CN110363570A - Classification methods of exhibiting, device, electronic equipment and storage medium in - Google Patents
Classification methods of exhibiting, device, electronic equipment and storage medium in Download PDFInfo
- Publication number
- CN110363570A CN110363570A CN201910533779.6A CN201910533779A CN110363570A CN 110363570 A CN110363570 A CN 110363570A CN 201910533779 A CN201910533779 A CN 201910533779A CN 110363570 A CN110363570 A CN 110363570A
- Authority
- CN
- China
- Prior art keywords
- classification
- search key
- application
- kinds
- probability
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses classification methods of exhibiting, device, electronic equipment and the storage mediums in application.The described method includes: obtaining the real-time search key set of target user；The target user is calculated to purpose preference probability all kinds of in application according to real-time search key set；According to preference determine the probability classification displaying sequence, show that classification corresponding at least partly classification identifies in the specified page of application according to classification displaying sequence；Using the triggering known in response to target class target, the page that corresponding classification is known with the target class target is jumped to from specified page.Beneficial effect is, it is conceived to this object for being ignored in the prior art of classification, the personalized of classification is realized to show, and sorting is realized based on the real-time search behavior of user, such as classification sequence can be carried out according to the keyword that new user's same day searched for, the offline preference of long history that user can not depended on, provides more good experience for user.
Description
Technical field
This application involves field of computer technology, and in particular to classification methods of exhibiting, device, electronic equipment in application and
Storage medium.
Background technique
Personalized service can bring more good experience for user, it helps the benefit for increasing service side is
A kind of mode of two-win.Therefore for provide plurality of optional service/goods service side for, by the service of user's more preference/
The forward displaying of commodity is a kind of resolving ideas, the sortord for also just needing accuracy high, and due to the attribute of different objects
Difference, the details of sortord is also just multifarious, and often a certain sortord is to A class commodity superior, but takes to B class
Business is but difficult to the effect played.
In addition, service/goods often can be divided into multiple classifications, on the one hand in the prior art also by modes such as clusters
Personalized displaying is carried out without reference to classification；On the other hand as previously mentioned, the attribute of classification and service/goods are there are difference,
Usual sortord is being directly converted to the effect that also can have not necessarily played when classification sequence, it is therefore desirable to a kind of effective
Carry out the mode of classification personalization displaying.
Summary of the invention
In view of the above problems, it proposes on the application overcomes the above problem or at least be partially solved in order to provide one kind
State classification methods of exhibiting, device, electronic equipment and the storage medium in the application of problem.
According to the one aspect of the application, the classification methods of exhibiting in a kind of application is provided, comprising:
Obtain the real-time search key set of target user；
The target user is calculated to purpose preference probability all kinds of in application according to the real-time search key set；
According to the preference determine the probability classification displaying sequence, according to the classification displaying sequence in the specified of the application
Classification mark corresponding at least partly classification is shown in the page；
It is described to apply the triggering known in response to target class target, it jumps to from the specified page and knows with the target class target
The page of corresponding classification.
Optionally, the search key in the real-time search key set includes:
Target user worked as in a consecutive days, in the application used search key.
It is optionally, described that according to the real-time search key set to calculate the target user inclined to purposes all kinds of in application
Good probability includes:
Determine each search key in historical search keyword set each according to the historical use data of the application
The preference probability of class now；
Each search key in real-time search key set is substituted into preset Piao in all kinds of preference probability now
The target user is calculated to all kinds of purpose preference probability in plain Bayesian formula.
Optionally, the historical use data according to the application determines each search in historical search keyword set
Keyword includes: in all kinds of preference probability now
According to the historical use data of the application, statistics obtains each search key in historical search keyword set
In all kinds of click-through-rates now；
The click-through-rate is smoothed, each search key obtained in historical search keyword set exists
All kinds of preference probability now.
Optionally, described that the click-through-rate is smoothed, it obtains each in historical search keyword set
Search key includes: in all kinds of preference probability now
By each search key in historical search keyword set in all kinds of click-through-rates now multiplied by corresponding
Confidence parameter obtains each search key in historical search keyword set in all kinds of preference probability now.
Optionally, keyword is specified search in the specified click-through-rate institute of class now in historical search keyword set
Corresponding confidence parameter Z is obtained by following formula:
N=p (1-p) Z2/D2；
Wherein, n is to specify search for keyword described in each user determined according to the historical use data passes through to click
Up to the amount of showing of the specified classification；P is precompensation parameter；D is default precision；Confidence parameter Z takes positive number.
Optionally, each search key by real-time search key set is in all kinds of preference probability generations now
Enter preset naive Bayesian formula, the target user is calculated includes: to all kinds of purpose preference probability
Based on formulaUser U is calculated to the preference probability of classification C；
Wherein, Odds (C, U) is calculated by following formula:
Wherein, P (C=1) is the prior probability of classification C；P (C=1 | Wj) it is search key WjPreference at classification C
Probability.
According to the another aspect of the application, the classification provided in a kind of application shows device, comprising:
Data capture unit is searched for, for obtaining the real-time search key set of target user；
Preference probability calculation unit, for calculating the target user in application according to the real-time search key set
All kinds of purpose preference probability；
Display unit, for existing according to the classification displaying sequence according to the preference determine the probability classification displaying sequence
Classification mark corresponding at least partly classification is shown in the specified page of the application；
It is described to apply the triggering known in response to target class target, it jumps to from the specified page and knows with the target class target
The page of corresponding classification.
Optionally, the search key in the real-time search key set includes:
Target user worked as in a consecutive days, in the application used search key.
Optionally, the preference probability calculation unit, for determining that history is searched according to the historical use data of the application
Each search key in rope keyword set is in all kinds of preference probability now；By respectively searching in real-time search key set
Rope keyword substitutes into preset naive Bayesian formula in all kinds of preference probability now, and the target user is calculated to all kinds of
Purpose preference probability.
Optionally, the preference probability calculation unit, for the historical use data according to the application, statistics is gone through
Each search key in history search key set is in all kinds of click-through-rates now；The click-through-rate is carried out flat
Sliding processing, obtains each search key in historical search keyword set in all kinds of preference probability now.
Optionally, the preference probability calculation unit, for by each search key in historical search keyword set
In all kinds of click-through-rates now multiplied by corresponding confidence parameter, each search obtained in historical search keyword set is crucial
Word is in all kinds of preference probability now.
Optionally, keyword is specified search in the specified click-through-rate institute of class now in historical search keyword set
Corresponding confidence parameter Z is obtained by following formula:
N=p (1-p) Z2/D2；
Wherein, n is to specify search for keyword described in each user determined according to the historical use data passes through to click
Up to the amount of showing of the specified classification；P is precompensation parameter；D is default precision；Confidence parameter Z takes positive number.
Optionally, the preference probability calculation unit, for being based on formulaIt calculates
User U is obtained to the preference probability of classification C；Wherein, Odds (C, U) is calculated by following formula:Wherein, P (C=1) is the prior probability of classification C；P(C
=1 | Wj) it is search key WjPreference probability at classification C.
According to the another aspect of the application, a kind of electronic equipment is provided, comprising: processor；And it is arranged to store
The memory of computer executable instructions, the executable instruction execute the processor such as any of the above-described institute
The method stated.
According to the application's in another aspect, providing a kind of computer readable storage medium, wherein described computer-readable
Storage medium stores one or more programs, and one or more of programs when being executed by a processor, are realized as any of the above-described
The method.
It can be seen from the above, the technical solution of the application is calculated by obtaining the real-time search key set of target user
Target user is to purpose preference probability all kinds of in application out, thus according to preference determine the probability classification displaying sequence, according to classification
Displaying sequence shows that corresponding at least partly classification classification identifies in the specified page of application so that using in response to
The triggering that target class target is known, the page that corresponding classification is known with the target class target is jumped to from specified page.The technical side
The beneficial effect of case is, is conceived to this object for being ignored in the prior art of classification, realizes the personalized of classification and show,
And sort be is realized based on user's real-time search behavior, such as can according to the keyword that new user searched on the same day into
The sequence of row classification, can not depend on the offline preference of long history of user, provide more good experience for user.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the application can
It is clearer and more comprehensible, below the special specific embodiment for lifting the application.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the application
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows the flow diagram of the classification methods of exhibiting in a kind of application according to the application one embodiment；
Fig. 2 shows the structural schematic diagrams that device is shown according to the classification in a kind of application of the application one embodiment；
Fig. 3 shows the structural schematic diagram of the electronic equipment according to the application one embodiment；
Fig. 4 shows the structural schematic diagram of the computer readable storage medium according to the application one embodiment；
Fig. 5 shows the application main interface schematic diagram according to the application one embodiment.
Specific embodiment
The exemplary embodiment of the application is more fully described below with reference to accompanying drawings.Although showing the application in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the application without should be by embodiments set forth here
It is limited.It is to be able to thoroughly understand the application on the contrary, providing these embodiments, and can be by scope of the present application
It is fully disclosed to those skilled in the art.
Fig. 1 shows the flow diagram of the classification methods of exhibiting in a kind of application according to the application one embodiment.
As shown in Figure 1, this method comprises:
Step S110 obtains the real-time search key set of target user.Here real-time search key is integrated into
It can be understood as search key only current comprising user in the narrow sense, in a broad sense it can also be expected that comprising user nearest
Used search key in a period of time (such as in the same day or a few houres).
It is general to purpose preferences all kinds of in application to calculate the target user according to real-time search key set by step S120
Rate.
Classification in the application, which can be, to be clustered certain commodity with same alike result or service to obtain.Example
Such as men's clothing, women's dress can belong to clothes classification；Chafing dish, ration etc. belong to food and drink classification.Classification can divide multiple ranks,
Such as men's clothing, women's dress all can serve as junior's classification of clothes.
And for step S120, the preference probability of classification is calculated, can be carried out for the classification shown is needed.Such as it is right
In the classification in main interface, rank is higher, then according to search key calculate be target user to hotel, food and drink, amusement
Etc. the preference of advanced classification；For the classification in sub-interface, rank is relatively low, then according to search key calculate be mesh
User is marked to the preference of the rudimentary classifications such as longuette, short skirt and trousers skirt.In a specific embodiment, classification is belonging to current page
The second level classification of class now, second level classification are usually ignored by technical solution in the prior art, but actually again closer to
The real demand at family, therefore the classification displaying sequence of second level classification is optimized and is of great significance.
Step S130, according to preference determine the probability classification displaying sequence, according to classification displaying sequentially in the specific page of application
Classification mark corresponding at least partly classification is shown in face.
Fig. 5 shows the application main interface schematic diagram according to the application one embodiment.As shown in figure 5, being wrapped in main interface
An icon has been respectively corresponded containing amusement, food and drink, hairdressing, training, hotel, performance classification and other recommendations, each classification
(icon) and text.In embodiments herein, classification mark includes at least one of text, icon, symbol, can also be with
For other forms.
Using the triggering known in response to target class target, class corresponding with the target class target knowledge is jumped to from specified page
The purpose page.Such as user clicks the icon that classification is entertained in Fig. 5, then application jumps to the page of amusement classification, opens up wherein
Show that KTV, swimming, secret room such as escape at juniors' classification and the new recommendation.
As it can be seen that method shown in FIG. 1, it is conceived to this object for being ignored in the prior art of classification, realizes classification
Personalization is shown, and sorting is to be realized based on the real-time search behavior of user, such as can be searched for according to new user's same day
The keyword crossed carries out classification sequence, can not depend on the offline preference of long history of user, provide for user more good
Experience.
Search key packet in one embodiment of the application, in the above method, in real-time search key set
Include: target user worked as in a consecutive days, in the application used search key.
Many applications are all supported to scan in application, such as user may search for " spring clothing ", " cinema ", " chafing dish "
Deng, using can according to the search of user provide result of page searching, show relevant commodity or service wherein.
Target user when in consecutive days used search key can be considered as under certain business scenarios
The real-time behavioral data of user is different from user in used search key before --- under certain business scenarios also referred to as
Historical behavior data or offline behavioral data.It is such be advantageous in that can be current closer to user demand, such as use
Mobile phone is lent other people and used by family, and user produces new hobby etc. situation, can quickly make the change in sequence.Using
, can be according to the High relevancy of search behavior and application using interior used search key, recommendation effect is more preferable.
In one embodiment of the application, in the above method, which is calculated according to the real-time search key set
Marking user to include to purpose preference probability all kinds of in application includes: to determine historical search according to the historical use data of the application
Each search key in keyword set is in all kinds of preference probability now；By each search in real-time search key set
Keyword substitutes into preset naive Bayesian formula in all kinds of preference probability now, and the target user is calculated to each classification
Preference probability.
Here, historical use data can be all users of the use application got by modes such as log recordings
Or the user data of a part of user (such as high-quality user), it also just contains each user and goes over used search key,
So as to determine historical search keyword set, the purpose is to by way of big data analysis, determine historical search key
Each search key is in all kinds of preference probability now in set of words.In one embodiment of the application, root in the above method
Determine each search key in historical search keyword set in all kinds of now inclined according to the historical use data of the application
Good probability includes: according to the historical use data of the application, and statistics obtains each search in historical search keyword set and closes
Keyword is in all kinds of click-through-rates now；The click-through-rate is smoothed, historical search keyword set is obtained
Each search key in conjunction is in all kinds of preference probability now.
CTR (Click-Through-Rate, click-through-rate) refers to actual click number in Internet advertising field
Divided by the amount of showing of advertisement.This application involves search scene under, it is similar it is previously described as, when user is interior defeated in application
After entering a search key, using result of page searching can be provided according to the search of user, relevant commodity are shown wherein
Or service.User clicks these commodity or service, can reach the details page of corresponding commodity or service, and this click behavior can be by
It records.And corresponding commodity or service when belonging to which classification it is believed that therefore, (example for a period of time can be passed through
Such as half a year) in the search-related data applied, determine each search key in historical search keyword set it is all kinds of now
CTR.In order to further increase precision, can be determined each in historical search keyword set by the way of smoothing processing
Search key is in all kinds of preference probability now.
In one embodiment of the application, in the above method, the click-through-rate is smoothed, is gone through
Each search key in history search key set includes: by historical search keyword set in all kinds of preference probability now
In each search key in all kinds of click-through-rates now multiplied by corresponding confidence parameter, obtain historical search keyword set
Each search key in conjunction is in all kinds of preference probability now.Specifically, in one embodiment of the application, the above method
In, keyword confidence corresponding to the specified click-through-rate of class now ginseng is specified search in historical search keyword set
Number Z is obtained by following formula: n=p (1-p) Z2/D2；Wherein, n is to be led to according to each user that historical use data determines
Cross the amount of showing that keyword clicks the specified classification of arrival that specifies search for；P is precompensation parameter；D is default precision；Confidence parameter Z takes
Positive number.
Embodiments described above utilize statistical confidence parameters to be smoothed to click-through-rate.In statistics
In, it when some proportion (such as masculinity proportion) is interested in totality, needs to face a problem: should be extracted from totality more
Few sample size.
Formula n=p (1-p) Z2/D2Utilization, sample size can be obtained by the standard deviation formula of ratio.P specifically can be with
Ratio when for sampling early period in sample, when practical application, can carry out conservative estimation by 0.5.
Under analogy to the scene of the embodiment of the present application, when a given combination (search key+classification), problem are as follows: right
Overall click ratio should take how many sample sizes (exposure PV) when interested.And since exposure PV is by daily record data etc.
The known quantity that can be known, then we can use that above-mentioned formula is counter to push letter parameter.
In one embodiment of the application, in the above method, each search by real-time search key set
Keyword substitutes into preset naive Bayesian formula in all kinds of preference probability now, and the target user is calculated to each classification
Preference probability include: based on formulaIt is general to the preference of classification C that user U is calculated
Rate；Wherein, Odds (C, U) is calculated by following formula:
Wherein, P (C=1) is the prior probability of classification C；P (C=1 | Wj) it is search key WjPreference probability at classification C.Pass through
Above-mentioned formula can calculate user to all kinds of purpose preference probability, to be ranked up.The prior probability of classification can also pass through
Data are searched for determine, for example, there are many classifications in all results, user clicks certain classifications, then the elder generation of these classifications
It is higher to test probability.Certainly prior probability can also be determined using other modes in other embodiments, such as promotes priority
Etc..
Present embodiments are suitable for the recommendation to classification, compare test by the displaying to second level classification,
Icon clicking rate promotes 0.06PT.Based on this, can be recommended with further progress respective class purpose material.
Fig. 2 shows the structural schematic diagrams that device is shown according to the classification in a kind of application of the application one embodiment.
As shown in Fig. 2, the classification in shows that device 200 includes:
Data capture unit 210 is searched for, for obtaining the real-time search key set of target user.
Preference probability calculation unit 220, it is corresponding for calculating the target user according to the real-time search key set
All kinds of purpose preference probability in.
Display unit 230 is used for according to preference determine the probability classification displaying sequence, according to classification displaying sequence in application
Classification mark corresponding at least partly classification is shown in specified page.
Using the triggering known in response to target class target, class corresponding with the target class target knowledge is jumped to from specified page
The purpose page.
As it can be seen that device shown in Fig. 2, it is conceived to this object for being ignored in the prior art of classification, realizes classification
Personalization is shown, and sorting is to be realized based on the real-time search behavior of user, such as can be searched for according to new user's same day
The keyword crossed carries out classification sequence, can not depend on the offline preference of long history of user, provide for user more good
Experience.
In one embodiment of the application, in above-mentioned apparatus, the search in the real-time search key set is crucial
Word includes: that target user worked as in a consecutive days, in the application used search key.
In one embodiment of the application, in above-mentioned apparatus, preference probability calculation unit 220, for being answered according to
Historical use data determines each search key in historical search keyword set in all kinds of preference probability now；It will
Each search key in real-time search key set substitutes into preset naive Bayesian public affairs in all kinds of preference probability now
The target user is calculated to all kinds of purpose preference probability in formula.
In one embodiment of the application, in above-mentioned apparatus, preference probability calculation unit 220, for being answered according to
Historical use data, it is logical in all kinds of clicks now that statistics obtains each search key in historical search keyword set
Cross rate；The click-through-rate is smoothed, obtains each search key in historical search keyword set each
The preference probability of class now.
In one embodiment of the application, in above-mentioned apparatus, preference probability calculation unit 220 is used for historical search
Each search key in keyword set, multiplied by corresponding confidence parameter, obtains history and searches in all kinds of click-through-rates now
Each search key in rope keyword set is in all kinds of preference probability now.
In one embodiment of the application, in above-mentioned apparatus, key is specified search in historical search keyword set
Word confidence parameter Z corresponding to the specified click-through-rate of class now is obtained by following formula: n=p (1-p) Z2/
D2；Wherein, n is that each user determined according to historical use data clicks the exhibition of the specified classification of arrival by specifying search for keyword
Now measure；P is precompensation parameter；D is default precision；Confidence parameter Z takes positive number.
In one embodiment of the application, in above-mentioned apparatus, preference probability calculation unit 220, for being based on formulaUser U is calculated to the preference probability of classification C；Wherein, Odds (C, U) passes through as follows
Formula is calculated:Wherein, P (C=1) is classification C's
Prior probability；P (C=1 | Wj) it is search key WjPreference probability at classification C.
It should be noted that the specific embodiment of above-mentioned each Installation practice is referred to aforementioned corresponding method embodiment
Specific embodiment carry out, details are not described herein.
In conclusion the technical solution of the application is calculated by obtaining the real-time search key set of target user
Target user is to purpose preference probability all kinds of in application, thus according to preference determine the probability classification displaying sequence, according to classification exhibition
Show that sequence shows classification mark corresponding at least partly classification in the specified page of application, so that using in response to mesh
The triggering for marking classification mark, the page that corresponding classification is known with the target class target is jumped to from specified page.The technical solution
Beneficial effect be, be conceived to this object for being ignored in the prior art of classification, realize the personalized of classification and show, and
And sequence is to be realized based on the real-time search behavior of user, such as can be carried out according to the keyword that new user's same day searched for
Classification sequence, can not depend on the offline preference of long history of user, provide more good experience for user.
It should be understood that
Algorithm and display be not inherently related to any certain computer, virtual bench or other equipment provided herein.
Various fexible units can also be used together with teachings based herein.As described above, it constructs required by this kind of device
Structure be obvious.In addition, the application is also not for any particular programming language.It should be understood that can use various
Programming language realizes present context described herein, and the description done above to language-specific is to disclose this Shen
Preferred forms please.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the application
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the application and help to understand one or more of the various inventive aspects,
Above in the description of the exemplary embodiment of the application, each feature of the application is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield this application claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as the separate embodiments of the application.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means to be in the application's
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
The various component embodiments of the application can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize that the classification in the application according to the embodiment of the present application is shown in device
Some or all components some or all functions.The application is also implemented as executing side as described herein
Some or all device or device programs (for example, computer program and computer program product) of method.It is such
It realizes that the program of the application can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or with any other shape
Formula provides.
For example, Fig. 3 shows the structural schematic diagram of the electronic equipment according to the application one embodiment.The electronic equipment
300 include processor 310 and the memory for being arranged to storage computer executable instructions (computer readable program code)
320.Memory 320 can be such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk or
The electronic memory of ROM etc.Memory 320 has the computer stored for executing any method and step in the above method
The memory space 330 of readable program code 331.For example, the memory space 330 for storing computer readable program code can be with
Including being respectively used to realize each computer readable program code 331 of the various steps in above method.It is computer-readable
Program code 331 can read or be written to this one or more calculating from one or more computer program product
In machine program product.These computer program products include such as hard disk, the journey of compact-disc (CD), storage card or floppy disk etc
Sequence code carrier.Such computer program product is usually computer readable storage medium described in such as Fig. 4.Fig. 4 is shown
According to a kind of structural schematic diagram of the computer readable storage medium of the application one embodiment.The computer-readable storage medium
Matter 400 is stored with for executing the computer readable program code 331 according to the present processes step, can be by electronic equipment
300 processor 310 is read, and when computer readable program code 331 is run by electronic equipment 300, leads to the electronic equipment
300 execute each step in method described above, specifically, the computer of the computer-readable recording medium storage
Readable program code 331 can execute method shown in any of the above-described embodiment.Computer readable program code 331 can be with
Appropriate form is compressed.
The application is limited it should be noted that above-described embodiment illustrates rather than the application, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The application can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (10)
1. the classification methods of exhibiting in a kind of application, which is characterized in that this method comprises:
Obtain the real-time search key set of target user；
The target user is calculated to purpose preference probability all kinds of in application according to the real-time search key set；
According to the preference determine the probability classification displaying sequence, according to the classification displaying sequentially in the specified page of the application
It is middle to show classification mark corresponding at least partly classification；
It is described to apply the triggering known in response to target class target, it is jumped to from the specified page corresponding with the target class target knowledge
Classification the page.
2. the method as described in claim 1, which is characterized in that the search key packet in the real-time search key set
It includes:
Target user worked as in a consecutive days, in the application used search key.
3. the method as described in claim 1, which is characterized in that described to calculate the mesh according to the real-time search key set
Mark user includes: to purpose preference probability all kinds of in application
Determine each search key in historical search keyword set in each classification according to the historical use data of the application
Under preference probability；
Each search key in real-time search key set is substituted into preset simple shellfish in all kinds of preference probability now
The target user is calculated to all kinds of purpose preference probability in this formula of leaf.
4. method as claimed in claim 3, which is characterized in that the historical use data according to the application determines history
Each search key in search key set includes: in all kinds of preference probability now
According to the historical use data of the application, statistics obtains each search key in historical search keyword set each
The click-through-rate of class now；
The click-through-rate is smoothed, obtains each search key in historical search keyword set all kinds of
Now preference probability.
5. method as claimed in claim 4, which is characterized in that it is described that the click-through-rate is smoothed, it obtains
Each search key in historical search keyword set includes: in all kinds of preference probability now
By each search key in historical search keyword set in all kinds of click-through-rates now multiplied by corresponding confidence
Parameter obtains each search key in historical search keyword set in all kinds of preference probability now.
6. method as claimed in claim 5, which is characterized in that the keyword that specifies search in historical search keyword set exists
Confidence parameter Z corresponding to the click-through-rate of specified class now is obtained by following formula:
N=p (1-p) Z2/D2；
Wherein, n clicks arrival institute by the keyword that specifies search for for each user determined according to the historical use data
State the amount of showing of specified classification；P is precompensation parameter；D is default precision；Confidence parameter Z takes positive number.
7. method as claimed in claim 3, which is characterized in that described that each search in real-time search key set is crucial
Word substitutes into preset naive Bayesian formula in all kinds of preference probability now, and it is inclined to all kinds of purposes that the target user is calculated
Good probability includes:
Based on formulaUser U is calculated to the preference probability of classification C；
Wherein, Odds (C, U) is calculated by following formula:
Wherein, P (C=1) is the prior probability of classification C；P (C=1 | Wj) it is search key WjPreference probability at classification C.
8. a kind of classification in application shows device, which is characterized in that the device includes:
Data capture unit is searched for, for obtaining the real-time search key set of target user；
Preference probability calculation unit, for calculating the target user to all kinds of in application according to the real-time search key set
Purpose preference probability；
Display unit is used for according to the preference determine the probability classification displaying sequence, according to the classification displaying sequence described
Classification mark corresponding at least partly classification is shown in the specified page of application；
It is described to apply the triggering known in response to target class target, it is jumped to from the specified page corresponding with the target class target knowledge
Classification the page.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes: processor；And be arranged to storage computer can
The memory executed instruction, the executable instruction execute the processor as any in claim 1-7
Method described in.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage is one or more
Program, one or more of programs when being executed by a processor, realize such as method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910533779.6A CN110363570A (en) | 2019-06-19 | 2019-06-19 | Classification methods of exhibiting, device, electronic equipment and storage medium in |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910533779.6A CN110363570A (en) | 2019-06-19 | 2019-06-19 | Classification methods of exhibiting, device, electronic equipment and storage medium in |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110363570A true CN110363570A (en) | 2019-10-22 |
Family
ID=68217432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910533779.6A Pending CN110363570A (en) | 2019-06-19 | 2019-06-19 | Classification methods of exhibiting, device, electronic equipment and storage medium in |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363570A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080339A (en) * | 2019-11-18 | 2020-04-28 | 口口相传(北京)网络技术有限公司 | Method and device for generating category preference data based on scene |
| CN112068941A (en) * | 2020-09-03 | 2020-12-11 | 北京百度网讯科技有限公司 | Application invoking method and device, electronic equipment and storage medium |
| CN112734538A (en) * | 2021-04-01 | 2021-04-30 | 北京三快在线科技有限公司 | Accommodation supply display method and device and electronic equipment |
-
2019
- 2019-06-19 CN CN201910533779.6A patent/CN110363570A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080339A (en) * | 2019-11-18 | 2020-04-28 | 口口相传(北京)网络技术有限公司 | Method and device for generating category preference data based on scene |
| CN111080339B (en) * | 2019-11-18 | 2024-01-30 | 口口相传(北京)网络技术有限公司 | Scene-based category preference data generation method and device |
| CN112068941A (en) * | 2020-09-03 | 2020-12-11 | 北京百度网讯科技有限公司 | Application invoking method and device, electronic equipment and storage medium |
| CN112068941B (en) * | 2020-09-03 | 2023-07-21 | 北京百度网讯科技有限公司 | Application calling method and device, electronic equipment and storage medium |
| CN112734538A (en) * | 2021-04-01 | 2021-04-30 | 北京三快在线科技有限公司 | Accommodation supply display method and device and electronic equipment |
| CN112734538B (en) * | 2021-04-01 | 2021-08-06 | 北京三快在线科技有限公司 | Accommodation supply display method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110941740B (en) | Video recommendation method and computer-readable storage medium | |
| CN103440335B (en) | Video recommendation method and device | |
| JP5736469B2 (en) | Search keyword recommendation based on user intention | |
| CN102929939B (en) | The offer method and device of customized information | |
| EP3139288A1 (en) | Item recommendation method and device | |
| CA3153598A1 (en) | Method of and device for predicting video playback integrity | |
| CN109829108B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN109300059B (en) | Dish recommending method and device | |
| WO2015034850A2 (en) | Feature selection for recommender systems | |
| CN108536694A (en) | Estimation method, device and the terminal device of user preference | |
| KR20160137935A (en) | Method, apparatus and server of dispalying social network information flow | |
| CN110363570A (en) | Classification methods of exhibiting, device, electronic equipment and storage medium in | |
| CN105512180B (en) | A kind of search recommended method and device | |
| WO2015154679A1 (en) | Method and device for ranking search results of multiple search engines | |
| CN103942328B (en) | A kind of video retrieval method and video-unit | |
| CN109241455B (en) | Recommended object display method and device | |
| KR101639656B1 (en) | Method and server apparatus for advertising | |
| CN106874335A (en) | Behavioral data processing method, device and server | |
| CN111259272B (en) | Search result ordering method and device | |
| CN110020152B (en) | Application recommendation method and device | |
| CN106557556A (en) | A kind of methods of exhibiting of Webpage, device, server and system | |
| CN109543113B (en) | Method and device for determining click recommendation words, storage medium and electronic equipment | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN109558538B (en) | Input association word construction method and device, storage medium and electronic equipment | |
| CN105786910B (en) | Entry weighing computation method and device |
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 |