技术领域technical field
本发明涉及计算机网络技术领域，特别是涉及一种网页展示方法和系统。The invention relates to the technical field of computer networks, in particular to a web page display method and system.
背景技术Background technique
目前，消费网站中网页展示方式一般为竖向排列，从网页第一个档期浏览到最后一个档期需要进行多次翻页，用户是没有耐心逐渐翻到最后一个档期的，导致用户可能错过其感兴趣的档期，因此，现在有两种方法对网页档期进行排序。At present, webpages in consumer websites are generally displayed in a vertical arrangement, and multiple page flips are required to browse from the first period to the last period of the webpage. Users are impatient to gradually turn to the last period, causing users to miss their experience. Interested schedules, so there are now two ways to sort page schedules.
第一种是人工排序，主要有排序人员根据经验和对网站历史销售数据的研究，人工地进行档期顺序的制定，在这种模式下所有用户看到的排序结果都是一样的。人工排序方法过分依赖人的经验知识，排序人员的喜好对于整体排序结果影响太大.所有人看到的排序结果都是一样的，并无个性化因素.The first is manual sorting, where the sorting personnel manually formulate the order of schedules based on experience and research on historical sales data of the website. In this mode, the sorting results seen by all users are the same. The artificial sorting method relies too much on human experience and knowledge, and the preferences of the sorting personnel have too much influence on the overall sorting results. The sorting results seen by everyone are the same, and there is no personalization factor.
第二种是用户分群，根据用户在网站上的历史行为，归纳总结出其喜好的档期，将用户分出若干个大的类别，然后给不同类别的用户群配置不同的网页排序结果，在这种模式下，同一用户群中的用户看到的排序结果是一样的。用户群分方法针对每一个用户群的排序结果依然是人工确定，无法规避负责人工排序负责人工排序的人员对最终结果影响，只能做到某一类型的人看到的结果是一样的，并不是完全的个性化。The second is user grouping. According to the user's historical behavior on the website, it summarizes its favorite schedule, divides users into several large categories, and then configures different webpage sorting results for different categories of user groups. In this In this mode, users in the same user group see the same sorting results. The user group classification method still manually determines the ranking results for each user group, and cannot avoid the influence of the personnel in charge of manual sorting on the final results. It can only ensure that the results seen by a certain type of people are the same, and Not completely personal.
发明内容Contents of the invention
基于此，有必要针对上述网页展示不够个性化的问题，提供一种网页展示方法和系统。Based on this, it is necessary to provide a method and system for displaying a webpage to solve the above-mentioned problem that the display of the webpage is not personalized enough.
一种网页展示方法，包括以下步骤：A method for displaying a webpage, comprising the following steps:
获取网页的各第一对象的第一特征数据、各第二对象的第二特征数据和各第二对象在各第一对象中的各历史行为数据；Obtain the first characteristic data of each first object of the webpage, the second characteristic data of each second object, and each historical behavior data of each second object in each first object;
根据预设的各历史行为数据与数值的关联关系，分别获取各第二对象在各第一对象中的历史行为和值，其中，历史行为和值为对应的第二对象在对应的第一对象中的各历史行为数据所关联的数值的总和；According to the preset association relationship between each historical behavior data and value, respectively obtain the historical behavior and value of each second object in each first object, wherein the historical behavior and value of the corresponding second object in the corresponding first object The sum of the values associated with each historical behavior data in ;
对于任意一个第一对象和任意一个第二对象，根据对应的第一特征数据和对应的第二特征数据构建组合特征数据，为对应的第一特征数据分配第一权重值，为组合特征数据分配第二权重值，其中，对于该第一对象和该第二对象，第二权重值与第一权重值之和在各第一对象中的排序，与该第二对象在各第一对象中的历史行为和值的排序一致；For any first object and any second object, construct combined feature data according to the corresponding first feature data and corresponding second feature data, assign a first weight value to the corresponding first feature data, and assign a weight value to the combined feature data The second weight value, wherein, for the first object and the second object, the order of the sum of the second weight value and the first weight value in each first object is related to the order of the second object in each first object The ordering of historical behavior and values is consistent;
针对目标第二对象，根据所分配的第一权重值与第二权重值的和值对各第一对象进行展示。For the target second object, each first object is displayed according to the sum of the assigned first weight value and the second weight value.
一种网页展示系统，包括以下单元：A webpage display system, comprising the following units:
特征获取单元，用于获取网页的各第一对象的第一特征数据、各第二对象的第二特征数据和各第二对象在各第一对象中的各历史行为数据；A feature acquisition unit, configured to acquire first feature data of each first object of the webpage, second feature data of each second object, and each historical behavior data of each second object in each first object;
第一获取单元，用于根据预设的各历史行为数据与数值的关联关系，分别获取各第二对象在各第一对象中的历史行为和值，其中，历史行为和值为对应的第二对象在对应的第一对象中的各历史行为数据所关联的数值的总和；The first acquiring unit is used to respectively acquire the historical behavior and value of each second object in each first object according to the preset association relationship between each historical behavior data and value, wherein the historical behavior and value are the corresponding second The sum of the values associated with the historical behavior data of the object in the corresponding first object;
分配单元，用于对于任意一个第一对象和任意一个第二对象，根据对应的第一特征数据和对应的第二特征数据构建组合特征数据，为对应的第一特征数据分配第一权重值，为组合特征数据分配第二权重值，其中，对于该第一对象和该第二对象，第二权重值与第一权重值之和在各第一对象中的排序，与该第二对象在各第一对象中的历史行为和值的排序一致；An allocating unit, for any first object and any second object, constructing combined feature data according to the corresponding first feature data and the corresponding second feature data, and assigning a first weight value to the corresponding first feature data, Assigning a second weight value to the combined feature data, wherein, for the first object and the second object, the order of the sum of the second weight value and the first weight value in each first object is related to the order of the second object in each The historical behavior in the first object is consistent with the ordering of values;
展示单元，用于针对目标第二对象，根据所分配的第一权重值与第二权重值的和值对各第一对象进行展示。The display unit is configured to display each first object according to the assigned sum of the first weight value and the second weight value for the target second object.
根据上述本发明的方案，其是根据第一对象的第一特征数据、第二对象的第二特征数据和第二对象在第一对象中的历史行为数据，获取第一对象的第一特征数据的第一权重值，以及第一对象的第一特征数据与第二对象的第二特征数据的组合特征数据的第二权重值；针对目标第二对象，根据第一权重值和第二权重值的和值对各第一对象进行展示。通过上述方案可以针对每个第二对象，对各第一对象进行不同的展示，实现网页的个性化展示。According to the above-mentioned solution of the present invention, the first characteristic data of the first object is obtained according to the first characteristic data of the first object, the second characteristic data of the second object and the historical behavior data of the second object in the first object The first weight value of , and the second weight value of the combined feature data of the first feature data of the first object and the second feature data of the second object; for the target second object, according to the first weight value and the second weight value The sum value of is displayed for each first object. Through the above solution, each first object can be displayed differently for each second object, so as to realize the personalized display of the webpage.
附图说明Description of drawings
图1为其中一个实施例的网页展示方法的流程示意图；FIG. 1 is a schematic flow chart of a method for displaying a webpage in one embodiment;
图2为其中一个实施例的网页展示系统的结构示意图；FIG. 2 is a schematic structural diagram of a webpage display system of one embodiment;
图3为其中一个实施例的网页展示系统的部分结构示意图。Fig. 3 is a partial structural diagram of a webpage display system of one embodiment.
具体实施方式Detailed ways
为使本发明的目的、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的详细说明。应当理解，此处所描述的具体实施方式仅仅用以解释本发明，并不限定本发明的保护范围。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 the specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.
参见图1所示，为本发明的网页展示方法的一个实施例。该实施例中的网页展示方法，包括以下步骤：Referring to FIG. 1 , it is an embodiment of the webpage display method of the present invention. The web page display method in this embodiment includes the following steps:
步骤S101：获取网页的各第一对象的第一特征数据、各第二对象的第二特征数据和各第二对象在各第一对象中的各历史行为数据；Step S101: Obtain the first characteristic data of each first object of the webpage, the second characteristic data of each second object, and each historical behavior data of each second object in each first object;
步骤S102：根据预设的各历史行为数据与数值的关联关系，分别获取各第二对象在各第一对象中的历史行为和值，其中，历史行为和值为对应的第二对象在对应的第一对象中的各历史行为数据所关联的数值的总和；Step S102: Acquire the historical behavior and value of each second object in each first object according to the preset association relationship between each historical behavior data and value, wherein the historical behavior and value of the corresponding second object in the corresponding The sum of the numerical values associated with each historical behavior data in the first object;
步骤S103：对于任意一个第一对象和任意一个第二对象，根据对应的第一特征数据和对应的第二特征数据构建组合特征数据，为对应的第一特征数据分配第一权重值，为组合特征数据分配第二权重值，其中，对于该第一对象和该第二对象，第二权重值与第一权重值之和在各第一对象中的排序，与该第二对象在各第一对象中的历史行为和值的排序一致；Step S103: For any first object and any second object, construct combined feature data according to the corresponding first feature data and corresponding second feature data, assign a first weight value to the corresponding first feature data, and create a combination The feature data assigns a second weight value, wherein, for the first object and the second object, the order of the sum of the second weight value and the first weight value in each first object is related to the ranking of the second object in each first object. The historical behavior in the object is consistent with the ordering of the values;
步骤S104：针对目标第二对象，根据所分配的第一权重值与第二权重值的和值对各第一对象进行展示。Step S104: For the target second object, display each first object according to the sum of the assigned first weight value and the second weight value.
上述步骤S101、步骤S102、步骤S103为网页展示方法的离线训练部分，步骤S104为网页展示方法的线上应用部分。The above step S101, step S102, and step S103 are the offline training part of the webpage presentation method, and step S104 is the online application part of the webpage presentation method.
根据本实施例的方案，其是根据第一对象的第一特征数据、第二对象的第二特征数据和第二对象在第一对象中的历史行为数据，获取第一对象的第一特征数据的第一权重值，以及第一对象的第一特征数据与第二对象的第二特征数据的组合特征数据的第二权重值；针对目标第二对象，根据第一权重值和第二权重值的和值对各第一对象进行展示。通过上述方案可以针对每个第二对象，对各第一对象进行不同的展示，实现网页的个性化展示。According to the solution of this embodiment, it is to obtain the first characteristic data of the first object according to the first characteristic data of the first object, the second characteristic data of the second object and the historical behavior data of the second object in the first object The first weight value of , and the second weight value of the combined feature data of the first feature data of the first object and the second feature data of the second object; for the target second object, according to the first weight value and the second weight value The sum value of is displayed for each first object. Through the above solution, each first object can be displayed differently for each second object, so as to realize the personalized display of the webpage.
优选的，第一对象为网页的档期，第二对象为网页的帐户；在步骤S102中，帐户在每个档期中的历史行为包括对该档期的浏览、加入购物车、收藏、购买等，这些历史行为预设的数值大小关系为：浏览的数值小于加入购物车的数值，加入购物车的数值小于收藏的数值，收藏的数值小于购买的数值。至于历史行为具体的数值可以由技术人员自由设定，只要数值大小符合上述比较原则即可。Preferably, the first object is the schedule of the webpage, and the second object is the account of the webpage; in step S102, the historical behavior of the account in each schedule includes browsing, adding to the shopping cart, bookmarking, purchasing, etc. of the schedule, these The preset numerical value relationship of history behavior is: the browsed value is less than the value added to the shopping cart, the value added to the shopping cart is less than the value of the favorite, and the value of the favorite is smaller than the value purchased. As for the specific value of historical behavior, it can be freely set by technicians, as long as the value meets the above comparison principles.
具体的，购买的数值可以为100000分，收藏的数值可以为1000分，加入购物车的数值可以为10分，浏览的数值可以为1分，每个档期中各种历史行为的数值的总和就是上述数值的总和，比如一个帐户打开了一个档期，将3个商品加入购物车，收藏了2个商品，购买了1个商品，那么该帐户在该档期中的历史行为的数据的总和就是100000*1+1000*2+10*3+1＝102031。Specifically, the value of purchase can be 100,000 points, the value of collection can be 1000 points, the value of adding to the shopping cart can be 10 points, and the value of browsing can be 1 point. The sum of the values of various historical behaviors in each schedule is The sum of the above values, for example, if an account opens a schedule, adds 3 items to the shopping cart, collects 2 items, and purchases 1 item, then the sum of the historical behavior data of the account in this schedule is 100000* 1+1000*2+10*3+1=102031.
优选的，在步骤S103中，对于任意一个档期和任意一个帐户，根据对应的第一特征数据和对应的第二特征数据构建组合特征数据，为对应的第一特征数据分配第一权重值，为组合特征数据分配第二权重值，其中，对于该第一对象和该第二对象，第二权重值与第一权重值之和在各第一对象中的排序，与该第二对象在各第一对象中的历史行为和值的排序一致；Preferably, in step S103, for any schedule and any account, construct combined feature data according to the corresponding first feature data and corresponding second feature data, and assign a first weight value to the corresponding first feature data, as The combined feature data assigns a second weight value, wherein, for the first object and the second object, the order of the sum of the second weight value and the first weight value in each first object is related to the ranking of the second object in each second object. The ordering of historical behavior and values in an object is consistent;
具体的，如某一账户在某一档期中的历史行为和值为102031，若该帐户的该和值102031在各个档期历史行为和值中的排序为第三，该档期中的第一特征数据的第一权重值为0.1，该帐户和该档期的组合特征数据的第二权重值为0.2，则第二权重值与第一权重值之和为0.3，该和值0.3在各个档期中的排序也为第三，即帐户在每个档期中的权重和值在各个档期中的排序应该与帐户在每个档期的历史行为和值在各个档期中的排序一致，也就是说，权重值的具体数值的分配是以历史行为数据和值为依据。Specifically, for example, if the historical behavior and value of an account in a certain period is 102031, if the order of the sum of 102031 of the account is the third in the historical behavior and value of each period, the first feature data in the period The first weight value of 0.1, the second weight value of the combined characteristic data of the account and the schedule is 0.2, then the sum of the second weight value and the first weight value is 0.3, and the order of the sum value 0.3 in each schedule Also for the third, that is, the order of the weight and value of the account in each period should be consistent with the historical behavior of the account in each period and the order of the value in each period, that is, the specific weight value Values are assigned based on historical behavioral data and values.
在其中一个实施例中，离线训练时，对于任意一个第二对象，各第一对象为有该第二对象历史行为的第一对象和没有该第二对象历史行为的部分第一对象，而不是所有的第一对象；因为第二对象的数量很多，所以对所有第二对象来说，相应的各第一对象可以覆盖所有的第一对象；线上应用时，对于任意一个第二对象，是对所有的第一对象进行排序并展示。In one of the embodiments, during offline training, for any second object, each first object is a first object with the historical behavior of the second object and a part of the first object without the historical behavior of the second object, instead of All the first objects; because there are many second objects, for all the second objects, the corresponding first objects can cover all the first objects; when applied online, for any second object, is Sort and display all first objects.
在其中一个实施例中，针对目标第二对象，根据所分配的第一权重值与第二权重值的和值对各第一对象进行展示的步骤包括以下步骤：In one embodiment, for the target second object, the step of displaying each first object according to the sum of the assigned first weight value and the second weight value includes the following steps:
根据目标第二对象的第二特征数据和各第一对象的第一特征数据，分别获取与目标第二对象对应的各组合特征数据的第二权重值，以及各第一对象的第一特征数据的第一权重值；According to the second characteristic data of the target second object and the first characteristic data of each first object, respectively acquire the second weight value of each combined characteristic data corresponding to the target second object, and the first characteristic data of each first object The first weight value of ;
对于任意一个第一对象，根据获取的该第一对象的第一特征数据的第一权重值与对应该第一对象和目标第二对象的组合特征的第二权重值之和，确定针对目标第二对象的该第一对象的权重值；For any first object, according to the sum of the first weight value of the acquired first feature data of the first object and the second weight value corresponding to the combined features of the first object and the target second object, determine the the weight value of the first object of the second object;
根据针对目标第二对象的各第一对象的权重值，对各第一对象进行排序，并按照排序结果在网页上为目标第二对象展示各第一对象。According to the weight value of each first object for the target second object, sort each first object, and display each first object for the target second object on the webpage according to the sorting result.
优选的，第一对象为网页的档期，第二对象为网页的帐户；当目标账户登录网页时，根据目标帐户的第二特征数据和各档期的第一特征数据，分别获取与目标帐户对应的各组合特征数据的第二权重值，以及各第一对象的第一特征数据的第一权重值；Preferably, the first object is the schedule of the webpage, and the second object is the account of the webpage; when the target account logs in to the webpage, according to the second feature data of the target account and the first feature data of each schedule, respectively obtain the information corresponding to the target account the second weight value of each combined characteristic data, and the first weight value of each first characteristic data of the first object;
对于任意一个档期，根据获取的该档期的第一特征数据的第一权重值与对应该档期和目标帐户的组合特征的第二权重值之和，确定针对目标帐户的该档期的权重值；For any one schedule, determine the weight value of the schedule for the target account according to the sum of the acquired first weight value of the first characteristic data of the schedule and the second weight value corresponding to the combined features of the schedule and the target account;
根据针对目标帐户的各档期的权重值，对各档期进行排序，并按照排序结果在网页上为目标帐户展示各档期。Sort each schedule according to the weight value of each schedule for the target account, and display each schedule for the target account on the webpage according to the sorting result.
排序是根据各档期的权重值从大到小的顺序对档期的先后顺序进行排列。Sorting is to arrange the sequence of the schedules according to the order of the weight value of each schedule from large to small.
根据帐户的第二特征数据、档期的第一特征数据，获得相应的第一权重值和第二权重值，以两者之和获得档期的权重值，再根据档期的权重值的大小对网页档期进行排序并展示。档期的权重值越大，说明帐户与之的关联度越高，相应的用户对其越感兴趣，通过上述方案可以针对访问网页的每一个帐户，将帐户对应的用户可能感兴趣的档期排在网页的最前面，因为每个用户对应的帐户的第二特征数据不同，所以每个用户看到的网页展示都是不同的，可以为每个用户设置最符合用户喜好的网页展示，从而实现网页展示针对用户的个性化排序。此外，帐户在网页档期上的历史行为数据改变以后，可以重新对网页档期进行排序，保证排序可以自动并实时地调整，将当前最佳的排序结果呈现给用户，提升用户体验，同时让网站的收益最大化。According to the second characteristic data of the account and the first characteristic data of the schedule, the corresponding first weight value and the second weight value are obtained, and the weight value of the schedule is obtained by the sum of the two, and then the web page schedule is calculated according to the weight value of the schedule Sort and display. The greater the weight value of the schedule, the higher the degree of association between the account and it, and the more interested the corresponding user is in it. Through the above scheme, for each account that visits the web page, the schedule that the user corresponding to the account may be interested in can be ranked in the At the front of the webpage, because the second characteristic data of the account corresponding to each user is different, the webpage displayed by each user is different. You can set the webpage display that best meets the user's preferences for each user, so as to realize the webpage Display personalized sorting for users. In addition, after the account's historical behavior data on the webpage schedule is changed, the webpage schedule can be re-sorted to ensure that the ranking can be adjusted automatically and in real time, presenting the current best sorting results to users, improving user experience, and at the same time making the website Maximize returns.
在其中一个实施例中，第一对象为网页的档期，第一特征数据包括档期的服务对象性别数据、品牌数据、类目数据、风格数据、价格数据、频道数据、等级数据和上线天数数据；第二对象为网页的帐户，第二特征数据包括帐户的服务对象性别数据、服务对象年龄数据、偏爱类目数据和偏爱品牌数据。In one of the embodiments, the first object is the schedule of the webpage, and the first feature data includes gender data, brand data, category data, style data, price data, channel data, grade data and online days data of the service object of the schedule; The second object is an account of a webpage, and the second characteristic data includes data of gender of the client, age of the client, preferred category data, and preferred brand of the account.
具体的，档期的服务对象性别是指该档期的产品的服务对象性别，如男装、女装等；风格可以是现代、古典等；帐户的服务对象性别是指该帐户对应的用户的性别。Specifically, the gender of the service object of the schedule refers to the gender of the service object of the product of the schedule, such as men's clothing, women's clothing, etc.; the style can be modern, classical, etc.; the gender of the service object of the account refers to the gender of the user corresponding to the account.
在其中一个实施例中，为对应的第一特征数据分配第一权重值，是指为对应的第一特征数据中的单个特征数据分别分配第一权重值；为组合特征数据分配第二权重值，是指为对应的第一特征数据中的单个特征数据和第二特征数据中的单个特征数据的组合特征分别分配第二权重值。In one of the embodiments, assigning a first weight value to the corresponding first feature data refers to assigning a first weight value to a single feature data in the corresponding first feature data; assigning a second weight value to the combined feature data , means assigning a second weight value to the combined features of the corresponding single feature data in the first feature data and the single feature data in the second feature data.
具体的，比如档期的第一特征数据为brand_Nike，cat_男装，帐户的第二特征数据为sex_男，style_现代，则档期的第一特征数据与帐户的第二特征数据的组合特征数据为brand_Nike&sex_男，brand_Nike&style_现代，cat_男装&sex_男，cat_男装&style_现代。Specifically, for example, the first characteristic data of the schedule is brand_Nike, cat_men's clothing, and the second characteristic data of the account is sex_male, style_modern, then the combined characteristic data of the first characteristic data of the schedule and the second characteristic data of the account For brand_Nike&sex_men, brand_Nike&style_modern, cat_mens&sex_men, cat_mens&style_modern.
在其中一个实施例中，使用排序支持向量机来构建各第一特征数据和各第二特征数据的各组合特征数据，为各第一特征数据分别分配第一权重值，为各组合特征数据分别分配第二权重值。In one of the embodiments, a sorting support vector machine is used to construct each combined feature data of each first feature data and each second feature data, respectively assign a first weight value to each first feature data, and assign a first weight value to each combined feature data respectively Assign a second weight value.
具体的，使用排序支持向量机(RankSVM)，为档期的第一特征数据分别分配第一权重值，为档期和帐户的组合特征数据分别分配第二权重值，以上一实施例中档期的第一特征数据和帐户的第二特征数据为例，具体数值可以为：Specifically, using a sorting support vector machine (RankSVM), assign first weight values to the first feature data of the schedule, and assign second weight values to the combined feature data of the schedule and account respectively. The first weight value of the schedule in the above embodiment Take the characteristic data and the second characteristic data of the account as an example, the specific values can be:
brand_Nike：0.0063863；brand_Nike: 0.0063863;
cat_男装：0.00465421；cat_mens: 0.00465421;
brand_Nike&sex_男：0.00157771；brand_Nike&sex_male: 0.00157771;
brand_Nike&style_现代：0.0121149；brand_Nike&style_modern: 0.0121149;
cat_男装&sex_男：0.000801377；cat_men&sex_male: 0.000801377;
cat_男装&style_现代：0.00385786。cat_menswear & style_modern: 0.00385786.
将上述第一特征数据的权重值以及第二特征数据的权重值相加，就可以得到该档期的权重值，上述权重值相加后的具体数值为0.007311337。依照此方法可以获得对应帐户的各个档期的权重值。The weight value of the schedule can be obtained by adding the weight value of the first characteristic data and the weight value of the second characteristic data, and the specific value after adding the above weight values is 0.007311337. According to this method, the weight value of each period of the corresponding account can be obtained.
利用排序支持向量机中的线性核进行求解，可以根据档期中各种所述历史行为的数值的总和获得对应档期的第一特征数据的第一权重值，以及对应档期的第一特征数据与帐户的第二特征数据的组合特征数据的第二权重值。该排序支持向量机需要使用用户对应的帐户的第二特征数据，建立帐户与档期之间的联系，而且帐户的第二特征数据与档期的第一特征数据的具体构成因素可以任意加入和组合，也就是说，任意的因素都可以进行考虑，排序支持向量机会对所有的档期的第一特征数据及档期的第一特征数据与帐户的第二特征数据的组合特征数据给出相应的权重值。Using the linear kernel in the sorting support vector machine to solve, the first weight value of the first characteristic data of the corresponding period can be obtained according to the sum of the values of various historical behaviors in the period, and the first characteristic data of the corresponding period and the account The second weight value of the combined feature data of the second feature data. The sorting support vector machine needs to use the second characteristic data of the account corresponding to the user to establish the connection between the account and the schedule, and the specific constituent factors of the second characteristic data of the account and the first characteristic data of the schedule can be added and combined arbitrarily, That is to say, arbitrary factors can be considered, and the sorting support vector machine gives corresponding weight values to the first characteristic data of all schedules and the combined characteristic data of the first characteristic data of schedules and the second characteristic data of accounts.
根据上述网页展示方法，本发明还提供一种网页展示系统，以下就本发明的网页展示系统的实施例进行详细说明。According to the above webpage display method, the present invention also provides a webpage display system, and the embodiments of the webpage display system of the present invention will be described in detail below.
参见图2所示，为本发明的网页展示系统的一个实施例。该实施例中的网页展示系统，包括以下单元：Referring to FIG. 2 , it is an embodiment of the webpage display system of the present invention. The web page display system in this embodiment includes the following units:
第一获取单元201，用于获取网页的各第一对象的第一特征数据、各第二对象的第二特征数据和各所述第二对象在各所述第一对象中的各历史行为数据；The first acquisition unit 201 is configured to acquire the first feature data of each first object of the webpage, the second feature data of each second object, and each historical behavior data of each second object in each of the first objects ;
第二获取单元202，用于根据预设的各历史行为数据与数值的关联关系，分别获取各所述第二对象在各所述第一对象中的历史行为和值，其中，所述历史行为和值为对应的第二对象在对应的第一对象中的各历史行为数据所关联的数值的总和；The second acquisition unit 202 is configured to respectively acquire the historical behavior and value of each of the second objects in each of the first objects according to the preset association relationship between each historical behavior data and a value, wherein the historical behavior The sum value is the sum of the values associated with the historical behavior data of the corresponding second object in the corresponding first object;
分配单元203，用于对于任意一个第一对象和任意一个第二对象，根据对应的所述第一特征数据和对应的所述第二特征数据构建组合特征数据，为对应的所述第一特征数据分配第一权重值，为所述组合特征数据分配第二权重值，其中，对于该第一对象和该第二对象，所述第二权重值与所述第一权重值之和在各所述第一对象中的排序，与该所述第二对象在各所述第一对象中的历史行为和值的排序一致；The allocation unit 203 is configured to, for any one of the first objects and any one of the second objects, construct combined feature data according to the corresponding first feature data and the corresponding second feature data, for the corresponding first feature assigning a first weight value to the data, and assigning a second weight value to the combined feature data, wherein, for the first object and the second object, the sum of the second weight value and the first weight value is at each The sorting in the first object is consistent with the historical behavior and value sorting of the second object in each of the first objects;
展示单元204，用于针对目标第二对象，根据所分配的第一权值、第二权值对各所述第一对象进行展示。The display unit 204 is configured to display each of the first objects according to the assigned first weight and second weight for the target second object.
在其中一个实施例中，如图3所示，展示单元204包括以下单元：In one of the embodiments, as shown in FIG. 3 , the display unit 204 includes the following units:
第三获取单元205，用于根据目标第二对象的第二特征数据和各第一对象的第一特征数据，分别获取与目标第二对象对应的各组合特征数据的第二权重值，以及各第一对象的第一特征数据的第一权重值；The third obtaining unit 205 is configured to obtain the second weight value of each combination feature data corresponding to the target second object according to the second feature data of the target second object and the first feature data of each first object, and each a first weight value of the first characteristic data of the first object;
确定单元206，用于对于任意一个第一对象，根据获取的该第一对象的第一特征数据的第一权重值与对应该第一对象和目标第二对象的组合特征的第二权重值之和，确定针对目标第二对象的该第一对象的权重值；The determination unit 206 is configured to, for any first object, obtain the first weight value of the first feature data of the first object according to the difference between the second weight value of the combined feature corresponding to the first object and the target second object. and, determining the weight value of the first object for the target second object;
排序单元207，用于根据针对目标第二对象的各第一对象的权重值，对各第一对象进行排序，并按照排序结果在网页上为目标第二对象展示各第一对象。The sorting unit 207 is configured to sort the first objects according to the weight values of the first objects for the target second objects, and display the first objects for the target second objects on the webpage according to the sorting results.
在其中一个实施例中，第一对象为网页的档期，第一特征数据包括档期的服务对象性别数据、品牌数据、类目数据、风格数据、价格数据、频道数据、等级数据和上线天数数据；第二对象为网页的帐户，第二特征数据包括帐户的服务对象性别数据、服务对象年龄数据、偏爱类目数据和偏爱品牌数据。In one of the embodiments, the first object is the schedule of the webpage, and the first feature data includes gender data, brand data, category data, style data, price data, channel data, grade data and online days data of the service object of the schedule; The second object is an account of a webpage, and the second characteristic data includes data of gender of the client, age of the client, preferred category data, and preferred brand of the account.
在其中一个实施例中，分配单元203为对应的第一特征数据分配第一权重值，是指为对应的第一特征数据中的单个特征数据分别分配第一权重值；为组合特征数据分配第二权重值，是指为对应的第一特征数据中的单个特征数据和第二特征数据中的单个特征数据的组合特征分别分配第二权重值。In one of the embodiments, the assigning unit 203 assigns the first weight value to the corresponding first feature data, which refers to assigning the first weight value to the single feature data in the corresponding first feature data; assigning the first weight value to the combined feature data Two weight values refer to assigning a second weight value to the combined features of the corresponding single feature data in the first feature data and the single feature data in the second feature data.
在其中一个实施例中，分配单元203使用排序支持向量机来构建各第一特征数据和各第二特征数据的各组合特征数据，为各第一特征数据分别分配第一权重值，为各组合特征数据分别分配第二权重值。In one of the embodiments, the assigning unit 203 uses sorting support vector machine to construct each combined feature data of each first feature data and each second feature data, respectively assigns a first weight value to each first feature data, and assigns a first weight value to each combination The characteristic data are respectively assigned a second weight value.
本发明的网页展示系统与本发明的网页展示方法一一对应，在上述网页展示方法的实施例阐述的技术特征及其有益效果均适用于网页展示系统的实施例中。The web page display system of the present invention corresponds one-to-one to the web page display method of the present invention, and the technical features and beneficial effects described in the embodiments of the web page display method above are applicable to the embodiments of the web page display system.
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。The various technical features of the above-mentioned embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the various technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, should be considered as within the scope of this specification.
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。The above-mentioned embodiments only express several implementation modes of the present invention, and the descriptions thereof are relatively specific and detailed, but should not be construed as limiting the patent scope of the invention. It should be pointed out that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention should be based on the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510944501.XACN105373628B (en) | 2015-12-15 | 2015-12-15 | web page display method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510944501.XACN105373628B (en) | 2015-12-15 | 2015-12-15 | web page display method and system |
| Publication Number | Publication Date |
|---|---|
| CN105373628A CN105373628A (en) | 2016-03-02 |
| CN105373628Btrue CN105373628B (en) | 2018-11-30 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510944501.XAActiveCN105373628B (en) | 2015-12-15 | 2015-12-15 | web page display method and system |
| Country | Link |
|---|---|
| CN (1) | CN105373628B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111177622A (en)* | 2019-12-23 | 2020-05-19 | 深圳壹账通智能科技有限公司 | Web page rendering method, device and computer equipment based on machine learning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102710773A (en)* | 2012-05-30 | 2012-10-03 | 杭州遥指科技有限公司 | Method and system for recommending network information |
| CN103457944A (en)* | 2013-08-27 | 2013-12-18 | 小米科技有限责任公司 | Method and device for pushing information and server |
| CN103546778A (en)* | 2013-07-17 | 2014-01-29 | Tcl集团股份有限公司 | Television program recommendation method and system, and implementation method of system |
| CN105100164A (en)* | 2014-05-20 | 2015-11-25 | 深圳市腾讯计算机系统有限公司 | Network service recommendation method and device |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6317722B1 (en)* | 1998-09-18 | 2001-11-13 | Amazon.Com, Inc. | Use of electronic shopping carts to generate personal recommendations |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102710773A (en)* | 2012-05-30 | 2012-10-03 | 杭州遥指科技有限公司 | Method and system for recommending network information |
| CN103546778A (en)* | 2013-07-17 | 2014-01-29 | Tcl集团股份有限公司 | Television program recommendation method and system, and implementation method of system |
| CN103457944A (en)* | 2013-08-27 | 2013-12-18 | 小米科技有限责任公司 | Method and device for pushing information and server |
| CN105100164A (en)* | 2014-05-20 | 2015-11-25 | 深圳市腾讯计算机系统有限公司 | Network service recommendation method and device |
| Publication number | Publication date |
|---|---|
| CN105373628A (en) | 2016-03-02 |
| Publication | Publication Date | Title |
|---|---|---|
| Hooi et al. | Intention to use online food delivery service in Malaysia among university students | |
| US20210241321A1 (en) | Method and system for requesting and transmitting marketing images or video | |
| US20140032359A1 (en) | System and method for providing intelligent recommendations | |
| US20140279197A1 (en) | Enhancing revenue of a retailer by making a recommendation to a customer | |
| US9785654B2 (en) | Method of e-commerce | |
| US20130268395A1 (en) | Automated product selection and distribution system | |
| CN107004203A (en) | Information processing system and method | |
| JP6635587B2 (en) | Advertising sentence selection device and program | |
| CN113744016A (en) | Object recommendation method and device, equipment and storage medium | |
| TW201539346A (en) | Customizing evaluation information presentation | |
| WO2017092602A1 (en) | Method for screening information delivery user and server | |
| CN113689259A (en) | A method and system for personalized product recommendation based on user behavior | |
| CA3138745A1 (en) | Method and device for circling and creating target population | |
| JP2016053784A (en) | Information recommendation program and information processing apparatus | |
| JP2024103482A (en) | Information processing device, information processing method, and program | |
| JP6916095B2 (en) | Server and product provision system | |
| JP6679706B1 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN105373628B (en) | web page display method and system | |
| JP6664604B1 (en) | Information processing apparatus, information processing method, and information processing program | |
| JP2017102948A (en) | Information processing apparatus, information processing method, and information processing program | |
| US20150006527A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| Baldominos et al. | An efficient and scalable recommender system for the smart web | |
| KR101657555B1 (en) | Method for generating a visiting intent information and method for recommending goods or contents using the same | |
| JP2019164755A (en) | Information processing device, information processing method, and information processing program | |
| JP6679707B1 (en) | Information processing apparatus, information processing method, and information processing program |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right | Effective date of registration:20160315 Address after:510370 Guangdong, Guangzhou, Fangcun, No., No. 20 Huahai street, building 1-5 Applicant after:Guangzhou Pinwei Software Co., Ltd. Address before:510370 Guangdong, Guangzhou, Fangcun, No., No. 20 Huahai street, building 1-5 Applicant before:Guangzhou VIPSHOP Information and Technology Co., Ltd. | |
| GR01 | Patent grant | ||
| GR01 | Patent grant |