CN110069696A - A kind of searching method, hybrid-sorting method, equipment and system - Google Patents

A kind of searching method, hybrid-sorting method, equipment and system Download PDF

Info

Publication number
CN110069696A
CN110069696A CN201710860286.4A CN201710860286A CN110069696A CN 110069696 A CN110069696 A CN 110069696A CN 201710860286 A CN201710860286 A CN 201710860286A CN 110069696 A CN110069696 A CN 110069696A
Authority
CN
China
Prior art keywords
product
attribute information
hybrid
content
result
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710860286.4A
Other languages
Chinese (zh)
Inventor
李阳华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
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 Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201710860286.4A priority Critical patent/CN110069696A/en
Publication of CN110069696A publication Critical patent/CN110069696A/en
Pending legal-status Critical Current

Links

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
    • 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
    • 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

Landscapes

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

Abstract

This application provides a kind of searching method, hybrid-sorting method, server, client, display systems, search system and equipment is calculated, is related to technical field of data processing.The hybrid-sorting method includes: the attribute information for obtaining product and the attribute information of product set；Obtain the attribute information of content and the attribute information of properties collection；The attribute information of the attribute information of product, content is mapped to the same space, obtains mapping result；The weight of product set and the weight of properties collection are determined according to the attribute information of the attribute information of product set and properties collection；The weight of weight and properties collection based on product set carries out hybrid-sorting to product, content using the mapping result, obtains hybrid-sorting result.By the technical solution of the application, difference of the different isomerization data on hybrid-sorting can be shielded, it is subsequent to be shown on the displaying position of product shelf according to hybrid-sorting result, realize the optimization under unified goal.

