CN109597858A - A kind of classification method of trade company and its recommended method and its device of device and trade company - Google Patents
A kind of classification method of trade company and its recommended method and its device of device and trade company Download PDFInfo
- Publication number
- CN109597858A CN109597858A CN201811534645.8A CN201811534645A CN109597858A CN 109597858 A CN109597858 A CN 109597858A CN 201811534645 A CN201811534645 A CN 201811534645A CN 109597858 A CN109597858 A CN 109597858A
- Authority
- CN
- China
- Prior art keywords
- trade company
- order data
- user
- merchant category
- recommended
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The present embodiments relate to technical field of data processing, a kind of classification method of trade company and its recommended method and its device of device and trade company are disclosed.A kind of classification method of trade company in the present invention, comprising: obtain History Order data, order data is clustered according to the user information of order data；Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；Classified according to characteristic of division to trade company to be sorted.A kind of sorter of trade company, the recommended method of trade company, recommendation apparatus, electronic equipment and non-volatile memory medium are also provided in the present invention, more intelligent classification and the way of recommendation can be provided, user is made to be easier to obtain desired trade company.
Description
Technical field
The present invention relates to data processing field, in particular to the classification method of a kind of trade company and its recommendation of device and trade company
Method and device thereof.
Background technique
Internet enterprises are based on platform development growth, and platform model becomes the mark sexual norm of Internet era.Platform
Middle trade company converges, although having assembled more trade companies and commodity, but also user is dazzled, searches desired trade company and quotient
It is more difficult when product.
The mode of classification is generally used to provide selection interface for user in existing platform, but simple classification has been unable to satisfy
The requirement of user's multiplicity.Existing another kind classification method, although using hierarchical cluster (such as K-means clustering algorithm),
Feature is extracted from trade company's feature, and the type that the feature and needs just extracted cluster inputs specific Clustering Model, in turn
Hierarchical cluster.Being polymerized to several classes does not have specific target, causes Clustering Effect undesirable, while only special with a dimension expression trade company
Sign, information content are not abundant enough.
Summary of the invention
A kind of classification method for being designed to provide trade company of embodiment of the present invention and its recommendation side of device and trade company
Method and its device can provide more intelligent classification and the way of recommendation, and user is made to be easier to obtain desired trade company.
In order to solve the above technical problems, embodiments of the present invention provide a kind of classification method of trade company, comprising: obtain
History Order data cluster the order data according to the user information of the order data；According to the institute after cluster
The degree of correlation for stating order data Zhong Ge trade company determines characteristic of division；Trade company to be sorted is divided according to the characteristic of division
Class.
Embodiments of the present invention additionally provide a kind of recommended method of trade company, comprising: obtain the History Order number of user
According to；Merchant Category to be recommended is determined according to the History Order data and Merchant Category information；By identified Merchant Category
Subordinate trade company recommend the user；Wherein, the classification method of the Merchant Category information from above-mentioned trade company.
Embodiments of the present invention additionally provide a kind of sorter of trade company, comprising: module are obtained, for obtaining history
Order data；Cluster module, for being clustered according to the user information of the order data to the order data；Determine mould
Block, for determining characteristic of division according to the degree of correlation of the order data Zhong Ge trade company after cluster；Categorization module is used for basis
The characteristic of division classifies to trade company to be sorted.
Embodiments of the present invention additionally provide a kind of recommendation apparatus of trade company, comprising: module are obtained, for obtaining user
History Order data；Classification determining module, it is to be recommended for being determined according to the History Order data and Merchant Category information
Merchant Category；Recommending module, for the subordinate trade company of identified Merchant Category to be recommended the user；Wherein, described
Sorter of the Merchant Category information from above-mentioned trade company.
Embodiments of the present invention additionally provide a kind of electronic equipment, including memory and processor, memory storage meter
Calculation machine program, processor execute when running program: History Order data are obtained, according to the user information of the order data to institute
Order data is stated to be clustered；Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；According to
The characteristic of division classifies to trade company to be sorted.
Embodiments of the present invention additionally provide a kind of electronic equipment, including memory and processor, memory storage meter
Calculation machine program, processor execute when running program: obtaining the History Order data of user；According to the History Order data and quotient
Family classification information determines Merchant Category to be recommended；The subordinate trade company of identified Merchant Category is recommended into the user；Its
In, the classification method of the Merchant Category information from above-mentioned trade company.
Embodiments of the present invention additionally provide a kind of non-volatile memory medium, for storing computer-readable program,
The computer-readable program is used to execute the classification method such as above-mentioned trade company for computer.
Embodiments of the present invention additionally provide a kind of non-volatile memory medium, for storing computer-readable program,
The computer-readable program is used to execute the recommended method such as above-mentioned trade company for computer.
In terms of existing technologies, the main distinction and its effect are embodiment of the present invention: from the lower odd number of user
According to starting with, the correlation of trade company is determined, taken user into consideration and placed an order implicit preference consistency itself, so relative to existing
For the mode classification of dining room angle, single angle is Merchant Category under user, more accurate, is analyzed also more data
Has referential.Later according to one-state and Merchant Category under the history of user, the Merchant Category recommended for user is determined, later
The recommendation of trade company is carried out to user according to the classification.Since Merchant Category uses the classification based on forms data under user, cover
The preference consistency of user, so recommendation later more targetedly more will meet the demand of user.
As a further improvement, described determine that classification is special according to the degree of correlation of the order data Zhong Ge trade company after cluster
Sign, specifically: training sample is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；Utilize the trained sample
This training obtains neural network model, and the input of the neural network model is at least two trade companies, and exporting is described at least two
The similarity of a trade company；The characteristic of division is determined according to the middle layer of neural network model.Go out to influence using model discrimination
The characteristic of division of Merchant Category result, feature determine accurate and effective.
As a further improvement, the neural network model is monolayer neural networks model.Utilize monolayer neural networks mould
Type so that feature determine it is simple and quick.
As a further improvement, the middle layer is preset with width, the width is bigger, the characteristic of division determined
Feature quantity it is more.Feature quantity can be easily adjusted using the adjustment of width, is adjusted as needed conducive to technical staff
The feature quantity of acquisition.
As a further improvement, the middle layer of the monolayer neural networks is obtained using following manner: minimizing the degree of correlation
The distance of highest trade company maximizes the distance of the minimum trade company of the degree of correlation, obtains the middle layer.Specify the acquisition of middle layer
Method.
As a further improvement, the highest trade company of the degree of correlation is the trade company to be placed an order by same user, the degree of correlation
Minimum trade company is the trade company to be placed an order by different user.Specify the determination method of the degree of correlation.
As a further improvement, the user information according to the order data clusters the order data,
It include: the order data for summarizing the same class user respectively and placing an order；Classify to the order data summarized.It is clear a kind of poly-
Class mode.
As a further improvement, the described pair of order data summarized is classified, specifically include: belonging in classification results
Of a sort order data is recorded as document files.Document files is established to analyze and call convenient for subsequent data.
Detailed description of the invention
Fig. 1 is the flow chart of the classification method of the trade company in first embodiment according to the present invention；
Fig. 2 is the flow chart for determining characteristic of division in the classification method of the trade company in second embodiment according to the present invention；
Fig. 3 is the schematic diagram clustered in the classification method of the trade company in second embodiment according to the present invention；
Fig. 4 is the schematic diagram of model training in the classification method of the trade company in second embodiment according to the present invention；
Fig. 5 is the flow chart of the recommended method of the trade company in third embodiment according to the present invention；
Fig. 6 is the sorter schematic diagram of the trade company in the 4th embodiment according to the present invention；
Fig. 7 is the recommendation apparatus schematic diagram of the trade company in the 5th embodiment according to the present invention；
Fig. 8 is the electronic devices structure schematic diagram that sixth embodiment provides according to the present invention.
Fig. 9 is the electronic devices structure schematic diagram that the 7th embodiment provides according to the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order to make the reader understand this application better, many technical details are proposed.But even if without these technical details
And various changes and modifications based on the following respective embodiments, the application technical solution claimed also may be implemented.With
Under the division of each embodiment be for convenience, any restriction should not to be constituted to specific implementation of the invention, it is each
Embodiment can be combined with each other mutual reference under the premise of reconcilable.
The first embodiment of the present invention is related to a kind of classification method of trade company, trade company therein can be dining room, dress ornament
Shop or beauty salon etc., present embodiment are mainly specifically described based on dining room.Its flow chart is as shown in Figure 1, this method packet
It includes:
Step 101, History Order data are obtained.
Specifically, History Order data can come from the institute of certain period in a user, one kind user either platform
There are History Order data.More specifically, may include user information in order data, merchant information, lower single time, place an order gold
The information such as volume.
Step 102, order data is clustered.
Specifically, order data is clustered according to the user information of order data in this step, wherein when cluster
Confirm whether Liang Jia trade company similar, can also can according to need according to whether place an order determination there are same user according to whether
It places an order determination there are same class user.That is, can summarize respectively under same class user (or same user) in this step
Single order data；Classify to the order data summarized.
Furtherly, since a user may place an order in different trade companies, and the personal preference of same user is basic
It is constant, thus the trade company that same user places an order conceal by it is single under the user of similar hobby a possibility that, according to whether existing same
Whether the one user determining Liang Ge trade company that places an order is similar, has taken user into consideration and has placed an order implicit consistency itself, so that classification knot
The demand that fruit is more close to the users.
Such as: KFC and the order in McDonald are respectively included in the History Order of a certain user, then it can be according to depositing
It places an order in same user, determines that KFC is similar with McDonald.It can be found that in practical application, user can select same flavor,
The trade company of style places an order, so this kind of trade company is classified as one kind, is conducive to determine the possible Xia Dan trade company of user.
It should be noted that being recorded as document files to of a sort order data affiliated in classification results in this step.
The History Order of single user can accurately portray the taste of single user, the information such as address, we are by single user
A series of History Order record treats as a document files, then the subsequent calling for carrying out data using these files is analyzed
When, it is more simple direct.
Above-mentioned steps 101 and 102 are the preparation stages of data, can also be as needed to ready in this stage
Data such as are cleaned, are denoised at the operation, and details are not described herein.
Step 103, characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster.
Specifically, trade company's analysis that characteristic of division can have similar users to place an order according to determined by History Order data
It obtains, the common trait for the trade company for having similar users to place an order is extracted, as characteristic of division.
More specifically, the degree of correlation can have preset determining rule, the highest trade company of the degree of correlation is by under same user
Single trade company, the minimum trade company of the degree of correlation is the trade company to be placed an order by different user.Wherein, the degree of correlation can be quantified as number,
If 1 and 0,1 indicates degree of correlation highest, 0 indicates that the degree of correlation is minimum, and number can be expressed in addition to being expressed with integer with percentage number,
It will not enumerate herein.
Step 104, classified according to characteristic of division to trade company to be sorted.
Specifically, characteristic of division is to can use the classification determined in step 103 for the foundation of Merchant Category to be sorted
Feature is classified, and in practical application, disaggregated model can be formed according to determining characteristic of division, to utilize disaggregated model pair
Trade company to be sorted is classified automatically, is quickly easily realized.
As it can be seen that present embodiment is in terms of existing technologies, the main distinction and its effect are: from the lower odd number of user
According to starting with, the correlation of trade company is determined, taken user into consideration and placed an order implicit preference consistency itself, so relative to existing
For the mode classification of dining room angle, single angle is Merchant Category under user, more accurate, is analyzed also more data
Have referential, it is also more accurate when needing commercial product recommending.
In addition, present embodiment can also be applied to boutique, there is hobby one since same user wears to cost in dress ornament
The characteristics of cause property, so the different boutiques that same user places an order, have the characteristics that lower single user it is similar according to lower single user into
Row classification so that be attributed to a kind of boutique by it is single under same user or same class user a possibility that it is higher, be conducive to subsequent
Dress ornament precisely recommend.
Second embodiment of the present invention is related to a kind of classification method of trade company.
Present embodiment specifies the concrete mode for determining characteristic of division according to the degree of correlation, is determined in a manner of model training
Characteristic of division, the determination process of characteristic of division as shown in Fig. 2, specifically includes the following steps:
Step 201, training sample is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster.
Specifically, by taking same user carries out order data cluster as an example, gathered by the order data that same user places an order and be
It is a kind of, that is to say, that cluster out a kind of order data respectively for each user.In practical application, a kind of user (can also be used
Family classification can make a reservation for) order data cluster is carried out, gathered by the order data that same class user places an order for one kind.
In embodiment, it can will be present between the trade company that same user places an order with Liang Ge trade company for a training sample
The degree of correlation is confirmed as 1, and the degree of correlation between the trade company to place an order there is no same user is confirmed as 0, the trade company that the degree of correlation is 1 later
In, training sample can be become two-by-two for one group, equally relevant degree is in 0 trade company, can two-by-two be one group becomes training sample
This.In present embodiment, the number of trade company is 2 in every group of training sample, in practical application in every group of training sample trade company
Number can be selected according to practical, will not enumerate herein.
Step 202, neural network model is obtained using training sample training.
Specifically, it is trained using the training sample determined in step 201, neural network model used by training
Input be at least two trade companies (one group of training sample), export at least two trade companies similarity (this group of training sample
The degree of correlation).
More specifically, neural network model can be monolayer neural networks model in present embodiment, simplify as far as possible
Computational complexity.
Step 203, characteristic of division is determined according to the middle layer of neural network.
Specifically, after the completion of training, the middle layer hidden in the neural network model is the classification obtained needed for including
Feature.
It should be noted that the width of middle layer is related with the feature quantity of characteristic of division, width is bigger, point determined
The feature quantity of category feature is more.In practical application, the quantity of the characteristic of division of acquisition is more, and subsequent computational complexity is more
Height, but the classification results obtained are more accurate, and the quantity of characteristic of division is fewer, and subsequent computational complexity is lower.So can be with
According to subsequent required feature quantity, change the width of middle layer.
Above-mentioned steps 201 to 203 are described according to how the mode of model training according to cluster result determines characteristic of division.
Present embodiment is further described the classification method of trade company by taking dining room as an example:
In History Order data acquisition, using exemplary cloud platform as source, the acquisition of History Order data is carried out；It
Afterwards, order cluster is carried out with placing an order for single user, cluster result as shown in figure 3, each user correspond to a document files, from
And obtain a series of document files；Then, model training is carried out with the order data in each document files, training principle is such as
Shown in Fig. 4.
Wherein, during the actual operation of model training, such as each dining room can be set by way of matrix operation
The id for pattern of delimiting the organizational structure, the coding mode such as corresponding id of dining room A are [0000000 ... 01000 ... 00000], and B corresponding id in dining room is
[0000000 ... 00001 ... 00000], in each id only one be " 1 ", remaining is " 0 ", and each not phase in the position where " 1 "
Together.
When training, input for same user it is a series of descended single dining room id, the similitude two-by-two in these dining rooms is 1, non-
The dining room correlation that same user places an order is 0, can use steepest descent method and back propagation, in this way can be by monolayer neuronal
The middle layer of network trains.
Further, monolayer neural networks are obtained after training, minimize the distance of the highest trade company of the degree of correlation, are maximized
The distance of the minimum trade company of the degree of correlation, obtains hiding middle layer, obtains dining room with the product of dining room id layer by layer using intermediate
Cluster feature (i.e. the vectorization data in dining room).
As it can be seen that present embodiment explicitly use model discrimination go out influence Merchant Category result characteristic of division method, instruction
Monolayer neural networks are specifically used when practicing, and simplify operation as far as possible, and characteristic of division determines accurate and effective.
Third embodiment of the present invention is related to a kind of recommended method of trade company, trade company therein equally can be dining room,
Boutique or beauty salon etc., present embodiment are mainly specifically described based on dining room.Its flow chart is as shown in figure 5, the party
Method includes:
Step 501, the History Order data of user are obtained.
Specifically, the History Order data of user to be recommended are obtained.
Step 502, Merchant Category to be recommended is determined according to History Order data and Merchant Category information.
Specifically, Merchant Category information can be using any in first embodiment or second embodiment in this step
Classification information in the classification method of a trade company.
More specifically, this step can specifically include: according to Merchant Category information by the order in History Order data
Classify；Merchant Category to be recommended is determined according to classification results.In present embodiment, first each History Order is divided
Class, classification foundation therein are Merchant Category belonging to order, and trade company's order of the same category is classified as one kind, determines each point later
The maximum class validation of History Order number can be Merchant Category to be recommended by the History Order number in class.
In practical application, Merchant Category to be recommended other than above-mentioned validation testing, can also using as under type into
Row confirmation: trade company belonging to order in History Order data is determined respectively；According to Merchant Category information by the trade company determined into
Row classification；Merchant Category to be recommended is determined according to classification results.Specifically, trade company belonging to each History Order is first determined,
The classification of each trade company is determined again, and the trade company of the same category is classified as one kind, determines trade company's quantity in each classification later, can be by quotient
The maximum class validation of amount amount is Merchant Category to be recommended.
Step 503, the subordinate trade company of identified Merchant Category is recommended into user.
Specifically, by after Merchant Category to be recommended confirmation, the trade company of classification subordinate can be recommended into user,
In, it when recommending, can specifically recommend all trade companies of classification subordinate, the part trade company of classification subordinate can also be recommended, recommend
Trade company's quantity can set according to actual needs, it is not limited here.
As it can be seen that present embodiment carries out quotient to user using the classification method in first embodiment or second embodiment
Family is recommended, and is a kind of practical application to above-mentioned classification method.Since classification foundation is obtained from the buying behavior of user, so
Determining classification more meets the buying habit of user, and the recommended method also allowed in present embodiment more meets user demand,
Recommendation results are more accurate targetedly.
Furthermore since present embodiment applies technical solution all in first embodiment or second embodiment,
So technical detail described in first embodiment or second embodiment is equally applicable to present embodiment, it is no longer superfluous herein
It states.
4th embodiment of the invention is related to a kind of sorter of trade company, as shown in fig. 6, the device includes:
Module is obtained, for obtaining History Order data.
Cluster module, for being clustered according to the user information of order data to order data.
Determining module, for determining characteristic of division according to the degree of correlation of the order data Zhong Ge trade company after cluster.
Categorization module, for being classified according to characteristic of division to trade company to be sorted.
In one example, cluster module specifically includes:
Sample determines submodule, for determining training sample according to the degree of correlation of the order data Zhong Ge trade company after cluster.
Training submodule, for obtaining neural network model using training sample training.Specifically, neural network model
Input be at least two trade companies, export as the similarity of at least two trade companies.
Submodule is determined, for determining characteristic of division according to the middle layer of neural network model.
In one example, above-mentioned neural network model can be monolayer neural networks model.
In one example, above-mentioned middle layer can be preset with width, wherein width is bigger, the characteristic of division determined
Feature quantity it is more.
In one example, the middle layer of above-mentioned monolayer neural networks is obtained using following manner: minimizing the degree of correlation most
The distance of high trade company maximizes the distance of the minimum trade company of the degree of correlation, obtains middle layer.
In one example, the highest trade company of the degree of correlation is the trade company to be placed an order by same user, the minimum trade company of the degree of correlation
For the trade company to be placed an order by different user.
In one example, cluster module can specifically include:
Collects submodule, the order data to place an order for summarizing same class user respectively.
Classification submodule, for classifying to the order data summarized.
In one example, of a sort order data affiliated in classification results is specifically recorded as document by classification submodule
File.
As it can be seen that present embodiment is in terms of existing technologies, the main distinction and its effect are: from the lower odd number of user
According to starting with, the correlation of trade company is determined, taken user into consideration and placed an order implicit preference consistency itself, so relative to existing
For the mode classification of dining room angle, single angle is Merchant Category under user, more accurate, is analyzed also more data
Have referential, it is also more accurate when needing commercial product recommending.
It is not difficult to find that present embodiment is Installation practice corresponding with first embodiment, present embodiment can be with
First embodiment is worked in coordination implementation.The relevant technical details mentioned in first embodiment still have in the present embodiment
Effect, in order to reduce repetition, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in
In first embodiment.
It is noted that each module involved in present embodiment is logic module, and in practical applications, one
A logic unit can be a physical unit, be also possible to a part of a physical unit, can also be with multiple physics lists
The combination of member is realized.In addition, in order to protrude innovative part of the invention, it will not be with solution institute of the present invention in present embodiment
The technical issues of proposition, the less close unit of relationship introduced, but this does not indicate that there is no other single in present embodiment
Member.
5th embodiment of the invention is related to a kind of recommendation apparatus of trade company, as shown in fig. 7, the device includes:
Module is obtained, for obtaining the History Order data of user.
Classification determining module, for determining Merchant Category to be recommended according to History Order data and Merchant Category information.
Recommending module, for the subordinate trade company of identified Merchant Category to be recommended user.
Wherein, the sorter of trade company of the Merchant Category information in the 4th embodiment.
In one example, classification determining module can specifically include:
First classification submodule, for the order in History Order data to be classified according to Merchant Category information.
First determines submodule, for determining Merchant Category to be recommended according to classification results.
In another example, classification determining module can specifically include:
Second determines submodule, for determining trade company belonging to order in History Order data respectively.
Second classification submodule, for the trade company determined to be classified according to Merchant Category information.
Third determines submodule, for determining Merchant Category to be recommended according to classification results.
As it can be seen that present embodiment is in terms of existing technologies, the main distinction and its effect are: present embodiment utilizes
Sorter in 4th embodiment carries out trade company's recommendation to user, is a kind of practical application to above-mentioned sorter.By
It obtains from the buying behavior of user in classification foundation, so the classification determined more meets the buying habit of user, also allows for
Recommended method in present embodiment more meets user demand, and recommendation results are more accurate targetedly.
It is not difficult to find that present embodiment is Installation practice corresponding with third embodiment, present embodiment can be with
Third embodiment is worked in coordination implementation.The relevant technical details mentioned in third embodiment still have in the present embodiment
Effect, in order to reduce repetition, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in
In third embodiment.
It is noted that each module involved in present embodiment is logic module, and in practical applications, one
A logic unit can be a physical unit, be also possible to a part of a physical unit, can also be with multiple physics lists
The combination of member is realized.In addition, in order to protrude innovative part of the invention, it will not be with solution institute of the present invention in present embodiment
The technical issues of proposition, the less close unit of relationship introduced, but this does not indicate that there is no other single in present embodiment
Member.
Sixth embodiment of the invention is related to a kind of electronic equipment, as shown in figure 8, the electronic equipment includes: at least one
A processor 801；And the memory 802 with the communication connection of at least one processor 801；And with scanning means communication link
The communication component 803 connect, communication component 803 send and receive data under the control of processor 801；Wherein, memory 802 is deposited
The instruction that can be executed by least one processor 801 is contained, instruction is executed by least one processor 801 to realize:
History Order data are obtained, order data is clustered according to the user information of order data.
Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster.
Classified according to characteristic of division to trade company to be sorted.
Specifically, which includes: one or more processors 801 and memory 802, at one in Fig. 8
For reason device 801.Processor 801, memory 802 can be connected by bus or other modes, to be connected by bus in Fig. 8
It is connected in example.Memory 802 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module.Processor 801 is stored in non-easy in memory 802 by operation
The property lost software program, instruction and module realize above-mentioned quotient thereby executing the various function application and data processing of equipment
The classification method at family.
Memory 802 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；It storage data area can the Save option list etc..In addition, memory 802 can be with
It can also include nonvolatile memory, for example, at least disk memory, a flash memory including high-speed random access memory
Device or other non-volatile solid state memory parts.In some embodiments, it includes relative to processing that memory 802 is optional
The remotely located memory 802 of device 801, these remote memories 802 can pass through network connection to external equipment.Above-mentioned network
Example include but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more module is stored in memory 802, when being executed by one or more processor 801, is held
The classification method of trade company in the above-mentioned any means embodiment of row.
The said goods can be performed the application embodiment provided by method, have the corresponding functional module of execution method and
Beneficial effect, the not technical detail of detailed description in the present embodiment, reference can be made to method provided by the application embodiment.
7th embodiment of the invention is related to a kind of electronic equipment, as shown in figure 9, the electronic equipment includes: at least one
A processor 901；And the memory 902 with the communication connection of at least one processor 901；And with scanning means communication link
The communication component 903 connect, communication component 903 send and receive data under the control of processor 901；Wherein, memory 902 is deposited
The instruction that can be executed by least one processor 901 is contained, instruction is executed by least one processor 901 to realize:
Obtain the History Order data of user；
Merchant Category to be recommended is determined according to History Order data and Merchant Category information；
The subordinate trade company of identified Merchant Category is recommended into user；
Wherein, the classification side of Merchant Category information any one trade company in first embodiment or second embodiment
Method.
Specifically, which includes: one or more processors 901 and memory 902, at one in Fig. 9
For reason device 901.Processor 901, memory 902 can be connected by bus or other modes, to be connected by bus in Fig. 9
It is connected in example.Memory 902 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module.Processor 901 is stored in non-easy in memory 902 by operation
The property lost software program, instruction and module realize above-mentioned quotient thereby executing the various function application and data processing of equipment
The recommended method at family.
Memory 902 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；It storage data area can the Save option list etc..In addition, memory 902 can be with
It can also include nonvolatile memory, for example, at least disk memory, a flash memory including high-speed random access memory
Device or other non-volatile solid state memory parts.In some embodiments, it includes relative to processing that memory 902 is optional
The remotely located memory 902 of device 901, these remote memories 902 can pass through network connection to external equipment.Above-mentioned network
Example include but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more module is stored in memory 902, when being executed by one or more processor 901, is held
The recommended method of trade company in the above-mentioned any means embodiment of row.
The said goods can be performed the application embodiment provided by method, have the corresponding functional module of execution method and
Beneficial effect, the not technical detail of detailed description in the present embodiment, reference can be made to method provided by the application embodiment.
8th embodiment of the invention is related to a kind of non-volatile memory medium, for storing computer-readable program,
Computer-readable program is used to execute the classification method embodiment of above-mentioned all or part of trade company for computer.
9th embodiment of the invention is related to a kind of non-volatile memory medium, for storing computer-readable program,
Computer-readable program is used to execute the recommended method embodiment of above-mentioned all or part of trade company for computer.
That is, it will be understood by those skilled in the art that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, which is stored in a storage medium, including some instructions are to make
It obtains an equipment (can be single-chip microcontroller, chip etc.) or processor (processor) executes each embodiment method of the application
All or part of the steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize specific embodiments of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
The application embodiment provides a kind of classification method of trade company of A1., comprising:
History Order data are obtained, the order data is clustered according to the user information of the order data；
Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Classified according to the characteristic of division to trade company to be sorted.
A2. the classification method of trade company according to a1, the order data Zhong Ge trade company according to after cluster
The degree of correlation determines characteristic of division, specifically:
Training sample is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Neural network model is obtained using training sample training, the input of the neural network model is at least two
Trade company exports as the similarity of at least two trade company；
The characteristic of division is determined according to the middle layer of the neural network model.
A3. the classification method of the trade company according to A2, the neural network model are monolayer neural networks model.
A4. the classification method of the trade company according to A2, the middle layer are preset with width, and the width is bigger, really
The feature quantity for the characteristic of division made is more.
A5. the middle layer of the classification method of the trade company according to A2, the monolayer neural networks utilizes following manner
It obtains:
The distance of the highest trade company of the degree of correlation is minimized, the distance of the minimum trade company of the degree of correlation is maximized, obtains in described
Interbed.
A6. the classification method of the trade company according to A1, the highest trade company of the degree of correlation are to be placed an order by same user
Trade company, the minimum trade company of the degree of correlation is the trade company to be placed an order by different user.
A7. the classification method of the trade company according to A1, the user information according to the order data is to described
Order data is clustered, comprising:
Summarize the order data that the same class user places an order respectively；
Classify to the order data summarized.
A8. the classification method of the trade company according to A7, the described pair of order data summarized are classified, are specifically included:
Of a sort order data affiliated in classification results is recorded as document files.
Embodiment further provides a kind of recommended methods of trade company of B9. by the application, comprising:
Obtain the History Order data of user；
Merchant Category to be recommended is determined according to the History Order data and Merchant Category information；
The subordinate trade company of identified Merchant Category is recommended into the user；
Wherein, classification method of the Merchant Category information from trade company described in any one of described A1 to A8.
B10. the recommended method of the trade company according to B9, it is described to be believed according to the History Order data and Merchant Category
Breath determines Merchant Category to be recommended, comprising:
The order in the History Order data is classified according to the Merchant Category information；
The Merchant Category to be recommended is determined according to classification results.
B11. the recommended method of the trade company according to B9, it is described to be believed according to the History Order data and Merchant Category
Breath determines Merchant Category to be recommended, comprising:
Trade company belonging to order in the History Order data is determined respectively；
The trade company determined is classified according to the Merchant Category information；
The Merchant Category to be recommended is determined according to classification results.
Embodiment further provides a kind of sorters of trade company of C12. by the application, comprising:
Module is obtained, for obtaining History Order data；
Cluster module, for being clustered according to the user information of the order data to the order data；
Determining module, for determining characteristic of division according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Categorization module, for being classified according to the characteristic of division to trade company to be sorted.
Embodiment further provides a kind of recommendation apparatus of trade company of D13. by the application, comprising:
Module is obtained, for obtaining the History Order data of user；
Classification determining module, for determining trade company to be recommended point according to the History Order data and Merchant Category information
Class；
Recommending module, for the subordinate trade company of identified Merchant Category to be recommended the user；
Wherein, sorter of the Merchant Category information from trade company described in described 12.
Embodiment further provides E14. a kind of electronic equipment by the application, comprising: memory and processor, memory storage
Computer program, processor execute when running program:
History Order data are obtained, the order data is clustered according to the user information of the order data；
Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Classified according to the characteristic of division to trade company to be sorted.
Embodiment further provides F15. a kind of electronic equipment by the application, comprising: memory and processor, memory storage
Computer program, processor execute when running program:
Obtain the History Order data of user；
Merchant Category to be recommended is determined according to the History Order data and Merchant Category information；
The subordinate trade company of identified Merchant Category is recommended into the user；
Wherein, classification method of the Merchant Category information from trade company described in any one of described A1 to A8.
Embodiment further provides a kind of non-volatile memory mediums of G16. by the application, for storing computer-readable journey
Sequence, the computer-readable program be used for for computer execute A1 into A8 it is any as described in trade company classification method.
Embodiment further provides a kind of non-volatile memory mediums of H17. by the application, for storing computer-readable journey
Sequence, the computer-readable program be used for for computer execute B9 into B11 it is any as described in trade company recommended method.
Claims (10)
1. a kind of classification method of trade company characterized by comprising
History Order data are obtained, the order data is clustered according to the user information of the order data；
Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Classified according to the characteristic of division to trade company to be sorted.
2. the classification method of trade company according to claim 1, which is characterized in that the order numbers according to after cluster
Characteristic of division is determined according to the degree of correlation of Zhong Ge trade company, specifically:
Training sample is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Neural network model is obtained using training sample training, the input of the neural network model is at least two quotient
Family exports as the similarity of at least two trade company；
The characteristic of division is determined according to the middle layer of the neural network model.
3. the classification method of trade company according to claim 2, which is characterized in that the neural network model is single layer mind
Through network model.
4. a kind of recommended method of trade company characterized by comprising
Obtain the History Order data of user；
Merchant Category to be recommended is determined according to the History Order data and Merchant Category information；
The subordinate trade company of identified Merchant Category is recommended into the user；
Wherein, classification method of the Merchant Category information from trade company described in described any one of claims 1 to 3.
5. a kind of sorter of trade company characterized by comprising
Module is obtained, for obtaining History Order data；
Cluster module, for being clustered according to the user information of the order data to the order data；
Determining module, for determining characteristic of division according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Categorization module, for being classified according to the characteristic of division to trade company to be sorted.
6. a kind of recommendation apparatus of trade company characterized by comprising
Module is obtained, for obtaining the History Order data of user；
Classification determining module, for determining Merchant Category to be recommended according to the History Order data and Merchant Category information；
Recommending module, for the subordinate trade company of identified Merchant Category to be recommended the user；
Wherein, sorter of the Merchant Category information from trade company described in the claim 5.
7. a kind of electronic equipment characterized by comprising memory and processor, memory store computer program, processor
It is executed when running program:
History Order data are obtained, the order data is clustered according to the user information of the order data；
Characteristic of division is determined according to the degree of correlation of the order data Zhong Ge trade company after cluster；
Classified according to the characteristic of division to trade company to be sorted.
8. a kind of electronic equipment characterized by comprising memory and processor, memory store computer program, processor
It is executed when running program:
Obtain the History Order data of user；
Merchant Category to be recommended is determined according to the History Order data and Merchant Category information；
The subordinate trade company of identified Merchant Category is recommended into the user；
Wherein, classification method of the Merchant Category information from trade company described in described any one of claims 1 to 3.
9. a kind of non-volatile memory medium, for storing computer-readable program, the computer-readable program is by for based on
Calculation machine executes the classification method such as trade company any one of claims 1 to 3.
10. a kind of non-volatile memory medium, for storing computer-readable program, the computer-readable program is by for based on
Calculation machine executes the recommended method of trade company as claimed in claim 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534645.8A CN109597858B (en) | 2018-12-14 | 2018-12-14 | Merchant classification method and device and merchant recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534645.8A CN109597858B (en) | 2018-12-14 | 2018-12-14 | Merchant classification method and device and merchant recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109597858A true CN109597858A (en) | 2019-04-09 |
| CN109597858B CN109597858B (en) | 2021-09-14 |
Family
ID=65960812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811534645.8A Active CN109597858B (en) | 2018-12-14 | 2018-12-14 | Merchant classification method and device and merchant recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109597858B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210905A (en) * | 2019-05-31 | 2019-09-06 | 拉扎斯网络科技（上海）有限公司 | Characteristic similarity calculation method, device, electronic equipment and computer storage medium |
| CN111242165A (en) * | 2019-12-30 | 2020-06-05 | 北京顺达同行科技有限公司 | Merchant clustering method and device, computer equipment and storage medium |
| CN111475691A (en) * | 2020-03-06 | 2020-07-31 | 拉扎斯网络科技（上海）有限公司 | Method and device for acquiring recommended object data and electronic equipment |
| CN111526037A (en) * | 2020-03-23 | 2020-08-11 | 北京三快在线科技有限公司 | Configuration method and device of network node, electronic equipment and readable storage medium |
| CN111667012A (en) * | 2020-06-10 | 2020-09-15 | 创新奇智(广州)科技有限公司 | Classification result correction method and device, correction equipment and readable storage medium |
| CN114417964A (en) * | 2021-12-10 | 2022-04-29 | 中国卫通集团股份有限公司 | Satellite operator classification method and device and electronic equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005012665A1 (en) * | 2005-03-18 | 2006-09-21 | Siemens Ag | Method for determining order of data arranged in computer from cluster involves partial correlation of order, they comprises components such as services and products, which occurs partially at several times |
| CN101404078A (en) * | 2008-09-16 | 2009-04-08 | 鲁东大学 | Cooperated electronic market based on market union |
| CN101996215A (en) * | 2009-08-27 | 2011-03-30 | 阿里巴巴集团控股有限公司 | Information matching method and system applied to e-commerce website |
| CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
| CN102760335A (en) * | 2012-07-18 | 2012-10-31 | 朱磊 | Intelligent wireless mobile cash register system and implementation method thereof |
| CN102930449A (en) * | 2012-11-12 | 2013-02-13 | 侯爵 | Online trade platform and method |
| CN103065258A (en) * | 2012-12-25 | 2013-04-24 | 苏州博康生物医疗科技有限公司 | Method for achieving intelligent service platform |
| CN103489108A (en) * | 2013-08-22 | 2014-01-01 | 浙江工商大学 | Large-scale order form matching method in community commerce cloud |
| CN105205689A (en) * | 2015-08-26 | 2015-12-30 | 深圳市万音达科技有限公司 | Method and system for recommending commercial tenant |
| WO2016091173A1 (en) * | 2014-12-09 | 2016-06-16 | 北京嘀嘀无限科技发展有限公司 | User maintenance system and method |
| CN106408326A (en) * | 2016-08-30 | 2017-02-15 | 常州航加网络科技有限公司 | Intelligent information management platform and management method thereof |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN108182621A (en) * | 2017-12-07 | 2018-06-19 | 合肥美的智能科技有限公司 | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium |
-
2018
- 2018-12-14 CN CN201811534645.8A patent/CN109597858B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005012665A1 (en) * | 2005-03-18 | 2006-09-21 | Siemens Ag | Method for determining order of data arranged in computer from cluster involves partial correlation of order, they comprises components such as services and products, which occurs partially at several times |
| CN101404078A (en) * | 2008-09-16 | 2009-04-08 | 鲁东大学 | Cooperated electronic market based on market union |
| CN101996215A (en) * | 2009-08-27 | 2011-03-30 | 阿里巴巴集团控股有限公司 | Information matching method and system applied to e-commerce website |
| CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
| CN102760335A (en) * | 2012-07-18 | 2012-10-31 | 朱磊 | Intelligent wireless mobile cash register system and implementation method thereof |
| CN102930449A (en) * | 2012-11-12 | 2013-02-13 | 侯爵 | Online trade platform and method |
| CN103065258A (en) * | 2012-12-25 | 2013-04-24 | 苏州博康生物医疗科技有限公司 | Method for achieving intelligent service platform |
| CN103489108A (en) * | 2013-08-22 | 2014-01-01 | 浙江工商大学 | Large-scale order form matching method in community commerce cloud |
| WO2016091173A1 (en) * | 2014-12-09 | 2016-06-16 | 北京嘀嘀无限科技发展有限公司 | User maintenance system and method |
| CN105205689A (en) * | 2015-08-26 | 2015-12-30 | 深圳市万音达科技有限公司 | Method and system for recommending commercial tenant |
| CN106408326A (en) * | 2016-08-30 | 2017-02-15 | 常州航加网络科技有限公司 | Intelligent information management platform and management method thereof |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN108182621A (en) * | 2017-12-07 | 2018-06-19 | 合肥美的智能科技有限公司 | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张志宏: "电子商务模式下的顾客行为特征提取及利润挖掘", 《中国博士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210905A (en) * | 2019-05-31 | 2019-09-06 | 拉扎斯网络科技（上海）有限公司 | Characteristic similarity calculation method, device, electronic equipment and computer storage medium |
| CN111242165A (en) * | 2019-12-30 | 2020-06-05 | 北京顺达同行科技有限公司 | Merchant clustering method and device, computer equipment and storage medium |
| CN111242165B (en) * | 2019-12-30 | 2020-10-23 | 北京顺达同行科技有限公司 | Merchant clustering method and device, computer equipment and storage medium |
| CN111475691A (en) * | 2020-03-06 | 2020-07-31 | 拉扎斯网络科技（上海）有限公司 | Method and device for acquiring recommended object data and electronic equipment |
| CN111526037A (en) * | 2020-03-23 | 2020-08-11 | 北京三快在线科技有限公司 | Configuration method and device of network node, electronic equipment and readable storage medium |
| CN111667012A (en) * | 2020-06-10 | 2020-09-15 | 创新奇智(广州)科技有限公司 | Classification result correction method and device, correction equipment and readable storage medium |
| CN114417964A (en) * | 2021-12-10 | 2022-04-29 | 中国卫通集团股份有限公司 | Satellite operator classification method and device and electronic equipment |
| CN114417964B (en) * | 2021-12-10 | 2023-09-12 | 中国卫通集团股份有限公司 | Satellite operator classification method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109597858B (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597858A (en) | A kind of classification method of trade company and its recommended method and its device of device and trade company | |
| CN106228386B (en) | A kind of information-pushing method and device | |
| CN110070067A (en) | The training method of video classification methods and its model, device and electronic equipment | |
| CN109871886A (en) | Abnormal point ratio optimization method, apparatus and computer equipment based on spectral clustering | |
| CN108388924A (en) | A kind of data classification method, device, equipment and computer readable storage medium | |
| CN107330750B (en) | A kind of recommended products figure method and device, electronic equipment | |
| CN104424339B (en) | The method, apparatus and system of data analysis | |
| CN107742107A (en) | Facial image sorting technique, device and server | |
| CN110221965A (en) | Test cases technology, test method, device, equipment and system | |
| CN106355449A (en) | User selecting method and device | |
| CN108665366A (en) | Determine method, terminal device and the computer readable storage medium of consumer's risk grade | |
| CN108108743A (en) | Abnormal user recognition methods and the device for identifying abnormal user | |
| CN106022568A (en) | Workflow processing method and apparatus | |
| CN109785066A (en) | Products Show method, apparatus, equipment and storage medium based on micro- expression | |
| CN105719045A (en) | Retention risk determiner | |
| CN106326913A (en) | Money laundering account determination method and device | |
| CN109636497A (en) | A kind of Products Show method and apparatus | |
| CN108846695A (en) | The prediction technique and device of terminal replacement cycle | |
| CN106874355A (en) | The collaborative filtering method of social networks and user's similarity is incorporated simultaneously | |
| CN109766470A (en) | Image search method, device and processing equipment | |
| CN109165377A (en) | Generate the method and tabulating equipment of form data | |
| CN108765146A (en) | The method and apparatus that a kind of basis has tracing pattern selection specific curves stock | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN106874943A (en) | Business object sorting technique and system | |
| Cañete-Sifuentes et al. | Classification based on multivariate contrast patterns |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |