基于物品的协同过滤算法，实现根据点赞推荐博客

算法类

public class ItemCF {

    // 定义用户-博客的点赞关系
    private Map<Integer, Set<Long>> userLikes = new HashMap<>();
    // 定义博客-用户的点赞关系
    private Map<Long, Set<Integer>> blogLikes = new HashMap<>();
    // 定义博客-博客之间的相似度
    private Map<Long, Map<Long, Double>> itemSimilarity = new HashMap<>();

    // 添加点赞关系
    public void addLike(List<Like> likes) {
        for(Like like : likes){
            int userId = like.getUserId();
            long blogId = like.getBlogId();

            // 添加用户-博客的点赞关系
            Set<Long> userBlogLikes = userLikes.getOrDefault(userId, new HashSet<>());
            userBlogLikes.add(blogId);
            userLikes.put(userId, userBlogLikes);

            // 添加博客-用户的点赞关系
            Set<Integer> blogUserLikes = blogLikes.getOrDefault(blogId, new HashSet<>());
            blogUserLikes.add(userId);
            blogLikes.put(blogId, blogUserLikes);
        }

    }

    // 计算博客-博客之间的相似度
    public void calculateSimilarity() {
        for (long blogId1 : blogLikes.keySet()) {
            Map<Long, Integer> commonLikes = new HashMap<>();
            for (int userId : blogLikes.get(blogId1)) {
                for (long blogId2 : userLikes.get(userId)) {
                    if (blogId1 == blogId2) {
                        continue;
                    }
                    commonLikes.put(blogId2, commonLikes.getOrDefault(blogId2, 0) + 1);
                }
            }
            for (long blogId2 : commonLikes.keySet()) {
                double similarity = (double) commonLikes.get(blogId2) / Math.sqrt(userLikes.size());
                Map<Long, Double> itemSimilarityMap = itemSimilarity.getOrDefault(blogId1, new HashMap<>());
                itemSimilarityMap.put(blogId2, similarity);
                itemSimilarity.put(blogId1, itemSimilarityMap);
            }
        }
    }

    // 获取与指定博客相似度最高的K个博客
    public List<Long> getSimilarBlogs(long blogId, int K) {
        List<Long> result = new ArrayList<>();
        Map<Long, Double> similarBlogs = itemSimilarity.get(blogId);
        if (similarBlogs != null) {
            List<Map.Entry<Long, Double>> list = new ArrayList<>(similarBlogs.entrySet());
            list.sort((a, b) -> b.getValue().compareTo(a.getValue()));
            for (int i = 0; i < K && i < list.size(); i++) {
                result.add(list.get(i).getKey());
            }
        }
        return result;
    }

    // 获取给定用户的推荐博客
    public List<Long> getRecommendation(int userId, int K) {
        Set<Long> likedBlogs = userLikes.get(userId);
        if (likedBlogs == null || likedBlogs.isEmpty()) {
            return Collections.emptyList();
        }
        Map<Long, Double> recommendation = new HashMap<>();
        for (long likedBlog : likedBlogs) {
            for (long similarBlog : getSimilarBlogs(likedBlog, K)) {
                if (likedBlogs.contains(similarBlog)) {
                    continue;
                }
                recommendation.put(similarBlog, recommendation.getOrDefault(similarBlog, 0.0) + itemSimilarity.get(likedBlog).get(similarBlog));
            }
        }
        List<Map.Entry<Long, Double>> list = new ArrayList<>(recommendation.entrySet());
        list.sort((a, b) -> b.getValue().compareTo(a.getValue()));
        List<Long> result = new ArrayList<>();
        for (int i = 0; i < K && i < list.size(); i++) {
            result.add(list.get(i).getKey());
        }
        return result;
    }


}

Like类

public class like{
	private Integer id;
	private Long blogId;
	private Integer userId;
	//其他省略
}

blog类

public class blog{
	private Long id;
	//其他省略
}

user类

public class user{
	private Integer id;
	//其他省略
}