CN110175883A - A kind of sort method, device, electronic equipment and non-volatile memory medium - Google Patents
A kind of sort method, device, electronic equipment and non-volatile memory medium Download PDFInfo
- Publication number
- CN110175883A CN110175883A CN201910285951.0A CN201910285951A CN110175883A CN 110175883 A CN110175883 A CN 110175883A CN 201910285951 A CN201910285951 A CN 201910285951A CN 110175883 A CN110175883 A CN 110175883A
- Authority
- CN
- China
- Prior art keywords
- commodity
- information
- trade company
- user
- fisrt feature
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0603—Catalogue ordering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present embodiments relate to artificial intelligence field, a kind of sort method and equipment, storage medium are disclosed.In the present invention, which includes: the information according to commodity, determines the fisrt feature factor, wherein commodity are corresponding with activity scene；According at least one in the related information between the information of the affiliated trade company of commodity, the information of user, trade company and user, the second feature factor is determined；According to the fisrt feature factor and the second feature factor, the score value of commodity is determined；According to the score value of commodity, commodity are ranked up.For different activity scenes, pass through the flexible configuration fisrt feature factor, in conjunction with the second feature factor, it is capable of the commodity intelligent sequencing model of fast construction difference active theme, and then commodity are ranked up, to realize the merchandise display in thousand people, thousand face, accurate recommendation is provided for user, it is more close to the users demand, and then improves the Experience Degree of user.
Description
Technical field
The present embodiments relate to artificial intelligence field, in particular to a kind of sort method, device, electronic equipment and Fei Yi
The property lost storage medium.
Background technique
Currently, user when buying take-away, is to carry out the transaction that places an order by taking out platform and trade company.In order to excavate use
The potential lower single wish in family, take out platform can the dimension based on vegetable to user carry out intelligent recommendation, for example, according to popularity ranking,
The different theme such as favorable comment degree, competitively priced carries out intelligent sequencing, and shows ranking results to user.
At least there are the following problems in the related technology for inventor's discovery: when carrying out intelligent recommendation to user, user can be wished
Hope the recommendation sequence for obtaining different dimensions, and different dimensions can have diversified proposed topic.Wherein, it is based on vegetable dimension
Proposed topic daily record data it is less, can not be from the inherence excavated in less data between vegetable and corresponding proposed topic
Incidence relation is not available family and obtains desired vegetable recommendation list；Also, the number of users due to taking out platform and vegetable number are all
Interaction data in hundred million ranks, and between user and vegetable is less, is generally formed using the information such as menu name or vegetable evaluation
The text data of vegetable, if text data are converted to the digital representation in mathematical model, calculation amount can be very big, can not obtain
Good ranking results are obtained, and then make user that can not obtain desired vegetable recommendation list, reduce user experience.
Summary of the invention
Embodiment of the present invention is designed to provide a kind of sort method and equipment, storage medium, sells to solve
Platform can not accurate recommendation go out the problem of adapting to the vegetable of different dimensions.
In order to solve the above technical problems, embodiments of the present invention provide a kind of sort method, comprising the following steps: root
According to the information of commodity, the fisrt feature factor is determined, wherein commodity are corresponding with activity scene；According to the letter of the affiliated trade company of commodity
At least one of in related information between breath, the information of user, trade company and user, determine the second feature factor；According to first
Characterization factor and the second feature factor, determine the score value of commodity；According to the score value of commodity, commodity are ranked up.
Embodiments of the present invention additionally provide a kind of collator, comprising: fisrt feature module, for according to commodity
Information determines the fisrt feature factor, wherein commodity are corresponding with activity scene；Second feature module, for according to belonging to commodity
At least one of in related information between the information of trade company, the information of user, trade company and user, determine the second feature factor；
Commodity score module, for determining the score value of commodity according to the fisrt feature factor and the second feature factor；Sorting module is used
In the score value according to commodity, commodity are ranked up.
Embodiments of the present invention additionally provide a kind of electronic equipment, including memory and processor, memory storage meter
Calculation machine program, processor execute when running program: according to the information of commodity, determining the fisrt feature factor, wherein commodity and activity
Scene is corresponding；According in the related information between the information of the affiliated trade company of commodity, the information of user, trade company and user at least
One, determine the second feature factor；According to the fisrt feature factor and the second feature factor, the score value of commodity is determined；According to quotient
The score value of product, is ranked up commodity.
Embodiments of the present invention additionally provide a kind of non-volatile memory medium, for storing computer-readable program,
Computer-readable program is for executing sort method as above for computer.
In terms of existing technologies, the main distinction and its effect are embodiment of the present invention: for different activities
Scene determines the score value of commodity in conjunction with the second feature factor by the flexible configuration fisrt feature factor, being capable of fast construction
The commodity intelligent sequencing model of different active themes, and then commodity are ranked up by the score value, to realize thousand people, thousand face
Merchandise display, provide accurate recommendation for user, demand of being more close to the users, and then improve user Experience Degree.
In addition, determining the score value of commodity according to the fisrt feature factor and the second feature factor, comprising: according to the first spy
Sign factor pair commodity are ranked up, and determine the fisrt feature number of commodity；According to the affiliated trade company of second feature factor pair commodity into
Row sequence determines the second feature number of trade company；Fusion is weighted to fisrt feature number and second feature number, obtains quotient
The score value of product.
In which, the score of commodity is obtained and being weighted fusion to fisrt feature number and second feature number
Value, the influence power of the fisrt feature factor can be embodied by making the score value more, or, the influence power of the second feature factor can be more embodied, into
And number score value obtained by fisrt feature number and second feature more and can embody the characteristic of the character pair factor, make quotient
Family can targetedly improve corresponding commodity by the score value, flat to sell to adapt to the demand of different activity scenes
While platform brings better income, experience effect of the user on sales platform is improved.
In addition, being weighted fusion to fisrt feature number and second feature number, the score value of commodity is obtained, comprising:
Determine that fisrt feature numbers corresponding weight, and, second feature numbers corresponding weight；It calculates fisrt feature and numbers corresponding power
The product of value and fisrt feature number, obtains the first product value；It calculates second feature and numbers corresponding weight and second feature volume
Number product, obtain the second product value；Calculate the first product value and the second product value and, by resulting and value as commodity
Score value.
In addition, determine that fisrt feature numbers corresponding weight, and, second feature numbers corresponding weight, comprising: determines the
The weight of one characterization factor and the second feature factor；According to weight, determine that fisrt feature numbers corresponding weight and second feature
Number corresponding weight.
In which, by the weight of the fisrt feature factor and the second feature factor, embodies and calculating obtaining for the commodity
During score value, it is specifically more heavily weighted toward which characterization factor, if biasing toward the fisrt feature factor, then it represents that the score of the commodity
Value more with reference to the factor of the linkage factor of commodity,；If laying particular stress on and the second feature factor, then it represents that the score value of the commodity
It is different according to the reference factor of weighting more with reference to the factor of merchant information point, it is determined that fisrt feature number is corresponding
Weight, and, second feature, which numbers corresponding weight, enables commodity so that can more embody the demand of user to the sequence of commodity
The demand for flexibly adapting to different activity scenes, improves the operation of trade company, obtains better income.
In addition, the related information between trade company and user, comprising: the interactive information of user and trade company, and, user accesses quotient
Contextual information when family；According in the related information between the information of the affiliated trade company of commodity, the information of user, trade company and user
At least one of, determine the second feature factor, comprising: the interaction when information of the affiliated trade company of commodity, user are accessed trade company is believed
At least one in contextual information when breath, the information of user and user access trade company is input in data model, determines quotient
The second feature factor of the affiliated trade company of product.
In which, by using data model, the second feature factor with universal adaptability can be obtained, make this
Two characterization factors can more embody the information of trade company, and then enable the corresponding commodity of second feature factor overall merit, pass through
Targetedly improve commodity, commodity can be made to adapt to the demand in different movable meeting-place.
In addition, being ranked up according to fisrt feature factor pair commodity, the fisrt feature number of commodity is determined, comprising: obtain
The number for the commodity being called back；According to the number of the fisrt feature factor and the commodity being called back, determine that the fisrt feature of commodity is compiled
Number.
In addition, the information of the affiliated trade company of commodity, comprising: the traffic statistics of trade company and the attribute information of trade company.
In addition, the information of user, comprising: the traffic statistics of user and the attribute information of user.
In addition, interactive information when user access trade company, comprising: interaction traffic statistics and pricing information；User visits
Ask contextual information when trade company, comprising: access information, distribution information and the network information.
In addition, the information of commodity, comprising: the moon sales volume of commodity, the positive rating of commodity, the corresponding distribution time of commodity, quotient
At least one of in the corresponding pricing information of product.
Detailed description of the invention
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element in attached drawing with same reference numbers label are expressed as similar element, remove
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is the sort method flow diagram in first embodiment according to the present invention；
Fig. 2 is the sort method flow diagram in second embodiment according to the present invention；
Fig. 3 is the structural schematic diagram of the collator in third embodiment according to the present invention；
Fig. 4 is the structural schematic diagram of the electronic equipment in the 4th embodiment according to the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order to make the reader understand this application better, many technical details are proposed.But even if without these technical details
And various changes and modifications based on the following respective embodiments, the application technical solution claimed also may be implemented.
Description and claims of this specification and term " first " in above-mentioned attached drawing, " second " etc. are for distinguishing
Similar object, without being used to describe a particular order or precedence order.It should be understood that the data used in this way are in appropriate feelings
It can be interchanged under condition, so that the embodiments described herein can be real with the sequence other than the content for illustrating or describing herein
It applies.In addition, term " includes " or " having " and its any deformation, it is intended that cover it is non-exclusive include, for example, containing one
Series of steps or the process, method, system, product or equipment of unit those of are not necessarily limited to be clearly listed step or unit,
It but may include other step or units being not clearly listed or intrinsic for these process, methods, product or equipment.
The first embodiment of the present invention is related to a kind of sort methods.For different activity scenes, pass through flexible configuration
The fisrt feature factor is capable of the commodity intelligent sequencing model of fast construction difference active theme, in turn in conjunction with the second feature factor
Commodity are ranked up, to realize the merchandise display in thousand people, thousand face, provide accurate recommendation for user, demand of being more close to the users,
And then improve the Experience Degree of user.
The realization details of the sort method in present embodiment is specifically described below, the following contents is only for convenience
Understand the realization details of this programme, not implements the necessary of this programme.
Fig. 1 show the flow chart of the sort method in present embodiment, and this method is applied to server, it may include as follows
Step.
In a step 101, according to the information of commodity, the fisrt feature factor is determined.
Wherein, commodity are corresponding with activity scene.For example, when user is when selecting commodity, it is desirable to which selection has preferential price
The commodity of lattice, then the activity scene is exactly competitively priced scene, and under the competitively priced scene, server can be corresponding according to commodity
Pricing information, filter out corresponding commodity and be presented to the user；If user wishes to obtain the higher commodity of evaluating deg, the work
Dynamic scene is exactly favorable comment degree scene, and under the favorable comment degree scene, server can filter out corresponding quotient according to the positive rating of commodity
Product are simultaneously presented to the user.
Wherein, the information of commodity, comprising: the moon sales volume of commodity, the positive rating of commodity, the corresponding distribution time of commodity, quotient
At least one of in the corresponding pricing information of product.
It should be noted that the fisrt feature factor therein includes one or more linkage factors of commodity, the linkage because
Son is to be chosen according to user's intelligence with product form, and each linkage factor pair answers a kind of information of commodity, for example, commodity in use
The moon sales volume as first linkage the factor, use the positive rating of the commodity as second linkage the factor, commodity in use is corresponding to match
Send the time as the third linkage factor, then the corresponding pricing information of commodity in use uses above as the four-axle linkage factor
The first linkage factor and the second linkage factor form the fisrt feature factor, or, carrying out group using the above first to fourth linkage factor
At the fisrt feature factor.It is because of these connection as the fisrt feature factor according at least one of above four kinds of linkages factor
Reason is able to reflect overall assessment of the user to the commodity, for example, commodity in use the moon sales volume as the fisrt feature factor,
If the moon sales volume of the commodity is higher, indicate that user more likes the commodity.
In a step 102, believed according to the association between the information of the affiliated trade company of commodity, the information of user, trade company and user
At least one of in breath, determine the second feature factor.
Wherein, the related information between trade company and user includes: the interactive information and user's access when user accesses trade company
Contextual information when trade company.
It should be noted that the interaction letter when information of the affiliated trade company of commodity in use, the information of user, user access trade company
At least one of in contextual information when breath and user access trade company, to determine the second feature factor, the second feature factor
Reflection is that user accesses the information of the trade company and which type of user is ready to access the trade company, is obtained based on information above
The overall merchant information point obtained is able to reflect overall assessment of the user to the trade company according to the merchant information point.
Wherein, the information of the affiliated trade company of commodity, comprising: the traffic statistics of trade company and the attribute information of trade company.
It should be noted that the traffic statistics of trade company therein specifically include: the commodity of the trade company are in a period of time
It is interior be clicked number, by lower single number, be exposed number, be clicked rate and interviewed purchase rate etc.；The attribute information of trade company is specific
Include: the trade company whether have full deactivation it is dynamic, whether be address information where the solid shop/brick and mortar store of new shop, the means of payment and the trade company
Deng.
Wherein, the information of user, comprising: the traffic statistics of user and the attribute information of user.
It should be noted that the traffic statistics of user specifically include: the click of the user whithin a period of time is each
The number of commodity, is clicked commodity rate and is visited and purchase commodity rate etc. lower single number；The attribute information of user specifically includes: the user's
Gender, whether the user is new user, the permanent residence of the user, the red packet sensitivity of the user, the user be white collar
Or student etc..
Wherein, interactive information when user's access trade company, comprising: interaction traffic statistics and pricing information.
It should be noted that interaction traffic statistics specifically include: the user whithin a period of time, clicks the trade company
The number of each commodity, the number to place an order in the commodity, the user click the clicking rate of the commodity of the trade company and visit purchase commodity rate
Deng；Pricing information specifically includes: the gap etc. between visitor's unit price of the user and visitor's unit price of the trade company.
Wherein, contextual information when user's access trade company, comprising: access information, distribution information and the network information.
It should be noted that access information refers to that the user specifically accesses the date of the trade company, distribution information refers to the quotient
Family is when dispensing the commodity that the user places an order, the distance passed through, and time on the day of the dispatching and weather condition etc., net
Network type, the device type used by a user etc. when network information includes user access trade company.
Wherein, interactive information, the information of user and user when the information of the affiliated trade company of commodity, user being accessed trade company visit
In contextual information when asking trade company at least one of be input in data model, determine the second feature of the affiliated trade company of commodity because
Son.
It should be noted that data model therein is to promote (Extreme Gradient using extreme gradient
Boosting, XGBoost) data model established of algorithm, Boosting method be it is a kind of be used to improve weak typing algorithm it is accurate
The method of degree, the thought of this method are to integrate many Weak Classifiers to form a strong classifier.And XGBoost algorithm
It is one of boosting algorithm, is a kind of promotion tree-model, therefore it is to integrate many tree-models to form one
Very strong classifier.
At one in the specific implementation, interactive information, the user when information of the affiliated trade company of commodity, user to be accessed to trade company
At least one of in contextual information when information and user access trade company, it is input in XGBoost data model, by line
The real time data of platform can calculate the second feature factor for obtaining the affiliated trade company of the commodity, wherein the second feature factor representation
Be the trade company information point, the specifying information of the trade company is characterized according to the information of the trade company point.
In step 103, according to the fisrt feature factor and the second feature factor, the score value of commodity is determined.
It should be noted that according to the fisrt feature factor of the commodity by user's favorable rating is able to reflect, and be able to reflect
User determines the score value of the commodity to the second feature factor of the evaluation of the affiliated trade company of the commodity, being capable of the thoroughly evaluating quotient
Product are liked by the favorite degree of user, and by the user of which type.
At one in the specific implementation, by by the fisrt feature factor (the linkage factors of the commodity), and, the second feature factor
(information of the trade company point) comprehensively considers, and obtains a comprehensive test factor, should come specific determine according to the comprehensive test factor
Specific score value of the commodity on platform, and the commodity are specifically evaluated using the score value, this can be embodied by the score value
Overall merit of the commodity in the angle of user.
At step 104, according to the score value of commodity, commodity are ranked up.
At one in the specific implementation, the score value of each commodity is taken together, by the score value carry out ascending order or
The arrangement of descending obtains each commodity sequencing numbers corresponding in the sequence, can be obtained each commodity at the angle of user
Putting in order for degree, enables platform in customer consumption, determines user selects the trend of which commodity according to the score value.
In the present embodiment, for different activity scenes, by the flexible configuration fisrt feature factor, in conjunction with the second spy
The factor is levied, determines the score value of commodity, is capable of the commodity intelligent sequencing model of fast construction difference active theme, and then by being somebody's turn to do
Score value is ranked up commodity, to realize the merchandise display in thousand people, thousand face, provides accurate recommendation for user, is more close to the users
Demand, and then improve the Experience Degree of user.
Second embodiment of the present invention is related to a kind of sort method.Second embodiment and first embodiment substantially phase
Together, it is in place of the main distinction: fusion is weighted to fisrt feature number and second feature number, specific determining commodity
Score value, and then commodity are ranked up according to the score value.
Specific process flow is as shown in Fig. 2, in the present embodiment, which includes step 201~206, because being somebody's turn to do
Step 201~202 are identical as step 101~102 in first embodiment in embodiment, also, walk in the embodiment
Rapid 206 is identical as the step 104 in first embodiment, and details are not described herein, and lower mask body introduces the step in present embodiment
Rapid 203~205.
In step 203, it is ranked up according to fisrt feature factor pair commodity, determines the fisrt feature number of commodity.
Wherein, the number for the commodity being called back is obtained；According to the number of the fisrt feature factor and the commodity being called back, determine
The fisrt feature of commodity is numbered.
At one in the specific implementation, obtaining quotient using the number for the commodity being called back divided by the fisrt feature factor, according to
The quotient, is ranked up commodity, each commodity sequencing numbers corresponding in the sequence is obtained, corresponding to each commodity
Sequencing numbers as commodity fisrt feature number.
In step 204, it is ranked up according to the affiliated trade company of second feature factor pair commodity, determines the second feature of trade company
Number.
At one in the specific implementation, the second feature factor representation be the trade company information point, according to the letter of the trade company
Breath point carries out descending to trade company or ascending order arranges, and after completing sequence, each trade company can obtain a corresponding sequence and compile
Number, it is numbered using the sequencing numbers as the second feature of the trade company.
In step 205, fusion is weighted to fisrt feature number and second feature number, obtains the score of commodity
Value.
Wherein, first determine that fisrt feature numbers corresponding weight, and, second feature numbers corresponding weight；Then it calculates
Fisrt feature numbers the product of corresponding weight and fisrt feature number, obtains the first product value；And calculate second feature number
The product of corresponding weight and second feature number, obtains the second product value；Finally calculate the first product value and the second product value
Sum, by resulting and score value of the value as commodity.
At one in the specific implementation, fisrt feature numbers corresponding weight and second feature numbers corresponding weight, according to
Following steps determine: determining the weight of the fisrt feature factor and the second feature factor；According to weight, fisrt feature number pair is determined
The weight and second feature answered number corresponding weight.
It should be noted that weight therein refers to the significance level of a certain factor or index relative to a certain things, by force
What is adjusted is the relative importance of factor or index, it is intended to contribution degree or importance.Specifically, in the score for calculating the commodity
During value, weight characterizes the contribution degree or significance level height of which specific characterization factor, if the fisrt feature factor (commodity
The linkage factor) significance level it is high, then fisrt feature numbers corresponding weight with regard to big, otherwise, if the second feature factor (quotient
The information at family point) significance level it is high, then second feature numbers corresponding weight with regard to big.Fisrt feature number corresponding weight with
What second feature numbered corresponding weight is 1 with value, according to the difference of the weight, makes the sequence of commodity that can more embody the need of user
It asks, can flexibly adapt to the demand of different activity scenes, provide accurate recommendation for user, demand of being more close to the users.
At one in the specific implementation, passing through the accounting rate that the fisrt feature factor and the second feature factor is manually set, use
The highest corresponding target accounting rate of purchase rate is returned, as the weight of the fisrt feature factor and the second feature factor.It needs to illustrate
, purchase rate therein of returning is to indicate user after first purchase commodity, after a period of time, buying the commodity once more
Probability.For example, the accounting rate that the fisrt feature factor and the second feature factor is manually set is respectively 0.1 and 0.9, or, 0.5 He
0.5, or, 0.8 and 0.2, according to different accounting rates, the purchase rate of returning for counting the commodity in preset time period is respectively 10%,
50%, 30%, wherein preset time period can be the different time span such as a week or one month.According to returning above
For purchase rate it is found that when the accounting rate of the fisrt feature factor and the second feature factor is 0.5 and 0.5, which returns purchase rate highest.
Therefore the weight of the fisrt feature factor and the second feature factor is 0.5 and 0.5, i.e. the fisrt feature factor and the second feature factor is being commented
The significance level when score value of the valence commodity is identical, then it is 0.5 that fisrt feature, which numbers corresponding weight, fisrt feature number pair
The weight answered also is 0.5.
At one in the specific implementation, server can determine the accounting rate of the fisrt feature factor and the second feature factor at random,
The accounting rate may be greater than the arbitrary value equal to 0 and less than or equal to 1, and corresponding different accounting rate counts in preset time period
Commodity return purchase rate, this, which returns purchase rate, can be used percentage to indicate；Then it is ranked up to returning purchase rate, purchase rate pair is returned according to highest
The accounting rate answered, to determine the weight of the fisrt feature factor and the second feature factor.For example, it is 80% that highest, which returns purchase rate, it is corresponding
Accounting rate be 4:6, then the weight of the fisrt feature factor and the second feature factor be 0.4:0.6, determine fisrt feature number pair
The weight answered is 0.4, and it is 0.6 that fisrt feature, which numbers corresponding weight, it should be noted that fisrt feature numbers corresponding weight
The adduction for numbering corresponding weight with fisrt feature is equal to 1.
At one in the specific implementation, the score value of commodity can be obtained according to the following formula:
Wherein,
Score indicates the score value of the commodity, and N is the number for the commodity recalled；
X representation formulaEnter ginseng；
When x is equal to i, wherein i indicates that value range is 0 any value into f, and f indicates the composition fisrt feature factor
The number for the factor that links；sortindex(i) it indicates to be ranked up according to each linkage factor pair commodity in the fisrt feature factor,
Obtain the corresponding sequencing numbers of the commodity；Indicate that the fisrt feature obtained according to the fisrt feature factor is numbered；
Such as: as f=4, indicate that the fisrt feature factor is made of 4 linkage factors, i.e., it, should by the moon sales volume of the commodity
The positive rating of commodity, the corresponding distribution time of commodity pricing information composition corresponding with the commodity；I therein takes 0 respectively, 1,
2,3 this four values calculate SR (i), and SR (0), SR (1), SR (2) and SR (3) are then summed up calculating, and it is special to obtain first
Assemble-publish number
When x is equal to XGboost (s), sortindex(XGboost (s)) indicates to be carried out according to second feature factor pair commodity
Sequence, obtains the corresponding sequencing numbers of the commodity；SR (XGboost (s)) indicates that obtain according to the second feature factor second is special
Assemble-publish number；Wherein, interactive information, the information of user and user when s indicates the information of the affiliated trade company of commodity, user accesses trade company
At least one of in contextual information when accessing trade company；By the way that s is input in XGboost (s) data model, using on line
The real time data of platform calculates the second feature number SR (XGboost (s)) for obtaining the affiliated trade company of the commodity；
α indicates that fisrt feature numbers corresponding weight, and β indicates that second feature numbers corresponding weight；
Such as: as α=0.5, β=0.5, indicate that the fisrt feature factor and the second feature factor are evaluating obtaining for the commodity
Significance level when score value is all 0.5, i.e., of equal importance；
The score value that the commodity are obtained according to above formula carries out commodity further according to score value corresponding to each commodity
Sequence, obtains final ranking results, so that trade company can determine whether corresponding goods are liked by user according to the ranking results,
And then the commodity not liked for user are targetedly improved, and trade company is made to improve result of management.
In this embodiment, fisrt feature number pair is determined by the weight of the fisrt feature factor and the second feature factor
The weight and second feature answered number corresponding weight, are numbered using corresponding weight to fisrt feature number and second feature
It is weighted fusion, and specifically determines the score value of commodity, the score value of the commodity obtained is enable to embody the commodity in different dimensional
So that trade company is targetedly improved corresponding goods according to the score value by the favorite degree of user in degree, enables commodity
Adapt to the different specific requirements for recommending scene.
The step of various methods divide above, be intended merely to describe it is clear, when realization can be merged into a step or
Certain steps are split, multiple steps are decomposed into, as long as including identical logical relation, all in the protection scope of this patent
It is interior；To adding inessential modification in algorithm or in process or introducing inessential design, but its algorithm is not changed
Core design with process is all in the protection scope of the patent.
Third embodiment of the present invention is related to a kind of collator, and the specific implementation of the device can be found in the first embodiment party
The associated description of formula, overlaps will not be repeated.It is worth noting that the specific implementation of the device in present embodiment can also be joined
See the associated description of second embodiment, but be not limited to both examples above, other unaccounted embodiments are also in this dress
Within the protection scope set.
As shown in figure 3, the collator specifically includes that fisrt feature module 301, for the information according to commodity, determine
The fisrt feature factor, wherein commodity are corresponding with activity scene；Second feature module 302, for according to the affiliated trade company of commodity
At least one of in related information between information, the information of user, trade company and user, determine the second feature factor；Commodity point
Digital-to-analogue block 303, for determining the score value of commodity according to the fisrt feature factor and the second feature factor；Sorting module 304 is used
In the score value according to commodity, commodity are ranked up.
In one example, commodity score module 303, is specifically used for: it is ranked up according to fisrt feature factor pair commodity,
Determine the fisrt feature number of commodity；According to second feature factor pair commodity, affiliated trade company is ranked up, and determines the second of trade company
Feature number；Fusion is weighted to fisrt feature number and second feature number, obtains the score value of commodity.
In one example, fusion is weighted to fisrt feature number and second feature number, obtains the score of commodity
Value comprises determining that fisrt feature numbers corresponding weight, and, second feature numbers corresponding weight；Calculate fisrt feature number
The product of corresponding weight and fisrt feature number, obtains the first product value；It calculates second feature and numbers corresponding weight and the
The product of two feature numbers obtains the second product value；Calculate the first product value and the second product value and, resulting and value is made
For the score value of commodity.
In one example, determine that fisrt feature numbers corresponding weight and the corresponding weight of second feature number includes:
Determine the weight of the fisrt feature factor and the second feature factor；According to weight, determine that fisrt feature numbers corresponding weight and the
The corresponding weight of two feature numbers.
In one example, second feature module 302, is specifically used for: the information of the affiliated trade company of commodity, user are accessed quotient
At least one in contextual information when the information of interactive information, user when family and user access trade company is input to data mould
In type, the second feature factor of the affiliated trade company of commodity is determined.
In one example, it is ranked up according to fisrt feature factor pair commodity, determines the fisrt feature number packet of commodity
It includes: obtaining the number for the commodity being called back；According to the number of the fisrt feature factor and the commodity being called back, the first of commodity is determined
Feature number.
In one example, the information of the affiliated trade company of commodity includes: the traffic statistics of trade company and the attribute letter of trade company
Breath.
In one example, the information of user includes: the traffic statistics of user and the attribute information of user.
In one example, interactive information when user's access trade company includes: interactive traffic statistics and pricing information；
Contextual information when user access trade company includes: access information, distribution information and the network information.
In one example, the information of commodity includes: the moon sales volume of commodity, the positive rating of commodity, the corresponding dispatching of commodity
At least one of time, in the corresponding pricing information of commodity.
It is not difficult to find that present embodiment is Installation practice corresponding with first or second embodiment, this embodiment party
Formula can work in coordination implementation with first or second embodiment.The relevant technical details mentioned in first or second embodiment exist
In present embodiment still effectively, in order to reduce repetition, which is not described herein again.Correspondingly, the correlation mentioned in present embodiment
Technical detail is also applicable in first or second embodiment.
It is noted that each module involved in present embodiment is logic module, and in practical applications, one
A logic unit can be a physical unit, be also possible to a part of a physical unit, can also be with multiple physics lists
The combination of member is realized.In addition, in order to protrude innovative part of the invention, it will not be with solution institute of the present invention in present embodiment
The technical issues of proposition, the less close unit of relationship introduced, but this does not indicate that there is no other single in present embodiment
Member.
In present embodiment, for different activity scenes, by the flexible configuration fisrt feature factor, in conjunction with second feature
The factor determines the score value of commodity, is capable of the commodity intelligent sequencing model of fast construction difference active theme, and then by being somebody's turn to do
Score value is ranked up commodity, to realize the merchandise display in thousand people, thousand face, provides accurate recommendation for user, being more close to the users needs
It asks, and then improves the Experience Degree of user.
4th embodiment of the invention is related to a kind of electronic equipment, as shown in figure 4, the electronic equipment includes: at least one
A processor 401；And the memory 402 with the communication connection of at least one processor 401；Wherein, memory 402 is stored with
The instruction that can be executed by least one processor 401, instruction are executed by least one processor 401 to realize: according to commodity
Information determines the fisrt feature factor, wherein commodity are corresponding with activity scene；According to the information of the affiliated trade company of commodity, user
At least one of in related information between information, trade company and user, determine the second feature factor；According to the fisrt feature factor and
The second feature factor determines the score value of commodity；According to the score value of commodity, commodity are ranked up.
Specifically, which includes: one or more processors 401 and memory 402, at one in Fig. 4
For reason device 401.Processor 401, memory 402 can be connected by bus or other modes, to be connected by bus in Fig. 4
It is connected in example.Memory 402 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module.Processor 401 is stored in non-easy in memory 402 by operation
The property lost software program, instruction and module are realized above-mentioned thereby executing the various function application and data processing of equipment
Sort method.
Memory 402 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；It storage data area can the Save option list etc..In addition, memory 402 can be with
It can also include nonvolatile memory, for example, at least disk memory, a flash memory including high-speed random access memory
Device or other non-volatile solid state memory parts.In some embodiments, it includes relative to processing that memory 402 is optional
The remotely located memory 402 of device 401, these remote memories 402 can pass through network connection to external equipment.Above-mentioned network
Example include but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more module is stored in memory 402, when being executed by one or more processor 401, is held
Sort method in the above-mentioned any means embodiment of row.
Method provided by the embodiment of the present application can be performed in the said goods, has the corresponding functional module of execution method and has
Beneficial effect, the not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present application.
5th embodiment of the invention is related to a kind of non-volatile memory medium, for storing computer-readable program,
Computer-readable program is used to execute above-mentioned all or part of embodiment of the method for computer.
That is, it will be understood by those skilled in the art that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, which is stored in a storage medium, including some instructions are to make
It obtains an equipment (can be single-chip microcontroller, chip etc.) or processor (processor) executes side described in each embodiment of the application
The all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize specific embodiments of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
The embodiment of the present application discloses a kind of sort method of A1., which is characterized in that the described method includes:
According to the information of commodity, the fisrt feature factor is determined, wherein the commodity are corresponding with activity scene；
According to the association letter between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of in breath, determine the second feature factor；
According to the fisrt feature factor and the second feature factor, the score value of the commodity is determined；
According to the score value of the commodity, the commodity are ranked up.
A2. sort method according to a1, which is characterized in that according to the fisrt feature factor and the second feature
The factor determines the score value of the commodity, comprising:
It is ranked up according to commodity described in the fisrt feature factor pair, determines the fisrt feature number of the commodity；
It is ranked up according to the affiliated trade company of commodity described in the second feature factor pair, determines the second feature of the trade company
Number；
Fusion is weighted to fisrt feature number and second feature number, obtains the score of the commodity
Value.
A3. the sort method according to A2, which is characterized in that fisrt feature number and the second feature are compiled
Number it is weighted fusion, obtains the score value of the commodity, comprising:
Determine that the fisrt feature numbers corresponding weight, and, the second feature numbers corresponding weight；
The product that the fisrt feature numbers corresponding weight and fisrt feature number is calculated, the first product is obtained
Value；
The product that the second feature numbers corresponding weight and second feature number is calculated, the second product is obtained
Value；
Calculate first product value and second product value and, will be resulting and be worth the scores as the commodity
Value.
A4. sort method according to a3, which is characterized in that determine that the fisrt feature numbers corresponding weight, and,
The second feature numbers corresponding weight, comprising:
Determine the weight of the fisrt feature factor and the second feature factor；
According to the weight, determine that the fisrt feature numbers corresponding weight and the second feature numbers corresponding power
Value.
A5. the sort method according to any one of A1 to A4, which is characterized in that the trade company and the user it
Between related information, comprising:
The interactive information of the user and the trade company, and, the user accesses the contextual information when trade company；
According to the association letter between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of in breath, determine the second feature factor, comprising:
By the information of the affiliated trade company of the commodity, interactive information, the information of the user of the user and the trade company
At least one in contextual information when accessing the trade company with the user is input in data model, determines the commodity
The second feature factor of affiliated trade company.
A6. the sort method according to A2, which is characterized in that carried out according to commodity described in the fisrt feature factor pair
Sequence determines the fisrt feature number of the commodity, comprising:
Obtain the number for the commodity being called back；
According to the number of the fisrt feature factor and the commodity being called back, determine that the fisrt feature of the commodity is compiled
Number.
A7. sort method according to a5, which is characterized in that the information of the affiliated trade company of commodity, comprising: the quotient
The attribute information of the traffic statistics at family and the trade company.
A8. sort method according to a5, which is characterized in that the information of the user, comprising: the flow of the user
The attribute information of statistical information and the user.
A9. sort method according to a5, which is characterized in that the user accesses the interactive information when trade company,
It include: interactive traffic statistics and pricing information；
The user accesses the contextual information when trade company, comprising: access information, distribution information and the network information.
A10. sort method according to a1, which is characterized in that the information of the commodity, comprising:
The moon sales volume of the commodity, the positive rating of the commodity, the corresponding distribution time of the commodity, the commodity are corresponding
Pricing information at least one of.
The embodiment of the present application discloses a kind of collator of B1. characterized by comprising
Fisrt feature module determines the fisrt feature factor for the information according to commodity, wherein the commodity and activity
Scene is corresponding；
Second feature module, for according to the information of the affiliated trade company of the commodity, the information of user, the trade company and described
At least one of in related information between user, determine the second feature factor；
Commodity score module, for determining the commodity according to the fisrt feature factor and the second feature factor
Score value；
Sorting module is ranked up the commodity for the score value according to the commodity.
The embodiment of the present application discloses C1. a kind of electronic equipment, including memory and processor, and memory stores computer
Program, processor execute when running program:
According to the information of commodity, the fisrt feature factor is determined, wherein the commodity are corresponding with activity scene；
According to the association letter between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of in breath, determine the second feature factor；
According to the fisrt feature factor and the second feature factor, the score value of the commodity is determined；
According to the score value of the commodity, the commodity are ranked up.
C2. the electronic equipment according to C1, which is characterized in that according to the fisrt feature factor and the second feature
The factor determines the score value of the commodity, comprising:
It is ranked up according to commodity described in the fisrt feature factor pair, determines the fisrt feature number of the commodity；
It is ranked up according to the affiliated trade company of commodity described in the second feature factor pair, determines the second feature of the trade company
Number；
Fusion is weighted to fisrt feature number and second feature number, obtains the score of the commodity
Value.
C3. the electronic equipment according to C2, which is characterized in that fisrt feature number and the second feature are compiled
Number it is weighted fusion, obtains the score value of the commodity, comprising:
Determine that the fisrt feature numbers corresponding weight, and, the second feature numbers corresponding weight；
The product that the fisrt feature numbers corresponding weight and fisrt feature number is calculated, the first product is obtained
Value；
The product that the second feature numbers corresponding weight and second feature number is calculated, the second product is obtained
Value；
Calculate first product value and second product value and, will be resulting and be worth the scores as the commodity
Value.
C4. the electronic equipment according to C3, which is characterized in that determine that the fisrt feature numbers corresponding weight, and,
The second feature numbers corresponding weight, comprising:
Determine the weight of the fisrt feature factor and the second feature factor；
According to the weight, determine that the fisrt feature numbers corresponding weight and the second feature numbers corresponding power
Value.
C5. the electronic equipment according to any one of C1 to C4, which is characterized in that the trade company and the user it
Between related information, comprising:
The interactive information of the user and the trade company, and, the user accesses the contextual information when trade company；
According to the association letter between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of in breath, determine the second feature factor, comprising:
By the information of the affiliated trade company of the commodity, interactive information, the information of the user of the user and the trade company
At least one in contextual information when accessing the trade company with the user is input in data model, determines the commodity
The second feature factor of affiliated trade company.
C6. the electronic equipment according to C2, which is characterized in that carried out according to commodity described in the fisrt feature factor pair
Sequence determines the fisrt feature number of the commodity, comprising:
Obtain the number for the commodity being called back；
According to the number of the fisrt feature factor and the commodity being called back, determine that the fisrt feature of the commodity is compiled
Number.
C7. the electronic equipment according to C5, which is characterized in that the information of the affiliated trade company of commodity, comprising: the quotient
The attribute information of the traffic statistics at family and the trade company.
C8. the electronic equipment according to C5, which is characterized in that the information of the user, comprising: the flow of the user
The attribute information of statistical information and the user.
C9. the electronic equipment according to C5, which is characterized in that the user accesses the interactive information when trade company,
It include: interactive traffic statistics and pricing information；
The user accesses the contextual information when trade company, comprising: access information, distribution information and the network information.
C10. the electronic equipment according to C1, which is characterized in that the information of the commodity, comprising:
The moon sales volume of the commodity, the positive rating of the commodity, the corresponding distribution time of the commodity, the commodity are corresponding
Pricing information at least one of.
The embodiment of the present application discloses a kind of non-volatile memory medium of D1., described for storing computer-readable program
Computer-readable program is used to execute the sort method as described in any one of A1 to A10 for computer.
Claims (10)
1. a kind of sort method, which is characterized in that the described method includes:
According to the information of commodity, the fisrt feature factor is determined, wherein the commodity are corresponding with activity scene；
According in the related information between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of, determine the second feature factor；
According to the fisrt feature factor and the second feature factor, the score value of the commodity is determined；
According to the score value of the commodity, the commodity are ranked up.
2. sort method according to claim 1, which is characterized in that according to the fisrt feature factor and second spy
The factor is levied, determines the score value of the commodity, comprising:
It is ranked up according to commodity described in the fisrt feature factor pair, determines the fisrt feature number of the commodity；
It is ranked up according to the affiliated trade company of commodity described in the second feature factor pair, determines that the second feature of the trade company is compiled
Number；
Fusion is weighted to fisrt feature number and second feature number, obtains the score value of the commodity.
3. sort method according to claim 2, which is characterized in that fisrt feature number and the second feature
Number is weighted fusion, obtains the score value of the commodity, comprising:
Determine that the fisrt feature numbers corresponding weight, and, the second feature numbers corresponding weight；
The product that the fisrt feature numbers corresponding weight and fisrt feature number is calculated, the first product value is obtained；
The product that the second feature numbers corresponding weight and second feature number is calculated, the second product value is obtained；
Calculate first product value and second product value and, will be resulting and be worth the score value as the commodity.
4. sort method according to claim 3, which is characterized in that determine that the fisrt feature numbers corresponding weight,
With the second feature numbers corresponding weight, comprising:
Determine the weight of the fisrt feature factor and the second feature factor；
According to the weight, determine that the fisrt feature numbers corresponding weight and the second feature numbers corresponding weight.
5. sort method according to any one of claims 1 to 4, which is characterized in that the trade company and the user
Between related information, comprising:
The interactive information of the user and the trade company, and, the user accesses the contextual information when trade company；
According in the related information between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of, determine the second feature factor, comprising:
By the information of the affiliated trade company of the commodity, interactive information, the information of the user and the institute of the user and the trade company
At least one stated in contextual information when user accesses the trade company is input in data model, is determined belonging to the commodity
The second feature factor of trade company.
6. sort method according to claim 2, which is characterized in that according to commodity described in the fisrt feature factor pair into
Row sequence determines the fisrt feature number of the commodity, comprising:
Obtain the number for the commodity being called back；
According to the number of the fisrt feature factor and the commodity being called back, the fisrt feature number of the commodity is determined.
7. sort method according to claim 5, which is characterized in that the information of the affiliated trade company of commodity, comprising: described
The attribute information of the traffic statistics of trade company and the trade company.
8. a kind of collator characterized by comprising
Fisrt feature module determines the fisrt feature factor for the information according to commodity, wherein the commodity and activity scene
It is corresponding；
Second feature module, for according to the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
Between related information at least one of, determine the second feature factor；
Commodity score module, for determining obtaining for the commodity according to the fisrt feature factor and the second feature factor
Score value；
Sorting module is ranked up the commodity for the score value according to the commodity.
9. a kind of electronic equipment, including memory and processor, memory stores computer program, and processor is held when running program
Row:
According to the information of commodity, the fisrt feature factor is determined, wherein the commodity are corresponding with activity scene；
According in the related information between the information of the affiliated trade company of the commodity, the information of user, the trade company and the user
At least one of, determine the second feature factor；
According to the fisrt feature factor and the second feature factor, the score value of the commodity is determined；
According to the score value of the commodity, the commodity are ranked up.
10. a kind of non-volatile memory medium, for storing computer-readable program, the computer-readable program is by for based on
Calculation machine executes the sort method as described in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910285951.0A CN110175883A (en) | 2019-04-10 | 2019-04-10 | A kind of sort method, device, electronic equipment and non-volatile memory medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910285951.0A CN110175883A (en) | 2019-04-10 | 2019-04-10 | A kind of sort method, device, electronic equipment and non-volatile memory medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110175883A true CN110175883A (en) | 2019-08-27 |
Family
ID=67689627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910285951.0A Pending CN110175883A (en) | 2019-04-10 | 2019-04-10 | A kind of sort method, device, electronic equipment and non-volatile memory medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175883A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807687A (en) * | 2019-10-29 | 2020-02-18 | 阿里巴巴（中国）有限公司 | Object data processing method, device, computing equipment and medium |
| CN112163879A (en) * | 2020-09-18 | 2021-01-01 | 深圳市分期乐网络科技有限公司 | User rights pushing method, device, server and storage medium |
| CN113434719A (en) * | 2021-07-05 | 2021-09-24 | 汪冬梅 | Interactive learning system for preschool education |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077306A (en) * | 2013-03-28 | 2014-10-01 | 阿里巴巴集团控股有限公司 | Search engine result sequencing method and search engine result sequencing system |
| CN105446972A (en) * | 2014-06-17 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Search method, device and system based on and fusing with user relation data |
| CN106445947A (en) * | 2015-08-06 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Data searching method and system |
| CN108053282A (en) * | 2017-12-15 | 2018-05-18 | 北京小度信息科技有限公司 | A kind of method for pushing of combined information, device and terminal |
| CN108335137A (en) * | 2018-01-31 | 2018-07-27 | 北京三快在线科技有限公司 | Sort method and device, electronic equipment, computer-readable medium |
| CN108416649A (en) * | 2018-02-05 | 2018-08-17 | 北京三快在线科技有限公司 | Search result ordering method, device, electronic equipment and storage medium |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
-
2019
- 2019-04-10 CN CN201910285951.0A patent/CN110175883A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077306A (en) * | 2013-03-28 | 2014-10-01 | 阿里巴巴集团控股有限公司 | Search engine result sequencing method and search engine result sequencing system |
| CN105446972A (en) * | 2014-06-17 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Search method, device and system based on and fusing with user relation data |
| CN106445947A (en) * | 2015-08-06 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Data searching method and system |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| CN108053282A (en) * | 2017-12-15 | 2018-05-18 | 北京小度信息科技有限公司 | A kind of method for pushing of combined information, device and terminal |
| CN108335137A (en) * | 2018-01-31 | 2018-07-27 | 北京三快在线科技有限公司 | Sort method and device, electronic equipment, computer-readable medium |
| CN108416649A (en) * | 2018-02-05 | 2018-08-17 | 北京三快在线科技有限公司 | Search result ordering method, device, electronic equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807687A (en) * | 2019-10-29 | 2020-02-18 | 阿里巴巴（中国）有限公司 | Object data processing method, device, computing equipment and medium |
| CN112163879A (en) * | 2020-09-18 | 2021-01-01 | 深圳市分期乐网络科技有限公司 | User rights pushing method, device, server and storage medium |
| CN112163879B (en) * | 2020-09-18 | 2024-05-24 | 深圳市分期乐网络科技有限公司 | User rights pushing method, device, server and storage medium |
| CN113434719A (en) * | 2021-07-05 | 2021-09-24 | 汪冬梅 | Interactive learning system for preschool education |
| CN113434719B (en) * | 2021-07-05 | 2022-11-25 | 芜湖穿越信息科技有限公司 | Interactive learning system for preschool education |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | The effect of online shopping platform strategies on search, display, and membership revenues | |
| Francois | Scale economies and imperfect competition in the GTAP model | |
| Akan et al. | Revenue management by sequential screening | |
| Phuong Ta et al. | A study of bank selection decisions in Singapore using the analytical hierarchy process | |
| US7689458B2 (en) | Systems and methods for determining bid value for content items to be placed on a rendered page | |
| Louviere et al. | Reliability and validity of the brand-anchored conjoint approach to measuring retailer images | |
| CN106934498A (en) | The recommendation method and system of hotel's house type in OTA websites | |
| Chen et al. | Information technology and switching costs | |
| Hattingh et al. | The rise of the African consumer | |
| CN107944593A (en) | A kind of resource allocation methods and device, electronic equipment | |
| CN110175883A (en) | A kind of sort method, device, electronic equipment and non-volatile memory medium | |
| CN109582876A (en) | Tourism industry user portrait building method, device and computer equipment | |
| CN108648058A (en) | Model sequencing method and device, electronic equipment, storage medium | |
| Cataldo et al. | Optimal pricing and composition of multiple bundles: A two-step approach | |
| CN107992500A (en) | A kind of information processing method and server | |
| DE102008050302A1 (en) | Method and system to provide sellers access to selected consumers | |
| CN109377376A (en) | The control methods and device, storage medium, terminal for information of managing money matters | |
| TW201727551A (en) | Rebating mechanism management system, method, and computer readable storage medium of the same | |
| Dhurkari | Strategic pricing decision using the analytic hierarchy process | |
| Carter et al. | When do I profit? Uncovering boundary conditions on reputation effects in online auctions | |
| Laussel et al. | The curse of knowledge: having access to customer information can reduce monopoly profits | |
| Baumol et al. | On the optimality of public-goods pricing with exclusion devices | |
| CN109858952A (en) | Data processing method and device under service scenarios | |
| CN108256881A (en) | A kind of traffic filtering method and apparatus | |
| Becker | Decomposition methods for large scale stochastic and robust optimization problems |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190827 |
|
| RJ01 | Rejection of invention patent application after publication |