CN108053268A - A kind of commercial articles clustering confirmation method and device - Google Patents
A kind of commercial articles clustering confirmation method and device Download PDFInfo
- Publication number
- CN108053268A CN108053268A CN201711484831.0A CN201711484831A CN108053268A CN 108053268 A CN108053268 A CN 108053268A CN 201711484831 A CN201711484831 A CN 201711484831A CN 108053268 A CN108053268 A CN 108053268A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- matrix
- data
- similarity
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of commercial articles clustering confirmation method and device, wherein, this method includes:Couple corresponding with the sales volume of targeted species commodity purchase user is sampled, and obtains customer consumption data to be clustered, wherein, customer consumption data buy the quantity of extensive stock for user;Using User ID as row, type of merchandize is row, and the first matrix is generated according to customer consumption data to be clustered, and the similarity of targeted species commodity between any two is calculated according to the data of the first matrix, and hierarchical clustering is carried out to targeted species commodity according to similarity, obtain commercial articles clustering result.The present invention is according to the cluster result, it can be realized that the higher type of merchandize of correlation in the order of user accurately to carry out bundle sale and recommendation to a variety of commodity, further improves effective sales volume of electric business.
Description
Technical field
The present invention relates to commodity consumption data analysis field more particularly to a kind of commercial articles clustering confirmation methods and device.
Background technology
With the fast development of network technology, electric business industry emerges rapidly therewith, and shopping at network infiltration is in people's life
Each corner.
The long-term electric business for laying particular emphasis on the industries such as women's dress, shoes and hats has accumulated many valuable data, can be sent out by data
Existing, the age may have entirely different style of wearing the clothes with similar people is taken in, it can be found that some special " clothes groups ", and
According to data combo promotion and recommendation can also be done to the commodity that some are often bought.
And during analyzing data, the way of the less electric business of commodity amount is end elimination system, be exactly sale not
Good commodity are directly eliminated, and change some new commodity, and this method is simple and directly perceived.Also some electrospray chambers take Pearson came
Correlation calculations do the relation between commodity, but under large-scale data, can not usually carry out commodity covariance exactly
It calculates and then realizes the accurate promotion and recommendation to commodity.
The content of the invention
An embodiment of the present invention provides a kind of commercial articles clustering confirmation method and devices, and solving current electric business can not be exactly
The technical issues of carrying out the reckoning of commodity covariance and then realizing the accurate promotion and recommendation to commodity.
An embodiment of the present invention provides a kind of commercial articles clustering confirmation method, including:
Couple corresponding with the sales volume of targeted species commodity purchase user is sampled, and obtains customer consumption to be clustered
Data, wherein, customer consumption data buy the quantity of extensive stock for user;
Using User ID as row, type of merchandize is row, and the first matrix is generated according to customer consumption data to be clustered, according to the
The data of one matrix calculate the similarity of targeted species commodity between any two, and targeted species commodity are divided according to similarity
Grade cluster, obtains commercial articles clustering result.
Preferably, a couple purchase user corresponding with the sales volume of targeted species commodity is sampled, and obtains to be clustered
Customer consumption data, wherein, customer consumption data further include before the quantity of extensive stock is bought for user:
The standard deviation of commodity sales number is calculated according to the sales volume of all kinds commodity got, rejects all kinds
It is not more than the data of standard deviation in the sales volume of class commodity, obtains the sales volume of targeted species commodity.
Preferably, using User ID as row, type of merchandize is row, and the first square is generated according to customer consumption data to be clustered
Battle array calculates the similarity of targeted species commodity between any two according to the data of the first matrix, and according to similarity to targeted species
Commodity carry out hierarchical clustering, obtain further including after commercial articles clustering result:
Transposition is carried out to the first matrix, obtains the second matrix, according between each user of the data of the second matrix calculating
Similarity, and hierarchical clustering is carried out to all users according to the similarity between each user, obtain user clustering result.
Preferably, calculating the similarity of targeted species commodity between any two according to the data of the first matrix is specially:
Pass through Euclidean distance or manhatton distance or Pearson came relatedness computation target according to the data of the first matrix
The distance of species commodity between any two, the distance of targeted species commodity between any two and targeted species commodity between any two similar
It spends corresponding.
Preferably, the embodiment of the present invention additionally provides a kind of commercial articles clustering confirmation device, including:
Sampling unit is sampled for a couple purchase user corresponding with the sales volume of targeted species commodity, is treated
The customer consumption data of cluster, wherein, customer consumption data buy the quantity of extensive stock for user;
Cluster cell, for using User ID as row, type of merchandize to be row, according to customer consumption data generation to be clustered the
One matrix calculates the similarity of targeted species commodity between any two according to the data of the first matrix, and according to similarity to target
Species commodity carry out hierarchical clustering, obtain commercial articles clustering result.
Preferably, a kind of commercial articles clustering provided in an embodiment of the present invention confirms that device further includes:
Culling unit, for calculating the standard of commodity sales number according to the sales volume of all kinds commodity got
Difference rejects the data for being not more than standard deviation in the sales volume of all kinds commodity, obtains the sales volume of targeted species commodity.
Preferably, a kind of commercial articles clustering provided in an embodiment of the present invention confirms that device further includes:
Transposition unit for carrying out transposition to the first matrix, obtains the second matrix, is calculated according to the data of the second matrix each
Similarity between a user, and hierarchical clustering is carried out to all users according to the similarity between each user, obtain user
Cluster result.
Preferably, cluster cell specifically includes:
Subelement is generated, for using User ID as row, type of merchandize to be row, is generated according to customer consumption data to be clustered
First matrix;
Computation subunit passes through Euclidean distance or manhatton distance or Pearson came for the data according to the first matrix
The distance of relatedness computation targeted species commodity between any two, the distance of targeted species commodity between any two and targeted species commodity
Similarity between any two is corresponding;
Subelement is clustered, for carrying out hierarchical clustering to targeted species commodity according to similarity, obtains commercial articles clustering result.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages:
An embodiment of the present invention provides a kind of commercial articles clustering confirmation method and device, wherein, this method includes:Pair and target
The corresponding purchase user of sales volume of species commodity is sampled, and obtains customer consumption data to be clustered, wherein, user disappears
Take the quantity that data buy extensive stock for user;Using User ID as row, type of merchandize is row, according to customer consumption to be clustered
Data generate the first matrix, and the similarity of targeted species commodity between any two is calculated according to the data of the first matrix, and according to phase
Hierarchical clustering is carried out to targeted species commodity like degree, obtains commercial articles clustering result.The present invention is by confirming targeted species commodity
Sales volume, and customer consumption data to be clustered are obtained after being sampled to its corresponding user, to the user's consumption data
It is presented in a manner of matrix computations and calculates the similarity between every two kinds of targeted species commodity, finally according to similarity to commodity
It carries out hierarchical clustering and obtains commercial articles clustering as a result, according to the cluster result, it can be realized that correlation is higher in the order of user
Type of merchandize, accurately to carry out bundle sale and recommendation to a variety of commodity, further improve effective sale of electric business
Volume.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow diagram of one embodiment of commercial articles clustering confirmation method provided in an embodiment of the present invention;
Fig. 2 is the structure diagram of one embodiment that a kind of commercial articles clustering provided in an embodiment of the present invention confirms device;
Fig. 3 is a kind of hierarchical clustering process of one embodiment of commercial articles clustering confirmation method provided in an embodiment of the present invention
Schematic diagram.
Specific embodiment
An embodiment of the present invention provides a kind of commercial articles clustering confirmation method and devices, and solving current electric business can not be exactly
The technical issues of carrying out the reckoning of commodity covariance and then realizing the accurate promotion and recommendation to commodity.
Goal of the invention, feature, advantage to enable the present invention is more apparent and understandable, below in conjunction with the present invention
Attached drawing in embodiment is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that disclosed below
Embodiment be only part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Scope.
Referring to Fig. 1, a kind of one embodiment of commercial articles clustering confirmation method provided by the invention, including:
101st, the standard deviation of commodity sales number is calculated according to the sales volume of all kinds commodity got, rejects institute
There are the data for being not more than standard deviation in the sales volume of species commodity, obtain the sales volume of targeted species commodity;
It collects comprising various commodity sales numbers in data, and commodity sales number substantially conforms to power law point
Cloth, to retain effective data, the present embodiment calculates commodity sales number by calculating the sales volume of all kinds commodity
Standard deviation, rejects the data for being not more than standard deviation in the sales volume of all kinds commodity, it is such as existing there are four types of commodity be respectively a,
Sales volume by calculating the standard deviation of these four commodity sales numbers, is more than the business of standard deviation by the b, sales volume of c and d
Product are left the targeted species commodity for participating in subsequently calculating, and what remaining was not more than reject.Wherein, the formula of standard deviation is calculated
For:
In formula, xiFor the sales volume of extensive stock, N is the number of species of commodity, and μ is the sales volume of extensive stock
Arithmetic mean of instantaneous value.
By the rejecting of data, retain effectively and be worth the type of merchandize and its sales volume of research, be subsequent matrix
Calculating is supported.
102nd, a couple purchase user corresponding with the sales volume of targeted species commodity is sampled, and obtains user to be clustered
Consumption data, wherein, customer consumption data buy the quantity of extensive stock for user;
In electronic commercial company, userbase is likely to be breached several hundred million, huge due to amount of user data, also needs
The filtering and screening of data are further carried out, after the sales volume of targeted species commodity is obtained, to the pin of targeted species commodity
The corresponding user of quantity is sold to be sampled, the ratio of sampling can be one of very, 1/20th etc., to user data into
After line sampling, the data of certain scale, i.e., customer consumption data to be clustered are obtained.
103rd, using User ID as row, type of merchandize is row, and the first matrix, root are generated according to customer consumption data to be clustered
Calculate the similarity of targeted species commodity between any two according to the data of the first matrix, and according to similarity to targeted species commodity into
Row hierarchical clustering obtains commercial articles clustering result;
In the present embodiment, the similarity according to the data of the first matrix calculating targeted species commodity between any two is specific
For:Pass through Euclidean distance or manhatton distance or Pearson came relatedness computation targeted species business according to the data of the first matrix
The distance of product between any two, similarity of the distance of targeted species commodity between any two with targeted species commodity between any two are opposite
It should.
It should be noted that the form of customer consumption data is generally as follows:User ID, commodity ID (species), quantity.Such as
User 1 has purchased commodity A, quantity 9, and user 1 has purchased commodity B, quantity 2, and user 2 has purchased commodity A, and quantity 4 is used
Family 2 has purchased commodity B, and more than consumption data is generated following first matrix by quantity 3 ...:
First matrix
User 1 | User 2 | User 3 | User 4 | User 5 | … | |
Commodity A | 9 | 4 | 0 | 0 | 0 | |
Commodity B | 2 | 3 | 5 | 0 | 0 | |
Commodity C | 0 | 0 | 2 | 0 | 0 | |
Commodity D | 0 | 0 | 0 | 7 | 11 | |
Commodity E | 0 | 0 | 0 | 9 | 8 | |
… |
Hierarchical clustering by continuously merging the most similar group two-by-two, to construct the level of a group
Structure.Each group therein is since a simple elements.During each iteration, hierarchical clustering algorithm meeting
The distance between each two group is calculated, and nearest Liang Ge groups are merged into a new group.This process repeats always
Go down, it is known that until only remaining next group.Then one piece of people occurred or commodity are found from group.These people or business
Product just have common feature.
It is the phase calculated between commodity and commodity purchasing to the core of the first matrix computations in the present embodiment, in clustering algorithm
Like degree the distance between (i.e. two kinds commodity), Euclidean distance or manhatton distance or the progress of the Pearson came degree of correlation can be passed through
It calculates, the process of calculating can be:As shown in figure 3, using commodity A, B, C, D, E as each independent group, extensive stock is calculated
Distance between any two, by data above, on the basis of commodity A, the distance between commodity B and commodity A are minimum, therefore will
A and B clusters continue to calculate and understand for new group A` subsequently through the data of user 3, the distance between commodity C and commodity B compared with
It is small, A` and C are clustered to obtain A``, and calculated by the data of user 4 and user 5, commodity D, commodity E are respectively with A``'s
Distance is larger, and the distance between commodity D and commodity E are smaller, therefore also can be D` by D and E clusters, then D` and A`` is clustered
For final result.By final result, grouping of commodities (A, B), (D, E) can preferentially carry out binding distribution, combine (A,
B, C) to take second place, combination (A, B, C, D, E) finally considers.
, can be by Pearson came similarity when similarity is calculated, it can be to avoid a other abnormal data to whole
Deviation caused by body, example code are as follows:
Pearson came similarity algorithm after # weightings.More similar, the value of return is fewer
#v1 and v2 is to need two groups of numerical value for comparing similarity
def pearson_similary(v1,v2):
Sum1=sum (v1)
Sum2=sum (v2)
Sum1Sq=sum ([pow (v, 2) for v in v1])
Sum2Sq=sum ([pow (v, 2) for v in v2])
PSum=sum ([v1 [i] * v2 [i] for i in range (len (v1))])
# calculates Pearson came similarity
Num=pSum- (sum1*sum2/len (v1))
Den=sqrt ((sum1Sq-pow (sum1,2)/len (v1)) * (sum2Sq-pow (sum2,2)/len (v1)))
If den==0:return 0
# processes result, more similar, and the value of return is fewer
return 1.0-num/den
104th, transposition is carried out to the first matrix, obtains the second matrix, according to the data of the second matrix calculate each user it
Between similarity, and according to the similarity between each user to all users carry out hierarchical clustering, obtain user clustering result.
In the present embodiment, the first matrix procession can be converted, code is as follows:
#data is a two-dimensional matrix
By carrying out transposition to the first matrix, can obtain the second matrix, as in step 103 to the data of the first matrix into
The process of row hierarchical clustering, user clustering can be obtained as a result, can be obtained by the result by carrying out hierarchical clustering to the second matrix
Know the similar crowd of purchase commodity, these crowds can be directed to and do personalized marketing strategy.
An embodiment of the present invention provides a kind of commercial articles clustering method, by confirming the sales volume of targeted species commodity, and
Customer consumption data to be clustered are obtained after being sampled to its corresponding user, to the user's consumption data with matrix computations
Mode presents and calculates the similarity between every two kinds of targeted species commodity, finally carries out hierarchical clustering to commodity according to similarity
Commercial articles clustering is obtained as a result, the grouping of commodities marketed of can obtaining being suitble to put together according to the cluster result, more into one
Step ground, the present invention can also find the crowd for having common consumption habit, can analyze consumer behavior and the custom of crowd.
The above are the detailed description of the embodiment progress to a kind of commercial articles clustering method provided by the invention, below to this hair
A kind of commercial articles clustering of bright offer confirms that one embodiment of device illustrates, referring to Fig. 2, the device includes:
Sampling unit 202 is sampled for a couple purchase user corresponding with the sales volume of targeted species commodity, obtains
Customer consumption data to be clustered, wherein, customer consumption data buy the quantity of extensive stock for user;
Cluster cell 203, for using User ID as row, type of merchandize to be row, is given birth to according to customer consumption data to be clustered
Into the first matrix, the similarity of targeted species commodity between any two is calculated according to the data of the first matrix, and according to similarity pair
Targeted species commodity carry out hierarchical clustering, obtain commercial articles clustering result.
In the present embodiment, a kind of commercial articles clustering provided in an embodiment of the present invention confirms that device further includes:
Culling unit 201, for calculating commodity sales number according to the sales volume of all kinds commodity got
Standard deviation rejects the data for being not more than standard deviation in the sales volume of all kinds commodity, obtains the sale of targeted species commodity
Quantity.
In the present embodiment, a kind of commercial articles clustering provided in an embodiment of the present invention confirms that device further includes:
Transposition unit 204 for carrying out transposition to the first matrix, obtains the second matrix, according to the data meter of the second matrix
The similarity between each user is calculated, and hierarchical clustering is carried out to all users according to the similarity between each user, is obtained
User clustering result.
In the present embodiment, cluster cell 203 specifically includes:
Subelement 2031 is generated, for using User ID as row, type of merchandize to be row, according to customer consumption data to be clustered
Generate the first matrix;
Computation subunit 2032 passes through Euclidean distance or manhatton distance or skin for the data according to the first matrix
The distance of the inferior relatedness computation targeted species commodity of that between any two, the distance and targeted species of targeted species commodity between any two
The similarity of commodity between any two is corresponding;
Subelement 2033 is clustered, for carrying out hierarchical clustering to targeted species commodity according to similarity, obtains commercial articles clustering
As a result.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit may be referred to the corresponding process in preceding method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
Division is only a kind of division of logic function, can there is other dividing mode, such as multiple units or component in actual implementation
It may be combined or can be integrated into another system or some features can be ignored or does not perform.It is another, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical location, you can be located at a place or can also be distributed to multiple
In network element.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
The form that hardware had both may be employed in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products
It embodies, which is stored in a storage medium, is used including some instructions so that a computer
Equipment (can be personal computer, server or the network equipment etc.) performs the complete of each embodiment the method for the present invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those of ordinary skill in the art that:It still can be to preceding
The technical solution recorded in each embodiment is stated to modify or carry out equivalent substitution to which part technical characteristic;And these
Modification is replaced, and the essence of appropriate technical solution is not made to depart from the spirit and scope of various embodiments of the present invention technical solution.
Claims (8)
1. a kind of commercial articles clustering confirmation method, which is characterized in that including:
Couple corresponding with the sales volume of targeted species commodity purchase user is sampled, and obtains customer consumption number to be clustered
According to, wherein, customer consumption data buy the quantity of extensive stock for user;
Using User ID as row, type of merchandize is row, the first matrix is generated according to customer consumption data to be clustered, according to the first square
The data of battle array calculate the similarity of targeted species commodity between any two, and targeted species commodity are carried out with classification according to similarity and is gathered
Class obtains commercial articles clustering result.
2. commercial articles clustering confirmation method according to claim 1, which is characterized in that the sale number pair with targeted species commodity
It measures corresponding purchase user to be sampled, obtains customer consumption data to be clustered, wherein, customer consumption data are bought for user
It is further included before the quantity of extensive stock:
The standard deviation of commodity sales number is calculated according to the sales volume of all kinds commodity got, rejects all kinds business
It is not more than the data of standard deviation in the sales volume of product, obtains the sales volume of targeted species commodity.
3. commercial articles clustering confirmation method according to claim 2, which is characterized in that using User ID as row, type of merchandize is
Row, the first matrix is generated according to customer consumption data to be clustered, and targeted species commodity two are calculated according to the data of the first matrix
Similarity between two, and hierarchical clustering is carried out to targeted species commodity according to similarity, it obtains going back after commercial articles clustering result
Including:
Transposition is carried out to the first matrix, obtains the second matrix, according to similar between each user of the data of the second matrix calculating
Degree, and hierarchical clustering is carried out to all users according to the similarity between each user, obtain user clustering result.
4. commercial articles clustering confirmation method according to claim 1, which is characterized in that calculate mesh according to the data of the first matrix
Marking the similarity of species commodity between any two is specially:
Pass through Euclidean distance or manhatton distance or Pearson came relatedness computation targeted species according to the data of the first matrix
The distance of commodity between any two, similarity phase of the distance of targeted species commodity between any two with targeted species commodity between any two
It is corresponding.
5. a kind of commercial articles clustering confirms device, which is characterized in that including:
Sampling unit is sampled for a couple purchase user corresponding with the sales volume of targeted species commodity, obtains to be clustered
Customer consumption data, wherein, customer consumption data for user buy extensive stock quantity;
For using User ID as row, type of merchandize to be row, the first square is generated according to customer consumption data to be clustered for cluster cell
Battle array calculates the similarity of targeted species commodity between any two according to the data of the first matrix, and according to similarity to targeted species
Commodity carry out hierarchical clustering, obtain commercial articles clustering result.
6. commercial articles clustering according to claim 5 confirms device, which is characterized in that further includes:
Culling unit, for calculating the standard deviation of commodity sales number according to the sales volume of all kinds commodity got,
The data for being not more than standard deviation in the sales volume of all kinds commodity are rejected, obtain the sales volume of targeted species commodity.
7. commercial articles clustering according to claim 6 confirms device, which is characterized in that further includes:
Transposition unit, for carrying out transposition to the first matrix, obtains the second matrix, and each use is calculated according to the data of the second matrix
Similarity between family, and hierarchical clustering is carried out to all users according to the similarity between each user, obtain user clustering
As a result.
8. commercial articles clustering according to claim 5 confirms device, which is characterized in that cluster cell specifically includes:
Subelement is generated, for using User ID as row, type of merchandize to be row, according to customer consumption data generation first to be clustered
Matrix;
Computation subunit is related by Euclidean distance or manhatton distance or Pearson came for the data according to the first matrix
Degree calculates the distance of targeted species commodity between any two, and the distance of targeted species commodity between any two and targeted species commodity are two-by-two
Between similarity it is corresponding;
Subelement is clustered, for carrying out hierarchical clustering to targeted species commodity according to similarity, obtains commercial articles clustering result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711484831.0A CN108053268A (en) | 2017-12-29 | 2017-12-29 | A kind of commercial articles clustering confirmation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711484831.0A CN108053268A (en) | 2017-12-29 | 2017-12-29 | A kind of commercial articles clustering confirmation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108053268A true CN108053268A (en) | 2018-05-18 |
Family
ID=62129313
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711484831.0A Pending CN108053268A (en) | 2017-12-29 | 2017-12-29 | A kind of commercial articles clustering confirmation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108053268A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255645A (en) * | 2018-07-20 | 2019-01-22 | 阿里巴巴集团控股有限公司 | A kind of consumption predictions method, apparatus and electronic equipment |
CN109740063A (en) * | 2019-01-17 | 2019-05-10 | 北京奇艺世纪科技有限公司 | Information recalls, information cluster method, device and equipment |
CN109902706A (en) * | 2018-11-09 | 2019-06-18 | 华为技术有限公司 | Recommended method and device |
CN111523918A (en) * | 2019-02-02 | 2020-08-11 | 北京极智嘉科技有限公司 | Commodity clustering method, commodity clustering device, commodity clustering equipment and storage medium |
CN111814944A (en) * | 2019-04-12 | 2020-10-23 | 北京百度网讯科技有限公司 | Vertex-to-community distribution method and device and terminal |
CN112329838A (en) * | 2020-11-02 | 2021-02-05 | 上海明略人工智能(集团)有限公司 | Method and device for determining category label of target set |
CN112434154A (en) * | 2019-08-26 | 2021-03-02 | 北京星选科技有限公司 | Object processing method and device, electronic equipment and storage medium |
CN113240453A (en) * | 2021-04-21 | 2021-08-10 | 福建神笔马良智能科技股份有限公司 | Commodity sales dynamic pushing management system based on block chain |
CN114648364A (en) * | 2022-03-30 | 2022-06-21 | 李艳华 | Method and system for analyzing sales data of electronic commerce website |
CN116796910A (en) * | 2023-08-21 | 2023-09-22 | 青岛中德智能技术研究院 | Order batch optimization method based on goods allocation strategy |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104111969A (en) * | 2014-06-04 | 2014-10-22 | 百度移信网络技术(北京)有限公司 | Method and system for measuring similarity |
CN105095306A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Operating method and device based on associated objects |
CN105335368A (en) * | 2014-06-06 | 2016-02-17 | 阿里巴巴集团控股有限公司 | Product clustering method and apparatus |
CN105809474A (en) * | 2016-02-29 | 2016-07-27 | 深圳市未来媒体技术研究院 | Hierarchical commodity information filtering and recommending method |
US20160379288A1 (en) * | 2015-06-29 | 2016-12-29 | Wal-Mart Stores, Inc. | Integrated Meal Plan Generation and Supply Chain Management |
CN107292713A (en) * | 2017-06-19 | 2017-10-24 | 武汉科技大学 | A kind of rule-based individual character merged with level recommends method |
-
2017
- 2017-12-29 CN CN201711484831.0A patent/CN108053268A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105095306A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Operating method and device based on associated objects |
CN104111969A (en) * | 2014-06-04 | 2014-10-22 | 百度移信网络技术(北京)有限公司 | Method and system for measuring similarity |
CN105335368A (en) * | 2014-06-06 | 2016-02-17 | 阿里巴巴集团控股有限公司 | Product clustering method and apparatus |
US20160379288A1 (en) * | 2015-06-29 | 2016-12-29 | Wal-Mart Stores, Inc. | Integrated Meal Plan Generation and Supply Chain Management |
CN105809474A (en) * | 2016-02-29 | 2016-07-27 | 深圳市未来媒体技术研究院 | Hierarchical commodity information filtering and recommending method |
CN107292713A (en) * | 2017-06-19 | 2017-10-24 | 武汉科技大学 | A kind of rule-based individual character merged with level recommends method |
Non-Patent Citations (1)
Title |
---|
张彩霞等: "《大数据时代,企业借助互联网成功转型升级》", 31 July 2015, 中国财富出版社 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255645B (en) * | 2018-07-20 | 2021-09-14 | 创新先进技术有限公司 | Consumption prediction method and device and electronic equipment |
CN109255645A (en) * | 2018-07-20 | 2019-01-22 | 阿里巴巴集团控股有限公司 | A kind of consumption predictions method, apparatus and electronic equipment |
CN109902706A (en) * | 2018-11-09 | 2019-06-18 | 华为技术有限公司 | Recommended method and device |
CN109902706B (en) * | 2018-11-09 | 2023-08-22 | 华为技术有限公司 | Recommendation method and device |
CN109740063A (en) * | 2019-01-17 | 2019-05-10 | 北京奇艺世纪科技有限公司 | Information recalls, information cluster method, device and equipment |
CN111523918A (en) * | 2019-02-02 | 2020-08-11 | 北京极智嘉科技有限公司 | Commodity clustering method, commodity clustering device, commodity clustering equipment and storage medium |
CN111523918B (en) * | 2019-02-02 | 2023-09-19 | 北京极智嘉科技股份有限公司 | Commodity clustering method, device, equipment and storage medium |
CN111814944A (en) * | 2019-04-12 | 2020-10-23 | 北京百度网讯科技有限公司 | Vertex-to-community distribution method and device and terminal |
CN112434154A (en) * | 2019-08-26 | 2021-03-02 | 北京星选科技有限公司 | Object processing method and device, electronic equipment and storage medium |
CN112329838A (en) * | 2020-11-02 | 2021-02-05 | 上海明略人工智能(集团)有限公司 | Method and device for determining category label of target set |
CN112329838B (en) * | 2020-11-02 | 2024-02-02 | 上海明略人工智能(集团)有限公司 | Method and device for determining target set category label |
CN113240453A (en) * | 2021-04-21 | 2021-08-10 | 福建神笔马良智能科技股份有限公司 | Commodity sales dynamic pushing management system based on block chain |
CN113240453B (en) * | 2021-04-21 | 2024-05-28 | 福建神笔马良智能科技股份有限公司 | Dynamic commodity sales promotion management system based on block chain |
CN114648364A (en) * | 2022-03-30 | 2022-06-21 | 李艳华 | Method and system for analyzing sales data of electronic commerce website |
CN116796910A (en) * | 2023-08-21 | 2023-09-22 | 青岛中德智能技术研究院 | Order batch optimization method based on goods allocation strategy |
CN116796910B (en) * | 2023-08-21 | 2023-11-21 | 青岛中德智能技术研究院 | Order batch optimization method based on goods allocation strategy |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108053268A (en) | A kind of commercial articles clustering confirmation method and device | |
Syakur et al. | Integration k-means clustering method and elbow method for identification of the best customer profile cluster | |
Aryuni et al. | Customer segmentation in XYZ bank using K-means and K-medoids clustering | |
CN106651546B (en) | Electronic commerce information recommendation method oriented to smart community | |
US20150294336A1 (en) | Multidimensional personal behavioral tomography | |
CN108960992A (en) | A kind of information recommendation method and relevant device | |
CN109559208A (en) | A kind of information recommendation method, server and computer-readable medium | |
CN107516246B (en) | User type determination method, user type determination device, medium and electronic equipment | |
Chen et al. | Predicting default risk on peer-to-peer lending imbalanced datasets | |
CN106529968A (en) | Customer classification method and system thereof based on transaction data | |
CN110489642A (en) | Method of Commodity Recommendation, system, equipment and the medium of Behavior-based control signature analysis | |
CN104715409A (en) | Method and system for electronic commerce user purchasing power classification | |
CN102521605A (en) | Wave band selection method for hyperspectral remote-sensing image | |
CN109948724A (en) | A kind of electric business brush single act detection method based on improvement LOF algorithm | |
Tan et al. | Time series clustering: A superior alternative for market basket analysis | |
CN106127493A (en) | A kind of method and device analyzing customer transaction behavior | |
CN105956122A (en) | Object attribute determining method and device | |
Farooqi et al. | Effectiveness of Data mining in Banking Industry: An empirical study | |
CN109461083B (en) | Method and device for determining preferential exchange rate | |
CN114626925A (en) | Recommendation method and device for financial products, electronic equipment and storage medium | |
Xue et al. | Intelligent mining on purchase information and recommendation system for e-commerce | |
Regmi et al. | Customer Market Segmentation using Machine Learning Algorithm | |
CN116362236A (en) | Target word mining method and device and storage medium | |
Rezaeian et al. | Measuring Customers Satisfaction of ECommerce Sites Using Clustering Techniques: Case Study of Nyazco Website. | |
Zhao | Marketing Segmentation in Consumer Product Industry |
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: 20180518 |