CN106547808A - Picture update method, classification sort method and device - Google Patents

Picture update method, classification sort method and device Download PDF

Info

Publication number
CN106547808A
CN106547808A CN201510917313.8A CN201510917313A CN106547808A CN 106547808 A CN106547808 A CN 106547808A CN 201510917313 A CN201510917313 A CN 201510917313A CN 106547808 A CN106547808 A CN 106547808A
Authority
CN
China
Prior art keywords
classification
picture
temperature
current
primary object
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
CN201510917313.8A
Other languages
Chinese (zh)
Inventor
何玉婵
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
Publication of CN106547808A publication Critical patent/CN106547808A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/958Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

This application discloses a kind of picture update method, classification sort method and device, the method is related to networking technology area.Including:Determine the temperature of the primary object that the current classification of the page includes;According to the first primary object for setting number is chosen in the primary object that temperature size includes from the current classification, the candidate target that the current classification includes is obtained;The picture of the candidate target is obtained, the picture set of the current classification is obtained;The picture that the entry position for updating the current classification according to the picture in the picture set of the current classification shows.The program can realize the picture for automatically updating the classification entry position displaying that the page includes, such that it is able to avoid by the way of artificial screening, and then save human resourcess, improve and update efficiency, especially in the case where the update cycle is shorter, optimal picture at the entry position of each classification can be supplied to user, lift Consumer's Experience.

Description

Picture update method, classification sort method and device
Technical field
The application is related to networking technology area, more particularly to a kind of picture update method, classification sort method and device.
Background technology
With developing rapidly for network technology, increasing user selects in online browsing information, watches video, chooses business Product etc., the page of website include multiple classifications, and these classifications can be the classification, or interim setting being fixedly installed Classification, such as during double 11, some classifications can be set temporarily and be easy to user to browse.In order to it is visual in image to The characteristics of family shows the object that each classification includes, it will usually arrange in the entry position of each classification and can represent classification spy The picture of point is shown, and the picture that the entry position of each classification is arranged can be fixed, it is also possible to periodically be updated.
According to related picture update method, the qualified picture in entry position that each classification is gone out by artificial screening first, Then the picture that the entry position for updating correspondence classification using the picture for filtering out shows.In the method, using artificial screening Mode screens the picture that the entry position of each classification shows, this needs to consume many human resourcess, and renewal efficiency is also very low, Especially in the case where the update cycle is shorter, it is impossible to which the optimal picture at the entry position of each classification is supplied to user, And then affect Consumer's Experience.
The content of the invention
The embodiment of the present application provides a kind of picture update method, classification sort method and device, to solve to deposit in correlation technique Update picture efficiency it is very low and affect Consumer's Experience problem.
According to the embodiment of the present application, there is provided a kind of picture update method, including:
Determine the temperature of the primary object that the current classification of the page includes;
According to the first primary object for setting number is chosen in the primary object that temperature size includes from the current classification, obtain The candidate target that the current classification includes;
The picture of the candidate target is obtained, the picture set of the current classification is obtained;
The picture that the entry position for updating the current classification according to the picture in the picture set of the current classification shows.
Specifically, determine the temperature of the primary object that the current classification of the page includes, specifically include:
Obtain the historical data in setting historical period;
The history feature information of the primary object that the current classification includes is counted according to the historical data;
The history feature information of each primary object that the current classification is included is brought in temperature model respectively, obtains correspondence The temperature of primary object.
Specifically, first is chosen in the primary object for including from the current classification according to temperature size and sets the original right of number As obtaining the candidate target that the current classification includes, specifically including:
The primary object that the current classification includes is ranked up according to temperature order from big to small, obtains the current class Purpose the first primary object sequence, starts selection described first from first primary object of the first primary object sequence and sets Determine the primary object of number, obtain the candidate target that the current classification includes;Or,
The primary object that the current classification includes is ranked up according to temperature order from small to large, obtains the current class Purpose the second primary object sequence, starts to choose described first from last primary object of the second primary object sequence The primary object of setting number, obtains the candidate target that the current classification includes.
Specifically, the picture of the candidate target is obtained, the picture set of the current classification is obtained, is specifically included:
Obtain the main picture and sub-pictures of the candidate target;
The picture of the first attribute information for meeting the current classification is filtered out from the main picture and sub-pictures for obtaining;
It is determined that whether the number of the picture for filtering out is more than the second setting number;
If the number of the picture for filtering out is more than the described second setting number, using the picture for filtering out as the current classification Picture set;
If the number of the picture for filtering out not less than described second setting number, from it is screened fall main picture and sub-pictures in obtain The picture for taking the second attribute information for meeting the current classification carries out picture processing, by the picture for filtering out and at picture Picture set of the picture of reason as the current classification.
Specifically, what the entry position for updating the current classification according to the picture in the picture set of the current classification showed Picture, specifically includes:
Picture in the picture set of the current classification is obtained successively with setting cycle;
The picture that the entry position that the picture for obtaining replaces the current classification is shown.
Optionally, also include:
Determine the temperature of the classification that the page includes;
The classification that the page includes is ranked up according to temperature size.
Specifically, determine the temperature of the classification that the page includes, specifically include:
Obtain the historical data of setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
Optionally, also include:
The access request that receive user sends;
Whether ID is carried in detecting the access request;
If ID is not carried in the access request, the step of perform the temperature of the classification for determining that the page includes.
Optionally, also include:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
Specifically, the corresponding preference classification of the ID is obtained, is specifically included:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
According to the embodiment of the present application, a kind of classification sort method is also provided, including:
Determine the temperature of the classification that the page includes;
The classification that the page includes is ranked up according to temperature size.
Specifically, determine the temperature of the classification that the page includes, specifically include:
Obtain the historical data in setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
Optionally, also include:
The access request that receive user sends;
Whether ID is carried in detecting the access request;
If ID is not carried in the access request, the step of perform the temperature of the classification for determining that the page includes.
Optionally, also include:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
Specifically, the corresponding preference classification of the ID is obtained, is specifically included:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
According to the embodiment of the present application, a kind of picture updating device is also provided, including:
First determining unit, for determining the temperature of primary object that the current classification of the page includes;
Unit is chosen, and number is set for first is chosen in the primary object that includes from the current classification according to temperature size Primary object, obtains the candidate target that the current classification includes;
Acquiring unit, for obtaining the picture of the candidate target, obtains the picture set of the current classification;
Updating block, updates the entry position of the current classification for the picture in the picture set according to the current classification The picture of displaying.
Specifically, first determining unit, for determining the temperature of primary object that the current classification of the page includes, specifically For:
Obtain the historical data in setting historical period;
The history feature information of the primary object that the current classification includes is counted according to the historical data;
The history feature information of each primary object that the current classification is included is brought in temperature model respectively, obtains correspondence The temperature of primary object.
Specifically, the selection unit, for choosing in the primary object that includes from the current classification according to temperature size The primary object of one setting number, obtains the candidate target that the current classification includes, specifically for:
The primary object that the current classification includes is ranked up according to temperature order from big to small, obtains the current class Purpose the first primary object sequence, starts selection described first from first primary object of the first primary object sequence and sets Determine the primary object of number, obtain the candidate target that the current classification includes;Or,
The primary object that the current classification includes is ranked up according to temperature order from small to large, obtains the current class Purpose the second primary object sequence, starts to choose described first from last primary object of the second primary object sequence The primary object of setting number, obtains the candidate target that the current classification includes.
Specifically, the acquiring unit, for obtaining the picture of the candidate target, obtains the pictures of the current classification Close, specifically for:
Obtain the main picture and sub-pictures of the candidate target;
The picture of the first attribute information for meeting the current classification is filtered out from the main picture and sub-pictures for obtaining;
It is determined that whether the number of the picture for filtering out is more than the second setting number;
If the number of the picture for filtering out is more than the described second setting number, using the picture for filtering out as the current classification Picture set;
If the number of the picture for filtering out not less than described second setting number, from it is screened fall main picture and sub-pictures in obtain The picture for taking the second attribute information for meeting the current classification carries out picture processing, by the picture for filtering out and at picture Picture set of the picture of reason as the current classification.
Specifically, the updating block, updates the current class for the picture in the picture set according to the current classification The picture that purpose entry position shows, specifically for:
Picture in the picture set of the current classification is obtained successively with setting cycle;
The picture that the entry position that the picture for obtaining replaces the current classification is shown.
Optionally, also include:
Second determining unit, for determining the temperature of classification that the page includes;
Sequencing unit, for being ranked up the classification that the page includes according to temperature size.
Specifically, second determining unit, for determining the temperature of classification that the page includes, specifically for:
Obtain the historical data of setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
Optionally, also include:
Receiving unit, for the access request that receive user sends;
Detector unit, for detecting in the access request whether carry ID;
Performance element, if for not carrying ID in the access request, turning to second determining unit.
Optionally, the performance element, is additionally operable to:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
Specifically, the performance element, for obtaining the corresponding preference classification of the ID, specifically for:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
According to the embodiment of the present application, a kind of classification collator is also provided, including:
Determining unit, for determining the temperature of classification that the page includes;
Sequencing unit, for being ranked up the classification that the page includes according to temperature size.
Specifically, the determining unit, for determining the temperature of classification that the page includes, specifically for:
Obtain the historical data in setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
Optionally, also include:
Receiving unit, for the access request that receive user sends;
Detector unit, for detecting in the access request whether carry ID;
Performance element, if for not carrying ID in the access request, turning to the determining unit.
Optionally, the performance element, is additionally operable to:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
Specifically, the performance element, for obtaining the corresponding preference classification of the ID, specifically for:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
According to the embodiment of the present application, a kind of picture update method is also provided, including:
The hot search keyword of same class purpose is obtained in setting time;
Extract the picture of the most fast-selling object that the class is matched with the hot search keyword now;
The picture of the most fast-selling object is updated into in the classification page master map position that correspondence classification shows.
Optionally, also include:
The quality of the picture of the most fast-selling object is audited, and when examination & verification passes through, is performed described most fast-selling by described in The step of picture of object updates in the classification page master map position that correspondence classification shows.
Optionally, also include:
Examination & verification not over when, extract the picture of time fast-selling object that the class match with the hot search keyword now;
The picture of described fast sale object is updated into in the classification page master map position that correspondence classification shows.
Specifically, it is characterised in that described to extract most fast-selling object that the class is matched with the hot search keyword now Picture, including:
Count the fetched data amount of fast-selling object under the hot search keyword;
The fetched data amount highest object is defined as into most fast-selling object;
The picture of most fast-selling object described in extracting.
Specifically, the same classification includes:Same class commodity or same class promote position.
According to the embodiment of the present application, a kind of picture updating device is also provided, including:
Acquiring unit, for the hot search keyword of same class purpose is obtained in setting time;
Extraction unit, for extracting the picture of the most fast-selling object that the class is matched with the hot search keyword now;
Updating block, updates in the classification page master map position that correspondence classification shows for the picture by the most fast-selling object.
Optionally, also include:
Examination & verification unit, for auditing to the quality of the picture;
The updating block, is additionally operable to when the examination & verification quality audit of the unit to the picture passes through, most fast-selling by described in The picture of object updates in the classification page master map position that correspondence classification shows.
Specifically, also include:
The extraction unit, be additionally operable to the examination & verification unit to the quality audit of the picture not over when, extract described The picture of time fast sale object that class is matched with the hot search keyword now;
The updating block, is additionally operable to for the picture of described fast sale object to update in the classification page master that correspondence classification shows Figure position.
Specifically, the extraction unit includes:
Statistic unit, for counting the fetched data amount of fast-selling object under the hot search keyword;
Determining unit, for the fetched data amount highest object is defined as most fast-selling object;
Subelement is extracted, for extracting the picture of the most fast-selling object.
Specifically, the described same classification that acquiring unit is obtained includes:Same class commodity or same class promote position.
The embodiment of the present application provides a kind of picture update method, classification sort method and device, determines the current classification bag of the page The temperature of the primary object for including;Number is set according to first is chosen in the primary object that temperature size includes from the current classification Primary object, obtain the candidate target that the current classification includes;The picture of the candidate target is obtained, described working as is obtained The picture set of front classification;The entry position of the current classification is updated according to the picture in the picture set of the current classification The picture of displaying.The program can realize the picture for automatically updating the classification entry position displaying that the page includes, such that it is able to keep away Exempt from by the way of artificial screening, and then save human resourcess, improve and update efficiency, it is especially shorter in the update cycle In the case of, the optimal picture at the entry position of each classification can be supplied to user, lift Consumer's Experience.
Description of the drawings
Accompanying drawing described herein is used for providing further understanding of the present application, constitutes the part of the application, the application's Schematic description and description does not constitute the improper restriction to the application for explaining the application.In the accompanying drawings:
Fig. 1 is a kind of flow chart of picture update method in the embodiment of the present application;
Fig. 2 is the flow chart of S11 in the embodiment of the present application;
Fig. 3 is the flow chart of S13 in the embodiment of the present application;
Fig. 4 is the flow chart of S14 in the embodiment of the present application;
Fig. 5 is a kind of flow chart of classification sort method in the embodiment of the present application;
Fig. 6 is the flow chart of S51 in the embodiment of the present application;
Fig. 7 is the flow chart of another kind of classification sort method in the embodiment of the present application;
Fig. 8 is the flow chart of S55 in the embodiment of the present application;
Fig. 9 is the flow chart of another kind of picture update method in the embodiment of the present application;
Figure 10 is a kind of structural representation of picture updating device in the embodiment of the present application;
Figure 11 is the structural representation of another kind of picture updating device in the embodiment of the present application;
Figure 12 is the structural representation of another kind of picture updating device in the embodiment of the present application;
Figure 13 is a kind of flow chart of classification collator in the embodiment of the present application;
Figure 14 is the structural representation of another kind of picture collator in the embodiment of the present application;
A kind of flow chart of picture update method that Figure 15 is provided for the embodiment of the present application;
A kind of another flow chart of picture update method that Figure 16 is provided for the embodiment of the present application;
A kind of schematic diagram of the displaying pattern of category list that Figure 17 is provided for the embodiment of the present application;
A kind of structural representation of picture updating device that Figure 18 is provided for the embodiment of the present application;
A kind of another structural representation of picture updating device that Figure 19 is provided for the embodiment of the present application;
Figure 20 provides a kind of structural representation of terminal unit for the embodiment of the present application.
Specific embodiment
In order that technical problems to be solved in this application, technical scheme and beneficial effect are clearer, clear, below in conjunction with Drawings and Examples, are further elaborated to the application.It should be appreciated that specific embodiment described herein is only To explain the application, it is not used to limit the application.
In order to solve the problems, such as that renewal picture efficiency is very low and affects Consumer's Experience, the application reality present in correlation technique Apply example and a kind of picture update method is provided, the method can be, but not limited to apply in the server of website, the flow process of the method As shown in figure 1, comprising the steps:
S11:Determine the temperature of the primary object that the current classification of the page includes.
One page of website would generally include multiple classifications, and these classifications can be the classifications that are fixedly installed, or face When the classification that arranges, for example, for page A, the classification being fixedly installed can be included:Clothing, case and bag, article of everyday use etc., The interim classification for arranging can also be included in double 11, New Year's Day, the Spring Festival etc. red-letter day:Double 11 main meeting-places, household electrical appliances main meeting-place Etc..
The classification for being currently needed for updating in one page the picture that entry position shows is referred to as current classification, in current classification generally Multiple objects can be included,, to liking the primary object that current classification includes, for example, this classification can include for clothing for these Multiple toggeries, for video, this classification can include multiple video resources, etc..Updating current classification entry position Picture when, select the picture for representing current classification feature in the picture of the primary object that can include from current classification, this When firstly the need of qualified primary object is picked out, specifically can be by determining the heat of primary object that current classification include Spend to realize.
S12:According to the first primary object for setting number is chosen in the primary object that temperature size includes from current classification, obtain The candidate target that current classification includes.
It is not that all primary objects that current classification includes all meet the requirements, current classification can be selected according to temperature size Including candidate target, the number of candidate target is the first setting number, and the first setting number can be carried out according to actual needs Setting.
S13:The picture of candidate target is obtained, the picture set of current classification is obtained.
S14:The picture that the entry position for updating current classification according to the picture in the picture set of current classification shows.
In order to enrich current classification entry position show picture, can adopt current classification picture set in picture according to It is secondary to update the picture that current classification entry position shows.
The program can realize the picture for automatically updating the classification entry position displaying that the page includes, such that it is able to avoid adopting people The mode of work screening, and then human resourcess are saved, improve and update efficiency, especially in the case where the update cycle is shorter, Optimal picture at the entry position of each classification can be supplied to user, lift Consumer's Experience.
Each step in above-mentioned picture update method is described in detail below.
Specifically, the temperature of the primary object that the current classification of the page includes, implementation such as Fig. 2 institutes are determined in above-mentioned S11 Show, specifically include following steps:
S111:Obtain the historical data in setting historical period.
Setting historical period can be set according to actual needs, for example, can be set as one week, two weeks, one month Etc..
S112:The history feature information of the primary object that current classification includes is counted according to historical data.
The history feature information of the primary object that current classification includes includes sales volume, amount of collection, click volume, pageview etc. One of or combination, can be set according to actual needs.
S113:The history feature information of each primary object that current classification is included is brought in temperature model respectively, obtains right Answer the temperature of primary object.
Existing temperature model, the history feature information of each primary object that current classification is included can be adopted to bring into respectively To in the temperature model, you can to obtain the temperature of correspondence primary object, for example, the temperature of the primary object for finally giving is 0.54th, 0.68,0.12 etc..
The temperature of each primary object that current classification includes is calculated, such that it is able to further select what current classification included Candidate target.
Specifically, first is chosen in the primary object for including from current classification according to temperature size in above-mentioned S12 and sets number Primary object, obtains the candidate target that current classification includes, specifically includes following two implementations:
The primary object that current classification includes is ranked up according to temperature order from big to small, is obtained by the first implementation To the first primary object sequence of current classification, start selection first from first primary object of the first primary object sequence and set Determine the primary object of number, obtain the candidate target that current classification includes.
The primary object that current classification includes is ranked up according to temperature order from small to large, is obtained by second implementation To the second primary object sequence of current classification, start selection first from last primary object of the second primary object sequence The primary object of setting number, obtains the candidate target that current classification includes.
Respectively according to temperature order from big to small and order from small to large in the first implementation and second implementation The primary object that current classification includes is ranked up, the first primary object for setting number is then chosen, it is current so as to obtain The candidate target that classification includes, can also obtain the candidate target that current classification includes using other modes, here not certainly Repeat again.
Specifically, the picture of candidate target is obtained in above-mentioned S13, the picture set of current classification is obtained, is realized process such as Fig. 3 It is shown, specifically include following steps:
S131:Obtain the main picture and sub-pictures of candidate target.
The object that generally each classification includes in website includes plurality of pictures, and for example, each object includes main picture and son Picture, when the picture set of candidate target is obtained, can obtain the main picture and sub-pictures of these candidate targets first, tool Body can be obtained from the data base of website.
S132:The picture of the first attribute information for meeting current classification is filtered out from the main picture and sub-pictures for obtaining.
First attribute information of current classification can be including the size of the entry position of current classification, background, word, main body etc. Deng one of or combination.
S133:It is determined that whether the number of the picture for filtering out is more than the second setting number, if the number of the picture for filtering out exceedes Second setting number, then perform S134;If the number of the picture for filtering out performs S135 not less than the second setting number.
Wherein, the second setting number can be set according to actual needs.
S134:Using the picture for filtering out as current classification picture set.
If the number of the picture for filtering out is more than the second setting number, that is to say, that got enough pictures, so as to sieve Picture set of all pictures selected as current classification.
S135:From it is screened fall main picture and sub-pictures in obtain the picture of the second attribute information that meets current classification and carry out Picture processing, using the picture for filtering out and through picture processing picture as current classification picture set.
If the number of the picture for filtering out is not less than the second setting number, that is to say, that do not get enough pictures, Ke Yicong It is screened fall main picture and sub-pictures in obtain the picture of the second attribute information for meeting current classification and carry out picture processing, will The picture that filters out and through picture processing picture as current classification picture set.
Wherein, the second attribute information can include one of master map condition of entry position, solid background of current classification etc. or Person combines.
Specifically, the figure that the entry position for updating current classification according to the picture in the picture set of current classification in S14 shows Piece, implementation is as shown in figure 4, specifically include following steps:
S141:Obtain the picture in the picture set of current classification with setting cycle successively.
S142:The picture that the entry position that the picture for obtaining replaces current classification is shown.
The picture that the entry position that current classification can be updated with setting cycle shows, so as to the entrance position for more enriching each classification The picture that place shows is put, Consumer's Experience is lifted.
Setting cycle can be set according to actual needs.
Picture update method is described above, based on same inventive concept, the embodiment of the present application also provides a kind of classification sequence side Method, the method can be not limited to using in the server, and the flow process of the method is as shown in figure 5, specifically include following steps:
S51:Determine the temperature of the classification that the page includes.
Multiple classifications would generally be included in the page of website, the temperature of the classification that each page includes can be determined successively.
S52:The classification that the page includes is ranked up according to temperature size.
In the program, the classification that the page includes can be ranked up according to temperature, in order to optimum classification sequence is provided To user, such that it is able to be easy to user to browse information, purchase commodity etc., user time is saved, Consumer's Experience is lifted.
Specifically, the temperature of classification that the page includes is determined in above-mentioned S51, realize process as shown in fig. 6, specifically include with Lower step:
S511:Obtain the historical data in setting historical period.
Setting historical period can be set according to actual needs, for example, can be set as one week, two weeks, one month Etc..
S512:It is original right that the history feature information and each classification that the classification that the page includes is counted according to historical data includes The history feature information of elephant.
The history feature information of the classification that the page includes includes one of volumes of searches, amount of collection, click volume etc. or combination, can To be set according to actual needs;The history feature information of the primary object that classification includes includes sales volume, amount of collection, point One of the amount of hitting, pageview etc. or combination, can be set according to actual needs.
S513:The history of the primary object that the history feature information and correspondence classification of each classification that the page is included includes is special Reference breath is brought in temperature model respectively, obtains the temperature of correspondence classification.
The temperature of each classification can be calculated using identical temperature model in S113.
The embodiment of the present application also provides another kind of classification sort method, and the flow process of the method is as shown in fig. 7, as shown in Figure 5 Method on the basis of, also include:
S53:The access request that receive user sends.
When user needs to access a website, it will usually send access request.
S54:ID is carried whether in test access request, if ID is not carried in access request, perform S51; If ID is carried in access request, S55 is performed.
The ID that user can register visits again website after logging in, it is also possible to which anonymous Identity accesses website, services utensil Body can be made a distinction by whether carrying ID in the access request.
If ID is not carried in access request, illustrate that user is website to be accessed with anonymous Identity, can perform S51.
S55:Obtain the corresponding preference classification of ID.
If ID is carried in access request, illustrate that user is that the identity to register accesses website, the user can be obtained Identify corresponding preference classification, that is, the preference classification for obtaining the user.
S56:Determine the temperature of preference classification.
The temperature of each classification can be calculated using identical temperature model in S113.
S57:Preference classification is ranked up according to temperature size.
S58:Preference classification after sequence is sent to into user.
User is sent to after be ranked up by the preference classification of user, due to directly entering classification user interested User is sent to after row sequence, is easy to user to browse classification interested, classification interested is searched for one by one without the need for user, from And lift Consumer's Experience.
Specifically, the corresponding preference classification of ID is obtained in above-mentioned S55, implementation is as shown in figure 8, specifically include Following steps:
S551:Obtain the historical data in setting historical period.
S552:The access times of the classification of association are identified according to historical data counting user.
All classifications that the ID was accessed are have recorded in historical data, these classifications can be counted according to historical data Access times.
S553:Access times are exceeded the classification of set point number as the corresponding preference classification of ID.
In the step, the corresponding preference classification of the ID is determined according to the size of access times, set point number can basis It is actually needed and is set, for example, is set as 10 times, 15 times, 20 times etc..
Below picture update method and classification sort method are described respectively, above-mentioned two method can also be combined, shape Into another kind of picture update method, the flow process of the method is as shown in figure 9, it should be noted that with above-mentioned two in the method In individual method, identical step is repeated no more.The method specifically includes following steps:
S91:The access request that receive user sends.
When user needs to access a website, it will usually send access request.
S92:ID is carried whether in test access request, if ID is not carried in access request, perform S95; If ID is carried in access request, S93 is performed.
The ID that user can register visits again website after logging in, it is also possible to which anonymous Identity accesses website, services utensil Body can be made a distinction by whether carrying ID in the access request.
S93:The historical data in setting historical period is obtained, the access of the classification of association is identified according to historical data counting user Number of times, access times are exceeded the classification of set point number as the corresponding preference classification of ID.
If ID is carried in access request, illustrate that user is that the identity to register accesses website, the user can be obtained Identify corresponding preference classification, that is, the preference classification for obtaining the user.Have recorded the ID to access in historical data The all classifications crossed, can count the access times of these classifications according to historical data.Set point number can be according to actual needs Set, for example, be set as 10 times, 15 times, 20 times etc..
S94:Determine the temperature of preference classification, preference classification is ranked up according to temperature size, by the preference classification after sequence User is sent to, S97 is performed.
The temperature of each classification can be calculated in this step and following steps using identical temperature model in S113.
User is sent to after be ranked up by the preference classification of user, due to directly entering classification user interested User is sent to after row sequence, is easy to user to browse classification interested, classification interested is searched for one by one without the need for user, from And lift Consumer's Experience.
S95:The historical data in setting historical period is obtained, the history feature of the classification that the page includes is counted according to historical data The history feature information of the primary object that information and each classification include, the history feature letter of each classification that the page is included The history feature information of the primary object that breath and correspondence classification include is brought in temperature model respectively, obtains the heat of correspondence classification Degree.
S96:The classification that the page includes is ranked up according to temperature size, the classification after sequence is sent to into user, perform S97.
If ID is not carried in access request, illustrate that user is website to be accessed with anonymous Identity, can be general by website Classification sequence is sent to user.
S97:Each classification for being sent to user, performs:The historical data in setting historical period is obtained, according to history The history feature information of the primary object that the current classification of data statisticss includes, each primary object that current classification is included are gone through History characteristic information is brought in temperature model respectively, obtains the temperature of correspondence primary object.
Select in the picture of the primary object that can include from current classification that to represent the picture of current classification feature current to update The picture that the entry position of classification shows, at this moment firstly the need of the temperature of primary object that current classification includes is determined realizing.
S98:According to the first primary object for setting number is chosen in the primary object that temperature size includes from current classification, obtain The candidate target that current classification includes.
S99:The main picture and sub-pictures of candidate target are obtained, is filtered out from the main picture and sub-pictures for obtaining and is met current class The picture of the first attribute information of purpose.
S100:It is determined that whether the number of the picture for filtering out is more than the second setting number, if the number of the picture for filtering out exceedes Second setting number, then perform S101;If the number of the picture for filtering out performs S102 not less than the second setting number.
S101:Using the picture for filtering out as the picture set of current classification, S103 is performed.
If the number of the picture for filtering out is more than the second setting number, that is to say, that got enough pictures, so as to sieve Picture set of all pictures selected as current classification.
S102:From it is screened fall main picture and sub-pictures in obtain the picture of the second attribute information that meets current classification and carry out Picture processing, using the picture for filtering out and through picture processing picture as current classification picture set, perform S103.
If the number of the picture for filtering out is not less than the second setting number, that is to say, that do not get enough pictures, Ke Yicong It is screened fall main picture and sub-pictures in obtain the picture of the second attribute information for meeting current classification and carry out picture processing, will The picture that filters out and through picture processing picture as current classification picture set.
S103:Obtain the picture in the picture set of current classification with setting cycle successively, the picture for obtaining is replaced into current class The picture that purpose entry position shows.
In order to enrich current classification entry position show picture, can adopt current classification picture set in picture according to It is secondary to update the picture that current classification entry position shows.
The program is based on the preference classification (User) of user, the temperature (Market) of classification and picture processing (Picture) The model of composition, abbreviation UMP models are realized from trend user pushing the classification of user preference, in order to by optimum classification Sequence is supplied to user, consequently facilitating user browses information, purchase commodity etc., saves user time, lifts Consumer's Experience; And, realization automatically updates the picture of the classification entry position displaying that the page includes, such that it is able to avoid using artificial screening Mode, and then human resourcess are saved, improve and update efficiency, especially in the case where the update cycle is shorter, can will be every Optimal picture at the entry position of individual classification is supplied to user, lifts Consumer's Experience.
Based on same inventive concept, the embodiment of the present application also provides a kind of picture updating device, the device with it is as shown in Figure 1 Method is corresponding, the structure of the device as illustrated in fig. 10, including:
First determining unit 101, for determining the temperature of primary object that the current classification of the page includes;
Unit 102 is chosen, for the first original for setting number is chosen in the primary object that includes from current classification according to temperature size Source object, obtains the candidate target that current classification includes;
Acquiring unit 103, for obtaining the picture of candidate target, obtains the picture set of current classification;
Updating block 104, what the entry position for updating current classification for the picture in the picture set according to current classification showed Picture.
The program can realize the picture for automatically updating the classification entry position displaying that the page includes, such that it is able to avoid adopting people The mode of work screening, and then human resourcess are saved, improve and update efficiency, especially in the case where the update cycle is shorter, Optimal picture at the entry position of each classification can be supplied to user, lift Consumer's Experience.
Specifically, the first determining unit 101 is for determining the temperature of primary object that the current classification of the page includes, concrete to use In:
Obtain the historical data in setting historical period;
The history feature information of the primary object that current classification includes is counted according to historical data;
The history feature information of each primary object that current classification is included is brought in temperature model respectively, obtains correspondence original The temperature of object.
Specifically, unit 102 is chosen, is set for first is chosen in the primary object that includes from current classification according to temperature size The primary object of number, obtains the candidate target that current classification includes, specifically for:
The primary object that current classification includes is ranked up according to temperature order from big to small, obtains the current classification First primary object sequence, starts to choose the original of the first setting number from first primary object of the first primary object sequence Object, obtains the candidate target that current classification includes;Or,
The primary object that current classification includes is ranked up according to temperature order from small to large, obtains the second of current classification Primary object sequence, starts to choose the original right of the first setting number from last primary object of the second primary object sequence As obtaining the candidate target that current classification includes.
Specifically, acquiring unit 103, for obtaining the picture of candidate target, obtain the picture set of current classification, concrete to use In:
Obtain the main picture and sub-pictures of candidate target;
The picture of the first attribute information for meeting current classification is filtered out from the main picture and sub-pictures for obtaining;
It is determined that whether the number of the picture for filtering out is more than the second setting number;
If the number of the picture for filtering out more than second setting number, using the picture for filtering out as current classification pictures Close;
If the number of the picture for filtering out not less than second setting number, from it is screened fall main picture and sub-pictures in obtain symbol Before being fated, the picture of the second attribute information of classification carries out picture processing, by the picture for filtering out and the picture through picture processing As the picture set of current classification.
Specifically, updating block 104, update the entrance position of current classification for the picture in the picture set according to current classification The picture of displaying is put, specifically for:
Obtain the picture in the picture set of current classification with setting cycle successively;
The picture that the entry position that the picture for obtaining replaces current classification is shown.
The embodiment of the present application also provides another kind of picture updating device, and the structure of the device as shown in figure 11, scheme with such as by the device In device shown in 10, identical unit omits not table, on the basis of device as shown in Figure 10, also includes:
Second determining unit 105, for determining the temperature of classification that the page includes;
Sequencing unit 106, for being ranked up the classification that the page includes according to temperature size.
Specifically, the second determining unit 105, for determining the temperature of classification that the page includes, specifically for:
Obtain the historical data of setting historical period;
Going through for the history feature information of classification that the page includes and the primary object that each classification including is counted according to historical data History characteristic information;
The history feature information of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Brought in temperature model respectively, obtain the temperature of correspondence classification.
The embodiment of the present application also provides another kind of picture updating device, and the structure of the device as shown in figure 12, scheme with such as by the device In device shown in 11, identical unit omits not table, on the basis of device as shown in figure 11, also includes:
Receiving unit 107, for the access request that receive user sends;
Detector unit 108, for whether carrying ID in test access request;
Performance element 109, if for not carrying ID in access request, turning to the second determining unit 105.
Optionally, performance element 109, are additionally operable to:
If ID is carried in access request, the corresponding preference classification of ID is obtained;
Determine the temperature of preference classification;
Preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into user.
Specifically, performance element 109, for obtaining the corresponding preference classification of ID, specifically for:
Obtain the historical data in setting historical period;
The access times of the classification of association are identified according to historical data counting user;
Access times are exceeded the classification of set point number as the corresponding preference classification of ID.
Based on same inventive concept, the embodiment of the present application also provides a kind of classification collator, the device with it is as shown in Figure 5 Method is corresponding, the structure of the device as shown in 13 figures, including:
Determining unit 131, for determining the temperature of classification that the page includes;
Sequencing unit 132, for being ranked up the classification that the page includes according to temperature size.
In the program, the classification that the page includes can be ranked up according to temperature, in order to optimum classification sequence is provided To user, such that it is able to be easy to user to browse information, purchase commodity etc., user time is saved, Consumer's Experience is lifted.
Specifically, determining unit 131, for determining the temperature of classification that the page includes, specifically for:
Obtain the historical data in setting historical period;
Going through for the history feature information of classification that the page includes and the primary object that each classification including is counted according to historical data History characteristic information;
The history feature information of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Brought in temperature model respectively, obtain the temperature of correspondence classification.
The embodiment of the present application also provides another kind of picture updating device, and the structure of the device as shown in figure 14, scheme with such as by the device In device shown in 13, identical unit omits not table, on the basis of device as shown in fig. 13 that, also includes:
Receiving unit 133, for the access request that receive user sends;
Detector unit 134, for whether carrying ID in test access request;
Performance element 135, if for ID is not carried in access request, turning to determining unit 131.
Optionally, performance element 135, are additionally operable to:
If ID is carried in access request, the corresponding preference classification of ID is obtained;
Determine the temperature of preference classification;
Preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into user.
Specifically, performance element 135, for obtaining the corresponding preference classification of ID, specifically for:
Obtain the historical data in setting historical period;
The access times of the classification of association are identified according to historical data counting user;
Access times are exceeded the classification of set point number as the corresponding preference classification of ID.
Figure 15 is referred to, a kind of flow chart of picture update method that Figure 15 is provided for the embodiment of the present application, methods described include:
Step 1501:The hot search keyword of same class purpose is obtained in setting time;
Wherein, setting time, can be arranged as needed, such as, could be arranged to 1 day, 2 days, or 5 days, or one Week etc.;It is of course also possible to be set to 2 hours, 5 hours etc..Or the hot search keyword of same class purpose is obtained in real time.
Same classification can be:Same class commodity, such as, women's dress etc., or same class promote position, such as, a certain Using popularization position etc..
In the step, if women's dress classification is searched in user's setting daily, system all can obtain women's dress classification daily automatically Hot search keyword, such as, women's dress class one-piece dress now etc. is searched in user's setting daily.
It should be noted that hot search keyword can be most hot search keyword, it is also possible to secondary hot search keyword, certainly, Can also be the hot search keyword of front three, or the hot search keyword of TOP V etc..Herein can be as needed Adaptability is arranged.
Step 1502:Extract the picture of the most fast-selling object that the class is matched with the hot search keyword now;
In the step, a kind of extracting mode is:The fetched data amount of fast-selling object under the hot search keyword is counted first; The fetched data amount highest object is defined as into most fast-selling object;The picture of most fast-selling object described in finally extracting.
In this embodiment, system is by counting the fetched data amount of fast-selling object, and according to the height of the conclusion of the business quantity successively Determine the fast-selling grade of object, it is generally lower to ask, the front three-level for determining fast-selling object is obtained, such as, by fast-selling grade 1 is exactly Fast-selling best object, secondly fast-selling grade 2 is exactly fast-selling somewhat more secondary object, fast-selling grade 3, be exactly fast sale again Object of any etc..It is of course also possible to determine several fast-selling grades, the present embodiment is not restricted more.
In the step, the present embodiment is by taking most hot key word as an example.If that is, the most hot search searched in step 1501 Key word is women's dress, then, the picture of the most fast-selling object under the women's dress can include:One-piece dress picture, is set with picture, T-shirt Picture, defends clothing picture, overcoat picture etc..The picture of most fast-selling object therein can be extracted in the step, such as, even Clothing skirt picture, or T-shirt picture, can also be and defend clothing picture, it is, of course, also possible to provide while extract plurality of picture, Such as, while extracting one-piece dress picture and suit picture etc..
Step 1503:The picture of the most fast-selling object is updated into in the classification page master map position that correspondence classification shows.
In the step, the picture of the most fast-selling object for extracting is replaced on the master map position that classification page correspondence classification shows Picture.
Wherein, the classification page, can be the original list of concrete object, such as, one-piece dress original list, or trousers Sublist page etc..
In the embodiment of the present application, system obtain based on the hot search keyword now of (as daily) same class in a period of time, And the picture of such fast-selling object for matching with the most hot search keyword now is extracted, then by the figure of the most fast-selling object Piece is updated in the classification page on the master map position of correspondence classification.That is, system automatically extracts picture, and periodic replacement Picture on master map position, to show the effective and popular of web object, lifts the captivation of web page contents, improves User searches the efficiency of web page contents, so as to more effectively using the value of picture.
Figure 16, a kind of another flow chart of picture update method that figure is provided for the embodiment of the present application, the embodiment are referred to also Difference with said method is, after the picture for extracting most fast-selling object, to judge whether the picture quality meets Require, if the picture meets required, the step of performing picture and replace.Methods described includes:
Step 1601:The hot search keyword of same class purpose is obtained in setting time;
It is same with step 1601, step 1501 is specifically referred to, be will not be described here.Certainly, in this step, it is also possible in real time Obtain the hot search keyword of same class purpose.
Step 1602:Extract the picture of the most fast-selling object that the class is matched with the hot search keyword now;
It is same with step 1602, step 1502 is specifically referred to, be will not be described here.
Step 1603:The quality of the picture of the most fast-selling object is audited, if examination & verification passes through, execution step 1604: Otherwise, execution step 1605 and step 1606;
In the step, after the picture for extracting most fast-selling object, first judge whether the quality of the picture meets requirement, such as, Whether the size of picture meets requirement, and whether resolution meets requirement, and whether brightness meets requirement etc..If meet required, Then examination & verification pass through, otherwise, audit not over.
Step 1604:The picture of the most fast-selling object is updated in the classification page on the master map position that correspondence classification shows;
The step and step 1503 are same, specifically refer to above-mentioned, will not be described here.
Step 1605:Extract the picture of time fast sale object that the class is matched with the hot search keyword now;
In the step, the process which provides the picture of secondary fast sale object is similar with the process of the picture for extracting most fast-selling object, its Specially:Count the fetched data amount of fast-selling object under the hot search keyword;By the fetched data amount time high object It is defined as time fast sale object;Extract the picture of described fast sale object.
If it should be noted that if the quality of the picture of this fast-selling object meets requirement, execution step 1606.
Step 1606:The picture of described fast sale object is updated into in the classification page master map position that correspondence classification shows.
In the step, update with the picture of most fast-selling object and be similar on the master map position that corresponding classification shows in the classification page, Specifically refer to above-mentioned, will not be described here.
In the embodiment of the present application, using picture intuitively representing as classification, based on (as daily) same classification in a period of time Under most hot search keyword and extract such now containing most hot search keyword most fast-selling object picture, and judge most The quality of the picture of fast-selling object, and when the picture quality satisfaction of most fast-selling object is required, replace automatically, if be unsatisfactory for Require, then extract time picture of fast sale object, and replace, i.e., with high resolution, while show the effective of object and Popularity, lifts the captivation of web page contents, while the efficiency that user searches web page contents is also improved, so as to more effective Using the value of picture.
In order to make it easy to understand, below with specific example illustrating.
The embodiment collects the hot search keyword of the women's dress classification, under statistics women's dress key word by taking women's dress classification as an example Article sales data, extracts the most fast-selling object (such as one-piece dress) that the women's dress class is matched with the hot search keyword now Picture, then judge whether the one-piece picture quality meets requirement, if meet required, by one-piece picture more On the new master map position that correspondence one-piece dress shows in the women's dress classification page, to show the commodity picture of the most hot money of high-quality.I.e. After clicking through, the one-piece picture will be presented on the first position of the women's dress classification.
Wherein, in the present embodiment, there is provided the displaying pattern of category list (i.e. intelligent picture classification) be illustrated in fig. 17 shown below, As shown in figure 17, when user clicks on the subcategory under classification displaying list, one-piece dress classification is such as clicked on, then enters into one-piece dress Original list, the master map merchandise display on one-piece dress classification is on first position of original list.
Based on above-mentioned method, the embodiment of the present application also provides a kind of picture updating device, and its structural representation is as shown in figure 18, Described device includes:Acquiring unit 181, extraction unit 182 and updating block 183, wherein,
The acquiring unit 181, for the hot search keyword of same class purpose is obtained in setting time;
Wherein, the described same classification that the acquiring unit 181 is obtained includes:Same class commodity or same class promote position.
The extraction unit 182, for extracting the figure of the most fast-selling object that the class is matched with the hot search keyword now Piece;
Wherein, the extraction unit includes:Statistic unit, determining unit and extraction subelement (not shown), wherein, institute Statistic unit is stated, for counting the fetched data amount of fast-selling object under the hot search keyword;The determining unit, is used for The fetched data amount highest object is defined as into most fast-selling object;The extraction subelement, it is described most fast-selling for extracting The picture of object.
The updating block 183, updates in the classification page master that correspondence classification shows for the picture by the most fast-selling object On figure position.
Optionally, in another embodiment, described device can also include:Examination & verification unit 191, its structural representation is as schemed Shown in 19, wherein,
The examination & verification unit 191, the quality of the picture for extracting to the extraction unit 182 are audited;
The updating block 183, is additionally operable to when the quality audit of examination & verification 191 pairs of pictures of unit passes through, will be described The picture of most fast-selling object is updated in the classification page on the master map position that correspondence classification shows;
The extraction unit 182, be additionally operable to it is described examination & verification 191 pairs of pictures of unit quality audit not over when, carry Take the picture of time fast sale object that the class is matched with the hot search keyword now;
The updating block 183, the picture of time fast sale object for being additionally operable to extract the extraction unit 182 are updated to classification page On the master map position that correspondence classification shows in face.
Process is realized in the function of unit and effect in described device, and refer to correspondence step in said method realizes process, Will not be described here.
Referring to Figure 20, a kind of structural representation of terminal unit is provided for the embodiment of the present application, the terminal unit 2000 includes: Processor 2010, memorizer 2020, transceiver 2030 and bus 2040;
Processor 2010, memorizer 2020, transceiver 2030 are connected with each other by bus 2040;Bus 2040 can be Isa bus, pci bus or eisa bus etc..The bus can be divided into address bus, data/address bus, controlling bus etc.. For ease of representing, only represented with a thick line in Figure 20, it is not intended that only one bus or a type of bus.
Memorizer 2020, for depositing program.Specifically, program can include program code, and described program code includes meter Calculation machine operational order.Memorizer 2020 may include high-speed RAM memorizer, it is also possible to also including nonvolatile memory (non-volatile memory), for example, at least one disk memory.User stores category list.
Transceiver 2030 is used to connect other equipment, and is communicated with other equipment.The specific transceiver 2030 can For:The hot search keyword of same class purpose is obtained in setting time;Wherein, the same classification includes:Same class Commodity or same class promote position.
The processor 2010 performs the described program code that stores in memorizer 2020, for extract the class now with institute State the picture of the most fast-selling object of hot search keyword matching;The picture of the most fast-selling object is updated into right in the classification page Answer on the master map position of classification displaying.
Alternatively, the processor 2010, is additionally operable to audit the quality of the picture of the most fast-selling object, and is examining When core passes through, the picture of the most fast-selling object is updated in the classification page on the master map position that correspondence classification shows.
Alternatively, the processor 2010, is additionally operable to:Examination & verification not over when, extract the class and search with the heat now The picture of time fast sale object of rope Keywords matching;The picture of described fast sale object is updated into in the classification page correspondence classification On the master map position of displaying.
Alternatively, the processor 2010 extracts the figure of the most fast-selling object that the class is matched with the hot search keyword now Piece, including:Count the fetched data amount of fast-selling object under the hot search keyword;By the fetched data amount highest pair As being defined as most fast-selling object;The picture of most fast-selling object described in extracting.
In the present embodiment, it is the intelligent picture classification pattern that picture is automatically updated based on temperature, is keeping different classification fixed bits While putting, the daily recommendation picture for updating can be allowed, that is, improve the resolution of classification content on webpage, when also can recommend immediately Under the hot money of popularity, lifted website lively atmosphere, increase user click desire, that is, improve point of the user to web page contents Rate is hit, so as to more effectively using the value of picture.
Described above illustrates and describes the preferred embodiment of the application, but as previously mentioned, it should be understood that the application not limits to In form disclosed herein, be not to be taken as the exclusion to other embodiment, and can be used for various other combinations, modification and Environment, and can be changed by the technology or knowledge of above-mentioned teaching or association area in invention contemplated scope described herein It is dynamic.And change that those skilled in the art are carried out and change be without departing from spirit and scope, then all should be appended by the application In scope of the claims.

Claims (40)

1. a kind of picture update method, it is characterised in that include:
Determine the temperature of the primary object that the current classification of the page includes;
According to the first primary object for setting number is chosen in the primary object that temperature size includes from the current classification, obtain The candidate target that the current classification includes;
The picture of the candidate target is obtained, the picture set of the current classification is obtained;
The picture that the entry position for updating the current classification according to the picture in the picture set of the current classification shows.
2. the method for claim 1, it is characterised in that determine the heat of the primary object that the current classification of the page includes Degree, specifically includes:
Obtain the historical data in setting historical period;
The history feature information of the primary object that the current classification includes is counted according to the historical data;
The history feature information of each primary object that the current classification is included is brought in temperature model respectively, obtains correspondence The temperature of primary object.
3. the method for claim 1, it is characterised in that according to temperature size from the current classification include it is original The first primary object for setting number is chosen in object, the candidate target that the current classification includes is obtained, is specifically included:
The primary object that the current classification includes is ranked up according to temperature order from big to small, obtains the current class Purpose the first primary object sequence, starts selection described first from first primary object of the first primary object sequence and sets Determine the primary object of number, obtain the candidate target that the current classification includes;Or,
The primary object that the current classification includes is ranked up according to temperature order from small to large, obtains the current class Purpose the second primary object sequence, starts to choose described first from last primary object of the second primary object sequence The primary object of setting number, obtains the candidate target that the current classification includes.
4. the method for claim 1, it is characterised in that obtain the picture of the candidate target, obtains described current The picture set of classification, specifically includes:
Obtain the main picture and sub-pictures of the candidate target;
The picture of the first attribute information for meeting the current classification is filtered out from the main picture and sub-pictures for obtaining;
It is determined that whether the number of the picture for filtering out is more than the second setting number;
If the number of the picture for filtering out is more than the described second setting number, using the picture for filtering out as the current classification Picture set;
If the number of the picture for filtering out not less than described second setting number, from it is screened fall main picture and sub-pictures in obtain The picture for taking the second attribute information for meeting the current classification carries out picture processing, by the picture for filtering out and at picture Picture set of the picture of reason as the current classification.
5. the method for claim 1, it is characterised in that according to the picture in the picture set of the current classification more The picture that the entry position of the new current classification shows, specifically includes:
Picture in the picture set of the current classification is obtained successively with setting cycle;
The picture that the entry position that the picture for obtaining replaces the current classification is shown.
6. the method as described in claim 1-5 is arbitrary, it is characterised in that also include:
Determine the temperature of the classification that the page includes;
The classification that the page includes is ranked up according to temperature size.
7. method as claimed in claim 6, it is characterised in that determine the temperature of the classification that the page includes is concrete to wrap Include:
Obtain the historical data of setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
8. method as claimed in claim 6, it is characterised in that also include:
The access request that receive user sends;
Whether ID is carried in detecting the access request;
If ID is not carried in the access request, the step of perform the temperature of the classification for determining that the page includes.
9. method as claimed in claim 8, it is characterised in that also include:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
10. method as claimed in claim 9, it is characterised in that obtain the corresponding preference classification of the ID, tool Body includes:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
11. a kind of classification sort methods, it is characterised in that include:
Determine the temperature of the classification that the page includes;
The classification that the page includes is ranked up according to temperature size.
12. methods as claimed in claim 11, it is characterised in that determine the temperature of the classification that the page includes, specifically include:
Obtain the historical data in setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
13. methods as claimed in claim 11, it is characterised in that also include:
The access request that receive user sends;
Whether ID is carried in detecting the access request;
If ID is not carried in the access request, the step of perform the temperature of the classification for determining that the page includes.
14. methods as claimed in claim 13, it is characterised in that also include:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
15. methods as claimed in claim 14, it is characterised in that obtain the corresponding preference classification of the ID, tool Body includes:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
16. a kind of picture updating devices, it is characterised in that include:
First determining unit, for determining the temperature of primary object that the current classification of the page includes;
Unit is chosen, and number is set for first is chosen in the primary object that includes from the current classification according to temperature size Primary object, obtains the candidate target that the current classification includes;
Acquiring unit, for obtaining the picture of the candidate target, obtains the picture set of the current classification;
Updating block, updates the entry position of the current classification for the picture in the picture set according to the current classification The picture of displaying.
17. devices as claimed in claim 16, it is characterised in that first determining unit, for determining working as the page The temperature of the primary object that front classification includes, specifically for:
Obtain the historical data in setting historical period;
The history feature information of the primary object that the current classification includes is counted according to the historical data;
The history feature information of each primary object that the current classification is included is brought in temperature model respectively, obtains correspondence The temperature of primary object.
18. devices as claimed in claim 16, it is characterised in that the selection unit, for according to temperature size from institute The first primary object for setting number is chosen in stating the primary object that current classification includes, the time that the current classification includes is obtained Object is selected, specifically for:
The primary object that the current classification includes is ranked up according to temperature order from big to small, obtains the current class Purpose the first primary object sequence, starts selection described first from first primary object of the first primary object sequence and sets Determine the primary object of number, obtain the candidate target that the current classification includes;Or,
The primary object that the current classification includes is ranked up according to temperature order from small to large, obtains the current class Purpose the second primary object sequence, starts to choose described first from last primary object of the second primary object sequence The primary object of setting number, obtains the candidate target that the current classification includes.
19. devices as claimed in claim 16, it is characterised in that the acquiring unit, for obtaining the candidate target Picture, obtain the picture set of the current classification, specifically for:
Obtain the main picture and sub-pictures of the candidate target;
The picture of the first attribute information for meeting the current classification is filtered out from the main picture and sub-pictures for obtaining;
It is determined that whether the number of the picture for filtering out is more than the second setting number;
If the number of the picture for filtering out is more than the described second setting number, using the picture for filtering out as the current classification Picture set;
If the number of the picture for filtering out not less than described second setting number, from it is screened fall main picture and sub-pictures in obtain The picture for taking the second attribute information for meeting the current classification carries out picture processing, by the picture for filtering out and at picture Picture set of the picture of reason as the current classification.
20. devices as claimed in claim 16, it is characterised in that the updating block, for according to the current classification Picture set in picture update the picture that the entry position of the current classification shows, specifically for:
Picture in the picture set of the current classification is obtained successively with setting cycle;
The picture that the entry position that the picture for obtaining replaces the current classification is shown.
21. devices as described in claim 16-20 is arbitrary, it is characterised in that also include:
Second determining unit, for determining the temperature of classification that the page includes;
Sequencing unit, for being ranked up the classification that the page includes according to temperature size.
22. devices as claimed in claim 21, it is characterised in that second determining unit, for determining the page Including classification temperature, specifically for:
Obtain the historical data of setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
23. devices as claimed in claim 21, it is characterised in that also include:
Receiving unit, for the access request that receive user sends;
Detector unit, for detecting in the access request whether carry ID;
Performance element, if for not carrying ID in the access request, turning to second determining unit.
24. devices as claimed in claim 23, it is characterised in that the performance element, are additionally operable to:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
25. devices as claimed in claim 24, it is characterised in that the performance element, for obtaining the ID Corresponding preference classification, specifically for:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
26. a kind of classification collators, it is characterised in that include:
Determining unit, for determining the temperature of classification that the page includes;
Sequencing unit, for being ranked up the classification that the page includes according to temperature size.
27. devices as claimed in claim 26, it is characterised in that the determining unit, for determining class that the page includes Purpose temperature, specifically for:
Obtain the historical data in setting historical period;
It is original that the history feature information and each classification that the classification that the page includes is counted according to the historical data includes The history feature information of object;
The history feature of the primary object that the history feature information and correspondence classification of each classification that the page is included includes Information is brought in temperature model respectively, obtains the temperature of correspondence classification.
28. devices as claimed in claim 26, it is characterised in that also include:
Receiving unit, for the access request that receive user sends;
Detector unit, for detecting in the access request whether carry ID;
Performance element, if for not carrying ID in the access request, turning to the determining unit.
29. devices as claimed in claim 28, it is characterised in that the performance element, are additionally operable to:
If ID is carried in the access request, obtain the corresponding preference classification of the ID;
Determine the temperature of the preference classification;
The preference classification is ranked up according to temperature size;
Preference classification after sequence is sent to into the user.
30. devices as claimed in claim 29, it is characterised in that the performance element, for obtaining the ID Corresponding preference classification, specifically for:
Obtain the historical data in setting historical period;
The access times of the classification of the ID association are counted according to the historical data;
Access times are exceeded the classification of set point number as the corresponding preference classification of the ID.
31. a kind of picture update methods, it is characterised in that include:
The hot search keyword of same class purpose is obtained in setting time;
Extract the picture of the most fast-selling object that the class is matched with the hot search keyword now;
The picture of the most fast-selling object is updated into in the classification page master map position that correspondence classification shows.
32. methods according to claim 31, it is characterised in that also include:
The quality of the picture of the most fast-selling object is audited, and when examination & verification passes through, is performed described most fast-selling by described in The step of picture of object updates in the classification page master map position that correspondence classification shows.
33. methods according to claim 32, it is characterised in that also include:
Examination & verification not over when, extract the picture of time fast-selling object that the class match with the hot search keyword now;
The picture of described fast sale object is updated into in the classification page master map position that correspondence classification shows.
34. methods according to any one of claim 31 to 33, it is characterised in that the extraction class now with The picture of the most fast-selling object of the hot search keyword matching, including:
Count the fetched data amount of fast-selling object under the hot search keyword;
The fetched data amount highest object is defined as into most fast-selling object;
The picture of most fast-selling object described in extracting.
35. methods according to any one of claim 31 to 33, it is characterised in that the same classification includes:Together Class I goodss or same class promote position.
36. a kind of picture updating devices, it is characterised in that include:
Acquiring unit, for the hot search keyword of same class purpose is obtained in setting time;
Extraction unit, for extracting the picture of the most fast-selling object that the class is matched with the hot search keyword now;
Updating block, updates in the classification page master map position that correspondence classification shows for the picture by the most fast-selling object.
37. devices according to claim 36, it is characterised in that also include:
Examination & verification unit, for auditing to the quality of the picture;
The updating block, is additionally operable to when the examination & verification quality audit of the unit to the picture passes through, most fast-selling by described in The picture of object updates in the classification page master map position that correspondence classification shows.
38. devices according to claim 37, it is characterised in that also include:
The extraction unit, be additionally operable to the examination & verification unit to the quality audit of the picture not over when, extract described The picture of time fast sale object that class is matched with the hot search keyword now;
The updating block, is additionally operable to for the picture of described fast sale object to update in the classification page master that correspondence classification shows Figure position.
39. devices according to claim 36 or 37, it is characterised in that the extraction unit includes:
Statistic unit, for counting the fetched data amount of fast-selling object under the hot search keyword;
Determining unit, for the fetched data amount highest object is defined as most fast-selling object;
Subelement is extracted, for extracting the picture of the most fast-selling object.
40. devices according to claim 36 or 37, it is characterised in that the described same classification that acquiring unit is obtained Including:Same class commodity or same class promote position.
CN201510917313.8A 2015-09-23 2015-12-10 Picture update method, classification sort method and device Pending CN106547808A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510612764 2015-09-23
CN2015106127640 2015-09-23

Publications (1)

Publication Number Publication Date
CN106547808A true CN106547808A (en) 2017-03-29

Family

ID=58365721

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510917313.8A Pending CN106547808A (en) 2015-09-23 2015-12-10 Picture update method, classification sort method and device

Country Status (1)

Country Link
CN (1) CN106547808A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106960046A (en) * 2017-03-30 2017-07-18 努比亚技术有限公司 Picture recommendation method and terminal
CN108228873A (en) * 2018-01-17 2018-06-29 腾讯科技(深圳)有限公司 Object recommendation, publication content delivery method, device, storage medium and equipment
CN109656433A (en) * 2017-10-11 2019-04-19 腾讯科技(深圳)有限公司 Category information processing method, device, computer equipment and storage medium
CN109831699A (en) * 2018-12-28 2019-05-31 广州华多网络科技有限公司 Image audit processing method, device, electronic equipment and storage medium
CN110209854A (en) * 2019-05-06 2019-09-06 无线生活(北京)信息技术有限公司 Picture determines method and device
CN110471721A (en) * 2018-05-10 2019-11-19 北京京东尚科信息技术有限公司 Page display method and system, electronic equipment and storage medium

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408964A (en) * 2008-11-25 2009-04-15 阿里巴巴集团控股有限公司 Method and apparatus for regulating foreground category of electronic commerce website
CN102339438A (en) * 2010-07-22 2012-02-01 阿里巴巴集团控股有限公司 Commodity information website publishing method, system and device
CN102866992A (en) * 2011-07-04 2013-01-09 阿里巴巴集团控股有限公司 Method and device for displaying product information in webpage
CN103455550A (en) * 2013-07-26 2013-12-18 百度在线网络技术(北京)有限公司 Method and device for acquiring image search results with contrast effect
CN103546778A (en) * 2013-07-17 2014-01-29 Tcl集团股份有限公司 Television program recommendation method and system, and implementation method of system
US20140040186A1 (en) * 2012-08-03 2014-02-06 Toshiba Tec Kabushiki Kaisha Information processing system, information processing apparatus and method for updating data
CN104346370A (en) * 2013-07-31 2015-02-11 阿里巴巴集团控股有限公司 Method and device for image searching and image text information acquiring
CN104346697A (en) * 2014-10-31 2015-02-11 亚信科技(南京)有限公司 Method and system for issuing product in grading way
CN104361109A (en) * 2014-11-27 2015-02-18 北京奇虎科技有限公司 Method and device for determining picture screening result
CN104794220A (en) * 2015-04-28 2015-07-22 百度在线网络技术(北京)有限公司 Information search method and information search device
CN104992348A (en) * 2015-06-24 2015-10-21 深圳市腾讯计算机系统有限公司 Method and device for displaying information

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408964A (en) * 2008-11-25 2009-04-15 阿里巴巴集团控股有限公司 Method and apparatus for regulating foreground category of electronic commerce website
CN102339438A (en) * 2010-07-22 2012-02-01 阿里巴巴集团控股有限公司 Commodity information website publishing method, system and device
CN102866992A (en) * 2011-07-04 2013-01-09 阿里巴巴集团控股有限公司 Method and device for displaying product information in webpage
US20140040186A1 (en) * 2012-08-03 2014-02-06 Toshiba Tec Kabushiki Kaisha Information processing system, information processing apparatus and method for updating data
CN103546778A (en) * 2013-07-17 2014-01-29 Tcl集团股份有限公司 Television program recommendation method and system, and implementation method of system
CN103455550A (en) * 2013-07-26 2013-12-18 百度在线网络技术(北京)有限公司 Method and device for acquiring image search results with contrast effect
CN104346370A (en) * 2013-07-31 2015-02-11 阿里巴巴集团控股有限公司 Method and device for image searching and image text information acquiring
CN104346697A (en) * 2014-10-31 2015-02-11 亚信科技(南京)有限公司 Method and system for issuing product in grading way
CN104361109A (en) * 2014-11-27 2015-02-18 北京奇虎科技有限公司 Method and device for determining picture screening result
CN104794220A (en) * 2015-04-28 2015-07-22 百度在线网络技术(北京)有限公司 Information search method and information search device
CN104992348A (en) * 2015-06-24 2015-10-21 深圳市腾讯计算机系统有限公司 Method and device for displaying information

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张仙锋: "《网络贸易》", 30 August 2011, 北京:中国铁道出版社 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106960046A (en) * 2017-03-30 2017-07-18 努比亚技术有限公司 Picture recommendation method and terminal
CN106960046B (en) * 2017-03-30 2020-08-28 山东创品信息咨询服务有限公司 Picture recommendation method and terminal
CN109656433A (en) * 2017-10-11 2019-04-19 腾讯科技(深圳)有限公司 Category information processing method, device, computer equipment and storage medium
CN109656433B (en) * 2017-10-11 2021-07-06 腾讯科技(深圳)有限公司 Category information processing method, category information processing device, computer equipment and storage medium
CN108228873A (en) * 2018-01-17 2018-06-29 腾讯科技(深圳)有限公司 Object recommendation, publication content delivery method, device, storage medium and equipment
CN108228873B (en) * 2018-01-17 2022-02-18 腾讯科技(深圳)有限公司 Object recommendation and release content pushing method and device, storage medium and equipment
CN110471721A (en) * 2018-05-10 2019-11-19 北京京东尚科信息技术有限公司 Page display method and system, electronic equipment and storage medium
CN109831699A (en) * 2018-12-28 2019-05-31 广州华多网络科技有限公司 Image audit processing method, device, electronic equipment and storage medium
CN109831699B (en) * 2018-12-28 2021-07-20 广州华多网络科技有限公司 Image auditing processing method and device, electronic equipment and storage medium
CN110209854A (en) * 2019-05-06 2019-09-06 无线生活(北京)信息技术有限公司 Picture determines method and device
CN110209854B (en) * 2019-05-06 2021-08-31 无线生活(北京)信息技术有限公司 Picture determination method and device

Similar Documents

Publication Publication Date Title
CN106547808A (en) Picture update method, classification sort method and device
CN109685631B (en) Personalized recommendation method based on big data user behavior analysis
WO2020171535A2 (en) Method for providing fashion item recommendation service by using user's body shape and purchase history
US9916613B1 (en) Automatic color palette based recommendations for affiliated colors
JP6315524B2 (en) Automatic image-based recommendations using color palettes
CN112015998B (en) Commodity recommendation method based on user portrait
JP4426563B2 (en) Information provision system
CN108124184A (en) A kind of method and device of living broadcast interactive
CN106649383A (en) Clothes management method and system
CN107633021A (en) A kind of dispensing of graph text information, generation method and device
CN103365904B (en) A kind of advertising message searching method and system
CN106910136A (en) It is method and device, the system of family's portrait
CN109903127A (en) Group recommendation method and device, storage medium and server
CN115983952B (en) Custom-made clothing design recommendation system
WO2021102564A1 (en) Automatic item recommendations based on visual attributes and complementarity
CN107832444A (en) Event based on search daily record finds method and device
KR20200141251A (en) Method of advertising personalized fashion item and server performing the same
CN109063120A (en) A kind of collaborative filtering recommending method and device based on cluster
CN110363570A (en) Classification methods of exhibiting, device, electronic equipment and storage medium in
CN111767459A (en) Item recommendation method and device
JP2010033608A (en) Information providing system
WO2020156306A1 (en) Clothing collocation information processing method, system and device, and data object processing method, system and device
CN105117935A (en) Realization method of intelligent dress matching and apparatus thereof
CN112966176B (en) Object display method and device, electronic equipment and readable storage medium
CN109658195A (en) A kind of merchandise display decision-making technique

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
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 1235489

Country of ref document: HK

RJ01 Rejection of invention patent application after publication

Application publication date: 20170329

RJ01 Rejection of invention patent application after publication
REG Reference to a national code

Ref country code: HK

Ref legal event code: WD

Ref document number: 1235489

Country of ref document: HK