Description

A kind of searching method, hybrid-sorting method, equipment and system
Technical field
The application belongs to technical field of data processing more particularly to a kind of searching method, hybrid-sorting method, displaying side Method, client, presentation device, display systems, search system, calculates equipment and computer readable storage medium at server.
Background technique
With the development of Internet technology and terminal technology, more and more companies by network sell oneself product or Service.On electronic site or in App (application program), operator shows networking products on product shelf, clear for user It lookes at and chooses.Networking products are a kind of corresponding to actuals or the virtual product of service, attribute include title, brief introduction, Logo (logo), charge information etc..Product shelf is the virtual carrier for placing networking products, for describing how to show networking products To user.Product shelf generally includes several and shows that position, each displaying position are used to show a networking products.
In the website of the prior art or App, each marketing line generally has following two ways when showing networking products:
1, fixed hole sequence.This is a kind of simple sortord, the equally spaced insertion of general product (such as theme, brand group) To position is shown, as shown in Figure 1.The defect of this mode is the ratio for not being adapted dynamically product and general product to meet difference The demand of crowd.
2, the mixed proportion of the unsupervised product by launching different proportion and general product, real-time collecting online feedback, Dynamic adjustment ratio.Although this method improves the fixed existing defect of hole sequence, but fed back by launching to collect, and needs wave Take very big flow to reach preferred proportion, and due to be unsupervised and target combine optimize it is relatively difficult.
Summary of the invention
In view of this, this application provides a kind of searching method, hybrid-sorting method, methods of exhibiting, servers, client End, display systems, search system, calculates equipment and computer readable storage medium at presentation device, by by product, content It is mapped to the same space, difference of the different isomerization data on hybrid-sorting is shielded with this, it is subsequent according to hybrid-sorting result It is shown on the displaying position of product shelf, realizes the optimization under unified goal.
To achieve the above object, it is as follows to provide technical solution by the application:
According to a first aspect of the present application, a kind of searching method is proposed, a search system is applied to, comprising:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, at least one described product structure At product set attribute information, the content of the attribute information of at least one content and at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
According to a second aspect of the present application, a kind of hybrid-sorting method is proposed, a server is applied to, comprising:
The attribute letter for the product set that the attribute information and at least one described product for obtaining at least one product are constituted Breath；
Obtain the attribute letter of the attribute information of at least one content and the properties collection of at least one Composition of contents Breath, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
According to the third aspect of the application, a kind of methods of exhibiting of product is proposed, is applied to presentation device, the method Include:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that row according at least one product Order parameter, at least one content parameters sortnig carry out hybrid-sorting and obtain；
Show the hybrid-sorting result.
According to the fourth aspect of the application, a kind of searching method is proposed, described search method is applied to a client, packet It includes:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained The attribute information of at least one product, the attribute information for the product set that at least one described product is constituted, at least one content Attribute information and at least one Composition of contents properties collection attribute information, at least one described content and more A product is associated；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
According to the 5th of the application the aspect, a kind of server is proposed, comprising:
Product attribute obtains module, for obtaining the attribute information and at least one described product of at least one product The attribute information of the product set of composition；
Contents attribute obtain module, for obtain at least one content attribute information and at least one described content The attribute information of the properties collection of composition, at least one described content are associated with multiple products；
Attribute information mapping block, for by the attribute of the attribute information of at least one product, at least one content Information MAP obtains mapping result to the same space；
Gather weight determination module, for according to the attribute information of the product set and the attribute of the properties collection Information determines the weight of the product set and the weight of the properties collection；
Hybrid-sorting module uses institute for the weight of weight and the properties collection based on the product set It states mapping result and hybrid-sorting is carried out at least one described product, at least one described content, obtain hybrid-sorting result.
According to the 6th of the application the aspect, a kind of client is proposed, comprising:
Search term acquisition module, for acquiring the search term of user's input；
Search term sending module, for described search word to be sent to a server, so that the server is according to Search term scans for, and obtains the attribute information of at least one product, the category for the product set that at least one described product is constituted The attribute information of the properties collection of property information, the attribute information of at least one content and at least one Composition of contents, institute It is associated with multiple products to state at least one content；
Ordering structure receiving module, the hybrid-sorting result returned for receiving the server；
Ranking results display module, for being shown using the hybrid-sorting result as search result.
According to the 7th of the application the aspect, a kind of search system is proposed, described search system includes client and clothes Business device,
The client is used for: described search word is sent to the server by the search term of acquisition user's input；
The server is used for: it is scanned for according to described search word, obtains the attribute information of at least one product, it is described At least one product constitute product set attribute information, the attribute information of at least one content and it is described at least one The attribute information of the properties collection of Composition of contents, by the attribute information of at least one product, the attribute of at least one content Information MAP obtains mapping result to the same space, according to the attribute information of the product set and the properties collection Attribute information determines the weight of the product set and the weight of the properties collection, the weight based on the product set with And the weight of the properties collection, at least one described product, at least one described content are carried out using the mapping result Hybrid-sorting obtains hybrid-sorting as a result, at least one described content is associated with multiple products；
The client is also used to: receiving the hybrid-sorting of the server return as a result, by the hybrid-sorting result It is shown as search result.
According to the eighth aspect of the application, a kind of presentation device is proposed, comprising:
Ranking results receiving module, for receiving the hybrid-sorting of server output as a result, the hybrid-sorting result It is to carry out hybrid-sorting according to the parameters sortnig of at least one product, the parameters sortnig of at least one content to obtain；
Display module, for showing the hybrid-sorting result.
According to the 9th of the application the aspect, a kind of display systems, including server and presentation device are proposed,
Wherein, the server is used for: obtaining the attribute information and at least one described product structure of at least one product At product set attribute information；Obtain the attribute information and at least one Composition of contents of at least one content The attribute information of properties collection, at least one described content are associated with multiple products；By the attribute of at least one product Information, at least one content attribute information be mapped to the same space, obtain mapping result；According to the attribute of the product set The attribute information of information and the properties collection determines the weight of the product set and the weight of the properties collection；Base In the weight of the product set and the weight of the properties collection, using the mapping result at least one described production Product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
The presentation device is used for: receiving the hybrid-sorting of the server output as a result, showing the hybrid-sorting knot Fruit.
According to the tenth of the application the aspect, a kind of calculating equipment is proposed, the calculating equipment includes: to be adapted for carrying out each finger The processor and storage equipment of order, the storage equipment are stored with a plurality of instruction, and described instruction is suitable for by processor load simultaneously It executes:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, at least one described product structure At product set attribute information, the content of the attribute information of at least one content and at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
On the one hand according to the tenth of the application the, a kind of calculating equipment is proposed, the calculating equipment includes: to be adapted for carrying out respectively The processor and storage equipment of instruction, the storage equipment are stored with a plurality of instruction, and described instruction is suitable for being loaded by processor And it executes:
The attribute letter for the product set that the attribute information and at least one described product for obtaining at least one product are constituted Breath；
Obtain the attribute letter of the attribute information of at least one content and the properties collection of at least one Composition of contents Breath, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
According to the 12nd of the application the aspect, a kind of calculating equipment is proposed, the calculating equipment includes: to be adapted for carrying out respectively The processor and storage equipment of instruction, the storage equipment are stored with a plurality of instruction, and described instruction is suitable for being loaded by processor And it executes:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that row according at least one product Order parameter, at least one content parameters sortnig carry out hybrid-sorting and obtain；
Show the hybrid-sorting result.
According to the 13rd of the application the aspect, a kind of calculating equipment is proposed, the calculating equipment includes: to be adapted for carrying out respectively The processor and storage equipment of instruction, the storage equipment are stored with a plurality of instruction, and described instruction is suitable for being loaded by processor And it executes:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained The attribute information of at least one product, the attribute information for the product set that at least one described product is constituted, at least one content Attribute information and at least one Composition of contents properties collection attribute information, at least one described content and more A product is associated；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
According to the fourteenth aspect of the application, a kind of computer readable storage medium is proposed, it is described computer-readable to deposit Storage media is stored with computer program, and the computer program is for executing:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, at least one described product structure At product set attribute information, the content of the attribute information of at least one content and at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
According to the 15th of the application aspect, a kind of computer readable storage medium is proposed, it is described computer-readable to deposit Storage media is stored with computer program, and the computer program is for executing:
The attribute letter for the product set that the attribute information and at least one described product for obtaining at least one product are constituted Breath；
Obtain the attribute letter of the attribute information of at least one content and the properties collection of at least one Composition of contents Breath, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
According to the 16th of the application aspect, a kind of computer readable storage medium is proposed, it is described computer-readable to deposit Storage media is stored with computer program, and the computer program is for executing:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that row according at least one product Order parameter, at least one content parameters sortnig carry out hybrid-sorting and obtain；
Show the hybrid-sorting result.
According to the 17th of the application aspect, a kind of computer readable storage medium is proposed, it is described computer-readable to deposit Storage media is stored with computer program, and the computer program is for executing:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained The attribute information of at least one product, the attribute information for the product set that at least one described product is constituted, at least one content Attribute information and at least one Composition of contents properties collection attribute information, at least one described content and more A product is associated；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
By above technical scheme as it can be seen that the application is by by product, content map to the same space, difference is shielded with this Difference of the isomeric data on hybrid-sorting, it is subsequent to be shown on the displaying position of product shelf according to hybrid-sorting result, Realize the optimization under unified goal.
For the above and other objects, features and advantages of the application can be clearer and more comprehensible, preferred embodiment is cited below particularly, And cooperate institute's accompanying drawings, it is described in detail below.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this The some embodiments recorded in application, for those of ordinary skill in the art, in the premise of not making the creative labor property Under, it is also possible to obtain other drawings based on these drawings.
Fig. 1 shows the schematic diagram of product shelf example after fixed hole sequence in the prior art；
Fig. 2 shows a kind of structural schematic diagrams of search system of the application；
Fig. 3 shows the interaction schematic diagram in a kind of search system of the application between client and server；
Fig. 4 shows a kind of structural schematic diagram of server of the application；
Fig. 5 shows a kind of structural schematic diagram of client of the application；
Fig. 6 shows a kind of structural schematic diagram of display systems of the application；
Fig. 7 shows the interaction schematic diagram in a kind of display systems of the application between server and presentation device；
Fig. 8 shows a kind of structural schematic diagram of presentation device of the application；
Fig. 9 shows a kind of flow diagram of searching method of the application；
Figure 10 shows a kind of flow diagram of hybrid-sorting method of the application；
Figure 11 shows the flow diagram that a kind of hybrid-sorting method client of the application is surveyed；
Figure 12 shows a kind of flow diagram of the methods of exhibiting of product of the application；
Figure 13 show in one specific embodiment of the application calculate product, content parameters sortnig network structure.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall in the protection scope of this application.
Below with reference to several representative embodiments of the application, the principle and spirit of the application are illustrated in detail.
Although being based on this application provides as the following examples or method operating procedure shown in the drawings or apparatus structure Routine may include more or less operating procedure or mould in the method or device without creative labor Module unit.In the step of there is no necessary causalities in logicality or structure, the execution sequences of these steps or device Modular structure is not limited to the embodiment of the present application or execution shown in the drawings sequence or modular structure.The method or modular structure Device in practice or end product in application, can according to embodiment or method shown in the drawings or modular structure into Row sequence executes or parallel execution.
As shown in Figure 1, networking products generally comprise product and general product, general production on the website of the prior art or in App It is (as shown in Figure 1 to buy one and present one that product are generally referred to as brand group (certain brand milk powder that quick-fried product land vertically as shown in figure 1) or theme Edible oil theme), product refers to single product (feeding bottle as shown in figure 1).Product in the prior art and general product exhibition Show when several on product shelf show positions, or be inserted into certain several hole position for general product is equally spaced, or launches different The mixed proportion of the product of ratio and general product, such sortord are not adapted dynamically the ratio of product and general product to expire The demand of sufficient different crowd.
Specifically, due to the development of business, the diversification of exhibition method is related to when introducing brand hole by single-item hole before Fusion and showing problem to isomeric data, moreover, single-item and brand belong to unused engine, ranking score is not comparable, I.e. the data source of isomery can not accomplish that ranking score is comparable.Such as: the score and particular commodity of the brand group in Fig. 1 are (such as Feeding bottle) score, the two scores are not the sequences point of dimension, even if a sequence point of the sequence point of brand group higher than commodity, It can not illustrate that this brand group should just come before this commodity, because the two scores are points of heterogeneous data source Number, can not directly be compared.Therefore, it is necessary to a kind of general frames to shield the difference on score, under unified goal into Row optimization.
In view of this, the invention also provides a kind of search system, Fig. 2 shows the structural schematic diagram of the search system, Referring to Fig. 2, the search system includes client 100 and server 200.Fig. 3 show in search system client and Interaction schematic diagram between server, referring to Fig. 3, in this application:
The client is used for: described search word is sent to the server by the search term of acquisition user's input；
The server is scanned for according to described search word, obtains the attribute information of at least one product, it is described at least The attribute information for the product set that one product is constituted, the attribute information of at least one content and at least one described content The attribute information of the properties collection of composition, at least one described content are associated with multiple products.
In a kind of embodiment of the application, the product can be commodity (feeding bottle of example as shown in figure 1), service, interior Hold (such as content product on today's tops), data (such as audio and video equipment) etc..The data are to embody the domain feature Data.For example, in the field of communications, data can be communication data；In news media field, data can be news number According to.Content is associated with multiple products, and all edible oil themes bought one and present one as shown in figure 1 are associated with a plurality of edible oils.
To make those skilled in the art more fully understand the application, in the specific embodiment of the application, with e-commerce It is illustrated for field.In this embodiment, there are multiple contents, all for example brand groups of content, each brand in properties collection Group is associated with multiple commodity.There are multiple products in product set, each product is a commodity.
In a kind of embodiment of the application, the attribute information of the attribute information of the product and the content is characterized At least one following information: title, size, weight, material, purposes, price, applicable object and exchange hand, and these attributes Information is real-time change.In the particular embodiment, when user buys, some product is relatively more, then in the attribute of the product In information, the attribute information of the exchange hand of characterization user's purchase will become larger.When user buy certain brand group it is relatively more, then In the attribute information of the content, the attribute information of the exchange hand of characterization user's purchase will become larger.
In a kind of embodiment of the application, the attribute information of the product set and the attribute of the properties collection At least one following information of information representation: the similarity between the number of product, the accounting of product and product, and these attributes Information is real-time change.
The attribute information of the attribute information of at least one product, at least one content is mapped to same sky by server Between, obtain mapping result.
It, will at least one described production by deep learning network or linear classifier in a kind of embodiment of the application The attribute information of product maps to a space；By deep learning network or linear classifier by the attribute of at least one content Information MAP is to the space.
Server determines the production according to the attribute information of the product set and the attribute information of the properties collection The weight of the weight of product set and the properties collection, the power of weight and the properties collection based on the product set Weight carries out hybrid-sorting at least one described product, at least one described content using the mapping result, obtains mixing row Sequence result.
In a kind of embodiment of the application, the power of weight and the properties collection based on the product set Weight, obtains institute by weighted average calculation at least one described product, at least one described content using the mapping result The parameters sortnig of at least one product, the parameters sortnig of at least one content are stated, from big to small according to the parameters sortnig At least one described product, at least one described content are ranked up, hybrid-sorting result is obtained.
Server exports hybrid-sorting result to client；
Client is shown using the hybrid-sorting result as search result.
Therefore, search system provided by the present application receives the search term of user's input, server root by client first It is constituted according to attribute information, at least one described product that search term searches for obtain at least one corresponding product of different search terms The properties collection of the attribute information of product set, the attribute information of at least one content and at least one Composition of contents Attribute information, at least one described content is associated with multiple products, secondly server by the attribute information of at least one product, The attribute information of at least one content is mapped to the same space, with this come shield different isomerization data parameters sortnig calculating on Difference simultaneously calculates at least one product, the corresponding parameters sortnig of at least one content, is carried out according to calculated parameters sortnig Hybrid-sorting, and being shown by client, realizes when a user conducts a search, search result can adjust automatically content and The ratio of product maximizes the personalization preferences for meeting user.
Fig. 4 shows a kind of structural representation of server of the application, referring to Fig. 4, the server 200 includes:
Product attribute obtain module 201, for obtain at least one product attribute information and it is described at least one production The attribute information for the product set that product are constituted.
Contents attribute obtains module 202, for obtaining the attribute information of at least one content and described at least one Hold the attribute information of the properties collection constituted, at least one described content is associated with multiple products.
Attribute information mapping block 203, for by the category of the attribute information of at least one product, at least one content Property information MAP obtains mapping result to the same space.
In a kind of embodiment of the application, as shown in figure 13, attribute information mapping block 203 includes:
Product attribute mapping block 21, at least one product by described in by deep learning network or linear classifier Attribute information map to a space, in Figure 13, D1 be product set, d1 be D1 a product attribute information.
Contents attribute mapping block 22, at least one content by described in by deep learning network or linear classifier Attribute information map to the space, so realize the category of the attribute information of at least one product, at least one content Property information MAP is to the same space.
Referring to Fig. 4, the server 200 further include:
Gather weight determination module 203, for according to the attribute information of the product set and the properties collection Attribute information determines the weight of the product set and the weight of the properties collection.
Hybrid-sorting module 204 is used for the weight of weight and the properties collection based on the product set The mapping result carries out hybrid-sorting at least one described product, at least one described content, obtains hybrid-sorting result.
In a kind of embodiment of the application, the hybrid-sorting module includes: parameters sortnig computing module, is used for base In the weight of the product set and the weight of the properties collection, using the mapping result at least one described production Product, at least one described content by weighted average calculation obtain at least one product parameters sortnig, described at least one The parameters sortnig of a content；Ranking results determining module, for according to the parameters sortnig from big to small to it is described at least one Product, at least one described content are ranked up, and obtain hybrid-sorting result.
In the embodiment shown in fig. 13, D1 is a product set, and D2 is properties collection, it is assumed that it is a brand group, A pile commodity are set forth below in each brand.D1, d2 are respectively an attribute of an element information of D1, D2, if d1 is one of D1 The attribute information of product, for describing what kind of product this product is.Z1, z2 are the attribute informations of set D1, D2, The characteristics of indicating this set.For example, for example assume there is 2 80 pieces of commodity, 8 40 pieces of commodity inside D1, in D2 4 sections of commodity of 2 section commodity of the bread containing Adidas, Nike, then the material of one of them in all for example 2 80 pieces of the commodity of d1 Matter, the accounting of all for example products of z1, is expressed as z1={ 0.2,0.8 }, i.e., the accounting of 80 pieces commodity is accounting for for 0.2,40 pieces of commodity Than being 0.8.The sales volume of all for example 2 sections Adidas commodity of d2, z2={ 1/3,2/3 } indicate that Adidas accounting is 1/3, resistance to It gram is 2/3.
In the specific embodiment shown in Figure 13, the network on the left side is known as networking component system of giving a mark, and the right is known as controlling Networking component system processed.Product attribute mapping block 21 passes through deep learning network or linear classifier for the attribute information of product A space is mapped to, contents attribute mapping block 22 is reflected the attribute information of content by deep learning network or linear classifier It is incident upon the space, is so realized the attribute information of product and the maps feature vectors of content to the same space, thereafter Product set and the corresponding weight of properties collection are determined by gathering weight determination module, and last parameters sortnig calculates Module obtains the corresponding parameters sortnig of the product by weighted average calculation.Specifically, the network architecture system includes two layers, First layer assembly believes the attribute of the content in the attribute information and properties collection of the product in each different product set Breath is mapped to the same space, obtains mapping result, such as may make score all to normalize to [0,1], then the second layer assembly Properties collection and the different weighted value of product set are assigned respectively, will finally combine the result of first layer and the weight of the second layer Value calculates last parameters sortnig, this parameter will determine final decision (sequence, displaying etc.).
Assuming that using SdTo indicate final products and the score of content after weighting, then in one embodiment, product attribute Mapping block, contents attribute mapping block are implementableIt is implementable to gather weight determination moduleThen root According to Figure 13, final products after weighting and the score of content can be calculated are as follows:
In above formula, k indicates the number and a of properties collection and product setkIndicate properties collection and product set Weight,It is a mapping function, effect is by attribute informationIt is mapped to the value of one [0,1]. It may be considered a majorized function.In the other embodiments of the application, it can also pass through other Function come implement product attribute mapping block, contents attribute mapping block and set weight determination module.
It is fitted in this embodiment with deep neural network DNNIt can equally be learnt with DNN each ak.For the convenience realized, a can be learnt with linear classifier linear functionk。
As described above, this application provides a kind of general frames to shield the difference on score, under unified goal into Row optimization, specifically, product attribute mapping block, contents attribute mapping block different types of attribute information is mapped to it is same Space, set weight determination module determines the corresponding weight of each set, and calculates product and the corresponding sequence of content Parameter, with this come shield different isomerization data parameters sortnig calculating on difference, it is subsequent according to calculated parameters sortnig into Row hybrid-sorting is simultaneously shown by client, realizes the ratio of adjust automatically product and content, maximizes the individual character for meeting user Change preference.In a kind of embodiment of the application, the server further includes ranking results output module, described for exporting Hybrid-sorting result is to a presentation device, so that presentation device is shown according to the hybrid-sorting result.
Fig. 5 shows a kind of structural schematic diagram of client of the application, referring to Fig. 5, the client includes:
Search term acquisition module 101, for acquiring the search term of user's input；
Search term sending module 102, for described search word to be sent to a server, so that the server is according to institute It states search term to scan for, obtains the attribute information of at least one product, the product set that at least one described product is constituted The attribute information of the properties collection of attribute information, the attribute information of at least one content and at least one Composition of contents, At least one described content is associated with multiple products；
Ordering structure receiving module 103, the hybrid-sorting result returned for receiving the server；
Ranking results display module 104, for being shown using the hybrid-sorting result as search result.
The invention also provides a kind of display systems, as shown in fig. 6, the display systems include server 200 and show Equipment 300.Fig. 7 shows the interaction schematic diagram in a kind of display systems of the application between server and presentation device, please join Fig. 7 is read, in this application:
The server is used for: what the attribute information and at least one described product for obtaining at least one product were constituted The attribute information of product set；Obtain the attribute information of at least one content and the content of at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；By the attribute information of at least one product, The attribute information of at least one content is mapped to the same space, obtains mapping result；According to the attribute information of the product set And the attribute information of the properties collection determines the weight of the product set and the weight of the properties collection；Based on institute The weight of product set and the weight of the properties collection are stated, using the mapping result at least one described product, institute It states at least one content and carries out hybrid-sorting, obtain hybrid-sorting result.
In a kind of embodiment of the application, the product can be commodity (feeding bottle of example as shown in figure 1), service, interior Hold (such as content product on today's tops), data (such as audio and video equipment) etc..The data are to embody the domain feature Data.For example, in the field of communications, data can be communication data；In news media field, data can be news number According to；In the field e-commerce (Electronic Commerce, EC), data can be commodity etc..Content and multiple product phases Association, all edible oil themes bought one and present one as shown in figure 1.
To make those skilled in the art more fully understand the application, in the specific embodiment of the application, with e-commerce It is illustrated for field.In this embodiment, there are multiple contents, all for example brand groups of content, each brand in properties collection Group is related to multiple commodity.There are multiple products in product set, each product is a commodity.
In a kind of embodiment of the application, the attribute information of the attribute information of the product and the content is characterized At least one following information: title, size, weight, material, purposes, price, applicable object and exchange hand, and these attributes Information is real-time change.In the particular embodiment, when user buys, some product is relatively more, then in the attribute of the product In information, the attribute information of the exchange hand of characterization user's purchase will become larger.When user buy certain brand group it is relatively more, then In the attribute information of the content, the attribute information of the exchange hand of characterization user's purchase will become larger.
In a kind of embodiment of the application, the attribute information of the product set and the attribute of the properties collection At least one following information of information representation: the similarity between the number of product, the accounting of product and product, and these attributes Information is real-time change.
It, will at least one described production by deep learning network or linear classifier in a kind of embodiment of the application The attribute information of product maps to a space；By deep learning network or linear classifier by the attribute of at least one content Information MAP is to the space.
In a kind of embodiment of the application, the power of weight and the properties collection based on the product set Weight, obtains institute by weighted average calculation at least one described product, at least one described content using the mapping result The parameters sortnig of at least one product, the parameters sortnig of at least one content are stated, from big to small according to the parameters sortnig At least one described product, at least one described content are ranked up, hybrid-sorting result is obtained.
The presentation device is used for: receiving the hybrid-sorting of the server output as a result, showing the hybrid-sorting knot Fruit.
In a kind of embodiment of the application, presentation device by the hybrid-sorting result it is corresponding at least one production Product, at least one content are shown in showing position.
Therefore, display systems provided by the present application are obtained by server real according to the different service conditions of user first The attribute information, at least for the product set that the attribute information of at least one product of Shi Gengxin, at least one described product are constituted The attribute information of the properties collection of the attribute information and at least one Composition of contents of one content, it is described at least one Hold associated with multiple products, next server is by the attribute information of at least one product, the attribute information of at least one content Be mapped to the same space, with this come shield different isomerization data parameters sortnig calculating on difference and calculate at least one production Product, the corresponding parameters sortnig of at least one content carry out hybrid-sorting according to calculated parameters sortnig, and by presentation device exhibition Show on the displaying position of product shelf, realize the ratio of adjust automatically business datum and business datum group, maximizes to meet and use The personalization preferences at family.
Fig. 8 shows a kind of structural schematic diagram of presentation device of the application, referring to Fig. 8, the presentation device 300 wraps It includes:
Ranking results receiving module 301, for receiving the hybrid-sorting of server output as a result, the hybrid-sorting knot Fruit is to carry out hybrid-sorting according to the parameters sortnig of at least one product, the parameters sortnig of at least one content to obtain；
Display module 302, for showing the hybrid-sorting result.
In a kind of embodiment of the application, the display module is used for the corresponding product of the hybrid-sorting result It is shown in showing position.
In a kind of embodiment of the application, due to attribute information real-time change, server is carried out according to attribute information The ranking results of hybrid-sorting also real-time change realizes for showing the product being shown in position and content according to user Property behavior real-time change, the ratio of adjust automatically product and content maximizes and meets the personalization preferences of user.
Present invention also provides a kind of calculating equipment, it is described calculate equipment include: be adapted for carrying out the processor of each instruction with And storage equipment, the storage equipment are stored with a plurality of instruction, described instruction is suitable for being loaded and being executed by processor:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, at least one described product structure At product set attribute information, the content of the attribute information of at least one content and at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
Present invention also provides a kind of calculating equipment, it is described calculate equipment include: be adapted for carrying out the processor of each instruction with And storage equipment, the storage equipment are stored with a plurality of instruction, described instruction is suitable for being loaded and being executed by processor:
The attribute letter for the product set that the attribute information and at least one described product for obtaining at least one product are constituted Breath；
Obtain the attribute letter of the attribute information of at least one content and the properties collection of at least one Composition of contents Breath, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
Present invention also provides a kind of calculating equipment, comprising: is adapted for carrying out the processor and storage equipment of each instruction, institute It states storage equipment and is stored with a plurality of instruction, described instruction is suitable for being loaded and being executed by processor:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that row according at least one product Order parameter, at least one content parameters sortnig carry out hybrid-sorting and obtain；
Show the hybrid-sorting result.
Present invention also provides a kind of calculating equipment, comprising: is adapted for carrying out the processor and storage equipment of each instruction, institute It states storage equipment and is stored with a plurality of instruction, described instruction is suitable for being loaded and being executed by processor:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained The attribute information of at least one product, the attribute information for the product set that at least one described product is constituted, at least one content Attribute information and at least one Composition of contents properties collection attribute information, at least one described content and more A product is associated；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
Present invention also provides a kind of computer readable storage mediums, are stored with computer program, the computer program For executing:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, at least one described product structure At product set attribute information, the content of the attribute information of at least one content and at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
Present invention also provides a kind of computer readable storage mediums, are stored with computer program, the computer program For executing:
The attribute letter for the product set that the attribute information and at least one described product for obtaining at least one product are constituted Breath；
Obtain the attribute letter of the attribute information of at least one content and the properties collection of at least one Composition of contents Breath, at least one described content are associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is obtained To mapping result；
The product set is determined according to the attribute information of the attribute information of the product set and the properties collection Weight and the properties collection weight；
The weight of weight and the properties collection based on the product set, using the mapping result to it is described extremely A few product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
Present invention also provides a kind of computer readable storage mediums, are stored with computer program, the computer program For executing:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that row according at least one product Order parameter, at least one content parameters sortnig carry out hybrid-sorting and obtain；
Show the hybrid-sorting result.
Present invention also provides a kind of computer readable storage mediums, are stored with computer program, the computer program For executing:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained The attribute information of at least one product, the attribute information for the product set that at least one described product is constituted, at least one content Attribute information and at least one Composition of contents properties collection attribute information, at least one described content and more A product is associated；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
Describe the application server, client, presentation device, display systems, search system, calculate equipment and After computer readable storage medium, next, the present processes are introduced with reference to attached drawing.The implementation of this method can be with Referring to the implementation of above system, overlaps will not be repeated.
Fig. 9 shows a kind of flow diagram of searching method of the application, referring to Fig. 9, the described method includes:
S101: the search term of acquisition user's input.
S102: scanning for according to described search word, obtains the attribute information of at least one product, at least one described production The attribute information for the product set that product are constituted, the attribute information of at least one content and at least one Composition of contents The attribute information of properties collection, at least one described content are associated with multiple products.
In a kind of embodiment of the application, the attribute information of the attribute information of the product and the content is characterized At least one following information: title, size, weight, material, purposes, price, applicable object and exchange hand.The product collection The attribute information of the attribute information of conjunction and the properties collection characterizes at least one following information: the number of product, product Similarity between accounting, product
S103: the attribute information of the attribute information of at least one product, at least one content is mapped to same sky Between, obtain mapping result.
In a kind of embodiment of the application, which includes: by deep learning network or linear classifier by institute The attribute information for stating at least one product maps to a space；Through deep learning network or linear classifier at least one by described in The attribute information of a content maps to the space.
S104: the product is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of the weight of set and the properties collection.
S105: the weight of weight and the properties collection based on the product set uses the mapping result pair At least one described product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
In a kind of embodiment of the application, in which includes: weight based on the product set and is described The weight for holding set, passes through weighted average at least one described product, at least one described content using the mapping result The parameters sortnig of at least one product, the parameters sortnig of at least one content is calculated, joins according to the sequence Number is from big to small ranked up at least one described product, at least one described content, obtains hybrid-sorting result.
S106: it is shown using the hybrid-sorting result as search result.
Figure 10 shows a kind of flow diagram of hybrid-sorting method of the application, referring to Fig. 10, the described method includes:
S201: the product set that the attribute information and at least one described product for obtaining at least one product are constituted Attribute information；
S202: the attribute information of at least one content and the properties collection of at least one Composition of contents are obtained Attribute information, at least one described content are associated with multiple products；
S203: the attribute information of the attribute information of at least one product, at least one content is mapped to same sky Between, obtain mapping result.
In a kind of embodiment of the application, which includes: by deep learning network or linear classifier by institute The attribute information for stating at least one product maps to a space；Through deep learning network or linear classifier at least one by described in The attribute information of a content maps to the space.
S204: the product is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of the weight of set and the properties collection；
S205: the weight of weight and the properties collection based on the product set uses the mapping result pair At least one described product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
In a kind of embodiment of the application, in which includes: weight based on the product set and is described The weight for holding set, passes through weighted average at least one described product, at least one described content using the mapping result The parameters sortnig of at least one product, the parameters sortnig of at least one content is calculated, joins according to the sequence Number is from big to small ranked up at least one described product, at least one described content, obtains hybrid-sorting result.
Figure 11 shows the flow diagram that a kind of hybrid-sorting method client of the application is surveyed, and please refers to Figure 11, the party Method includes:
S301: the search term of acquisition user's input；
S302: being sent to a server for described search word, so that the server is scanned for according to described search word, Obtain the attribute information of at least one product, the attribute information for the product set that at least one described product is constituted, at least one The attribute information of the properties collection of the attribute information of content and at least one Composition of contents, at least one described content It is associated with multiple products；
S303: the hybrid-sorting result that the server returns is received；
S304: it is shown using the hybrid-sorting result as search result.
Figure 12 shows a kind of flow diagram of the methods of exhibiting of product of the application, please refers to Figure 12, this method comprises:
S401: receiving the hybrid-sorting of server output as a result, the hybrid-sorting is the result is that according at least one production The parameters sortnig of product, the parameters sortnig of at least one content carry out what hybrid-sorting obtained.
S402: the hybrid-sorting result is shown.
In a kind of embodiment of the application, the step is by the corresponding product of the hybrid-sorting result in showing position It is shown.
In a kind of embodiment of the application, due to attribute information real-time change, obtained according to attribute information Ranking results also real-time change realizes and shows that the product being shown in position, content are real-time according to the personalized behavior of user Variation realizes the ratio of adjust automatically product and content, maximizes the personalization preferences for meeting user.
It should be noted that although describing the operation of the method for the present invention in the accompanying drawings with particular order, this is not required that Or hint must execute these operations in this particular order, or have to carry out operation shown in whole and be just able to achieve the phase The result of prestige.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or will One step is decomposed into execution of multiple steps.
Although this application provides the method operating procedure as described in embodiment or flow chart, based on conventional or noninvasive The means for the property made may include more or less operating procedure.The step of enumerating in embodiment sequence is only numerous steps One of execution sequence mode, does not represent and unique executes sequence.It, can when device or client production in practice executes To execute or parallel execute (such as at parallel processor or multithreading according to embodiment or method shown in the drawings sequence The environment of reason, even distributed data processing environment).The terms "include", "comprise" or its any other variant are intended to contain Lid non-exclusive inclusion, so that process, method, product or equipment including a series of elements are not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, product or equipment Intrinsic element.In the absence of more restrictions, be not precluded include the process, method of the element, product or There is also other identical or equivalent elements in person's equipment.
Unit, device or module that above-described embodiment illustrates etc. can specifically realize by computer chip or entity, or It is realized by the product with certain function.For convenience of description, various modules point are divided into function when describing apparatus above It does not describe.It certainly, when implementing the application can the function of each module is real in the same or multiple software and or hardware It is existing, the module for realizing same function can also be realized by the combination of multiple submodule or subelement etc..Dress described above Set that embodiment is only schematical, for example, the division of the unit, only a kind of logical function partition, in actual implementation There may be another division manner, such as multiple units or components can be combined or can be integrated into another system or one A little features can be ignored, or not execute.Another point, shown or discussed mutual coupling or direct-coupling or communication link Connecing can be through some interfaces, the indirect coupling or communication connection of device or unit, can be electrical property, mechanical or other shapes Formula.
It is also known in the art that other than realizing controller in a manner of pure computer readable program code, it is complete Entirely can by by method and step carry out programming in logic come so that controller with logic gate, switch, specific integrated circuit, programmable Logic controller realizes identical function with the form for being embedded in microcontroller etc..Therefore this controller is considered one kind Hardware component, and the structure that the device for realizing various functions that its inside includes can also be considered as in hardware component.Or Person even, can will be considered as realizing the device of various functions either the software module of implementation method can be hardware again Structure in component.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, group Part, data structure, class etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments, By executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module can To be located in the local and remote computer storage media including storage equipment.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can It realizes by means of software and necessary general hardware platform.Based on this understanding, the technical solution essence of the application On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment (can be personal computer, mobile terminal, server or the network equipment etc.) executes each embodiment of the application or implementation Method described in certain parts of example.
Each embodiment in this specification is described in a progressive manner, the same or similar portion between each embodiment Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.The application can be used for crowd In mostly general or special purpose computing system environments or configuration.Such as: personal computer, server computer, handheld device or Portable device, laptop device, multicomputer system, microprocessor-based system, set top box, programmable electronics set Standby, network PC, minicomputer, mainframe computer, distributed computing environment including any of the above system or equipment etc..
Although depicting the application by embodiment, it will be appreciated by the skilled addressee that the application there are many deformation and Variation is without departing from spirit herein, it is desirable to which the attached claims include these deformations and change without departing from the application's Spirit.

Claims (29)

1. a kind of searching method, which is characterized in that described search method is applied to a search system, comprising:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, what at least one described product was constituted The attribute information of product set, the properties collection of the attribute information of at least one content and at least one Composition of contents Attribute information, at least one described content is associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is reflected Penetrate result；
The power of the product set is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of weight and the properties collection；
The weight of weight and the properties collection based on the product set, using the mapping result to described at least one A product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
2. the method according to claim 1, wherein the attribute of the attribute information of the product and the content At least one following information of information representation: title, size, weight, material, purposes, price, applicable object and exchange hand.
3. according to the method described in claim 2, it is characterized in that, attribute information and the content set of the product set The attribute information of conjunction characterizes at least one following information: the number of product, the accounting of product, the similarity between product.
4. according to the method described in claim 3, it is characterized in that, by the attribute information of at least one product, at least one The attribute information of a content is mapped to the same space, and obtaining mapping result includes: by deep learning network or linear classifier The attribute information of at least one product is mapped into a space；It is described extremely by deep learning network or linear classifier general The attribute information of a few content maps to the space.
5. according to the method described in claim 4, it is characterized in that, weight and the content set based on the product set The weight of conjunction carries out hybrid-sorting at least one described product, at least one described content using the mapping result, obtains Hybrid-sorting result includes the weight of weight and the properties collection based on the product set, uses the mapping result The sequence of at least one product is obtained by weighted average calculation at least one described product, at least one described content The parameters sortnig of parameter, at least one content, according to the parameters sortnig from big to small at least one described product, institute It states at least one content to be ranked up, obtains hybrid-sorting result.
6. a kind of hybrid-sorting method, which is characterized in that the method is applied to a server, comprising:
The attribute information for the product set that the attribute information and at least one described product for obtaining at least one product are constituted；
The attribute information of the attribute information of at least one content and the properties collection of at least one Composition of contents is obtained, At least one described content is associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is reflected Penetrate result；
The power of the product set is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of weight and the properties collection；
The weight of weight and the properties collection based on the product set, using the mapping result to described at least one A product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
7. according to the method described in claim 6, it is characterized in that, by the attribute information of at least one product, at least one The attribute information of a content is mapped to the same space, and obtaining mapping result includes: by deep learning network or linear classifier The attribute information of at least one product is mapped into a space；It is described extremely by deep learning network or linear classifier general The attribute information of a few content maps to the space.
8. the method according to the description of claim 7 is characterized in that weight and the content set based on the product set The weight of conjunction carries out hybrid-sorting at least one described product, at least one described content using the mapping result, obtains Hybrid-sorting result includes the weight of weight and the properties collection based on the product set, uses the mapping result The sequence of at least one product is obtained by weighted average calculation at least one described product, at least one described content The parameters sortnig of parameter, at least one content, according to the parameters sortnig from big to small at least one described product, institute It states at least one content to be ranked up, obtains hybrid-sorting result.
9. according to the method described in claim 8, it is characterized in that, the method also includes exporting the hybrid-sorting result extremely One presentation device, so that presentation device is shown according to the hybrid-sorting result.
10. a kind of methods of exhibiting, which is characterized in that the method is applied to a presentation device, comprising:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that the sequence according at least one product is joined It counts, the parameters sortnig of at least one content carries out what hybrid-sorting obtained；
Show the hybrid-sorting result.
11. according to the method described in claim 10, it is characterized in that, showing that the hybrid-sorting result includes by the mixing At least one corresponding product of ranking results, at least one content are shown in showing position.
12. a kind of searching method, which is characterized in that described search method is applied to a client, comprising:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained at least The attribute information of one product, the attribute information for the product set that at least one described product is constituted, the category of at least one content Property information and at least one Composition of contents properties collection attribute information, at least one described content and multiple productions Condition association；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
13. a kind of server, which is characterized in that the server includes:
Product attribute obtains module, and the attribute information and at least one described product for obtaining at least one product are constituted Product set attribute information；
Contents attribute obtains module, for obtaining the attribute information and at least one described Composition of contents of at least one content Properties collection attribute information, at least one described content is associated with multiple products；
Attribute information mapping block, for by the attribute information of the attribute information of at least one product, at least one content It is mapped to the same space, obtains mapping result；
Gather weight determination module, for according to the attribute information of the product set and the attribute information of the properties collection Determine the weight of the product set and the weight of the properties collection；
Hybrid-sorting module is reflected for the weight of weight and the properties collection based on the product set using described It penetrates result and hybrid-sorting is carried out at least one described product, at least one described content, obtain hybrid-sorting result.
14. server according to claim 13, which is characterized in that the attribute information mapping block includes: product category Property mapping block, for being mapped to the attribute information of at least one product by deep learning network or linear classifier One space；Contents attribute mapping block, for passing through deep learning network or linear classifier at least one content Attribute information maps to the space.
15. server according to claim 14, which is characterized in that the hybrid-sorting module includes: parameters sortnig meter Module is calculated, for the weight of weight and the properties collection based on the product set, using the mapping result to institute State at least one product, at least one described content is joined by the sequence that weighted average calculation obtains at least one product The parameters sortnig of at least one several, described content；Ranking results determining module, for right from big to small according to the parameters sortnig At least one described product, at least one described content are ranked up, and obtain hybrid-sorting result.
16. server according to claim 15, which is characterized in that the server further includes ranking results output mould Block, for exporting the hybrid-sorting result to a presentation device, so that presentation device is carried out according to the hybrid-sorting result It shows.
17. a kind of client characterized by comprising
Search term acquisition module, for acquiring the search term of user's input；
Search term sending module, for described search word to be sent to a server, so that the server is according to described search Word scans for, and obtains the attribute information of at least one product, the attribute letter for the product set that at least one described product is constituted Breath, the attribute information of the properties collection of the attribute information of at least one content and at least one Composition of contents, it is described extremely A few content is associated with multiple products；
Ordering structure receiving module, the hybrid-sorting result returned for receiving the server；
Ranking results display module, for being shown using the hybrid-sorting result as search result.
18. a kind of search system, which is characterized in that described search system includes client and server,
The client is used for: described search word is sent to the server by the search term of acquisition user's input；
The server is used for: scanned for according to described search word, obtain the attribute information of at least one product, it is described at least The attribute information for the product set that one product is constituted, the attribute information of at least one content and at least one described content The attribute information of the properties collection of composition, by the attribute information of at least one product, the attribute information of at least one content It is mapped to the same space, obtains mapping result, according to the attribute information of the product set and the attribute of the properties collection Information determines the weight of the product set and the weight of the properties collection, weight and institute based on the product set The weight for stating properties collection mixes at least one described product, at least one described content using the mapping result Sequence, obtains hybrid-sorting as a result, at least one described content is associated with multiple products；
The client is also used to: receive the hybrid-sorting that the server returns as a result, using the hybrid-sorting result as Search result is shown.
19. a kind of presentation device, which is characterized in that the presentation device includes:
Ranking results receiving module, for receive a server output hybrid-sorting as a result, the hybrid-sorting the result is that according to Carry out what hybrid-sorting obtained according to the parameters sortnig of the parameters sortnig of at least one product, at least one content；
Display module, for showing the hybrid-sorting result.
20. presentation device according to claim 19, which is characterized in that the display module is used for the hybrid-sorting As a result at least one corresponding product, at least one content are shown in showing position.
21. a kind of display systems, which is characterized in that the display systems include server and presentation device,
Wherein, the server is used for: what the attribute information and at least one described product for obtaining at least one product were constituted The attribute information of product set；Obtain the attribute information of at least one content and the content of at least one Composition of contents The attribute information of set, at least one described content are associated with multiple products；By the attribute information of at least one product, The attribute information of at least one content is mapped to the same space, obtains mapping result；According to the attribute information of the product set And the attribute information of the properties collection determines the weight of the product set and the weight of the properties collection；Based on institute The weight of product set and the weight of the properties collection are stated, using the mapping result at least one described product, institute It states at least one content and carries out hybrid-sorting, obtain hybrid-sorting result；
The presentation device is used for: receiving the hybrid-sorting of the server output as a result, showing the hybrid-sorting result.
22. a kind of calculating equipment, which is characterized in that the calculating equipment includes: to be adapted for carrying out the processor of each instruction and deposit Equipment is stored up, the storage equipment is stored with a plurality of instruction, and described instruction is suitable for being loaded and being executed by processor:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, what at least one described product was constituted The attribute information of product set, the properties collection of the attribute information of at least one content and at least one Composition of contents Attribute information, at least one described content is associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is reflected Penetrate result；
The power of the product set is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of weight and the properties collection；
The weight of weight and the properties collection based on the product set, using the mapping result to described at least one A product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
23. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey Sequence, the computer program is for executing:
Acquire the search term of user's input；
It is scanned for according to described search word, obtains the attribute information of at least one product, what at least one described product was constituted The attribute information of product set, the properties collection of the attribute information of at least one content and at least one Composition of contents Attribute information, at least one described content is associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is reflected Penetrate result；
The power of the product set is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of weight and the properties collection；
The weight of weight and the properties collection based on the product set, using the mapping result to described at least one A product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result；
It is shown using the hybrid-sorting result as search result.
24. a kind of calculating equipment, which is characterized in that the calculating equipment includes: to be adapted for carrying out the processor of each instruction and deposit Equipment is stored up, the storage equipment is stored with a plurality of instruction, and described instruction is suitable for being loaded and being executed by processor:
The attribute information for the product set that the attribute information and at least one described product for obtaining at least one product are constituted；
The attribute information of the attribute information of at least one content and the properties collection of at least one Composition of contents is obtained, At least one described content is associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is reflected Penetrate result；
The power of the product set is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of weight and the properties collection；
The weight of weight and the properties collection based on the product set, using the mapping result to described at least one A product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
25. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey Sequence, the computer program is for executing:
The attribute information for the product set that the attribute information and at least one described product for obtaining at least one product are constituted；
The attribute information of the attribute information of at least one content and the properties collection of at least one Composition of contents is obtained, At least one described content is associated with multiple products；
The attribute information of the attribute information of at least one product, at least one content is mapped to the same space, is reflected Penetrate result；
The power of the product set is determined according to the attribute information of the attribute information of the product set and the properties collection The weight of weight and the properties collection；
The weight of weight and the properties collection based on the product set, using the mapping result to described at least one A product, at least one described content carry out hybrid-sorting, obtain hybrid-sorting result.
26. a kind of calculating equipment, which is characterized in that the calculating equipment includes: to be adapted for carrying out the processor of each instruction and deposit Equipment is stored up, the storage equipment is stored with a plurality of instruction, and described instruction is suitable for being loaded and being executed by processor:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that the sequence according at least one product is joined It counts, the parameters sortnig of at least one content carries out what hybrid-sorting obtained；
Show the hybrid-sorting result.
27. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey Sequence, the computer program is for executing:
The hybrid-sorting of server output is received as a result, the hybrid-sorting is the result is that the sequence according at least one product is joined It counts, the parameters sortnig of at least one content carries out what hybrid-sorting obtained；
Show the hybrid-sorting result.
28. a kind of calculating equipment, which is characterized in that the calculating equipment includes: to be adapted for carrying out the processor of each instruction and deposit Equipment is stored up, the storage equipment is stored with a plurality of instruction, and described instruction is suitable for being loaded and being executed by processor:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained at least The attribute information of one product, the attribute information for the product set that at least one described product is constituted, the category of at least one content Property information and at least one Composition of contents properties collection attribute information, at least one described content and multiple productions Condition association；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
29. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey Sequence, the computer program is for executing:
Acquire the search term of user's input；
Described search word is sent to a server, so that the server is scanned for according to described search word, is obtained at least The attribute information of one product, the attribute information for the product set that at least one described product is constituted, the category of at least one content Property information and at least one Composition of contents properties collection attribute information, at least one described content and multiple productions Condition association；
Receive the hybrid-sorting result that the server returns；
It is shown using the hybrid-sorting result as search result.
CN201710860286.4A 2017-09-21 2017-09-21 A kind of searching method, hybrid-sorting method, equipment and system Pending CN110069696A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710860286.4A CN110069696A (en) 2017-09-21 2017-09-21 A kind of searching method, hybrid-sorting method, equipment and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710860286.4A CN110069696A (en) 2017-09-21 2017-09-21 A kind of searching method, hybrid-sorting method, equipment and system

Publications (1)

Publication Number Publication Date
CN110069696A true CN110069696A (en) 2019-07-30

Family

ID=67364452

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710860286.4A Pending CN110069696A (en) 2017-09-21 2017-09-21 A kind of searching method, hybrid-sorting method, equipment and system

Country Status (1)

Country Link
CN (1) CN110069696A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111563206A (en) * 2020-07-03 2020-08-21 北京每日优鲜电子商务有限公司 Article information sequence display method and device, electronic equipment and medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013153725A1 (en) * 2012-04-12 2013-10-17 日本電気株式会社 Data search device, data search method, and program for data search
CN106951508A (en) * 2017-03-16 2017-07-14 微鲸科技有限公司 A kind of many list ordering methods, device and electronic equipment
CN107122447A (en) * 2017-04-25 2017-09-01 南京邮电大学 The network searching system and control method of a kind of multi-data source fusion based on preference

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013153725A1 (en) * 2012-04-12 2013-10-17 日本電気株式会社 Data search device, data search method, and program for data search
CN106951508A (en) * 2017-03-16 2017-07-14 微鲸科技有限公司 A kind of many list ordering methods, device and electronic equipment
CN107122447A (en) * 2017-04-25 2017-09-01 南京邮电大学 The network searching system and control method of a kind of multi-data source fusion based on preference

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111563206A (en) * 2020-07-03 2020-08-21 北京每日优鲜电子商务有限公司 Article information sequence display method and device, electronic equipment and medium
CN111563206B (en) * 2020-07-03 2024-01-12 秦皇岛肆拾贰宇数字科技有限公司 Method, device, electronic equipment and medium for displaying object information sequence

Similar Documents

Publication Publication Date Title
US9607010B1 (en) Techniques for shape-based search of content
CN106791970A (en) The method and device of merchandise news is presented in video playback
US8296194B2 (en) Method, medium, and system for ranking dishes at eating establishments
CN111506849B (en) Page generation method and device
US8750625B2 (en) Image categorization based on comparisons between images
CN105135782B (en) A kind of Intelligent refrigerator management system based on Internet of Things
CN109447713A (en) A kind of recommended method and device of knowledge based map
US20140279232A1 (en) System and method for an affinity capture, user feedback and affinity analysis
CN108509466A (en) A kind of information recommendation method and device
CN110335123B (en) Commodity recommendation method, system, computer readable medium and device based on social e-commerce platform
CN106484766B (en) Searching method and device based on artificial intelligence
CN106227873A (en) Searching method and device
WO2017107797A1 (en) Method and device for displaying network products on product shelf
CN107527303A (en) A kind of rural tourism visualized recommendation method and system
CN106354855A (en) Recommendation method and system
CN108470377A (en) AR sees room device
CN111580788A (en) Template matching information recommendation method and device and electronic equipment
CN108090810A (en) A kind of Products Show system based on big data
CN108521366A (en) Expression method for pushing and electronic equipment
CN110069696A (en) A kind of searching method, hybrid-sorting method, equipment and system
CN111654714B (en) Information processing method, apparatus, electronic device and storage medium
CN111753180A (en) Search method, search device, electronic equipment and computer storage medium
CN104216945A (en) 4K picture management platform, information management method and downloading management method
CN105912549A (en) Content recommendation method and device thereof
CN107360468A (en) A kind of video push system and method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination