Реализация простой рекомендации по контенту на основе тегов

+-------+------------+------+-----+---------+-------+
| Field | Type       | Null | Key | Default | Extra |
+-------+------------+------+-----+---------+-------+
| tag   | text       | YES  |     | NULL    |       |
| count | bigint(20) | YES  |     | NULL    |       |
| tagid | int(11)    | NO   | PRI | 0       |       |
+-------+------------+------+-----+---------+-------+

+-----------+------------+------+-----+---------+-------+
| Field     | Type       | Null | Key | Default | Extra |
+-----------+------------+------+-----+---------+-------+
| id        | bigint(20) | NO   | PRI | 0       |       |
| articleid | bigint(20) | YES  |     | NULL    |       |
| tagid     | int(11)    | YES  |     | NULL    |       |
+-----------+------------+------+-----+---------+-------+

+----+-----------+-------+
| id | articleid | tagid |
+----+-----------+-------+
|  1 |       776 |   589 |
|  2 |       776 |   471 |
|  3 |       776 |  1455 |
|  4 |       776 |  1287 |
|  5 |       776 |    52 |
|  6 |       777 |  1386 |
|  7 |       777 |   588 |
|  8 |       777 |   109 |
|  9 |       777 |   603 |
| 10 |       777 |  1299 |
+----+-----------+-------+

mysql> select articleid, GROUP_CONCAT(tagid) as tags from tag_map GROUP BY articleid;
+-----------+--------------------------+
| articleid | tags                     |
+-----------+--------------------------+
|        12 | 1178,1067,49,693,1227    |
|        13 | 196,2004,2071,927,131    |
|        14 | 1945,713,1711,2024,49    |
|        15 | 35,119,9,1,1180          |
|        16 | 1182,1924,2200,181,1938  |
|        17 | 46,492,414,424,620       |
|        18 | 415,499,153,567,674      |
|        19 | 1602,805,691,1613,194    |
|        20 | 2070,1994,886,575,1149   |
|        21 | 1953,1961,1534,2038,1393 |
+-----------+--------------------------+

public function getAllGroupByArticleId(){
        // Cache query data, because this is full table data, and does not update the article will not change, that is, every recommendation to get data from the database once, will certainly have an impact on performance, so make a cache.
        if($cache = CacheHelper::getCache()){
            return $cache;
        }
        $query_result = $this->query('select articleid, GROUP_CONCAT(tagid) as tags from tag_map GROUP BY articleid');

        $result = [];
        foreach($query_result as $key => $value){
            // With articleid as key, the value is all tagID arrays under that ID.
            $result[$value['articleid']] = explode(",",$value['tags']);
        }

        CacheHelper::setCache($result, 86400);

        return $result;

    }

/**
     * [Return similar article recommendations based on specified articles]
     *@ Article ID specified by param $articleid
     *@ Number of recommended items to be returned by param $top
     *@ Return Array Recommendation Item Array
     */
function getArticleRecommend($articleid, $top = 5){
        if($cache = CacheHelper::getCache()){
            return $cache;
        }
        try{
            $articleid = intval($articleid);
            $m = new TagMapModel();
            $all_tags = $m - > getAllGroupByArticleId (); // Call the above function to return tags for all articles
            $finded = $all_tags [$articleid]; // Because it contains all the articles above, it must contain the current article.

            Unset ($all_tags [$articleid]); /// Delete the current article from the array, otherwise you and yourself will surely be the most similar.

            $jaccard_arr= []; // for storage similarity
            foreach ($all_tags as $key => $value) {
                $intersect = array_intersect ($finded, $value); // Compute intersection
                $union = array_unique (array_merge ($finded, $value);//Computational union set

                $jaccard_arr[$key] = (float)(count($intersect) / count($union));
            }

            Arsort ($jaccard_arr); /// sorted by similarity, with the most similar row at the front

            $jaccard_keys = array_keys ($jaccard_arr); // Since the key of the array is the article id, you can just take the key out here.
            Array_splice ($jaccard_keys, $top); // Get the first N recommendations

            // Here we have got the ID of the most similar N articles. The next work is to query the relevant information from the database through these IDs.
    
            $articleModels = new \Api\Model\ArticleModel();
            $recommendArticles = $articleModels->getRecommendByTag($jaccard_keys);
            CacheHelper:: setCache ($recommend Articles, 604800); // Cache 7 days
            return $recommendArticles;
        } catch (\Exception $e) {
            Throw new Exception ("Get Recommendation Articles Error");
        }
    }