feat:解决冲突

ad-engine-service/src/main/java/com/tzld/piaoquan/ad/engine/service/score/RankService680.java

@@ -1,7 +1,6 @@
 package com.tzld.piaoquan.ad.engine.service.score;
 
 import com.ctrip.framework.apollo.spring.annotation.ApolloJsonValue;
-import com.tzld.piaoquan.ad.engine.commons.enums.RedisPrefixEnum;
 import com.tzld.piaoquan.ad.engine.commons.score.ScoreParam;
 import com.tzld.piaoquan.ad.engine.commons.score.ScorerUtils;
 import com.tzld.piaoquan.ad.engine.commons.thread.ThreadPoolFactory;
@@ -11,7 +10,6 @@ import com.tzld.piaoquan.ad.engine.service.score.dto.AdPlatformCreativeDTO;
 import com.tzld.piaoquan.ad.engine.service.score.param.RankRecommendRequestParam;
 import com.tzld.piaoquan.recommend.feature.domain.ad.base.AdRankItem;
 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.Value;
@@ -25,6 +23,7 @@ import java.io.InputStreamReader;
 import java.util.*;
 import java.util.concurrent.ConcurrentHashMap;
 import java.util.concurrent.CountDownLatch;
+import java.util.concurrent.Future;
 import java.util.concurrent.TimeUnit;
 import java.util.stream.Collectors;
 
@@ -37,8 +36,8 @@ public class RankService680 extends RankStrategyXGBBasic {
 
     private Map<String, Double> bucketsLen = new HashMap<>();
 
-    @Value("${similarity.concurrent: false}")
-    private boolean similarityConcurrent;
+    @Value("${word2vec.exp:694}")
+    private String word2vecExp;
 
     @ApolloJsonValue("${rank.score.weight.680:{}}")
     private Map<String, Double> weightMap;
@@ -59,6 +58,7 @@ public class RankService680 extends RankStrategyXGBBasic {
 
         long start = System.currentTimeMillis();
         // 特征处理
+        // feature1
         Feature feature = this.getFeature(scoreParam, request);
 
         Map<String, Map<String, String>> userFeature = feature.getUserFeature();
@@ -84,135 +84,124 @@ public class RankService680 extends RankStrategyXGBBasic {
         Map<String, String> sceneFeatureMap = this.handleSceneFeature(ts);
         long time1 = System.currentTimeMillis();
 
-        List<AdRankItem> adRankItems = new ArrayList<>(request.getAdIdList().size());
+        List<AdRankItem> adRankItems = new ArrayList<>();
         Random random = new Random();
-        if (similarityConcurrent) {
-            for (AdPlatformCreativeDTO dto : request.getAdIdList()) {
+        List<Future<AdRankItem>> futures = new ArrayList<>();
+        CountDownLatch cdl1 = new CountDownLatch(request.getAdIdList().size());
+        for (AdPlatformCreativeDTO dto : request.getAdIdList()) {
+            Future<AdRankItem> future = ThreadPoolFactory.feature().submit(() -> {
                 AdRankItem adRankItem = new AdRankItem();
-                adRankItem.setAdId(dto.getCreativeId());
-                adRankItem.setCreativeCode(dto.getCreativeCode());
-                adRankItem.setAdVerId(dto.getAdVerId());
-                adRankItem.setVideoId(request.getVideoId());
-                adRankItem.setCpa(dto.getCpa());
-                adRankItem.setId(dto.getAdId());
-                adRankItem.setCampaignId(dto.getCampaignId());
-                adRankItem.setCpm(ObjUtil.nullOrDefault(dto.getCpm(), 90).doubleValue());
-                adRankItem.setRandom(random.nextInt(1000));
-                if (noApiAdVerIds.contains(dto.getAdVerId())) {
-                    adRankItem.getExt().put("isApi", "0");
-                } else {
-                    adRankItem.getExt().put("isApi", "1");
-                }
-
-
-                String cidStr = dto.getCreativeId().toString();
-                Map<String, String> cidFeatureMap = adRankItem.getFeatureMap();
-                Map<String, Map<String, String>> cidFeature = allCidFeature.getOrDefault(cidStr, new HashMap<>());
-                Map<String, String> b1Feature = cidFeature.getOrDefault("alg_cid_feature_basic_info", new HashMap<>());
-
-                Map<String, Map<String, String>> adVerFeature = allAdVerFeature.getOrDefault(dto.getAdVerId(), new HashMap<>());
-
-                Map<String, String> d1Feature = cidFeature.getOrDefault("alg_cid_feature_vid_cf", new HashMap<>());
-
-                this.handleB1Feature(b1Feature, cidFeatureMap, cidStr);
-
-                this.handleB2ToB5AndB8ToB9Feature(cidFeature, adVerFeature, cidFeatureMap);
-
-                this.handleB6ToB7Feature(cidFeature, cidFeatureMap);
-
-                this.handleC1UIFeature(midTimeDiffMap, actionStaticMap, cidFeatureMap, cidStr);
-
-                this.handleD1Feature(d1Feature, cidFeatureMap);
-
-                this.handleD2Feature(vidRankMaps, cidFeatureMap, cidStr);
-
-                // adRankItem.setFeatureMap(cidFeatureMap);
+                try {
+                    adRankItem.setAdId(dto.getCreativeId());
+                    adRankItem.setCreativeCode(dto.getCreativeCode());
+                    adRankItem.setAdVerId(dto.getAdVerId());
+                    adRankItem.setVideoId(request.getVideoId());
+                    adRankItem.setCpa(dto.getCpa());
+                    adRankItem.setId(dto.getAdId());
+                    adRankItem.setCampaignId(dto.getCampaignId());
+                    adRankItem.setCpm(ObjUtil.nullOrDefault(dto.getCpm(), 90).doubleValue());
+                    adRankItem.setRandom(random.nextInt(1000));
+                    if (noApiAdVerIds.contains(dto.getAdVerId())) {
+                        adRankItem.getExt().put("isApi", "0");
+                    } else {
+                        adRankItem.getExt().put("isApi", "1");
+                    }
 
-                adRankItems.add(adRankItem);
+                    String cidStr = dto.getCreativeId().toString();
+                    Map<String, String> cidFeatureMap = adRankItem.getFeatureMap();
+                    Map<String, Map<String, String>> cidFeature = allCidFeature.getOrDefault(cidStr, new HashMap<>());
+                    Map<String, String> b1Feature = cidFeature.getOrDefault("alg_cid_feature_basic_info", new HashMap<>());
 
-            }
+                    Map<String, Map<String, String>> adVerFeature = allAdVerFeature.getOrDefault(dto.getAdVerId(), new HashMap<>());
 
+                    Map<String, String> d1Feature = cidFeature.getOrDefault("alg_cid_feature_vid_cf", new HashMap<>());
 
-            CountDownLatch cdl = new CountDownLatch(adRankItems.size());
-            for (AdRankItem item : adRankItems) {
-                ThreadPoolFactory.defaultPool().submit(() -> {
-                    try {
-                        String cidStr = String.valueOf(item.getAdId());
-                        Map<String, Map<String, String>> cidFeature = allCidFeature.getOrDefault(cidStr, new HashMap<>());
-                        Map<String, String> b1Feature = cidFeature.getOrDefault("alg_cid_feature_basic_info", new HashMap<>());
-                        String title = b1Feature.getOrDefault("cidtitle", "");
-                        this.handleE1AndE2Feature(e1Feature, e2Feature, title, item.getFeatureMap());
-                        this.handleD3AndB1Feature(d3Feature, title, item.getFeatureMap());
-                    } finally {
-                        cdl.countDown();
-                    }
-                });
-            }
+                    this.handleB1Feature(b1Feature, cidFeatureMap, cidStr);
+                    this.handleB2ToB5AndB8ToB9Feature(cidFeature, adVerFeature, cidFeatureMap);
+                    this.handleB6ToB7Feature(cidFeature, cidFeatureMap);
+                    this.handleC1UIFeature(midTimeDiffMap, actionStaticMap, cidFeatureMap, cidStr);
+                    this.handleD1Feature(d1Feature, cidFeatureMap);
+                    this.handleD2Feature(vidRankMaps, cidFeatureMap, cidStr);
+                    return adRankItem;
+                } finally {
+                    cdl1.countDown();
+                }
+            });
+            futures.add(future);
+        }
+        try {
+            cdl1.await(300, TimeUnit.MILLISECONDS);
+        } catch (Exception e) {
+            log.error("handleE1AndE2Feature and handleD3AndB1Feature wait timeout", e);
+        }
+        for (Future<AdRankItem> future : futures) {
             try {
-                cdl.await(200, TimeUnit.MILLISECONDS);
+                if (future.isDone()) {
+                    adRankItems.add(future.get());
+                }
             } catch (Exception e) {
-                log.error("handleE1AndE2Feature and handleD3AndB1Feature wait timeout", e);
-            }
-        } else {
-            for (AdPlatformCreativeDTO dto : request.getAdIdList()) {
-                AdRankItem adRankItem = new AdRankItem();
-                adRankItem.setAdId(dto.getCreativeId());
-                adRankItem.setCreativeCode(dto.getCreativeCode());
-                adRankItem.setAdVerId(dto.getAdVerId());
-                adRankItem.setVideoId(request.getVideoId());
-                adRankItem.setCpa(dto.getCpa());
-                adRankItem.setId(dto.getAdId());
-                adRankItem.setCampaignId(dto.getCampaignId());
-                adRankItem.setCpm(ObjUtil.nullOrDefault(dto.getCpm(), 90).doubleValue());
-                adRankItem.setRandom(random.nextInt(1000));
-
-                String cidStr = dto.getCreativeId().toString();
-                Map<String, String> cidFeatureMap = adRankItem.getFeatureMap();
-                Map<String, Map<String, String>> cidFeature = allCidFeature.getOrDefault(cidStr, new HashMap<>());
-                Map<String, String> b1Feature = cidFeature.getOrDefault("alg_cid_feature_basic_info", new HashMap<>());
-
-                Map<String, Map<String, String>> adVerFeature = allAdVerFeature.getOrDefault(dto.getAdVerId(), new HashMap<>());
-
-                Map<String, String> d1Feature = cidFeature.getOrDefault("alg_cid_feature_vid_cf", new HashMap<>());
-
-                this.handleB1Feature(b1Feature, cidFeatureMap, cidStr);
-
-                this.handleB2ToB5AndB8ToB9Feature(cidFeature, adVerFeature, cidFeatureMap);
-
-                this.handleB6ToB7Feature(cidFeature, cidFeatureMap);
-
-                this.handleC1UIFeature(midTimeDiffMap, actionStaticMap, cidFeatureMap, cidStr);
-
-                this.handleD1Feature(d1Feature, cidFeatureMap);
-
-                this.handleD2Feature(vidRankMaps, cidFeatureMap, cidStr);
-
-                String title = b1Feature.getOrDefault("cidtitle", "");
-                this.handleE1AndE2Feature(e1Feature, e2Feature, title, cidFeatureMap);
-                this.handleD3AndB1Feature(d3Feature, title, cidFeatureMap);
-
-                // adRankItem.setFeatureMap(cidFeatureMap);
-
-                adRankItems.add(adRankItem);
-
+                log.error("Feature handle error", e);
             }
         }
 
         long time2 = System.currentTimeMillis();
+        // feature3
+        CountDownLatch cdl2 = new CountDownLatch(adRankItems.size() * 2);
+        for (AdRankItem item : adRankItems) {
+            String cidStr = String.valueOf(item.getAdId());
+            Map<String, Map<String, String>> cidFeature = allCidFeature.getOrDefault(cidStr, new HashMap<>());
+            Map<String, String> b1Feature = cidFeature.getOrDefault("alg_cid_feature_basic_info", new HashMap<>());
+            String title = b1Feature.getOrDefault("cidtitle", "");
+            ThreadPoolFactory.defaultPool().submit(() -> {
+                try {
+                    this.handleE1AndE2Feature(e1Feature, e2Feature, title, item.getFeatureMap(), scoreParam);
+                } finally {
+                    cdl2.countDown();
+                }
+            });
+            ThreadPoolFactory.defaultPool().submit(() -> {
+                try {
+                    this.handleD3AndB1Feature(d3Feature, title, item.getFeatureMap(), scoreParam);
+                } finally {
+                    cdl2.countDown();
+                }
+            });
+        }
+        long time31 = System.currentTimeMillis();
+        try {
+            cdl2.await(150, TimeUnit.MILLISECONDS);
+        } catch (Exception e) {
+            log.error("handleE1AndE2Feature and handleD3AndB1Feature wait timeout", e);
+        }
+
+        // feature4
+        long time3 = System.currentTimeMillis();
         // 分桶
         this.readBucketFile();
         userFeatureMap = this.featureBucket(userFeatureMap);
+        CountDownLatch cdl4 = new CountDownLatch(adRankItems.size());
         for (AdRankItem adRankItem : adRankItems) {
-            Map<String, String> featureMap = adRankItem.getFeatureMap();
-            adRankItem.setFeatureMap(this.featureBucket(featureMap));
+            ThreadPoolFactory.feature().submit(() -> {
+                try {
+                    Map<String, String> featureMap = adRankItem.getFeatureMap();
+                    adRankItem.setFeatureMap(this.featureBucket(featureMap));
+                } finally {
+                    cdl4.countDown();
+                }
+            });
         }
-
+        try {
+            cdl4.await(100, TimeUnit.MILLISECONDS);
+        } catch (Exception e) {
+            log.error("handleE1AndE2Feature and handleD3AndB1Feature wait timeout", e);
+        }
+        long time4 = System.currentTimeMillis();
         // 打分排序
+        // getScorerPipeline
         List<AdRankItem> result = ScorerUtils.getScorerPipeline(ScorerUtils.XGBOOST_SCORE_CONF_20240909).scoring(sceneFeatureMap, userFeatureMap, adRankItems);
-        long time3 = System.currentTimeMillis();
-
+        long time5 = System.currentTimeMillis();
+        // loop
         double cpmCoefficient = weightParam.getOrDefault("cpmCoefficient", 0.9);
-
         for (AdRankItem item : result) {
             item.setScore(item.getLrScore() * item.getCpa());
             item.getScoreMap().put("cpa", item.getCpa());
@@ -253,9 +242,10 @@ public class RankService680 extends RankStrategyXGBBasic {
             }
         }
 
-        long time4 = System.currentTimeMillis();
-        log.info("cost={}, feature1={}, feature2={}, getScorerPipeline={}, loop={}",
-                time4 - start, time1 - start, time2 - time1, time3 - time2, time4 - time3);
+        log.info("cost={}, feature1={}, feature2={}, feature31={}, feature32={}, feature4={}, getScorerPipeline={}, " +
+                        "adIdSize={}, adRankItemsSize={}",
+                time5 - start, time1 - start, time2 - time1, time31 - time2, time3 - time31, time4 - time3,
+                time5 - time4, request.getAdIdList().size(), adRankItems.size());
 
         result.sort(ComparatorUtil.equalsRandomComparator());
 
@@ -291,7 +281,14 @@ public class RankService680 extends RankStrategyXGBBasic {
         Map<String, String> b9Feature = c1Feature.getOrDefault("alg_cid_feature_weChatVersion_action", new HashMap<>());
 
         List<String> timeList = Arrays.asList("1h", "2h", "3h", "6h", "12h", "1d", "3d", "7d", "yesterday", "today");
-        List<Tuple2<Map<String, String>, String>> featureList = Arrays.asList(new Tuple2<>(b2Feature, "b2"), new Tuple2<>(b3Feature, "b3"), new Tuple2<>(b4Feature, "b4"), new Tuple2<>(b5Feature, "b5"), new Tuple2<>(b8Feature, "b8"), new Tuple2<>(b9Feature, "b9"));
+        List<Tuple2<Map<String, String>, String>> featureList = Arrays.asList(
+                new Tuple2<>(b2Feature, "b2"),
+                new Tuple2<>(b3Feature, "b3"),
+                new Tuple2<>(b4Feature, "b4"),
+                new Tuple2<>(b5Feature, "b5"),
+                new Tuple2<>(b8Feature, "b8"),
+                new Tuple2<>(b9Feature, "b9")
+        );
         for (Tuple2<Map<String, String>, String> tuple2 : featureList) {
             Map<String, String> feature = tuple2.f1;
             String prefix = tuple2.f2;
@@ -299,13 +296,11 @@ public class RankService680 extends RankStrategyXGBBasic {
                 double view = Double.parseDouble(feature.getOrDefault("ad_view_" + time, "0"));
                 double click = Double.parseDouble(feature.getOrDefault("ad_click_" + time, "0"));
                 double conver = Double.parseDouble(feature.getOrDefault("ad_conversion_" + time, "0"));
-                double income = Double.parseDouble(feature.getOrDefault("ad_income_" + time, "0"));
                 double f2 = NumUtil.div(conver, view);
                 cidFeatureMap.put(prefix + "_" + time + "_ctr", String.valueOf(NumUtil.div(click, view)));
                 cidFeatureMap.put(prefix + "_" + time + "_ctcvr", String.valueOf(f2));
                 cidFeatureMap.put(prefix + "_" + time + "_cvr", String.valueOf(NumUtil.div(conver, click)));
                 cidFeatureMap.put(prefix + "_" + time + "_conver", String.valueOf(conver));
-                // cidFeatureMap.put(prefix + "_" + time + "_ecpm", String.valueOf(NumUtil.div(income * 1000, view)));
 
                 cidFeatureMap.put(prefix + "_" + time + "_click", String.valueOf(click));
                 cidFeatureMap.put(prefix + "_" + time + "_conver*log(view)", String.valueOf(conver * NumUtil.log(view)));
@@ -320,7 +315,10 @@ public class RankService680 extends RankStrategyXGBBasic {
         Map<String, String> b7Feature = c1Feature.getOrDefault("alg_cid_feature_hour_action", new HashMap<>());
 
         List<String> timeList = Arrays.asList("7d", "14d");
-        List<Tuple2<Map<String, String>, String>> featureList = Arrays.asList(new Tuple2<>(b6Feature, "b6"), new Tuple2<>(b7Feature, "b7"));
+        List<Tuple2<Map<String, String>, String>> featureList = Arrays.asList(
+                new Tuple2<>(b6Feature, "b6"),
+                new Tuple2<>(b7Feature, "b7")
+        );
         for (Tuple2<Map<String, String>, String> tuple2 : featureList) {
             Map<String, String> feature = tuple2.f1;
             String prefix = tuple2.f2;
@@ -350,13 +348,15 @@ public class RankService680 extends RankStrategyXGBBasic {
         List<TupleMapEntry<Tuple5>> midActionList = new ArrayList<>();
         if (c1Feature.containsKey("action")) {
             String action = c1Feature.get("action");
-            midActionList = Arrays.stream(action.split(",")).map(r -> {
+            midActionList = Arrays.stream(action.split(","))
+                    .map(r -> {
                         String[] rList = r.split(":");
                         Tuple5 tuple5 = new Tuple5(rList[1], rList[2], rList[3], rList[4], rList[5]);
                         return new TupleMapEntry<>(rList[0], tuple5);
                     })
                     // TODO 倒排
-                    .sorted((a, b) -> Integer.compare(Integer.parseInt(b.value.f1), Integer.parseInt(a.value.f1))).collect(Collectors.toList());
+                    .sorted((a, b) -> Integer.compare(Integer.parseInt(b.value.f1), Integer.parseInt(a.value.f1)))
+                    .collect(Collectors.toList());
         }
 
         double viewAll = midActionList.size();
@@ -398,7 +398,10 @@ public class RankService680 extends RankStrategyXGBBasic {
             featureMap.put("actionstatic_income", String.valueOf(midActionStatic.getOrDefault("actionstatic_income_" + cid, 0.0)));
         }
         if (midActionStatic.containsKey("actionstatic_view_" + cid) && midActionStatic.containsKey("actionstatic_click_" + cid)) {
-            double ctr = NumUtil.div(midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0), midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0));
+            double ctr = NumUtil.div(
+                    midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0),
+                    midActionStatic.getOrDefault("actionstatic_view_" + cid, 0.0)
+            );
             featureMap.put("actionstatic_ctr", String.valueOf(ctr));
         }
         if (midActionStatic.containsKey("actionstatic_view_" + cid) && midActionStatic.containsKey("actionstatic_conver_" + cid)) {
@@ -447,16 +450,23 @@ public class RankService680 extends RankStrategyXGBBasic {
         }
     }
 
-    private void handleD3AndB1Feature(Map<String, String> d3Feature, String cTitle, Map<String, String> featureMap) {
+    private void handleD3AndB1Feature(Map<String, String> d3Feature, String cTitle, Map<String, String> featureMap,
+                                      ScoreParam scoreParam) {
         if (MapUtils.isEmpty(d3Feature) || !d3Feature.containsKey("title") || StringUtils.isEmpty(cTitle)) {
             return;
         }
         String vTitle = d3Feature.get("title");
-        double score = Similarity.conceptSimilarity(cTitle, vTitle);
+        double score;
+        if (scoreParam.getExpCodeSet().contains(word2vecExp)) {
+            score = SimilarityUtils.word2VecSimilarity(cTitle, vTitle);
+        } else {
+            score = Similarity.conceptSimilarity(cTitle, vTitle);
+        }
         featureMap.put("ctitle_vtitle_similarity", String.valueOf(score));
     }
 
-    private void handleE1AndE2Feature(Map<String, String> e1Feature, Map<String, String> e2Feature, String title, Map<String, String> featureMap) {
+    private void handleE1AndE2Feature(Map<String, String> e1Feature, Map<String, String> e2Feature, String title,
+                                      Map<String, String> featureMap, ScoreParam scoreParam) {
         if (StringUtils.isEmpty(title)) {
             return;
         }
@@ -474,7 +484,13 @@ public class RankService680 extends RankStrategyXGBBasic {
             for (String tagsField : tagsFieldList) {
                 if (StringUtils.isNotEmpty(feature.get(tagsField))) {
                     String tags = feature.get(tagsField);
-                    Double[] doubles = ExtractorUtils.funcC34567ForTags(tags, title);
+                    //Double[] doubles = ExtractorUtils.funcC34567ForTags(tags, title);
+                    Double[] doubles;
+                    if (scoreParam.getExpCodeSet().contains(word2vecExp)) {
+                        doubles = ExtractorUtils.funcC34567ForTagsNew(tags, title);
+                    } else {
+                        doubles = ExtractorUtils.funcC34567ForTags(tags, title);
+                    }
                     featureMap.put(prefix + "_" + tagsField + "_matchnum", String.valueOf(doubles[0]));
                     featureMap.put(prefix + "_" + tagsField + "_maxscore", String.valueOf(doubles[1]));
                     featureMap.put(prefix + "_" + tagsField + "_avgscore", String.valueOf(doubles[2]));

ad-engine-service/src/main/java/com/tzld/piaoquan/ad/engine/service/score/RankService683.java

@@ -84,6 +84,11 @@ public class RankService683 extends RankStrategyXGBBasic {
                     adRankItem.setCampaignId(dto.getCampaignId());
                     adRankItem.setCpm(ObjUtil.nullOrDefault(dto.getCpm(), 90).doubleValue());
                     adRankItem.setRandom(random.nextInt(1000));
+                    if (noApiAdVerIds.contains(dto.getAdVerId())) {
+                        adRankItem.getExt().put("isApi", "0");
+                    } else {
+                        adRankItem.getExt().put("isApi", "1");
+                    }
 
                     String cidStr = dto.getCreativeId().toString();
                     Map<String, String> cidFeatureMap = adRankItem.getFeatureMap();

ad-engine-service/src/main/java/com/tzld/piaoquan/ad/engine/service/score/RankStrategyXGBAutoUpdateModel688.java

@@ -95,6 +95,11 @@ public class RankStrategyXGBAutoUpdateModel688 extends RankStrategyXGBBasic {
                     adRankItem.setCampaignId(dto.getCampaignId());
                     adRankItem.setCpm(ObjUtil.nullOrDefault(dto.getCpm(), 90).doubleValue());
                     adRankItem.setRandom(random.nextInt(1000));
+                    if (noApiAdVerIds.contains(dto.getAdVerId())) {
+                        adRankItem.getExt().put("isApi", "0");
+                    } else {
+                        adRankItem.getExt().put("isApi", "1");
+                    }
 
                     String cidStr = dto.getCreativeId().toString();
                     Map<String, String> cidFeatureMap = adRankItem.getFeatureMap();