CN107358512A - Characteristics of objects processing method and processing device, electronic equipment - Google Patents
Characteristics of objects processing method and processing device, electronic equipment Download PDFInfo
- Publication number
- CN107358512A CN107358512A CN201710601743.8A CN201710601743A CN107358512A CN 107358512 A CN107358512 A CN 107358512A CN 201710601743 A CN201710601743 A CN 201710601743A CN 107358512 A CN107358512 A CN 107358512A
- Authority
- CN
- China
- Prior art keywords
- user
- fisrt feature
- feature
- objects
- optimized
- 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]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Abstract
This disclosure relates to a kind of characteristics of objects processing method and processing device, electronic equipment, computer-readable medium.The characteristics of objects processing method includes:Obtain the fisrt feature of the first object;The first user of first object is counted, the second object corresponding with first object is obtained according to the first user of first object;The feature to be optimized of first object is determined according to the fisrt feature and second object.The disclosure can preferably position the reason for the first object bandwagon effect is not good enough.
Description
Technical field
This disclosure relates to technical field of data processing, in particular to a kind of characteristics of objects processing method and processing device, electricity
Sub- equipment, computer-readable medium.
Background technology
Present internet development is rapid, the customer volume multiplication of website, and the information shown to user is more and more.In order to strengthen
The competitiveness of website, the user behavior data that website needs analyze and process is more and more, and traditional tupe can not expire
The demand of foot website development now.
In the prior art, for the bandwagon effect evaluation method in each shop on website, only the data from shop itself
Hand, it is easy to influenceed by other external factors (such as time, season etc.).For example the reduction of a shop order volume very may be used
Can be that whole relevant industries order is all few, is not that the Back ground Information of the shop in itself is changed because to dull season.
The content of the invention
The disclosure provides a kind of characteristics of objects processing method and processing device, electronic equipment, computer-readable medium, can be at least
Partially or entirely solve above-mentioned problems of the prior art.
Other characteristics and advantage of the disclosure will be apparent from by following detailed description, or partially by the disclosure
Practice and acquistion.
According to an aspect of this disclosure, there is provided a kind of characteristics of objects processing method, including:Obtain the first of the first object
Feature;The first user of first object is determined, is obtained and first object according to the first user of first object
Corresponding second object;The feature to be optimized of first object is determined according to the fisrt feature and second object.
In a kind of exemplary embodiment of the disclosure, obtaining the fisrt feature of the first object includes:Count the first history
The effectiveness indicator of first object in period, and collect the characteristic of first object;Obtain each characteristic
To the significance level of the effectiveness indicator;Significance level according to each characteristic to the effectiveness indicator, obtain described the
The fisrt feature of one object.
In a kind of exemplary embodiment of the disclosure, determining the first user of first object includes:Obtain second
The user conversation of first object in historical time section;By in the user conversation of first object not with first object
First user of the user to conclude the transaction as first object.
In a kind of exemplary embodiment of the disclosure, obtained and described first according to the first user of first object
The second object includes corresponding to object:The first user with first object in same user conversation is obtained to conclude the transaction
Other objects, will other described objects as second object.
In a kind of exemplary embodiment of the disclosure, methods described also includes:By second object according to it is described
The trading volume of first user is ranked up;Key second pair of second object as first object of preparatory condition will be met
As;The feature to be optimized of first object is determined according to the fisrt feature and crucial second object.
In a kind of exemplary embodiment of the disclosure, methods described also includes:Phase is determined for the feature to be optimized
The Optimizing Suggestions answered.
According to an aspect of this disclosure, there is provided a kind of characteristics of objects processing unit, including:Fisrt feature acquisition module,
For obtaining the fisrt feature of the first object;Second object acquisition module, for determining the first user of first object, root
The second object corresponding with first object is obtained according to the first user of first object;Characteristic determination module to be optimized,
For determining the feature to be optimized of first object according to the fisrt feature and second object.
In a kind of exemplary embodiment of the disclosure, the second object acquisition module includes user conversation acquiring unit
And the first user's determining unit;Wherein, the user conversation acquiring unit is used to obtain described the in the second historical time section
The user conversation of one object;The first user statistic unit be used for by the user conversation of first object not with described the
The user that one object is concluded the transaction is defined as the first user of first object.
According to an aspect of this disclosure, there is provided a kind of electronic equipment, including memory, processor and it is stored in the storage
On device and the computer program that can run on the processor, any of the above-described embodiment is realized when the program is by the computing device
In method and step.
According to an aspect of this disclosure, there is provided a kind of computer-readable medium, computer program is stored thereon with, it is described
The method and step in any of the above-described embodiment is realized when program is executed by processor.
Characteristics of objects processing method and processing device, electronic equipment in some embodiments of the disclosure, computer-readable Jie
Matter, by obtaining the fisrt feature of the first object, and the first user of first object is determined, so as to according to first use
Family obtains corresponding second object, on the one hand, can determine treating for first object by the fisrt feature and second object
Optimize feature;On the other hand, the reason for the first object bandwagon effect is not good enough can preferably be positioned.
It should be appreciated that the general description and following detailed description of the above are only exemplary, this can not be limited
It is open.
Brief description of the drawings
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
Become more fully apparent.
Fig. 1 is a kind of flow chart of characteristics of objects processing method according to an illustrative embodiments.
Fig. 2 is a kind of flow of the method for the fisrt feature of the object of acquisition first according to an illustrative embodiments
Figure.
Fig. 3 is a kind of flow chart of the method for crucial second object of acquisition according to an illustrative embodiments.
Fig. 4 is the flow chart of another characteristics of objects processing method according to an illustrative embodiments.
Fig. 5 schematically shows a kind of page schematic diagram of characteristics of objects processing method in an illustrative embodiments.
Fig. 6 is a kind of block diagram of characteristics of objects processing unit according to an illustrative embodiments.
Fig. 7 is the schematic diagram of a kind of electronic equipment according to an illustrative embodiments.
Embodiment
Example embodiment is described more fully with referring now to accompanying drawing.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein;On the contrary, these embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Accompanying drawing is only the disclosure
Schematic illustrations, be not necessarily drawn to scale.Identical reference represents same or similar part in figure, thus
Repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In mode.In the following description, there is provided many details fully understand so as to provide to embodiment of the present disclosure.So
And it will be appreciated by persons skilled in the art that the technical scheme of the disclosure can be put into practice and omit one in the specific detail
Or more, or other methods, constituent element, device, step etc. can be used.In other cases, it is not shown in detail or describes
Known features, method, apparatus, realization or operation are to avoid that a presumptuous guest usurps the role of the host and so that each side of the disclosure thickens.
Fig. 1 is a kind of flow chart of characteristics of objects processing method according to an illustrative embodiments.
As shown in figure 1, the characteristics of objects processing method may comprise steps of.
In step s 110, the fisrt feature of the first object is obtained.
In the step s 120, the first user of first object is determined, is obtained according to the first user of first object
Take the second object corresponding with first object.
In step s 130, the spy to be optimized of first object is determined according to the fisrt feature and second object
Sign.
The characteristics of objects processing method that embodiment of the present invention provides, by the fisrt feature for finding out the first object first;
Then the first user of first object in the past period is counted, according to the first user of first object acquisition and institute
State the second object corresponding to the first object;Finally, the fisrt feature of first object and the fisrt feature of second object are contrasted
Between difference, can preferably position the first object bandwagon effect it is not good enough the reason for.
It is illustrated below by each step in Fig. 2-4 pairs of methods describeds of the embodiment of the present invention.
With reference to shown in figure 2, the fisrt feature that above-mentioned steps S110 obtains first object may further include
Following steps.
In step S111, the effectiveness indicator of first object in the first historical time section is counted, and collects described the
The characteristic of one object.
In the embodiment of the present invention, carried out exemplified by assessing the bandwagon effect (such as promotion effect) of displaying content in certain shop
For example, wherein first object can be shop A.The first object example in the first historical time section can be chosen
Such as shop A order data (such as order volume, the order amount of money/turnover) is used as the effectiveness indicator, it is assumed that will order here
Single amount is used as effectiveness indicator, for assessing the bandwagon effect of first object, can be generally considered as, in identical historical time
In section, the bandwagon effect in the order volume more at most shop is better.It is simultaneously as much as possible collect first object this first
Characteristic of the details as first object in historical time section.
In the exemplary embodiment, when the characteristic of first object can include the opening of first object
Between, finishing the time, average score, high score scoring number, low point scoring number, low point comment fraction scale, average price, described first to go through
One or more in physical inventory, picture number, star, commodity richness, blueprint comment number in the history period etc..Its
Described in average score can be obtained by many modes, such as can be averaged with each user to first object score
Value is used as the average score.High score scoring number and the low point of scoring number can rule of thumb with different industry etc. because
Usually distinguish, this is not construed as limiting.The average price can refer to the average value of the price of all commodity of first object.
In the embodiment of the present invention, can from described in log statistic in the first historical time section (such as nearest one week) this first
The effectiveness indicator and characteristic of object, the disclosure are not construed as limiting to this.
In the embodiment of the present invention, methods described can also include to the effectiveness indicator of first object and the original of characteristic
The step of beginning data are selected, quantified and pre-processed.
The features such as the imperfect, inconsistent of data, Noise is the common feature of large database or data warehouse, its
In have our attributes interested, such as merchandise news of the first object, but information is all not completely useful, with reference to net
The characteristic stood, cleaning again, integrated, stipulations and conversion are carried out to information.The process of cleaning fills out default value, smooth number by mending
Increase the integrality of data and uniformity according to removing the mode such as invalid data.So that input data becomes efficient.From original
Data in, extract target industry and useful feature information out.
In step S112, significance level of each characteristic to the effectiveness indicator is obtained.
In the embodiment of the present invention, each characteristic can be obtained to the effectiveness indicator by way of machine modeling
Significance level.Can be using the effectiveness indicator such as order volume of first object in the first historical time section as input
Label.
In the embodiment of the present invention, using above-mentioned label and characteristic, machine learning model, such as linear regression are established
Model, the relation between each characteristic and label i.e. effectiveness indicator is found, exported by the machine learning model each
Significance level/importance of the characteristic to the label.
In step S113, the significance level according to each characteristic to the effectiveness indicator, described first pair is obtained
The fisrt feature of elephant.
For example, descending arrangement can be carried out to the significance level of the effectiveness indicator according to each characteristic, choose most
Important preceding N (N is positive integer) individual characteristic is (also referred to as crucial special as the fisrt feature for influenceing the effectiveness indicator
Sign).
With linear regression for example, label data is designated as y, characteristic has n, is designated as x1, x2, x3 ... xn respectively
(it is assumed here that having done sliding-model control to discontinuous characteristic, n is the positive integer more than or equal to 1), establishes linear return
Return model y=w0+w1*x1+w2*x2+ ...+wn*xn, regression coefficient w0, w1, w2 ... will be obtained after model training
Wn value, finds N (N is the positive integer more than or equal to 1 and less than or equal to n) individual coefficient of maximum absolute value, and this N number of coefficient is corresponding
Characteristic x be most important N number of feature, namely maximum N number of fisrt feature or key feature are influenceed on label.
It should be noted that key feature (i.e. fisrt feature) here is different from above-mentioned effectiveness indicator.Above-mentioned effect
Fruit index is the bandwagon effect for assessing the displaying content of first object such as order volume, turnover, and here
Key feature is can be by improving it, so as to optimize the effectiveness indicator.For example, it is assumed that the fisrt feature obtained includes institute
State the stock of the first object, can be by being adjusted to the stock of first object so that the order volume of first object or
The increase of person's turnover.
With reference to shown in figure 3, determined in above-mentioned steps S120 first object the first user may further include with
Lower step.
In step S121, the user conversation of first object in the second historical time section is obtained.
Here it is a user conversation to define operation behavior of the user on network in the range of certain time.
In the embodiment of the present invention, user is in certain website or App (application, application program) model of upper certain time
The behavior of (for example, between can defining 5 minutes to 30 minutes, but the disclosure is not limited to this) (is searched for, browsed, point in enclosing
Hit) it is defined as a user conversation (Session).
It should be noted that the behavior of user here includes the behavior of any user in the range of certain time, example
Payment can such as be included, place an order behavior.If certain user has carried out multiple search, browsed, point in the range of the certain time
A behavior user conversation at last such as hit, temporally scope divides by Session here.
In step S122, the user that will not conclude the transaction in the user conversation of first object with first object
The first user as first object.
For example, for the A of shop, found in daily record and all in the past period (such as nearest one week) browse, search
Rope, the user Session for clicking on the shop.In all user Session it is final without and the user that concludes the transaction of the shop
Referred to as the first user of first object.
With continued reference to Fig. 3, obtained and described first pair according to the first user of first object in above-mentioned steps S120
As corresponding second object can further include following steps.
In step S123, obtain what is concluded the transaction in same user conversation with the first user of first object
Other objects, by other described objects as second object.
For example, to shop A, its first user is counted in daily record in same user Session, it is final and which
Other a little objects (other shops) have reached transaction, and other objects of this part are exactly the second object corresponding with first object.
For example, a shop B, finds all user Session set related to this shop B.See this user
There is which user not buy the product in the B of shop in Session set, and bought the product in other shops.Here same use
What family Session referred to is exactly this Session set.
With continued reference to Fig. 3, obtained and described first pair according to the first user of first object in above-mentioned steps S120
As corresponding second object can further include following steps.
In step S124, second object is ranked up according to the trading volume with first user.
In step s 125, key second object of second object as first object of preparatory condition will be met.
In the embodiment of the present invention, when second object corresponding with first object of acquisition includes multiple,
Can be by second object according to carrying out descending with the trading volume of first user or ascending order arranges, (M is by M before selection
Positive integer, such as 5, but the disclosure is not limited to this) or rear M keys second of second object as first object
Object.
It should be noted that methods described can also include:Determine belonging to first object and/or second object
Commercial circle, geographical position can also be positioned to the first couple by the second object within same commercial circle, managing same classification
The object of key second of elephant.
In the embodiment of the present invention, described first pair is determined according to first index and second object in step S130
The feature to be optimized of elephant can determine in the following manner:The fisrt feature corresponding with its second of first object is counted respectively
The corresponding index of object, provide the difference between index.Each the fisrt feature that there were significant differences is that first object needs
The i.e. described feature to be optimized of the feature to be optimized.
It should be noted that the corresponding index of the fisrt feature of above-mentioned first object and its second object refers to that this first
Fisrt feature in object and identical characteristic in second object, it is assumed for example that the fisrt feature bag that the first object has
The physical inventory and average score of first object are included, then second object corresponding to the physical inventory of first object is corresponding
Feature refers to that (second object can be one or more for the physical inventory of second object;When second object is multiple
It is such as average value for the physical inventory that can be the plurality of second object or multiple things of the plurality of second object
Reason stock is compared with the physical inventory of first object respectively).The second couple corresponding to the average score of first object
The individual features of elephant refer to the average score of second object.Other fisrt feature are by that analogy.
In other embodiments, can also be relative with crucial second object by the fisrt feature of first object
The feature answered determines the feature to be optimized of first object, particularly when the second number of objects corresponding with first object
When comparing more, if the first object is compared with each fisrt feature of each second object, it is necessary to more time and
Amount of calculation, now only choose crucial second object and be compared with each fisrt feature of first object.
Here significant difference can define according to the percentage of the difference between two features that can quantify completely,
Such as (some fisrt feature of first object-one of them second object contrast characteristic corresponding with the fisrt feature)/
The contrast characteristic, or (some fisrt feature of first object-plurality of second object is corresponding with the fisrt feature
The average value of contrast characteristic)/the plurality of second object contrast characteristic average value, when its calculated value more than 50% it is considered that
It is with significant difference between two features to be, but the disclosure is not construed as limiting to this, can according to concrete application scene come
What sets as significant difference.
Wherein, the contrast of the feature of the first object and its second object or its crucial second object can rule of thumb or
Person general knowledge is judged.Such as user scores this, it is generally recognized that scoring is higher better.In another example finishing the time this
, it is believed that finishing time more late better.Again for example average price this, it is generally recognized that lower better etc. of price
Deng.But the disclosure is not limited to this.
Fig. 4 is the flow chart of another characteristics of objects processing method according to an illustrative embodiments.
As shown in figure 4, the characteristics of objects processing method may comprise steps of.
In step S210, the fisrt feature of the first object is obtained.
In step S220, the first user of first object is determined, is obtained according to the first user of first object
Take the second object corresponding with first object.
In step S230, the spy to be optimized of first object is determined according to the fisrt feature and second object
Sign.
Step S210-230 in the embodiment of the present invention is referred to the step S110-130 in above-described embodiment, herein not
Repeat again.
In step S240, corresponding Optimizing Suggestions are determined for the feature to be optimized.
Embodiment of the present invention proposes a kind of characteristics of objects processing method, by taking network shop as an example, is primarily based on first
The loss user in shop is that competition shop is found in each first shop, and the feature for contrasting the first shop and competing between shop is poor
It is different, the reason for so as to preferably position the content displaying less effective in the first shop, and export corresponding Optimizing Suggestions, energy
Enough solve the optimization problem of shop feature, effective prioritization scheme is provided for shop.
Fig. 5 schematically shows a kind of page schematic diagram of characteristics of objects processing method in an illustrative embodiments.
As shown in fig. 5, it is assumed that the first object is have selected to be illustrated exemplified by the A of shop.
First, by establishing machine learning model, shop A key feature can be obtained.Such as shop A physical library
Deposit, the time of opening for business, the finishing time, picture number, average score, low point of comment number, commodity richness etc..
Then, other store informations that customer loss arrives are got according to shop A loss user, used here according to being lost in
The descending sort from big to small of the trading volume at family, shop A loss number of users is -11 here, wherein being lost to the 4 of shop C1
It is individual, 4 of shop C2 are lost to, the 3 of shop C3 is lost to, so as to obtain shop C1, shop C2, shop C3 as its second couple
As.
Finally, shop A each key feature feature corresponding with above-mentioned second object is compared respectively, obtained
Gap comparison result.Wherein gap comparison result can include gap contrast and Optimizing Suggestions (or referred to as result is fed back),
Corresponding result feedback is exported according to gap contrast.
Such as shop A physical inventory is 50, shop C1 and C2 physical inventory are 60, and shop C3 physical inventory is
70, it is assumed that take comparison index of the average value of the physical inventory of three the second objects as shop A physical inventory here, then thing
Stock's gap contrast=50- (60+60+70)/3 ≈ -13 are managed, now, system can be " storehouse to the Optimizing Suggestions that shop A is exported
Deposit very little, it is proposed that stock buildup ".In another example shop A picture numbers are 16, shop C1 picture number is 31, shop C2 figure
Piece quantity is 23, and shop C3 picture number is 55, then picture number gap contrast=16- (31+23+55)/3 ≈ -20, this
When, Optimizing Suggestions that system is exported to shop A can be " picture very little, it is proposed that upload more high-quality pictures ".Further for example, shop
It is 64 that low point of A, which comments on number, and shop C1 low point of comment number is 34, and low point of shop C2 comments on number as 50, low point of shop C3
It is 40 to comment on number, then low point of comment number gap contrast=(34+50+40)/3-64 ≈ -23, and now, the Optimizing Suggestions provided can be with
For " low point of comment number is too many, it is proposed that actively replys user comment and explains and misunderstands ".In another example shop A commodity richness is 4,
Shop C1 to C3 commodity richness is respectively 5,4 and 8, then commodity richness gap contrast=4- (5+4+8)/3 ≈ -1.6, this
When, the Optimizing Suggestions provided can be " increase type of merchandize ".
It should be noted that, although it is used as using the average value of the individual features of multiple second objects in above-described embodiment
The comparison characteristic value of the key feature of one object, but in other embodiments, the key feature of the first object can also be distinguished
It is compared with the individual features value of each second object in multiple second objects, or uses other calculation formula shapes
Formula, the disclosure are not construed as limiting to this.
Fig. 6 is a kind of block diagram of characteristics of objects processing unit according to an illustrative embodiments.
As shown in fig. 6, the characteristics of objects processing unit 100 can include fisrt feature acquisition module 110, the second object obtains
Modulus block 120 and characteristic determination module to be optimized 130.
Wherein, fisrt feature acquisition module 110 can be used for the fisrt feature for obtaining the first object;Second object acquisition mould
Block 120 is determined for the first user of first object, according to the first user of first object obtain with it is described
Second object corresponding to first object;The index determining module 130 to be optimized is used for according to the fisrt feature and described the
Two objects determine the feature to be optimized of first object
In the exemplary embodiment, fisrt feature acquisition module 110 may further include data collection module, importance
Output unit and fisrt feature acquiring unit.
Wherein, the data collection module can be used for counting the effect of first object in the first historical time section and refer to
Mark, and collect the characteristic of first object.
In the exemplary embodiment, when the characteristic of first object can include the opening of first object
Between, the finishing time, average score, high score scoring number, low point of scoring number, average price, the storehouse in the first historical time section
Deposit, the one or more in picture number, star, commodity richness etc..
The importance output unit can be used for obtaining significance level of each characteristic to the effectiveness indicator.
The fisrt feature acquiring unit can be used for the significance level to the effectiveness indicator according to each characteristic,
Obtain the fisrt feature of first object.
In the exemplary embodiment, the second object acquisition module 120 may further include user conversation acquiring unit with
And the first user's determining unit.
Wherein, the user conversation acquiring unit can be used for the use for obtaining first object in the second historical time section
Family session.
The first user statistic unit can be used for by the user conversation of first object not with described first pair
As the user to conclude the transaction is defined as the first user of first object.
In the exemplary embodiment, the second object acquisition module 120 can further include the second object acquisition unit.
Wherein, the second object acquisition unit can be used for obtaining uses in same user conversation with the first of first object
Other objects that family is concluded the transaction, by other described objects as second object.
In the exemplary embodiment, the characteristics of objects processing unit 100 can also include crucial second object acquisition module.
The crucial second object acquisition module may further include sequencing unit and crucial second object acquisition unit.
The sequencing unit can be used for second object being ranked up according to the trading volume with first user.
The crucial second object acquisition unit can be used for the second object using preparatory condition is met as described first
The object of key second of object.
In the exemplary embodiment, the index determining module 130 to be optimized is additionally operable to according to the fisrt feature and institute
State the feature to be optimized that crucial second object determines first object
It should be noted that the module of characteristics of objects processing unit and the specific implementation of unit in foregoing invention embodiment
The content for the characteristics of objects processing method being referred in foregoing invention embodiment, will not be repeated here.
According to the another exemplary embodiment of the disclosure, additionally provide a kind of electronic equipment, its can include memory,
Processor and the computer program that can be run on the memory and on the processor is stored in, wherein, the program is handled by this
Device realizes the method and step in foregoing invention embodiment when performing.
Below with reference to Fig. 7, it illustrates suitable for for realizing the structural representation of the electronic equipment 200 of the embodiment of the present application
Figure.Electronic equipment shown in Fig. 7 is only an example, the function and use range of the embodiment of the present application should not be brought any
Limitation.
As shown in fig. 7, electronic equipment 200 includes processor 201, it can be according to the program being stored in memory 203
And perform various appropriate actions and processing.Especially, in accordance with an embodiment of the present disclosure, above with reference to the process of flow chart description
It may be implemented as computer software programs.For example, embodiment of the disclosure includes a kind of computer program product, it includes holding
Computer program on a computer-readable medium is carried, the computer program includes the journey for being used for the method shown in execution flow chart
Sequence code, when the computer program is performed by processor 201, perform the above-mentioned function of being limited in the system of the application.Processing
Device 201, memory 203 and communication interface 202 are connected with each other by bus.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the device of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, a part for above-mentioned module, program segment or code include one or more
For realizing the executable instruction of defined logic function.It should also be noted that some as replace realization in, institute in square frame
The function of mark can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actual
On can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also
It is noted that the combination of each square frame and block diagram in block diagram or flow chart or the square frame in flow chart, can use and perform rule
Fixed function or the special hardware based system of operation are realized, or can use the group of specialized hardware and computer instruction
Close to realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor.
As on the other hand, the disclosure additionally provides a kind of computer-readable medium, and the computer-readable medium can be
Included in equipment described in above-described embodiment;Can also be individualism, and without be incorporated the equipment in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the equipment, makes
Obtaining the equipment includes:Obtain the fisrt feature of the first object;The first user of first object is determined, according to described first pair
The first user of elephant obtains the second object corresponding with first object;It is true according to the fisrt feature and second object
The feature to be optimized of fixed first object.
The illustrative embodiments of the disclosure are particularly shown and described above.It should be appreciated that the disclosure is unlimited
In detailed construction described herein, set-up mode or implementation method;On the contrary, the disclosure is intended to cover included in appended claims
Spirit and scope in various modifications and equivalence setting.
Claims (10)
- A kind of 1. characteristics of objects processing method, it is characterised in that including:Obtain the fisrt feature of the first object;The first user of first object is determined, is obtained and first object pair according to the first user of first object The second object answered;The feature to be optimized of first object is determined according to the fisrt feature and second object.
- 2. characteristics of objects processing method according to claim 1, it is characterised in that obtain the fisrt feature bag of the first object Include:The effectiveness indicator of first object in the first historical time section is counted, and collects the characteristic of first object;Obtain significance level of each characteristic to the effectiveness indicator;Significance level according to each characteristic to the effectiveness indicator, obtain the fisrt feature of first object.
- 3. characteristics of objects processing method according to claim 1, it is characterised in that determine that the first of first object uses Family includes:Obtain the user conversation of first object in the second historical time section;Using in the user conversation of first object not with the user that first object is concluded the transaction as first object The first user.
- 4. characteristics of objects processing method according to claim 3, it is characterised in that used according to the first of first object Family, which obtains the second object corresponding with first object, to be included:Other objects concluded the transaction in same user conversation with first user are obtained, will other described object conducts Second object.
- 5. according to any described characteristics of objects processing methods of claim 1-4, it is characterised in that methods described also includes:Second object is ranked up according to the trading volume with first user;Key second object of second object as first object of preparatory condition will be met;It is described to determine that the feature to be optimized of first object includes with second object according to the fisrt feature:The feature to be optimized of first object is determined according to the fisrt feature and crucial second object.
- 6. according to any described characteristics of objects processing methods of claim 1-4, it is characterised in that methods described also includes:Corresponding Optimizing Suggestions are determined for the feature to be optimized.
- A kind of 7. characteristics of objects processing unit, it is characterised in that including:Fisrt feature acquisition module, for obtaining the fisrt feature of the first object;Second object acquisition module, for determining the first user of first object, used according to the first of first object Family obtains the second object corresponding with first object;Characteristic determination module to be optimized, for determining treating for first object according to the fisrt feature and second object Optimize feature.
- 8. characteristics of objects processing unit according to claim 7, it is characterised in that the second object acquisition module includes User conversation acquiring unit and first user's determining unit;Wherein, the user conversation acquiring unit is gone through for obtaining second The user conversation of first object in the history period;The first user determining unit is used to that friendship will not to be reached with first object in the user conversation of first object Easy user is defined as the first user of first object.
- 9. a kind of electronic equipment, including memory, processor and it is stored on the memory and can runs on the processor Computer program, it is characterised in that the method step described in claim any one of 1-6 is realized when the program is by the computing device Suddenly.
- 10. a kind of computer-readable medium, is stored thereon with computer program, it is characterised in that described program is held by processor The method and step as described in claim 1-6 is any is realized during row.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710601743.8A CN107358512A (en) | 2017-07-21 | 2017-07-21 | Characteristics of objects processing method and processing device, electronic equipment |
CN201711085312.7A CN107730369B (en) | 2017-07-21 | 2017-11-07 | Object feature processing method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710601743.8A CN107358512A (en) | 2017-07-21 | 2017-07-21 | Characteristics of objects processing method and processing device, electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107358512A true CN107358512A (en) | 2017-11-17 |
Family
ID=60284390
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710601743.8A Pending CN107358512A (en) | 2017-07-21 | 2017-07-21 | Characteristics of objects processing method and processing device, electronic equipment |
CN201711085312.7A Active CN107730369B (en) | 2017-07-21 | 2017-11-07 | Object feature processing method and device and electronic equipment |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711085312.7A Active CN107730369B (en) | 2017-07-21 | 2017-11-07 | Object feature processing method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN107358512A (en) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8386285B2 (en) * | 2011-05-25 | 2013-02-26 | International Business Machines Corporation | Demand modeling and prediction in a retail category |
JP2015082246A (en) * | 2013-10-23 | 2015-04-27 | 東芝テック株式会社 | Sales information presentation method and sales information presentation program |
-
2017
- 2017-07-21 CN CN201710601743.8A patent/CN107358512A/en active Pending
- 2017-11-07 CN CN201711085312.7A patent/CN107730369B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107730369A (en) | 2018-02-23 |
CN107730369B (en) | 2020-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111008858B (en) | Commodity sales prediction method and system | |
US20140108190A1 (en) | Recommending product information | |
CN109816482B (en) | Knowledge graph construction method, device and equipment of e-commerce platform and storage medium | |
CN109840796B (en) | Decision factor analysis device and decision factor analysis method | |
CN106469382A (en) | Idle merchandise items information processing method and device | |
CN110457577B (en) | Data processing method, device, equipment and computer storage medium | |
CN102609422A (en) | Class misplacing identification method and device | |
CN112750011A (en) | Commodity recommendation method and device and electronic equipment | |
CN103631801B (en) | A kind of method and device that merchandise news is provided | |
US10255300B1 (en) | Automatically extracting profile feature attribute data from event data | |
CN106934648A (en) | A kind of data processing method and device | |
CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
CN110570233A (en) | User buyback time prediction method and device for e-commerce platform | |
CN110602532A (en) | Entity article recommendation method, device, server and storage medium | |
CN108133390A (en) | For predicting the method and apparatus of user behavior and computing device | |
CN104992348A (en) | Method and device for displaying information | |
CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
CN115953182A (en) | Commodity sales promotion method and device, computer equipment and storage medium | |
CN110427545B (en) | Information pushing method and system | |
CN111951051B (en) | Method, device and system for recommending products to clients | |
CN116501979A (en) | Information recommendation method, information recommendation device, computer equipment and computer readable storage medium | |
CN107358512A (en) | Characteristics of objects processing method and processing device, electronic equipment | |
CN109146606A (en) | A kind of brand recommended method, electronic equipment, storage medium and system | |
CN111026933B (en) | Content recommendation method and device, electronic equipment and storage medium | |
CN113297467A (en) | Recommendation method, recommendation device and computer storage medium |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171117 |