and 26 deletions
.idea/workspace.xml
View file @ 6c04f4ff
......@@ -4,29 +4,17 @@
<option name="autoReloadType" value="SELECTIVE" />
</component>
<component name="ChangeListManager">
<list default="true" id="26f8285c-12a3-40dc-b957-23c37b8f3c67" name="Changes" comment="">
<change afterPath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/auth/AuthInterceptorConfiguration.java" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/promptwords/algo_suggest" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/promptwords/algo_suggest_bak260118" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/promptwords/algo_suggest_bak260119" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge1.jsonl" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge2.jsonl" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge3.jsonl" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/default.jsonl" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/suggest_algorithm.jsonl" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/suggest_algorithm_bak.jsonl" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/test_result/res1.xlsx" afterDir="false" />
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/test_result/result.xlsx" afterDir="false" />
<list default="true" id="26f8285c-12a3-40dc-b957-23c37b8f3c67" name="Changes" comment="fix">
<change afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge/algo_knowledge4.jsonl" afterDir="false" />
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/domain/response/ResponseMessage.java" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/domain/response/ResponseMessage.java" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/service/chatService/ChatServiceImpl.java" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/service/chatService/ChatServiceImpl.java" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/service/handler/IntentTool.java" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/service/handler/IntentTool.java" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/utils/DataSummaryUtil.java" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/utils/DataSummaryUtil.java" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/service/sessionService/ChatSessionManager.java" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/java/pro/spss/server/agent/service/sessionService/ChatSessionManager.java" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/application-wn.yml" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/application-wn.yml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/mapper/DaAgentMessageMapper.xml" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/mybatis/mapper/DaAgentMessageMapper.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/mapper/DaAgentSessionMapper.xml" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/mybatis/mapper/DaAgentSessionMapper.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/mapper/ResultMapper.xml" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/mybatis/mapper/ResultMapper.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/promptwords/0_1.txt" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/promptwords/0_1.txt" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge1.jsonl" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge/algo_knowledge1.jsonl" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge2.jsonl" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge/algo_knowledge2.jsonl" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge3.jsonl" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_knowledge/algo_knowledge3.jsonl" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/testcases/suggest_algorithm.jsonl" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_suggest_request/suggest_algorithm.jsonl" afterDir="false" />
<change beforePath="$PROJECT_DIR$/src/main/resources/testcases/suggest_algorithm_bak.jsonl" beforeDir="false" afterPath="$PROJECT_DIR$/src/main/resources/testcases/algo_suggest_request/suggest_algorithm_bak.jsonl" afterDir="false" />
</list>
<option name="SHOW_DIALOG" value="false" />
<option name="HIGHLIGHT_CONFLICTS" value="true" />
......@@ -52,10 +40,10 @@
"RunOnceActivity.ShowReadmeOnStart": "true",
"RunOnceActivity.TerminalTabsStorage.copyFrom.TerminalArrangementManager.252": "true",
"RunOnceActivity.git.unshallow": "true",
"Spring Boot.Application.executor": "Run",
"Spring Boot.Application.executor": "Debug",
"git-widget-placeholder": "master",
"kotlin-language-version-configured": "true",
"last_opened_file_path": "D:/projects/ciecc-agent/src/main/resources/testcases/test_result",
"last_opened_file_path": "D:/projects/ciecc-agent/src/main/resources/testcases/algo_suggest_request",
"project.structure.last.edited": "Project",
"project.structure.proportion": "0.15",
"project.structure.side.proportion": "0.21954022",
......@@ -64,13 +52,15 @@
}]]></component>
<component name="RecentsManager">
<key name="CopyFile.RECENT_KEYS">
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases\test_result" />
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases\algo_suggest_request" />
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases" />
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases\test_result" />
<recent name="D:\projects\ciecc-agent\src\main\resources\promptwords" />
<recent name="D:\projects\ciecc-agent\src\main\resources" />
<recent name="D:\projects\ciecc-agent\src\main\java\pro\spss\server\agent" />
</key>
<key name="MoveFile.RECENT_KEYS">
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases\algo_suggest_request" />
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases\algo_knowledge" />
<recent name="D:\projects\ciecc-agent\src\main\resources\testcases" />
<recent name="D:\projects\ciecc-agent\src\main\resources\mybatis" />
</key>
......@@ -111,8 +101,21 @@
<option name="presentableId" value="Default" />
<updated>1768553899700</updated>
</task>
<task id="LOCAL-00001" summary="fix">
<option name="closed" value="true" />
<created>1768958069929</created>
<option name="number" value="00001" />
<option name="presentableId" value="LOCAL-00001" />
<option name="project" value="LOCAL" />
<updated>1768958069929</updated>
</task>
<option name="localTasksCounter" value="2" />
<servers />
</component>
<component name="VcsManagerConfiguration">
<MESSAGE value="fix" />
<option name="LAST_COMMIT_MESSAGE" value="fix" />
</component>
<component name="XDebuggerManager">
<watches-manager>
<configuration name="SpringBootApplicationConfigurationType">
......
src/main/java/pro/spss/server/agent/service/chatService/ChatServiceImpl.java
View file @ 6c04f4ff
......@@ -6,6 +6,7 @@ import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.scheduling.annotation.Async;
import org.springframework.stereotype.Service;
import pro.spss.server.agent.domain.constant.ChatConstants;
import pro.spss.server.agent.domain.enums.ChatStatusEnum;
import pro.spss.server.agent.domain.enums.ConversationStateEnum;
import pro.spss.server.agent.domain.enums.CreateWayEnum;
......@@ -81,6 +82,8 @@ public class ChatServiceImpl implements BaseChatService {
}
chatSessionManager.initSession(sessionId, CreateWayEnum.ALGO_FIRST);
JSONArray messages = chatSessionManager.getMessages(sessionId);
messages.add(ChatConstants.createMessage(ChatConstants.ROLE_SYSTEM, initPrompt));
sseService.sendMessage(ResponseMessageType.INIT.getType(), sessionId, userChatMessage.getToken(), initPrompt);
return true;
......@@ -127,7 +130,7 @@ public class ChatServiceImpl implements BaseChatService {
*/
private ResponseMessage executeTool(UserChatMessage userChatMessage, RequestParams requestParams, String toolName, long startTimestamp) {
String sessionId = userChatMessage.getUserId();
JSONArray historyCopy = new JSONArray(chatSessionManager.getMessages(sessionId));
JSONArray historyCopy = chatSessionManager.getMessages(sessionId);
String prompt = userChatMessage.getPrompt();
ResponseMessage responseMessage = conversationHandler.toolExecutor(requestParams, userChatMessage, toolName, historyCopy, prompt);
responseMessage.setStartTimestamp(startTimestamp);
......
src/main/java/pro/spss/server/agent/service/sessionService/ChatSessionManager.java
View file @ 6c04f4ff
......@@ -2,6 +2,7 @@ package pro.spss.server.agent.service.sessionService;
import com.alibaba.fastjson2.JSONArray;
import lombok.Getter;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Component;
import pro.spss.server.agent.domain.constant.ChatConstants;
import pro.spss.server.agent.domain.enums.ConversationStateEnum;
......@@ -25,7 +26,8 @@ public class ChatSessionManager {
}
public void initSession(String sessionId, CreateWayEnum createWay) {
JSONArray messages = new JSONArray(ChatConstants.SYSTEM_MESSAGES);
JSONArray messages = new JSONArray();
messages.add(ChatConstants.createMessage(ChatConstants.ROLE_SYSTEM, ChatConstants.WELCOME_MESSAGE));
chatSessions.put(sessionId, messages);
RequestParams params = new RequestParams();
......
src/main/resources/testcases/algo_knowledge/algo_knowledge4.jsonl 0 → 100644
View file @ 6c04f4ff
[
{"name":"最小二乘回归","task":["回归","预测"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["可解释性强","对多重共线性敏感"]},
{"name":"岭回归","task":["回归","预测"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["抗多重共线性","模型稳定"]},
{"name":"套索回归","task":["回归","预测"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["特征选择","模型稀疏"]},
{"name":"多项式回归","task":["回归","预测"],"data":"非时间序列","relation":"非线性","sample":"不限","complexity":"复杂","property":["拟合弯曲关系","易过拟合"]},
{"name":"支持向量机回归","task":["回归","预测"],"data":"非时间序列","relation":"非线性","sample":"偏小样本","complexity":"复杂","property":["小样本表现好","对参数敏感"]},
{"name":"BP神经网络","task":["回归","预测"],"data":"非时间序列","relation":"非线性","sample":"不限","complexity":"复杂","property":["表达能力强","可解释性弱"]},
{"name":"梯度提升树","task":["回归","分类","预测"],"data":"非时间序列","relation":"非线性","sample":"不限","complexity":"复杂","property":["精度高","对噪声敏感"]},
{"name":"移动平均法","task":["预测"],"data":"时间序列","relation":"不限","sample":"偏小样本","complexity":"简单","property":["平滑波动","对突变反应慢"]},
{"name":"指数平滑法","task":["预测"],"data":"时间序列","relation":"不限","sample":"偏小样本","complexity":"简单","property":["重视近期数据","适合短期预测"]},
{"name":"自回归模型（AR）","task":["预测"],"data":"时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["依赖历史值","要求平稳"]},
{"name":"滑动平均模型（MA）","task":["预测"],"data":"时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["刻画随机扰动","短期效果好"]},
{"name":"自回归滑动平均模型","task":["预测"],"data":"时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["综合AR和MA","预测能力强"]},
{"name":"差分自回归移动平均模型","task":["预测"],"data":"时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["处理非平稳序列","建模步骤多"]},
{"name":"灰色模型","task":["预测"],"data":"时间序列","relation":"线性","sample":"小样本","complexity":"简单","property":["小样本适用","抗随机性弱"]},
{"name":"决策树","task":["分类","决策"],"data":"非时间序列","relation":"非线性","sample":"不限","complexity":"简单","property":["结构直观","易过拟合"]},
{"name":"随机森林","task":["分类","预测"],"data":"非时间序列","relation":"非线性","sample":"不限","complexity":"复杂","property":["稳定性高","计算量大"]},
{"name":"自适应增强算法","task":["分类","预测"],"data":"非时间序列","relation":"非线性","sample":"不限","complexity":"复杂","property":["关注难样本","对噪声敏感"]},
{"name":"判别分析","task":["分类"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["模型简洁","分布假设强"]},
{"name":"二分类逻辑回归","task":["分类","回归"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["概率输出","可解释性好"]},
{"name":"皮尔逊相关分析","task":["相关"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["衡量线性关系","对异常值敏感"]},
{"name":"斯皮尔曼相关分析","task":["相关"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"简单","property":["基于秩次","对异常值不敏感"]},
{"name":"独立样本t检验","task":["检验"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"简单","property":["比较均值差异","要求正态性"]},
{"name":"正态检验","task":["检验"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"简单","property":["检验分布形态","对样本量敏感"]},
{"name":"K-均值聚类","task":["聚类"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"简单","property":["速度快","对初始中心敏感"]},
{"name":"层次聚类","task":["聚类"],"data":"非时间序列","relation":"不限","sample":"小样本","complexity":"复杂","property":["结构直观","计算量大"]},
{"name":"因子分析","task":["降维","评价"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["提取潜在因子","解释性强"]},
{"name":"主成分分析","task":["降维"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["信息压缩","可解释性弱"]},
{"name":"优劣解距离法","task":["排序","评价"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"简单","property":["结果直观","依赖权重"]},
{"name":"秩和比评价法","task":["排序","评价"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"简单","property":["计算简单","信息损失多"]},
{"name":"模糊综合评价","task":["评价","排序"],"data":"非时间序列","relation":"不限","sample":"不限","complexity":"复杂","property":["处理模糊信息","主观性强"]},
{"name":"数据包络分析（CCR）","task":["效率","评价"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["规模报酬不变","适合同规模对象"]},
{"name":"数据包络分析（BCC）","task":["效率","评价"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"复杂","property":["规模报酬可变","区分技术效率"]},
{"name":"柯布-道格拉斯生产函数","task":["效率","回归"],"data":"非时间序列","relation":"线性","sample":"不限","complexity":"简单","property":["形式简单","函数假设强"]}
]
算法标签体系简要说明
通过标签对算法的适用场景和特性进行结构化描述，用于支持算法自动推荐、条件筛选和规则匹配。
任务类型：说明算法能解决的问题，如预测、回归、分类、排序、聚类、相关、检验、降维、评价、效率等。
数据类型：区分是否为时间序列数据。
关系形式：描述模型刻画关系的方式，包括线性、非线性或不限。
样本规模：表示算法对样本数量的适应程度，如小样本或不限。
复杂度：表示算法实现和计算难度，分为简单或复杂。
通过这些标签，可以将用户需求与算法能力快速匹配，实现智能推荐与筛选。
样本很小、特征少 → 优先简单模型
特征多、关系明显非线性 → 偏向复杂模型
\ No newline at end of file
src/main/resources/testcases/algo_suggest_request/suggest_algorithm1.jsonl 0 → 100644
View file @ 6c04f4ff
{"prompt":"促销支出和销售量之间是不是存在线性关系？","dataId":"","confirm":false,"sessionId":"S1001","expected":"最小二乘回归"}
{"prompt":"哪些地区的实际销售量和模型预测差距最大？","dataId":"","confirm":false,"sessionId":"S1001","expected":"最小二乘回归"}
{"prompt":"这个模型是否适合长期指导促销预算分配，还是只适合当前样本？","dataId":"","confirm":false,"sessionId":"S1001","expected":"最小二乘回归"}
{"prompt":"这几个指标里，哪个和 GDP 增速关系最明显？","dataId":"","confirm":false,"sessionId":"S1001","expected":"岭回归"}
{"prompt":"固定资产投资增速和基础设施投资增速的变化是不是经常很相似？","dataId":"","confirm":false,"sessionId":"S1001","expected":"岭回归"}
{"prompt":"当固定资产投资和基础设施投资在大多数样本里都高度同步时，用它们同时预测 GDP，会不会影响结果的稳定性？","dataId":"","confirm":false,"sessionId":"S1001","expected":"岭回归"}
{"prompt":"这几个指标里，哪些对 GDP 增速影响最明显？","dataId":"","confirm":false,"sessionId":"S1001","expected":"套索回归"}
{"prompt":"如果只保留对 GDP 真正有用的指标，哪些可以不要？","dataId":"","confirm":false,"sessionId":"S1001","expected":"套索回归"}
{"prompt":"在多个指标一起影响 GDP 的情况下，能不能自动挑出最关键的指标，其它影响很小的就忽略掉？","dataId":"","confirm":false,"sessionId":"S1001","expected":"套索回归"}
{"prompt":"职位级别越高，薪资是不是涨得越来越快？","dataId":"","confirm":false,"sessionId":"S1001","expected":"多项式回归"}
{"prompt":"职位从低级到高级，薪资增长是不是不是匀速的，而是后面涨得更猛？","dataId":"","confirm":false,"sessionId":"S1001","expected":"多项式回归"}
{"prompt":"如果薪资和级别之间是“越往后涨得越快”的弯曲关系，用简单直线会不会不准，需要用能拟合弯曲关系的方法？","dataId":"","confirm":false,"sessionId":"S1001","expected":"多项式回归"}
{"prompt":"这些指标和 GDP 同比之间的关系，看起来是不是不太像一条直线？","dataId":"","confirm":false,"sessionId":"S1001","expected":"支持向量机回归"}
{"prompt":"在样本不多、波动又很大的情况下，用简单方法预测 GDP 会不会不准？","dataId":"","confirm":false,"sessionId":"S1001","expected":"支持向量机回归"}
{"prompt":"如果数据量不大、关系又比较复杂，有没有一种方法在小样本下也能学到这种“弯弯曲曲”的关系来做预测？","dataId":"","confirm":false,"sessionId":"S1001","expected":"支持向量机回归"}
{"prompt":"人力成本和原材料成本变化，对收益增长率影响明显吗？中等问题：","dataId":"","confirm":false,"sessionId":"S1001","expected":"BP神经网络"}
{"prompt":"当人力成本、原材料成本一点点变化时，收益的变化是不是有时候不太规律、很难用直线说明？","dataId":"","confirm":false,"sessionId":"S1001","expected":"BP神经网络"}
{"prompt":"如果收益和成本之间的关系很复杂、变化不规则，用简单公式说不清，那有没有办法直接从数据里学出这种复杂关系来做预测？","dataId":"","confirm":false,"sessionId":"S1001","expected":"BP神经网络"}
{"prompt":"这些信息里，哪些最容易看出一个人会不会违约？","dataId":"","confirm":false,"sessionId":"S1001","expected":"梯度提升树"}
{"prompt":"有的人单看某一项数据好像没问题，但放在一起看却变成高风险，这是怎么回事？","dataId":"","confirm":false,"sessionId":"S1001","expected":"梯度提升树"}
{"prompt":"如果判断违约要同时看很多条件、而且关系还挺复杂，有没有一种办法能把这些情况组合起来，尽量判断得更准？","dataId":"","confirm":false,"sessionId":"S1001","expected":"梯度提升树"}
{"prompt":"每个月的销售额大概是往上走的，下一月大概会是多少？","dataId":"","confirm":false,"sessionId":"S1001","expected":"移动平均法"}
{"prompt":"有时候某个月突然高一点或低一点，这种波动能不能“平滑”一下再看趋势？","dataId":"","confirm":false,"sessionId":"S1001","expected":"移动平均法"}
{"prompt":"如果我更关心整体走势而不是某个月的突然变化，有没有办法把这些起伏压一压，再用来预测下个月的销售额？","dataId":"","confirm":false,"sessionId":"S1001","expected":"移动平均法"}
{"prompt":"最近几年的销售量，对预测下一年的影响是不是更大？","dataId":"","confirm":false,"sessionId":"S1001","expected":"指数平滑法"}
{"prompt":"早些年的数据和最近的数据，预测时是不是应该更看重新的？","dataId":"","confirm":false,"sessionId":"S1001","expected":"指数平滑法"}
{"prompt":"如果我主要想做短期预测，能不能让模型更“偏向”最近的数据来判断未来的销售量？","dataId":"","confirm":false,"sessionId":"S1001","expected":"指数平滑法"}
{"prompt":"这个月的销售量，会不会主要受前几个月的影响？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自回归模型（AR）"}
{"prompt":"如果前几个月卖得多，这个月一般也会偏多吗？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自回归模型（AR）"}
{"prompt":"能不能只靠过去几个月的销售量，来推算下一个月大概能卖多少？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自回归模型（AR）"}
{"prompt":"有些月份产能利用率突然高一点或低一点，是不是偶然情况造成的？","dataId":"","confirm":false,"sessionId":"S1001","expected":"滑动平均模型（MA）"}
{"prompt":"这些突然的波动，会不会影响后面几个月的产能利用率？","dataId":"","confirm":false,"sessionId":"S1001","expected":"滑动平均模型（MA）"}
{"prompt":"如果主要是一些“随机起伏”在影响数据，能不能专门把这些波动考虑进去，用来做短期预测？","dataId":"","confirm":false,"sessionId":"S1001","expected":"滑动平均模型（MA）"}
{"prompt":"这个月的产量，会不会主要受前几个月产量的影响？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自回归滑动平均模型"}
{"prompt":"有时候产量突然高一点或低一点，这种波动会不会影响后面的走势？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自回归滑动平均模型"}
{"prompt":"如果既有“跟着过去走的规律”，又有一些偶然波动，能不能同时把这两种情况一起考虑来预测下个月的产量？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自回归滑动平均模型"}
{"prompt":"销售额一直在往上走，是不是每个月都在增长？","dataId":"","confirm":false,"sessionId":"S1001","expected":"差分自回归移动平均模型"}
{"prompt":"如果一直这样上涨，用原来的数据直接预测，会不会不太准？","dataId":"","confirm":false,"sessionId":"S1001","expected":"差分自回归移动平均模型"}
{"prompt":"要是数据本身一直在变、不是稳定水平，能不能先把“变化幅度”拿出来，再用它来预测后面的销售额？","dataId":"","confirm":false,"sessionId":"S1001","expected":"差分自回归移动平均模型"}
{"prompt":"只有这么几年数据，也能大概看出以后会怎么涨吗？","dataId":"","confirm":false,"sessionId":"S1001","expected":"灰色模型"}
{"prompt":"数据不多、还有点波动，用常见方法会不会不太准？","dataId":"","confirm":false,"sessionId":"S1001","expected":"灰色模型"}
{"prompt":"要是数据本身一直在变、不是稳定水平，能不能先把“变化幅度”拿出来，再用它来预测后面的销售额？","dataId":"","confirm":false,"sessionId":"S1001","expected":"灰色模型"}
{"prompt":"看这些条件，大概能不能直接判断一个供应商算不算重要？","dataId":"","confirm":false,"sessionId":"S1001","expected":"决策树"}
{"prompt":"是不是可以一步步按条件来筛，比如先看产量，再看品质、服务？","dataId":"","confirm":false,"sessionId":"S1001","expected":"决策树"}
{"prompt":"能不能把这种判断过程整理成一套清楚的规则，让系统自己照着规则给供应商分类？","dataId":"","confirm":false,"sessionId":"S1001","expected":"决策树"}
{"prompt":"看这些信息，能不能大概判断一个员工会不会离职？","dataId":"","confirm":false,"sessionId":"S1001","expected":"随机森林"}
{"prompt":"单看某一个条件有时不准，是不是要把很多条件一起看才靠谱？","dataId":"","confirm":false,"sessionId":"S1001","expected":"随机森林"}
{"prompt":"如果判断离职要考虑很多因素、而且关系又挺复杂，有没有一种办法多从不同角度一起判断，结果会更稳一些？","dataId":"","confirm":false,"sessionId":"S1001","expected":"随机森林"}
{"prompt":"看这些指标，能不能大概分出哪些企业信用好、哪些一般？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自适应增强算法"}
{"prompt":"有些企业看起来条件差不多，但结果却不一样，这是为什么？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自适应增强算法"}
{"prompt":"如果有些企业特别难判断，能不能让系统多关注这些“容易分错”的情况，把分类做得更准一点？","dataId":"","confirm":false,"sessionId":"S1001","expected":"自适应增强算法"}
{"prompt":"看这些指标，能不能大概分出哪些企业是正常的，哪些是有风险的？","dataId":"","confirm":false,"sessionId":"S1001","expected":"判别分析"}
{"prompt":"这些企业的数据，好像正常的和有风险的在数值上有点区别，是不是能找出一个大致的分界线？","dataId":"","confirm":false,"sessionId":"S1001","expected":"判别分析"}
{"prompt":"能不能根据这些指标，总结出一套“长得像这样的大多是正常、像那样的大多是风险”的判断方法，让系统自动来分？","dataId":"","confirm":false,"sessionId":"S1001","expected":"判别分析"}
{"prompt":"能不能根据年龄、性别和收入，大概判断一个人会不会想买这个产品？","dataId":"","confirm":false,"sessionId":"S1001","expected":"二分类逻辑回归"}
{"prompt":"这些条件变化时，购买的可能性是变大还是变小？","dataId":"","confirm":false,"sessionId":"S1001","expected":"二分类逻辑回归"}
{"prompt":"能不能不只告诉我“会不会买”，还能告诉我“有多大概率会买”？","dataId":"","confirm":false,"sessionId":"S1001","expected":"二分类逻辑回归"}
{"prompt":"工作时间多一点，销售额是不是一般也会高一点？","dataId":"","confirm":false,"sessionId":"S1001","expected":"皮尔逊相关分析"}
{"prompt":"工作时间、销售额和客户满意度之间，是不是有一起变化的情况？","dataId":"","confirm":false,"sessionId":"S1001","expected":"皮尔逊相关分析"}
{"prompt":"能不能用一个数字，来表示这几个指标之间“关系有多紧密”？","dataId":"","confirm":false,"sessionId":"S1001","expected":"皮尔逊相关分析"}
{"prompt":"身高高一点的学生，体重是不是一般也更大？","dataId":"","confirm":false,"sessionId":"S1001","expected":"斯皮尔曼相关分析"}
{"prompt":"把学生按身高、体重、肺活量从小到大排个顺序，这些顺序会不会差不多？","dataId":"","confirm":false,"sessionId":"S1001","expected":"斯皮尔曼相关分析"}
{"prompt":"就算有个别学生数据特别高或特别低，能不能还能判断这些指标之间是不是大致一起升或一起降？","dataId":"","confirm":false,"sessionId":"S1001","expected":"斯皮尔曼相关分析"}
{"prompt":"方式A和方式B，哪种卖得更多？","dataId":"","confirm":false,"sessionId":"S1001","expected":"独立样本t检验"}
{"prompt":"两种方式的平均销售额，是不是差得挺明显？","dataId":"","confirm":false,"sessionId":"S1001","expected":"独立样本t检验"}
{"prompt":"这种差别是真的存在，还是只是样本刚好不一样造成的？","dataId":"","confirm":false,"sessionId":"S1001","expected":"独立样本t检验"}
{"prompt":"这些胆固醇数据，看起来是不是大多集中在一个范围里？","dataId":"","confirm":false,"sessionId":"S1001","expected":"正态检验"}
{"prompt":"这些数值是“中间多、两头少”的那种分布吗？","dataId":"","confirm":false,"sessionId":"S1001","expected":"正态检验"}
{"prompt":"能不能判断这些数据是不是符合常见的那种“钟形分布”，而不是乱七八糟的形状？","dataId":"","confirm":false,"sessionId":"S1001","expected":"正态检验"}
{"prompt":"这些顾客，大概能分成几类消费水平不一样的人？","dataId":"","confirm":false,"sessionId":"S1001","expected":"K-均值聚类"}
{"prompt":"消费金额和购买次数差不多的顾客，是不是可以归到一组？","dataId":"","confirm":false,"sessionId":"S1001","expected":"K-均值聚类"}
{"prompt":"能不能自动把顾客按“花钱多少、买得多不多”分成几群，方便我区别对待？","dataId":"","confirm":false,"sessionId":"S1001","expected":"K-均值聚类"}
{"prompt":"这些用户里，活跃程度差不多的人能不能分成几组？","dataId":"","confirm":false,"sessionId":"S1001","expected":"层次聚类"}
{"prompt":"发帖、评论、点赞、粉丝都差不多的用户，是不是可以归为一类？","dataId":"","confirm":false,"sessionId":"S1001","expected":"层次聚类"}
{"prompt":"能不能一步步把用户按“越来越像”的程度分组，让我看到他们是怎么慢慢分成几类的？","dataId":"","confirm":false,"sessionId":"S1001","expected":"层次聚类"}
{"prompt":"这么多经济指标，看起来都挺相关的，是不是有点重复？","dataId":"","confirm":false,"sessionId":"S1001","expected":"因子分析"}
{"prompt":"能不能把这些指标归成几类，比如“工业类”“消费类”“投资类”这种？","dataId":"","confirm":false,"sessionId":"S1001","expected":"因子分析"}
{"prompt":"能不能用少数几个“综合指标”，来代替这一大堆原始数据，还能大致反映地区的经济情况？","dataId":"","confirm":false,"sessionId":"S1001","expected":"因子分析"}
{"prompt":"有没有一两个指标，就已经能大概看出整体水平高不高？","dataId":"","confirm":false,"sessionId":"S1001","expected":"主成分分析"}
{"prompt":"能不能把这些指标按“差不多的放一类”分成几组？","dataId":"","confirm":false,"sessionId":"S1001","expected":"主成分分析"}
{"prompt":"能不能用更少的几个“综合指标”，来代表现在这一大堆数据，方便比较和分析？","dataId":"","confirm":false,"sessionId":"S1001","expected":"主成分分析"}
{"prompt":"这些煤矿里，哪个整体情况最好、哪个最差？","dataId":"","confirm":false,"sessionId":"S1001","expected":"优劣解距离法"}
{"prompt":"同时看粉尘、二氧化硫和患病率，怎么综合判断一个煤矿的好坏？","dataId":"","confirm":false,"sessionId":"S1001","expected":"优劣解距离法"}
{"prompt":"能不能按“离最好情况有多远、离最差情况有多远”，给每个煤矿排个名？","dataId":"","confirm":false,"sessionId":"S1001","expected":"优劣解距离法"}
{"prompt":"这些行业里，整体表现最好的是哪个？","dataId":"","confirm":false,"sessionId":"S1001","expected":"秩和比评价法"}
{"prompt":"如果把每个指标都排个名，再综合起来，会不会更好比较？","dataId":"","confirm":false,"sessionId":"S1001","expected":"秩和比评价法"}
{"prompt":"能不能先把各个指标变成“名次”，再用这些名次来给行业做一个总体排序？","dataId":"","confirm":false,"sessionId":"S1001","expected":"秩和比评价法"}
{"prompt":"这些能力里，哪几项看起来评价最好？","dataId":"","confirm":false,"sessionId":"S1001","expected":"模糊综合评价"}
{"prompt":"有些评价不是非好即坏，这种“介于中间”的情况怎么一起算？","dataId":"","confirm":false,"sessionId":"S1001","expected":"模糊综合评价"}
{"prompt":"能不能把“非常好、好、一般、比较不好、非常不好”这种模糊评价，综合成一个总体结果来排序？","dataId":"","confirm":false,"sessionId":"S1001","expected":"模糊综合评价"}
{"prompt":"这些地区里，哪几个看起来投入多、产出也多？","dataId":"","confirm":false,"sessionId":"S1001","expected":"数据包络分析（CCR）"}
{"prompt":"有的地区投入差不多，但成果差很多，这是为什么？","dataId":"","confirm":false,"sessionId":"S1001","expected":"数据包络分析（CCR）"}
{"prompt":"能不能在“投入”和“产出”一起考虑的情况下，判断哪些地区用同样的资源干得最有效率？","dataId":"","confirm":false,"sessionId":"S1001","expected":"数据包络分析（CCR）"}
{"prompt":"这些地区里，哪些看起来用资源用得最划算？","dataId":"","confirm":false,"sessionId":"S1001","expected":"数据包络分析（BCC）"}
{"prompt":"有的地方投入不算多，但成果不错，是不是方法更高效？","dataId":"","confirm":false,"sessionId":"S1001","expected":"数据包络分析（BCC）"}
{"prompt":"在考虑不同地区规模不一样的情况下，能不能分别看“做事本身的效率”和“规模带来的影响”？","dataId":"","confirm":false,"sessionId":"S1001","expected":"数据包络分析（BCC）"}
{"prompt":"多投点钱或多用点人，产量是不是一般就会多一些？","dataId":"","confirm":false,"sessionId":"S1001","expected":""}
{"prompt":"是多加资本更有用，还是多加劳动力更有用？","dataId":"","confirm":false,"sessionId":"S1001","expected":""}
{"prompt":"能不能用一个简单的公式，来说明“资本和劳动力一起是怎么影响产量的”？","dataId":"","confirm":false,"sessionId":"S1001","expected":""}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment