添加用户个人技能标签提取

2026-03-20 11:34:12 +08:00
parent dc2e241151
commit 971694d648
7 changed files with 466 additions and 6 deletions
@@ -0,0 +1,13 @@
+package org.jiayunet.mapper;
+
+import org.apache.ibatis.annotations.Mapper;
+import org.jiayunet.pojo.po.UserProfileSkillTagRelation;
+
+/**
+ * 用户技能标签关联Mapper
+ *
+ * @author zk
+ */
+@Mapper
+public interface UserProfileSkillTagRelationMapper extends CommonMapper<UserProfileSkillTagRelation> {
+}
@@ -0,0 +1,30 @@
+package org.jiayunet.pojo.po;
+
+import com.baomidou.mybatisplus.annotation.IdType;
+import com.baomidou.mybatisplus.annotation.TableId;
+import com.baomidou.mybatisplus.annotation.TableName;
+import lombok.Data;
+
+import java.time.Instant;
+
+/**
+ * 用户技能标签关联表（bg_user_profile_skill_tag_relation）
+ *
+ * @author zk
+ */
+@Data
+@TableName(value = "bg_user_profile_skill_tag_relation")
+public class UserProfileSkillTagRelation {
+
+    @TableId(type = IdType.AUTO)
+    private Long id;
+
+    /** 用户ID */
+    private Long userId;
+
+    /** 技能标签ID */
+    private Long skillTagId;
+
+    /** 创建时间 */
+    private Instant createTime;
+}
@@ -0,0 +1,324 @@
+package org.jiayunet.service;
+
+import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
+import com.fasterxml.jackson.databind.JsonNode;
+import lombok.extern.slf4j.Slf4j;
+import org.jiayunet.ai.AiChatAbility;
+import org.jiayunet.mapper.*;
+import org.jiayunet.pojo.po.*;
+import org.jiayunet.tool.HttpTool;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.scheduling.annotation.Async;
+import org.springframework.stereotype.Service;
+
+import java.time.Instant;
+import java.util.*;
+import java.util.stream.Collectors;
+
+/**
+ * 用户技能标签匹配服务
+ * <p>主要功能：根据用户个人资料，AI识别匹配的技能标签</p>
+ * <p>依赖：AiChatAbility（AI调用）</p>
+ * <p>使用表：bg_user_profile（主表）、bg_user_profile_*（5张子表）、
+ * bg_job_category（岗位分类）、bg_skill_tag（技能标签）、
+ * bg_user_profile_skill_tag_relation（关联表）</p>
+ *
+ * @author zk
+ */
+@Slf4j
+@Service
+public class UserSkillTagMatchService {
+
+    @Autowired
+    private AiChatAbility aiChatAbility;
+
+    @Autowired
+    private UserProfileMapper userProfileMapper;
+
+    @Autowired
+    private UserProfileEducationMapper educationMapper;
+
+    @Autowired
+    private UserProfileWorkMapper workMapper;
+
+    @Autowired
+    private UserProfileInternshipMapper internshipMapper;
+
+    @Autowired
+    private UserProfileProjectMapper projectMapper;
+
+    @Autowired
+    private UserProfileCompetitionMapper competitionMapper;
+
+    @Autowired
+    private JobCategoryMapper jobCategoryMapper;
+
+    @Autowired
+    private SkillTagMapper skillTagMapper;
+
+    @Autowired
+    private UserProfileSkillTagRelationMapper relationMapper;
+
+    /**
+     * 异步匹配用户技能标签
+     * <p>1. 查询用户完整个人资料 2. 第一次AI调用识别二级分类 3. 查询三级分类
+     * 4. 查询候选技能标签 5. 第二次AI调用匹配技能标签 6. 全量替换关联表</p>
+     */
+    @Async("userProfileAsyncExecutor")
+    public void matchUserSkillTags(Long userId) {
+        try {
+            log.info("开始匹配用户技能标签, userId={}", userId);
+
+            // 1. 查询用户完整个人资料
+            UserProfile profile = userProfileMapper.selectOne(new LambdaQueryWrapper<UserProfile>().eq(UserProfile::getUserId, userId));
+            if (profile == null) {
+                log.info("用户主表为空，清空技能标签, userId={}", userId);
+                clearRelations(userId);
+                return;
+            }
+
+            List<UserProfileEducation> educationList = educationMapper.selectList(new LambdaQueryWrapper<UserProfileEducation>().eq(UserProfileEducation::getUserId, userId));
+            List<UserProfileWork> workList = workMapper.selectList(new LambdaQueryWrapper<UserProfileWork>().eq(UserProfileWork::getUserId, userId));
+            List<UserProfileInternship> internshipList = internshipMapper.selectList(new LambdaQueryWrapper<UserProfileInternship>().eq(UserProfileInternship::getUserId, userId));
+            List<UserProfileProject> projectList = projectMapper.selectList(new LambdaQueryWrapper<UserProfileProject>().eq(UserProfileProject::getUserId, userId));
+            List<UserProfileCompetition> competitionList = competitionMapper.selectList(new LambdaQueryWrapper<UserProfileCompetition>().eq(UserProfileCompetition::getUserId, userId));
+
+            // 2. 数据有效性检查
+            if (educationList.isEmpty() && workList.isEmpty() && internshipList.isEmpty() && projectList.isEmpty() && competitionList.isEmpty()) {
+                log.info("用户所有子表为空，清空技能标签, userId={}", userId);
+                clearRelations(userId);
+                return;
+            }
+
+            // 3. 第一次 AI 调用（识别二级分类）
+            List<Long> categoryIds = identifyCategories(profile, educationList, workList, internshipList, projectList, competitionList);
+            if (categoryIds.isEmpty()) {
+                log.info("AI未识别出岗位分类，清空技能标签, userId={}", userId);
+                clearRelations(userId);
+                return;
+            }
+
+            // 4. 查询三级分类（技能标签挂在三级分类下）
+            List<JobCategory> level3Categories = jobCategoryMapper.selectList(new LambdaQueryWrapper<JobCategory>().eq(JobCategory::getLevel, 3).in(JobCategory::getParentId, categoryIds));
+            if (level3Categories.isEmpty()) {
+                log.info("二级分类下无三级分类，清空技能标签, userId={}", userId);
+                clearRelations(userId);
+                return;
+            }
+
+            // 5. 查询候选技能标签（使用三级分类ID）
+            List<Long> level3CategoryIds = level3Categories.stream().map(JobCategory::getId).collect(Collectors.toList());
+            List<SkillTag> candidateTags = skillTagMapper.selectList(new LambdaQueryWrapper<SkillTag>().in(SkillTag::getCategoryId, level3CategoryIds));
+            if (candidateTags.isEmpty()) {
+                log.info("候选技能标签为空，清空技能标签, userId={}", userId);
+                clearRelations(userId);
+                return;
+            }
+
+            // 6. 第二次 AI 调用（匹配技能标签）
+            List<Long> matchedTagIds = matchSkillTags(profile, educationList, workList, internshipList, projectList, competitionList, candidateTags);
+
+            // 7. 全量替换关联表
+            replaceRelations(userId, matchedTagIds);
+
+            log.info("用户技能标签匹配完成, userId={}, 匹配{}个标签", userId, matchedTagIds.size());
+
+        } catch (Exception e) {
+            log.error("用户技能标签匹配异常, userId={}", userId, e);
+        }
+    }
+
+    /**
+     * 第一次 AI 调用：识别用户所属的二级岗位分类
+     */
+    private List<Long> identifyCategories(UserProfile profile, List<UserProfileEducation> educationList,
+                                           List<UserProfileWork> workList, List<UserProfileInternship> internshipList,
+                                           List<UserProfileProject> projectList, List<UserProfileCompetition> competitionList) {
+        // 构建用户资料 JSON
+        Map<String, Object> profileData = new HashMap<>();
+        profileData.put("name", profile.getName());
+        profileData.put("workYears", profile.getWorkYears());
+        profileData.put("education", educationList);
+        profileData.put("work", workList);
+        profileData.put("internship", internshipList);
+        profileData.put("project", projectList);
+        profileData.put("competition", competitionList);
+
+        String profileJson;
+        try {
+            profileJson = HttpTool.objectMapper.writeValueAsString(profileData);
+        } catch (Exception e) {
+            log.error("用户资料序列化失败", e);
+            return List.of();
+        }
+
+        // 查询所有二级分类
+        List<JobCategory> allCategories = jobCategoryMapper.selectList(new LambdaQueryWrapper<JobCategory>().eq(JobCategory::getLevel, 2));
+        
+        // 构建分类列表文本（带一级分类名称）
+        Map<Long, String> parentNameMap = new HashMap<>();
+        List<JobCategory> parentCategories = jobCategoryMapper.selectList(new LambdaQueryWrapper<JobCategory>().eq(JobCategory::getLevel, 1));
+        for (JobCategory parent : parentCategories) {
+            parentNameMap.put(parent.getId(), parent.getName());
+        }
+
+        StringBuilder categoryText = new StringBuilder();
+        for (JobCategory category : allCategories) {
+            String parentName = parentNameMap.getOrDefault(category.getParentId(), "未知");
+            categoryText.append(String.format("ID: %d, 名称: %s > %s\n", category.getId(), parentName, category.getName()));
+        }
+
+        // 构建 Prompt
+        String systemPrompt = """
+                任务：根据用户个人资料，选择最匹配的二级岗位分类。
+                
+                规则：
+                1. 选择 1-10 个最匹配的二级分类（优先核心岗位，按匹配度排序）
+                2. 信息不足无法判断时返回空数组 []
+                3. 只返回纯数字数组 JSON，不要任何其他文字
+                
+                返回格式示例：
+                - 有分类：[23, 45, 67]
+                - 无法判断：[]
+                """;
+
+        String userMessage = "【用户个人资料】\n" + profileJson + "\n\n【二级岗位分类列表（格式：一级分类 > 二级分类）】\n" + categoryText;
+
+        try {
+            String aiResponse = aiChatAbility.chat(systemPrompt, userMessage);
+            return parseIdArray(aiResponse, allCategories.stream().map(JobCategory::getId).collect(Collectors.toSet()));
+        } catch (Exception e) {
+            log.error("AI识别岗位分类失败", e);
+            return List.of();
+        }
+    }
+
+    /**
+     * 第二次 AI 调用：从候选标签中匹配用户技能标签
+     */
+    private List<Long> matchSkillTags(UserProfile profile, List<UserProfileEducation> educationList,
+                                       List<UserProfileWork> workList, List<UserProfileInternship> internshipList,
+                                       List<UserProfileProject> projectList, List<UserProfileCompetition> competitionList,
+                                       List<SkillTag> candidateTags) {
+        // 构建用户资料 JSON
+        Map<String, Object> profileData = new HashMap<>();
+        profileData.put("name", profile.getName());
+        profileData.put("workYears", profile.getWorkYears());
+        profileData.put("education", educationList);
+        profileData.put("work", workList);
+        profileData.put("internship", internshipList);
+        profileData.put("project", projectList);
+        profileData.put("competition", competitionList);
+
+        String profileJson;
+        try {
+            profileJson = HttpTool.objectMapper.writeValueAsString(profileData);
+        } catch (Exception e) {
+            log.error("用户资料序列化失败", e);
+            return List.of();
+        }
+
+        // 构建候选标签文本（按分类分组）
+        Map<Long, String> categoryNameMap = new HashMap<>();
+        Set<Long> categoryIds = candidateTags.stream().map(SkillTag::getCategoryId).collect(Collectors.toSet());
+        List<JobCategory> categories = jobCategoryMapper.selectList(new LambdaQueryWrapper<JobCategory>().in(JobCategory::getId, categoryIds));
+        for (JobCategory category : categories) {
+            categoryNameMap.put(category.getId(), category.getName());
+        }
+
+        StringBuilder tagText = new StringBuilder();
+        Map<Long, List<SkillTag>> groupedTags = candidateTags.stream().collect(Collectors.groupingBy(SkillTag::getCategoryId));
+        for (Map.Entry<Long, List<SkillTag>> entry : groupedTags.entrySet()) {
+            String categoryName = categoryNameMap.getOrDefault(entry.getKey(), "未知");
+            tagText.append("【").append(categoryName).append("】\n");
+            for (SkillTag tag : entry.getValue()) {
+                tagText.append(String.format("ID: %d, 名称: %s\n", tag.getId(), tag.getName()));
+            }
+            tagText.append("\n");
+        }
+
+        // 构建 Prompt
+        String systemPrompt = """
+                任务：根据用户个人资料，从候选技能标签中选出匹配的标签。
+                
+                规则：
+                1. 只选择用户明确具备或可推断的技能
+                2. 无法匹配返回空数组 []
+                3. 只返回纯数字数组 JSON，不要任何其他文字
+                
+                返回格式示例：
+                - 有匹配：[12, 34, 56]
+                - 无匹配：[]
+                """;
+
+        String userMessage = "【用户个人资料】\n" + profileJson + "\n\n【候选技能标签（按分类分组）】\n" + tagText;
+
+        try {
+            String aiResponse = aiChatAbility.chat(systemPrompt, userMessage);
+            return parseIdArray(aiResponse, candidateTags.stream().map(SkillTag::getId).collect(Collectors.toSet()));
+        } catch (Exception e) {
+            log.error("AI匹配技能标签失败", e);
+            return List.of();
+        }
+    }
+
+    /**
+     * 解析 AI 返回的 ID 数组
+     */
+    private List<Long> parseIdArray(String aiResponse, Set<Long> validIds) {
+        String json = aiResponse.trim();
+        if (json.startsWith("```")) {
+            json = json.replaceAll("^```\\w*\\n?", "").replaceAll("\\n?```$", "").trim();
+        }
+
+        try {
+            JsonNode arrayNode = HttpTool.objectMapper.readTree(json);
+            List<Long> result = new ArrayList<>();
+            if (arrayNode.isArray()) {
+                for (JsonNode node : arrayNode) {
+                    long id = node.asLong(0);
+                    if (id > 0 && validIds.contains(id) && !result.contains(id)) {
+                        result.add(id);
+                    }
+                }
+            }
+            return result;
+        } catch (Exception e) {
+            log.warn("AI返回解析失败: {}", json, e);
+            return List.of();
+        }
+    }
+
+    /**
+     * 清空用户技能标签关联
+     */
+    public void clearRelations(Long userId) {
+        relationMapper.delete(new LambdaQueryWrapper<UserProfileSkillTagRelation>().eq(UserProfileSkillTagRelation::getUserId, userId));
+    }
+
+    /**
+     * 全量替换用户技能标签关联
+     */
+
+    public void replaceRelations(Long userId, List<Long> skillTagIds) {
+        // 先删除
+        relationMapper.delete(new LambdaQueryWrapper<UserProfileSkillTagRelation>().eq(UserProfileSkillTagRelation::getUserId, userId));
+
+        // 结果为空则只删除
+        if (skillTagIds.isEmpty()) {
+            return;
+        }
+
+        // 批量插入
+        Instant now = Instant.now();
+        List<UserProfileSkillTagRelation> relations = skillTagIds.stream().map(tagId -> {
+            UserProfileSkillTagRelation relation = new UserProfileSkillTagRelation();
+            relation.setUserId(userId);
+            relation.setSkillTagId(tagId);
+            relation.setCreateTime(now);
+            return relation;
+        }).collect(Collectors.toList());
+
+        relationMapper.batchInsert(relations);
+    }
+}