CN109493101A - Target brand message determines method, apparatus, electronic equipment and storage medium - Google Patents
Target brand message determines method, apparatus, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109493101A CN109493101A CN201710811278.0A CN201710811278A CN109493101A CN 109493101 A CN109493101 A CN 109493101A CN 201710811278 A CN201710811278 A CN 201710811278A CN 109493101 A CN109493101 A CN 109493101A
- Authority
- CN
- China
- Prior art keywords
- brand message
- data
- user
- brand
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The disclosure is directed to a kind of target brand messages to determine method, target brand message determining device, electronic equipment and computer readable storage medium, be related to technical field of electronic commerce.This method comprises: counting the Shopping Behaviors data of all users corresponding with each brand message according to multiple dimensions, wherein the multiple dimension includes region dimension and user's dimension;Based on the Shopping Behaviors data, by clustering algorithm from each dimensional analysis to the preference of the brand message;The brand message that the preference is greater than preset threshold is determined as the target brand message and shows the target brand message.The disclosure can efficiently obtain the brand message of user preference and profound excavation customer consumption preference, improve the accuracy of brand promotion.
Description
Technical field
This disclosure relates to which technical field of electronic commerce, determines method, target in particular to a kind of target brand message
Brand message device, electronic equipment and computer readable storage medium.
Background technique
With the extensive use of big data technology, precision marketing, which has become brand quotient in electronic commerce affair practice, to be carried out
The important channel of marketing and brand promotion.But the effect that each region generates same brand differs widely, each user couple
The preference of same brand is not also identical.
Currently, main in the related technology carry out commercial product recommending to user using search recommender system.Specifically, main right
The correlation of user's search term, commodity basic information, inventory information carry out retrieval ordering, to be paid close attention to and be purchased based on user's history
It buys the modes such as record and platform promotion and commercial product recommending is carried out to user.
In the above scheme, on the one hand, due to not distinguishing region and user, in the advertising campaign of brand day, own
What regional and all users saw in the promotion page is all identical brand, cannot achieve accuracy brand promotion;It is another
Aspect can not quickly carry out brand recommendation according to user preference in each recommendation position based on the recommendation results that search term generates, from
And cause brand promotion efficiency poor.For example, user, which buys TV, is keen to A brand, but position is recommended but to recommend B brand.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
A kind of target brand message of being designed to provide of the disclosure determines that method, target brand message device, electronics are set
Standby and computer readable storage medium, and then overcome the limitation and defect due to the relevant technologies at least to a certain extent and lead
One or more problem caused.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of target brand message is provided and determines method, comprising:
The Shopping Behaviors data of all users corresponding with each brand message are counted according to multiple dimensions, wherein described
Multiple dimensions include region dimension and user's dimension;
Based on the Shopping Behaviors data, by clustering algorithm from each dimensional analysis to the preference of the brand message
Degree;
The brand message that the preference is greater than preset threshold is determined as the target brand message and is shown
The target brand message.
In a kind of exemplary embodiment of the disclosure, the Shopping Behaviors data include corresponding with the brand message
User click data and user's order data.
In a kind of exemplary embodiment of the disclosure, in the shopping for counting all users corresponding with each brand message
Before behavioral data, the method also includes:
Processing is filtered to user click data and user's order data, filter out the first user click data and
First user's order data.
In a kind of exemplary embodiment of the disclosure, the shopping row of all users corresponding with each brand message is counted
Include: for data
The first user order data and the brand message are associated and generate region order brand message;
The region order brand message is grouped according to brand message dimension, to count all users to each described
The click data of brand message.
In a kind of exemplary embodiment of the disclosure, the shopping row of all users corresponding with each brand message is counted
For data further include:
First user click data and the brand message are associated and generate user's click brand message;
It clicks brand message to the user to be grouped according to brand message dimension, to count all users to each described
The click data of brand message.
In a kind of exemplary embodiment of the disclosure, the brand is believed from each dimensional analysis by clustering algorithm
The preference of breath includes:
Each region is clustered by k-means++ clustering algorithm according to the Shopping Behaviors data and is obtained and each institute
State the corresponding influence value in region.
In a kind of exemplary embodiment of the disclosure, the brand is believed from each dimensional analysis by clustering algorithm
The preference of breath further include:
Each user is clustered by k-means++ clustering algorithm according to the Shopping Behaviors data and is obtained and each institute
State the corresponding preference value of user.
In a kind of exemplary embodiment of the disclosure, show that the target brand message includes:
The corresponding target brand message is shown according to user identifier and/or ground domain identifier.
According to one aspect of the disclosure, a kind of target brand message determining device is provided, comprising:
Data statistics module, for counting the shopping row of all users corresponding with each brand message according to two dimensions
For data, wherein the Shopping Behaviors data include click data corresponding with the brand message and order data;
Cluster calculation module calculates each dimension to institute by clustering algorithm for being based on the Shopping Behaviors data
State the preference of brand message;
Target determination module, the brand message for the preference to be greater than preset threshold are determined as the mesh
Mark brand message simultaneously shows the target brand message.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising:
Processor;And
Memory is stored with computer-readable instruction on the memory, and the computer-readable instruction is by the processing
Realize that the target brand message according to above-mentioned any one determines method when device executes.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, computer program is stored thereon with,
Realize that the target brand message according to above-mentioned any one determines method when the computer program is executed by processor.
Target brand message in a kind of exemplary embodiment of the disclosure determines that method, target brand message determine dress
It sets, in electronic equipment and computer readable storage medium, Shopping Behaviors data is counted by region dimension and user's dimension, and
Cluster calculation is carried out to all regions and all users accordingly, to determine target brand message.On the one hand, based on the shopping of user
Behavioral data calculates user to the preference of brand message, can excavate multiple brands of user preference, and then can be more
Profound level excavates customers' consumption psychology and preference, improves the efficiency and precision of brand promotion and marketing;On the other hand, based on purchase
Object behavioral data calculates region to the preference of brand message, can excavate region to the preference of brand message and influence,
By carrying out different brand promotions for different geographical, in order to precision marketing.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, the above and other feature and advantage of the disclosure will become
It is more obvious.
Fig. 1 diagrammatically illustrates the architecture diagram of the target brand message system of one exemplary embodiment of the disclosure;
The target brand message that Fig. 2 diagrammatically illustrates one exemplary embodiment of the disclosure determines the flow chart of method;
Fig. 3 diagrammatically illustrates the block diagram of the target brand message determining device of one exemplary embodiment of the disclosure;
Fig. 4 diagrammatically illustrates the block diagram of the electronic equipment according to one exemplary embodiment of the disclosure;And
Fig. 5 shows the schematic diagram of the computer readable storage medium according to one exemplary embodiment of the disclosure.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein;On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
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, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can be with technical solution of the disclosure without one in the specific detail or more
It is more, or can be using other methods, constituent element, material, device, step etc..In other cases, it is not shown in detail or describes
Known features, method, apparatus, realization, material or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings 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 of functional entity or functional entity, or realized in heterogeneous networks and/or processor device and/or microcontroller device
These functional entitys.
In this example embodiment, provide firstly a kind of for determining the system platform of target brand message, framework
Can with as shown in Figure 1, the platform may include refine characteristic module, Distributed Message Queue module, advertisement delivery system,
Search system, recommender system and precision marketing system.Wherein, refine characteristic module can be used for executing data screening,
The operations such as relevance tidal data recovering and clustering algorithm calculate, feature representation data is formed;Distributed Message Queue is mainly used for
Determine target brand message, and by determining target brand message push to advertisement delivery system, search system, recommender system with
And precision marketing system.
Next, being based on above system platform, a kind of target brand message determination side is provided in this example embodiment
Method.With reference to shown in Fig. 2, which determines that method may comprise steps of:
Step S210. counts the Shopping Behaviors data of all users corresponding with each brand message according to multiple dimensions,
Wherein, the multiple dimension includes region dimension and user's dimension;
Step S220. is based on the Shopping Behaviors data, calculates each dimension by clustering algorithm and believes the brand
The preference of breath;
The brand message that the preference is greater than preset threshold is determined as the target brand by step S230. to be believed
It ceases and shows the target brand message.
Method is determined according to the target brand message in this example embodiment, on the one hand, the Shopping Behaviors number based on user
Multiple brands of user preference can be excavated to the preference of brand message according to user is calculated, and then being capable of deeper time
Customers' consumption psychology and preference are excavated, the efficiency and precision of brand promotion and marketing are improved;On the other hand, Shopping Behaviors are based on
Data calculate region to the preference of brand message, can excavate region to the preference of brand message and influence, pass through needle
Different brand promotions is carried out, to different geographical in order to precision marketing.
In the following, by determining that method is further detailed to the target brand message in this example embodiment.
In step S210, the Shopping Behaviors number of all users corresponding with each brand message is counted according to multiple dimensions
According to, wherein the multiple dimension includes region dimension and user's dimension.
In this exemplary embodiment, all data relevant to user, brand message etc. can be obtained in the database, then
Shopping Behaviors data are generated after being pre-processed and are stored in data warehouse as shown in Figure 1, in order to further be counted
According to mining data.All users herein can be all users of the current electric business platform of registration.
The Shopping Behaviors data may include click data of the user to a certain brand, also may include user to a certain
The order data of brand, wherein the quantity of order is no more than touching quantity.Specifically, user click data and user's order numbers
According to the critical field containing user identifier ID, commodity sign ID, Brand title and address mark IP.Such as user
A certain order data user identifier A, commodity sign B, Brand title C and address identify 113.140.0.0.
The multiple dimension may include region dimension and user's dimension, in addition to this it is possible to include that user identity is tieed up
Degree, such as student, white collar etc., or also may include age dimension, this example is not particularly limited this.In order to overcome correlation
The defect of brand promotion in technology counts corresponding with each brand message from region dimension and user's dimension in this example respectively
The Shopping Behaviors data of all users.
You need to add is that in this example embodiment, in the purchase for counting all users corresponding with each brand message
Before object behavioral data, the method can also include:
Processing is filtered to user click data and user's order data, filter out the first user click data and
First user's order data.
In the present example embodiment, in the Shopping Behaviors data for counting all users corresponding with each brand message
Before, in order to avoid the influence of impurity data present in all user click datas and user's order data, can to
Family click data and user's order data are filtered processing, are ordered with filtering out the first user click data and the first user
Forms data.The first user click data is the validated user click data after filtering out impurity data herein;Similar, first
User's order data is the validated user order data after filtering out impurity data.All data can be by corresponding
The form of log sheet is stored and is indicated, such as click data is corresponding with user's click logs table, and user's order data is ordered with user
Single log sheet is corresponding.
Specifically filter process is as follows: with the presence or absence of automatic in verification user click data and user's order data
The crawler data for obtaining web page contents, if there is then filtering crawler data;Whether detect in Shopping Behaviors data includes blacklist
User ID, if there is then filtering the data of the User ID;Whether include blacklist IP, if there is then if detecting in Shopping Behaviors data
All Shopping Behaviors data of filtering black list IP;Whether the critical field that must include in verification Shopping Behaviors data lacks,
For example, if any one in missing User ID, brand name, address ip, then filter the data;Verify Shopping Behaviors data
In whether include blacklist brand, if there is then filtering the corresponding all data of the blacklist brand.For filtration step,
Input is user's click logs table and user's order log sheet, and output is that validated user click logs table and validated user are ordered
Single log sheet.
It can be respectively from the different angle statistics of region dimension and user's dimension two and each brand message in this example
The Shopping Behaviors data of corresponding all users.Specifically, it for the dimension of region, counts corresponding with each brand message
The Shopping Behaviors data of all users may include:
The first user order data and the brand message are associated and generate region order brand message;
The region order brand message is grouped according to brand message dimension, to count all users to each described
The order data of brand message.
In the present example embodiment, can first to filtered effective region order data and the brand message into
Row association, and all fields and the library IP of region IP are associated, corresponding region name is found out, is ordered with generating effective region
Single brand message, brand message herein still may include commodity SKU- brand dimension table.
It is associated with specifically, SKUID can be carried out with commodity SKU- brand dimension table to effective region order log sheet, and
All fields and the library IP of region IP are associated, to generate effective region order brand log sheet.
You need to add is that an area can have multiple address fields, multiple since IP is artificially to divide as needed
Address field also may belong to areal, it is thus determined that an IP address region needs to judge by complete IP, i.e.,
All fields of region IP in all valid orders can be matched with the library IP, so that it is determined that each region order pair
The region name answered.Such as it can determine that 123.125.71.38 belongs to Beijing.
Then effective region order brand message is grouped according to brand message dimension, to count all regions
Order data of all users to each brand message.Specifically, to the effective region order brand day generated after association
Will table is grouped from brand dimension, to count the region order numbers of each brand.This example can be from all effective regions
In order data, the tables of data of " region-brand-hits-order numbers " form is extracted.The tables of data of the form may include
Same region user also may include click of the different geographical to same brand to the click data and order data of different brands
Data and order data.For example, generate representative order numbers tables of data can for " E-B-100-50 ", " E-C-500-10 " and
“F-B-200-50”。
In addition to this, for user's dimension, in this example embodiment, institute corresponding with each brand message is counted
Having the Shopping Behaviors data of user can also include:
First user click data and the brand message are associated and generate user's click brand message;
It clicks brand message to the user to be grouped according to brand message dimension, to count all users to each described
The click data of brand message.
In the present example embodiment, can first to filtered validated user click data and the brand message into
Row association generates validated user and clicks brand message, and brand message herein may include commodity SKU- brand dimension table.Specifically
For, SKUID can be carried out with commodity SKU- brand dimension table to validated user click logs table and be associated with, to generate validated user
Brand log sheet is clicked, validated user click logs table and validated user order log sheet may each comprise commodity SKU field, IP
Information field.
Then it clicks brand message to validated user to be grouped according to brand message dimension, to count all users couple
The click data of each brand message.Specifically, clicking brand log sheet from brand to the validated user generated after association
Dimension is grouped, thus hits of the counting user to each brand.This example can from institute's validated user click data,
Extract the tables of data of " user-brand-hits-order numbers " form.The tables of data of the form may include same user couple
The click data and order data of different brands also may include click data and order numbers of the different user to same brand
According to.For example, the tables of data of the representative hits generated can be " A-B-100-50 ", " A-C-500-10 " and " AA-B-200-
50”。
In conclusion for statistic procedure, input be validated user click logs table that filtration step generates and
Validated user order log sheet and commodity SKU- brand dimension table, output is comprising " user-brand-hits " form
And the tables of data of " region-brand-order numbers " form.
In step S220, the Shopping Behaviors data are based on, by clustering algorithm from each dimensional analysis to described
The preference of brand message.
In the present example embodiment, preference may include fancy grade, influence degree etc., such as can be according to step
The Shopping Behaviors data of the user counted in rapid S210, it is a certain from user's dimension and region dimensional analysis respectively using clustering algorithm
A user is to the fancy grade of the brand message and a certain region to the influence degree of brand message.
The clustering algorithm can flock together similar things, and dissimilar things is divided into different classes
Other process, can will be to the larger and lesser user of a certain Brang Preference degree and region area by clustering algorithm in this example
It separates, to be conducive to targetedly provide brand recommendation for user and promote.The clustering algorithm may include similarity measurements
Measure many algorithms such as k-means algorithm and hierarchical clustering.
Specifically, in this example embodiment, by clustering algorithm from each dimensional analysis to the brand message
Preference may include:
Each region is clustered by k-means++ clustering algorithm according to the Shopping Behaviors data and is obtained and each institute
State the corresponding influence value in region.
In the present example embodiment, it is specifically described by taking k-means++ clustering algorithm as an example.Its basic thought is pair
For several groups of samples, the space coordinate of each data point can be provided, then can be judged with the distance between data point,
Distance is closer, and data point can consider more similar.
Specifically, the preference of various brands is analyzed in each region first, region is to the inclined of brand herein
Good degree can be understood as influence degree, can with one specifically influence value indicate.Can by k-means++ algorithm,
All regions are clustered from two dimensions of click data and order data in the Shopping Behaviors data of statistics, were clustered
Journey include: firstly, from include multiple objects database in randomly select a sample as initial cluster center, then calculate
Then the shortest distance between each sample and current cluster centre calculates each sample and is chosen as the general of next cluster centre
Rate selects next cluster centre by wheel disc method, and the remoter next cluster centre the better with current cluster centre, and selection is each
Cluster centre and then each sample of calculating, will according to sample at a distance from each cluster centre at a distance from all cluster centres
It is assigned to nearest cluster;Then the average value of each cluster is recalculated.This process constantly repeats, until criterion function is received
It holds back.Specifically convergence process can be carried out by program and circulation.In general, using square error criterion, definition such as formula (1)
It is shown:
Wherein, E represents the summation of the square error of all objects in database, and p is the point in space, and mi is cluster centre
The average value of Ci.
It for example, can all regions of influence journey according to to(for) same brand by above-mentioned k-means++ algorithm
Degree carries out classification processing to all regions, and can be determined all regions for same with a distance from central point according to Regional Distribution
The influence degree of one brand, can using all regions to the mean value of the preference of a certain brand as cluster centre, example
If more modern age table influence degree is bigger with a distance from central point for region location, influence degree is far represented more with a distance from central point
It is small, the farther away Regional Distribution with a distance from central point can be ignored at this time.For example, for same brand B, region position
Set ascending sequence with a distance from central point O are as follows: OE < OF < < OG < OH, then influence degree of region E, the F for the brand
It is larger, and region G, H are smaller for the influence degree of the brand.
In addition to this, in this example embodiment, by clustering algorithm from each dimensional analysis to the brand message
Preference can also include:
Each user is clustered by k-means++ clustering algorithm according to the Shopping Behaviors data and is obtained and each institute
State the corresponding preference value of user.
In the present example embodiment, user can indicate the preference of brand by specific preference value.Still
Can by above-mentioned formula (1) describe k-means++ algorithm and all users for same brand preference to institute
There is user to carry out classification processing, and can be determined all users for same brand with a distance from central point according to user distribution
Preference, can using all users to the mean value of the preference of a certain brand as cluster centre, work as user distribution
More modern age table preference is bigger with a distance from central point for position, and it is smaller that preference is far represented with a distance from central point.It removes
It, can also be according to the k-means++ algorithm and same user that can be described by above-mentioned formula (1) to multiple brands except this
Preference carry out clustering processing, so that it is determined that the more brand message of the user preference.
For example, for same brand B, user distribution sequence descending with a distance from central point O are as follows: OM
> OAA > > ON > OA, then user N, A is larger for the preference of the brand, and user M, AA are for the preference of the brand
It is smaller.In this way, it can recommend to determine multiple target users for a certain brand, can also be carried out for a certain user
The maximum brand of preference is recommended, in order to precision marketing.
Next, the brand message that the preference is greater than preset threshold is determined as institute in step S230
It states target brand message and shows the target brand message.
In the present example embodiment, preset threshold can according to user Shopping Behaviors data determine value, can also
Think and the value determined after method according to real processing results, this public affairs are determined using the target brand message in this example embodiment
This is opened in without particular determination.Relationship between specific preference and preset threshold can be completed by program.Citing
For, if indicating preference from small to large respectively with number 1-10, preset threshold can be set to 8, also can be set
It is 9.The brand message that preference is greater than 8 or 9 can be determined as target brand message, the target brand message can be used
In indicating a certain maximum brand message of user preference degree, can be used for indicating a certain maximum brand of regional impact degree
Information and target brand message may include one or more.For user and two kinds of region dimension, the default threshold of setting
Value may be the same or different.
In addition, in order to accurately provide selection for user, can also will be greater than pre- when including multiple target brand messages
If the preference of threshold value is successively ranked up from big to small, and then the maximum brand message of preference is determined as target product
Board information can be by all brand messages for the condition that meets when preference is all larger than preset threshold and preference is equal
It is determined as target brand message.For example, user A is respectively 7,8,9 to the preference of brand B, C, D, and preset threshold is
8, then it can be using the corresponding information of brand D as target brand message.
Specifically, showing that the target brand message may include: in this example embodiment
The corresponding target brand message is shown according to user identifier and/or ground domain identifier.
In the present example embodiment, the target brand corresponding with the user only can be shown according to user identifier
Information, can also a base area domain identifier show the target brand message corresponding with the region, can also simultaneously basis
User identifier and ground domain identifier are shown and the region is corresponding and corresponding with the user target brand message.User's mark
Knowing for example can be the corresponding ID of user, such as member's name, login name;Ground domain identifier for example can be IP address.
For example, user A is respectively 7,8,9 to the preference of brand B, C, D, preset threshold 8, then can to
Family A shows the corresponding information of brand D;User AA is respectively 8,9,6 to the preference of brand B, C, D, preset threshold 8, then
The corresponding information of brand 9 can be shown to user AA;Region E is respectively 7,8,9 to the preference of brand B, C, D, presets threshold
Value is 9, then the corresponding information of brand D can be shown to region E.For the user A in region E, product can also be shown
The corresponding information of board D.
By the method in this example, user can be calculated based on the Shopping Behaviors data of user to the preference of brand message
Degree, deeper time excavate customers' consumption psychology and preference, allow user that can more directly see the biggish brand of preference
Commodity, promote efficiency and precision that personalized brand recommends and improves brand promotion and marketing;At the same time it can also based on purchase
Object behavioral data calculates region to the preference of brand message, different brand promotions is carried out for different geographical, so that not
The brand seen with the user of region is different, promotes the compartmentalization to brand and promotes, reinforces the brand promotion of precision.
In addition, a kind of target brand message determining device is additionally provided in this example embodiment, refering to what is shown in Fig. 3, institute
Stating device 300 may include:
Data statistics module 301 can be used for counting all users corresponding with each brand message according to two dimensions
Shopping Behaviors data, wherein the Shopping Behaviors data include click data corresponding with the brand message and order numbers
According to;
Cluster calculation module 302 can be used for calculating each dimension by clustering algorithm based on the Shopping Behaviors data
Spend the preference to the brand message;
Target determination module 303, the brand message that can be used for for the preference being greater than preset threshold determine
For the target brand message and show the target brand message.
Due to each functional module and target product of the target brand message determining device 300 of the example embodiment of the disclosure
Board information determines that the step of example embodiment of method corresponding, therefore details are not described herein.
It should be noted that although be referred in the above detailed description target brand message determining device several modules or
Unit, but this division is not enforceable.In fact, according to embodiment of the present disclosure, above-described two or more
Multimode or the feature and function of unit can embody in a module or unit.Conversely, above-described one
Module or the feature and function of unit can be to be embodied by multiple modules or unit with further division.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized 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 embodied in the following forms, it may be assumed that complete hardware embodiment, completely
Software implementation (including firmware, microcode etc.) or hardware and software in terms of combine embodiment, may be collectively referred to as here
Circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 4.Electronics shown in Fig. 4 is set
Standby 600 be only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 4, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 610, at least one above-mentioned storage unit 620, the different system components of connection
The bus 630 of (including storage unit 620 and processing unit 610), display unit 640.
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that various according to the present invention described in the execution of the processing unit 610 above-mentioned " illustrative methods " part of this specification
The step of exemplary embodiment.For example, the processing unit 610 can execute step S210. as shown in Figure 2 according to multiple
Dimension counts the Shopping Behaviors data of all users corresponding with each brand message, wherein the multiple dimension includes region
Dimension and user's dimension;Step S220. is based on the Shopping Behaviors data, calculates each dimension to described by clustering algorithm
The preference of brand message;The brand message that the preference is greater than preset threshold is determined as institute by step S230.
It states target brand message and shows the target brand message.
Storage unit 620 may include the readable 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.
Storage unit 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
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 670 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, terminal installation or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
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 comprising program code, it is described when described program product is run on the terminal device
Program code is for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to the present invention
The step of various exemplary embodiments.
Refering to what is shown in Fig. 5, the program product 700 for realizing the above method of embodiment according to the present invention is described,
It can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device, such as
It is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium 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 above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, touch control terminal or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (11)
1. a kind of target brand message determines method characterized by comprising
The Shopping Behaviors data of all users corresponding with each brand message are counted according to multiple dimensions, wherein the multiple
Dimension includes region dimension and user's dimension;
Based on the Shopping Behaviors data, by clustering algorithm from each dimensional analysis to the preference journey of the brand message
Degree;
The brand message that the preference is greater than preset threshold is determined as described in the target brand message and display
Target brand message.
2. target brand message according to claim 1 determines method, which is characterized in that the Shopping Behaviors data include
User click data corresponding with the brand message and user's order data.
3. target brand message according to claim 2 determines method, which is characterized in that in statistics and each brand message
Before the Shopping Behaviors data of corresponding all users, the method also includes:
Processing is filtered to user click data and user's order data, filters out the first user click data and first
User's order data.
4. target brand message according to claim 3 determines method, which is characterized in that statistics and each brand message pair
The Shopping Behaviors data of all users answered include:
The first user order data and the brand message are associated and generate region order brand message;
The region order brand message is grouped according to brand message dimension, to count all users to each brand
The click data of information.
5. target brand message according to claim 3 determines method, which is characterized in that statistics and each brand message pair
The Shopping Behaviors data of all users answered further include:
First user click data and the brand message are associated and generate user's click brand message;
It clicks brand message to the user to be grouped according to brand message dimension, to count all users to each brand
The click data of information.
6. target brand message according to claim 1 determines method, which is characterized in that by clustering algorithm from each described
Dimensional analysis includes: to the preference of the brand message
Each region is clustered by k-means++ clustering algorithm according to the Shopping Behaviors data and obtain with it is each described
The corresponding influence value in domain.
7. target brand message according to claim 1 determines method, which is characterized in that by clustering algorithm from each described
Preference of the dimensional analysis to the brand message further include:
Each user is clustered by k-means++ clustering algorithm according to the Shopping Behaviors data and is obtained and each use
The corresponding preference value in family.
8. target brand message according to claim 1 determines method, which is characterized in that show the target brand message
Include:
The corresponding target brand message is shown according to user identifier and/or ground domain identifier.
9. a kind of target brand message determining device characterized by comprising
Data statistics module, for counting the Shopping Behaviors number of all users corresponding with each brand message according to two dimensions
According to, wherein the Shopping Behaviors data include click data corresponding with the brand message and order data;
Cluster calculation module calculates each dimension to the product by clustering algorithm for being based on the Shopping Behaviors data
The preference of board information;
Target determination module, the brand message for the preference to be greater than preset threshold are determined as the target product
Board information simultaneously shows the target brand message.
10. a kind of electronic equipment characterized by comprising
Processor;And
Memory is stored with computer-readable instruction on the memory, and the computer-readable instruction is held by the processor
Realize that target brand message according to any one of claim 1 to 8 determines method when row.
11. a kind of computer readable storage medium, is stored thereon with computer program, the computer program is executed by processor
Shi Shixian target brand message according to any one of claim 1 to 8 determines method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710811278.0A CN109493101A (en) | 2017-09-11 | 2017-09-11 | Target brand message determines method, apparatus, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710811278.0A CN109493101A (en) | 2017-09-11 | 2017-09-11 | Target brand message determines method, apparatus, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109493101A true CN109493101A (en) | 2019-03-19 |
Family
ID=65687678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710811278.0A Pending CN109493101A (en) | 2017-09-11 | 2017-09-11 | Target brand message determines method, apparatus, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493101A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110298697A (en) * | 2019-06-24 | 2019-10-01 | 恩亿科(北京)数据科技有限公司 | The method and apparatus for obtaining the shopping need information of user |
CN110490646A (en) * | 2019-08-01 | 2019-11-22 | 北京东方国信科技股份有限公司 | The determination method and device of automobile brand target user |
CN110599373A (en) * | 2019-08-30 | 2019-12-20 | 北京金堤科技有限公司 | Trademark data generation method and device |
CN110930090A (en) * | 2019-11-04 | 2020-03-27 | 图林科技(深圳)有限公司 | E-commerce big data logistics supply chain control system based on artificial intelligence and block chain |
CN110992089A (en) * | 2019-11-25 | 2020-04-10 | 秒针信息技术有限公司 | Traffic sharing method and device, electronic equipment and readable storage medium |
CN111915115A (en) * | 2019-05-10 | 2020-11-10 | 北京沃东天骏信息技术有限公司 | Execution policy setting method and device |
CN113763004A (en) * | 2020-09-07 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information matching method and device |
CN114528484A (en) * | 2022-01-26 | 2022-05-24 | 北京金堤科技有限公司 | Preference mining method and device, storage medium and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104408641A (en) * | 2014-10-29 | 2015-03-11 | 深圳先进技术研究院 | Brand feature extraction method and system of electronic commerce recommendation model |
CN105046533A (en) * | 2015-08-07 | 2015-11-11 | 北京品友互动信息技术有限公司 | Method and apparatus for analyzing information delivery influence factor |
CN106817384A (en) * | 2015-11-27 | 2017-06-09 | 亿阳信通股份有限公司 | A kind of analysis method and system that behavior is accessed based on user's telecommunications |
CN106909663A (en) * | 2017-02-27 | 2017-06-30 | 杭州泰指尚科技有限公司 | Based on tagging user Brang Preference behavior prediction method and its device |
US20170337568A1 (en) * | 2015-02-13 | 2017-11-23 | Baidu Online Network Technology (Beijing) Co., Ltd. | Data processing method, system and computer device based on electronic payment behaviors |
-
2017
- 2017-09-11 CN CN201710811278.0A patent/CN109493101A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104408641A (en) * | 2014-10-29 | 2015-03-11 | 深圳先进技术研究院 | Brand feature extraction method and system of electronic commerce recommendation model |
US20170337568A1 (en) * | 2015-02-13 | 2017-11-23 | Baidu Online Network Technology (Beijing) Co., Ltd. | Data processing method, system and computer device based on electronic payment behaviors |
CN105046533A (en) * | 2015-08-07 | 2015-11-11 | 北京品友互动信息技术有限公司 | Method and apparatus for analyzing information delivery influence factor |
CN106817384A (en) * | 2015-11-27 | 2017-06-09 | 亿阳信通股份有限公司 | A kind of analysis method and system that behavior is accessed based on user's telecommunications |
CN106909663A (en) * | 2017-02-27 | 2017-06-30 | 杭州泰指尚科技有限公司 | Based on tagging user Brang Preference behavior prediction method and its device |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111915115A (en) * | 2019-05-10 | 2020-11-10 | 北京沃东天骏信息技术有限公司 | Execution policy setting method and device |
CN110298697A (en) * | 2019-06-24 | 2019-10-01 | 恩亿科(北京)数据科技有限公司 | The method and apparatus for obtaining the shopping need information of user |
CN110490646A (en) * | 2019-08-01 | 2019-11-22 | 北京东方国信科技股份有限公司 | The determination method and device of automobile brand target user |
CN110599373A (en) * | 2019-08-30 | 2019-12-20 | 北京金堤科技有限公司 | Trademark data generation method and device |
CN110930090A (en) * | 2019-11-04 | 2020-03-27 | 图林科技(深圳)有限公司 | E-commerce big data logistics supply chain control system based on artificial intelligence and block chain |
CN110930090B (en) * | 2019-11-04 | 2021-02-02 | 四川中油九洲北斗科技能源有限公司 | E-commerce big data logistics supply chain control system based on artificial intelligence and block chain |
CN110992089A (en) * | 2019-11-25 | 2020-04-10 | 秒针信息技术有限公司 | Traffic sharing method and device, electronic equipment and readable storage medium |
CN110992089B (en) * | 2019-11-25 | 2023-08-29 | 秒针信息技术有限公司 | Traffic sharing method and device, electronic equipment and readable storage medium |
CN113763004A (en) * | 2020-09-07 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information matching method and device |
CN114528484A (en) * | 2022-01-26 | 2022-05-24 | 北京金堤科技有限公司 | Preference mining method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109493101A (en) | Target brand message determines method, apparatus, electronic equipment and storage medium | |
KR102408476B1 (en) | Method for predicing purchase probability based on behavior sequence of user and apparatus therefor | |
CN110268409B (en) | Novel nonparametric statistical behavior recognition ecosystem for power fraud detection | |
US9386109B1 (en) | Web page associated with a node in a website traffic pattern | |
US20190019203A1 (en) | Method for providing marketing management data for optimization of distribution and logistics and apparatus for the same | |
CN108540826A (en) | Barrage method for pushing, device, electronic equipment and storage medium | |
CN109389442A (en) | Method of Commodity Recommendation and device, storage medium and electric terminal | |
EP2942749A1 (en) | Method and system for evaluating user satisfaction with respect to a user session | |
CN105893526A (en) | Multi-source data fusion system and method | |
CN106708821A (en) | User personalized shopping behavior-based commodity recommendation method | |
KR102191486B1 (en) | Automatic advertisement execution device, method for automatically generating campaign information for an advertisement medium to execute an advertisement and computer program for executing the method | |
JP2015099593A (en) | Generalized graph, rule, and spatial structure based on recommendation engine | |
US11017430B2 (en) | Delivering advertisements based on user sentiment and learned behavior | |
CN102365637A (en) | Characterizing user information | |
US10097664B2 (en) | Recommending media items based on purchase history | |
CN105069036A (en) | Information recommendation method and apparatus | |
CN110674620A (en) | Target file generation method, device, medium and electronic equipment | |
CN109299356A (en) | Activity recommendation method, apparatus, electronic equipment and storage medium based on big data | |
CN111695023A (en) | Information recommendation method and device, storage medium and equipment | |
CN111242709A (en) | Message pushing method and device, equipment and storage medium thereof | |
CN109934194A (en) | Picture classification method, edge device, system and storage medium | |
US20190220871A1 (en) | Physical product interaction based session | |
US20160267525A1 (en) | Determining traffic quality using event-based traffic scoring | |
CN112115710B (en) | Industry information identification method and device | |
KR20140031416A (en) | Item recommend system based on a collaborative filtering and method thereof, apparatus supporting the same |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |