CN107507028A - User preference determines method, apparatus, equipment and storage medium - Google Patents
User preference determines method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN107507028A CN107507028A CN201710699894.1A CN201710699894A CN107507028A CN 107507028 A CN107507028 A CN 107507028A CN 201710699894 A CN201710699894 A CN 201710699894A CN 107507028 A CN107507028 A CN 107507028A
- Authority
- CN
- China
- Prior art keywords
- user
- brand image
- word
- brand
- image word
- 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.)
- Granted
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- 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
-
- 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
Abstract
The disclosure is directed to a kind of user preference to determine method, apparatus, electronic equipment and storage medium.This method includes:The Shopping Behaviors data of statistics user corresponding with various brands image word in brand image dictionary, wherein, brand image word corresponding with various brands title is stored with the brand image dictionary;Shopping Behaviors data based on user calculate degree of membership of the user to various brands image word by fuzzy clustering;And degree of membership is defined as to the brand image of user preference more than the brand image word of first threshold.The disclosure can efficiently excavate the brand image of user preference from the Shopping Behaviors data of user, so can deeper level excavate customers' consumption psychology and preference, be easy to precision marketing, and reduce cost of labor.
Description
Technical field
This disclosure relates to big data technical field, method, user preference are determined in particular to a kind of user preference
Determining device, electronic equipment and computer-readable recording medium.
Background technology
With the extensive use of big data technology, precision marketing has become brand business in electronic commerce affair practice and entered
The important channel of row marketing activity, how to carry out precision marketing to the preference of brand image according to user turns into a weight
Want research direction.
At present, the determination of user preference is mainly to be realized by the scheme of survey.In this scheme, one
Aspect is manually carried out due to needing, and efficiency is low;On the other hand judged because user is mainly based upon subjective factor, it is difficult
Accurately to draw the brand image of the real preference of user, so as to which the precision marketing to user can not be realized.
A kind of accordingly, it is desirable to provide user preference determination side that can solve the problem that one or more of above mentioned problem problem
Method and user preference determining device.
It should be noted that information is only used for strengthening to the background of the disclosure disclosed in above-mentioned background section
Understand, therefore can include not forming the information to prior art known to persons of ordinary skill in the art.
The content of the invention
The purpose of the disclosure be to provide a kind of user preference determine method, user preference determining device, electronic equipment with
And computer-readable recording medium, and then at least overcome to a certain extent due to limitation and the defect of correlation technique and cause
One or more problem.
According to an aspect of this disclosure, there is provided a kind of user preference determines method, including:
The Shopping Behaviors data of statistics user corresponding with various brands image word in brand image dictionary, wherein, the product
Brand image word corresponding with various brands title is stored with board image dictionary;
Person in servitude of the user to various brands image word is calculated by fuzzy clustering based on the Shopping Behaviors data of the user
Category degree;And
The degree of membership is defined as to the brand image of the user preference more than the brand image word of first threshold.
In a kind of exemplary embodiment of the disclosure, the Shopping Behaviors data based on the user pass through fuzzy clustering
Calculate the user includes to the degree of membership of various brands image word:
Calculate the distance between Shopping Behaviors data and various brands image word of the user;
Degree of membership of the user to various brands image word is calculated based on the distance.
In a kind of exemplary embodiment of the disclosure, the user preference determines that method also includes:
By every merchandise news brand image word progress corresponding with various brands title in commodity information database
Match somebody with somebody.
In a kind of exemplary embodiment of the disclosure, the user preference determines that method also includes:
Every merchandise news and the brand image word based on matching are generated on every merchandise news and the brand
The frequent item set of vivid word;
Merchandise news support being more than in the frequent item set of Second Threshold is added in the brand image dictionary.
In a kind of exemplary embodiment of the disclosure, generate on every merchandise news and the brand image word
Frequent item set includes:
By FP-growth computings generation on every merchandise news and the frequent item set of brand image word.
In a kind of exemplary embodiment of the disclosure, statistics is corresponding with various brands image word in brand image dictionary
The Shopping Behaviors data of user include:
The Shopping Behaviors data of user are normalized;
The shopping row of the statistics user through normalized corresponding with various brands image word in brand image dictionary
For data.
According to an aspect of this disclosure, there is provided a kind of user preference determining device, including:
Statistic unit, for counting the Shopping Behaviors number of user corresponding with various brands image word in brand image dictionary
According to, wherein, brand image word corresponding with various brands title is stored with the brand image dictionary;
Degree of membership computing unit, the use is calculated by fuzzy clustering for the Shopping Behaviors data based on the user
Degree of membership of the family to various brands image word;And
User preference determining unit, the brand image word for the degree of membership to be more than to first threshold are defined as described
The brand image of user preference.
In a kind of exemplary embodiment of the disclosure, the Shopping Behaviors data based on the user pass through fuzzy clustering
Calculate the user includes to the degree of membership of various brands image word:
Calculate the distance between Shopping Behaviors data and various brands image word of the user;
Degree of membership of the user to various brands image word is calculated based on the distance.
According to an aspect of this disclosure, there is provided a kind of electronic equipment, including:
Processor;And
Memory, computer-readable instruction is stored with the memory, the computer-readable instruction is by the processing
Realize that the user preference according to above-mentioned any one determines method when device performs.
According to an aspect of this disclosure, a kind of computer-readable recording medium is additionally provided, is stored thereon with computer
Program, realize that the user preference according to above-mentioned any one determines method when the computer program is executed by processor.
User preference in a kind of exemplary embodiment of the disclosure determines that method, user preference determining device, electronics are set
Standby and computer-readable recording medium, the Shopping Behaviors data of user corresponding with various brands image word are counted, based on user
Shopping Behaviors data by fuzzy clustering calculate user to the degree of membership of various brands image word, degree of membership is more than the first threshold
The brand image word of value is defined as the brand image of user preference.On the one hand, count user's corresponding with various brands image word
Shopping Behaviors data, the Shopping Behaviors data of user can be associated with brand image word, so as to be beneficial to pass through user
Shopping Behaviors data are analyzed the brand image of user preference;On the other hand, the Shopping Behaviors data based on user pass through
Fuzzy clustering calculates degree of membership of the user to various brands image word, and the brand image word that degree of membership is more than to first threshold determines
For the brand image of user preference, the more of user preference can be automatically and efficiently excavated from the Shopping Behaviors data of user
Individual brand image, so can deeper level excavate customers' consumption psychology and preference, be easy to precision marketing, and reduce people
Work cost.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Its example embodiment is described in detail by referring to accompanying drawing, the above and other feature and advantage of the disclosure will become
Obtain more obvious.
Fig. 1 diagrammatically illustrates the flow chart that method is determined according to the user preference of the exemplary embodiment of the disclosure one;
Fig. 2 diagrammatically illustrates the Organization Chart that system is determined according to the user preference of the exemplary embodiment of the disclosure one;
Fig. 3 diagrammatically illustrates the flow chart that system is determined according to the user preference of the exemplary embodiment of the disclosure one;
Fig. 4 diagrammatically illustrates the FP-tree of the structure according to the exemplary embodiment of the disclosure one schematic diagram;
Fig. 5 diagrammatically illustrates the block diagram of the user preference determining device according to the exemplary embodiment of the disclosure one;
Fig. 6 diagrammatically illustrates the block diagram of the electronic equipment according to the exemplary embodiment of the disclosure one;
Fig. 7 shows the schematic diagram of the computer-readable recording medium according to the exemplary embodiment of the disclosure one.
Embodiment
Example embodiment is described more fully with referring now to accompanying drawing.However, example embodiment can be real in a variety of forms
Apply, and be not understood as limited to embodiment set forth herein;On the contrary, these embodiments are provided so that the disclosure will comprehensively and
Completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.The identical reference table in figure
Show same or similar part, 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 example.In the following description, there is provided many details fully understand so as to provide to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can put into practice the technical scheme of the disclosure without one in the specific detail or
More, or can be using other methods, constituent element, material, device, step etc..In other cases, be not shown in detail or
Description known features, method, apparatus, realization, material are operated to avoid each side of the fuzzy disclosure.
Block diagram shown in accompanying drawing is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or these are realized in the module of one or more softwares hardening
A part for functional entity or functional entity, or in heterogeneous networks and/or processor device and/or microcontroller device in fact
These existing functional entitys.
In this example embodiment, it provide firstly a kind of user preference and determine method.With reference to shown in figure 1, the user is inclined
Determine that method may comprise steps of well:
Step S110. counts the Shopping Behaviors data of user corresponding with various brands image word in brand image dictionary, its
In, brand image word corresponding with various brands title is stored with the brand image dictionary;
Step S120. calculates the user to various brands based on the Shopping Behaviors data of the user by fuzzy clustering
The degree of membership of vivid word;And
The degree of membership is defined as the product of the user preference by step S130. more than the brand image word of first threshold
Board image.
Method is determined according to the user preference in this example embodiment, on the one hand, statistics is corresponding with various brands image word
The Shopping Behaviors data of user, the Shopping Behaviors data of user can be associated with brand image word, so as to be beneficial to pass through
User's Shopping Behaviors data are analyzed the brand image of user preference;On the other hand, the Shopping Behaviors data based on user
Degree of membership of the user to various brands image word is calculated by fuzzy clustering, degree of membership is more than to the brand image word of first threshold
It is defined as the brand image of user preference, can automatically and efficiently excavates user preference from the Shopping Behaviors data of user
Multiple brand images, so can deeper level excavate customers' consumption psychology and preference, be easy to precision marketing, and reduce
Cost of labor.
Below, it will determine that method is further detailed to the user preference in this example embodiment.
In step s 110, the Shopping Behaviors number of user corresponding with various brands image word in brand image dictionary is counted
According to, wherein, brand image word corresponding with various brands title is stored with the brand image dictionary.
In this exemplary embodiment, brand corresponding with various brands title can be previously stored with brand image dictionary
Vivid word., can be by brand expert or business scope expert in brand image word cold start-up module 210 shown in reference picture 2
Brand image positioning is described, brand expert enters by using fewer but better accurate word as far as possible to the abstract concept of image of brand
Row is summarized, and then the brand image word of summary is input in brand image dictionary.By taking computer brand as an example, brand image word
The basic format of storehouse table can be with as shown in table 1 below:
The brand image dictionary table of table 1.
Further, in this exemplary embodiment, can be by the commodity information database of shopping website backstage storage
Every merchandise news brand image word corresponding with various brands title is matched, so as to by user in information of goods information data
Shopping Behaviors data in storehouse associate user and brand, and this can pass through the commodity image word matching module in Fig. 2
220 realize, shown in specific implementation flow reference picture 3.In this exemplary embodiment, the category in merchandise news is mainly utilized
The electric business such as word, function word, qualifier or the special vocabulary of brand, association these words of matching primitives and the product in brand image dictionary
Board image word.It is as shown in table 2 below, using " brand " field common in brand image dictionary table and merchandise news table, by brand
Brand image word in vivid dictionary is together with the Data Matching in merchandise news table, subsequently to feed back mould in frequent item set
Processing in block 230 and fuzzy clustering module 250 is prepared.
The merchandise news table of table 2.
In the implementation of this example, pass through " association " field and the merchandise news of table 2 in the brand image dictionary table of table 1
" association " field in table, the brand image word that will can be collected about " associating " in brand image word cold start-up module 210
In " association " merchandise news in Corresponding matching to merchandise news table, so as to the purchase by user in merchandise news table
Thing behavioral data associates user with " association " brand.
Further, in this exemplary embodiment, shown in reference picture 2 and Fig. 3, in user-brand image word feature machining
In module 240, every merchandise news of matching and the brand image word can be handled, such as count each use
Family granularity is about the Shopping Behaviors feature on brand image word, such as purchase number, the purchase amount of money, order volume etc., by normalizing
After change, it is input to fuzzy clustering module and carries out fuzzy clustering calculating.For example, user has shopping on n brand image word
Behavior for example has order volume on n brand image word, then can build the purchase on n brand image word corresponding with user
Thing behavioural characteristic, shown in table 3 specific as follows:
Shopping Behaviors mark sheet on the n brand image word corresponding with user of table 3.
In this exemplary embodiment, if there is m user in commodity information database, m user and n brand shape
, can be by the Input matrix of the m*n to fuzzy clustering mould shown in reference picture 2 and Fig. 3 as word can form m*n matrix
Clustered in block 250.If in addition, there are data and refer in the Shopping Behaviors feature on n various brands image word corresponding with user
Inconsistent situation is marked, each Shopping Behaviors characteristic index can be normalized, to ensure that dimension is unified.Originally showing
In example embodiment, data normalization processing is average standardization, and processing method is average and standard based on initial data
Difference carries out data normalization, and average is the intensity of metric data, and calculation formula is:
Wherein, x1 to xn is the initial data for needing to be normalized, and n is brand image word quantity.
Standard deviation std is the dispersion degree of metric data, and calculation formula is:
The formula of standardization is:
Wherein, XoldTo need the data being normalized, Xnew is the data after normalized.
It should be noted that in this exemplary embodiment, the Shopping Behaviors feature of user is not limited to buy number, purchase
The amount of money, order volume, such as Shopping Behaviors feature can also be to add shopping cart quantity and collection quantity etc., and this is equally at this
In disclosed protection domain.
Next, in the step s 120, the Shopping Behaviors data based on the user calculate the use by fuzzy clustering
Degree of membership of the family to various brands image word.
In this exemplary embodiment, can be by each user of user-brand image word feature machining module in brand shape
As the Shopping Behaviors characteristic index on word as input calculates behavior expression of the user on brand image word, according to fuzzy
Cluster calculation goes out fuzzy membership of the user on each brand image word.
Fuzzy clustering is different from traditional hard cluster, is a kind of algorithm of soft segmentation.It is each to need in fuzzy clustering
The sample clustered can be subordinate to multiple classifications simultaneously, and total degree of membership sum of all categories of each sample is 1, so logical
The size of comparative sample degree of membership in each class is crossed, it is known that subordinate degree or degree of approximation of the sample in each class.
In this example embodiment, user is more inclined to which brand image can be shown to the degree of membership of various brands according to user
Good or hobby.
Specifically, in this exemplary embodiment, the implementation method of fuzzy clustering can be:By n Shopping Behaviors feature
(i=1,2 ..., n) is divided into c ambiguity group to vector x i, and c can be the number of brand image word.Brand image word can conduct
The cluster centre of each group, cluster centre can be that the cost function for causing non-similarity index reaches minimum brand image word.
Fuzzy clustering causes each data-oriented point to pass through degree of membership of the value between 0 and 1 to indicate it belong to each group i.e. various brands
The degree of vivid word.It is adapted with introducing fuzzy division, it is allowed to which Subject Matrix U has element of the value between 0 and 1.In addition,
Constrained plus normalization, data set degree of membership and be always equal to 1, as shown in following formula 4:
So, the cost function (or object function) for fuzzy clustering being carried out to n Shopping Behaviors feature is exactly that following formula is general
Change form:
Wherein, here uij spans between 0 and 1;Ci be ambiguity group i cluster centre, dij=| | ci-xj |
| the Euclidean distance between ith cluster center and j-th of data point, and m (belong to 1 to infinite) is that a weighting refers to
Number.
Further, in the implementation of this example, shown in reference picture 3, fuzzy clustering is carried out to n Shopping Behaviors feature
Detailed process can be divided into following 3 submodules:
Submodule 1:Determine initial parameter:In this exemplary embodiment, initial parameter can have two, and one is fuzzy
It is brand image word number c to cluster number, and another is the parameter m of control algolithm pliability.In this exemplary embodiment, c can
A positive integer for being not more than 20 is thought, because cluster number can excessively be unfavorable for understanding and specific service application, in addition, also
Optimal cluster number c can be searched for by trellis traversal, this is equally in the protection domain of the disclosure.Originally showing
In example embodiment, pliability parameter m typically can not be excessive, otherwise can influence Clustering Effect, pliability parameter m can take 2-5 it
Between number, or take the positive integer such as 2 or other appropriate numbers no more than 10, the disclosure is herein without special
Limit.
Submodule 2:According to given Shopping Behaviors data sample and corresponding sampling feature vectors, fuzzy matrix is constructed, its
In, i cluster centre initialization can be to randomly select, and then progressive alternate optimal solution is:
Wherein:Xj is sample number strong point, and uij is degrees of membership of the sample number strong point j to cluster centre i.
Submodule 3:Judge whether object function restrains (stopping iteration, output result):
This programme object function is
Wherein:Dij is Euclidean distances of the sample number strong point j to cluster centre i.The condition of convergence can be certain calculating
Threshold value is less than the threshold values of some determination, or is less than some with respect to the knots modification of last time target function value for the threshold value of certain calculating
Threshold values.If object function reaches the above-mentioned condition of convergence, algorithm computing stops, you being derived as sample number strong point j to cluster
Center i degree of membership.
Next, in step s 130, the brand image word that the degree of membership is more than to first threshold is defined as the use
The brand image of family preference.
In this exemplary embodiment, first threshold can according to the Shopping Behaviors of the number of brand image word and user
The value that data volume determines, or determine method afterwards according to actual treatment using the user preference in this example embodiment
As a result the value determined, the disclosure is herein without particular determination., can be in user-brand image shown in reference picture 2 and Fig. 3
It is defined as the brand image of user preference with the brand image word that degree of membership is more than to first threshold in module 260, and exports institute
The brand image of the user preference of determination.
Further, in this exemplary embodiment, can in order to enrich the content of the brand image in brand image dictionary
With the information according to the various brands commodity on shopping platform come the addition brand image word into brand image dictionary.Therefore, the use
Family preference determines that method can also include:Every merchandise news and the brand image word based on matching are generated on items
Merchandise news and the frequent item set of the brand image word;Commodity support being more than in the frequent item set of Second Threshold are believed
Breath is added in the brand image dictionary.In this example embodiment, Second Threshold is the business in merchandise news table
The settings such as the calculating performance of the quantity of product item of information, the quantity of the brand image word in brand image dictionary and computer
Value.
Specifically, shown in reference picture 2 and Fig. 3, in frequent item set feedback module:It can calculate and brand image word
Matched merchandise news item occurs frequent in merchandise sales in the brand image word and merchandise news table selected in the table of storehouse
Item situation, it will meet that the merchandise news item of the i.e. co-occurrence of Second Threshold of the minimum support threshold of frequent episode adds brand image word
In the table of storehouse, automatic expansion brand image dictionary and the subsequently covering to commodity and user are realized.
In this exemplary embodiment, the frequent item set of generation includes two parts:A part comes from brand image dictionary
Brand image word, another part comes from category word in merchandise news table, function word, qualifier etc., respectively with brand shape
As the calculating of word progress frequent item set, so as to export the word higher with predetermined brand image Term co-occurrence frequency.It will meet
The minimum support threshold of frequent episode is the higher merchandise news item of the co-occurrence frequency of Second Threshold as original brand image word
Supplement, after progressive alternate, gradually enrich in brand image dictionary, so as to realize the autonomous expansion of brand image dictionary
Fill.
Further, in this exemplary embodiment, brand image word and commodity can be generated by FP-growth methods
The frequent item set of category word, function word, qualifier in information table etc., specific implementation flow are as follows:Constantly iteration is by brand
The construction and projection process of vivid word and the FP-tree that all kinds of words are formed in merchandise news table.For each frequent of composition
, construct its condition data for projection storehouse and projection FP-tree.This process is repeated to the FP-tree of each new structure, until
The new FP-tree of construction is sky, or only includes a paths.When the FP-tree of construction is space-time, its prefix is as frequent
Pattern;When only including a paths, it is possible to combination and is connected with the prefix of this tree can obtain frequent mould by enumerating
Formula.
Shown in reference picture 4, FP-tree is a kind of special prefix trees, is made up of frequent item head table and item prefix trees.Institute
Prefix trees to be called, are a kind of data structures for storing candidate, the branch of tree is identified with key name, the node storage suffix item of tree,
Path representation item collection.FP-tree generation method is as follows:
The first step, generates transaction itemset, and form is as shown in table 4 below:
The transaction itemset of table 4. and frequent episode
Item collection id | Item collection | Frequent episode |
001 | { f, a, c, d, g, i, m, p } | { f, c, a, m, p } |
002 | { a, b, c, f, l, m, o } | { f, c, a, b, m } |
003 | { b, f, h, j, o, w } | { f, b } |
004 | { b, c, k, s, p } | { c, b, p } |
005 | { a, f, c, e, l, p, m, n } | { f, c, a, m, p } |
In this exemplary embodiment, for the sake of simple and convenient, the brand image in brand image dictionary is represented with letter
Each merchandise news vocabulary in word or merchandise news table, item collection can be represented by the product in brand image word and merchandise news table
The item collection of the compositions such as class word, function word, qualifier.By minimum support be 3 to calculate when, the brand in first scan database
Vivid word and each merchandise news vocabulary, the frequency of occurrences of each individual event is calculated, retain the note that the frequency of occurrences is more than minimum support
Record.Therefore, the item that the frequency of occurrences is more than 3 is only remained in a most right row in table 4.
Second step:The frequency of occurrences for the item for meeting minimum support is calculated, and frequent episode is arranged by frequency descending, it is raw
Into the frequent episode rearranged.The frequency of every appearance is as shown in table 5 below in item collection:
Every frequency occurred in the item collection of table 5.
Frequency | |
f | 4 |
c | 4 |
a | 3 |
b | 3 |
m | 3 |
p | 3 |
As shown in table 5, in each frequent episode that upper table 4 is calculated, alphabetical f occurs 4 times, and alphabetical c occurs 4 times,
Alphabetical a occurs 3 times, and the frequency that each letter occurs is arranged in descending order, rearranged frequent episode is obtained, in table 4
Shown in a most right row.
3rd step, the brand image word in scan database and each merchandise news vocabulary, build FP-tree, finally again
As a result it is as shown in Figure 4.In Fig. 4, the path of each solid line can represent item collection, and the FP-tree is a high compression
Structure, the full detail for Mining Frequent Itemsets Based is stored, after FP-tree is generated, you can pass through the FP-tree
The frequent item set of various brands image word is obtained, so as to expand brand image dictionary.Further, since FP-tree algorithms are only
Rescan need to be carried out to transaction database, and without producing substantial amounts of Candidate Set, therefore data processing effect can be improved
Rate.
It should be noted that although describe each step of method in the disclosure with particular order in the accompanying drawings, but
It is that this, which does not require that or implied, to perform these steps according to the particular order, or has to carry out shown in whole
Step could realize desired result.It is additional or alternative, it is convenient to omit some steps, multiple steps to be merged into one
Step is performed, and/or a step is decomposed into execution of multiple steps etc..
In addition, in this exemplary embodiment, additionally provide a kind of user preference determining device.Shown in reference picture 5, the use
Family preference determining device can include:Statistic unit 510, degree of membership computing unit 520 and user preference determining unit 530.
Wherein:
Statistic unit 510 is used for the Shopping Behaviors for counting user corresponding with various brands image word in brand image dictionary
Data, wherein, brand image word corresponding with various brands title is stored with the brand image dictionary;
Described in degree of membership computing unit 520 is used to calculating by fuzzy clustering based on the Shopping Behaviors data of the user
Degree of membership of the user to various brands image word;And
The brand image word that user preference determining unit 530 is used to the degree of membership being more than first threshold is defined as institute
State the brand image of user preference.
Further, in this exemplary embodiment, the Shopping Behaviors data based on the user are calculated by fuzzy clustering
The user can include to the degree of membership of various brands image word:
Calculate the distance between Shopping Behaviors data and various brands image word of the user;
Degree of membership of the user to various brands image word is calculated based on the distance.
In addition, in this exemplary embodiment, the user preference determining device can also include:Matching unit, for inciting somebody to action
Every merchandise news brand image word corresponding with various brands title in commodity information database is matched.
In addition, in this exemplary embodiment, the user preference determining device can also include:Frequent item set generation is single
Member, for generating the frequent item set on every merchandise news and the brand image word;Adding device, for by support
It is added to more than the merchandise news in the frequent item set of Second Threshold in the brand image dictionary.
Further, in this exemplary embodiment, generate on the frequent of every merchandise news and the brand image word
Item collection can include:
By FP-growth computings generation on every merchandise news and the frequent item set of brand image word.
Further, in this exemplary embodiment, user corresponding with various brands image word in brand image dictionary is counted
Shopping Behaviors data can include:
The Shopping Behaviors data of user are normalized;
The shopping row of the statistics user through normalized corresponding with various brands image word in brand image dictionary
For data.
Due to each functional module and user preference of the user preference determining device 400 of the example embodiment of the disclosure
The step of determining the example embodiment of method is corresponding, therefore will not be repeated here.
It should be noted that although some modules or list of user preference determining device are referred in above-detailed
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Either the feature of unit and function can embody module in a module or unit.A conversely, above-described mould
Either the feature of unit and function can be further divided into being embodied by multiple modules or unit block.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can realize the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be implemented as following form, i.e.,:It is complete hardware embodiment, complete
The embodiment combined in terms of full software implementation (including firmware, microcode etc.), or hardware and software, can be referred to as here
For " circuit ", " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 6.Electronics shown in Fig. 6 is set
Standby 600 be only an example, should not bring any restrictions to the function and use range of the embodiment of the present invention.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can be with
Including but not limited to:Above-mentioned at least one processing unit 610, above-mentioned at least one memory cell 620, connection different system group
The bus 630 of part (including memory cell 620 and processing unit 610), display unit 640.
Wherein, the memory cell is had program stored therein code, and described program code can be held by the processing unit 610
OK so that the processing unit 610 performs various according to the present invention described in above-mentioned " illustrative methods " part of this specification
The step of exemplary embodiment.For example, the processing unit 610 can perform as shown in fig. 1 step S110. statistics with
The Shopping Behaviors data of user corresponding to various brands image word in brand image dictionary, wherein, in the brand image dictionary
It is stored with brand image word corresponding with various brands title;Shopping Behaviors data of the step S120. based on the user pass through mould
User described in cluster calculation is pasted to the degree of membership of various brands image word;And the degree of membership is more than the first threshold by step S130.
The brand image word of value is defined as the brand image of the user preference.
Memory cell 620 can include the computer-readable recording medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Memory cell 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to:Operating system, one or more application program, other program moulds
Block and routine data, the realization of network environment may be included in each or certain combination in these examples.
Bus 630 can be to represent the one or more in a few class bus structures, including memory cell bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any total knot in a variety of bus structures
The local bus of structure.
Electronic equipment 600 can also be with one or more external equipments 670 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment communication interacted with the electronic equipment 600 can be also enabled a user to one or more, and/or with making
Obtain any equipment that the electronic equipment 600 can be communicated with one or more of the other computing device (such as router, modulation
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600
Network adapter 660 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public affairs can also be passed through
Common network network, such as internet) communication.As illustrated, network adapter 660 passes through the other of bus 630 and electronic equipment 600
Module communicates.It should be understood that although not shown in the drawings, can combine electronic equipment 600 uses other hardware and/or software mould
Block, include but is not limited to:Microcode, device driver, redundant processing unit, external disk drive array, RAID system, magnetic
Tape drive and data backup storage system etc..
The description of embodiment more than, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can be realized, can also be realized by way of software combines necessary hardware by software.Therefore, it is real according to the disclosure
Applying the technical scheme of example can be embodied in the form of software product, the software product can be stored in one it is non-volatile
In storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are to cause a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is performed according to the embodiment of the present disclosure
Method.
In an exemplary embodiment of the disclosure, a kind of computer-readable recording medium is additionally provided, is stored thereon with energy
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention can be with
It is embodied as a kind of form of program product, it includes program code, when described program product is run on the terminal device, institute
State program code be used for make the terminal device perform described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various exemplary embodiments.
With reference to shown in figure 7, the program product 700 according to an embodiment of the invention for being used to realize the above method is described,
It can use portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device, such as
Run on PC.However, the program product not limited to this of the present invention, in this document, readable storage medium storing program for executing can be appointed
What is included or the tangible medium of storage program, the program can be commanded execution system, device either device using or with
It is used in combination.
Described program product can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can be readable
Signal media or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray,
Or system, device or the device of semiconductor, or any combination above.The more specifically example of readable storage medium storing program for executing is (non-poor
The list of act) include:Electrical connection, portable disc, hard disk, random access memory (RAM) with one or more wires,
Read-only storage (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc is read-only deposits
Reservoir (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry readable program code.The data-signal of this propagation can take various forms, and including but not limited to electromagnetism is believed
Number, optical signal or above-mentioned any appropriate combination.Readable signal medium can also be beyond readable storage medium storing program for executing it is any can
Read medium, the computer-readable recording medium can send, propagate either transmit for being used by instruction execution system, device or device or
Person's program in connection.
The program code included on computer-readable recording medium can be transmitted with any appropriate medium, including but not limited to wirelessly, be had
Line, optical cable, RF etc., or above-mentioned any appropriate combination.
Can being combined to write the program operated for performing the present invention with one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., include routine
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
Perform on computing device, partly perform on a user device, the software kit independent as one performs, is partly counted in user
Its upper side point is calculated to perform or perform in remote computing device or server completely on a remote computing.It is being related to
In the situation of remote computing device, remote computing device can pass through the network of any kind, including LAN (LAN) or wide
Domain net (WAN), is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize Internet service
Provider passes through Internet connection).
In addition, above-mentioned accompanying drawing is only the schematic theory of the processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limitation purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings was not intended that or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing for example can be performed either synchronously or asynchronously in multiple modules.
The description of embodiment more than, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can be realized, can also be realized by way of software combines necessary hardware by software.Therefore, it is real according to the disclosure
Applying the technical scheme of example can be embodied in the form of software product, the software product can be stored in one it is non-volatile
In storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are to cause a calculating
Equipment (can be personal computer, server, touch control terminal or network equipment etc.) is performed according to the embodiment of the present disclosure
Method.
Those skilled in the art will readily occur to the disclosure after considering specification and putting into practice invention disclosed herein
Other embodiments.The application is intended to any modification, purposes or the adaptations of the disclosure, these modifications, purposes or
Person's adaptations follow the general principle of the disclosure and including the undocumented common knowledges in the art of the disclosure
Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the disclosure and spirit are by right
It is required that point out.
It should be appreciated that the precision architecture that the disclosure is not limited to be described above and is shown in the drawings, and
And various modifications and changes can be being carried out without departing from the scope.The scope of the present disclosure is only limited by appended claim.
Claims (10)
1. a kind of user preference determines method, it is characterised in that including:
The Shopping Behaviors data of statistics user corresponding with various brands image word in brand image dictionary, wherein, the brand shape
As being stored with brand image word corresponding with various brands title in dictionary;
Degree of membership of the user to various brands image word is calculated by fuzzy clustering based on the Shopping Behaviors data of the user;
And
The degree of membership is defined as to the brand image of the user preference more than the brand image word of first threshold.
2. user preference according to claim 1 determines method, it is characterised in that the Shopping Behaviors number based on the user
The degree of membership of various brands image word is included according to the user is calculated by fuzzy clustering:
Calculate the distance between Shopping Behaviors data and various brands image word of the user;
Degree of membership of the user to various brands image word is calculated based on the distance.
3. user preference according to claim 1 or 2 determines method, it is characterised in that the user preference determines method
Also include:
Every merchandise news brand image word corresponding with various brands title in commodity information database is matched.
4. user preference according to claim 3 determines method, it is characterised in that the user preference determines that method is also wrapped
Include:
Every merchandise news and the brand image word based on matching are generated on every merchandise news and the brand image
The frequent item set of word;
Merchandise news support being more than in the frequent item set of Second Threshold is added in the brand image dictionary.
5. user preference according to claim 3 determines method, it is characterised in that generation is on every merchandise news and institute
Stating the frequent item set of brand image word includes:
By FP-growth computings generation on every merchandise news and the frequent item set of brand image word.
6. user preference according to claim 1 determines method, it is characterised in that statistics and each product in brand image dictionary
The Shopping Behaviors data of user include corresponding to board image word:
The Shopping Behaviors data of user are normalized;
The Shopping Behaviors number of the statistics user through normalized corresponding with various brands image word in brand image dictionary
According to.
A kind of 7. user preference determining device, it is characterised in that including:
Statistic unit, for counting the Shopping Behaviors data of user corresponding with various brands image word in brand image dictionary, its
In, brand image word corresponding with various brands title is stored with the brand image dictionary;
Degree of membership computing unit, for calculating the user to each by fuzzy clustering based on the Shopping Behaviors data of the user
The degree of membership of brand image word;And
User preference determining unit, it is inclined that the brand image word for the degree of membership to be more than to first threshold is defined as the user
Good brand image.
8. user preference determining device according to claim 7, it is characterised in that the Shopping Behaviors number based on the user
The degree of membership of various brands image word is included according to the user is calculated by fuzzy clustering:
Calculate the distance between Shopping Behaviors data and various brands image word of the user;
Degree of membership of the user to various brands image word is calculated based on the distance.
9. a kind of electronic equipment, it is characterised in that including:
Processor;And
Memory, computer-readable instruction is stored with the memory, the computer-readable instruction is held by the processor
Realize that user preference according to any one of claim 1 to 6 determines method during row.
10. a kind of computer-readable recording medium, is stored thereon with computer program, the computer program is executed by processor
Shi Shixian user preferences according to any one of claim 1 to 6 determine method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710699894.1A CN107507028B (en) | 2017-08-16 | 2017-08-16 | User preference determination method, device, equipment and storage medium |
PCT/CN2018/100688 WO2019034087A1 (en) | 2017-08-16 | 2018-08-15 | User preference determination method, apparatus, device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710699894.1A CN107507028B (en) | 2017-08-16 | 2017-08-16 | User preference determination method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107507028A true CN107507028A (en) | 2017-12-22 |
CN107507028B CN107507028B (en) | 2021-11-30 |
Family
ID=60690818
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710699894.1A Active CN107507028B (en) | 2017-08-16 | 2017-08-16 | User preference determination method, device, equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107507028B (en) |
WO (1) | WO2019034087A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009897A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing |
CN109359246A (en) * | 2018-12-07 | 2019-02-19 | 上海宏原信息科技有限公司 | A kind of brand cohesion calculation method based on forum user speech |
WO2019034087A1 (en) * | 2017-08-16 | 2019-02-21 | 北京京东尚科信息技术有限公司 | User preference determination method, apparatus, device, and storage medium |
CN109658195A (en) * | 2018-12-24 | 2019-04-19 | 北京亿百分科技有限公司 | A kind of merchandise display decision-making technique |
CN110110033A (en) * | 2018-01-29 | 2019-08-09 | 清华大学 | Information extracting method, device, computer equipment and storage medium |
CN110413852A (en) * | 2019-07-19 | 2019-11-05 | 深圳市元征科技股份有限公司 | A kind of information-pushing method, device, equipment and medium |
CN111401409A (en) * | 2020-02-28 | 2020-07-10 | 创新奇智(青岛)科技有限公司 | Commodity brand feature acquisition method, sales volume prediction method, device and electronic equipment |
CN113553493A (en) * | 2020-04-24 | 2021-10-26 | 哈尔滨工业大学 | Service selection method based on demand service probability matrix |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
CN103810251A (en) * | 2014-01-21 | 2014-05-21 | 南京财经大学 | Method and device for extracting text |
CN104298778A (en) * | 2014-11-04 | 2015-01-21 | 北京科技大学 | Method and system for predicting quality of rolled steel product based on association rule tree |
US20150261926A1 (en) * | 2008-10-15 | 2015-09-17 | Nikola Kirilov Kasabov | Data analysis and predictive systems and related methodologies |
CN105488597A (en) * | 2015-12-28 | 2016-04-13 | 中国民航信息网络股份有限公司 | Passenger destination prediction method and system |
CN105975608A (en) * | 2016-05-17 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Data mining method and device |
JP2016206986A (en) * | 2015-04-23 | 2016-12-08 | 日本電信電話株式会社 | Clustering device, method, and program |
CN106294462A (en) * | 2015-06-01 | 2017-01-04 | Tcl集团股份有限公司 | A kind of method and system obtaining recommendation video |
CN106844787A (en) * | 2017-03-16 | 2017-06-13 | 四川大学 | It is a kind of for automobile industry finds targeted customer and matches the recommendation method of target product |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8160918B1 (en) * | 2005-01-14 | 2012-04-17 | Comscore, Inc. | Method and apparatus for determining brand preference |
US20060242011A1 (en) * | 2005-04-21 | 2006-10-26 | International Business Machines Corporation | Method and system for automatic, customer-specific purchasing preferences and patterns of complementary products |
CN103745379A (en) * | 2013-12-23 | 2014-04-23 | 苏州亚安智能科技有限公司 | Method for realizing customer-demand-based orientationi electronic-commerce platform |
CN106682968B (en) * | 2017-01-10 | 2021-07-02 | 北京三快在线科技有限公司 | Navigation menu generation method and device and server |
CN107507028B (en) * | 2017-08-16 | 2021-11-30 | 北京京东尚科信息技术有限公司 | User preference determination method, device, equipment and storage medium |
-
2017
- 2017-08-16 CN CN201710699894.1A patent/CN107507028B/en active Active
-
2018
- 2018-08-15 WO PCT/CN2018/100688 patent/WO2019034087A1/en active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150261926A1 (en) * | 2008-10-15 | 2015-09-17 | Nikola Kirilov Kasabov | Data analysis and predictive systems and related methodologies |
CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
CN103810251A (en) * | 2014-01-21 | 2014-05-21 | 南京财经大学 | Method and device for extracting text |
CN104298778A (en) * | 2014-11-04 | 2015-01-21 | 北京科技大学 | Method and system for predicting quality of rolled steel product based on association rule tree |
JP2016206986A (en) * | 2015-04-23 | 2016-12-08 | 日本電信電話株式会社 | Clustering device, method, and program |
CN106294462A (en) * | 2015-06-01 | 2017-01-04 | Tcl集团股份有限公司 | A kind of method and system obtaining recommendation video |
CN105488597A (en) * | 2015-12-28 | 2016-04-13 | 中国民航信息网络股份有限公司 | Passenger destination prediction method and system |
CN105975608A (en) * | 2016-05-17 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Data mining method and device |
CN106844787A (en) * | 2017-03-16 | 2017-06-13 | 四川大学 | It is a kind of for automobile industry finds targeted customer and matches the recommendation method of target product |
Non-Patent Citations (3)
Title |
---|
TONY CHENG-KUI HUANG: "Discovery of fuzzy quantitative sequential patterns with multiple minimum supports and adjustable membership functions", 《INFORMATION SCIENCES》 * |
张应辉 等: "基于模糊聚类的旅游推荐算法", 《计算机技术与发展》 * |
许栋浩: "一种顾及模糊属性的空间关联规则挖掘方法", 《测绘科学技术学报》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019034087A1 (en) * | 2017-08-16 | 2019-02-21 | 北京京东尚科信息技术有限公司 | User preference determination method, apparatus, device, and storage medium |
CN108009897A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing |
CN110110033A (en) * | 2018-01-29 | 2019-08-09 | 清华大学 | Information extracting method, device, computer equipment and storage medium |
CN109359246A (en) * | 2018-12-07 | 2019-02-19 | 上海宏原信息科技有限公司 | A kind of brand cohesion calculation method based on forum user speech |
CN109658195A (en) * | 2018-12-24 | 2019-04-19 | 北京亿百分科技有限公司 | A kind of merchandise display decision-making technique |
CN109658195B (en) * | 2018-12-24 | 2020-12-25 | 北京亿百分科技有限公司 | Commodity display decision method |
CN110413852A (en) * | 2019-07-19 | 2019-11-05 | 深圳市元征科技股份有限公司 | A kind of information-pushing method, device, equipment and medium |
CN111401409A (en) * | 2020-02-28 | 2020-07-10 | 创新奇智(青岛)科技有限公司 | Commodity brand feature acquisition method, sales volume prediction method, device and electronic equipment |
CN111401409B (en) * | 2020-02-28 | 2023-04-18 | 创新奇智(青岛)科技有限公司 | Commodity brand feature acquisition method, sales volume prediction method, device and electronic equipment |
CN113553493A (en) * | 2020-04-24 | 2021-10-26 | 哈尔滨工业大学 | Service selection method based on demand service probability matrix |
Also Published As
Publication number | Publication date |
---|---|
WO2019034087A1 (en) | 2019-02-21 |
CN107507028B (en) | 2021-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107507028A (en) | User preference determines method, apparatus, equipment and storage medium | |
US20210027146A1 (en) | Method and apparatus for determining interest of user for information item | |
WO2020211566A1 (en) | Method and device for making recommendation to user, computing apparatus, and storage medium | |
CN111339415B (en) | Click rate prediction method and device based on multi-interactive attention network | |
TWI612488B (en) | Computer device and method for predicting market demand of commodities | |
CN111797321B (en) | Personalized knowledge recommendation method and system for different scenes | |
CN111259263B (en) | Article recommendation method and device, computer equipment and storage medium | |
CN104574192A (en) | Method and device for identifying same user from multiple social networks | |
CN116010684A (en) | Article recommendation method, device and storage medium | |
CN111241394A (en) | Data processing method and device, computer readable storage medium and electronic equipment | |
CN109615504A (en) | Products Show method, apparatus, electronic equipment and computer readable storage medium | |
CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
CN112215629B (en) | Multi-target advertisement generating system and method based on construction countermeasure sample | |
CN113342994B (en) | Recommendation system based on non-sampling cooperative knowledge graph network | |
CN114997916A (en) | Prediction method, system, electronic device and storage medium of potential user | |
CN112818091A (en) | Object query method, device, medium and equipment based on keyword extraction | |
CN112287111B (en) | Text processing method and related device | |
CN110348581B (en) | User feature optimizing method, device, medium and electronic equipment in user feature group | |
CN113569578B (en) | User intention recognition method and device and computer equipment | |
CN109902273A (en) | The modeling method and device of keyword generation model | |
CN112328899B (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
US20230267277A1 (en) | Systems and methods for using document activity logs to train machine-learned models for determining document relevance | |
CN112561599A (en) | Click rate prediction method based on attention network learning and fusing domain feature interaction | |
Li et al. | CTR prediction with user behavior: An augmented method of deep factorization machines | |
Hasan et al. | Multi-criteria Rating and Review based Recommendation Model |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |