WO2022100483A1 - 用于定制模板库的模板推荐方法、装置、系统和介质 - Google Patents

用于定制模板库的模板推荐方法、装置、系统和介质 Download PDF

Info

Publication number
WO2022100483A1
WO2022100483A1 PCT/CN2021/128167 CN2021128167W WO2022100483A1 WO 2022100483 A1 WO2022100483 A1 WO 2022100483A1 CN 2021128167 W CN2021128167 W CN 2021128167W WO 2022100483 A1 WO2022100483 A1 WO 2022100483A1
Authority
WO
WIPO (PCT)
Prior art keywords
template
customized
recommended
item
target
Prior art date
Application number
PCT/CN2021/128167
Other languages
English (en)
French (fr)
Inventor
蔡启明
申作军
王琼萍
Original Assignee
北京沃东天骏信息技术有限公司
北京京东尚科信息技术有限公司
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 北京沃东天骏信息技术有限公司, 北京京东尚科信息技术有限公司 filed Critical 北京沃东天骏信息技术有限公司
Publication of WO2022100483A1 publication Critical patent/WO2022100483A1/zh

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
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • 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]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers

Definitions

  • the present disclosure relates to the field of computer technology, and more particularly, to a template recommendation method, apparatus, system and medium for customizing a template library.
  • C2M Customer to Manufactory, user direct connection to manufacturers
  • the C2M model can provide consumers with services of customized items.
  • Custom items require merchants to configure custom item information in the background, such as custom component models, custom picture styles, and so on.
  • the configuration information of these customized items needs to be manually entered one by one. If there are many customized items involved, or there are many customized items that the merchant needs to maintain, the workload will be very large, and it is easy to make mistakes. For wrong configuration, troubleshoot problems It is also more troublesome and takes more time. Therefore, the generation efficiency of custom items is low.
  • the present disclosure provides a template recommendation method, apparatus, system and medium for customizing a template library.
  • One aspect of the present disclosure provides a template recommendation method for a customized template library, the customized template library includes multiple recommended template sets, each recommended template set in the multiple recommended template sets corresponds to a category, and the Each recommended template set includes a plurality of templates, and the template includes at least one customized item and attribute information of each customized item in the at least one customized item; the method includes: acquiring recommendation rules and configured templates of the target object , the recommendation rule includes at least one of a category range, a custom item attribute rule, a custom item combination rule, and an item range; based on the category range, determine at least one target recommendation template set in the multiple recommended template sets; from Each target recommendation template set in the at least one target recommendation template set filters out the configured templates, and obtains a target recommendation template subset of each target recommendation template set; Combining at least one of the rule and the item scope, and determining at least one target template from the target recommendation template subset of each target recommendation template set as a recommended template; sending the recommended template to the target object, so that all The target object generates a new customized
  • the customized template library further includes a plurality of recommended removal template sets, each recommended removal template set in the plurality of recommended removal template sets corresponds to a category, and each recommended removal template set corresponds to a category, and each recommended removal template set corresponds to a category.
  • the template set includes a plurality of templates; the method further includes: determining at least one target recommended removal template set from the plurality of recommended removal template sets based on the category of the customized item to which the configured template belongs; determining the at least one target removal recommended template set; Whether each target recommended removal template set in the target recommended removal template set includes the configured template; if any target recommended removal template set in the at least one target recommended removal template set includes the configured template, Notifying the target object to delete the configured template.
  • the step of generating the customized template library includes: acquiring category, template, and transaction information of each customized item in a plurality of customized items;
  • the templates of each customized item are divided into template sets for each category; based on the similarity between the templates in each template set, the templates in each template set are clustered into multiple template subsets, and the template sets for each category are obtained.
  • the customized template library further includes a plurality of recommended removal template sets
  • the method further includes: generating a recommended removal recommendation for each category based on the scores of the plurality of template subsets for each category frame template set.
  • acquiring the category, template and transaction information of each customized item in the plurality of customized items includes: acquiring the category and template of each customized item from a configuration system configured to be based on The configuration information of the customization item of each customized item generates the template of each customized item; obtains the transaction information of each customized item from the first business platform, and the first business platform is used for the Trading services are available for each custom item.
  • acquiring the category, template and transaction information of each customized item in the plurality of customized items includes: acquiring the category, template and transaction information of each customized item from the second business platform through a web crawler , the second business platform is used to provide transaction services for each customized item.
  • the transaction information of the customized item includes transaction volume information of the customized item and comment information for the customized item.
  • the customized item includes components, pictures, words, symbols, packaging and materials.
  • a template recommendation device for a customized template library
  • the customized template library includes multiple recommended template sets, each recommended template set in the multiple recommended template sets corresponds to a category, and the Each recommended template set includes a plurality of templates, and the template includes at least one customized item and attribute information of each customized item in the at least one customized item
  • the apparatus includes: an obtaining module for obtaining the target object's A recommendation rule and a configured template, the recommendation rule includes at least one of a category range, a custom item attribute rule, a custom item combination rule, and an item range; a first determination module is configured to determine the multiple categories based on the category range.
  • At least one target recommendation template set in the at least one target recommendation template set a filtering module, configured to filter out the configured templates from each target recommendation template set in the at least one target recommendation template set, to obtain the target of each target recommendation template set A recommended template subset; a second determination module configured to, based on at least one of the custom item attribute rule, custom item combination rule and item scope of the target object, select a target recommendation template subset from the target recommendation template set of each target recommendation template set At least one target template is centrally determined as a recommended template; a sending module is configured to send the recommended template to the target object, so that the target object generates a new customized item based on the recommended template.
  • Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which when executed, are used to implement the method as described above.
  • Another aspect of the present disclosure provides a computer program comprising computer-executable instructions, which when executed, are used to implement the method as described above.
  • Another aspect of the present disclosure provides a computer system including: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more programs When executed by a plurality of processors, the one or more processors are caused to implement the method as described above.
  • FIG. 1 schematically shows an exemplary system architecture to which the template recommendation method and apparatus for customizing a template library according to an embodiment of the present disclosure can be applied;
  • FIG. 2 schematically shows a schematic diagram of a custom template library according to an embodiment of the present disclosure
  • FIG. 3 schematically shows a flowchart of a template recommendation method for customizing a template library according to an embodiment of the present disclosure
  • FIG. 4 schematically shows a flowchart of a template recommendation method for customizing a template library according to another embodiment of the present disclosure
  • FIG. 5 schematically shows a flowchart of a method for generating a custom template library according to an embodiment of the present disclosure
  • FIG. 6 schematically shows a flowchart of a method for acquiring category, template and transaction information of each customized item in a plurality of customized items according to an embodiment of the present disclosure
  • FIG. 7 schematically shows a flowchart of a template recommendation method for customizing a template library according to another embodiment of the present disclosure
  • FIG. 8 schematically shows a block diagram of a template recommendation apparatus for customizing a template library according to an embodiment of the present disclosure.
  • FIG. 9 schematically illustrates a block diagram of a computer system according to an embodiment of the present disclosure.
  • At least one of the “systems” shall include, but not be limited to, systems with A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc. ).
  • E-commerce has been developed for many years, and there are many various e-commerce platforms.
  • the systems used by various e-commerce platforms are similar, mainly including consumer-oriented item display, order/payment system, and delivery of orders to merchants or warehouses.
  • E-commerce platforms have been very mature in selling standard products, and they have also been selling customized products for a long time.
  • C2M emphasizes the connection between manufacturing and consumers. Under the C2M model, consumers place orders directly through the platform, and factories receive personalized demand orders from consumers, and then design, purchase, produce, and deliver goods according to their needs. It mainly includes pure flexible production, rapid supply chain response of small batches and multiple batches.
  • Embodiments of the present disclosure provide a template recommendation method for a customized template library, where the customized template library includes multiple recommended template sets, each recommended template set in the multiple recommended template sets corresponds to a category, and each recommended template set includes a plurality of templates, wherein the template includes at least one customized item and attribute information of each customized item in the at least one customized item; the method includes: obtaining recommendation rules and configured templates of the target object, and the recommended rules include category scope, customized item attribute rules, at least one of a custom item combination rule and an item range; based on the category range, determine at least one target recommendation template set in multiple recommendation template sets; filter out the configured templates from each target recommendation template set in the at least one target recommendation template set , obtain the target recommendation template subset of each target recommendation template set; based on at least one of the custom item attribute rules, custom item combination rules and item scope of the target object, from the target recommendation template subset of each target recommendation template set At least one target template is determined as a recommended template; the recommended template is sent to the target object, so that the target object
  • FIG. 1 schematically shows an exemplary system architecture 100 to which a template recommendation method and apparatus for customizing a template library according to an embodiment of the present disclosure may be applied.
  • FIG. 1 is only an example of a system architecture to which the embodiments of the present disclosure can be applied, so as to help those skilled in the art to understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used for other A device, system, environment or scene.
  • the system architecture 100 may include a terminal device 101 , a terminal device 102 , a terminal device 103 , a network 104 , a server 105 , a server 106 , and a server 107 .
  • the network 104 is a medium for providing communication links between the terminal devices 101 to 103 and the servers 105 to 107 .
  • the network 104 may include various connection types, such as wired and/or wireless communication links, and the like.
  • the terminal devices 101 to 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.
  • the server 105 may be a background server of a configuration system for providing a configuration service for customized items of customized items to users, the server 106 may be used to provide users with a customized template recommendation service for customized items, and the server 107 may be used to customize items for users.
  • Various e-commerce platforms that provide transaction services for items.
  • the user A configures the customization item information of the item a through the terminal device 101.
  • the customization item may include components such as a hard disk, a memory, and a CPU.
  • the customized item information includes attribute values of each component, such as the type, size, and price of the hard disk. , Brand, size and price of memory, model and price of CPU, etc.
  • the terminal device 101 sends the configured customization item information of the item a to the server 105, and the server 105 generates a customization template for the item a.
  • the customization item may include pictures, text and symbols, for example, the customization item information may include picture style and pixels, font, color and size of the text and symbols.
  • the terminal device 102 sends the configured customization item information of the item b to the server 105, and the server 105 generates a customization template for the item b.
  • the server 106 may obtain transaction data of a plurality of customized items in the server 107, and the transaction data includes transaction volume and user comments. Server 106 may also obtain custom templates for a plurality of custom items in server 105 . The server 106 may associate the transaction data of the customized item with the customized item information based on the item number of the customized item, and then divide the customized items by category based on the category of the customized item, and group the customized items of the same category together. The server 106 may also perform some statistics on the customization items of the customized items based on the transaction data of the customized items. For example, a certain customized item (such as a certain picture) or a combination of customized items (components, pictures and texts) may be counted based on the transaction volume of the customized items. any combination of ) and so on.
  • a certain customized item such as a certain picture
  • a combination of customized items may be counted based on the transaction volume of the customized items. any combination of ) and so on.
  • the server 106 can generate a recommendation template from pictures, words and components with high transaction volume, or any combination of pictures, words and components, and then can send the recommended template to the terminal device 101 to the terminal device 103 .
  • the server 106 sends a customized item template of a combination of pictures and words with high sales to the terminal device 103. If the user of the terminal device 103 adopts the template recommended by the server 106, the terminal device 103 can generate a customized item based on the recommended template with one click. A preview link of custom items can also be generated for user reference.
  • the template recommendation method for customizing the template library provided by the embodiment of the present disclosure may generally be executed by the server 106 .
  • the template recommendation apparatus for customizing the template library provided by the embodiment of the present disclosure may generally be set in the server 106 .
  • terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.
  • FIG. 2 schematically shows a schematic diagram of a custom template library according to an embodiment of the present disclosure.
  • the customized template library 210 includes a recommended template set 211 and a recommended removal template set 212 .
  • the recommended template set 211 may include recommended template sets of multiple categories
  • the suggested removal template set 212 may include recommended removal template sets of multiple categories.
  • the server 106 obtains transaction data of customized items from multiple e-commerce platforms, and obtains customized information of customized items from a configuration system, and then can save the transaction data and customized information of customized items in the customized Template library 210.
  • the sales volume, popularity, market trend and trend of the customized items can be analyzed based on information such as transaction volume, comments and popularity, and then the customized template library 210 can be analyzed based on the analysis results.
  • the customized items in the catalog are divided into a recommended template set 211 and a recommended take-off template set 212 .
  • the customized items with high sales, high popularity, and good market trends and trends are divided into the recommended template set 211
  • the customized items with low sales, low popularity, and bad market trends and trends are divided into Recommended template set 212.
  • the customized items may be further classified based on the category of the customized item, and a recommended template set and recommended removal template set for each category are obtained.
  • the classification of categories can be, for example, clothing, electronic products, furniture, food, etc., as well as women's categories, men's categories, pregnancy and baby categories, etc., and each category can be further divided into multiple sub-categories.
  • FIG. 3 schematically shows a flowchart of a template recommendation method for customizing a template library according to an embodiment of the present disclosure.
  • the customized template library includes multiple recommended template sets, each recommended template set corresponds to a category, each recommended template set includes multiple recommended customized item templates, and the templates include at least one customized item and at least one customized item.
  • the customized items may include components, pictures (or patterns), words and symbols, etc.
  • the components may be, for example, the CPU, memory, and hard disk of a computer, and the attributes of the components may include CPU model, hard disk size, memory brand, and the like.
  • a picture may be a copyrighted various material pictures, and the properties of the picture may include pixels and styles.
  • the words and symbols can be various slogans, logos, etc., and the properties of the words and symbols can include fonts, font sizes, and colors.
  • a customized item can be a template, a combination of multiple customized items can also be a template, and a customized item completely composed of customized items is also a template.
  • the pattern on the T-shirt is a template
  • the graphic and text combination on the T-shirt is a template
  • the customized computer composed of CPU, memory, hard disk, display, etc. is also a template.
  • the method includes operations S301 to S305.
  • a recommendation rule and a configured template of the target object are obtained, and the recommendation rule includes at least one of a category range, a custom item attribute rule, a custom item combination rule, and an item range.
  • the target object may be an electronic device of a user (merchant or manufacturer) who subscribes to the template recommendation service, for example, may be terminal device 101 to terminal device 103 as shown in FIG. 1 .
  • the category range may include at least one category, which may be, for example, a clothing category and a women's category, T-shirts and shirts, and the like.
  • Custom item attribute rules can be attribute requirements set by the user, including picture style, font color, memory brand, etc.
  • the user can specify that only pictures of a certain style are recommended, and only a certain model of CPU is recommended.
  • the custom item combination rule may be a custom item combination requirement set by the user, and may include a combination item requirement and a combination quantity requirement.
  • a user can specify a template that only recommends a combination of pictures and text, and only recommends a combination of items with no more than 3 templates, and so on.
  • the range of items can be items specified by the user that need to be recommended, such as a customized computer composed of CPU, memory, hard disk, and monitor.
  • a configured template is a template that has been configured by a user, there may be multiple configured templates, and each configured template may include at least one customized item, such as a pattern on a T-shirt configured by a user, A combination of graphics and text on a T-shirt or a custom computer composed of CPU, memory, hard disk and monitor, etc.
  • At least one target recommended template set in the multiple recommended template sets is determined.
  • the recommended template set of category 1 may be determined as the target recommended template set.
  • the configured templates are filtered out from each target recommendation template set in the at least one target recommendation template set, and a target recommendation template subset of each target recommendation template set is obtained.
  • the templates that have been configured by the user are filtered from the recommended template set of category 1 to obtain a target recommended template subset, and templates that meet the user's requirements are further filtered from the subset.
  • At least one target template is determined as a recommendation template from the target recommendation template subset of each target recommendation template set based on at least one of the custom item attribute rule, the custom item combination rule and the item scope of the target object.
  • custom item attribute rules such as picture style
  • custom item combination rules such as text combination, no more than two pictures
  • item range such as clothing
  • the customized items that meet the above requirements are screened out as the target customized items, and the customized template of the target customized item can be fed back to the user as a recommendation template, and there can be multiple recommendation templates.
  • a plurality of customized T-shirts and customized shirts that meet the user's requirements are selected from the subset of target recommended templates, and the customized T-shirts and customized shirt templates are used as recommended templates.
  • the recommended template is sent to the target object, so that the target object generates a new customized item based on the recommended template.
  • the target object can directly use the recommended template to generate a customized item after receiving the feedback recommendation template, and can generate a corresponding preview link so that the user can view the effect of the customized item.
  • the recommended templates that conform to the recommendation rules are screened from the recommended template set, and the recommended templates are sent to the target objects, so that the target objects can directly generate customized items based on the recommended templates, Improved the efficiency of generating custom items.
  • the recommended template set is generated based on customized items with high sales, high popularity, and good market trends and trends, the templates recommended to merchants are conducive to improving merchants' customized items, so that merchants can update customized items in a timely manner. Introduce custom items that are more popular in the market.
  • FIG. 4 schematically shows a flowchart of a template recommendation method for customizing a template library according to another embodiment of the present disclosure.
  • the customized template library further includes a plurality of recommended removal template sets, each recommended removal template set in the multiple recommended removal template sets corresponds to a category, and each recommended removal template set includes multiple recommendations A template for a custom item that has been removed from the shelf.
  • the method includes operations S401 to S403.
  • At least one target recommended removal template set is determined from multiple recommended removal template sets based on the category of the customized item to which the configured template belongs.
  • the configured templates are templates that have been configured by the user. If the categories to which the configured templates belong are category 1 and category 2, the set of recommended removal templates for category 1 and category 2 is determined as the target recommended removal template set.
  • each target proposed removal template set in the at least one target proposed removal template set includes a configured template.
  • any target recommended removal template set in the at least one target recommended removal template set includes the configured template, the target object is notified to delete the configured template.
  • the set of templates recommended to be removed from the shelves is generated based on customized items with low sales, low popularity, and poor market trends and trends, the recommended templates for merchants to remove from shelves are helpful for merchants to update customized items in a timely manner and remove them from shelves. Custom items with low market popularity.
  • FIG. 5 schematically shows a flowchart of a method for generating a custom template library according to an embodiment of the present disclosure.
  • the method includes operations S501 to S506.
  • the transaction information of the customized item includes transaction volume information of the customized item and comment information for the customized item.
  • the template may include at least one custom item and attributes, such as picture pixel and style, font, color and size of text, model of CPU, size of hard disk, brand of memory, etc.
  • the templates of the plurality of customized items are divided into template sets for each category.
  • each template set in the multiple template sets corresponds to a category, such as a template set of category 1, a template set of category 2, and so on.
  • the templates in each template set are clustered into multiple template subsets to obtain multiple template subsets for each category.
  • each template can be expressed as an expression of ⁇ custom item 1, custom item 2, ...>, and based on the expressions of each two templates, it is possible to calculate The similarity or association between the two templates. Templates with high similarity or correlation are then put together to form multiple template subsets.
  • the template set of category 1 includes template subset 1, template subset 2 . . . template subset k, where k is an integer greater than 2.
  • the templates in template subset 1 have high similarity with each other
  • the templates in template subset 2 have high similarity with each other
  • the templates in template subset 1 and the templates in template subset 2 The similarity between them is low. In this way, it is convenient to count the sales of pictures with the same theme and the sales of combinations of pictures and texts of the same style. Similar templates with high sales can be recommended when recommending to the target audience.
  • the customization item for an image can calculate the similarity based on the theme and style of the image, and can also extract features from the image for vectorized representation, and then calculate the similarity between the images based on the vector of the image.
  • the similarity between the components can be determined directly based on the attribute values (such as model, size, etc.) of the components.
  • each template subset is scored based on the transaction information of the customized items of the template in each template subset to obtain a score for each template subset.
  • the template subset 1 can be scored based on the transaction data of the customized items of the templates in the template subset 1.
  • the dimensions such as rating assign weights, and then perform a weighted average to obtain the score of the template.
  • the comprehensive score of each template in the template subset 1 is obtained, and the scoring strategy of the comprehensive score can be, for example, the average value or the weighted average value of each template.
  • template subset 2 to template subset k the same method is used to calculate the score of each template in the template subset and the comprehensive score of the template subset.
  • the embodiments of the present disclosure do not limit the scoring method for each template in the template subset and the scoring method for the comprehensive score of the template subset.
  • a recommended template set for each category is generated based on the scores of the plurality of template subsets for each category.
  • a set of recommended takedown templates for each category is generated based on the scores of the plurality of template subsets for each category.
  • template subset 1 to template subset k can be sorted based on the score of each template subset, and the template subsets in the top preset positions (such as the top 100) can be combined together to generate a recommended template.
  • Set put together the template subsets of the preset positions (such as 50 positions) after the ranking and combine them to generate a set of recommended delisting templates.
  • FIG. 6 schematically shows a flowchart of a method for acquiring category, template and transaction information of each customized item in a plurality of customized items according to an embodiment of the present disclosure.
  • the method includes operations S601 to S602.
  • the configuration system is configured to generate a template of each customized item based on configuration information of the customized item of each customized item.
  • the user can configure the customization item attributes of the customized item through the configuration system.
  • the user can configure the customization item of a customized T-shirt through the configuration system, and can configure the picture and text combination used for the T-shirt, the position, style, information such as color.
  • the configuration system generates and saves a template of the T-shirt based on the user's configuration information.
  • templates for customized items can be obtained through the configuration system.
  • transaction information of each customized item from the first business platform is acquired.
  • the first business platform is an e-commerce platform for providing transaction services for customized items
  • the transaction web page of the e-commerce platform can display the transaction volume, customized items, and customized item attributes of customized items.
  • the transaction volume information on the transaction web page can be read through the web crawler, and the customized items and customized item attribute information on the transaction web page can also be read through the web crawler.
  • the customized items of a customized computer that can be displayed on the transaction web page include a CPU and a hard disk, the CPU model is XX, and the hard disk size is XXX.
  • the attributes of the above-mentioned customized items and the sales volume of the customized items can be obtained through a web crawler.
  • FIG. 7 schematically shows a flowchart of a template recommendation method for customizing a template library according to another embodiment of the present disclosure.
  • the execution body includes a first terminal, a second terminal, a third terminal, a configuration system, a business platform, and a recommendation system.
  • the first terminal, the second terminal and the third terminal are terminals used by the user (merchant or manufacturer), and the configuration system is a system used to provide the user with a configuration service of customized items of customized items.
  • Business platforms are various e-commerce platforms used to provide transaction services for users' customized items.
  • the recommendation system is a recommendation system for a template recommendation method for customizing a template library according to an embodiment of the present disclosure.
  • the first terminal configures the customization item information of the item a on the configuration system, and generates a template of the item a.
  • the second terminal configures the customization item information of the item b on the configuration system, and generates a template of the item b.
  • the method includes operations S701 to S705.
  • the recommendation system acquires the template of the item a from the configuration system.
  • the recommendation system obtains the template of the item b from the configuration system.
  • the recommendation system may acquire templates of multiple customized items from the configuration system, and the templates for acquiring item a and item b are only examples.
  • the recommendation system obtains transaction data of a plurality of customized items from the business platform.
  • the business platform may be an e-commerce platform directly connected to the recommendation system through a dedicated line, and may directly obtain information such as transaction volume and comments of customized items on the platform.
  • the business platform also includes other e-commerce platforms that cannot be directly connected to the recommendation system.
  • information such as the sales volume of customized items, customized items, and customized item attributes on the platform webpage can be read through a web crawler.
  • the recommendation system In operation S704, the recommendation system generates a recommendation template library based on the acquired transaction data of the plurality of customized items.
  • the recommendation system performs statistics on the acquired customized items, for example, based on information such as transaction volume, comments, and popularity, the customized items can be analyzed in multiple dimensions such as sales, popularity, market trends, and trends. , the most recommended template to get customized items with high sales and high market popularity.
  • the recommendation system sends the recommended templates in the recommended template library to the third terminal.
  • the recommendation system may send the recommendation template to a terminal that has subscribed to a template recommendation service, such as a third terminal. Further, the recommendation system may send a template conforming to the user's recommendation rules to the terminal based on the recommendation rules set by the terminal.
  • FIG. 8 schematically shows a block diagram of a template recommendation apparatus for customizing a template library according to an embodiment of the present disclosure.
  • the template recommendation apparatus 800 for customizing a template library includes an acquiring module 801 , a first determining module 802 , a filtering module 803 , a second determining module 804 and a sending module 805 .
  • the obtaining module 801 is configured to obtain a recommendation rule and a configured template of the target object, where the recommendation rule includes at least one of a category range, a custom item attribute rule, a custom item combination rule, and an item range.
  • the first determining module 802 is configured to determine at least one target recommended template set from the multiple recommended template sets based on the category range.
  • the filtering module 803 is configured to filter out the configured templates from each target recommendation template set in the at least one target recommendation template set, so as to obtain a target recommendation template subset of each target recommendation template set.
  • the second determining module 804 is configured to determine at least one target template from the target recommendation template subset of each target recommendation template set as a recommendation template based on at least one of the custom item attribute rule, the custom item combination rule and the item scope of the target object .
  • the sending module 805 is configured to send the recommended template to the target object, so that the target object generates a new customized item based on the recommended template.
  • the customized template library further includes a plurality of recommended removal template sets, each recommended removal template set in the multiple recommended removal template sets corresponds to a category, and each recommended removal template set includes multiple recommendations A template for a custom item that has been removed from the shelf.
  • the template recommendation apparatus 800 for customizing a template library further includes a third determination module, a fourth determination module, and a notification module.
  • the third determination module is configured to determine at least one target recommended removal template set from multiple recommended removal template sets based on the category of the customized item to which the configured template belongs.
  • the fourth determination module is configured to determine whether each target recommended removal template set in the at least one target recommended removal template set includes a configured template.
  • the notification module is configured to notify the target object to delete the configured template if any target recommended removal template set in the at least one target recommended removal template set includes a configured template.
  • the template recommending apparatus 800 for a custom template library further includes a generating module, and the generating module is used for generating the custom template library.
  • the generating module includes an acquiring unit, a dividing unit, a clustering unit, a scoring unit, a first generating unit and a second generating unit.
  • the acquiring unit is used for acquiring category, template and transaction information of each customized item in the plurality of customized items.
  • the dividing unit is used for dividing templates of multiple custom items into template sets for each category based on the category of each custom item.
  • the clustering unit is used for clustering the templates in each template set into multiple template subsets based on the similarity between the templates in each template set, so as to obtain multiple template subsets for each category.
  • the scoring unit is configured to score each template subset based on the transaction information of the customized items of the template in each template subset to obtain a score for each template subset.
  • the first generating unit is configured to generate a recommended template set for each category based on the scores of the plurality of template subsets for each category.
  • the second generating unit is configured to generate a suggested removal template set for each category based on the scores of the multiple template subsets for each category.
  • the acquisition unit includes a first acquisition subunit, a second acquisition subunit, and a third acquisition subunit.
  • the first obtaining subunit is configured to obtain the category and template of each customized item from the configuration system, and the configuration system is configured to generate the template of each customized item based on the configuration information of the customized item of each customized item.
  • the second acquiring subunit is used for acquiring transaction information of each customized item from the first business platform, and the first business platform is used for providing transaction services for each customized item.
  • the third obtaining subunit is used to obtain the category, template and transaction information of each customized item from the second business platform through a web crawler, and the second business platform is used to provide transaction services for each customized item.
  • the transaction information of the customized item includes transaction volume information of the customized item and comment information for the customized item.
  • customized items include components, pictures, text, symbols, packaging, materials, and the like.
  • modules, sub-modules, units, sub-units, or at least part of the functions of any of them according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be divided into multiple modules for implementation.
  • any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least partially as hardware circuits, such as field programmable gate arrays (FPGA), programmable logic arrays (PLA), A system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or any other reasonable means of hardware or firmware that integrates or packages circuits, or can be implemented in software, hardware, and firmware Any one of these implementations or an appropriate combination of any of them is implemented.
  • FPGA field programmable gate arrays
  • PLA programmable logic arrays
  • ASIC application specific integrated circuit
  • any one of these implementations or an appropriate combination of any of them is implemented.
  • one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure may be implemented at least in part as computer program modules that, when executed, may perform corresponding functions.
  • any one of the acquisition module 801 , the first determination module 802 , the filtering module 803 , the second determination module 804 and the sending module 805 may be combined in one module/unit/subunit to implement, or any one of these modules A /unit/subunit can be split into multiple modules/units/subunits.
  • at least part of the functionality of one or more of these modules/units/subunits may be combined with at least part of the functionality of other modules/units/subunits and combined in one module/unit/subunit realized in.
  • At least one of the acquiring module 801 , the first determining module 802 , the filtering module 803 , the second determining module 804 , and the transmitting module 805 may be at least partially implemented as a hardware circuit, such as a field programmable gate Array (FPGA), Programmable Logic Array (PLA), System-on-Chip, System-on-Substrate, System-on-Package, Application-Specific Integrated Circuit (ASIC), or any other reasonable means by which circuits can be integrated or packaged as hardware or firmware, or any one of the three implementation manners of software, hardware and firmware, or an appropriate combination of any of them.
  • FPGA field programmable gate Array
  • PLA Programmable Logic Array
  • ASIC Application-Specific Integrated Circuit
  • At least one of the acquiring module 801, the first determining module 802, the filtering module 803, the second determining module 804, and the sending module 805 may be implemented at least in part as a computer program module, and when the computer program module is executed, The corresponding function can be executed.
  • the part of the template recommendation device for customizing the template library in the embodiment of the present disclosure corresponds to the part of the template recommending method for customizing the template library in the embodiment of the present disclosure, and the template for customizing the template library
  • the recommendation device part refers to the template recommendation method for customizing the template library, which will not be repeated here.
  • Figure 9 schematically illustrates a block diagram of a computer system suitable for implementing the methods described above, according to an embodiment of the present disclosure.
  • the computer system shown in FIG. 9 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • a computer system 900 includes a processor 901 that can be loaded into a random access memory (RAM) 903 according to a program stored in a read only memory (ROM) 902 or from a storage section 908 program to perform various appropriate actions and processes.
  • the processor 901 may include, for example, a general-purpose microprocessor (eg, a CPU), an instruction set processor and/or a related chipset, and/or a special-purpose microprocessor (eg, an application-specific integrated circuit (ASIC)), among others.
  • the processor 901 may also include on-board memory for caching purposes.
  • the processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiments of the present disclosure.
  • the processor 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904.
  • the processor 901 performs various operations of the method flow according to an embodiment of the present disclosure by executing programs in the ROM 902 and/or the RAM 903.
  • the program may also be stored in one or more memories other than ROM 902 and RAM 903.
  • the processor 901 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.
  • the system 900 may also include an input/output (I/O) interface 905 that is also connected to the bus 904 .
  • System 900 may also include one or more of the following components connected to I/O interface 905: input portion 906 including keyboard, mouse, etc.; including components such as cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers
  • I/O interface 905 input portion 906 including keyboard, mouse, etc.
  • input portion 906 including keyboard, mouse, etc.
  • components such as cathode ray tube (CRT), liquid crystal display (LCD), etc.
  • a storage section 908 including a hard disk, etc.
  • a communication section 909 including a network interface card such as a LAN card, a modem, and the like.
  • the communication section 909 performs communication processing via a network such as the Internet.
  • a drive 910 is also connected to the I/O interface 905 as needed.
  • a removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 908 as needed.
  • the method flow according to an embodiment of the present disclosure may be implemented as a computer software program.
  • embodiments of the present disclosure include a computer program article comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods illustrated in the flowcharts.
  • the computer program may be downloaded and installed from the network via the communication portion 909, and/or installed from the removable medium 911.
  • the above-described functions defined in the system of the embodiment of the present disclosure are performed.
  • the above-described systems, apparatuses, apparatuses, modules, units, etc. can be implemented by computer program modules.
  • the present disclosure also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the device/apparatus/system described in the above embodiments; it may also exist alone without being assembled into the device/system. device/system.
  • the above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, implement the method according to the embodiment of the present disclosure.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disk read only memory (CD- ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable storage medium may include one or more memories other than ROM 902 and/or RAM 903 and/or ROM 902 and RAM 903 described above.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.
  • Those skilled in the art will appreciate that various combinations and/or combinations of features recited in various embodiments and/or claims of the present disclosure are possible, even if such combinations or combinations are not expressly recited in the present disclosure.
  • various combinations and/or combinations of the features recited in the various embodiments of the present disclosure and/or in the claims may be made without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of this disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开提供了一种用于定制模板库的模板推荐方法，包括获取目标对象的推荐规则和已配置模板；基于品类范围，确定多个推荐模板集中的至少一个目标推荐模板集；从至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉已配置模板，得到每个目标推荐模板集的目标推荐模板子集；基于目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板；将推荐模板发送给目标对象，以使目标对象基于推荐模板生成新的定制物品。本公开还提供了一种用于定制模板库的模板推荐装置、系统和介质。

Description

用于定制模板库的模板推荐方法、装置、系统和介质
本申请要求于2020年11月12日递交的中国专利申请No.202011264804.4的优先权，其内容一并在此作为参考。
技术领域
本公开涉及计算机技术领域，更具体地，涉及一种用于定制模板库的模板推荐方法、装置、系统和介质。
背景技术
随着计算机和电子商务的快速发展，C2M(Customer to Manufactory，用户直连制造商)逐渐模式成为电商平台的热点。
C2M模式能够为消费者提供定制物品的服务。定制物品需要商家在后台配置定制项信息，如定制组件的型号，定制图片风格等等。这些定制项的配置信息需要手工逐条录入，如果涉及到的定制项比较多，或者商家需要维护的定制物品比较多，工作量就会非常的大，而且很容易出错，对于错误的配置，排查问题也比较麻烦，需要花比较多的时间。因此，定制物品的生成效率低。
发明内容
有鉴于此，本公开提供了一种用于定制模板库的模板推荐方法、装置、系统和介质。
本公开的一个方面提供了一种用于定制模板库的模板推荐方法，所述定制模板库包括多个推荐模板集，所述多个推荐模板集中的每个推荐模板集对应一个品类，所述每个推荐模板集包括多个模板，所述模板包括至少一个定制项和所述至少一个定制项中的每个定制项的属性信息；所述方法包括：获取目标对象的推荐规则和已配置模板，所述推荐规则包括品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一；基于所述品类范围，确定所述多个推荐模板集中的至少一个目标推荐模板集；从所述至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉所述已配置模板，得到每个目标推荐模板集的目标推荐模板子集；基于所述目标 对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从所述每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板；将所述推荐模板发送给所述目标对象，以使所述目标对象基于所述推荐模板生成新的定制物品。
根据本公开的实施例，所述定制模板库还包括多个建议下架模板集，所述多个建议下架模板集中的每个建议下架模板集对应一个品类，所述每个建议下架模板集包括多个模板；所述还包括：基于所述已配置模板属于的定制物品的品类，从所述多个建议下架模板集中确定至少一个目标建议下架模板集；确定所述至少一个目标建议下架模板集中的每个目标建议下架模板集中是否包括所述已配置模板；如果所述至少一个目标建议下架模板集中的任一目标建议下架模板集包括所述已配置模板，通知所述目标对象删除所述已配置模板。
根据本公开的实施例，所述定制模板库的生成步骤包括：获取多个定制物品中的每个定制物品的品类、模板和交易信息；基于所述每个定制物品的品类，将所述多个定制物品的模板划分为针对每个品类的模板集；基于每个模板集中的模板之间的相似度，将每个模板集中的模板聚类为多个模板子集，得到针对每个品类的多个模板子集；基于每个模板子集中的模板的定制物品的交易信息对每个模板子集进行打分，得到每个模板子集的得分；基于针对每个品类的多个模板子集的得分，生成针对每个品类的推荐模板集。
根据本公开的实施例，所述定制模板库还包括多个建议下架模板集，所述方法还包括：基于针对每个品类的多个模板子集的得分，生成针对每个品类的建议下架模板集。
根据本公开的实施例，获取多个定制物品中的每个定制物品的品类、模板和交易信息包括：获取来自配置系统的所述每个定制物品的品类和模板，所述配置系统用于基于所述每个定制物品的定制项的配置信息生成所述每个定制物品的模板；获取来自第一业务平台的所述每个定制物品的交易信息，所述第一业务平台用于为所述每个定制物品提供交易服务。
根据本公开的实施例，获取多个定制物品中的每个定制物品的品类、模板和交易信息包括：通过网页爬虫获取来自第二业务平台的所述每个定 制物品的品类、模板和交易信息，所述第二业务平台用于为所述每个定制物品提供交易服务。
根据本公开的实施例，所述定制物品的交易信息包括所述定制物品的交易量信息和针对所述定制物品的评论信息。
根据本公开的实施例，所述定制项包括组件、图片、文字、符号、包装和材质。
本公开的另一个方面提供了一种用于定制模板库的模板推荐装置，所述定制模板库包括多个推荐模板集，所述多个推荐模板集中的每个推荐模板集对应一个品类，所述每个推荐模板集包括多个模板，所述模板包括至少一个定制项和所述至少一个定制项中的每个定制项的属性信息；所述装置包括：获取模块，用于获取目标对象的推荐规则和已配置模板，所述推荐规则包括品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一；第一确定模块，用于基于所述品类范围，确定所述多个推荐模板集中的至少一个目标推荐模板集；过滤模块，用于从所述至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉所述已配置模板，得到每个目标推荐模板集的目标推荐模板子集；第二确定模块，用于基于所述目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从所述每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板；发送模块，用于将所述推荐模板发送给所述目标对象，以使所述目标对象基于所述推荐模板生成新的定制物品。
本公开的另一方面提供了一种计算机可读存储介质，存储有计算机可执行指令，所述指令在被执行时用于实现如上所述的方法。
本公开的另一方面提供了一种计算机程序，所述计算机程序包括计算机可执行指令，所述指令在被执行时用于实现如上所述的方法。
本公开的另一方面提供了一种计算机系统，包括：一个或多个处理器；存储装置，用于存储一个或多个程序，其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如上所述的方法。
根据本公开的实施例，采用了基于目标对象的推荐规则和已配置模板，从推荐模板集中筛选出符合推荐规则的推荐模板，将推荐模板发送给目标 对象的技术手段。由于目标对象基于推荐模板能够直接生成定制物品，所以至少部分地克服了相关技术中用户逐条配置定制项造成的定制物品配置效率低的技术问题，进而达到了提高定制物品的生成效率的技术效果。
附图说明
通过以下参照附图对本公开实施例的描述，本公开的上述以及其他目的、特征和优点将更为清楚，在附图中：
图1示意性示出了可以应用根据本公开实施例的用于定制模板库的模板推荐方法和装置的示例性系统架构；
图2示意性示出了根据本公开实施例的定制模板库的示意图；
图3示意性示出了根据本公开实施例的用于定制模板库的模板推荐方法的流程图；
图4示意性示出了根据本公开另一实施例的用于定制模板库的模板推荐方法的流程图；
图5示意性示出了根据本公开实施例的定制模板库的生成方法的流程图；
图6示意性示出了根据本公开实施例的获取多个定制物品中的每个定制物品的品类、模板和交易信息的方法的流程图；
图7示意性示出了根据本公开另一实施例的用于定制模板库的模板推荐方法的流程图；
图8示意性示出了根据本公开的实施例的用于定制模板库的模板推荐装置的框图；以及
图9示意性示出了根据本公开实施例的计算机系统的框图。
具体实施方式
以下，将参照附图来描述本公开的实施例。但是应该理解，这些描述只是示例性的，而并非要限制本公开的范围。在下面的详细描述中，为便于解释，阐述了许多具体的细节以提供对本公开实施例的全面理解。然而，明显地，一个或多个实施例在没有这些具体细节的情况下也可以被实施。此外，在以下说明中，省略了对公知结构和技术的描述，以避免不必要地混淆本公开的概念。
在此使用的术语仅仅是为了描述具体实施例，而并非意在限制本公开。 在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在，但是并不排除存在或添加一个或多个其他特征、步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义，除非另外定义。应注意，这里使用的术语应解释为具有与本说明书的上下文相一致的含义，而不应以理想化或过于刻板的方式来解释。
在使用类似于“A、B和C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。在使用类似于“A、B或C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B或C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。
电子商务已经发展了很多年，各种电商平台也有很多，各种电商平台使用的系统大同小异，主要包括面向消费者的物品展示，下单/支付的系统，将订单下发到商家或者仓库的订单处理系统，商家或者仓库使用的发货系统，将商品送到消费者指定地址的物流系统，以及相关的售后、客服系统等。电商平台在销售标准商品方面已经非常的成熟，销售定制商品也有比较长一段时间，在柔性供应链逐渐成熟的今天，C2M模式已经慢慢开始被电商平台纳入到销售体系之中。
C2M强调的是制造业与消费者的衔接。在C2M模式下，消费者直接通过平台下单，工厂接收消费者的个性化需求订单，然后根据需求设计、采购、生产、发货。主要包括纯柔性生产，小批量多批次的快速供应链反应。
本公开的实施例提供了一种用于定制模板库的模板推荐方法，定制模板库包括多个推荐模板集，多个推荐模板集中的每个推荐模板集对应一个品类，每个推荐模板集包括多个模板，模板包括至少一个定制项和至少一 个定制项中的每个定制项的属性信息；方法包括：获取目标对象的推荐规则和已配置模板，推荐规则包括品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一；基于品类范围，确定多个推荐模板集中的至少一个目标推荐模板集；从至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉已配置模板，得到每个目标推荐模板集的目标推荐模板子集；基于目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板；将推荐模板发送给目标对象，以使目标对象基于推荐模板生成新的定制物品。
图1示意性示出了可以应用根据本公开实施例的用于定制模板库的模板推荐方法和装置的示例性系统架构100。需要注意的是，图1所示仅为可以应用本公开实施例的系统架构的示例，以帮助本领域技术人员理解本公开的技术内容，但并不意味着本公开实施例不可以用于其他设备、系统、环境或场景。
如图1所示，根据该实施例的系统架构100可以包括终端设备101、终端设备102、终端设备103、网络104、服务器105、服务器106和服务器107。网络104用以在终端设备101至103和服务器105至107之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线和/或无线通信链路等等。
终端设备101至103可以是具有显示屏并且支持网页浏览的各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。
服务器105可以是用于为用户提供定制物品的定制项的配置服务的配置系统的后台服务器，服务器106可以用于为用户提供定制物品的定制模板推荐服务，服务器107可以是用于为用户的定制物品提供交易服务的各种电商平台。
用户(如商家或厂家)可以通过终端设备101至103与服务器105至服务器107交互，以接收或发送消息等。示例性地，用户A通过终端设备101配置物品a的定制项信息，定制项例如可以包括括硬盘、内存和CPU等组件，定制项信息包括各组件的属性值，例如硬盘的类型、大小和价格， 内存的品牌、大小和价格，CPU的型号和价格等。终端设备101将配置好的物品a的定制项信息发送给服务器105，服务器105生成该物品a的定制模板。
用户B通过终端设备102配置物品b的定制项信息，定制项例如可以包括图片、文字和符号等，定制项信息例如可以包括图片风格和像素，文字和符号的字体、颜色和大小等。终端设备102将配置好的物品b的定制项信息发送给服务器105，服务器105生成该物品b的定制模板。
服务器106可以获取服务器107中的多个定制物品的交易数据，交易数据包括交易量和用户评论等。服务器106还可以获取服务器105中的多个定制物品的定制模板。服务器106可以基于定制物品的物品编号将定制物品的交易数据和定制项信息关联起来，然后基于定制物品的品类，将定制物品按照品类进行划分，将相同品类的定制物品放在一起。服务器106还可以基于定制物品的交易数据对定制物品的定制项做一些统计，例如可以基于定制物品的交易量统计某一定制项(如某一图片)或定制项组合(组件、图片和文字中的任意组合)的交易量等等。
服务器106可以将交易量高的图片、文字和组件，或者图片、文字和组件中的任意组合生成推荐模板，然后可以将推荐模板发送给终端设备101至终端设备103。例如，服务器106将销量高的图片和文字组合的定制项模板发送给终端设备103，终端设备103的用户如果采纳了服务器106推荐的模板，则终端设备103可以基于推荐模板一键生成定制物品，还可以生成定制物品的预览连接，供用户参考。
需要说明的是，本公开实施例所提供的用于定制模板库的模板推荐方法一般可以由服务器106执行。相应地，本公开实施例所提供的用于定制模板库的模板推荐装置一般可以设置于服务器106中。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。
图2示意性示出了根据本公开实施例的定制模板库的示意图。
如图2所示，该定制模板库210包括推荐模板集211和建议下架模板集212。其中，推荐模板集211中可以包括多个品类的推荐模板集合，建议下架模板集212可以包括多个品类的建议下架模板集合。
根据本公开的实施例，服务器106从多个电商平台上获取到定制物品的交易数据，以及从配置系统获取到定制物品的定制信息，然后可以将定制物品的交易数据和定制信息保存在定制模板库210中。针对定制模板库210中的定制物品，基于交易量、评论和热度等信息可以进行定制物品的销量、受欢迎程度、市场趋势和潮流趋势等方面的分析，然后可以基于分析结果将定制模板库210中的定制物品划分为推荐模板集211和建议下架模板集212。例如，将销量高、受欢迎程度高、市场趋势和潮流趋势好的定制物品划分到推荐模板集211中，将将销量低、受欢迎程度低、市场趋势和潮流趋势不好的定制物品划分到推荐模板集212中。
根据本公开的实施例，在推荐模板集211和建议下架模板集212中可以基于定制物品的品类进一步对定制物品进行分类，得到针对每个品类的推荐模板集合和建议下架模板集合。其中，品类的划分例如可以是服装类、电子产品类、家具类和食品类等，还可以是女士品类、男士品类和孕婴类等，每个品类还可以继续划分为多个子品类。
图3示意性示出了根据本公开实施例的用于定制模板库的模板推荐方法的流程图。
根据本公开的实施例，该定制模板库包括多个推荐模板集，每个推荐模板集对应一个品类，每个推荐模板集包括多个推荐的定制物品的模板，模板包括至少一个定制项和至少一个定制项中的每个定制项的属性信息。其中，定制项可以包括组件、图片(或图案)、文字和符号等，组件例如可以是电脑的CPU、内存和硬盘等，组件的属性可以包括CPU型号、硬盘大小、内存品牌等。图片例如可以是具有版权各种素材图，图片的属性可以包括像素和风格等。文字和符号可以是各种标语、标志等，文字和符号的属性可以包括字体、字体大小和颜色等。
需要说明的是，一个定制项可以是一个模板，多个定制项的组合也可以是一个模板，一个完全由定制项组合成的定制物品也是一个模板。示例性地，T恤上的图案是一个模板，T恤上的图文组合是一个模板，由CPU、内存、硬盘和显示器等组成的定制电脑也是一个模板。
如图3所示，该方法包括操作S301～S305。
在操作S301，获取目标对象的推荐规则和已配置模板，推荐规则包括 品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一。
根据本公开的实施例，目标对象可以是开通模板推荐服务的用户(商家或厂家)的电子设备，例如可以是如图1所示终端设备101至终端设备103。
根据本公开的实施例，品类范围可以包括至少一个品类，例如可以是服装类和女士品类，T恤和衬衫等。定制项属性规则可以是用户设置的属性要求，可以包括图片风格、字体颜色以及内存品牌等，例如用户可以指定只推荐某一风格的图片，只推荐某个型号的CPU等。定制项组合规则可以是用户设置的定制项组合要求，可以包括组合项要求和组合数量要求，例如用户可以指定只推荐图片和文字组合的模板，只推荐组合项不超过3个模板等等。物品范围可以是用户指定需要推荐的物品，如由CPU、内存、硬盘和显示器等组成的定制电脑等。
根据本公开的实施例，已配置模板为用户已经配置过的模板，已配置模板可以有多个，每个已配置模板可以包括至少一个定制项，如用户已经配置的一个T恤上的图案、T恤上的图文组合或者由CPU、内存、硬盘和显示器等组成的定制电脑等。
在操作S302，基于品类范围，确定多个推荐模板集中的至少个目标推荐模板集。
示例性地，用户的推荐规则中如果指定了服装，服装的品类例如为品类1，则可以确定品类1的推荐模板集为目标推荐模板集。
在操作S303，从至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉已配置模板，得到每个目标推荐模板集的目标推荐模板子集。
示例性地，从品类1的推荐模板集中过滤掉用户已经配置的模板，得到目标推荐模板子集，从该子集合中进一步筛选符合用户要求的模板。
在操作S304，基于目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板。
根据本公开的实施例，基于用户的定制项属性规则(如图片风格)定制项组合规则(如图文组合、图片不超过两幅)和物品范围(如服装)等，从目标推荐模板子集中筛选出符合上述要求的定制物品为目标定制物品， 该目标定制物品的定制模板可以作为推荐模板反馈给用户，推荐模板可以有多个。示例性地，从目标推荐模板子集中筛选出多个符合用户要求的定制T恤和定制衬衣，将该定制T恤和定制衬衣的模板作为推荐模板。
在操作S305，将推荐模板发送给目标对象，以使目标对象基于推荐模板生成新的定制物品。
根据本公开的实施例，目标对象接收到反馈的推荐模板，可以直接使用推荐模板生成定制物品，并且可以生成对应的预览链接，使用户能够查看定制物品的效果。
根据本公开的实施例，基于目标对象的推荐规则和已配置模板，从推荐模板集中筛选出符合推荐规则的推荐模板，将推荐模板发送给目标对象，以便目标对象基于推荐模板直接生成定制物品，提高了生成定制物品的效率。
此外，由于推荐模板集是基于销量高、受欢迎程度高、市场趋势和潮流趋势好的定制物品生成的，因此，推荐给商家的模板有利于改进商家的定制物品，使商家及时更新定制物品，推出更受市场欢迎的定制物品。
图4示意性示出了根据本公开另一实施例的用于定制模板库的模板推荐方法的流程图。
根据本公开的实施例，定制模板库还包括多个建议下架模板集，多个建议下架模板集中的每个建议下架模板集对应一个品类，每个建议下架模板集包括多个建议下架的定制物品的模板。
如图4所示，该方法包括操作S401～S403。
在操作S401，基于已配置模板属于的定制物品的品类，从多个建议下架模板集中确定至少一个目标建议下架模板集。
示例性地，已配置模板为用户已经配置过的模板，如果已配置模板属于的品类为品类1和品类2，则确定品类1和品类2的建议下架模板集为目标建议下架模板集。
在操作S402，确定至少一个目标建议下架模板集中的每个目标建议下架模板集中是否包括已配置模板。
在操作S403，如果至少一个目标建议下架模板集中的任一目标建议下架模板集包括已配置模板，通知目标对象删除已配置模板。
示例性地，分别筛选品类1和品类2的建议下架模板集中是否存在该已配置模板，如果品类1和品类2的建议下架模板集任一一个建议下架模板集包含了该已配置模板，可以通知目标对象删除已配置模板。由于以便商家下架对应的定制物品。
此外，由于建议下架模板集是基于销量低、受欢迎程度低、市场趋势和潮流趋势不好的定制物品生成的，因此，建议商家的下架的模板有利于商家及时更新定制物品，下架市场欢迎度低的定制物品。
图5示意性示出了根据本公开实施例的定制模板库的生成方法的流程图。
如图5所示，该方法包括操作S501～操作S506。
在操作S501，获取多个定制物品中的每个定制物品的品类、模板和交易信息。
根据本公开的实施例，定制物品的交易信息包括定制物品的交易量信息和针对定制物品的评论信息。模板可以包括至少一个定制项及属性，如图片像素和风格，文字的字体、颜色和大小，CPU的型号，硬盘的大小，内存的品牌等。
在操作S502，基于每个定制物品的品类，将多个定制物品的模板划分为针对每个品类的模板集。
根据本公开的实施例，多个模板集中的每个模板集对应一个品类，如品类1的模板集、品类2的模板集等等。
在操作S503，基于每个模板集中的模板之间的相似度，将每个模板集中的模板聚类为多个模板子集，得到针对每个品类的多个模板子集。
根据本公开的实施例，针对同一品类中的定制物品模板集，每个模板可以表示为<定制项1，定制项2，……>的表达式，基于每两个模板的表达式，可以计算该两个模板之间的相似度或关联度。然后将相似度或关联度高的模板放在一起，形成多个模板子集。例如，品类1的模板集包括模板子集1、模板子集2……模板子集k，k为大于2的整数。其中，模板子集1中的模板彼此之间的相似度较高，模板子集2中的模板彼此之间的相似度较高，而模板子集1中的模板和模板子集2中的模板之间的相似度较低。由此，可以便于统计同主题的图片的销量以及同风格的图文组合的销 量等等。在向目标对象推荐时可以推荐销量高的相似的模板。
根据本公开的实施例，针对图像的定制项可以基于图像的主题、风格计算相似度，还可以从图像中提取特征进行向量化表示，然后基于图像的向量计算图像间的相似度。针对文字的定制项，也可以向量化文字，计算文本之间的相似度。针对组件的定制项，可以直接基于组件的属性值(如型号、大小等)确定组件之间的相似度。
在操作S504，基于每个模板子集中的模板的定制物品的交易信息对每个模板子集进行打分，得到每个模板子集的得分。
示例性地，针对模板子集1，基于该模板子集1中的模板的定制物品的交易数据可以对该模板子集1打分，打分策略例如可以是对每个模板的定制物品在销量、热评度等维度分配权重，然后进行加权平均得到该模板的得分。针对该模板子集1中每个模板的综合得分得到该模板子集1的综合得分，综合得分的打分策略例如可以是每个模板的平均值或加权平均值等。针对模板子集2至模板子集k，采用同样的方法计算该模板子集中每个模板的分数以及该模板子集的综合得分。本公开实施例对模板子集中每个模板的打分方法以及对模板子集的综合得分的打分方法不做限制。
在操作S505，基于针对每个品类的多个模板子集的得分，生成针对每个品类的推荐模板集。
在操作S506，基于针对每个品类的多个模板子集的得分，生成针对每个品类的建议下架模板集。
示例性地，可以基于每个模板子集的得分对模板子集1至模板子集k进行排序，可以将排名前预设位(如前100位)的模板子集放在一起组合生成推荐模板集，将排名后预设位(如50位)的模板子集放在一起组合生成建议下架模板集。
图6示意性示出了根据本公开实施例的获取多个定制物品中的每个定制物品的品类、模板和交易信息的方法的流程图。
如图6所示，该方法包括操作S601～操作S602。
在操作S601，获取来自配置系统的每个定制物品的品类和模板。
根据本公开的实施例，配置系统用于基于每个定制物品的定制项的配置信息生成每个定制物品的模板。用户通过配置系统可以配置定制物品的 定制项属性，例如，用户通过配置系统可以配置某定制T恤的定制项，可以配置用于该T恤的图片和文字组合、图文组合的位置、风格、颜色等信息。配置系统基于用户的配置信息生成该T恤的模板并保存。由此，可以通过该配置系统获取定制物品的模板。
在操作S602，获取来自第一业务平台的每个定制物品的交易信息。
根据本公开的实施例，第一业务平台是用于为定制物品提供交易服务的电商平台，该电商平台的交易网页上可以显示定制物品的交易量、定制项和定制项属性。对于能够直接连通访问到的电商平台，可以请求获取定制物品的交易信息。对于不能直接访问到的电商平台，可以通过网页爬虫读取交易网页上的交易量信息，还可以通过网页爬虫读取交易网页上的定制项和定制项属性信息。
示例性地，交易网页上可以显示某定制电脑的定制项包括CPU和硬盘，CPU型号为XX，硬盘大小为XXX。可以通过网页爬虫获取上述定制项的属性以及定制物品的销量。
图7示意性示出了根据本公开另一实施例的用于定制模板库的模板推荐方法的流程图。
如图7所示，执行主体包括第一终端、第二终端、第三终端、配置系统、业务平台和推荐系统。其中，第一终端、第二终端和第三终端为用户(商家或厂家)使用的终端，配置系统是用于为用户提供定制物品的定制项的配置服务的系统。业务平台是用于为用户的定制物品提供交易服务的各种电商平台。推荐系统是根据本公开的实施例的用于定制模板库的模板推荐方法的推荐系统。第一终端在配置系统上配置物品a的定制项信息，生成物品a的模板。第二终端在配置系统上配置物品b的定制项信息，生成物品b的模板。
该方法包括操作S701～操作S705。
在操作S701，推荐系统从配置系统获取物品a的模板。
在操作S702，推荐系统从配置系统获取物品b的模板。
根据本公开的实施例，推荐系统可以从配置系统获取多个定制物品的模板，获取物品a和物品b的模板仅为示例。
在操作S703，推荐系统从业务平台获取多个定制物品的交易数据。
根据本公开的实施例，业务平台可以是与推荐系统通过专线直接连通的电商平台，可以直接获取平台上的定制物品的交易量、评论等信息。
需要说明的是，业务平台还包括不能与推荐系统直接连通的其他电商平台，针对这些平台，可以通过网页爬虫读取到平台网页上的定制物品的销量、定制项和定制项属性等信息。
在操作S704，推荐系统基于获取到的多个定制物品的交易数据，生成推荐模板库。
根据本公开的实施例，推荐系统对获取到的定制物品进行统计，例如，基于交易量、评论和热度等信息可以对定制物品进行销量、受欢迎程度、市场趋势和潮流趋势等多维度的分析，得到销量高、受市场欢迎度高的定制物品的模板最为推荐模板。
在操作S705，推荐系统将推荐模板库中的推荐模板发送给第三终端。
根据本公开的实施例，推荐系统可以将推荐模板发送给开通模板推荐服务的终端，如第三终端。进一步地，推荐系统可以基于终端设置的推荐规则，将符合用户的推荐规则的模板发送给终端。
图8示意性示出了根据本公开的实施例的用于定制模板库的模板推荐装置的框图。
如图8所示，用于定制模板库的模板推荐装置800包括获取模块801、第一确定模块802、过滤模块803、第二确定模块804和和发送模块805。
获取模块801用于获取目标对象的推荐规则和已配置模板，推荐规则包括品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一。
第一确定模块802用于基于品类范围，确定多个推荐模板集中的至少一个目标推荐模板集。
过滤模块803用于从至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉已配置模板，得到每个目标推荐模板集的目标推荐模板子集。
第二确定模块804用于基于目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板。
发送模块805用于将推荐模板发送给目标对象，以使目标对象基于推 荐模板生成新的定制物品。
根据本公开的实施例，定制模板库还包括多个建议下架模板集，多个建议下架模板集中的每个建议下架模板集对应一个品类，每个建议下架模板集包括多个建议下架的定制物品的模板。
根据本公开的实施例，用于定制模板库的模板推荐装置800还包括第三确定模块、第四确定模块和通知模块。
根据本公开的实施例，第三确定模块用于基于已配置模板属于的定制物品的品类，从多个建议下架模板集中确定至少一个目标建议下架模板集。
根据本公开的实施例，第四确定模块用于确定至少一个目标建议下架模板集中的每个目标建议下架模板集中是否包括已配置模板。
根据本公开的实施例，通知模块用于如果至少一个目标建议下架模板集中的任一目标建议下架模板集包括已配置模板，通知目标对象删除已配置模板。
根据本公开的实施例，根据本公开的实施例，用于定制模板库的模板推荐装置800还包括生成模块，生成模块用于生成定制模板库。
生成模块包括获取单元、划分单元、聚类单元、打分单元、第一生成单元和第二生成单元。
获取单元用于获取多个定制物品中的每个定制物品的品类、模板和交易信息。
划分单元用于基于每个定制物品的品类，将多个定制物品的模板划分为针对每个品类的模板集。
聚类单元用于基于每个模板集中的模板之间的相似度，将每个模板集中的模板聚类为多个模板子集，得到针对每个品类的多个模板子集。
打分单元用于基于每个模板子集中的模板的定制物品的交易信息对每个模板子集进行打分，得到每个模板子集的得分。
第一生成单元用于基于针对每个品类的多个模板子集的得分，生成针对每个品类的推荐模板集。
第二生成单元用于基于针对每个品类的多个模板子集的得分，生成针对每个品类的建议下架模板集。
根据本公开的实施例，获取单元包括第一获取子单元、第二获取子单 元和第三获取子单元。
第一获取子单元用于获取来自配置系统的每个定制物品的品类和模板，配置系统用于基于每个定制物品的定制项的配置信息生成每个定制物品的模板。
第二获取子单元用于获取来自第一业务平台的每个定制物品的交易信息，第一业务平台用于为每个定制物品提供交易服务。
第三获取子单元用于通过网页爬虫获取来自第二业务平台的每个定制物品的品类、模板和交易信息，第二业务平台用于为每个定制物品提供交易服务。
根据本公开的实施例，定制物品的交易信息包括定制物品的交易量信息和针对定制物品的评论信息。
根据本公开的实施例，定制项包括组件、图片、文字、符号、包装和材质等。
根据本公开的实施例的模块、子模块、单元、子单元中的任意多个、或其中任意多个的至少部分功能可以在一个模块中实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以被拆分成多个模块来实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式的硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，根据本公开实施例的模块、子模块、单元、子单元中的一个或多个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
例如，获取模块801、第一确定模块802、过滤模块803、第二确定模块804和和发送模块805中的任意多个可以合并在一个模块/单元/子单元中实现，或者其中的任意一个模块/单元/子单元可以被拆分成多个模块/单元/子单元。或者，这些模块/单元/子单元中的一个或多个模块/单元/子单元的至少部分功能可以与其他模块/单元/子单元的至少部分功能相结合， 并在一个模块/单元/子单元中实现。根据本公开的实施例，获取模块801、第一确定模块802、过滤模块803、第二确定模块804和和发送模块805中的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，获取模块801、第一确定模块802、过滤模块803、第二确定模块804和和发送模块805中的至少一个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
需要说明的是，本公开的实施例中用于定制模板库的模板推荐装置部分与本公开的实施例中用于定制模板库的模板推荐方法部分是相对应的，用于定制模板库的模板推荐装置部分的描述具体参考用于定制模板库的模板推荐方法部分，在此不再赘述。
图9示意性示出了根据本公开实施例的适于实现上文描述的方法的计算机系统的框图。图9示出的计算机系统仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图9所示，根据本公开实施例的计算机系统900包括处理器901，其可以根据存储在只读存储器(ROM)902中的程序或者从存储部分908加载到随机访问存储器(RAM)903中的程序而执行各种适当的动作和处理。处理器901例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))，等等。处理器901还可以包括用于缓存用途的板载存储器。处理器901可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 903中，存储有系统900操作所需的各种程序和数据。处理器901、ROM 902以及RAM 903通过总线904彼此相连。处理器901通过执行ROM 902和/或RAM 903中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意，所述程序也可以存储在除ROM 902和RAM 903以外的一个或多个存储器中。处理器901也可以通过执行存储在所述 一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
根据本公开的实施例，系统900还可以包括输入/输出(I/O)接口905，输入/输出(I/O)接口905也连接至总线904。系统900还可以包括连接至I/O接口905的以下部件中的一项或多项：包括键盘、鼠标等的输入部分906；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分907；包括硬盘等的存储部分908；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分909。通信部分909经由诸如因特网的网络执行通信处理。驱动器910也根据需要连接至I/O接口905。可拆卸介质911，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器910上，以便于从其上读出的计算机程序根据需要被安装入存储部分908。
根据本公开的实施例，根据本公开实施例的方法流程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序物品，其包括承载在计算机可读存储介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分909从网络上被下载和安装，和/或从可拆卸介质911被安装。在该计算机程序被处理器901执行时，执行本公开实施例的系统中限定的上述功能。根据本公开的实施例，上文描述的系统、设备、装置、模块、单元等可以通过计算机程序模块来实现。
本公开还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的设备/装置/系统中所包含的；也可以是单独存在，而未装配入该设备/装置/系统中。上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被执行时，实现根据本公开实施例的方法。
根据本公开的实施例，计算机可读存储介质可以是非易失性的计算机可读存储介质。例如可以包括但不限于：便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读 存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
例如，根据本公开的实施例，计算机可读存储介质可以包括上文描述的ROM 902和/或RAM 903和/或ROM 902和RAM 903以外的一个或多个存储器。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序物品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。本领域技术人员可以理解，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合，即使这样的组合或结合没有明确记载于本公开中。特别地，在不脱离本公开精神和教导的情况下，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开的范围。
以上对本公开的实施例进行了描述。但是，这些实施例仅仅是为了说明的目的，而并非为了限制本公开的范围。尽管在以上分别描述了各实施例，但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围，本领域技术人员可以做出多种替代和修改，这些替代和修改都应落在本公开的范围之内。

Claims (11)

  1. 一种用于定制模板库的模板推荐方法，所述定制模板库包括多个推荐模板集，所述多个推荐模板集中的每个推荐模板集对应一个品类，所述每个推荐模板集包括多个模板，所述模板包括至少一个定制项和所述至少一个定制项中的每个定制项的属性信息；所述方法包括：
    获取目标对象的推荐规则和已配置模板，所述推荐规则包括品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一；
    基于所述品类范围，确定所述多个推荐模板集中的至少一个目标推荐模板集；
    从所述至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉所述已配置模板，得到每个目标推荐模板集的目标推荐模板子集；
    基于所述目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从所述每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板；
    将所述推荐模板发送给所述目标对象，以使所述目标对象基于所述推荐模板生成新的定制物品。
  2. 根据权利要求1所述的方法，其中，所述定制模板库还包括多个建议下架模板集，所述多个建议下架模板集中的每个建议下架模板集对应一个品类，所述每个建议下架模板集包括多个模板；
    所述还包括：
    基于所述已配置模板属于的定制物品的品类，从所述多个建议下架模板集中确定至少一个目标建议下架模板集；
    确定所述至少一个目标建议下架模板集中的每个目标建议下架模板集中是否包括所述已配置模板；
    如果所述至少一个目标建议下架模板集中的任一目标建议下架模板集包括所述已配置模板，通知所述目标对象删除所述已配置模板。
  3. 根据权利要求1所述的方法，其中，所述定制模板库的生成 步骤包括：
    获取多个定制物品中的每个定制物品的品类、模板和交易信息；
    基于所述每个定制物品的品类，将所述多个定制物品的模板划分为针对每个品类的模板集；
    基于每个模板集中的模板之间的相似度，将每个模板集中的模板聚类为多个模板子集，得到针对每个品类的多个模板子集；
    基于每个模板子集中的模板的定制物品的交易信息对每个模板子集进行打分，得到每个模板子集的得分；
    基于针对每个品类的多个模板子集的得分，生成针对每个品类的推荐模板集。
  4. 根据权利要求3所述的方法，其中，所述定制模板库还包括多个建议下架模板集，所述方法还包括：
    基于针对每个品类的多个模板子集的得分，生成针对每个品类的建议下架模板集。
  5. 根据权利要求3所述的方法，其中，获取多个定制物品中的每个定制物品的品类、模板和交易信息包括：
    获取来自配置系统的所述每个定制物品的品类和模板，所述配置系统用于基于所述每个定制物品的定制项的配置信息生成所述每个定制物品的模板；
    获取来自第一业务平台的所述每个定制物品的交易信息，所述第一业务平台用于为所述每个定制物品提供交易服务。
  6. 根据权利要求3所述的方法，其中，获取多个定制物品中的每个定制物品的品类、模板和交易信息包括：
    通过网页爬虫获取来自第二业务平台的所述每个定制物品的品类、模板和交易信息，所述第二业务平台用于为所述每个定制物品提供交易服务。
  7. 根据权利要求3至6中任一项所述的方法，其中，所述定制物品的交易信息包括所述定制物品的交易量信息和针对所述定制物品的评论信息。
  8. 根据权利要求1至6中任一项所述的方法，其中，所述定制 项包括组件、图片、文字、符号、包装和材质。
  9. 一种用于定制模板库的模板推荐装置，所述定制模板库包括多个推荐模板集，所述多个推荐模板集中的每个推荐模板集对应一个品类，所述每个推荐模板集包括多个模板，所述模板包括至少一个定制项和所述至少一个定制项中的每个定制项的属性信息；所述装置包括：
    获取模块，用于获取目标对象的推荐规则和已配置模板，所述推荐规则包括品类范围、定制项属性规则、定制项组合规则和物品范围中的至少之一；
    第一确定模块，用于基于所述品类范围，确定所述多个推荐模板集中的至少一个目标推荐模板集；
    过滤模块，用于从所述至少一个目标推荐模板集中的每个目标推荐模板集中过滤掉所述已配置模板，得到每个目标推荐模板集的目标推荐模板子集；
    第二确定模块，用于基于所述目标对象的定制项属性规则、定制项组合规则和物品范围中的至少之一，从所述每个目标推荐模板集的目标推荐模板子集中确定至少一个目标模板为推荐模板；
    发送模块，用于将所述推荐模板发送给所述目标对象，以使所述目标对象基于所述推荐模板生成新的定制物品。
  10. 一种计算机系统，包括：
    一个或多个处理器；
    存储器，用于存储一个或多个程序，
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现权利要求1至8中任一项所述的方法。
  11. 一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器实现权利要求1至8中任一项所述的方法。
PCT/CN2021/128167 2020-11-12 2021-11-02 用于定制模板库的模板推荐方法、装置、系统和介质 WO2022100483A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011264804.4A CN112347359A (zh) 2020-11-12 2020-11-12 用于定制模板库的模板推荐方法、装置、系统和介质
CN202011264804.4 2020-11-12

Publications (1)

Publication Number Publication Date
WO2022100483A1 true WO2022100483A1 (zh) 2022-05-19

Family

ID=74363568

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/128167 WO2022100483A1 (zh) 2020-11-12 2021-11-02 用于定制模板库的模板推荐方法、装置、系统和介质

Country Status (2)

Country Link
CN (1) CN112347359A (zh)
WO (1) WO2022100483A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117350266A (zh) * 2023-12-06 2024-01-05 本溪钢铁（集团）信息自动化有限责任公司 一种自动生成文档的方法及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112347359A (zh) * 2020-11-12 2021-02-09 北京沃东天骏信息技术有限公司 用于定制模板库的模板推荐方法、装置、系统和介质
CN117236967B (zh) * 2023-11-07 2024-01-23 南通极粟设计服务有限公司 一种用于定制化咨询服务的互动模版进化方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110173068A1 (en) * 2010-01-12 2011-07-14 David Joseph O'Hanlon Unified data burst internet advertising and em alert methods
CN109542421A (zh) * 2018-11-12 2019-03-29 夸克链科技（深圳）有限公司 一种模块化区块链智能合约
CN110517111A (zh) * 2019-08-15 2019-11-29 青岛科技大学 一种产品个性化定制方法
CN112347359A (zh) * 2020-11-12 2021-02-09 北京沃东天骏信息技术有限公司 用于定制模板库的模板推荐方法、装置、系统和介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20230041454A (ko) * 2021-09-17 2023-03-24 주식회사 팀솔루션 머신러닝 기반의 웹 페이지 템플릿 추천 방법 및 이를 위한 장치

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110173068A1 (en) * 2010-01-12 2011-07-14 David Joseph O'Hanlon Unified data burst internet advertising and em alert methods
CN109542421A (zh) * 2018-11-12 2019-03-29 夸克链科技（深圳）有限公司 一种模块化区块链智能合约
CN110517111A (zh) * 2019-08-15 2019-11-29 青岛科技大学 一种产品个性化定制方法
CN112347359A (zh) * 2020-11-12 2021-02-09 北京沃东天骏信息技术有限公司 用于定制模板库的模板推荐方法、装置、系统和介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117350266A (zh) * 2023-12-06 2024-01-05 本溪钢铁（集团）信息自动化有限责任公司 一种自动生成文档的方法及系统
CN117350266B (zh) * 2023-12-06 2024-03-08 本溪钢铁（集团）信息自动化有限责任公司 一种自动生成文档的方法及系统

Also Published As

Publication number Publication date
CN112347359A (zh) 2021-02-09

Similar Documents

Publication Publication Date Title
WO2022100483A1 (zh) 用于定制模板库的模板推荐方法、装置、系统和介质
US20230316575A1 (en) Item recommendations based on image feature data
US20230092579A1 (en) Identifying product metadata from an item image
US9710841B2 (en) Method and medium for recommending a personalized ensemble
EP3742377A1 (en) Commodity customization method, apparatus, device and storage medium
CN110020188A (zh) 基于隐式交互和简档数据的全局向量推荐
CN111177563A (zh) 一种信息推荐方法、装置、电子设备和存储介质
JP6324433B2 (ja) 配信装置、配信方法および配信プログラム
US20160343054A1 (en) Image acquisition and feature extraction apparatus, method of feature extraction and feature identification, and method for creating and providing advertisement content
CN107169839A (zh) 商品展示方法、装置及电子设备
JP2016001405A (ja) 配信装置、配信方法および配信プログラム
JP6945518B2 (ja) 情報処理装置、情報処理方法および情報処理プログラム
CN112288461A (zh) 广告信息推送方法、装置、介质及电子设备
WO2023066139A1 (zh) 显示商品信息的方法、装置及系统
CN112907699B (zh) 对象处理方法及装置
JP5899269B2 (ja) 生成装置、生成方法および生成プログラム
US20220198431A1 (en) Text messaging service based commerce system
CN115311046A (zh) 商品信息流展示方法及电子设备
CN110874167A (zh) 数据处理方法、装置和机器可读介质
JP6289519B2 (ja) 生成装置、生成方法および生成プログラム
TWI684876B (zh) 產品圖片智慧系統及方法
JP2018180610A (ja) 情報処理装置、情報配信方法、及び情報配信プログラム
CN107492002A (zh) 一种用于共享设备的促销方法和系统
JP2023149360A (ja) レビュー提供システム、レビュー提供方法及びプログラム
CN113792236A (zh) 页面请求方法、页面访问系统、电子设备及存储介质

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: 21891010

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21891010

Country of ref document: EP

Kind code of ref document: A1