feat:广告引擎FM模型迭代

ad-engine-commons/src/main/java/com/tzld/piaoquan/ad/engine/commons/util/DateUtils.java

@@ -1,6 +1,9 @@
 package com.tzld.piaoquan.ad.engine.commons.util;
 
 import java.text.SimpleDateFormat;
+import java.time.Instant;
+import java.time.LocalDateTime;
+import java.time.ZoneId;
 import java.util.Calendar;
 import java.util.Date;
 
@@ -27,4 +30,17 @@ public final class DateUtils {
         Date previousDate = calendar.getTime();
         return dateFormat.format(previousDate);
     }
+
+    public static int getHourByTimestamp(long timestamp) {
+        return LocalDateTime
+                .ofInstant(Instant.ofEpochSecond(timestamp), ZoneId.systemDefault())
+                .getHour();
+    }
+
+    public static int getDayOrWeekByTimestamp(long timestamp) {
+        return LocalDateTime
+                .ofInstant(Instant.ofEpochSecond(timestamp), ZoneId.systemDefault())
+                .getDayOfWeek()
+                .getValue();
+    }
 }

ad-engine-service/src/main/java/com/tzld/piaoquan/ad/engine/service/feature/Feature.java

@@ -8,8 +8,6 @@ import java.util.Map;
 @Data
 public class Feature {
 
-    private long elapsed;
-
     // k1:创意、k2:表、k3:特征、v:特征值
     private Map<String, Map<String, Map<String, String>>> cidFeature = new HashMap<>();
 

ad-engine-service/src/main/java/com/tzld/piaoquan/ad/engine/service/feature/FeatureService.java

@@ -54,7 +54,7 @@ public class FeatureService {
             }
 
             // cid + wechatversion
-            // protos.add(genWithCidAndWechatVersion("alg_cid_feature_weChatVersion_action", cidStr, context.getMachineinfoWechatversion()));
+            protos.add(genWithCidAndWechatVersion("alg_cid_feature_weChatVersion_action", cidStr, context.getMachineinfoWechatversion()));
 
             // cid + vid
             if (Objects.nonNull(param.getVideoId())) {
@@ -70,6 +70,7 @@ public class FeatureService {
         // vid
         if (Objects.nonNull(param.getVideoId())) {
             protos.add(genWithVid("alg_cid_feature_vid_cf_rank", param.getVideoId().toString()));
+            protos.add(genWithVid("alg_vid_feature_basic_info", param.getVideoId().toString()));
         }
 
         // mid
@@ -79,12 +80,10 @@ public class FeatureService {
             protos.add(genWithMid("alg_mid_feature_share_tags", param.getMid()));
         }
 
-        long start = System.currentTimeMillis();
         Map<String, String> featureMap = remoteService.getFeature(protos);
         featureMap = this.featureStrCover(featureMap);
 
         Feature feature = new Feature();
-        feature.setElapsed(System.currentTimeMillis() - start);
 
         for (Map.Entry<String, String> entry : featureMap.entrySet()) {
             String key = entry.getKey();

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

@@ -1,7 +1,9 @@
 package com.tzld.piaoquan.ad.engine.service.score;
 
+import com.ctrip.framework.apollo.spring.annotation.ApolloJsonValue;
 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.util.DateUtils;
 import com.tzld.piaoquan.ad.engine.commons.util.ExtractorUtils;
 import com.tzld.piaoquan.ad.engine.commons.util.NumUtil;
 import com.tzld.piaoquan.ad.engine.service.feature.Feature;
@@ -15,6 +17,7 @@ import org.apache.commons.lang3.StringUtils;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.beans.factory.annotation.Value;
 import org.springframework.stereotype.Service;
+import org.xm.Similarity;
 
 import java.io.BufferedReader;
 import java.io.IOException;
@@ -27,8 +30,8 @@ import java.util.stream.Collectors;
 @Service
 public class RankService680 {
 
-    @Value("${id.feature.default.value:0.01}")
-    private String idDefaultValue;
+    @ApolloJsonValue("${no.postback.conversion.adverids:[]}")
+    private Set<String> noPostbackConversionAdVerIds;
 
     @Autowired
     private FeatureService featureService;
@@ -43,11 +46,7 @@ public class RankService680 {
 
 
         // 特征处理
-        long start = System.currentTimeMillis();
         Feature feature = this.getFeature(scoreParam, request);
-        long getFeatureElapsed = System.currentTimeMillis() - start;
-
-        long invokeFeatureServiceElapsed = feature.getElapsed();
 
         Map<String, Map<String, String>> userFeature = feature.getUserFeature();
         Map<String, Map<String, String>> videoFeature = feature.getVideoFeature();
@@ -62,12 +61,14 @@ public class RankService680 {
         Map<String, Double> actionStaticMap = this.parseC1FeatureListToActionStaticMap(midActionList);
 
         Map<String, String> d2Feature = videoFeature.getOrDefault("alg_cid_feature_vid_cf_rank", new HashMap<>());
+        Map<String, String> d3Feature = videoFeature.getOrDefault("alg_vid_feature_basic_info", new HashMap<>());
 
         Map<String, Map<String, Double>> vidRankMaps = this.parseD2FeatureMap(d2Feature);
 
         Map<String, String> e1Feature = userFeature.getOrDefault("alg_mid_feature_return_tags", new HashMap<>());
         Map<String, String> e2Feature = userFeature.getOrDefault("alg_mid_feature_share_tags", new HashMap<>());
 
+        Map<String, String> sceneFeatureMap = this.handleSceneFeature(ts);
 
         List<AdRankItem> adRankItems = new ArrayList<>(request.getAdIdList().size());
         for (AdPlatformCreativeDTO dto : request.getAdIdList()) {
@@ -79,8 +80,7 @@ public class RankService680 {
             adRankItem.setCpa(dto.getCpa());
             adRankItem.setId(dto.getAdId());
             adRankItem.setCampaignId(dto.getCampaignId());
-            adRankItem.getExt().put("getFeatureElapsed", getFeatureElapsed);
-            adRankItem.getExt().put("invokeFeatureServiceElapsed", invokeFeatureServiceElapsed);
+            adRankItem.setCpm(dto.getCpm());
 
             String cidStr = dto.getCreativeId().toString();
             Map<String, String> cidFeatureMap = new HashMap<>();
@@ -91,10 +91,9 @@ public class RankService680 {
 
             Map<String, String> d1Feature = cidFeature.getOrDefault("alg_cid_feature_vid_cf", new HashMap<>());
 
-
             this.handleB1Feature(b1Feature, cidFeatureMap, cidStr);
 
-            this.handleB2ToB5AndB8Feature(cidFeature, adVerFeature, cidFeatureMap);
+            this.handleB2ToB5AndB8ToB9Feature(cidFeature, adVerFeature, cidFeatureMap);
 
             this.handleB6ToB7Feature(cidFeature, cidFeatureMap);
 
@@ -107,6 +106,8 @@ public class RankService680 {
             String title = b1Feature.getOrDefault("cidtitle", "");
             this.handleE1AndE2Feature(e1Feature, e2Feature, title, cidFeatureMap);
 
+            this.handleD3AndB1Feature(d3Feature, title, cidFeatureMap);
+
             adRankItem.setFeatureMap(cidFeatureMap);
 
             adRankItems.add(adRankItem);
@@ -114,25 +115,26 @@ public class RankService680 {
         }
 
         // 分桶
-        long featureBucketStart = System.currentTimeMillis();
         this.readBucketFile();
         userFeatureMap = this.featureBucket(userFeatureMap);
         for (AdRankItem adRankItem : adRankItems) {
             Map<String, String> featureMap = adRankItem.getFeatureMap();
             adRankItem.setFeatureMap(this.featureBucket(featureMap));
-            adRankItem.getExt().put("featureBucketElapsed", System.currentTimeMillis() - featureBucketStart);
         }
 
         // 打分排序
-        long scoreStart = System.currentTimeMillis();
         List<AdRankItem> result = ScorerUtils.getScorerPipeline(ScorerUtils.LR_ROV_SCORE_20240626)
-                .scoring(new HashMap<>(), userFeatureMap, adRankItems);
-        long scoreElapsed = System.currentTimeMillis() - scoreStart;
+                .scoring(sceneFeatureMap, userFeatureMap, adRankItems);
         for (AdRankItem item : result) {
             item.setScore(item.getLrScore() * item.getCpa());
             item.getScoreMap().put("cpa", item.getCpa());
             item.getFeatureMap().putAll(userFeatureMap);
-            item.getExt().put("scoreElapsed", scoreElapsed);
+            item.getFeatureMap().putAll(sceneFeatureMap);
+
+            // 没有转化回传的广告主，使用后台配置的CPM
+            if (noPostbackConversionAdVerIds.contains(item.getAdVerId())) {
+                item.setScore(item.getCpm() / 1000);
+            }
 
             for (Map.Entry<String, Map<String, String>> entry : videoFeature.entrySet()) {
                 if (MapUtils.isNotEmpty(entry.getValue())) {
@@ -159,19 +161,6 @@ public class RankService680 {
                     item.getMetaFeatureMap().put(entry.getKey(), entry.getValue());
                 }
             }
-
-            // if (MapUtils.isNotEmpty(videoFeature)) {
-            //     item.getMetaFeatureMap().putAll(videoFeature);
-            // }
-            // if (MapUtils.isNotEmpty(userFeature)) {
-            //     item.getMetaFeatureMap().putAll(userFeature);
-            // }
-            // if (allAdVerFeature.containsKey(item.getAdVerId())) {
-            //     item.getMetaFeatureMap().putAll(allAdVerFeature.get(item.getAdVerId()));
-            // }
-            // if (allCidFeature.containsKey(String.valueOf(item.getAdId()))) {
-            //     item.getMetaFeatureMap().putAll(allCidFeature.get(String.valueOf(item.getAdId())));
-            // }
         }
 
         Collections.sort(result);
@@ -195,14 +184,14 @@ public class RankService680 {
     }
 
     private void handleB1Feature(Map<String, String> b1Feature, Map<String, String> cidFeatureMap, String cid) {
-        cidFeatureMap.put("cid_" + cid, "0.01");
+        cidFeatureMap.put("cid_" + cid, "0.1");
         // if (StringUtils.isNotBlank(b1Feature.get("adid"))) {
         //     String adId = b1Feature.get("adid");
         //     cidFeatureMap.put("adid_" + adId, idDefaultValue);
         // }
         if (StringUtils.isNotBlank(b1Feature.get("adverid"))) {
             String adVerId = b1Feature.get("adverid");
-            cidFeatureMap.put("adverid_" + adVerId, "0.01");
+            cidFeatureMap.put("adverid_" + adVerId, "0.1");
         }
         // if (StringUtils.isNotBlank(b1Feature.get("targeting_conversion"))) {
         //     String targetingConversion = b1Feature.get("targeting_conversion");
@@ -214,20 +203,22 @@ public class RankService680 {
         }
     }
 
-    private void handleB2ToB5AndB8Feature(Map<String, Map<String, String>> c1Feature, Map<String, Map<String, String>> adVerFeature, Map<String, String> cidFeatureMap) {
+    private void handleB2ToB5AndB8ToB9Feature(Map<String, Map<String, String>> c1Feature, Map<String, Map<String, String>> adVerFeature, Map<String, String> cidFeatureMap) {
         Map<String, String> b2Feature = adVerFeature.getOrDefault("alg_cid_feature_adver_action", new HashMap<>());
         Map<String, String> b3Feature = c1Feature.getOrDefault("alg_cid_feature_cid_action", new HashMap<>());
         Map<String, String> b4Feature = c1Feature.getOrDefault("alg_cid_feature_region_action", new HashMap<>());
         Map<String, String> b5Feature = c1Feature.getOrDefault("alg_cid_feature_app_action", new HashMap<>());
         Map<String, String> b8Feature = c1Feature.getOrDefault("alg_cid_feature_brand_action", new HashMap<>());
+        Map<String, String> b9Feature = c1Feature.getOrDefault("alg_cid_feature_weChatVersion_action", new HashMap<>());
 
-        List<String> timeList = Arrays.asList("3h", "6h", "12h", "1d", "3d", "7d");
+        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<>(b8Feature, "b8"),
+                new Tuple2<>(b9Feature, "b9")
         );
         for (Tuple2<Map<String, String>, String> tuple2 : featureList) {
             Map<String, String> feature = tuple2.f1;
@@ -242,7 +233,7 @@ public class RankService680 {
                 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 + "_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)));
@@ -274,7 +265,7 @@ public class RankService680 {
                 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 + "_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)));
@@ -312,7 +303,7 @@ public class RankService680 {
         featureMap.put("ctr_all", String.valueOf(NumUtil.div(clickAll, viewAll)));
         featureMap.put("ctcvr_all", String.valueOf(NumUtil.div(converAll, viewAll)));
         featureMap.put("cvr_all", String.valueOf(NumUtil.div(clickAll, converAll)));
-        featureMap.put("ecpm_all", String.valueOf(NumUtil.div(incomeAll * 1000, viewAll)));
+        // featureMap.put("ecpm_all", String.valueOf(NumUtil.div(incomeAll * 1000, viewAll)));
 
         return midActionList;
     }
@@ -355,8 +346,8 @@ public class RankService680 {
         }
         if (midActionStatic.containsKey("actionstatic_conver_" + cid) && midActionStatic.containsKey("actionstatic_click_" + cid)) {
             double cvr = NumUtil.div(
-                    midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0),
-                    midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0)
+                    midActionStatic.getOrDefault("actionstatic_conver_" + cid, 0.0),
+                    midActionStatic.getOrDefault("actionstatic_click_" + cid, 0.0)
             );
             featureMap.put("actionstatic_cvr", String.valueOf(cvr));
         }
@@ -372,7 +363,7 @@ public class RankService680 {
             featureMap.put("d1_feature_" + prefix + "_ctcvr", String.valueOf(NumUtil.div(conver, view)));
             featureMap.put("d1_feature_" + prefix + "_cvr", String.valueOf(NumUtil.div(conver, click)));
             featureMap.put("d1_feature_" + prefix + "_conver", String.valueOf(conver));
-            featureMap.put("d1_feature_" + prefix + "_ecpm", String.valueOf(NumUtil.div(income * 1000, view)));
+            // featureMap.put("d1_feature_" + prefix + "_ecpm", String.valueOf(NumUtil.div(income * 1000, view)));
         }
     }
 
@@ -381,7 +372,8 @@ public class RankService680 {
             return;
         }
 
-        List<String> prefixes1 = Arrays.asList("ctr", "ctcvr", "ecpm");
+        // List<String> prefixes1 = Arrays.asList("ctr", "ctcvr", "ecpm");
+        List<String> prefixes1 = Arrays.asList("ctr", "ctcvr");
         List<String> prefixes2 = Arrays.asList("1d", "3d", "7d", "14d");
 
         for (String prefix1 : prefixes1) {
@@ -397,6 +389,15 @@ public class RankService680 {
         }
     }
 
+    private void handleD3AndB1Feature(Map<String, String> d3Feature, String cTitle, Map<String, String> featureMap) {
+        if (MapUtils.isEmpty(d3Feature) || !d3Feature.containsKey("title") || StringUtils.isEmpty(cTitle)) {
+            return;
+        }
+        String vTitle = d3Feature.get("title");
+        double 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) {
         if (StringUtils.isEmpty(title)) {
             return;
@@ -485,12 +486,19 @@ public class RankService680 {
         return vidRankMaps;
     }
 
+    public Map<String, String> handleSceneFeature(long ts) {
+        Map<String, String> sceneFeatureMap = new HashMap<>();
+        sceneFeatureMap.put("hour_" + DateUtils.getHourByTimestamp(ts), "0.1");
+        sceneFeatureMap.put("dayofweek_" + DateUtils.getDayOrWeekByTimestamp(ts), "0.1");
+        return sceneFeatureMap;
+    }
+
     private void readBucketFile() {
         if (MapUtils.isNotEmpty(bucketsMap)) {
             return;
         }
         synchronized (this) {
-            InputStream resourceStream = RankService680.class.getClassLoader().getResourceAsStream("20240704_ad_bucket_351.txt");
+            InputStream resourceStream = RankService680.class.getClassLoader().getResourceAsStream("20240718_ad_bucket_688.txt");
             if (resourceStream != null) {
                 try (BufferedReader reader = new BufferedReader(new InputStreamReader(resourceStream))) {
                     Map<String, double[]> bucketsMap = new HashMap<>();

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

@@ -21,6 +21,8 @@ public class AdPlatformCreativeDTO {
 
     private Double cpa;
 
+    private Double cpm;
+
     private Double bid1;
 
     private Double bid2;

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

@@ -90,12 +90,7 @@ public class RankServiceImpl implements RankService {
 
     private AdRankItem rankBy680(RankRecommendRequestParam request) {
         ScoreParam scoreParam = RequestConvert.requestConvert(request);
-        long start = System.currentTimeMillis();
         List<AdRankItem> adRankItems = fmRankService.adItemRank(request, scoreParam);
-        long elapsed = System.currentTimeMillis() - start;
-        for (AdRankItem adRankItem : adRankItems) {
-            adRankItem.getExt().put("rankElapsed", elapsed);
-        }
         logHubService.scoreLogUpload(scoreParam, request.getAdIdList(), adRankItems, request, "LRModelScore", "680");
         return adRankItems.get(0);
     }