技术领域technical field
本发明涉及智能购物技术领域，更具体地，涉及商品推荐方法和系统。The present invention relates to the technical field of intelligent shopping, and more particularly, to a method and system for recommending products.
背景技术Background technique
用户通过网站购物时，网站通常会以突出或者区别显示的方式向用户推荐其可能感兴趣的产品或者业务。在推荐过程中主要依据的是用户历史购买行为，根据其购买记录为其推荐具有关联性的商品。When a user is shopping through a website, the website usually recommends products or services that may be of interest to the user in a prominent or differentiated manner. The recommendation process is mainly based on the user's historical purchase behavior, and relevant products are recommended for them according to their purchase records.
用户购买了某个商品之后，很可能对这个商品的“配件产品”(如手机-＞手机套、贴膜，笔记本-＞散热架、鼠标等)和其“周边产品”(如洗面奶-＞面霜，婴儿奶粉-＞纸尿裤等)也有潜在的需求。现有技术公开了一种推荐方法：1)用户欲购买的商品加入购物车；2)搜索该欲购买商品信息所属的类别；3)将该类目下包含的其他商品信息按某一时间段内的销量进行排序，并将排位靠前的商品信息作为推荐商品信息推荐给用户。由此可知，现有技术中的商品推荐方法多为帮助用户找到最适合的关联产品或附属产品，并在购物路径上展现出来，由用户选择是否购买。After a user purchases a certain product, it is likely that the "accessory products" of this product (such as mobile phone -> mobile phone case, film, notebook -> cooling rack, mouse, etc.) and its "peripheral products" (such as facial cleanser -> facial cream) , baby milk powder -> diapers, etc.) also have potential demand. The prior art discloses a recommendation method: 1) adding the product that the user wants to buy into the shopping cart; 2) searching for the category to which the product information to be purchased belongs; 3) other product information contained in the category is classified according to a certain time period It sorts the sales volume within the system, and recommends the top-ranked product information to the user as the recommended product information. From this, it can be seen that most of the commodity recommendation methods in the prior art are to help users find the most suitable related products or auxiliary products, and display them on the shopping path, and let the user choose whether to buy or not.
在某些情况下，一些商品用户当前无法购买，例如需要缴费成为会员才可购买、或者某一业务的附属业务(如增量服务或者加量包等)需要订购了主业务/主套餐后才可叠加购买。对于这些需要用户满足一定条件才能购买的附属商品，现有技术中通常在商品搜索页面根据现有的搜索算法无差别的列明，或者在推荐商品信息时遵循“用户能看得到的必须是能够买到的”的原则，过滤掉这些用户无法购买的商品或者业务。In some cases, some commodity users cannot currently purchase, for example, they need to pay to become a member before they can purchase, or the subsidiary business of a certain business (such as incremental service or additional package, etc.) needs to subscribe to the main business/main package. Can be purchased in stacks. For these affiliated products that require users to meet certain conditions to purchase, in the prior art, they are usually listed indiscriminately on the product search page according to the existing search algorithms, or when recommending product information, follow the guidelines of "What users can see must be able to According to the principle of "purchased", the products or services that cannot be purchased by these users are filtered out.
现有技术中，通过用户行为的历史记录为其推荐其关注的商品的附属产品，或者为其推荐其希望订购的业务的附属业务。但是在用户不曾关注某一商品或者某一业务时，就不会向用户推荐该商品/业务的附属产品/业务。而真正吸引用户的可能正是这些附属产品或者附属业务。对于用户当前无法订购的(附属)产品或者(附属)业务，若不加以区别的以搜索结果的方式展示给用户，用户却不能购买，会给用户带来困扰；若在推荐中直接过滤掉，则很可能屏蔽了用户真正想订购的商品。In the prior art, the user recommends the affiliated products of the commodity he is interested in, or recommends the affiliated service of the service he wants to order through the history of the user's behavior. However, when the user has not paid attention to a certain commodity or a certain business, the user will not be recommended to the user for the subsidiary products/services of the commodity/business. And it may be these affiliated products or affiliated businesses that really attract users. For the (affiliated) products or (affiliated) services that the user cannot currently order, if they are displayed to the user in the form of search results without distinction, but the user cannot purchase it, it will cause trouble to the user; if it is directly filtered out in the recommendation, It is very likely that the item that the user really wants to order is blocked.
发明内容SUMMARY OF THE INVENTION
本发明提供一种克服上述问题或者至少部分地解决上述问题的商品推荐方法和系统。The present invention provides a product recommendation method and system that overcomes the above problems or at least partially solves the above problems.
根据本发明的一个方面，提供一种商品推荐方法，包括：According to one aspect of the present invention, a method for recommending products is provided, comprising:
S1、获取用户因不符合购买条件而无法订购的多个附属商品；S1. Obtain multiple affiliated products that the user cannot order because they do not meet the purchase conditions;
S2、获取各所述附属商品在符合购买条件的抽样人群中的购买比例；对于任意一个附属商品，根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率；S2. Obtain the purchase ratio of each of the affiliated commodities in the sampled population that meets the purchase conditions; for any affiliated commodity, obtain the probability that the user purchases the affiliated commodity according to the purchase ratio of the affiliated commodity in the sampled population that meets the purchase conditions ;
S3、根据用户购买各附属商品的概率由高到低的顺序，向用户推荐附属商品，并根据附属商品-主商品关联关系提示购买该附属商品所需的主商品；S3. Recommend ancillary commodities to the user according to the descending order of the probability that the user purchases each ancillary commodity, and prompt the main commodity required to purchase the ancillary commodity according to the association relationship between the ancillary commodity and the main commodity;
其中，在所述附属商品-主商品关联关系中任意一个附属商品至少与一个主商品存在关联关系，所述符合购买条件的判定方法为用户已购买与该附属商品存在关联关系的主商品。Wherein, in the affiliated commodity-main commodity association relationship, any affiliated commodity is associated with at least one main commodity, and the method for determining that the purchase condition is met is that the user has purchased the main commodity that is associated with the affiliated commodity.
优选地，所述附属商品-主商品关联关系的确定方法还包括：Preferably, the method for determining the associated relationship between the subsidiary commodity and the main commodity further includes:
从购物网站提供的所有商品中确定作为主商品的商品；Identify the item as the main item from all items available on the shopping site;
将所述所有商品中不作为主商品的任意一个商品作为附属商品；对任意一个附属商品，建立该附属商品与至少一个主商品的关联关系。优选地，所述步骤S1具体包括：Any one of the commodities that is not the main commodity is regarded as a subsidiary commodity; for any subsidiary commodity, an association relationship between the subsidiary commodity and at least one main commodity is established. Preferably, the step S1 specifically includes:
根据用户已购买的商品和所述附属商品-主商品关联关系，获知用户当前未购买的主商品；According to the commodity that the user has purchased and the affiliated commodity-main commodity association relationship, learn the main commodity that the user has not purchased currently;
根据所述附属商品-主商品关联关系，获取与所述用户当前未购买的主商品存在关联关系的所有附属商品，作为所述用户因不符合购买条件而无法订购的多个附属商品；According to the affiliated commodity-main commodity association relationship, acquire all affiliated commodities that are associated with the main commodity not currently purchased by the user, as multiple affiliated commodities that the user cannot order because they do not meet the purchase conditions;
其中，所述用户已购买的商品中至少包括一个主商品。Wherein, the commodities purchased by the user include at least one main commodity.
优选地，所述根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，具体包括：Preferably, obtaining the probability that the user purchases the affiliated commodity according to the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions, specifically includes:
将该附属商品在符合购买条件的抽样人群中的购买比例，作为用户购买该附属商品的概率。The purchase ratio of the affiliated product among the sampled population that meets the purchase conditions is taken as the probability that the user purchases the affiliated product.
优选地，所述根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，具体包括：Preferably, obtaining the probability that the user purchases the affiliated commodity according to the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions, specifically includes:
对该附属商品在符合购买条件的抽样人群中的购买比例进行归一化处理，将归一化后处理的结果作为用户购买各附属商品的概率。The purchase ratio of the affiliated product in the sampling population that meets the purchase conditions is normalized, and the result of the normalized processing is used as the probability of the user purchasing each affiliated product.
优选地，所述根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，具体包括：Preferably, obtaining the probability that the user purchases the affiliated commodity according to the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions, specifically includes:
计算用户购买该附属商品对应的各主商品的置信度；Calculate the confidence level of each main product corresponding to the user purchasing the subsidiary product;
将该附属商品在符合购买条件的抽样人群中的购买比例与所述置信度的乘积，作为得用户购买该附属商品的概率。The product of the purchase ratio of the affiliated commodity in the sample population that meets the purchase conditions and the confidence level is taken as the probability that the user purchases the affiliated commodity.
优选地，所述对该附属商品在符合购买条件的抽样人群中的购买比例进行归一化处理的步骤，具有包括：Preferably, the step of normalizing the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions includes:
根据所述附属商品-主商品关联关系，获得与该附属商品对应的主商品具有关联关系的所有附属商品；According to the affiliated commodity-main commodity association relationship, obtain all affiliated commodities that have an association relationship with the main commodity corresponding to the affiliated commodity;
获取所述所有附属商品在符合购买条件的抽样人群中的购买比例；Obtain the purchase ratio of all the affiliated products in the sample population that meets the purchase conditions;
将该附属商品在符合购买条件的抽样人群中的购买比例与所述所有附属商品在符合购买条件的抽样人群中的购买比例之和的商，作为归一化后处理的结果。The quotient of the purchase ratio of the affiliated commodity in the sampling population meeting the purchase conditions and the sum of the purchase proportions of all the affiliated commodities in the sampling population meeting the purchase condition is taken as the result of the normalized post-processing.
根据本发明的另一个方面，还提供一种商品推荐系统，包括：According to another aspect of the present invention, there is also provided a product recommendation system, comprising:
附属商品模块，用于获取用户因不符合购买条件而无法订购的多个附属商品；The affiliated product module, used to obtain multiple affiliated products that users cannot order because they do not meet the purchase conditions;
概率模块，用于获取各所述附属商品在符合购买条件的抽样人群中的购买比例；对于任意一个附属商品，根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率；The probability module is used to obtain the purchase ratio of each of the affiliated products in the sampled population that meets the purchase conditions; for any affiliated product, according to the purchase ratio of the affiliated product in the sampled population that meets the purchase conditions, it is obtained that the user purchased the affiliated product the probability of the commodity;
推荐模块，用于按照用户购买各附属商品的概率由高到低的顺序，向用户推荐附属商品，并根据附属商品-主商品关联关系提示购买该附属商品所需的主商品；The recommendation module is used for recommending the subsidiary commodities to the user in descending order of the probability that the user purchases each subsidiary commodity, and prompting the main commodities required for purchasing the subsidiary commodities according to the relation between the subsidiary commodities and the main commodities;
其中，在所述附属商品-主商品关联关系中任意一个附属商品至少与一个主商品存在关联关系，所述符合购买条件的判定方法为表示用户已购买与该附属商品存在关联关系的主商品。Wherein, in the affiliated commodity-main commodity association relationship, any affiliated commodity is associated with at least one main commodity, and the method for determining that the purchase condition is met is to indicate that the user has purchased the main commodity that is associated with the affiliated commodity.
优选地，所述商品推荐系统还包括：Preferably, the product recommendation system further includes:
关联模块，用于确定所述附属商品-主商品关联关系，所述关联模块具体用于：an association module, used to determine the associated relationship between the subsidiary commodity and the main commodity, and the association module is specifically used for:
从购物网站提供的所有商品中确定作为主商品的商品；Identify the item as the main item from all items available on the shopping site;
将所述所有商品中不作为主商品的任意一个商品作为附属商品；对任意一个附属商品，建立该附属商品与至少一个主商品的关联关系。Any one of the commodities that is not the main commodity is regarded as a subsidiary commodity; for any subsidiary commodity, an association relationship between the subsidiary commodity and at least one main commodity is established.
优选地，所述附属商品模块具体包括：Preferably, the affiliated commodity module specifically includes:
主商品单元，根据用户已购买的商品和所述附属商品-主商品关联关系，获知用户当前未购买的主商品；The main commodity unit, according to the commodity that the user has purchased and the ancillary commodity-main commodity association relationship, to know the main commodity that the user has not purchased currently;
附属商品单元，根据所述附属商品-主商品关联关系，获取与所述用户当前未购买的主商品存在关联关系的所有附属商品，作为所述用户因不符合购买条件而无法订购的多个附属商品；The affiliated commodity unit, according to the affiliated commodity-main commodity association relationship, obtains all affiliated commodities that have an associated relationship with the main commodity that the user has not purchased currently, as multiple affiliated commodities that the user cannot order because the user does not meet the purchase conditions commodity;
其中，所述用户已购买的商品中至少包括一个主商品。Wherein, the commodities purchased by the user include at least one main commodity.
本发明提出的商品推荐方法及系统，通过获取用户因不符合购买条件而无法订购的多个附属商品，为实现向用户推荐当前无法购买但销售火爆的商品提供了基础，通过获取各附属商品在符合购买条件的抽样人群中的购买比例，能够获知用户倾向购买的附属商品的排名，最后根据排名向用户推荐附属商品，并提供相应的主商品的购买链接，一方面能够对明星附属商品进行有针对性的推荐，避免其商品信息被用户屏蔽，或者其商品信息淹没在普通商品中；另一方面，还会拉动用户对这些附属商品的订购，促进消费。The product recommendation method and system proposed by the present invention provide a basis for recommending to the user a plurality of auxiliary products that cannot be ordered because the user does not meet the purchase conditions and cannot be ordered. The proportion of purchases among the sampled people who meet the purchase conditions can be used to know the ranking of the affiliated products that users tend to buy, and finally recommend the affiliated products to the user according to the ranking, and provide the purchase link of the corresponding main product. Targeted recommendations can prevent its product information from being blocked by users, or its product information is submerged in ordinary products; on the other hand, it will also drive users to order these subsidiary products and promote consumption.
附图说明Description of drawings
图1为根据本发明实施例的商品推荐方法的流程示意图；1 is a schematic flowchart of a product recommendation method according to an embodiment of the present invention;
图2为根据本发明实施例的商品推荐系统的功能框图。FIG. 2 is a functional block diagram of a product recommendation system according to an embodiment of the present invention.
具体实施方式Detailed ways
下面结合附图和实施例，对本发明的具体实施方式作进一步详细描述。以下实施例用于说明本发明，但不用来限制本发明的范围。The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. The following examples are intended to illustrate the present invention, but not to limit the scope of the present invention.
为了克服现有技术的上述问题，本发明实施例提供一种商品推荐方法。本发明各个实施例主要说明对用户目前不能购买，但却很可能购买的商品进行推荐。本发明实施例所涉及的商品分为主商品和附属商品。主商品和附属商品之间存在关联关系，也称之为依赖关系，即拥有主商品是购买与该主商品存在关联关系的附属产品的前提。例如，只有属于A类付费会员的用户才能够订购只有这类会员能够订购的附属业务A1和A2，则称A类付费会员是主商品，附属业务A1和A2是对应该主商品A的附属商品。本发明实施例所述涉及的商品，可以包括各种可以合法交易的实体产品或虚拟产品，例如话费业务套餐、生鲜水果、会员资格等等。In order to overcome the above problems of the prior art, an embodiment of the present invention provides a method for recommending products. Each embodiment of the present invention mainly describes recommending commodities that users cannot currently purchase but are likely to purchase. The commodities involved in the embodiments of the present invention are divided into main commodities and auxiliary commodities. There is an association relationship between the main commodity and the affiliated commodity, which is also called a dependency relationship, that is, the possession of the main commodity is the premise of purchasing an affiliated product that has an association relationship with the main commodity. For example, only the users who belong to the A-type paid members can order the affiliated services A1 and A2 that only such members can order, then the A-type paid members are said to be the main commodities, and the affiliated services A1 and A2 are the subordinate commodities corresponding to the main commodity A. . The commodities involved in the embodiments of the present invention may include various physical products or virtual products that can be legally traded, such as service packages for phone bills, fresh fruits, membership, and so on.
结合图1，是本发明实施例的一种商品推荐方法的流程示意图，该实施例描述了基于本发明的一种向用户推荐当前没有资格购买的商品的方法，该方法包括：1 is a schematic flowchart of a method for recommending products according to an embodiment of the present invention. The embodiment describes a method for recommending products that are not currently eligible for purchase to users based on the present invention, and the method includes:
S101、获取用户因不符合购买条件而无法订购的多个附属商品。S101. Acquire multiple auxiliary commodities that the user cannot order because the user does not meet the purchase conditions.
在具体应用时，根据用户的历史购物请求可以获得用户购买过的商品，通过对商品按照预设的规则进行分类，即可确定商品中哪些属于主商品，哪些属于附属商品，通过查询分类结果，可以知道用户购买过商品哪些属于主商品，相应地也就知道了用户还没有购买过的主商品，由于主商品和附属商品存在关联关系，因此，可以进一步获取用户还无法购买的附属商品，这些附属商品就是因为用户没有购买相应主商品而受限无法购买的商品。本实施例并不对附属商品对应的主商品的个数进行限制，这是因为在实际应用时，某些商品的购买条件可能不止一种。In the specific application, the products purchased by the user can be obtained according to the user's historical shopping requests. By classifying the products according to the preset rules, it can be determined which of the products belong to the main product and which belong to the auxiliary products. By querying the classification results, You can know which products the user has purchased belong to the main product, and correspondingly know the main product that the user has not purchased. Since the main product and the subsidiary product are related, you can further obtain the subsidiary products that the user cannot buy yet. These are Ancillary products are products that cannot be purchased because the user has not purchased the corresponding main product. This embodiment does not limit the number of main commodities corresponding to the subsidiary commodities, because in practical application, some commodities may have more than one purchase condition.
S102、获取各附属商品在符合购买条件的抽样人群中的购买比例；对于任意一个附属商品，根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，符合购买条件的判定方法为用户已购买与该附属商品存在关联关系的主商品。S102: Obtain the purchase ratio of each affiliated product among the sampled population that meets the purchase conditions; for any affiliated product, obtain the probability that the user purchases the affiliated product according to the purchase ratio of the affiliated product in the sampled population that meets the purchase conditions, and meets the The determination method of the purchase condition is that the user has purchased the main commodity that is associated with the subsidiary commodity.
需要说明的是，通过对购物网站中各商品(包括主商品和附属商品)的购买情况进行统计，可以获知每种附属商品的购买人数和符合购买该附属商品条件的人数，通过将两个数值相除，即可获知附属商品在符合购买条件的抽样人群中的购买比例。例如附属商品：5元购买1斤羊肉必须满足条件：用户已购买金牌会员资格，那么统计可知购买该商品的人数为n，而购买了金牌会员资格的用户的人数为m，那么该附属商品的购买比例为n/m。It should be noted that, by collecting statistics on the purchases of each product (including the main product and the subsidiary product) in the shopping website, the number of purchasers of each subsidiary product and the number of people who meet the conditions for purchasing the subsidiary product can be obtained. Divide the ratio to obtain the purchase ratio of the affiliated products among the sampled population that meets the purchase conditions. For example, an affiliated product: 5 yuan to buy 1 catty of mutton must meet the conditions: the user has purchased the gold membership, then the statistics show that the number of people who bought the product is n, and the number of users who purchased the gold membership is m, then the number of the affiliated product is n. The purchase ratio is n/m.
由于某些商品的购买量非常大，统计每个商品的实际购买人数比较困难，因此可以通过抽样的方式选择一定数量的用户，然后统计抽样中所有用户中符合购买条件的人数以及实际购买的人数，获得购买比例。比如抽样选择了10000名用户，统计这10000名用户中符合购买附属商品1的人数一共有3000名，而实际购买附属商品1的人数有1500人，那么认为附属商品1在符合购买条件的抽样人群中的购买比例为50％。Due to the large amount of purchases of certain products, it is difficult to count the actual number of purchasers of each product. Therefore, a certain number of users can be selected by sampling, and then the number of people who meet the purchase conditions and the number of people who actually purchase among all users in the sampling can be counted. , to get the purchase ratio. For example, 10,000 users are selected by sampling, and a total of 3,000 people are eligible to purchase affiliated product 1 among the 10,000 users, and 1,500 people actually purchase affiliated product 1, then it is considered that affiliated product 1 is among the sampling groups that meet the purchase conditions. The purchase ratio in 50%.
显然，每种商品在符合购买条件的人群中的购买比例越高，说明这款商品受欢迎的程度越高，用户将来购买该商品的可能性也越大。Obviously, the higher the purchase ratio of each product among the people who meet the purchase conditions, the higher the popularity of the product, and the greater the possibility that users will buy the product in the future.
S103、按照用户购买各附属商品的概率由高到低的顺序，向用户推荐附属商品，并根据附属商品-主商品关联关系提示购买该附属商品所需的主商品，在附属商品-主商品关联关系中任意一个附属商品至少与一个主商品存在关联关系。S103. Recommend the affiliated commodities to the user in descending order of the probability that the user purchases each affiliated commodity, and prompt the main commodity required to purchase the affiliated commodity according to the affiliated commodity-main commodity association relationship. Any subsidiary product in the relationship is associated with at least one main product.
需要说明的是，附属商品-主商品关联关系包含了购物网站中每一个商品的属性，即该商品是属于主商品还是附属商品，当该商品为主商品时，列出与其存在关联关系的的附属商品，当该商品为附属商品时，列出与其存在关联关系的主商品，在具体实施时，可以采用(主商品A；附属商品A1，附属商品A2，…An)的形式表达一组存在关联关系的主商品和附属商品。It should be noted that the affiliated product-main product relationship includes the attributes of each product in the shopping website, that is, whether the product belongs to the main product or the auxiliary product. When the product is the main product, list the related products. Auxiliary commodity, when the commodity is an auxiliary commodity, it lists the main commodity that has an associated relationship with it. In specific implementation, it can express a group of existences in the form of (main commodity A; auxiliary commodity A1, auxiliary commodity A2, ... An) The main and subsidiary products of the relationship.
在获得步骤S102获得的用户购买各附属商品的概率后，根据各附属商品的概率由高到低的顺序，向用户推荐附属商品，使得用户接收到最可能购买的商品，提高商品交易的效率。After obtaining the probability of the user purchasing each affiliated commodity obtained in step S102, the affiliated commodity is recommended to the user according to the probability of each affiliated commodity in descending order, so that the user receives the most likely purchased commodity and improves the efficiency of commodity transaction.
在实际应用时，可以将推荐的附属商品以邮件的方式向用户的邮箱进行推送，也可以在用户登录购物客户端时，以弹窗的形式进行提醒。In practical application, the recommended affiliated products can be pushed to the user's mailbox by email, or a pop-up window can be used to remind the user when the user logs in to the shopping client.
在一个可选实施例中，将推荐的附属商品添加至用户的购物车，需要注意的是，当直接将推荐的附属商品添加至购物车时，每次添加的数量需要进行控制，例如2-3个，当客户对添加进购物车的附属商品及需要购买的主商品全部进行购买或购买预设数量后，才会继续将后续的附属商品和需要购买的主商品添加至购物车，否则将不再直接添加至购物车，防止客户产生负面情绪。In an optional embodiment, the recommended affiliated products are added to the user's shopping cart. It should be noted that when the recommended affiliated products are directly added to the shopping cart, the quantity added each time needs to be controlled, for example, 2- 3. When the customer purchases all the subsidiary products added to the shopping cart and the main product to be purchased or purchases the preset quantity, the subsequent subsidiary products and the main product to be purchased will continue to be added to the shopping cart. Stop adding directly to cart to prevent negative emotions from customers.
在上述各实施例的基础上，附属商品-主商品关联关系的确定方法还包括：On the basis of the above embodiments, the method for determining the associated relationship between the subsidiary commodity and the main commodity further includes:
从购物网站提供的所有商品中确定作为主商品的商品；Identify the item as the main item from all items available on the shopping site;
将所述所有商品中不作为主商品的任意一个商品作为附属商品；对任意一个附属商品，建立该附属商品与至少一个主商品的关联关系。Any one of the commodities that is not the main commodity is regarded as a subsidiary commodity; for any subsidiary commodity, an association relationship between the subsidiary commodity and at least one main commodity is established.
需要说明的是，本发明实施例通过对商品进行分类，获知每种商品属于主商品或附属商品，并根据该商品为主商品或附属商品，将其与附属商品或主商品进行关联。具体的分类规则可以由不同公司根据自身的业务情况进行分类，本发明不做具体的限定。It should be noted that, in the embodiment of the present invention, by classifying the commodities, it is known that each commodity belongs to the main commodity or the auxiliary commodity, and the commodity is associated with the auxiliary commodity or the main commodity according to the main commodity or the auxiliary commodity. The specific classification rules can be classified by different companies according to their own business conditions, which are not specifically limited in the present invention.
在上述各实施例的基础上，步骤S101具体包括：On the basis of the above embodiments, step S101 specifically includes:
根据用户已购买的商品和附属商品-主商品关联关系，获知用户当前未购买的主商品。According to the commodity that the user has purchased and the affiliated commodity-main commodity association relationship, the main commodity that the user has not purchased currently is known.
在具体应用时，用户已购买的商品必然既有主商品也有附属商品，由于附属商品-主商品关联关系中标示了各主商品，显然很容易获知用户当前未购买的主商品。In a specific application, the product that the user has purchased must have both the main product and the subsidiary product. Since the main product is marked in the subsidiary product-main product association relationship, it is obviously easy to know the main product that the user has not purchased.
根据附属商品-主商品关联关系，获取与用户当前未购买的主商品存在关联关系的所有附属商品，作为用户因不符合购买条件而无法订购的多个附属商品；According to the affiliated commodity-main commodity association relationship, obtain all affiliated commodities that are associated with the main commodity that the user has not purchased, as multiple affiliated commodities that the user cannot order because they do not meet the purchase conditions;
其中，所述用户已购买的商品中至少包括一个主商品。Wherein, the commodities purchased by the user include at least one main commodity.
例如，附属商品-主商品关联关系中标示了三种主商品A、B和C，主商品A具有A1和A2两个附属商品，主商品B具有B1和B2两个附属商品，主商品C具有C1、C2和C3三个附属商品，已知用户已购买了主商品A，那么用户当前未购买的主商品即为B和C，用户因不符合购买条件而无法订购的附属商品即为B1、B2、C1、C2和C3。For example, three main commodities A, B and C are indicated in the affiliated commodity-main commodity relationship. Main commodity A has two affiliated commodities A1 and A2, main commodity B has two affiliated commodities B1 and B2, and main commodity C has two affiliated commodities. There are three subsidiary commodities C1, C2 and C3. It is known that the user has purchased the main commodity A, then the main commodities that the user has not purchased are B and C, and the subsidiary commodities that the user cannot order because they do not meet the purchase conditions are B1, B2, C1, C2 and C3.
在上述各实施例的基础上，根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，具体包括：On the basis of the above embodiments, according to the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions, the probability of the user purchasing the affiliated commodity is obtained, which specifically includes:
将该附属商品在符合购买条件的抽样人群中的购买比例，作为用户购买该附属商品的概率。The purchase ratio of the affiliated product among the sampled population that meets the purchase conditions is taken as the probability that the user purchases the affiliated product.
需要说明的是，本实施例的获得用户购买附属商品的概率的方法具有简单、准确率较高的优点。It should be noted that the method for obtaining the probability of a user purchasing an accessory commodity in this embodiment has the advantages of simplicity and high accuracy.
由于某些商品的购买人数非常大，统计所有购买人数和购买比例存在耗时较大的缺点，因此，在一个可选实施例中，根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，具体包括：Since the number of purchasers of some commodities is very large, it takes a long time to count all the number of buyers and the purchase ratio. Therefore, in an optional embodiment, according to the purchase ratio of the affiliated product among the sampled population that meets the purchase conditions , to obtain the probability that the user purchases the affiliated product, including:
对该附属商品在符合购买条件的抽样人群中的购买比例进行归一化处理，将归一化后处理的结果作为用户购买各附属商品的概率。The purchase ratio of the affiliated product in the sampling population that meets the purchase conditions is normalized, and the result of the normalized processing is used as the probability of the user purchasing each affiliated product.
通过抽样选取一定数量的符合购买条件的人群，计算该人群中购买附属商品的比例，能够减少购买比例的获取难度，本实施例进一步对购买比例进行归一化处理，能够归纳统一样本的统计分布性，有效缩小量值。Selecting a certain number of people who meet the purchasing conditions by sampling, and calculating the proportion of purchasing ancillary products in the population can reduce the difficulty of obtaining the purchasing proportion. In this embodiment, the purchasing proportion is further normalized, and the statistical distribution of the unified sample can be summarized. , effectively reducing the magnitude.
在上述各实施例的基础上，本实施例的根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率，具体包括：On the basis of the above-mentioned embodiments, in this embodiment, the probability that the user purchases the affiliated commodity is obtained according to the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions, which specifically includes:
计算用户购买该附属商品对应的各主商品的置信度；Calculate the confidence level of each main product corresponding to the user purchasing the subsidiary product;
将该附属商品在符合购买条件的抽样人群中的购买比例与置信度的乘积，作为得用户购买该附属商品的概率。The product of the purchase ratio of the affiliated commodity in the sampled population that meets the purchase conditions and the confidence level is taken as the probability that the user purchases the affiliated commodity.
需要说明的是，置信度，也称为可靠度，它是指特定个体对待特定命题真实性相信的程度，也就是概率是对个人信念合理性的量度。在抽样对总体参数作出估计时，由于样本的随机性，其结论总是不确定的。因此，采用一种概率的陈述方法，也就是数理统计中的区间估计法，即估计值与总体参数在一定允许的误差范围以内，其相应的概率有多大，这个相应的概率称作置信度。本实施例通过增加置信度的计算，能够进一步增加估计的准确程度。It should be noted that confidence, also known as reliability, refers to the degree to which a particular individual believes in the truth of a particular proposition, that is, probability is a measure of the rationality of individual beliefs. When sampling to estimate population parameters, the conclusion is always uncertain due to the randomness of the sample. Therefore, a probability statement method is adopted, that is, the interval estimation method in mathematical statistics, that is, the estimated value and the overall parameter are within a certain allowable error range, what is the corresponding probability, and this corresponding probability is called confidence. This embodiment can further increase the accuracy of the estimation by increasing the calculation of the confidence level.
需要注意的是，置信度根据待推荐商品的不同，计算方法也可能不同，具体计算可参考现有的算法，例如经分算法、大数法则等等。置信度的计算非本申请的核心。例如，若待推荐的是运营商的套餐，可以根据用户每月arpu、mou和dou(即月消费、语音使用量和流量使用量)等跟套餐的匹配度来计算推荐的置信度；电商则可以根据用户的历史购买记录、访问记录、收藏记录等数据来计算推荐置信度。It should be noted that the calculation method of the confidence level may be different according to the different products to be recommended. For the specific calculation, please refer to the existing algorithms, such as the division algorithm, the law of large numbers, and so on. The calculation of confidence is not the core of this application. For example, if the package to be recommended is an operator's package, the confidence level of the recommendation can be calculated based on the user's monthly arpu, mou and dou (that is, monthly consumption, voice usage and traffic usage) and the matching degree of the package; Then, the recommendation confidence can be calculated according to the user's historical purchase records, access records, collection records and other data.
在上述实施例的基础上，对该附属商品在符合购买条件的抽样人群中的购买比例进行归一化处理的步骤，具有包括：On the basis of the above-mentioned embodiment, the step of normalizing the purchase ratio of the affiliated commodity in the sampling population that meets the purchase conditions includes:
根据附属商品-主商品关联关系，获得与该附属商品对应的主商品具有关联关系的所有附属商品；According to the affiliated commodity-main commodity association relationship, obtain all affiliated commodities that have an associated relationship with the main commodity corresponding to the affiliated commodity;
获取所有附属商品在符合购买条件的抽样人群中的购买比例；Obtain the purchase ratio of all affiliated products among the sampled population eligible for purchase;
将该附属商品在符合购买条件的抽样人群中的购买比例与所有附属商品在符合购买条件的抽样人群中的购买比例之和的商，作为归一化后处理的结果。The quotient of the purchase ratio of the affiliated product in the sampled population that meets the purchase conditions and the sum of the purchase proportions of all the affiliated products in the sampled population that meets the purchase conditions is taken as the result of normalized post-processing.
例如，主商品A具有A1、A2和A3三个附属商品，购买主商品A(即具有购买A1、A2和A3三个附属商品的资格)的抽样人群的人数为10万人，其中，购买附属商品A1的人数为4万，购买附属商品A2的人数为2万，购买附属商品A3的人数为2万，那么在对购买附属商品A1进行归一化处理时，首先获得了与附属商品A1对应的主商品A具有关联关系的所有附属商品A2和A3，然后获取附属商品A2在抽样人群中的购买比例为2÷10＝20％，附属商品A2在抽样人群中的购买比例为2÷10＝20％，同理，购买附属商品A1在抽样人群中的购买比例为40％，因此，所有附属商品在符合购买条件的抽样人群中的购买比例之和为80％，因此，附属商品A1在符合购买条件的抽样人群中的购买比例，进行归一化处理后的结果为0.4÷0.8＝0.5。For example, the main commodity A has three subsidiary commodities A1, A2 and A3, and the number of sampled people who purchase the main commodity A (that is, qualified to purchase the three subsidiary commodities A1, A2 and A3) is 100,000, of which There are 40,000 people who purchased product A1, 20,000 people who bought the affiliated product A2, and 20,000 people who bought the affiliated product A3. Then, when normalizing the purchase of the affiliated product A1, the corresponding product corresponding to the affiliated product A1 is obtained first. The main commodity A of the main commodity A has all the affiliated commodities A2 and A3 in the associated relationship, and then the purchase ratio of the affiliated commodity A2 in the sampled population is 2÷10=20%, and the purchase ratio of the affiliated commodity A2 in the sampled population is 2÷10= 20%, in the same way, the purchase proportion of the affiliated product A1 in the sampled population is 40%. Therefore, the sum of the purchase proportion of all affiliated products in the sampled population that meets the purchase conditions is 80%. The purchase ratio of the sampled population of purchase conditions, after normalization, the result is 0.4÷0.8=0.5.
根据本发明的另一个方面，还提供一种商品推荐系统，如图2所示，该系统用于在前述各实施例中向用户推荐当前没有资格购买的商品，因此，在前序各实施例中的商品推荐方法中的描述和定义，可以用于本发明实施例中各执行模块的理解。According to another aspect of the present invention, a product recommendation system is also provided. As shown in FIG. 2 , the system is used to recommend products that are not currently eligible for purchase to users in the foregoing embodiments. Therefore, in the preceding embodiments The descriptions and definitions in the commodity recommendation method in , can be used for the understanding of each execution module in this embodiment of the present invention.
如图所示，商品推荐系统包括：As shown in the figure, the product recommendation system includes:
附属商品模块201，用于获取用户因不符合购买条件而无法订购的多个附属商品。The affiliated commodity module 201 is used to acquire multiple affiliated commodities that the user cannot order because they do not meet the purchase conditions.
在具体应用时，附属商品模块201根据用户的历史购物请求可以获得用户购买过的商品，通过对商品按照预设的规则进行分类，即可确定商品中哪些属于主商品，哪些属于附属商品，通过查询分类结果，可以知道用户购买过哪些主商品，相应地也就知道了用户还没有购买过的主商品，由于主商品和附属商品存在关联关系，因此，可以进一步获取用户还无法购买的附属商品，这些附属商品就是因为用户没有购买相应主商品而受限无法购买的商品。本实施例并不对附属商品对应的主商品的个数进行限制，这是因为在实际应用时，某些商品的购买条件可能不止一种。In a specific application, the accessory product module 201 can obtain the products purchased by the user according to the user's historical shopping requests, and by classifying the products according to preset rules, it can determine which of the products belong to the main product and which belong to the auxiliary products. By querying the classification results, you can know which main commodities the user has purchased, and correspondingly the main commodities that the user has not purchased. Since the main commodity and the subsidiary commodities are related, you can further obtain the subsidiary commodities that the user cannot purchase. , these subsidiary products are products that cannot be purchased because the user has not purchased the corresponding main product. This embodiment does not limit the number of main commodities corresponding to the subsidiary commodities, because in practical application, some commodities may have more than one purchase condition.
概率模块202，用于获取各附属商品在符合购买条件的抽样人群中的购买比例；对于任意一个附属商品，根据该附属商品在符合购买条件的抽样人群中的购买比例，获得用户购买该附属商品的概率,符合购买条件的判定方法为用户已购买与该附属商品存在关联关系的主商品。The probability module 202 is used to obtain the purchase ratio of each affiliated product in the sampled population that meets the purchase conditions; for any affiliated product, according to the purchase ratio of the affiliated product in the sampled population that meets the purchase condition, it is obtained that the user purchased the affiliated product The probability that the purchase condition is met is that the user has purchased the main product that is associated with the subsidiary product.
需要说明的是，概率模块202通过对购物网站中各商品的购买情况进行统计，可以获知每种附属商品的购买人数和负荷购买该附属商品条件的人数，通过将两个数值相除，即可获知附属商品在符合购买条件的抽样人群中的购买比例。例如附属商品：5元购买1斤羊肉必须满足条件：用户已购买金牌会员资格，那么统计可知购买该商品的人数为n，而购买了金牌会员资格的用户的人数为m，那么该附属商品的购买比例为n/m。It should be noted that the probability module 202 can obtain the number of purchasers of each affiliated commodity and the number of people who purchase the condition of the affiliated commodity by collecting statistics on the purchases of each commodity in the shopping website. By dividing the two values, Get the percentage of purchases of affiliated products among the sampled population eligible for purchase. For example, an affiliated product: 5 yuan to buy 1 catty of mutton must meet the conditions: the user has purchased the gold membership, then the statistics show that the number of people who bought the product is n, and the number of users who purchased the gold membership is m, then the number of the affiliated product is n. The purchase ratio is n/m.
由于某些商品的购买量非常大，统计每个商品的实际购买人数比较困难，因此可以通过抽样的方式选择一定数量的用户，然后统计抽样中所有用户中符合购买条件的人数以及实际购买的人数，获得购买比例。比如抽样选择了10000名用户，统计这10000名用户中符合购买附属商品1的人数一共有3000名，而实际购买附属商品1的人数有1500人，那么认为附属商品1在符合购买条件的抽样人群中的购买比例为50％。Due to the large amount of purchases of certain products, it is difficult to count the actual number of purchasers of each product. Therefore, a certain number of users can be selected by sampling, and then the number of people who meet the purchase conditions and the number of people who actually purchase among all users in the sampling can be counted. , to get the purchase ratio. For example, 10,000 users are selected by sampling, and among the 10,000 users, there are 3,000 people who are eligible to purchase ancillary product 1, and 1,500 people actually buy ancillary product 1, then it is considered that ancillary product 1 is in the sample population that meets the purchase conditions. The purchase ratio in 50%.
显然，每种商品在符合购买条件的人群中的购买比例越高，说明这款商品受欢迎的程度越高，用户将来购买该商品的可能性也越大。Obviously, the higher the purchase ratio of each product among the people who meet the purchase conditions, the higher the popularity of the product, and the greater the possibility that users will buy the product in the future.
推荐模块203，用于按照用户购买各附属商品的概率由高到低的顺序，向用户推荐附属商品，并根据附属商品-主商品关联关系提示购买该附属商品所需的主商品，在附属商品-主商品关联关系中任意一个附属商品至少与一个主商品存在关联关系。The recommendation module 203 is configured to recommend the subsidiary commodities to the user in descending order of the probability that the user purchases the subsidiary commodities, and prompt the main commodities required to purchase the subsidiary commodities according to the correlation between the subsidiary commodities and the main commodities. -Any one of the subsidiary commodities in the main commodity association relationship is associated with at least one main commodity.
需要说明的是，附属商品-主商品关联关系包含了购物网站中每一个商品的属性，即该商品是属于主商品还是附属商品，当该商品为主商品时，列出与其存在关联关系的的附属商品，当该商品为附属商品时，列出与其存在关联关系的主商品，在具体实施时，可以采用(主商品A；附属商品A1，附属商品A2，…An)的形式表达一组存在关联关系的主商品和附属商品。It should be noted that the affiliated product-main product relationship includes the attributes of each product in the shopping website, that is, whether the product belongs to the main product or the auxiliary product. When the product is the main product, list the related products. Auxiliary commodity, when the commodity is an auxiliary commodity, it lists the main commodity that has an associated relationship with it. In specific implementation, it can express a group of existences in the form of (main commodity A; auxiliary commodity A1, auxiliary commodity A2, ... An) The main and subsidiary products of the relationship.
在概率模块202获得的用户购买各附属商品的概率后，推荐模块203根据各附属商品的概率由高到低的顺序，向用户推荐附属商品，使得用户接收到最可能购买的商品，提高商品交易的效率。After the probability module 202 obtains the probability that the user purchases each affiliated commodity, the recommendation module 203 recommends the affiliated commodity to the user according to the probability of each affiliated commodity in descending order, so that the user can receive the most likely purchased commodity and improve commodity transactions. s efficiency.
在实际应用时，可以将推荐的附属商品以邮件的方式向用户的邮箱进行推送，也可以在用户登录购物客户端时，以弹窗的形式进行提醒。In practical application, the recommended affiliated products can be pushed to the user's mailbox by email, or a pop-up window can be used to remind the user when the user logs in to the shopping client.
在一个可选实施例中，将推荐的附属商品添加至用户的购物车，需要注意的是，当直接将推荐的附属商品添加至购物车时，每次添加的数量需要进行控制，例如2-3个，当客户对添加进购物车的附属商品及需要购买的主商品全部进行购买或购买预设数量后，才会继续将后续的附属商品和需要购买的主商品添加至购物车，否则将不再直接添加至购物车，防止客户产生负面情绪。In an optional embodiment, the recommended affiliated products are added to the user's shopping cart. It should be noted that when the recommended affiliated products are directly added to the shopping cart, the quantity added each time needs to be controlled, for example, 2- 3. When the customer purchases all the subsidiary products added to the shopping cart and the main product to be purchased or purchases the preset quantity, the subsequent subsidiary products and the main product to be purchased will continue to be added to the shopping cart. Stop adding directly to cart to prevent negative emotions from customers.
在上述各实施例的基础上，商品推荐系统还包括：On the basis of the above embodiments, the product recommendation system further includes:
关联模块，用于确定所述附属商品-主商品关联关系，所述关联模块具体用于：an association module, used to determine the associated relationship between the subsidiary commodity and the main commodity, and the association module is specifically used for:
从购物网站提供的所有商品中确定作为主商品的商品；Identify the item as the main item from all items available on the shopping site;
将所述所有商品中不作为主商品的任意一个商品作为附属商品；对任意一个附属商品，建立该附属商品与至少一个主商品的关联关系Take any one of the commodities that is not the main commodity as a subsidiary commodity; for any subsidiary commodity, establish an association relationship between the subsidiary commodity and at least one main commodity
需要说明的是，本发明实施例中关联模块对商品进行分类，获知每种商品属于主商品或附属商品，并根据该商品为主商品或附属商品，将其与附属商品或主商品进行关联。具体的分类规则可以由不同公司根据自身的业务情况进行分类，本发明不做具体的限定。It should be noted that the association module in the embodiment of the present invention classifies the commodities, learns that each commodity belongs to the main commodity or ancillary commodity, and associates the commodity with the subordinate commodity or the main commodity according to the main commodity or ancillary commodity. The specific classification rules can be classified by different companies according to their own business conditions, which are not specifically limited in the present invention.
在上述各实施例的基础上，附属商品模块具体包括：On the basis of the above embodiments, the accessory commodity module specifically includes:
主商品单元，根据用户已购买的商品和附属商品-主商品关联关系，获知用户当前未购买的主商品；The main commodity unit, according to the commodity purchased by the user and the affiliated commodity-main commodity association, learns the main commodity that the user has not purchased currently;
在具体应用时，用户已购买的商品必然既有主商品也有附属商品，由于附属商品-主商品关联关系中标示了各主商品，显然主商品单元很容易获知用户当前未购买的主商品。In the specific application, the products that the user has purchased must have both the main product and the subsidiary product. Since each main product is marked in the subsidiary product-main product association relationship, it is obvious that the main product unit can easily know the main product that the user has not purchased.
附属商品单元，根据附属商品-主商品关联关系，获取与用户当前未购买的主商品存在关联关系的所有附属商品，作为用户因不符合购买条件而无法订购的多个附属商品。The affiliated commodity unit, according to the affiliated commodity-main commodity association relationship, obtains all affiliated commodities that are associated with the main commodity that the user has not purchased currently, as multiple affiliated commodities that the user cannot order because the user does not meet the purchase conditions.
其中，所述用户已购买的商品中至少包括一个主商品。Wherein, the commodities purchased by the user include at least one main commodity.
例如，附属商品-主商品关联关系中标示了三种主商品A、B和C，主商品A具有A1和A2两个附属商品，主商品B具有B1和B2两个附属商品，主商品C具有C1、C2和C3三个附属商品，已知用户已购买了主商品A，那么用户当前未购买的主商品即为B和C，用户因不符合购买条件而无法订购的附属商品即为B1、B2、C1、C2和C3。For example, three main commodities A, B, and C are indicated in the sub-commodity-main commodity relationship. Main commodity A has two sub-commodities A1 and A2, main commodity B has two sub-commodities B1 and B2, and main commodity C has two sub-commodities. There are three subsidiary commodities C1, C2 and C3. It is known that the user has purchased the main commodity A, then the main commodities that the user has not purchased are B and C, and the subsidiary commodities that the user cannot order because they do not meet the purchase conditions are B1, B2, C1, C2 and C3.
下面就本发明实施例的应用场景进行举例说明。The following describes an example of an application scenario of the embodiment of the present invention.
场景一scene one
某电商平台分为生鲜水果、服装日用、办公电子等频道，各频段均有各自的会员制度。某日生鲜水果频道有特价羊肉，仅限生鲜水果频道的会员抢购，并且系统发现几乎所有的生鲜水果频道会员都抢购了该款羊肉；同日办公电子频道有某款仅限会员购买的手机，销量较高。An e-commerce platform is divided into channels such as fresh fruit, daily clothing, office electronics, etc. Each frequency band has its own membership system. On a certain day, the fresh fruit channel has special mutton, which can only be purchased by members of the fresh fruit channel, and the system found that almost all the members of the fresh fruit channel have snapped up the mutton; on the same day, the office electronic channel has a certain type of mutton that can only be purchased by members. Mobile phones are selling well.
当某用户登录该电商平台后，系统为其推荐特价羊肉，并附加成为生鲜水果频道会员的链接；同时推荐该款手机，并附加成为办公电子频道会员的链接。When a user logs in to the e-commerce platform, the system recommends special mutton for him, and attaches a link to become a member of the fresh fruit channel; at the same time, recommends the mobile phone and attaches a link to become a member of the office electronic channel.
场景二scene two
某IT公司向个人/企业用户提供各种SaaS和PaaS服务，其服务通常具有基本框架或者套餐，在各框架/套餐下可能会有针对公司人事、流程管理、邮件管理、数据存储、安全服务等各类子业务，若其邮件管理子业务为某一框架下的明星业务，则在某用户还不能订购这些子业务时，仍有针对性的给该用户进行邮件管理业务的推荐，并附加其所属的业务框架的订购途径。该方法能够通过明星子业务带动基础业务的订购。An IT company provides various SaaS and PaaS services to individual/enterprise users. Its services usually have basic frameworks or packages. Under each framework/package, there may be services for company personnel, process management, email management, data storage, security services, etc. For various sub-services, if the email management sub-service is a star service under a certain framework, when a user cannot subscribe to these sub-services, the email management service will still be recommended to the user and attached with other sub-services. The ordering route of the business framework to which it belongs. This method can drive the subscription of the basic business through the star sub-business.
场景三scene three
运营商话费套餐平台的套餐购买页面中推荐某些独立的附属业务，例如流量增量包、通话时长增量包等等，这些业务通常廉价并且购买灵活，销量高，用户接受程度高。但是大多数增量包依托于不同的基本套餐，在推荐各套餐中的明星增量产品时，附加该模型增量产品所属的基本套餐的订购链接，在引导用户订购明星增量产品时同步推荐基础套餐的订购。Some independent ancillary services are recommended on the package purchase page of the operator's phone billing plan platform, such as traffic increment package, call duration increment package, etc. These services are usually cheap and flexible to purchase, with high sales volume and high user acceptance. However, most incremental packages rely on different basic packages. When recommending the star incremental products in each package, the order link of the basic package to which the incremental products of the model belong will be attached, and the recommendation will be synchronized when guiding users to order the star incremental products. Subscription of the basic package.
以上所描述的装置实施例仅仅是示意性的，其中作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place , or distributed to multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.
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各实施方式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。基于这样的理解，上述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，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分的方法。From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on this understanding, the above-mentioned technical solutions can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic Disks, optical discs, etc., include instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods of various embodiments or portions of embodiments.
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711368412.0ACN109934654B (en) | 2017-12-18 | 2017-12-18 | Commodity recommendation method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711368412.0ACN109934654B (en) | 2017-12-18 | 2017-12-18 | Commodity recommendation method and system |
| Publication Number | Publication Date |
|---|---|
| CN109934654Atrue CN109934654A (en) | 2019-06-25 |
| CN109934654B CN109934654B (en) | 2021-11-23 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711368412.0AActiveCN109934654B (en) | 2017-12-18 | 2017-12-18 | Commodity recommendation method and system |
| Country | Link |
|---|---|
| CN (1) | CN109934654B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969491A (en)* | 2019-12-17 | 2020-04-07 | 深圳市梦网百科信息技术有限公司 | Commodity pushing method, system and equipment based on network path |
| CN111489234A (en)* | 2020-04-08 | 2020-08-04 | 高邮市新世纪灯具城经营管理有限公司 | Lamp information management method and system |
| CN114025179A (en)* | 2021-09-30 | 2022-02-08 | 北京达佳互联信息技术有限公司 | Virtual article distribution system, method, device, equipment and storage medium |
| CN114638675A (en)* | 2022-05-19 | 2022-06-17 | 深圳市明珞锋科技有限责任公司 | Sale pushing system for classifying commodities according to commodity purchase collocation |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202257679U (en)* | 2011-01-25 | 2012-05-30 | 郭曦 | Intelligent commodity and promotion recommendation system based on cloud analysis |
| KR101596631B1 (en)* | 2015-04-24 | 2016-03-07 | 경희대학교 산학협력단 | Method for recommanding product using big data |
| CN106485562A (en)* | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202257679U (en)* | 2011-01-25 | 2012-05-30 | 郭曦 | Intelligent commodity and promotion recommendation system based on cloud analysis |
| KR101596631B1 (en)* | 2015-04-24 | 2016-03-07 | 경희대학교 산학협력단 | Method for recommanding product using big data |
| CN106485562A (en)* | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| Title |
|---|
| 百度在线网络技术（北京）有限公司: "QQ空间设置仅自己可见后，如何查看被挡访客？", 《百度》* |
| 顾聘聘: "基于商品类目结构的自适应推荐系统", 《中国优秀硕士学位论文全书数据库（电子期刊） 经济与管理科学辑》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969491A (en)* | 2019-12-17 | 2020-04-07 | 深圳市梦网百科信息技术有限公司 | Commodity pushing method, system and equipment based on network path |
| CN110969491B (en)* | 2019-12-17 | 2023-08-29 | 深圳市梦网视讯有限公司 | Commodity pushing method, system and equipment based on network path |
| CN111489234A (en)* | 2020-04-08 | 2020-08-04 | 高邮市新世纪灯具城经营管理有限公司 | Lamp information management method and system |
| CN114025179A (en)* | 2021-09-30 | 2022-02-08 | 北京达佳互联信息技术有限公司 | Virtual article distribution system, method, device, equipment and storage medium |
| CN114638675A (en)* | 2022-05-19 | 2022-06-17 | 深圳市明珞锋科技有限责任公司 | Sale pushing system for classifying commodities according to commodity purchase collocation |
| Publication number | Publication date |
|---|---|
| CN109934654B (en) | 2021-11-23 |
| Publication | Publication Date | Title |
|---|---|---|
| Kooti et al. | Portrait of an online shopper: Understanding and predicting consumer behavior | |
| US20090106081A1 (en) | Internet advertising using product conversion data | |
| US20130006853A1 (en) | Enterprise system, method and computer program product for aggregating and pro rating expenses across members of a networked virtual collective | |
| CN109934654B (en) | Commodity recommendation method and system | |
| TWI652639B (en) | Recommended system and method of product promotion combination | |
| CN107665448A (en) | Method, device and storage medium for determining consumption contribution value | |
| CN107301592A (en) | The method and device excavated for commodity substitute | |
| CN103971256A (en) | A method and device for pushing information | |
| CN113516496B (en) | Advertisement conversion rate estimation model construction method, device, equipment and medium thereof | |
| US12073440B2 (en) | Advertising model | |
| CN110084643A (en) | A kind of merchandise valuation method and device based on historical trading distribution | |
| WO2017151793A1 (en) | Business to consumer enterprise software system | |
| CN110866698A (en) | Device for assessing service score of service provider | |
| CN112053190A (en) | Stall data management method and device, storage medium and equipment | |
| CN110796520A (en) | Commodity recommendation method and device, computing equipment and medium | |
| CN112037041A (en) | Product recommendation method, device and equipment based on bank outlet number calling machine | |
| US20130254019A1 (en) | User level incremental revenue and conversion prediction for internet marketing display advertising | |
| CN113298550A (en) | Commodity price adjusting method and device and server | |
| CN114648369B (en) | Electronic commerce data processing method and system | |
| CN108510302A (en) | A kind of marketing decision-making method and trading server | |
| CN107481088B (en) | Information display method and device | |
| Ivanova et al. | Black Friday Tool for Sales Promotion | |
| CN107239988A (en) | System is presented in commodity data | |
| Qi et al. | A Conceptual Model to Determining the Antecedents of Mobile Payment Loyalty: A Cognitive and Affective Perspective. | |
| CN111400622A (en) | Method and device for showing quantity of short-lived commodities in distributed e-commerce system |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |