Merge branch 'feature_20260507_recall_strategy_exp' of algorithm/recommend-server into master

recommend-server-service/src/main/java/com/tzld/piaoquan/recommend/server/service/rank/strategy/RankStrategy4RegionMergeModelV564.java

@@ -15,7 +15,6 @@ import com.tzld.piaoquan.recommend.server.service.recall.strategy.*;
 import com.tzld.piaoquan.recommend.server.service.score.ScorerUtils;
 import com.tzld.piaoquan.recommend.server.util.*;
 import lombok.extern.slf4j.Slf4j;
-import org.apache.commons.collections4.CollectionUtils;
 import org.apache.commons.collections4.MapUtils;
 import org.apache.commons.lang3.StringUtils;
 import org.springframework.beans.factory.annotation.Autowired;
@@ -24,9 +23,18 @@ import org.springframework.stereotype.Service;
 import java.util.*;
 import java.util.concurrent.Future;
 import java.util.concurrent.TimeUnit;
-import java.util.stream.Collectors;
-import java.util.stream.Stream;
 
+/**
+ * V564 实验：基于 V569,移除以下 8 路召回
+ *   - recall_pool_region_h     (RegionHRecallStrategy)
+ *   - recall_pool_24h          (RegionRelative24HRecallStrategy)
+ *   - recall_pool_region_24h   (Region24HRecallStrategy)
+ *   - rov_recall_24h_dup       (RegionRelative24HDupRecallStrategy)
+ *   - rov_recall_h_h           (RegionHDupRecallStrategy)
+ *   - priori_province_rovn     (PrioriProvinceRovnRecallStrategy)
+ *   - priori_province_str      (PrioriProvinceStrRecallStrategy)
+ *   - priori_province_ros      (PrioriProvinceRosRecallStrategy)
+ */
 @Service
 @Slf4j
 public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeModelBasic {
@@ -49,8 +57,7 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
         Set<Long> setVideo = new HashSet<>();
         setVideo.add(param.getHeadVid());
         List<Video> rovRecallRank = new ArrayList<>();
-        // -------------------5路特殊旧召回------------------
-        RecallUtils.extractOldSpecialRecall(mergeWeight.getOrDefault("oldSpecialN", (double) param.getSize()).intValue(), param, setVideo, rovRecallRank);
+        // V564: 移除 5 路特殊旧召回 (RegionH / RegionHDup / Region24H / RegionRelative24H / RegionRelative24HDup)
         //-------------------return相似召回------------------
         RecallUtils.extractRecall(mergeWeight.getOrDefault("v6", 5.0).intValue(), param, ReturnVideoRecallStrategy.PUSH_FORM, setVideo, rovRecallRank);
         //-------------------新地域召回------------------
@@ -71,16 +78,13 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
         RecallUtils.extractRecall(mergeWeight.getOrDefault("headCate2Rov", 5.0).intValue(), param, HeadCate2RovRecallStrategy.PUSH_FROM, setVideo, rovRecallRank);
         //-------------------city rovn------------------
         RecallUtils.extractRecall(mergeWeight.getOrDefault("cityRov", 5.0).intValue(), param, CityRovnRecallStrategy.PUSH_FROM, setVideo, rovRecallRank);
-        //-------------------priori province rovn------------------
-        RecallUtils.extractRecall(mergeWeight.getOrDefault("prioriProvinceRov", 3.0).intValue(), param, PrioriProvinceRovnRecallStrategy.PUSH_FROM, setVideo, rovRecallRank);
-        //-------------------priori province str------------------
-        RecallUtils.extractRecall(mergeWeight.getOrDefault("prioriProvinceStr", 1.0).intValue(), param, PrioriProvinceStrRecallStrategy.PUSH_FROM, setVideo, rovRecallRank);
-        //-------------------priori province ros------------------
-        RecallUtils.extractRecall(mergeWeight.getOrDefault("prioriProvinceRos", 1.0).intValue(), param, PrioriProvinceRosRecallStrategy.PUSH_FROM, setVideo, rovRecallRank);
+        // V564: 移除 priori_province_rovn / priori_province_str / priori_province_ros
         //-------------------return1 cate2 ros------------------
         RecallUtils.extractRecall(mergeWeight.getOrDefault("return1Cate2Ros", 5.0).intValue(), param, Return1Cate2RosRecallStrategy.PUSH_FORM, setVideo, rovRecallRank);
         //-------------------return1 cate2 str------------------
         RecallUtils.extractRecall(mergeWeight.getOrDefault("return1Cate2Str", 5.0).intValue(), param, Return1Cate2StrRecallStrategy.PUSH_FORM, setVideo, rovRecallRank);
+        //--------------deconstruction keywords ros-------------
+        RecallUtils.extractRecall(mergeWeight.getOrDefault("deconstructionKeywordsRos", 5.0).intValue(), param, UserDeconstructionKeywordsRecallStrategy.PUSH_FORM, setVideo, rovRecallRank);
 
         // 记录召回源中的视频
         this.rankBeforePostProcessor(rovRecallRank);
@@ -94,22 +98,8 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
         // 1. 批量获取特征  省份参数要对齐  headvid  要传递过来！
         // k1:视频、k2:表、k3:特征、v:特征值
         Map<String, String> headVideoInfo = param.getHeadInfo();
-
-        // 用户的序列特征
-        Map<String, Map<String, String>> unionIdFeature = featureService.getUnionIdFeature(param.getUnionId());
-        Map<String, String> userNetworkSeqFeature = unionIdFeature.getOrDefault("alg_user_network_seq_feature", new HashMap<>());
-        List<String> actVidSeq = FeatureUtils.extractVidsFromUserNetworkSeqFeature(userNetworkSeqFeature, "a_v_s");
-        List<String> netVidSeq = FeatureUtils.extractVidsFromUserNetworkSeqFeature(userNetworkSeqFeature, "n_v_s");
-
         List<String> vids = CommonCollectionUtils.toListDistinct(rovRecallRank, v -> String.valueOf(v.getVideoId()));
-
-        List<String> allVids = Stream.of(actVidSeq, netVidSeq, vids)
-                .flatMap(Collection::stream)
-                .distinct()
-                .filter(StringUtils::isNotBlank)
-                .collect(Collectors.toList());
-
-        Map<String, Map<String, Map<String, String>>> videoBaseInfoMap = featureService.getVideoBaseInfo("", allVids);
+        Map<String, Map<String, Map<String, String>>> videoBaseInfoMap = featureService.getVideoBaseInfo("", vids);
         Map<String, Map<String, Map<String, String>>> videoBCData = featureService.getVideoStatistics(vids);
 
         FeatureService.Feature feature = featureService.getFeatureV4(param, headVideoInfo, videoBaseInfoMap, vids);
@@ -123,20 +113,15 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
         Map<String, Map<String, String>> userBehaviorVideoMap = param.getBehaviorVideos();
         Map<String, String> creativeInfo = param.getCreativeInfoFeature();
 
-        Map<String, String> featureMapToString = new HashMap<>();
-        FeatureV6.parseStringFeatureMap(featureMapToString, param);
-        FeatureV6.putVideoStringFeatures("h", headVideoInfo, featureMapToString);
-
         // 3. 特征处理
         List<RankItem> rankItems = CommonCollectionUtils.toList(rovRecallRank, RankItem::new);
         Map<String, Float> userFeatureMap = getUserFeature(currentMs, param, creativeInfo, headVideoInfo, userProfile, featureOriginUser);
         batchGetVideoFeature(currentMs, userProfile, creativeInfo, headVideoInfo, videoBaseInfoMap,
-                newC7Map, newC8Map, featureOriginUser, userBehaviorVideoMap, featureOriginVideo, featureMapToString, userFeatureMap, rankItems);
-
+                newC7Map, newC8Map, featureOriginUser, userBehaviorVideoMap, featureOriginVideo, rankItems);
 
         // 4. 排序模型计算
         Map<String, Float> sceneFeatureMap = new HashMap<>(0);
-        List<RankItem> items = ScorerUtils.getScorerPipeline("feeds_score_config_dnn_20260417.conf").scoring(sceneFeatureMap, userFeatureMap, rankItems);
+        List<RankItem> items = ScorerUtils.getScorerPipeline("feeds_score_config_str_and_ros_20260319.conf").scoring(sceneFeatureMap, userFeatureMap, userFeatureMap, rankItems);
 
         // 5. 排序公式特征
         double xgbRovNegRate = mergeWeight.getOrDefault("xgbRovNegRate", 0.059);
@@ -158,15 +143,9 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
         double b0Ror1hW = mergeWeight.getOrDefault("b0_ror_1h_w", 0d);
         double b0Ror24hW = mergeWeight.getOrDefault("b0_ror_24h_w", 0d);
 
-        double cnRovn1hW = mergeWeight.getOrDefault("cn_rovn_1h_w", 0d);
-        double cnRovn24hW = mergeWeight.getOrDefault("cn_rovn_24h_w", 0d);
-
-        double dnRovn1hW = mergeWeight.getOrDefault("dn_rovn_1h_w", 0d);
-        double dnRovn24hW = mergeWeight.getOrDefault("dn_rovn_24h_w", 0d);
-
         Map<String, Map<String, String>> vid2MapFeature = this.getVideoRedisFeature(vids, "redis:vid_hasreturn_vor:");
 
-
+        // 获取权重
         Map<String, String> contextInfo = getContextInfo(param);
 
         List<Video> result = new ArrayList<>();
@@ -180,9 +159,8 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
             double hasReturnRovScore = Double.parseDouble(vid2MapFeature.getOrDefault(item.getVideoId() + "", new HashMap<>()).getOrDefault("rov", "0"));
             item.getScoresMap().put("hasReturnRovScore", hasReturnRovScore);
 
-            double norDNNScore = item.getScoresMap().getOrDefault("NorDNNScore", 0d);
-            double newNorDNNScore = norPowerCalibration(xgbNorPowerWeight, xgbNorPowerExp, norDNNScore);
-            item.getScoresMap().put("newNorDNNScore", newNorDNNScore);
+            double norXGBScore = item.getScoresMap().getOrDefault("NorXGBScore", 0d);
+            double newNorXGBScore = norPowerCalibration(xgbNorPowerWeight, xgbNorPowerExp, norXGBScore);
             item.getScoresMap().put("rosAdd", rosAdd);
             item.getScoresMap().put("rosW", rosW);
 
@@ -192,7 +170,6 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
             item.getScoresMap().put("vorW", vorW);
 
             Map<String, String> bcData = videoBCData.getOrDefault(String.valueOf(item.getVideoId()), new HashMap<>()).getOrDefault("alg_vid_feature_b_c_data", new HashMap<>());
-            Map<String, String> cdNData = videoBCData.getOrDefault(String.valueOf(item.getVideoId()), new HashMap<>()).getOrDefault("alg_vid_feature_cn_dn_data", new HashMap<>());
 
             double c1Rovn1h = Double.parseDouble(bcData.getOrDefault("c1_rovn_1h", "0"));
             double c1Rovn24h = Double.parseDouble(bcData.getOrDefault("c1_rovn_24h", "0"));
@@ -212,7 +189,6 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
             item.getScoresMap().put("b0Str24hW", b0Str24hW);
             item.getScoresMap().put("b0Str24h", b0Str24h);
 
-
             double b0Ror1h = Double.parseDouble(bcData.getOrDefault("b_ror1_1h", "0"));
             double b0Ror24h = Double.parseDouble(bcData.getOrDefault("b_ror1_24h", "0"));
             double b0RorScore = b0Ror1hW * b0Ror1h + b0Ror24hW * b0Ror24h;
@@ -222,25 +198,7 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
             item.getScoresMap().put("b0Ror24hW", b0Ror24hW);
             item.getScoresMap().put("b0Ror24h", b0Ror24h);
 
-            double cnRovn1h = Double.parseDouble(cdNData.getOrDefault("cn_rovn_1h", "0"));
-            double cnRovn24h = Double.parseDouble(cdNData.getOrDefault("cn_rovn_24h", "0"));
-            double cnRovnScore = cnRovn1hW * cnRovn1h + cnRovn24hW * cnRovn24h;
-            item.getScoresMap().put("cnRovnScore", cnRovnScore);
-            item.getScoresMap().put("cnRovn1hW", cnRovn1hW);
-            item.getScoresMap().put("cnRovn1h", cnRovn1h);
-            item.getScoresMap().put("cnRovn24hW", cnRovn24hW);
-            item.getScoresMap().put("cnRovn24h", cnRovn24h);
-
-            double dnRovn1h = Double.parseDouble(cdNData.getOrDefault("dn_rovn_1h", "0"));
-            double dnRovn24h = Double.parseDouble(cdNData.getOrDefault("dn_rovn_24h", "0"));
-            double dnRovnScore = dnRovn1hW * dnRovn1h + dnRovn24hW * dnRovn24h;
-            item.getScoresMap().put("dnRovnScore", dnRovnScore);
-            item.getScoresMap().put("dnRovn1hW", dnRovn1hW);
-            item.getScoresMap().put("dnRovn1h", dnRovn1h);
-            item.getScoresMap().put("dnRovn24hW", dnRovn24hW);
-            item.getScoresMap().put("dnRovn24h", dnRovn24h);
-
-            score = fmRov * (rosAdd + rosW * newNorDNNScore) * (vorAdd + vorW * vor) + c1RovnScore + b0StrScore + b0RorScore + cnRovnScore + dnRovnScore;
+            score = fmRov * (rosAdd + rosW * newNorXGBScore) * (vorAdd + vorW * vor) + c1RovnScore + b0StrScore + b0RorScore;
 
             Video video = item.getVideo();
             video.setScore(score);
@@ -274,7 +232,7 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
             if (MapUtils.isNotEmpty(contextInfo)) {
                 video.getMetaFeatureMap().put("context", contextInfo);
             }
-            if (Objects.nonNull(video.getRankVideoInfoMap()) && video.getRankVideoInfoMap().containsKey(video.getVideoId())) {
+            if (Objects.nonNull(video.getRankVideoInfoMap()) && video.getRankVideoInfoMap().containsKey(video.getVideoId())){
                 video.getRankVideoInfoMap().get(video.getVideoId()).setScore(score);
                 video.getRankVideoInfoMap().get(video.getVideoId()).setScoresMap(video.getScoresMap());
             }
@@ -361,28 +319,15 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
                                       Map<String, Map<String, String>> userOriginInfo,
                                       Map<String, Map<String, String>> historyVideoMap,
                                       Map<String, Map<String, Map<String, String>>> videoOriginInfo,
-                                      Map<String, String> featureMapToString,
-                                      Map<String, Float> userFeatureMap,
                                       List<RankItem> rankItems) {
-        if (CollectionUtils.isNotEmpty(rankItems)) {
+        if (null != rankItems && !rankItems.isEmpty()) {
             List<Future<Integer>> futures = new ArrayList<>();
             for (RankItem item : rankItems) {
                 String vid = item.getVideoId() + "";
                 Map<String, String> rankInfo = videoBaseInfoMap.getOrDefault(vid, new HashMap<>()).getOrDefault("alg_vid_feature_basic_info", new HashMap<>());
                 Future<Integer> future = ThreadPoolFactory.defaultPool().submit(() -> {
-                    Map<String, Float> featureMap = new HashMap<>(userFeatureMap);
-                    Map<String, Float> videoFeature = getVideoFeature(currentMs, vid, userProfile, creativeInfo, headInfo, rankInfo, c7Map, c8Map, userOriginInfo, historyVideoMap, videoOriginInfo);
-                    featureMap.putAll(videoFeature);
-                    item.featureMap = featureMap;
-
-                    Map<String, String> userNetworkSeqFeature = userOriginInfo.getOrDefault("alg_user_network_seq_feature", new HashMap<>());
-
-                    Map<String, String> featureMapString = new HashMap<>(featureMapToString);
-                    FeatureV6.putVideoStringFeatures("r", rankInfo, featureMapString);
-                    featureMapString.put("r@vid", "r_vid_" + vid);
-                    FeatureV6.putProfileVideoCrossStringFeature(currentMs, userProfile, historyVideoMap, featureMapString);
-                    FeatureV6.putUserNetworkSeqFeature(featureMapString, userNetworkSeqFeature, videoBaseInfoMap);
-                    item.featureMapString = featureMapString;
+                    item.featureMap = getVideoFeature(currentMs, vid, userProfile, creativeInfo, headInfo, rankInfo, c7Map, c8Map, userOriginInfo, historyVideoMap, videoOriginInfo);
+                    item.norFeatureMap = item.featureMap;
                     return 1;
                 });
                 futures.add(future);
@@ -454,4 +399,48 @@ public class RankStrategy4RegionMergeModelV564 extends RankStrategy4RegionMergeM
         }
         return newScore;
     }
+
+    private Map<String, Double> findSimCateScore(String headCate2, int length) {
+        if (StringUtils.isBlank(headCate2)) {
+            return new HashMap<>();
+        }
+
+        String redisKey = String.format("alg_recsys_good_cate_pair_list:%s", headCate2);
+        String cate2Value = redisTemplate.opsForValue().get(redisKey);
+        if (StringUtils.isEmpty(cate2Value)) {
+            return new HashMap<>();
+        }
+
+        return this.parsePair(cate2Value, length);
+    }
+
+    private Map<String, Double> parsePair(String value, int length) {
+        if (StringUtils.isBlank(value)) {
+            return new HashMap<>();
+        }
+
+        String[] split = value.split("\t");
+        if (split.length != 2) {
+            return new HashMap<>();
+        }
+
+        String[] valueList = split[0].trim().split(",");
+        String[] scoreList = split[1].trim().split(",");
+        if (valueList.length != scoreList.length) {
+            return new HashMap<>();
+        }
+
+        int minLength = Math.min(length, valueList.length);
+        Map<String, Double> resultMap = new HashMap<>();
+        for (int i = 0; i < minLength; i++) {
+            resultMap.put(valueList[i].trim(), Double.parseDouble(scoreList[i].trim()));
+        }
+
+        return resultMap;
+    }
+
+    private String findVideoMergeCate2(Map<String, Map<String, Map<String, String>>> featureOriginVideo, String vid) {
+        Map<String, String> videoInfo = featureOriginVideo.getOrDefault(vid, new HashMap<>()).getOrDefault("alg_vid_feature_basic_info", new HashMap<>());
+        return videoInfo.get("merge_second_level_cate");
+    }
 }