客户管理功能调整， 音频模型调整

pom.xml

@@ -38,6 +38,12 @@
             <groupId>org.springframework.boot</groupId>
             <artifactId>spring-boot-starter-web</artifactId>
         </dependency>
+        
+        <!-- Apache HttpClient 5 for RestTemplate -->
+        <dependency>
+            <groupId>org.apache.httpcomponents.client5</groupId>
+            <artifactId>httpclient5</artifactId>
+        </dependency>
 
         <dependency>
             <groupId>org.springframework.boot</groupId>

src/main/java/com/rj/common/PasswordUtil.java

@@ -179,6 +179,9 @@ public class PasswordUtil {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/common/ServiceManager.java

@@ -163,6 +163,9 @@ public class ServiceManager {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/config/AliyunConfig.java

@@ -140,6 +140,9 @@ public class AliyunConfig {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/controller/CustomerManagementController.java

@@ -135,8 +135,8 @@ public class CustomerManagementController {
             @RequestParam(defaultValue = "1") Integer current,
             @Parameter(description = "每页大小", example = "10")
             @RequestParam(defaultValue = "10") Integer size,
-            @Parameter(description = "客户姓名（模糊查询）")
-            @RequestParam(required = false) String customerName,
+            @Parameter(description = "客户姓名（模糊查询）")@RequestParam(required = false) String customerName,
+            @Parameter(description = "所属人（模糊查询）")@RequestParam(required = false) String salesName,
             @Parameter(description = "联系方式（模糊查询）")
             @RequestParam(required = false) String contact,
             @Parameter(description = "所属门店ID")
@@ -150,6 +150,9 @@ public class CustomerManagementController {
             if (customerName != null && !customerName.trim().isEmpty()) {
                 queryWrapper.like(CustomerManagement::getCustomerName, customerName);
             }
+            if (salesName != null && !salesName.trim().isEmpty()) {
+                queryWrapper.like(CustomerManagement::getSalesName, salesName);
+            }
             if (contact != null && !contact.trim().isEmpty()) {
                 queryWrapper.like(CustomerManagement::getContact, contact);
             }

src/main/java/com/rj/controller/SiliconFlowTtsController.java

@@ -419,7 +419,7 @@ public class SiliconFlowTtsController {
             String fileExtension = originalFilename != null && originalFilename.contains(".") 
                 ? originalFilename.substring(originalFilename.lastIndexOf(".")) 
                 : ".mp3";
-            String uniqueFileName = "audio/" + UUID.randomUUID().toString() + fileExtension;
+            String uniqueFileName = "/" + UUID.randomUUID().toString() + fileExtension;
             
             // 上传文件到MinIO
             String minioUrl = minIOService.uploadFileWithName(file, uniqueFileName);

src/main/java/com/rj/controller/TtsRequestLogController.java

@@ -5,6 +5,8 @@ import com.baomidou.mybatisplus.extension.plugins.pagination.Page;
 import com.rj.entity.TtsRequestLog;
 import com.rj.mapper.TtsRequestLogMapper;
 import com.rj.service.ITtsRequestLogService;
+import com.rj.dto.AsrRequest;
+import com.rj.dto.AsrResponse;
 import io.swagger.v3.oas.annotations.Operation;
 import io.swagger.v3.oas.annotations.Parameter;
 import io.swagger.v3.oas.annotations.tags.Tag;
@@ -13,7 +15,6 @@ import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.http.ResponseEntity;
 import org.springframework.web.bind.annotation.*;
 
-import java.time.LocalDateTime;
 import java.util.HashMap;
 import java.util.Map;
 
@@ -40,6 +41,7 @@ public class TtsRequestLogController {
     public ResponseEntity<Map<String, Object>> getTtsRequestLogs(
             @Parameter(description = "页码") @RequestParam(defaultValue = "1") Integer pageNum,
             @Parameter(description = "每页大小") @RequestParam(defaultValue = "10") Integer pageSize,
+            @Parameter(description = "音乐名称") @RequestParam(required = false) String audioName,
             @Parameter(description = "状态") @RequestParam(required = false) String status,
             @Parameter(description = "模型") @RequestParam(required = false) String model,
             @Parameter(description = "创建人姓名") @RequestParam(required = false) String creatorName,
@@ -48,12 +50,15 @@ public class TtsRequestLogController {
             @Parameter(description = "结束时间") @RequestParam(required = false) String endTime) {
         
         Map<String, Object> result = new HashMap<>();
-        
+
         try {
             Page<TtsRequestLog> page = new Page<>(pageNum, pageSize);
             QueryWrapper<TtsRequestLog> queryWrapper = new QueryWrapper<>();
             
             // 添加查询条件
+            if (audioName != null && !audioName.trim().isEmpty()) {
+                queryWrapper.like("audio_name", audioName);
+            }
             if (status != null && !status.trim().isEmpty()) {
                 queryWrapper.eq("status", status);
             }
@@ -149,4 +154,28 @@ public class TtsRequestLogController {
             return ResponseEntity.status(500).body(result);
         }
     }
+    
+    @PostMapping("/speech-to-text")
+    @Operation(summary = "语音转文本", description = "将语音文件转换为文本")
+    public ResponseEntity<AsrResponse> speechToText(
+            @Parameter(description = "语音转文本请求参数") @RequestBody AsrRequest request) {
+        
+        try {
+            if (!ttsRequestLogService.isAsrServiceAvailable()) {
+                return ResponseEntity.status(500).body(AsrResponse.error("ASR服务不可用，请检查配置"));
+            }
+            
+            AsrResponse response = ttsRequestLogService.speechToText(request);
+            
+            if (response.isSuccess()) {
+                return ResponseEntity.ok(response);
+            } else {
+                return ResponseEntity.status(500).body(response);
+            }
+            
+        } catch (Exception e) {
+            log.error("语音转文本失败: {}", e.getMessage(), e);
+            return ResponseEntity.status(500).body(AsrResponse.error("语音转文本失败: " + e.getMessage()));
+        }
+    }
 }

src/main/java/com/rj/controller/sys/MenuController.java

@@ -401,6 +401,9 @@ public class MenuController {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/controller/sys/RoleController.java

@@ -371,6 +371,9 @@ public class RoleController {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/controller/sys/UserRoleController.java

@@ -377,6 +377,9 @@ public class UserRoleController {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/dto/AsrRequest.java

@@ -0,0 +1,90 @@
+package com.rj.dto;
+
+import io.swagger.v3.oas.annotations.media.Schema;
+import lombok.Data;
+
+import jakarta.validation.constraints.NotBlank;
+
+/**
+ * 语音转文本请求DTO
+ * 
+ * @author rj
+ * @date 2025-01-02
+ */
+@Data
+@Schema(description = "语音转文本请求参数")
+public class AsrRequest {
+    
+    /**
+     * 音频文件URL
+     */
+    @NotBlank(message = "音频文件URL不能为空")
+    @Schema(description = "音频文件URL", example = "https://example.com/audio.mp3")
+    private String audioUrl;
+    
+    /**
+     * 模型名称
+     */
+    @Schema(description = "ASR模型名称", example = "paraformer-v2")
+    private String model = "paraformer-v2";
+    
+    /**
+     * 音频格式
+     */
+    @Schema(description = "音频格式", example = "wav")
+    private String format = "wav";
+    
+    /**
+     * 采样率
+     */
+    @Schema(description = "采样率", example = "16000")
+    private Integer sampleRate = 16000;
+    
+    /**
+     * 是否启用标点符号
+     */
+    @Schema(description = "是否启用标点符号", example = "true")
+    private Boolean enablePunctuation = true;
+    
+    /**
+     * 是否启用数字转换
+     */
+    @Schema(description = "是否启用数字转换", example = "true")
+    private Boolean enableNumberConversion = true;
+    
+    /**
+     * 是否启用说话人分离
+     */
+    @Schema(description = "是否启用说话人分离", example = "false")
+    private Boolean enableSpeakerDiarization = false;
+    
+    /**
+     * 说话人数量
+     */
+    @Schema(description = "说话人数量", example = "1")
+    private Integer speakerCount = 1;
+    
+    /**
+     * 创建人姓名
+     */
+    @Schema(description = "创建人姓名", example = "张三")
+    private String creatorName;
+    
+    /**
+     * 创建人电话
+     */
+    @Schema(description = "创建人电话", example = "13800138000")
+    private String creatorPhone;
+    
+    /**
+     * 音频名称
+     */
+    @Schema(description = "音频名称", example = "test_audio")
+    private String audioName;
+    
+    /**
+     * 关联的TTS请求日志ID
+     */
+    @Schema(description = "关联的TTS请求日志ID", example = "12345678-1234-1234-1234-123456789012")
+    private String id;
+}

src/main/java/com/rj/dto/AsrResponse.java

@@ -0,0 +1,160 @@
+package com.rj.dto;
+
+import io.swagger.v3.oas.annotations.media.Schema;
+import lombok.Data;
+
+import java.time.LocalDateTime;
+import java.util.List;
+
+/**
+ * 语音转文本响应DTO
+ * 
+ * @author rj
+ * @date 2025-01-02
+ */
+@Data
+@Schema(description = "语音转文本响应结果")
+public class AsrResponse {
+    
+    /**
+     * 是否成功
+     */
+    @Schema(description = "是否成功")
+    private boolean success;
+    
+    /**
+     * 消息
+     */
+    @Schema(description = "响应消息")
+    private String message;
+    
+    /**
+     * 识别结果文本
+     */
+    @Schema(description = "识别结果文本")
+    private String text;
+    
+    /**
+     * 识别结果列表（包含时间戳和说话人信息）
+     */
+    @Schema(description = "识别结果列表")
+    private List<AsrResult> results;
+    
+    /**
+     * 音频时长（秒）
+     */
+    @Schema(description = "音频时长（秒）")
+    private Double duration;
+    
+    /**
+     * 处理时间（毫秒）
+     */
+    @Schema(description = "处理时间（毫秒）")
+    private Long processingTimeMs;
+    
+    /**
+     * 任务ID
+     */
+    @Schema(description = "任务ID")
+    private String taskId;
+    
+    /**
+     * 请求ID
+     */
+    @Schema(description = "请求ID")
+    private String requestId;
+    
+    /**
+     * 错误代码
+     */
+    @Schema(description = "错误代码")
+    private String errorCode;
+    
+    /**
+     * 错误信息
+     */
+    @Schema(description = "错误信息")
+    private String errorMessage;
+    
+    /**
+     * 创建时间
+     */
+    @Schema(description = "创建时间")
+    private LocalDateTime createTime;
+    
+    /**
+     * 识别结果详情
+     */
+    @Data
+    @Schema(description = "识别结果详情")
+    public static class AsrResult {
+        
+        /**
+         * 开始时间（秒）
+         */
+        @Schema(description = "开始时间（秒）")
+        private Double startTime;
+        
+        /**
+         * 结束时间（秒）
+         */
+        @Schema(description = "结束时间（秒）")
+        private Double endTime;
+        
+        /**
+         * 识别文本
+         */
+        @Schema(description = "识别文本")
+        private String text;
+        
+        /**
+         * 说话人ID
+         */
+        @Schema(description = "说话人ID")
+        private String speakerId;
+        
+        /**
+         * 置信度
+         */
+        @Schema(description = "置信度")
+        private Double confidence;
+    }
+    
+    /**
+     * 创建成功响应
+     */
+    public static AsrResponse success(String text, List<AsrResult> results, Double duration, 
+                                    Long processingTimeMs, String taskId, String requestId) {
+        AsrResponse response = new AsrResponse();
+        response.setSuccess(true);
+        response.setMessage("语音识别成功");
+        response.setText(text);
+        response.setResults(results);
+        response.setDuration(duration);
+        response.setProcessingTimeMs(processingTimeMs);
+        response.setTaskId(taskId);
+        response.setRequestId(requestId);
+        response.setCreateTime(LocalDateTime.now());
+        return response;
+    }
+    
+    /**
+     * 创建错误响应
+     */
+    public static AsrResponse error(String message) {
+        return error(message, null, null);
+    }
+    
+    /**
+     * 创建错误响应
+     */
+    public static AsrResponse error(String message, String errorCode, String errorMessage) {
+        AsrResponse response = new AsrResponse();
+        response.setSuccess(false);
+        response.setMessage(message);
+        response.setErrorCode(errorCode);
+        response.setErrorMessage(errorMessage);
+        response.setCreateTime(LocalDateTime.now());
+        return response;
+    }
+}

src/main/java/com/rj/dto/DifyWorkflowResponseDto.java

@@ -143,6 +143,9 @@ public class DifyWorkflowResponseDto {
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/entity/CustomerManagement.java

@@ -73,5 +73,9 @@ public class CustomerManagement implements Serializable {
     @TableField("update_time")
     private LocalDateTime updateTime;
 
+    @Schema(description = "备注")
+    @TableField("remark")
+    private String remark;
+
 
 }

src/main/java/com/rj/mapper/CustomerProfileAnalysisMapper.java

@@ -86,6 +86,9 @@ public interface CustomerProfileAnalysisMapper extends BaseMapper<CustomerProfil
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/service/ITtsRequestLogService.java

@@ -2,6 +2,8 @@ package com.rj.service;
 
 import com.rj.entity.TtsRequestLog;
 import com.rj.utils.MinIOUrlGenerator;
+import com.rj.dto.AsrRequest;
+import com.rj.dto.AsrResponse;
 
 /**
  * TTS请求日志服务接口
@@ -41,4 +43,19 @@ public interface ITtsRequestLogService {
      * @return 是否设置成功
      */
     boolean setShortUrlByAudioName(String audioName);
+    
+    /**
+     * 语音转文本
+     * 
+     * @param request ASR请求
+     * @return ASR响应
+     */
+    AsrResponse speechToText(AsrRequest request);
+    
+    /**
+     * 检查ASR服务是否可用
+     * 
+     * @return 是否可用
+     */
+    boolean isAsrServiceAvailable();
 }

src/main/java/com/rj/service/biz/ICustomerProfileAnalysisService.java

@@ -107,6 +107,9 @@ public interface ICustomerProfileAnalysisService extends IService<CustomerProfil
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/service/biz/impl/CustomerProfileAnalysisServiceImpl.java

@@ -142,6 +142,9 @@ public class CustomerProfileAnalysisServiceImpl extends ServiceImpl<CustomerProf
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/service/impl/TtsRequestLogServiceImpl.java

@@ -1,15 +1,24 @@
 package com.rj.service.impl;
 
+import com.alibaba.dashscope.audio.asr.transcription.*;
 import com.rj.entity.TtsRequestLog;
 import com.rj.mapper.TtsRequestLogMapper;
 import com.rj.service.ITtsRequestLogService;
 import com.rj.utils.MinIOUrlGenerator;
+import com.rj.dto.AsrRequest;
+import com.rj.dto.AsrResponse;
 import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
 import lombok.extern.slf4j.Slf4j;
 import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.beans.factory.annotation.Value;
 import org.springframework.stereotype.Service;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.databind.JsonNode;
 
 import java.time.LocalDateTime;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
 
 /**
  * TTS请求日志服务实现类
@@ -27,6 +36,15 @@ public class TtsRequestLogServiceImpl implements ITtsRequestLogService {
     @Autowired
     private MinIOUrlGenerator urlGenerator;
     
+    @Value("${dashscope.api.key}")
+    private String apiKey;
+    
+    @Value("${asr.enabled:true}")
+    private boolean asrEnabled;
+    
+    @Value("${asr.default-model:paraformer-v2}")
+    private String defaultAsrModel;
+    
     @Override
     public boolean saveTtsRequestLog(TtsRequestLog requestLog) {
         try {
@@ -52,7 +70,7 @@ public class TtsRequestLogServiceImpl implements ITtsRequestLogService {
     @Override
     public boolean setShortUrlByAudioName(MinIOUrlGenerator.UrlInfo urlInfo ) {
         try {
-            if (urlInfo == null || urlInfo.getFileName().trim().isEmpty()) {
+            if (urlInfo == null || urlInfo.getFileName() == null || urlInfo.getFileName().trim().isEmpty()) {
                 log.error("音频名称不能为空");
                 return false;
             }
@@ -92,4 +110,291 @@ public class TtsRequestLogServiceImpl implements ITtsRequestLogService {
     public boolean setShortUrlByAudioName(String audioName) {
         return false;
     }
+    
+    @Override
+    public AsrResponse speechToText(AsrRequest request) {
+        long startTime = System.currentTimeMillis();
+        
+        try {
+            if (!isAsrServiceAvailable()) {
+                return AsrResponse.error("ASR服务不可用，请检查配置");
+            }
+            
+            if (request.getAudioUrl() == null || request.getAudioUrl().trim().isEmpty()) {
+                return AsrResponse.error("音频文件URL不能为空");
+            }
+            
+            // 设置默认值
+            if (request.getModel() == null || request.getModel().trim().isEmpty()) {
+                request.setModel(defaultAsrModel);
+            }
+            if (request.getFormat() == null || request.getFormat().trim().isEmpty()) {
+                request.setFormat("wav");
+            }
+            if (request.getSampleRate() == null) {
+                request.setSampleRate(16000);
+            }
+            if (request.getEnablePunctuation() == null) {
+                request.setEnablePunctuation(true);
+            }
+            if (request.getEnableNumberConversion() == null) {
+                request.setEnableNumberConversion(true);
+            }
+            if (request.getEnableSpeakerDiarization() == null) {
+                request.setEnableSpeakerDiarization(false);
+            }
+            if (request.getSpeakerCount() == null) {
+                request.setSpeakerCount(1);
+            }
+            
+            log.info("开始语音识别 - 音频URL: {}, 模型: {}, 格式: {}, 采样率: {}", 
+                    request.getAudioUrl(), request.getModel(), request.getFormat(), request.getSampleRate());
+            
+            // 创建转写请求参数
+            TranscriptionParam param = TranscriptionParam.builder()
+                    .apiKey(apiKey)
+                    .model(request.getModel())
+                    .fileUrls(Arrays.asList(request.getAudioUrl()))
+                    .build();
+            
+            // 创建转写对象
+            Transcription transcription = new Transcription();
+            
+            // 提交转写请求
+            TranscriptionResult result = transcription.asyncCall(param);
+            String taskId = result.getTaskId();
+            String requestId = result.getRequestId();
+            
+            log.info("ASR任务已提交 - TaskId: {}, RequestId: {}", taskId, requestId);
+            
+            // 等待任务完成
+            TranscriptionQueryParam queryParam = TranscriptionQueryParam.FromTranscriptionParam(param, taskId);
+            result = transcription.wait(queryParam);
+            log.info("语音识别完成 - result: {} ", result);
+            long processingTime = System.currentTimeMillis() - startTime;
+            
+            if (result.getResults() != null && !result.getResults().isEmpty()) {
+                // 解析识别结果 - 从results中获取transcriptionUrl并下载识别结果
+                String fullText = "";
+                Double duration = 0.0;
+                List<AsrResponse.AsrResult> asrResults = new ArrayList<>();
+                
+                try {
+                    // 从usage中获取时长信息
+                    if (result.getUsage() != null) {
+                        // 从usage对象中获取duration，usage通常是一个JsonObject
+                        try {
+                            String usageStr = result.getUsage().toString();
+                            if (usageStr.contains("\"duration\"")) {
+                                int durationStart = usageStr.indexOf("\"duration\":") + 11;
+                                int durationEnd = usageStr.indexOf(",", durationStart);
+                                if (durationEnd == -1) {
+                                    durationEnd = usageStr.indexOf("}", durationStart);
+                                }
+                                if (durationStart > 10 && durationEnd > durationStart) {
+                                    duration = Double.parseDouble(usageStr.substring(durationStart, durationEnd).trim());
+                                }
+                            }
+                        } catch (Exception e) {
+                            log.warn("解析usage中的duration失败: {}", e.getMessage());
+                        }
+                    }
+                    
+                    // 遍历所有结果，获取transcriptionUrl并下载识别文本
+                    for (TranscriptionTaskResult taskResult : result.getResults()) {
+                        if (taskResult.getTranscriptionUrl() != null) {
+                            try {
+                                // 从transcriptionUrl下载识别结果
+                                String transcriptionResult = downloadTranscriptionResult(taskResult.getTranscriptionUrl());
+                                log.info("transcriptionResult: {}" , transcriptionResult);
+
+                                if (transcriptionResult != null && !transcriptionResult.trim().isEmpty()) {
+                                    // 解析transcription结果JSON
+                                    String extractedText = parseTranscriptionResult(transcriptionResult);
+                                    if (extractedText != null && !extractedText.trim().isEmpty()) {
+                                        fullText += extractedText;
+                                        
+                                        // 输出识别文本到控制台
+                                        System.out.println("=== 语音识别结果 ===");
+                                        System.out.println("任务ID: " + taskId);
+                                        System.out.println("识别文本: " + extractedText);
+                                        System.out.println("==================");
+                                        
+                                        // 创建结果对象
+                                        AsrResponse.AsrResult asrResult = new AsrResponse.AsrResult();
+                                        asrResult.setText(extractedText);
+                                        asrResult.setStartTime(0.0);
+                                        asrResult.setEndTime(duration);
+                                        asrResults.add(asrResult);
+                                    }
+                                }
+                            } catch (Exception e) {
+                                log.warn("下载transcription结果失败: {}", e.getMessage());
+                            }
+                        }
+                    }
+                    
+                } catch (Exception e) {
+                    log.warn("解析ASR结果时出错: {}", e.getMessage());
+                }
+                
+                if (fullText.trim().isEmpty()) {
+                    log.warn("ASR识别结果为空 - TaskId: {}", taskId);
+                    return AsrResponse.error("语音识别结果为空");
+                }
+                
+                log.info("语音识别完成 - 识别文本长度: {}, 处理时间: {}ms", fullText.length(), processingTime);
+                
+                // 如果提供了TTS日志ID，则保存识别文本到数据库
+                if (request.getId() != null && !request.getId().trim().isEmpty()) {
+                    saveRecognizedTextToDatabase(request.getId(), fullText);
+                }
+                
+                return AsrResponse.success(fullText, asrResults, duration, processingTime, taskId, requestId);
+            } else {
+                log.warn("ASR识别结果为空 - TaskId: {}", taskId);
+                return AsrResponse.error("语音识别结果为空");
+            }
+            
+        } catch (Exception e) {
+            log.error("语音识别失败: {}", e.getMessage(), e);
+            return AsrResponse.error("语音识别失败: " + e.getMessage());
+        }
+    }
+    
+    @Override
+    public boolean isAsrServiceAvailable() {
+        return asrEnabled && apiKey != null && !apiKey.trim().isEmpty();
+    }
+    
+    /**
+     * 下载transcription结果
+     */
+    private String downloadTranscriptionResult(String transcriptionUrl) {
+        try {
+            log.info("开始下载transcription结果，URL: {}", transcriptionUrl);
+            
+            // 使用简单的URL连接下载transcription结果，避免HttpClient依赖问题
+            java.net.URL url = new java.net.URL(transcriptionUrl);
+            java.net.HttpURLConnection connection = (java.net.HttpURLConnection) url.openConnection();
+            
+            // 设置请求头
+            connection.setRequestMethod("GET");
+            connection.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36");
+            connection.setRequestProperty("Accept", "application/json");
+            connection.setConnectTimeout(30000); // 30秒连接超时
+            connection.setReadTimeout(60000);   // 60秒读取超时
+            
+            int responseCode = connection.getResponseCode();
+            if (responseCode == 200) {
+                // 读取响应内容
+                StringBuilder result = new StringBuilder();
+                try (java.io.BufferedReader reader = new java.io.BufferedReader(
+                        new java.io.InputStreamReader(connection.getInputStream(), java.nio.charset.StandardCharsets.UTF_8))) {
+                    String line;
+                    while ((line = reader.readLine()) != null) {
+                        result.append(line).append("\n");
+                    }
+                }
+                
+                String responseBody = result.toString().trim();
+                log.info("成功下载transcription结果，长度: {} 字符", responseBody.length());
+                return responseBody;
+            } else {
+                log.warn("下载transcription结果失败，状态码: {}", responseCode);
+                return null;
+            }
+        } catch (Exception e) {
+            log.error("下载transcription结果异常: {}", e.getMessage(), e);
+            return null;
+        }
+    }
+    
+    /**
+     * 解析transcription结果JSON，提取识别文本
+     */
+    private String parseTranscriptionResult(String transcriptionJson) {
+        try {
+            // 使用Jackson解析JSON
+            ObjectMapper mapper = new ObjectMapper();
+            JsonNode rootNode = mapper.readTree(transcriptionJson);
+            
+            log.info("开始解析transcription JSON");
+            
+            // 根据阿里云ASR返回的JSON结构解析
+            // 阿里云返回的结构: {"transcripts": [{"text": "识别的文本", "sentences": [...]}]}
+            JsonNode transcriptsNode = rootNode.get("transcripts");
+            if (transcriptsNode != null && transcriptsNode.isArray() && transcriptsNode.size() > 0) {
+                JsonNode firstTranscript = transcriptsNode.get(0);
+                JsonNode textNode = firstTranscript.get("text");
+                if (textNode != null && !textNode.isNull()) {
+                    String text = textNode.asText();
+                    log.info("成功提取识别文本: {}", text);
+                    return text;
+                }
+            }
+            
+            // 如果没有transcripts字段，尝试其他可能的字段结构
+            JsonNode resultsNode = rootNode.get("results");
+            if (resultsNode != null && resultsNode.isArray()) {
+                StringBuilder textBuilder = new StringBuilder();
+                for (JsonNode resultNode : resultsNode) {
+                    JsonNode textNode = resultNode.get("text");
+                    if (textNode != null && !textNode.isNull()) {
+                        String text = textNode.asText();
+                        textBuilder.append(text).append(" ");
+                        log.info("提取到文本片段: {}", text);
+                    }
+                }
+                String fullText = textBuilder.toString().trim();
+                if (!fullText.isEmpty()) {
+                    log.info("完整识别文本: {}", fullText);
+                    return fullText;
+                }
+            }
+            
+            // 如果没有results字段，尝试直接获取text字段
+            JsonNode textNode = rootNode.get("text");
+            if (textNode != null && !textNode.isNull()) {
+                String text = textNode.asText();
+                log.info("直接获取文本: {}", text);
+                return text;
+            }
+            
+            // 如果都没有，记录JSON结构用于调试
+            log.warn("未找到预期的文本字段，JSON结构: {}", rootNode.toString());
+            return null;
+        } catch (Exception e) {
+            log.error("解析transcription结果JSON失败: {}", e.getMessage(), e);
+            return null;
+        }
+    }
+    
+    /**
+     * 保存识别文本到数据库
+     */
+    private void saveRecognizedTextToDatabase(String ttsLogId, String recognizedText) {
+        try {
+            // 根据ID查询TTS请求日志
+            TtsRequestLog ttsLog = ttsRequestLogMapper.selectById(ttsLogId);
+            if (ttsLog != null) {
+                // 将识别文本保存到inputText字段
+                ttsLog.setInputText(recognizedText);
+                ttsLog.setInputLength(recognizedText.length());
+                ttsLog.setUpdateTime(LocalDateTime.now());
+                
+                // 保存到数据库
+                int updateResult = ttsRequestLogMapper.updateById(ttsLog);
+                if (updateResult > 0) {
+                    log.info("成功保存识别文本到数据库，TTS日志ID: {}, 文本长度: {}", ttsLogId, recognizedText.length());
+                } else {
+                    log.warn("保存识别文本到数据库失败，TTS日志ID: {}", ttsLogId);
+                }
+            } else {
+                log.warn("未找到对应的TTS请求日志，ID: {}", ttsLogId);
+            }
+        } catch (Exception e) {
+            log.error("保存识别文本到数据库异常: {}", e.getMessage(), e);
+        }
+    }
 }

src/main/java/com/rj/service/sys/impl/MenuServiceImpl.java

@@ -114,6 +114,9 @@ public class MenuServiceImpl extends ServiceImpl<MenuMapper, Menu> implements IM
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/service/sys/impl/RoleServiceImpl.java

@@ -114,6 +114,9 @@ public class RoleServiceImpl extends ServiceImpl<RoleMapper, Role> implements IR
 
 
 
+
+
+
 
 
 

src/main/java/com/rj/service/sys/impl/UserRoleServiceImpl.java

@@ -114,6 +114,9 @@ public class UserRoleServiceImpl extends ServiceImpl<UserRoleMapper, UserRole> i
 
 
 
+
+
+
 
 
 

src/main/resources/application-audio.yml

@@ -123,6 +123,9 @@ spring:
 
 
 
+
+
+
 
 
 

src/main/resources/application.properties

@@ -1 +1 @@
-spring.application.name=Langchain4j-heima20250803
+spring.application.name=Langchain4j-cst20250803

src/main/resources/application.yml

@@ -125,6 +125,27 @@ aliyun:
   # 是否启用阿里云服务
   enabled: true
 
+# ASR语音识别配置
+asr:
+  # 是否启用ASR服务
+  enabled: true
+  # 默认ASR模型
+  default-model: paraformer-v2
+  # 请求超时时间（毫秒）
+  timeout: 60000
+  # 是否启用标点符号
+  enable-punctuation: true
+  # 是否启用数字转换
+  enable-number-conversion: true
+  # 是否启用说话人分离
+  enable-speaker-diarization: false
+  # 默认说话人数量
+  default-speaker-count: 1
+  # 默认音频格式
+  default-format: wav
+  # 默认采样率
+  default-sample-rate: 16000
+
 
 springdoc:
   swagger-ui:

src/main/resources/mapper/AudioManagementStatisticsMapper.xml

@@ -100,6 +100,9 @@
 
 
 
+
+
+
 
 
 

src/main/resources/mapper/CustomerManagementMapper.xml

@@ -14,13 +14,14 @@
         <result column="recording_count" property="recordingCount" />
         <result column="intended_model" property="intendedModel" />
         <result column="info_card" property="infoCard" />
+        <result column="remark" property="remark" />
         <result column="create_time" property="createTime" />
         <result column="update_time" property="updateTime" />
     </resultMap>
 
     <!-- 通用查询结果列 -->
     <sql id="Base_Column_List">
-        id, customer_name, contact, dealership_id, dealership_name, sales_id, sales_name, recording_count, intended_model, info_card, create_time, update_time
+        id, customer_name, contact, dealership_id, dealership_name, sales_id, sales_name, recording_count, intended_model, info_card, remark, create_time, update_time
     </sql>
 
 </mapper>

src/main/resources/static/tts-demo.html

@@ -299,6 +299,9 @@
 
 
 
+
+
+
 
 
 

src/main/sql/customer_management.sql

@@ -32,6 +32,7 @@ CREATE TABLE `customer_management`  (
   `recording_count` int NULL DEFAULT 0 COMMENT '录音条数',
   `intended_model` varchar(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '意向车型',
   `info_card` varchar(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '信息卡',
+  `remark` varchar(500) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '备注',
   `create_time` datetime NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
   `update_time` datetime NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '更新时间',
   PRIMARY KEY (`id`) USING BTREE

src/test/java/com/rj/Langchain4jHeima20250803ApplicationTests.java

@@ -1,13 +0,0 @@
-package com.rj;
-
-import org.junit.jupiter.api.Test;
-import org.springframework.boot.test.context.SpringBootTest;
-
-@SpringBootTest
-class Langchain4jHeima20250803ApplicationTests {
-
-    @Test
-    void contextLoads() {
-    }
-
-}

src/test/java/com/rj/service/FaceDetectImageCountTest.java

@@ -237,6 +237,9 @@ public class FaceDetectImageCountTest {
 
 
 
+
+
+
 
 
 

src/test/java/com/rj/service/TtsRequestLogServiceAsrTest.java

@@ -0,0 +1,63 @@
+package com.rj.service;
+
+import com.rj.dto.AsrRequest;
+import com.rj.dto.AsrResponse;
+import org.junit.jupiter.api.Test;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.boot.test.context.SpringBootTest;
+
+/**
+ * TtsRequestLogService ASR功能测试类
+ * 
+ * @author rj
+ * @date 2025-01-02
+ */
+@SpringBootTest
+public class TtsRequestLogServiceAsrTest {
+    
+    @Autowired
+    private ITtsRequestLogService ttsRequestLogService;
+    
+    @Test
+    public void testSpeechToText() {
+        // 创建测试请求
+        AsrRequest request = new AsrRequest();
+        request.setAudioUrl("https://api.huayang-star.com/api/audio/1957424645898579969_a2db5d76-b52c-4289-9c7e-ed55d7f15e42.mp3");
+        request.setModel("paraformer-v2");
+        request.setFormat("mp3");
+        request.setSampleRate(16000);
+        request.setEnablePunctuation(true);
+        request.setEnableNumberConversion(true);
+        request.setCreatorName("测试用户");
+        request.setCreatorPhone("13800138000");
+        request.setAudioName("测试音频");
+        
+        // 执行语音识别
+        AsrResponse response = ttsRequestLogService.speechToText(request);
+        
+        // 打印结果
+        System.out.println("识别结果: " + response.isSuccess());
+        System.out.println("识别文本: " + response.getText());
+        System.out.println("处理时间: " + response.getProcessingTimeMs() + "ms");
+        System.out.println("任务ID: " + response.getTaskId());
+        System.out.println("请求ID: " + response.getRequestId());
+        
+        if (response.getResults() != null && !response.getResults().isEmpty()) {
+            System.out.println("结果详情:");
+            for (AsrResponse.AsrResult result : response.getResults()) {
+                System.out.println("  文本: " + result.getText());
+                System.out.println("  开始时间: " + result.getStartTime());
+                System.out.println("  结束时间: " + result.getEndTime());
+                System.out.println("  说话人ID: " + result.getSpeakerId());
+                System.out.println("  置信度: " + result.getConfidence());
+            }
+        }
+    }
+    
+    @Test
+    public void testAsrServiceAvailable() {
+        boolean available = ttsRequestLogService.isAsrServiceAvailable();
+        System.out.println("ASR服务是否可用: " + available);
+    }
+}
+

src/test/java/com/rj/service/TtsRequestLogShortUrlTest.java

@@ -178,6 +178,9 @@ public class TtsRequestLogShortUrlTest {
 
 
 
+
+
+
 
 
 

src/test/java/com/rj/service/VideoSynthesisTempUrlTest.java

@@ -156,6 +156,9 @@ public class VideoSynthesisTempUrlTest {
 
 
 
+
+
+
 
 
 

src/test/java/com/rj/service/VideoSynthesisVideoNameTest.java

@@ -131,6 +131,9 @@ public class VideoSynthesisVideoNameTest {
 
 
 
+
+
+