WO2016116018A1 - 一种信息发布方法及装置 - Google Patents

一种信息发布方法及装置 Download PDF

Info

Publication number
WO2016116018A1
WO2016116018A1 PCT/CN2016/071163 CN2016071163W WO2016116018A1 WO 2016116018 A1 WO2016116018 A1 WO 2016116018A1 CN 2016071163 W CN2016071163 W CN 2016071163W WO 2016116018 A1 WO2016116018 A1 WO 2016116018A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
data object
data objects
combined image
information
Prior art date
Application number
PCT/CN2016/071163
Other languages
English (en)
French (fr)
Inventor
陈霄
张萌
Original Assignee
阿里巴巴集团控股有限公司
陈霄
张萌
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿里巴巴集团控股有限公司, 陈霄, 张萌 filed Critical 阿里巴巴集团控股有限公司
Priority to JP2017538700A priority Critical patent/JP2018509684A/ja
Publication of WO2016116018A1 publication Critical patent/WO2016116018A1/zh
Priority to US15/653,425 priority patent/US20170316034A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0603—Catalogue ordering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0621—Item configuration or customization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0623—Item investigation
    • G06Q30/0625—Directed, with specific intent or strategy
    • G06Q30/0627—Directed, with specific intent or strategy using item specifications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to an information publishing method and apparatus.
  • the server sends an image of a single data object to be published to the client and displays it on the front page.
  • the post-release page displayed to the user is only the information of a single data object published by the merchant, and the information displayed after being released by using the publishing method is relatively simple and the display effect is not good.
  • the embodiment of the present application provides a method and an apparatus for distributing information to solve the technical problem that the information displayed by the single data object after the information is released in the prior art leads to poor display performance.
  • An embodiment of the present application provides a method for publishing information, including the following steps:
  • the combined image is sent to the user.
  • An embodiment of the present application provides an information distribution apparatus, including:
  • a receiving module configured to receive input information of the user
  • a data object search module configured to extract one or more keywords from the user input information; Searching for one or more keywords to obtain at least two data objects, each data object comprising at least one picture;
  • a generating module configured to respectively extract at least part of an image from a picture of at least two data objects; and generate a combined image according to the extracted at least part of the image;
  • a sending module configured to send the combined image to the user.
  • the user input information is first received and one or more keywords are extracted, and at least two data objects are obtained according to one or more keyword searches, and each data object includes at least one image, respectively, from at least one At least part of the image is extracted from the image of the two data objects, and a combined image is generated according to at least part of the extracted image, and finally the combined image is sent to the user, so that when the information is published, the information to be published is no longer the information of the single data object. It is a combination of information of a plurality of data objects, and provides the user with an image in which a plurality of data objects are combined, and the display effect after the release of the information distribution method is better.
  • FIG. 1 is a schematic flowchart diagram of an implementation of an information distribution method in an embodiment of the present application
  • FIG. 2 is a schematic diagram of the information before and after the information is released in the embodiment of the present application
  • FIG. 3 is a schematic structural diagram of an information distribution apparatus in an embodiment of the present application.
  • the embodiment of the present application provides an information publishing method and apparatus, The description will be given.
  • FIG. 1 is a schematic flowchart of the implementation of the information publishing method in the embodiment of the present application. As shown in the figure, the information publishing method may include the following steps:
  • Step 101 Receive input information of a user.
  • Step 102 Extract one or more keywords from user input information
  • Step 103 Search for at least two data objects according to one or more keywords, each data object includes at least one picture;
  • Step 104 Extract at least part of the image from the pictures of the at least two data objects respectively.
  • Step 105 Generate a component image according to at least part of the extracted image
  • Step 106 Send the combined image to the user.
  • the keywords may be style keywords such as "Korean version” and "Japanese”, or keywords such as "European furniture”. Searching for at least two data objects according to one or more keywords, specifically determining at least two items according to style keywords such as "Korean version” and "Japanese”, such as two Korean clothes, or a Korean version of clothes and a string Korean version of the necklace and so on. These items contain at least one item display image, which can be a front picture, a back picture, and the like.
  • Extracting one or more keywords from user input information may use existing keyword extraction techniques. Searching for at least two data objects based on one or more keywords may be based on these keywords as input sets to establish a weight model for semantics. The search results in at least two data objects, and the specific implementation may adopt the prior art.
  • the specific method of keyword extraction and the manner of searching for data objects according to keywords are not limited.
  • At least part of the image is extracted from the images of the at least two data objects, and the main image in the image of the data object may be extracted by using a mapping algorithm such as Bayesian, and then the image feature values are extracted, such as Colors, textures, shapes, etc., analyze and establish high-order indexes and other operations.
  • the extracted image may be subjected to image processing such as deepening and coloring.
  • the specific image processing techniques may be performed by using existing image processing techniques, and are not described herein.
  • the combined image may also include other information such as the picture path of the picture of each data object.
  • one or more keywords may be extracted according to the user input information, and at least two data objects are searched according to the keywords, and each data is obtained.
  • the object includes at least one picture, and at least part of the image is extracted from the picture, and the partial image generation combined image is sent to the user, and the user is provided with a combined image of the picture containing the plurality of data objects, so that the published information is not only a single data object.
  • Information but a combination of information from multiple data objects.
  • the combined image may also include link information for each data object.
  • the link information of each data object may be a specific page unicast resource locator (URL) address of each item, such as a detail page URL address of the windbreaker.
  • URL page unicast resource locator
  • the link information of each data object can be located to the position of the partial image of the data object in the combined image, and the link information of the data object can be automatically accessed when the user clicks on the partial image of the data object.
  • the detail page URL address of the windbreaker may be the same as the position of the windbreaker image so that the user can automatically link to the detail page of the windbreaker when clicking on the windbreaker image.
  • the foregoing positioning can be implemented by using the map and area attributes of the img tag in the prior art, and the specific implementation manner can be as follows:
  • the above code is an implementation of the URL address locating by using the map and area attributes in the img tag. Those skilled in the art may also use other methods to implement the positioning. This application does not limit this.
  • the combined image of the link information including each data object may be directly sent to the user without performing the above operations such as positioning, so that the user may be linked to the data object.
  • the effect of the information and the partial image of the data object is displayed separately, such as displaying the link information of the windbreaker and the link information of the scarf under the image of the windbreaker and the scarf.
  • the display effect of the combined image is not as good as that of the positioning, the two methods can be used in specific use, and those skilled in the art can select according to actual needs.
  • the embodiment of the present application further includes the link information of each data object in the combined image, so that when the user sees the combined image, the link information of the data object can be further accessed, which is convenient and quick, and further improves the user experience.
  • the embodiment of the present application can also be implemented as follows.
  • data objects can be searched for under different categories.
  • the search can be performed under different categories such as clothing, accessories, shoes, bags, etc., and at least two items such as Korean clothing, accessories, shoes or bags are obtained, so that the generated combined image includes multiple classes. Items under the head, not items of the same category.
  • the embodiment of the present application searches for at least two data objects in different categories according to keywords, and finally combines partial images of data objects in different categories, so that the combined images are closer to the user's matching requirements, and provide different users.
  • the combined image of the data objects under the category further enhances the display effect brought by the combined image.
  • the information publishing method may further include: determining an identifier of each data object;
  • the combined image may also include an identification of each data object.
  • the identifier of each data object may be a keyword generated according to an existing algorithm or a certain rule, for example, taking the item "Dior True My Series of Perfume” as an example, the identifier of the item may be "Dior perfume” or “true” Keywords such as "My series", this application does not limit the identification of each data object and the specific generation method of the logo.
  • the identifier of each of the data objects may be marked to the part of each data object. The position of the sub-image in the combined image.
  • the position of each data object is marked to the position of the partial image of each data object in the combined image is not limited to the same as the coordinate position of the data object and the image of the data object.
  • the image portion of the occluded item is identified, and the identification of the item may also be marked to the upper left or lower right corner of the image of the item.
  • the upper left corner of the cup image in the combined image is marked with a "sticker" or the like for identifying and interpreting the cup, so that the user can view and understand the meaning represented by the cup image.
  • the identifier of each data object may be marked as a page element by using an absolute positioning method of a cascading style sheet (CSS, Cascading Style Sheets), and may be marked to a corresponding position of a partial image of each data object, or may be otherwise To mark, this application does not limit the specific marking method.
  • CSS cascading style sheet
  • the identifier of each data object may be further determined, and the identifier is included in the generated combined image so as to be used for each data.
  • the object is identified, interpreted, and the like, so that the user can understand the data object from the logo or the like in addition to the combined image.
  • the generating a combined image according to the extracted at least part of the image may specifically include:
  • a partial image of each data object is combined in different sizes and/or positions to produce a combined image of a specified size.
  • the specified size may be determined according to the size of the advertisement slot of the item on the item display page.
  • partial images of a plurality of data objects are combined into different sizes, positions, and the like into a combined image of a specified size, so that the generated combined image can satisfy the display size requirement.
  • the data object can be searched for in a plurality of merchant stores.
  • various merchants of Taobao website can choose some hot products to promote on the Taobao website page.
  • the merchant can set a description word for each product for each commodity, such as: "Chinese Valentine's Day gift for girlfriend creative heart-shaped sterling silver necklace.”
  • the merchandise promoted by the advertisement space is only the hot sale item set by each merchant, and the promotion method of the single product does not achieve a good promotion effect.
  • the hot-selling items of each merchant are combined, and the commodity matching scheme is provided for the general consumer to be promoted as an advertisement, thereby improving the promotion effect and promoting the success of the commodity transaction.
  • the embodiment of the present application may extract keywords such as "Korean version” from the information of "send a girlfriend's Korean clothes". Then, according to the item description words and the category of the item set by the merchant, from the hot item promotion (such as the pre-established "baby boutique library"), the clothing style of the "Korean version” is searched across the shop. Accessories, shoes, bags, etc., determine the clothing, accessories, shoes, bags, four categories of products that meet the preset style, such as the four single product images shown on the left side of Figure 2.
  • the corresponding keyword of the product can be determined for each item image, for example, the keyword of "Chinese Valentine's Day gift for girlfriend creative heart-shaped sterling silver necklace” can be "sterling silver necklace”.
  • the images of these four items are processed by a mapping algorithm such as Bayesian, and the white background in the single-item image of the white background is deleted, and the single-product image is obtained by the map, and the four single-product images are colored according to the color.
  • a mapping algorithm such as Bayesian
  • the white background in the single-item image of the white background is deleted, and the single-product image is obtained by the map, and the four single-product images are colored according to the color.
  • the feature values such as texture and shape are matched, they are combined to display an image of the matching scheme.
  • the combined image may be a combined image of the size of the advertisement slot generated by scaling each of the individual product images to obtain different sizes and combining them according to different arrangement layouts.
  • the arrangement layout of each single product image can be converted into the coordinates of each single product image in the combined image, and the keywords of each single product are marked as page elements to each single by CSS absolute positioning.
  • the coordinates of the product image that is, the position of the corresponding item; and then the map through the img tag And the area attribute locates the URL address of the item to the position of the keyword element, automatically labels each item in the combined image, and the label links to the detail page of the item, thereby achieving automatic marking purposes.
  • the combined image may include information such as the coordinates, the keyword of the item, the URL address of the item, the name of the item image, the source path of the item image, the source of the combined image, and the like.
  • FIG. 2 is a schematic diagram showing clothes, accessories, shoes, and luggage.
  • the advertisement image presented to the user by the browser page may be as shown in the right image of FIG. 2 .
  • the embodiments of the present application are aimed at the most popular apparel products in the e-commerce industry.
  • the utility model finally realizes efficient promotion of apparel products, and solves the problem of PC and mobile.
  • the problem of automatic product combination promotion can save a lot of manual design and operation costs.
  • an information publishing apparatus is also provided in the embodiment of the present application. Since the principle of solving the problem of these devices is similar to the information publishing method, the implementation of these devices can refer to the implementation of the method, and the repetition is no longer Narration.
  • FIG. 3 is a schematic structural diagram of an information distribution apparatus in the embodiment of the present application. As shown in the figure, the information distribution apparatus may include:
  • the receiving module 301 is configured to receive input information of the user
  • a data object search module 302 configured to extract one or more keywords from user input information; and obtain at least two data objects according to one or more keyword searches, each data object including at least one picture;
  • a generating module 303 configured to respectively extract at least part of an image from a picture of at least two data objects; and generate a combined image according to the extracted at least part of the image;
  • the sending module 304 is configured to send the combined image to the user.
  • the generating module 303 may be specifically configured to generate a combined image according to the extracted at least part of the image and the link information of each data object.
  • the data object search module 302 can be specifically configured to search for at least two data objects under different categories.
  • the information publishing apparatus may further include:
  • An identifier determining module 305 configured to determine an identifier of each data object after searching for at least two data objects according to one or more keywords;
  • the generating module 303 can be further configured to generate a combined image based on the extracted at least part of the image and the identity of each of the data objects.
  • the generating module 303 may be specifically configured to combine partial images of each data object into different sizes and/or positions to generate a combined image of a specified size.
  • the data object search module 302 may be specifically configured to search for the at least two data objects in a plurality of merchant stores.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Processing Or Creating Images (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Processing (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种信息发布方法及装置，包括：接收用户的输入信息（101）；从所述用户输入信息提取一个或多个关键词（102）；根据所述一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一图片（103）；分别从至少两个数据对象的图片中抽取至少部分图像（104）；根据所述抽取的至少部分图像生成一个组合图像（105）；将所述组合图像发送给所述用户（106）。采用所提供的方法及装置，发布的信息不再是单一数据对象的信息，而是多个数据对象的信息的组合，使得信息发布后的展示效果更佳。

Description

一种信息发布方法及装置 技术领域
本申请涉及互联网技术领域，尤其涉及一种信息发布方法及装置。
背景技术
目前，各个商家在进行信息发布时，服务器是将待发布的单个数据对象的图像发送至客户端并显示在前端页面上。在发布后的前端页面展示给用户的仅是该商家发布的单个数据对象的信息，利用这种发布方式发布后所展示的信息较为单一、展示效果不佳。
现有技术不足在于：
信息发布后展示的仅是单个数据对象的信息，展示效果不佳。
发明内容
本申请实施例提出了一种信息发布方法及装置，以解决现有技术中信息发布后展示的仅是单个数据对象的信息导致展示效果不佳的技术问题。
本申请实施例提供了一种信息发布方法，包括如下步骤：
接收用户的输入信息；
从所述用户输入信息提取一个或多个关键词；
根据所述一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一图片；
分别从至少两个数据对象的图片中抽取至少部分图像；
根据所述抽取的至少部分图像生成一个组合图像；
将所述组合图像发送给所述用户。
本申请实施例提供了一种信息发布装置，包括：
接收模块，用于接收用户的输入信息；
数据对象搜索模块，用于从所述用户输入信息提取一个或多个关键词；根 据所述一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一个图片；
生成模块，用于分别从至少两个数据对象的图片中抽取至少部分图像；根据所述抽取的至少部分图像生成一个组合图像；
发送模块，用于将所述组合图像发送给所述用户。
有益效果如下：
在本申请实施例中，首先接收用户的输入信息并从中提取一个或多个关键词，根据一个或多个关键词搜索得到至少两个数据对象，每一个数据对象包含至少一个图片，分别从至少两个数据对象的图片中抽取至少部分图像，根据抽取的至少部分图像生成一个组合图像，最终将这个组合图像发送给用户，从而使得进行信息发布时，发布的信息不再是单一数据对象的信息，而是多个数据对象的信息的组合，给用户提供多个数据对象组合后的图像，采用这种信息发布方式发布后的展示效果更佳。
附图说明
下面将参照附图描述本申请的具体实施例，其中：
图1示出了本申请实施例中信息发布方法实施的流程示意图；
图2示出了本申请实施例中信息发布前后的示意图；
图3示出了本申请实施例中信息发布装置的结构示意图。
具体实施方式
为了使本申请的技术方案及优点更加清楚明白，以下结合附图对本申请的示例性实施例进行进一步详细的说明，显然，所描述的实施例仅是本申请的一部分实施例，而不是所有实施例的穷举。并且在不冲突的情况下，本说明中的实施例及实施例中的特征可以互相结合。
针对现有技术的不足，本申请实施例提出了一种信息发布方法及装置，下 面进行说明。
图1示出了本申请实施例中信息发布方法实施的流程示意图，如图所示，信息发布方法可以包括如下步骤：
步骤101、接收用户的输入信息；
步骤102、从用户输入信息提取一个或多个关键词；
步骤103、根据一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一图片；
步骤104、分别从至少两个数据对象的图片中抽取至少部分图像；
步骤105、根据抽取的至少部分图像生成一个组成图像；
步骤106、将组合图像发送给用户。
其中，以服装组合发布为例，关键词可以是“韩版”、“日系”等风格关键字，也可以是“欧式家具”等关键字。根据一个或多个关键词搜索得到至少两个数据对象，具体可以是根据“韩版”、“日系”等风格关键字确定至少两个物品，如两件韩版衣服、或者一件韩版衣服和一串韩版项链等。这些物品均包含至少一张物品展示图片，可以是正面图片、背面图片等。
从用户输入信息提取一个或多个关键词可以采用现有的关键词提取技术，根据一个或多个关键词搜索得到至少两个数据对象可以是以这些关键词作为输入集建立权重模型进行语义化搜索得到至少两个数据对象，具体的实现方式可以采用现有技术，本申请对关键词提取的具体方式以及根据关键词搜索数据对象的方式等不作限制。
在具体实施中，分别从至少两个数据对象的图片中抽取至少部分图像，可以利用贝叶斯等抠图算法将数据对象的图片中的主图抠出，然后提取其中的图像特征值，如颜色、纹理、形状等，进行分析并建立高阶索引等操作。除此之外，还可以对抽取的部分图像进行加深、调色等图像处理，这些图像处理的具体操作步骤均可以采用现有的图像处理技术，在此不作赘述。
组合图像还可以包括每个数据对象的图片的图片路径等其他信息。
由于本申请实施例所提供的信息发布方法，在接收到用户的输入信息后可以根据用户输入信息提取出一个或多个关键词，并根据这些关键词搜索得到至少两个数据对象，每一个数据对象包含至少一个图片，分别从图片中抽取至少部分图像，将这些部分图像生成组合图像发送给用户，为用户提供了包含多个数据对象的图片的组合图像，使得发布的信息不仅是单一数据对象的信息，而是多个数据对象的信息的组合。
实施中，组合图像还可以包括每个数据对象的链接信息。
其中，继续以服装组合发布为例，每个数据对象的链接信息可以是每个物品的详情页统一资源定位符(URL，Uniform Resource Locator)地址，如风衣的详情页URL地址等。
每个数据对象的链接信息可以定位到该数据对象的部分图像在组合图像中的位置，当用户点击该数据对象的部分图像时即可自动访问该数据对象的链接信息。例如，风衣的详情页URL地址可以与风衣图像的位置相同，使得用户在点击风衣图像时可以自动链接到风衣的详情页。
在具体实施中，可以通过现有技术中img标签的map和area属性来实现上述定位，具体的实现方式可以如下所示：
<img src＝"图形文件名"usemap＝"#图的名称">
<map name＝"图的名称">
<area shape＝形状coords＝区域坐标列表href＝"URL地址">
…
<area shape＝形状coords＝区域坐标列表href＝"URL地址">
</map>
上述代码为img标签中利用map和area属性实现URL地址定位的实现方式，本领域技术人员也可以采用其他方式来实现定位，本申请对此不做限制。
在具体实施中，也可以不进行上述定位等操作、直接将包含每个数据对象的链接信息的组合图像发送给用户，这样显示给用户的可能是数据对象的链接 信息与数据对象的部分图像分开显示的效果，如在风衣和围巾的图像下方显示风衣的链接信息以及围巾的链接信息等。虽然这种组合图像的展示效果不及采用定位后的展示效果，但这两种方式在具体使用时均可以采用，本领域技术人员可以根据实际需要进行选择。
本申请实施例通过将每个数据对象的链接信息包含在组合图像中，使得当用户看到组合图像时还可以进一步访问该数据对象的链接信息，方便快捷，进一步提升了用户体验。
为避免组合图像中数据对象来自于同一类目下，如风衣和风衣组合，导致展示效果不能满足用户实际需要的问题，本申请实施例还可以采用如下方式实施。
实施中，数据对象可以为在不同类目下搜索得到。
例如，可以根据“韩版”关键词在服装、饰品、鞋、箱包等不同类目下进行搜索，得到韩版服装、饰品、鞋或箱包等至少两个物品，从而使得生成的组合图像包括多个类目下的物品，而不是同一类目下的物品。
本申请实施例根据关键词在不同类目下搜索得到至少两个数据对象，最终将不同类目下的数据对象的部分图像组合，使得组合后的图像更加贴近用户的搭配需求，为用户提供不同类目下的数据对象的组合图像，进一步提高了组合图像所带来的展示效果。
实施中，根据一个或多个关键词搜索得到至少两个数据对象之后，所述信息发布方法可以进一步包括：确定每个数据对象的标识；
所述组合图像还可以包括：每个数据对象的标识。
其中，每个数据对象的标识可以是根据现有的算法或一定的规则生成的关键字，如：以“迪奥真我系列香水”物品为例，该物品的标识可以是“迪奥香水”或“真我系列”等关键字，本申请对每个数据对象的标识以及标识的具体生成方式不作限制。
在具体实施中，可以将所述每个数据对象的标识标记到每个数据对象的部 分图像在组合图像中的位置。
其中，将每个数据对象的标识标记到每个数据对象的部分图像在组合图像中的位置并不仅限于数据对象的标识与数据对象的图像二者坐标位置相同，具体实施时，为避免物品的标识遮挡物品的图像部分，也可以将物品的标识标记到该物品的图像的左上角或右下角等位置。如：在组合图像中的杯子图像的左上角标记“保温杯”等类似标识，用于标识、解释说明该杯子，便于用户查看、了解杯子图像所代表的含义等。
具体实施中，可以通过级联样式表(CSS，Cascading Style Sheets)的绝对定位方式将每个数据对象的标识作为页面元素，标记到每个数据对象的部分图像的相应位置，也可以采用其他方式来标记，本申请对具体的标记方法不做限制。
本申请实施例中在根据一个或多个关键词搜索得到至少两个数据对象之后，可以进一步再确定每个数据对象的标识，并将这个标识包含在生成的组合图像中，以便对每个数据对象进行标识、解释说明等，使得用户在看到组合图像之外还可以从文字等标识了解该数据对象。
实施中，所述根据抽取的至少部分图像生成一个组合图像，可以具体包括：
将每个数据对象的部分图像按不同的尺寸和/或位置组合生成指定大小的组合图像。
具体实施中，指定大小可以根据物品展示页面该物品的广告位的大小来确定。
本申请实施例中将多个数据对象的部分图像按照不同的尺寸、位置等组合成指定大小的组合图像，以便可以使得生成的组合图像满足展示尺寸要求。
实施中，所述数据对象可以为在多个商家店铺中搜索得到。
现有技术中，如果商家要进行组合物品信息发布时，通常需要设计人员来制作组合图像且组合的图像仅限于自家商品，这种方式对于经营单类目物品的商家并不适合。而本申请实施例中，由于各个物品是由服务器来确定，服务器 可以跨店铺的自动搜索等，不仅降低了人工成本，而且扩大了物品组合的范围。
为了便于本申请的实施，下面以淘宝网站的商品推广作为实例进行说明。
目前，淘宝网站的各个商家可以选择一些热卖商品在淘宝网站页面上推广。在进行单品推广时，商家可以对每个商品分别设置一些商品的描述词语，以便普通消费者搜索等，例如：“七夕情人节礼物送女友创意心形纯银项链”。其中，广告位所推广的商品仅是各个商家所设置的热卖单品，而这种单品推广方式并没有达到较好的推广效果。
因此，本申请实施例中提出将各个商家的热卖单品组合起来，为普通消费者提供商品搭配方案作为广告进行推广，从而提高推广效果、促进商品交易成功。
当普通消费者在淘宝网站的搜索框输入“送女友韩版衣服”等信息时，本申请实施例可以从“送女友韩版衣服”信息中提取出关键词，如“韩版”。然后根据商家自行设置的单品描述词语以及该商品的所属类目，从热卖的单品推广(如网站预先建立的“宝贝精品库”)中，跨店铺地搜索风格为“韩版”的服装、配饰、鞋、包包等，确定服装、配饰、鞋、包包这四个类别下满足预设风格的单品图像，如图2左侧所示的四个单品图像。
此外，还可以为每个单品图像确定该商品相应的关键字，如“七夕情人节礼物送女友创意心形纯银项链”商品的关键字可以为“纯银项链”。
这四个单品的图像利用贝叶斯等抠图算法进行抠图处理，将白底的单品图像中的白底删除，抠图得到单品图像并将这四个单品图像根据颜色、纹理、形状等特征值进行匹配后，组合成展示该搭配方案的图像。组合图像可以是各个单品图像按照一定比例缩放得到不同尺寸、按照不同排列布局组合，生成的广告位大小的组合图像。
本申请实施例中可以将每种单品图像的排列布局转换为每个单品图像在组合图像中的坐标，通过CSS绝对定位方式将每种单品的关键字作为页面元素标记到每种单品图像的坐标中，也即对应单品的位置；再通过img标签的map 和area属性将单品的URL地址定位到关键字元素的位置，自动给组合图像中每个商品打上标签，标签链接到该商品的详情页，从而实现自动打标目的。
组合图像可以包括该坐标、单品的关键字、单品的URL地址、单品图像的名称、单品图像来源路径、组合图像的来源等信息。
最终，将标记好详情页链接的广告图像(也即生成的组合图像)推送给普通消费者，显示在普通消费者的淘宝页面的右侧或底端等广告位上，为普通消费者提供搭配方案。图2中示出的是以服装、配饰、鞋、箱包为例的示意图，浏览器页面呈现给用户的广告图像可以如图2中右侧图像所示。
本申请实施例针对目前电商行业最热门的服饰类商品，通过跨店铺自动搭配、抠图、组合图像、自动标记商品链接，最终实现了服饰商品的高效推广，解决了PC端、移动端上的商品自动组合推广问题，同时可以节省大量的人工设计和运营的成本。
基于同一发明构思，本申请实施例中还提供了一种信息发布装置，由于这些设备解决问题的原理与一种信息发布方法相似，因此这些设备的实施可以参见方法的实施，重复之处不再赘述。
图3示出了本申请实施例中信息发布装置的结构示意图，如图所示，信息发布装置可以包括：
接收模块301，用于接收用户的输入信息；
数据对象搜索模块302，用于从用户输入信息提取一个或多个关键词；根据一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一个图片；
生成模块303，用于分别从至少两个数据对象的图片中抽取至少部分图像；根据抽取的至少部分图像生成一个组合图像；
发送模块304，用于将组合图像发送给用户。
实施中，生成模块303可以具体用于根据所述抽取的至少部分图像以及每个数据对象的链接信息生成一个组合图像。
实施中，数据对象搜索模块302可以具体用于在不同类目下搜索得到至少两个数据对象。
实施中，所述信息发布装置可以进一步包括：
标识确定模块305，用于根据一个或多个关键词搜索得到至少两个数据对象之后，确定每个数据对象的标识；
生成模块303可以进一步用于根据抽取的至少部分图像以及每个数据对象的标识生成一个组合图像。
实施中，生成模块303可以具体用于将每个数据对象的部分图像按不同的尺寸和/或位置组合生成指定大小的组合图像。
实施中，数据对象搜索模块302可以具体用于在多个商家店铺中搜索得到所述至少两个数据对象。
为了描述的方便，以上所述装置的各部分以功能分为各种模块或单元分别描述。当然，在实施本申请时可以把各模块或单元的功能在同一个或多个软件或硬件中实现。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。

Claims (12)

  1. 一种信息发布方法，其特征在于，包括如下步骤：
    接收用户的输入信息；
    从所述用户输入信息提取一个或多个关键词；
    根据所述一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一图片；
    分别从至少两个数据对象的图片中抽取至少部分图像；
    根据所述抽取的至少部分图像生成一个组合图像；
    将所述组合图像发送给所述用户。
  2. 如权利要求1所述的方法，其特征在于，所述组合图像还包括每个数据对象的链接信息。
  3. 如权利要求1所述的方法，其特征在于，所述数据对象为在不同类目下搜索得到。
  4. 如权利要求1所述的方法，其特征在于，所述根据一个或多个关键词搜索得到至少两个数据对象之后，所述方法进一步包括：确定每个数据对象的标识；
    所述组合图像还包括所述每个数据对象的标识。
  5. 如权利要求1所述的方法，其特征在于，所述根据抽取的至少部分图像生成一个组合图像，具体包括：
    将每个数据对象的部分图像按不同的尺寸和/或位置组合生成指定大小的组合图像。
  6. 如权利要求1所述的方法，其特征在于，所述数据对象为在多个商家店铺中搜索得到。
  7. 一种信息发布装置，其特征在于，包括：
    接收模块，用于接收用户的输入信息；
    数据对象搜索模块，用于从所述用户输入信息提取一个或多个关键词；根 据所述一个或多个关键词搜索得到至少两个数据对象，每一数据对象包含至少一个图片；
    生成模块，用于分别从至少两个数据对象的图片中抽取至少部分图像；根据所述抽取的至少部分图像生成一个组合图像；
    发送模块，用于将所述组合图像发送给所述用户。
  8. 如权利要求7所述的装置，其特征在于，所述生成模块具体用于根据所述抽取的至少部分图像以及每个数据对象的链接信息生成一个组合图像。
  9. 如权利要求7所述的装置，其特征在于，所述数据对象搜索模块具体用于在不同类目下搜索得到至少两个数据对象。
  10. 如权利要求7所述的装置，其特征在于，进一步包括：标识确定模块，用于根据一个或多个关键词搜索得到至少两个数据对象之后，确定每个数据对象的标识；所述生成模块进一步用于根据所述抽取的至少部分图像以及每个数据对象的标识生成一个组合图像。
  11. 如权利要求7所述的装置，其特征在于，所述生成模块具体用于将每个数据对象的部分图像按不同的尺寸和/或位置组合生成指定大小的组合图像。
  12. 如权利要求7所述的装置，其特征在于，所述数据对象搜索模块具体用于在多个商家店铺中搜索得到所述至少两个数据对象。
PCT/CN2016/071163 2015-01-23 2016-01-18 一种信息发布方法及装置 WO2016116018A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2017538700A JP2018509684A (ja) 2015-01-23 2016-01-18 情報公開方法及び装置
US15/653,425 US20170316034A1 (en) 2015-01-23 2017-07-18 Information publishing method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510035601.0A CN105868219B (zh) 2015-01-23 2015-01-23 一种信息发布方法及装置
CN201510035601.0 2015-01-23

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/653,425 Continuation US20170316034A1 (en) 2015-01-23 2017-07-18 Information publishing method and apparatus

Publications (1)

Publication Number Publication Date
WO2016116018A1 true WO2016116018A1 (zh) 2016-07-28

Family

ID=56416428

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/071163 WO2016116018A1 (zh) 2015-01-23 2016-01-18 一种信息发布方法及装置

Country Status (4)

Country Link
US (1) US20170316034A1 (zh)
JP (1) JP2018509684A (zh)
CN (1) CN105868219B (zh)
WO (1) WO2016116018A1 (zh)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106815744A (zh) * 2016-12-12 2017-06-09 网易无尾熊（杭州）科技有限公司 一种电子资源发放方法、设备和系统
CN109146586A (zh) * 2017-06-15 2019-01-04 阿里巴巴集团控股有限公司 提供数据对象信息页面的方法及装置
CN109785276A (zh) * 2017-11-10 2019-05-21 阿里巴巴集团控股有限公司 一种业务对象图片的合成方法和装置
CN107832469B (zh) * 2017-11-29 2019-04-09 北京洪泰同创信息技术有限公司 一种企业logo图像的生成方法及装置
JP6572500B1 (ja) * 2018-03-14 2019-09-11 エスゼット ディージェイアイ テクノロジー カンパニー リミテッドＳｚ Ｄｊｉ Ｔｅｃｈｎｏｌｏｇｙ Ｃｏ．，Ｌｔｄ 画像処理装置、撮像装置、移動体、画像処理方法、及びプログラム
CN109147007B (zh) * 2018-08-01 2023-09-01 Oppo（重庆）智能科技有限公司 贴纸加载方法、装置、终端及计算机可读存储介质
CN111768470A (zh) * 2019-06-20 2020-10-13 北京京东尚科信息技术有限公司 图片生成方法、装置、计算机设备及计算机可读存储介质
CN111709767B (zh) * 2020-05-06 2024-02-23 口碑(上海)信息技术有限公司 一种数据处理方法及装置
CN111768264A (zh) * 2020-05-26 2020-10-13 上海晶赞融宣科技有限公司 商品展示图片生成方法及装置、存储介质、终端
CN112750013A (zh) * 2021-01-15 2021-05-04 珠海必要工业科技股份有限公司 衍生对象生成方法和装置
US20220382763A1 (en) * 2021-05-25 2022-12-01 Dell Products, Lp Populating search results with intent and context-based images

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060184425A1 (en) * 2005-02-11 2006-08-17 Hanechak Brian D Product system and method
CN101441651A (zh) * 2007-11-20 2009-05-27 富士胶片株式会社 商品搜索系统、商品搜索方法以及商品搜索程序
US20110022529A1 (en) * 2009-07-22 2011-01-27 Fernando Barsoba Social network creation using image recognition
CN102375823A (zh) * 2010-08-13 2012-03-14 腾讯科技（深圳）有限公司 搜索结果聚合显示方法及系统
CN103699652A (zh) * 2013-12-26 2014-04-02 浙江宇天科技股份有限公司 一种访问网页的方法和系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003108593A (ja) * 2001-10-01 2003-04-11 Fuji Photo Film Co Ltd 絞込検索装置
US8010624B2 (en) * 2008-03-27 2011-08-30 Amazon Technologies, Inc. Dynamic composition for image transmission
US20150178786A1 (en) * 2012-12-25 2015-06-25 Catharina A.J. Claessens Pictollage: Image-Based Contextual Advertising Through Programmatically Composed Collages
US9117239B2 (en) * 2013-03-13 2015-08-25 Reno Acquisitions, Llc Method and system for generating a data grid interface to monitor and recommend relevant products
CN103544621A (zh) * 2013-11-05 2014-01-29 钱志湘 一种服饰组合图示方法
US20180330429A1 (en) * 2014-02-05 2018-11-15 Google Inc. Leading Edge Detection, Rotation, and Occlusion of Space Between Neighboring Image Pairs of a Set of Images
CN104090965A (zh) * 2014-07-15 2014-10-08 百度在线网络技术（北京）有限公司 搜索结果的展现方法和装置
US10223727B2 (en) * 2014-10-20 2019-03-05 Oath Inc. E-commerce recommendation system and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060184425A1 (en) * 2005-02-11 2006-08-17 Hanechak Brian D Product system and method
CN101441651A (zh) * 2007-11-20 2009-05-27 富士胶片株式会社 商品搜索系统、商品搜索方法以及商品搜索程序
US20110022529A1 (en) * 2009-07-22 2011-01-27 Fernando Barsoba Social network creation using image recognition
CN102375823A (zh) * 2010-08-13 2012-03-14 腾讯科技（深圳）有限公司 搜索结果聚合显示方法及系统
CN103699652A (zh) * 2013-12-26 2014-04-02 浙江宇天科技股份有限公司 一种访问网页的方法和系统

Also Published As

Publication number Publication date
CN105868219B (zh) 2019-09-17
CN105868219A (zh) 2016-08-17
US20170316034A1 (en) 2017-11-02
JP2018509684A (ja) 2018-04-05

Similar Documents

Publication Publication Date Title
WO2016116018A1 (zh) 一种信息发布方法及装置
US20230192947A1 (en) System and method allowing social fashion selection in an electronic marketplace
US10747826B2 (en) Interactive clothes searching in online stores
TWI760299B (zh) 銷售物件資訊的圖片展示方法及裝置
KR101511050B1 (ko) 상품 정보를 제공하고 표시하는 방법, 장치, 시스템 및 컴퓨터 프로그램
US8718369B1 (en) Techniques for shape-based search of content
TWI631474B (zh) Method and device for product identification label and method for product navigation
US9324102B2 (en) System and method to retrieve relevant inventory using sketch-based query
CN106610785B (zh) 商品对象列表信息处理方法及装置
CN102567543A (zh) 一种服装图片的搜索方法和装置
US11195227B2 (en) Visual search, discovery and attribution method, system, and computer program product
TW201743289A (zh) 搭配效果圖的產生方法、裝置及系統
US20170061527A1 (en) System and apparatus for displaying content based on location
US20160042233A1 (en) Method and system for facilitating evaluation of visual appeal of two or more objects
KR101322914B1 (ko) 비주얼 아이템이 적용된 제품의 검색방법
CN105868299A (zh) 一种数据搜索方法和装置
CN113191858A (zh) 基于图片搜索的商品展示方法及装置
KR20100125878A (ko) 오브젝트이미지 추출을 통한 광고 시스템 및 그 방법
KR102062248B1 (ko) 온라인 신문기사의 아티클 이미지를 분석하여 매칭되는 커머셜 이미지를 노출하는 방법
JP6356774B2 (ja) 選択装置、選択方法および選択プログラム
CN104731820A (zh) 基于立体图像的信息数据查询和选择方法
KR20140078001A (ko) 데코레이션 기반의 상품정보 제공시스템 및 방법
CN109272337A (zh) 对象标签的生成方法及相关设备
KR20210003706A (ko) 코디네이션 패션 아이템을 추천하는 방법
KR102285942B1 (ko) 사용자에게 패션 아이템 추천 서비스를 제공하는 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16739765

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017538700

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16739765

Country of ref document: EP

Kind code of ref document: A1