CN103077220A - User group correlation degree-based personalized recommendation method and system - Google Patents
User group correlation degree-based personalized recommendation method and systemDownload PDFInfo
- Publication number
- CN103077220A CN103077220ACN2012105901043ACN201210590104ACN103077220ACN 103077220 ACN103077220 ACN 103077220ACN 2012105901043 ACN2012105901043 ACN 2012105901043ACN 201210590104 ACN201210590104 ACN 201210590104ACN 103077220 ACN103077220 ACN 103077220A
- Authority
- CN
- China
- Prior art keywords
- cluster
- user
- distance
- clusters
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription19
- 238000004364calculation methodMethods0.000claimsdescription5
- 239000013598vectorSubstances0.000claimsdescription5
- 238000004891communicationMethods0.000abstractdescription2
- 238000010586diagramMethods0.000description9
- 238000001914filtrationMethods0.000description6
- 238000012986modificationMethods0.000description2
- 230000004048modificationEffects0.000description2
- 238000004458analytical methodMethods0.000description1
- 238000010420art techniqueMethods0.000description1
- 238000005516engineering processMethods0.000description1
- 238000011156evaluationMethods0.000description1
- 239000011159matrix materialSubstances0.000description1
- 238000012552reviewMethods0.000description1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Translated fromChineseDescription
Translated fromChinese技术领域technical field
本发明属于互联网通信领域，尤其涉及一种基于用户群关联度的个性化推荐方法和系统。The invention belongs to the field of Internet communication, and in particular relates to a personalized recommendation method and system based on user group relevance.
背景技术Background technique
推荐系统是根据用户的历史行为记录，如商品购买记录、网络点击日志等信息，分析用户兴趣爱好，并根据分析结果向其推荐相应产品或信息的智能系统。The recommendation system is an intelligent system that analyzes the user's interests and hobbies based on the user's historical behavior records, such as commodity purchase records, network click logs, and recommends corresponding products or information to them based on the analysis results.
协同过滤是当前推荐系统中最常用、最有效的算法，算法的出发点是具有相同或者相似兴趣偏好的用户，对产品的评价也是类似的。其主要步骤有两个：1、查找n个与目标用户最相似的其他用户，称为最近邻居；2、根据最近邻居对产品的评分情况来预测目标用户对产品可能的评分值，并向目标用户推荐预测评分值最高的前m个产品。Collaborative filtering is the most commonly used and most effective algorithm in the current recommendation system. The starting point of the algorithm is users with the same or similar interest preferences, and the evaluation of products is similar. There are two main steps: 1. Find n other users who are most similar to the target user, which are called nearest neighbors; 2. Predict the possible rating value of the target user for the product according to the ratings of the nearest neighbors to the product, and report to the target user The user recommends the top m products with the highest predicted ratings.
随着用户数量和系统规模的不断扩大，协同过滤技术面临严重的数据稀疏性、推荐的实时性以及推荐系统的可扩展性等方面的挑战。With the continuous expansion of the number of users and the scale of the system, collaborative filtering technology faces serious challenges in terms of data sparsity, real-time recommendation, and scalability of the recommendation system.
请参阅图1及图2，本发明人发现其主要问题之一在于：如图1所示，在海量数据环境下，需要计算目标用户与其他所有用户之间的相似度，导致了算法效率低下。如图2所示，针对此问题，基于聚类的协同过滤算法通常的做法是：通过事先对用户离线进行聚类作为解决方案。当需要在线推荐时，系统从用户所在聚簇（用户群）中选择最近邻居，通过这样的方法可以降低目标用户对最近邻居的搜索空间，达到提高算法效率的目标，其基本步骤如下：Please refer to Figure 1 and Figure 2, the inventors found that one of the main problems is: as shown in Figure 1, in a massive data environment, it is necessary to calculate the similarity between the target user and all other users, resulting in low efficiency of the algorithm . As shown in Figure 2, for this problem, the common method of clustering-based collaborative filtering algorithm is to cluster users offline in advance as a solution. When an online recommendation is required, the system selects the nearest neighbor from the cluster (user group) where the user is located. This method can reduce the search space of the target user for the nearest neighbor and achieve the goal of improving the efficiency of the algorithm. The basic steps are as follows:
(1)、离线对用户进行聚类；(1) Clustering users offline;
(2)、在目标用户所在聚簇查找n个最近邻居。(2) Find n nearest neighbors in the cluster where the target user is located.
(3)、根据n个最近邻居对产品的评分预测用户对相关产品的评分值。(3) Predict the user's ratings on related products based on the n nearest neighbors' ratings on the products.
(4)、根据预测评分值的高低，选取前m个产品推荐给用户。(4) Select the first m products and recommend them to the user according to the predicted score value.
然而，如图3所示，本发明的发明人进一步发现，基于聚类的协同过滤算法存在着如下问题：当用户在聚簇中所处位置与聚簇中心的距离大于所在位置与聚簇边缘的位置时，目标用户与其他聚簇内用户的距离往往小于其所在聚簇用户的距离。以聚类阶段使用k-means算法为例，对用户聚类的标准应该是用户被划分到与其最接近的类别中心所标识的聚簇。然而，由于“目标用户”到聚簇A中心点的距离小于其到聚簇B中心点的距离，因此导致“目标用户”虽然被划分到聚簇A中，但是“目标用户”到“用户D”的距离却小于其到“用户E”的距离。However, as shown in Figure 3, the inventors of the present invention have further found that the collaborative filtering algorithm based on clustering has the following problems: when the distance between the user's position in the cluster and the cluster center is greater than the distance between the position and the cluster edge When the location of the target user is smaller than the distance between the target user and other users in the cluster, the distance between the target user and the users in the cluster is often smaller. Taking the k-means algorithm used in the clustering stage as an example, the standard for user clustering should be that the user is divided into the cluster identified by the closest category center. However, because the distance from the "target user" to the center point of cluster A is smaller than the distance to the center point of cluster B, although the "target user" is divided into cluster A, the distance between "target user" and "user D ” is smaller than the distance to “User E”.
如图3所示，由于“目标用户”和“用户D”分别处于不同的聚簇A与聚簇B，因此使用当前的基于聚簇的协同聚类算法，在选择“目标用户”的最近邻居时，舍弃了“用户D”而选择用户“E”，导致遗漏了大量类似“用户E”的最近邻居，使得推荐结果的误差较高。As shown in Figure 3, since the "target user" and "user D" are in different clusters A and B, the current cluster-based cooperative clustering algorithm is used to select the nearest neighbor of the "target user". In this case, "User D" was discarded and User "E" was selected, resulting in the omission of a large number of nearest neighbors similar to "User E", resulting in a higher error in the recommendation results.
发明内容Contents of the invention
有鉴于此，本发明实施例提供一种基于用户群关联度的个性化推荐方法和系统，旨在解决上述因目标用户与真实最近邻居大量丢失而造成推荐结果误差较大的问题。In view of this, the embodiments of the present invention provide a personalized recommendation method and system based on user group relevance, aiming to solve the above-mentioned problem of large error in recommendation results caused by a large number of missing target users and real nearest neighbors.
为此，本发明实施例提供了如下技术方案：For this reason, the embodiment of the present invention provides following technical scheme:
一种基于用户群关联度的个性化推荐方法，包括：A personalized recommendation method based on user group relevance, including:
A、使用聚类算法对用户进行聚类；A. Use a clustering algorithm to cluster users;
B、判断目标用户与聚簇边缘的距离，当距离大于给定阈值则执行步骤C，否则：B. Determine the distance between the target user and the cluster edge. When the distance is greater than the given threshold, execute step C, otherwise:
B-1、计算目标用户所在聚簇与其他聚簇之间的关联度；B-1. Calculate the degree of association between the cluster where the target user is located and other clusters;
B-2、合并与用户所在聚簇最相关的前r个聚簇；B-2. Merge the first r clusters most relevant to the cluster where the user is located;
B-3、在合并后的聚簇内查找n个最近邻居，进而执行步骤D；B-3. Find n nearest neighbors in the merged cluster, and then execute step D;
C、在目标用户所在聚簇中查找n个最近邻居；C. Find n nearest neighbors in the cluster where the target user is located;
D、根据最近邻居对产品的评分预测用户对相关产品的评分值；以及D. Predict the user's rating value for related products based on the ratings of the nearest neighbors for the product; and
E、根据预测评分值的高低，选取前m个产品推荐给用户。E. Select the top m products and recommend them to the user according to the predicted score value.
另外，本发明实施例还进一步提供了如下技术方案：In addition, the embodiments of the present invention further provide the following technical solutions:
一种基于用户群关联度的个性化推荐系统，包括：A personalized recommendation system based on user group relevance, including:
聚类模块，用于使用聚类算法对用户进行聚类；A clustering module for clustering users using a clustering algorithm;
判断模块，用于判断目标用户与聚簇边缘的距离，当距离大于给定阈值则执行查找模块，否则执行关联度计算单元、聚簇合并单元、以及查找子单元，其中关联度计算单元用于计算目标用户所在聚簇与其他聚簇之间的关联度；聚簇合并单元用于合并与用户所在聚簇最相关的前r个聚簇；查找子单元用于在合并后的聚簇内查找n个最近邻居并提交给评分预测模块；The judging module is used to judge the distance between the target user and the edge of the cluster, and when the distance is greater than a given threshold, the search module is executed; otherwise, the correlation calculation unit, the cluster merging unit, and the search subunit are executed, wherein the correlation calculation unit is used for Calculate the degree of association between the cluster where the target user is located and other clusters; the cluster merging unit is used to merge the first r clusters that are most relevant to the cluster where the user is located; the search subunit is used to search within the merged cluster n nearest neighbors and submitted to the score prediction module;
查找模块，用于在目标用户所在聚簇中查找n个最近邻居；A search module, configured to search for n nearest neighbors in the cluster where the target user is located;
评分预测模块，用于根据最近邻居对产品的评分预测用户对相关产品的评分值；以及A score prediction module, used to predict the user's rating of related products based on the ratings of the nearest neighbors to the product; and
推荐模块，用于根据预测评分值的高低，选取前m个产品推荐给用户。The recommendation module is used to select the first m products to recommend to the user according to the predicted score value.
相对于现有技术，本发明实施例提供的基于用户群关联度的个性化推荐方法及系统通过对用户进行聚类，并计算用户聚簇之间的关联度，在实施推荐时，通过相邻聚簇之间的合并来发现真实的最近邻居，扩充可选推荐空间，解决了因目标用户真实最近邻居大量丢失而造成推荐结果精确度降低的问题，从而提升个性化推荐的精确度。Compared with the prior art, the personalized recommendation method and system based on user group correlation degree provided by the embodiment of the present invention cluster users and calculate the correlation degree between user clusters. Merge between clusters to discover the real nearest neighbors, expand the optional recommendation space, and solve the problem of reduced accuracy of recommendation results due to the loss of a large number of real nearest neighbors of target users, thereby improving the accuracy of personalized recommendations.
附图说明Description of drawings
图1是现有协同过滤算法对目标用户最近邻居进行查找的示意图；Fig. 1 is a schematic diagram of searching the nearest neighbors of the target user by the existing collaborative filtering algorithm;
图2是基于聚类的系统过滤算法对目标用户最近邻居进行查找的示意图；Fig. 2 is a schematic diagram of searching the nearest neighbor of the target user based on the clustering system filtering algorithm;
图3是聚簇内用户间相似度大于聚簇间用户相似度的示例图；Figure 3 is an example diagram in which the similarity between users within a cluster is greater than the similarity between users between clusters;
图4是本发明第一实施例提供的基于用户群关联度的个性化推荐方法的流程示意图；Fig. 4 is a schematic flowchart of a personalized recommendation method based on user group relevance provided by the first embodiment of the present invention;
图5是图4中步骤A使用聚类算法对用户进行聚类的示意图；FIG. 5 is a schematic diagram of clustering users using a clustering algorithm in step A in FIG. 4;
图6是具有较高关联度的聚簇的示意图；Fig. 6 is a schematic diagram of a cluster with a higher degree of association;
图7是图4中合并与用户所在聚簇最相关的聚簇的示意图；Fig. 7 is a schematic diagram of merging the cluster most relevant to the cluster where the user is located in Fig. 4;
图8是在临时聚簇内查找目标用户最近邻居的示意图；Fig. 8 is a schematic diagram of finding the nearest neighbor of the target user in the temporary cluster;
图9是本发明第二实施例提供的基于用户群关联度的个性化推荐系统的结构示意图。Fig. 9 is a schematic structural diagram of a personalized recommendation system based on user group relevance provided by the second embodiment of the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的仅是本发明的一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that what is described here is only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
实施例一Embodiment one
图4是本发明第一实施例提供的一种基于用户群关联度的个性化推荐方法的方法流程图，其包括步骤A至步骤E。Fig. 4 is a flow chart of a personalized recommendation method based on user group relevance provided by the first embodiment of the present invention, which includes Step A to Step E.
步骤A、使用聚类算法对用户进行聚类；Step A, using a clustering algorithm to cluster the users;
步骤B、判断目标用户与聚簇边缘的距离，当距离大于给定阈值则执行步骤C，否则：Step B. Determine the distance between the target user and the cluster edge. When the distance is greater than a given threshold, execute step C. Otherwise:
B-1、计算目标用户所在聚簇与其他聚簇之间的关联度；B-1. Calculate the degree of association between the cluster where the target user is located and other clusters;
B-2、合并与用户所在聚簇最相关的前r个聚簇；B-2. Merge the first r clusters most relevant to the cluster where the user is located;
B-3、在合并后的聚簇内查找n个最近邻居，进而执行步骤D；B-3. Find n nearest neighbors in the merged cluster, and then execute step D;
步骤C、在目标用户所在聚簇中查找n个最近邻居；Step C. Find n nearest neighbors in the cluster where the target user is located;
步骤D、根据最近邻居对产品的评分预测用户对相关产品的评分值。Step D. Predict the user's ratings on related products based on the ratings of the nearest neighbors on the products.
步骤E、根据预测评分值的高低，选取前m个产品推荐给用户。Step E. Select the top m products and recommend them to the user according to the predicted score value.
请一起参阅图5-图8，下面将结合具体实施方式对上述方法进行说明，其中图2为所述个性化推荐方法的步骤执行框图。Please refer to FIG. 5-FIG. 8 together. The above-mentioned method will be described below in conjunction with specific implementation methods, wherein FIG. 2 is a block diagram of the steps of the personalized recommendation method.
在步骤A中，根据用户-产品评分矩阵，以用户对产品的评分向量作为对用户的描述，对用户进行聚类。具体而言，可通过计算向量之间的余弦夹角作为用户之间的相似度，并使用k-means算法对用户进行聚类。可以理解的是，也可以使用其他常用聚类算法对用户进行聚类，如K-MEDOIDS算、Clara算法或Clarans算法。In step A, according to the user-product rating matrix, the user's rating vector for the product is used as the user's description, and the users are clustered. Specifically, the cosine angle between the vectors can be calculated as the similarity between users, and the k-means algorithm can be used to cluster the users. It can be understood that other commonly used clustering algorithms can also be used to cluster users, such as K-MEDOIDS algorithm, Clara algorithm or Clarans algorithm.
如图5所示，在本实施例中，通过步骤A对用户进行聚类后的结果包括A、B、C、D四个聚簇(图6中聚簇A、C、D用具有阴影的圆表示，聚簇B用没有阴影的圆表示)，其中聚簇B为目标用户所在的聚簇。As shown in Figure 5, in this embodiment, the result of clustering users through step A includes four clusters A, B, C, and D (in Figure 6, clusters A, C, and D are shaded. circles, and cluster B is represented by a circle without shadow), where cluster B is the cluster where the target user is located.
在步骤B中，判断目标用户与聚簇边缘的距离，如果此距离大于给定阈值则执行步骤C，否则执行步骤B-1至步骤B-3。本实施例中，目标用户与聚簇B边缘的距离较小(小于或等于给定阈值)，即“目标用户”到聚簇B中心点的距离较大，靠近聚簇C，因此需要执行步骤B-1至步骤B-3。In step B, the distance between the target user and the cluster edge is judged, and if the distance is greater than a given threshold, step C is executed; otherwise, steps B-1 to B-3 are executed. In this embodiment, the distance between the target user and the edge of cluster B is small (less than or equal to a given threshold), that is, the distance between the "target user" and the center point of cluster B is relatively large, and it is close to cluster C, so steps need to be performed B-1 to step B-3.
在步骤B-1中：计算聚类之间的关联度（用户群之间的关联度）。本实施例中，在计算聚簇之间的关联度前，首先给出如下定义：In step B-1: calculate the degree of association between clusters (the degree of association between user groups). In this embodiment, before calculating the degree of association between clusters, the following definitions are first given:
定义1：评分用户集合：Ui＝{∪uj}，s(uj，i)≠0，其中s(uj，i)为用户uj对产品i的评分值，定义1给出了曾对产品i进行过评价的集合。Definition 1: A set of rating users: Ui ＝{∪uj }, s(uj , i)≠0, where s(uj , i) is the rating value of user uj on product i, definition 1 gives A collection of reviews for product i.
定义2：用户关注度，用来计算关注某产品用户的数量，即针对产品i，评分用户集合的大小：n(i)＝|Ui|。Definition 2: User attention, which is used to calculate the number of users who follow a certain product, that is, the size of the set of scoring users for product i: n(i)=|Ui |.
基于用户关注度，用户聚簇之间的关联度定义如下：Based on user attention, the correlation between user clusters is defined as follows:
定义3：聚簇关联度（用户群关联度），两个聚簇内用户关注度大于N的共同评分项，与两个聚簇内用户层给出过评分项总和的比值：
另外，在其它变更实施方式中，可将步骤B中用户聚簇之间的关联度用聚簇之间距离所替代，定义两个聚簇中心之间的距离为两个聚簇之间的距离，根据距离从小到大排序。In addition, in other modified implementations, the degree of association between user clusters in step B can be replaced by the distance between clusters, and the distance between the centers of two clusters can be defined as the distance between two clusters , sorted according to the distance from small to large.
请参阅图6及图7，在步骤B-2中，合并与用户所在聚簇最相关的前r个聚簇，具体地，可选择与目标用户所在聚簇距离最相近的前r个聚簇进行合并。本实施例中，聚簇B、C有较高关联度(图6用没有阴影的圆表示)，合并为一个临时聚簇，如图7所示。Please refer to Figure 6 and Figure 7, in step B-2, merge the top r clusters that are most related to the cluster where the user is located, specifically, select the top r clusters that are closest to the cluster where the target user is located to merge. In this embodiment, clusters B and C have a relatively high degree of correlation (indicated by unshaded circles in FIG. 6 ), and are merged into a temporary cluster, as shown in FIG. 7 .
请参阅图8，在步骤B-3中，在合并后的聚簇内查找n个最近邻居，本实施例中，在临时聚簇内目标用户的前3个最近邻居为用户C、D、G。Please refer to Figure 8, in step B-3, search for n nearest neighbors in the merged cluster, in this embodiment, the first 3 nearest neighbors of the target user in the temporary cluster are users C, D, and G .
当步骤B-3完后，跳过步骤C执行步骤D，即根据最近邻居对产品的评分预测用户对相关产品的评分值。After step B-3 is completed, step C is skipped and step D is executed, that is, to predict the rating value of the user for related products based on the ratings of the nearest neighbors for the product.
最后执行步骤E，即根据预测评分值的高低，选取前m个产品推荐给用户。步骤D跟E均为较为常为的现有技术，在此不加赘述。Finally, step E is executed, that is, to select the first m products and recommend them to the user according to the predicted score value. Steps D and E are relatively common prior art techniques, and will not be repeated here.
由此，本发明第一实施例提供的基于用户群关联度的个性化推荐方法，通过对用户进行聚类，并计算用户聚簇之间的关联度，在实施推荐时，通过相邻聚簇之间的合并来发现真实的最近邻居，扩充可选推荐空间，解决因目标用户真实最近邻居大量丢失而造成推荐结果精确度降低的问题，从而提升个性化推荐的精确度。Therefore, the personalized recommendation method based on user group association degree provided by the first embodiment of the present invention clusters users and calculates the association degree between user clusters. The combination between them can discover the real nearest neighbors, expand the optional recommendation space, and solve the problem that the accuracy of the recommendation results is reduced due to the loss of the target user’s real nearest neighbors, thereby improving the accuracy of personalized recommendations.
实施例二Embodiment two
图9是本发明第二实施例提供的一种基于用户群关联度的个性化推荐系统100的结构示意图，包括聚类模块11、判断模块12、查找模块13、评分预测模块14、以及推荐模块15。Fig. 9 is a schematic structural diagram of a
聚类模块11用于使用聚类算法对用户进行聚类。The clustering module 11 is used for clustering users using a clustering algorithm.
判断模块12，用于判断目标用户与聚簇边缘的距离，当距离大于给定阈值则执行查找模块13，否则执行关联度计算单元131、聚簇合并单元132、以及查找子单元133。其中关联度计算单元131用于计算目标用户所在聚簇与其他聚簇之间的关联度；聚簇合并单元132用于合并与用户所在聚簇最相关的前r个聚簇；查找子单元133用于在合并后的聚簇内查找n个最近邻居并提交给评分预测模块14。The judging
在本实施例中，查找模块13用于在目标用户所在聚簇中查找n个最近邻居。评分预测模块14用于根据最近邻居对产品的评分预测用户对相关产品的评分值。推荐模块15用于根据预测评分值的高低，选取前m个产品推荐给用户。In this embodiment, the
本实施例中，所述聚类模块11通过计算向量之间的余弦夹角作为用户之间的相似度，使用k-means算法对用户进行聚类。所述聚簇合并单元132用于定义两个聚簇中心之间的距离为两个聚簇之间的距离，根据距离从小到大排序，并选择与目标用户所在聚簇距离最相近的前r个聚簇进行合并。In this embodiment, the clustering module 11 uses the k-means algorithm to cluster the users by calculating the cosine angle between the vectors as the similarity between the users. The
由此，本发明第二实施例提供的基于用户群关联度的个性化推荐系统100，通过对用户进行聚类，并计算用户聚簇之间的关联度，在实施推荐时，通过相邻聚簇之间的合并来发现真实的最近邻居，扩充可选推荐空间，解决因目标用户真实最近邻居大量丢失而造成推荐结果精确度降低的问题，从而提升个性化推荐的精确度。Therefore, the
本发明实施例第二实施例的系统100，与前述的第一实施例的方法构思和原理相同，因此在第二实施例中对与第一实施例中相同的部分不再赘述。The
本领域技术人员可以理解实施例中的系统中的模块可以按照实施例描述进行分布于实施例的系统中，也可以进行相应变化位于不同于本实施例的一个或多个系统中。上述实施例的模块可以合并为一个模块，也可以进一步拆分成多个子模块。Those skilled in the art can understand that the modules in the system of the embodiment can be distributed in the system of the embodiment according to the description of the embodiment, or can be located in one or more systems different from the embodiment according to the corresponding changes. The modules in the above embodiments can be combined into one module, and can also be further split into multiple sub-modules.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到本发明可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台终端设备（可以是手机，个人计算机，服务器，或者网络设备等）执行本发明各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is a better implementation Way. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to make a A terminal device (which may be a mobile phone, a personal computer, a server, or a network device, etc.) executes the methods described in various embodiments of the present invention.
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视本发明的保护范围。The above is only a preferred embodiment of the present invention, it should be pointed out that, for those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications can also be made. It should be regarded as the protection scope of the present invention.
Claims (8)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210590104.3ACN103077220B (en) | 2012-12-29 | 2012-12-29 | A kind of personalized recommendation method based on the customer group degree of association and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210590104.3ACN103077220B (en) | 2012-12-29 | 2012-12-29 | A kind of personalized recommendation method based on the customer group degree of association and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103077220Atrue CN103077220A (en) | 2013-05-01 |
| CN103077220B CN103077220B (en) | 2016-06-29 |
Family
ID=48153750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210590104.3AActiveCN103077220B (en) | 2012-12-29 | 2012-12-29 | A kind of personalized recommendation method based on the customer group degree of association and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103077220B (en) |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544206A (en)* | 2013-07-16 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for achieving individualized recommendations |
| CN103559252A (en)* | 2013-11-01 | 2014-02-05 | 桂林电子科技大学 | Method for recommending scenery spots probably browsed by tourists |
| CN103942302A (en)* | 2014-04-16 | 2014-07-23 | 苏州大学 | Method for establishment and application of inter-relevance-feedback relational network |
| CN104217030A (en)* | 2014-09-28 | 2014-12-17 | 北京奇虎科技有限公司 | Method and device for classifying users according to search log data of server |
| CN104424235A (en)* | 2013-08-26 | 2015-03-18 | 腾讯科技（深圳）有限公司 | Method and device for clustering user information |
| CN104517227A (en)* | 2013-09-27 | 2015-04-15 | 上海酷远物联网科技有限公司 | Method and system for shopping through Internet or Internet of things |
| CN105139020A (en)* | 2015-07-06 | 2015-12-09 | 无线生活（杭州）信息科技有限公司 | User clustering method and device |
| CN105389713A (en)* | 2015-10-15 | 2016-03-09 | 南京大学 | Mobile data traffic package recommendation algorithm based on user historical data |
| CN106162348A (en)* | 2015-04-13 | 2016-11-23 | 海信集团有限公司 | A kind of personal program recommends method and device |
| CN106202391A (en)* | 2016-07-08 | 2016-12-07 | 深圳市中北明夷科技有限公司 | The automatic classification method of a kind of user's community and device |
| CN106446079A (en)* | 2016-09-08 | 2017-02-22 | 中国科学院计算技术研究所 | Distributed file system-oriented file prefetching/caching method and apparatus |
| CN106919611A (en)* | 2015-12-25 | 2017-07-04 | 北京国双科技有限公司 | Product information method for pushing and device |
| CN106997358A (en)* | 2016-01-22 | 2017-08-01 | 中移（杭州）信息技术有限公司 | Information recommendation method and device |
| CN107016589A (en)* | 2016-08-10 | 2017-08-04 | 阿里巴巴集团控股有限公司 | The determination method and device of recommended products |
| CN107295107A (en)* | 2017-08-01 | 2017-10-24 | 深圳天珑无线科技有限公司 | Recommendation method, recommendation apparatus and mobile terminal |
| CN107481114A (en)* | 2017-08-16 | 2017-12-15 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, e-commerce system and storage medium |
| CN107679898A (en)* | 2017-09-26 | 2018-02-09 | 浪潮软件股份有限公司 | A kind of Method of Commodity Recommendation and device |
| WO2018041168A1 (en)* | 2016-08-31 | 2018-03-08 | 腾讯科技（深圳）有限公司 | Information pushing method, storage medium and server |
| CN109241449A (en)* | 2018-10-30 | 2019-01-18 | 国信优易数据有限公司 | A kind of item recommendation method and device |
| CN109408562A (en)* | 2018-11-07 | 2019-03-01 | 广东工业大学 | A kind of grouping recommended method and its device based on client characteristics |
| CN109409964A (en)* | 2018-11-27 | 2019-03-01 | 口碑(上海)信息技术有限公司 | The recognition methods of Premium Brands and device |
| CN109508291A (en)* | 2018-10-31 | 2019-03-22 | 武汉雨滴科技有限公司 | A kind of application quality evaluation method |
| CN109740054A (en)* | 2018-12-27 | 2019-05-10 | 丹翰智能科技(上海)有限公司 | It is a kind of for determining the method and apparatus of the association financial information of target user |
| CN109903138A (en)* | 2019-02-28 | 2019-06-18 | 华中科技大学 | A Personalized Product Recommendation Method |
| WO2019154096A1 (en)* | 2018-02-08 | 2019-08-15 | 阿里巴巴集团控股有限公司 | Information sharing method and device |
| CN110135893A (en)* | 2019-04-16 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Determination method, apparatus, computer equipment and the storage medium of potential user |
| US10387513B2 (en) | 2015-08-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended content list |
| US10387115B2 (en) | 2015-09-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items |
| US10394420B2 (en) | 2016-05-12 | 2019-08-27 | Yandex Europe Ag | Computer-implemented method of generating a content recommendation interface |
| US10430481B2 (en) | 2016-07-07 | 2019-10-01 | Yandex Europe Ag | Method and apparatus for generating a content recommendation in a recommendation system |
| US10452731B2 (en) | 2015-09-28 | 2019-10-22 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items for a user |
| CN110503494A (en)* | 2018-05-16 | 2019-11-26 | 江苏天智互联科技股份有限公司 | A kind of recommender system for electric business marketing platform |
| USD882600S1 (en) | 2017-01-13 | 2020-04-28 | Yandex Europe Ag | Display screen with graphical user interface |
| CN111209531A (en)* | 2018-11-21 | 2020-05-29 | 百度在线网络技术（北京）有限公司 | Method and device for processing association degree and storage medium |
| US10674215B2 (en) | 2018-09-14 | 2020-06-02 | Yandex Europe Ag | Method and system for determining a relevancy parameter for content item |
| US10706325B2 (en) | 2016-07-07 | 2020-07-07 | Yandex Europe Ag | Method and apparatus for selecting a network resource as a source of content for a recommendation system |
| CN111552883A (en)* | 2020-05-13 | 2020-08-18 | 咪咕文化科技有限公司 | Content recommendation method and computer-readable storage medium |
| CN112003953A (en)* | 2020-09-29 | 2020-11-27 | 中移（杭州）信息技术有限公司 | Advertising push method and server |
| US11086888B2 (en) | 2018-10-09 | 2021-08-10 | Yandex Europe Ag | Method and system for generating digital content recommendation |
| CN113468419A (en)* | 2021-06-28 | 2021-10-01 | 北京达佳互联信息技术有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| US11263217B2 (en) | 2018-09-14 | 2022-03-01 | Yandex Europe Ag | Method of and system for determining user-specific proportions of content for recommendation |
| US11276076B2 (en) | 2018-09-14 | 2022-03-15 | Yandex Europe Ag | Method and system for generating a digital content recommendation |
| US11276079B2 (en) | 2019-09-09 | 2022-03-15 | Yandex Europe Ag | Method and system for meeting service level of content item promotion |
| US11288333B2 (en) | 2018-10-08 | 2022-03-29 | Yandex Europe Ag | Method and system for estimating user-item interaction data based on stored interaction data by using multiple models |
| CN114627523A (en)* | 2021-04-23 | 2022-06-14 | 亚信科技（中国）有限公司 | Face recognition method and device, electronic equipment and computer storage medium |
| CN114912031A (en)* | 2021-12-29 | 2022-08-16 | 天翼数字生活科技有限公司 | Hybrid recommendation method and system based on clustering and collaborative filtering |
| CN115409039A (en)* | 2022-08-25 | 2022-11-29 | 中国第一汽车股份有限公司 | Standard vehicle type data analysis method and device, electronic equipment and medium |
| CN118429020A (en)* | 2024-05-16 | 2024-08-02 | 深圳高灯云科技有限公司 | Merchant recommendation method, merchant recommendation device, merchant recommendation computer device, merchant recommendation storage medium and merchant recommendation program product |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107481066A (en)* | 2017-08-29 | 2017-12-15 | 艾普英捷（北京）智能科技股份有限公司 | A kind of competing product analysis method and system based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040083232A1 (en)* | 2002-10-25 | 2004-04-29 | Christopher Ronnewinkel | Association learning for automated recommendations |
| CN101329683A (en)* | 2008-07-25 | 2008-12-24 | 华为技术有限公司 | Recommendation system and method |
| CN101685458A (en)* | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN102591873A (en)* | 2011-01-12 | 2012-07-18 | 腾讯科技（深圳）有限公司 | Method and equipment for information recommendation |
- 2012
- 2012-12-29CNCN201210590104.3Apatent/CN103077220B/enactiveActive
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040083232A1 (en)* | 2002-10-25 | 2004-04-29 | Christopher Ronnewinkel | Association learning for automated recommendations |
| CN101329683A (en)* | 2008-07-25 | 2008-12-24 | 华为技术有限公司 | Recommendation system and method |
| CN101685458A (en)* | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN102591873A (en)* | 2011-01-12 | 2012-07-18 | 腾讯科技（深圳）有限公司 | Method and equipment for information recommendation |
Cited By (64)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544206A (en)* | 2013-07-16 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for achieving individualized recommendations |
| CN103544206B (en)* | 2013-07-16 | 2017-09-15 | Tcl集团股份有限公司 | A kind of realization method and system of personalized recommendation |
| CN104424235A (en)* | 2013-08-26 | 2015-03-18 | 腾讯科技（深圳）有限公司 | Method and device for clustering user information |
| CN104424235B (en)* | 2013-08-26 | 2018-01-05 | 腾讯科技（深圳）有限公司 | The method and apparatus for realizing user profile cluster |
| CN104517227A (en)* | 2013-09-27 | 2015-04-15 | 上海酷远物联网科技有限公司 | Method and system for shopping through Internet or Internet of things |
| CN103559252A (en)* | 2013-11-01 | 2014-02-05 | 桂林电子科技大学 | Method for recommending scenery spots probably browsed by tourists |
| CN103942302B (en)* | 2014-04-16 | 2017-04-19 | 苏州大学 | Method for establishment and application of inter-relevance-feedback relational network |
| CN103942302A (en)* | 2014-04-16 | 2014-07-23 | 苏州大学 | Method for establishment and application of inter-relevance-feedback relational network |
| CN104217030A (en)* | 2014-09-28 | 2014-12-17 | 北京奇虎科技有限公司 | Method and device for classifying users according to search log data of server |
| CN106162348A (en)* | 2015-04-13 | 2016-11-23 | 海信集团有限公司 | A kind of personal program recommends method and device |
| CN105139020B (en)* | 2015-07-06 | 2018-07-20 | 无线生活（杭州）信息科技有限公司 | A kind of user clustering method and device |
| CN105139020A (en)* | 2015-07-06 | 2015-12-09 | 无线生活（杭州）信息科技有限公司 | User clustering method and device |
| US10387513B2 (en) | 2015-08-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended content list |
| US10387115B2 (en) | 2015-09-28 | 2019-08-20 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items |
| US10452731B2 (en) | 2015-09-28 | 2019-10-22 | Yandex Europe Ag | Method and apparatus for generating a recommended set of items for a user |
| CN105389713A (en)* | 2015-10-15 | 2016-03-09 | 南京大学 | Mobile data traffic package recommendation algorithm based on user historical data |
| CN106919611A (en)* | 2015-12-25 | 2017-07-04 | 北京国双科技有限公司 | Product information method for pushing and device |
| CN106919611B (en)* | 2015-12-25 | 2020-05-22 | 北京国双科技有限公司 | Product information push method and device |
| CN106997358A (en)* | 2016-01-22 | 2017-08-01 | 中移（杭州）信息技术有限公司 | Information recommendation method and device |
| US10394420B2 (en) | 2016-05-12 | 2019-08-27 | Yandex Europe Ag | Computer-implemented method of generating a content recommendation interface |
| US10706325B2 (en) | 2016-07-07 | 2020-07-07 | Yandex Europe Ag | Method and apparatus for selecting a network resource as a source of content for a recommendation system |
| US10430481B2 (en) | 2016-07-07 | 2019-10-01 | Yandex Europe Ag | Method and apparatus for generating a content recommendation in a recommendation system |
| CN106202391A (en)* | 2016-07-08 | 2016-12-07 | 深圳市中北明夷科技有限公司 | The automatic classification method of a kind of user's community and device |
| CN107016589A (en)* | 2016-08-10 | 2017-08-04 | 阿里巴巴集团控股有限公司 | The determination method and device of recommended products |
| WO2018041168A1 (en)* | 2016-08-31 | 2018-03-08 | 腾讯科技（深圳）有限公司 | Information pushing method, storage medium and server |
| US11574139B2 (en) | 2016-08-31 | 2023-02-07 | Tencent Technology (Shenzhen) Company Limited | Information pushing method, storage medium and server |
| CN106446079A (en)* | 2016-09-08 | 2017-02-22 | 中国科学院计算技术研究所 | Distributed file system-oriented file prefetching/caching method and apparatus |
| CN106446079B (en)* | 2016-09-08 | 2019-06-18 | 中国科学院计算技术研究所 | A file prefetching/caching method and device for distributed file system |
| USD892847S1 (en) | 2017-01-13 | 2020-08-11 | Yandex Europe Ag | Display screen with graphical user interface |
| USD892846S1 (en) | 2017-01-13 | 2020-08-11 | Yandex Europe Ag | Display screen with graphical user interface |
| USD890802S1 (en) | 2017-01-13 | 2020-07-21 | Yandex Europe Ag | Display screen with graphical user interface |
| USD882600S1 (en) | 2017-01-13 | 2020-04-28 | Yandex Europe Ag | Display screen with graphical user interface |
| USD980246S1 (en) | 2017-01-13 | 2023-03-07 | Yandex Europe Ag | Display screen with graphical user interface |
| CN107295107A (en)* | 2017-08-01 | 2017-10-24 | 深圳天珑无线科技有限公司 | Recommendation method, recommendation apparatus and mobile terminal |
| CN107481114A (en)* | 2017-08-16 | 2017-12-15 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, e-commerce system and storage medium |
| CN107679898A (en)* | 2017-09-26 | 2018-02-09 | 浪潮软件股份有限公司 | A kind of Method of Commodity Recommendation and device |
| WO2019154096A1 (en)* | 2018-02-08 | 2019-08-15 | 阿里巴巴集团控股有限公司 | Information sharing method and device |
| CN110503494A (en)* | 2018-05-16 | 2019-11-26 | 江苏天智互联科技股份有限公司 | A kind of recommender system for electric business marketing platform |
| US11276076B2 (en) | 2018-09-14 | 2022-03-15 | Yandex Europe Ag | Method and system for generating a digital content recommendation |
| US10674215B2 (en) | 2018-09-14 | 2020-06-02 | Yandex Europe Ag | Method and system for determining a relevancy parameter for content item |
| US11263217B2 (en) | 2018-09-14 | 2022-03-01 | Yandex Europe Ag | Method of and system for determining user-specific proportions of content for recommendation |
| US11288333B2 (en) | 2018-10-08 | 2022-03-29 | Yandex Europe Ag | Method and system for estimating user-item interaction data based on stored interaction data by using multiple models |
| US11086888B2 (en) | 2018-10-09 | 2021-08-10 | Yandex Europe Ag | Method and system for generating digital content recommendation |
| CN109241449A (en)* | 2018-10-30 | 2019-01-18 | 国信优易数据有限公司 | A kind of item recommendation method and device |
| CN109508291B (en)* | 2018-10-31 | 2022-02-08 | 武汉雨滴科技有限公司 | Application quality evaluation method |
| CN109508291A (en)* | 2018-10-31 | 2019-03-22 | 武汉雨滴科技有限公司 | A kind of application quality evaluation method |
| CN109408562A (en)* | 2018-11-07 | 2019-03-01 | 广东工业大学 | A kind of grouping recommended method and its device based on client characteristics |
| CN109408562B (en)* | 2018-11-07 | 2021-11-26 | 广东工业大学 | Grouping recommendation method and device based on client characteristics |
| CN111209531A (en)* | 2018-11-21 | 2020-05-29 | 百度在线网络技术（北京）有限公司 | Method and device for processing association degree and storage medium |
| CN111209531B (en)* | 2018-11-21 | 2023-08-08 | 百度在线网络技术（北京）有限公司 | Correlation degree processing method, device and storage medium |
| CN109409964A (en)* | 2018-11-27 | 2019-03-01 | 口碑(上海)信息技术有限公司 | The recognition methods of Premium Brands and device |
| CN109740054A (en)* | 2018-12-27 | 2019-05-10 | 丹翰智能科技(上海)有限公司 | It is a kind of for determining the method and apparatus of the association financial information of target user |
| CN109903138A (en)* | 2019-02-28 | 2019-06-18 | 华中科技大学 | A Personalized Product Recommendation Method |
| CN110135893A (en)* | 2019-04-16 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Determination method, apparatus, computer equipment and the storage medium of potential user |
| US11276079B2 (en) | 2019-09-09 | 2022-03-15 | Yandex Europe Ag | Method and system for meeting service level of content item promotion |
| CN111552883B (en)* | 2020-05-13 | 2023-12-12 | 咪咕文化科技有限公司 | Content recommendation method and computer-readable storage medium |
| CN111552883A (en)* | 2020-05-13 | 2020-08-18 | 咪咕文化科技有限公司 | Content recommendation method and computer-readable storage medium |
| CN112003953A (en)* | 2020-09-29 | 2020-11-27 | 中移（杭州）信息技术有限公司 | Advertising push method and server |
| CN112003953B (en)* | 2020-09-29 | 2023-04-07 | 中移（杭州）信息技术有限公司 | Advertisement pushing method and server |
| CN114627523A (en)* | 2021-04-23 | 2022-06-14 | 亚信科技（中国）有限公司 | Face recognition method and device, electronic equipment and computer storage medium |
| CN113468419A (en)* | 2021-06-28 | 2021-10-01 | 北京达佳互联信息技术有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN114912031A (en)* | 2021-12-29 | 2022-08-16 | 天翼数字生活科技有限公司 | Hybrid recommendation method and system based on clustering and collaborative filtering |
| CN115409039A (en)* | 2022-08-25 | 2022-11-29 | 中国第一汽车股份有限公司 | Standard vehicle type data analysis method and device, electronic equipment and medium |
| CN118429020A (en)* | 2024-05-16 | 2024-08-02 | 深圳高灯云科技有限公司 | Merchant recommendation method, merchant recommendation device, merchant recommendation computer device, merchant recommendation storage medium and merchant recommendation program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103077220B (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103077220B (en) | A kind of personalized recommendation method based on the customer group degree of association and system | |
| CN103678672B (en) | Method for recommending information | |
| CN103514304B (en) | Project recommendation method and device | |
| CN104601438B (en) | A kind of friend recommendation method and apparatus | |
| CN105373597B (en) | User collaborative filtering recommendation method based on k‑medoids item clustering and local interest fusion | |
| CN101685458B (en) | Recommendation method and system based on collaborative filtering | |
| CN110532479A (en) | A kind of information recommendation method, device and equipment | |
| WO2021109464A1 (en) | Personalized teaching resource recommendation method for large-scale users | |
| WO2019233258A1 (en) | Method, apparatus and system for sending information, and computer-readable storage medium | |
| CN104391849A (en) | Collaborative filtering recommendation method for integrating temporal context information | |
| CN102495864A (en) | Collaborative filtering recommending method and system based on grading | |
| CN106850750B (en) | A method and device for real-time push information | |
| CN107526850A (en) | Social networks friend recommendation method based on multiple personality feature mixed architecture | |
| Rahmani et al. | Category-aware location embedding for point-of-interest recommendation | |
| CN102750336A (en) | Resource individuation recommendation method based on user relevance | |
| CN105678590B (en) | Cloud model-based topN recommendation method for social network | |
| CN111475744B (en) | Personalized position recommendation method based on ensemble learning | |
| CN105023178B (en) | A kind of electronic commerce recommending method based on ontology | |
| CN103337028A (en) | Recommendation method and device | |
| CN104751353A (en) | Cluster and Slope One prediction based collaborative filtering method | |
| CN114036376A (en) | Time-aware self-adaptive interest point recommendation method based on K-means clustering | |
| KR101910424B1 (en) | Method for movie ratings prediction using sentiment analysis of movie tags, recording medium and device for performing the method | |
| CN115131058B (en) | Account identification method, device, equipment and storage medium | |
| CN105260458A (en) | Video recommendation method for display apparatus and display apparatus | |
| CN110309864A (en) | A Method of Collaborative Filtering Recommendation Scheme Fusion of Local Similarity and Global Similarity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |