CN109961309A - Business recommended method and system - Google Patents
Business recommended method and system Download PDFInfo
- Publication number
- CN109961309A CN109961309A CN201711426356.1A CN201711426356A CN109961309A CN 109961309 A CN109961309 A CN 109961309A CN 201711426356 A CN201711426356 A CN 201711426356A CN 109961309 A CN109961309 A CN 109961309A
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- service
- business
- personal information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of business recommended method and systems, are related to business recommended technical field, comprising: obtain the personal information of each user in user group；According to type of service, the key condition of business is determined；Judge whether the personal information of each user in user group meets key condition one by one；If it is, determining that the user for meeting key condition is service-user to be recommended；According to the personal information of service-user to be recommended, characteristic value is obtained；According to characteristic value, judge whether to recommend business to service-user to be recommended.Type of service can be passed through, determine the key condition of the business, then a rough screening is carried out to the customer information under big data by key condition, using the user screened as user to be recommended, follow up characteristic value again, treats recommended user and is accurately screened, and recommends business to the people by accurately screening, be able to carry out targetedly it is business recommended, so as to promote the likability of client.
Description
Technical field
The present invention relates to business recommended technical fields, more particularly, to a kind of business recommended method and system.
Background technique
As Internet technology constantly develops, more and more data are converged in internet, these data are a bit
It is implicit, unknown, potential in advance comprising useful information, these data can be used for indicating concept, rule, rule, mode etc.
Deng.It is therefore desirable to can be used to carry out business by analysis tool from the relationship found in mass data between data slot
And the prediction of industry development.
In the related technology, when recommending business to user, often occurring will be different types of business recommended to depositing in database
The same a collection of user group of storage, this may result in some people for having bought related service and receives information, or be not suitable for purchasing
The people for buying related service receives recommendation message, does so the complaint that can not only cause client, and the likability of company is caused to decline,
The resource of company is wasted simultaneously.
Summary of the invention
In view of this, the purpose of the present invention is to provide business recommended method and system, it can be by type of service, really
Then the key condition of the fixed business carries out a rough screening to the customer information under big data by key condition, will sieve
The user elected is as user to be recommended, then the characteristic value that follows up, and treats recommended user and is accurately screened, to by accurate
The people of screening recommends business, be able to carry out it is targetedly business recommended, so as to promote the likability of client.
In a first aspect, the embodiment of the invention provides a kind of business recommended methods, comprising: obtain each of user group
The personal information of user；According to type of service, the key condition of business is determined；Judge each user's in user group one by one
Whether personal information meets the key condition；If it is, determining that the user for meeting the key condition is business to be recommended
User；According to the personal information of service-user to be recommended, characteristic value is obtained；According to the characteristic value, judge whether to it is described to
Service-user is recommended to recommend business.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein
The personal information according to service-user to be recommended obtains characteristic value, comprising: is believed according to the individual of service-user to be recommended
Breath obtains relationship characteristic value；According to the personal information of service-user to be recommended, cluster feature value is obtained；It is special to the relationship
Value and cluster feature value are weighted processing, obtain characteristic value.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein
The personal information according to service-user to be recommended, obtain relationship characteristic value, comprising: from the user group extract with to
Recommend the trade user of service-user transaction；Obtain the Transaction Information of the service-user to be recommended and the trade user, institute
Stating Transaction Information includes transaction count and transaction amount；Judge in the corresponding Transaction Information of the trade user, if there are institutes
State that transaction count meets preset times and the transaction amount meets preset cost；If it is, extract the transaction count and
The corresponding trade user of the maximum value of the transaction amount；Determine the grade of the corresponding trade user of maximum value；According to etc.
Grade determines that the relationship characteristic value of service-user to be recommended is setting value.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein
The personal information according to service-user to be recommended obtains cluster feature value, comprising: contact is extracted from the user group
User；Obtain the personal information of the contact user；Personal information and the contact user to the service-user to be recommended
Personal information carry out clustering；According to cluster analysis result, cluster feature value is obtained.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein
It is described according to the characteristic value, judge whether to recommend business to the service-user to be recommended, comprising: judge the characteristic value
Whether default characteristic value is greater than；If it is, recommending business to the service-user to be recommended.
Second aspect, the embodiment of the present invention also provide a kind of business recommended system, comprising: obtain module, use for obtaining
The personal information of each user in the group of family；Condition module is determined, for determining the key condition of business according to type of service；
Judgment module, for judging whether the personal information of each user in user group meets the key condition one by one；It determines and uses
Family module, for if it is, determining that the user for meeting the key condition is service-user to be recommended；Characteristic module is obtained,
For the personal information according to service-user to be recommended, characteristic value is obtained；Recommend business module, for according to the feature
Value judges whether to recommend business to the service-user to be recommended.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein
The acquisition characteristic module, comprising: relationship characteristic value submodule is obtained, for the personal information according to service-user to be recommended,
Obtain relationship characteristic value；Cluster feature value submodule is obtained, according to the personal information of service-user to be recommended, it is special to obtain cluster
Value indicative；Submodule is weighted, for being weighted processing to the relationship especially value and cluster feature value, obtains characteristic value.
In conjunction with second aspect, the embodiment of the invention provides second of possible embodiments of second aspect, wherein
The acquisition relationship characteristic value submodule, is used for: extracting from the user group and uses with the transaction of service-user to be recommended transaction
Family；Obtain the Transaction Information of the service-user to be recommended and the trade user, the Transaction Information include transaction count and
Transaction amount；Judge in the corresponding Transaction Information of the trade user, if there are the transaction counts to meet preset times
And the transaction amount meets preset cost；If it is, extracting the maximum value pair of the transaction count and the transaction amount
The trade user answered；Determine the grade of the corresponding trade user of maximum value；According to grade, service-user to be recommended is determined
Relationship characteristic value be setting value.
In conjunction with second aspect, the embodiment of the invention provides the third possible embodiments of second aspect, wherein
The acquisition cluster feature value submodule, is used for: contact user is extracted from the user group；Obtain the contact user's
Personal information；The personal information of personal information and the contact user to the service-user to be recommended carries out clustering；
According to cluster analysis result, cluster feature value is obtained.
In conjunction with second aspect, the embodiment of the invention provides the 4th kind of possible embodiments of second aspect, wherein
The recommendation business module, is used for: judging whether the characteristic value is greater than default characteristic value；If it is, to described to be recommended
Service-user recommends business.
The embodiment of the present invention brings following the utility model has the advantages that can determine the crucial item of the business by type of service
Then part carries out a rough screening to the customer information under big data by key condition, using the user screened as
User to be recommended, then the characteristic value that follows up, treat recommended user and are accurately screened, and recommend business to the people by accurately screening,
Be able to carry out targetedly it is business recommended, so as to promote the likability of client.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claim
Specifically noted structure is achieved and obtained in book and attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and match
Appended attached drawing is closed, is described in detail below.
Detailed description of the invention
It, below will be to tool in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Body embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing be some embodiments of the present invention, for those of ordinary skill in the art, what is do not made the creative labor
Under the premise of, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow chart of business recommended method provided by one embodiment of the present invention；
Fig. 2 is the flow chart for the business recommended method that another embodiment of the present invention provides；
Fig. 3 is the flow chart for the business recommended method that further embodiment of the present invention provides；
Fig. 4 is the structure chart of business recommended system provided by one embodiment of the present invention.
Icon:
The business recommended system of 200-；210- obtains module；220- determines condition module；230- judgment module；240- is determined
Line module；250- obtains characteristic module；260- recommends business module.
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
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
When to lead referral business, first to customer portrait, customer portrait is exactly that client is divided into group one by one,
Inside each group, the feature of client is closely similar；And between different groups, the feature of client has larger difference.Pass through
Different groups are distinguished, each group can effectively be managed and take corresponding business development.However, usually
By it is different types of it is business recommended it is same recommend the user group stored in database, this may result in some bought
The people of related service receives information, or be not suitable for buy related service people receive recommendation message, doing so can not only draw
The complaint for playing client, causes the likability of company to decline, while wasting the resource of company.Based on this, the embodiment of the present invention
A kind of business recommended method and system provided, can be determined the key condition of the business, then be passed through by type of service
Key condition carries out a rough screening to the customer information under big data, using the user screened as use to be recommended
Family, then the characteristic value that follows up, treat recommended user and are accurately screened, and recommend business to by the people accurately screened, are able to carry out
It is targetedly business recommended, so as to promote the likability of client.
For convenient for understanding the present embodiment, first to a kind of business recommended method disclosed in the embodiment of the present invention
It describes in detail, it is shown in Figure 1, comprising:
S110: the personal information of each user in user group is obtained.
For example, by taking bank as an example, bank want to the user of oneself recommend a finance product, then, just first from
The request for obtaining the personal information of user is sent in database in bank, can obtain of each user in user group
People's information.Personal information includes at least field: name, age, identification card number, address, mobile phone, income, marital status, business
Buy the information such as time, the amount of money, type of business.Particularly, in financial recommendation business, data, which generally require, does secrecy processing.
Such as: to initial data progress data desensitization process, formation desensitization data, the data that will desensitize are put down with the acquisition initial data
Platform establishes mapping, to find former data by the desensitization data.Obtain each user in user group had been guarantor
The personal information of close processing.Desensitize data format such as: name: Lee *, identification card number: 1101011982********, the age:
35, address: Dongcheng District, Beijing during March * * *, mobile phone: 13901234***, income: 20000 yuan/month, marital status: married, related
Business buys the time: in November, 2017, the amount of money: 100,000 yuan (RMB).
S120: according to type of service, the key condition of business is determined.
Specifically, front desk service type is preset, front desk service type is standardized.Type of service citing: fund
Financing, purchase private insurance, health protection class product, determine the type of recommendation business first in the step s 120, for example, fund is managed
Then wealth determines the key condition of fund financing.Wherein, key condition, which refers to, determines that user is likely to purchase according to type of service
Or the condition of the business is subscribed to, such as, if it is determined that type of service is fund financing, then key condition can be set to the moon
Income is greater than 10000, or can be set to address within wide deep Fourth Ring of going up north；If it is determined that type of service is health protection class
Product, then key condition can be set to the age at 40 years old or more；If it is determined that type of service is private insurance, then crucial item
Part can be set to the crowd that occupation is hazardous occupation.
S130: judge whether the personal information of each user in user group meets key condition one by one.
Citing, to recommend Fund-based Financial Service, key condition is that monthly income is greater than for 10000, and the individual of user is believed
Monthly income in breath is compared with the key condition.
S140: if it is, determining that the user for meeting key condition is service-user to be recommended.
For example, if the user in the user group got meets the condition in step S130, assert the satisfaction
The user of condition is service-user to be recommended.That is, screened in big data by key condition first, filter out with to
The user that the business of recommendation is not obviously inconsistent.
S150: according to the personal information of service-user to be recommended, characteristic value is obtained.
In some embodiments, step S150, comprising: according to the personal information of service-user to be recommended, it is special to obtain relationship
Value indicative；According to the personal information of service-user to be recommended, cluster feature value is obtained；The relationship is especially worth and cluster feature
Value is weighted processing, obtains characteristic value.
Wherein, relationship characteristic value refers to a numerical value of the Transaction Information of service-user to be recommended.Cluster feature value refers to
Service-user to be recommended carries out obtaining a numerical value when clustering.
As shown in connection with fig. 2, according to the personal information of service-user to be recommended, relationship characteristic value is obtained, comprising:
S151: the trade user with service-user to be recommended transaction is extracted from user group.
Wherein, trade user refers to the user for having transaction with user to be recommended, this transaction can be and use to be recommended
There was the user of money transfer records at family, had the transaction of other money with user to be recommended, such as transferred accounts with wechat.
Specifically, whether confirmation and service-user to be recommended had transaction from transaction record, if having transaction,
Then think that the user is trade user, and finds all users for having transaction with service-user to be recommended in user group.
S152: obtaining the Transaction Information of service-user and trade user to be recommended, and Transaction Information includes transaction count and friendship
The easy amount of money.
Specifically, after determining trade user, it will acquire and believe with the transaction of service-user to be recommended and trade user
Breath had the trade user of transaction record to be distributed as Wei for example, user to be recommended is Zhang by taking bank transfer as an example with Zhang
Certain and Liu, Wei are added to obtain a transaction total degree with the number of the All Activity of Zhang, by the institute of Wei and Zhang
There is the amount of money of transaction to be added to obtain a transaction total amount, Transaction Information as transaction total degree and the transaction of Zhang and Wei
Total amount.
S153: judge in the corresponding Transaction Information of trade user, if there are transaction counts to meet preset times and transaction
The amount of money meets preset cost.
Citing: when preset times be 20 times, the preset cost that transaction amount set be 400,000, then judge these trade use
Whether there are transaction count and transaction amount to meet 20 times and 400,000 in family.
S154: if it is, the corresponding transaction of the maximum value for extracting the transaction count and the transaction amount is used
Family.
Specifically, it if so, then extracting these people for meeting transaction count and transaction amount, such as trades
User Zhang transaction count and transaction amount are 30 and 500,000, and Lee's transaction count and transaction amount are 10 and 400,000, and transaction is used
Family model transaction count and transaction amount are 40 and 1,000,000, then meeting condition is Zhang and Fan.Extraction model is maximum value
Corresponding trade user.
S155: the grade of the corresponding trade user of maximum value is determined.
For example, hierarchy rules are as follows: it according to actual production is every 20 just in case grade, every 20 next grade, such as
Transfer accounts 1,000,000 be 50 point 800,000 is 40 points.20 times and 200,000 be the first estate, 40 times and 400,000 be the second grade, 60 times and 60
Ten thousand be the tertiary gradient, and 80 times and 800,000 are the fourth estate, and so on.
For example, trade user model transaction count and transaction amount are 40 and 1,000,000, then according to hierarchy rules, model
Certain is the second grade.
S156: according to grade, determine that the relationship characteristic value of service-user to be recommended is setting value.
Citing, then the second grade of model is 50 points.
As shown in connection with fig. 3, according to the personal information of service-user to be recommended, cluster feature value is obtained, comprising:
S1511: contact user is extracted from user group.
Wherein, contact user refers to the business once crossed and bought this type of service, for example, if pushing away to specific client
A finance product is recommended, then bought the artificial contact user of finance product.
S1512: the personal information of contact user is obtained.
Specifically, the personal information of user is obtained from database.
S1513: the personal information of personal information and contact user to service-user to be recommended carries out clustering.
Specifically: firstly, the personal information using user group is trained, making a classifier, both carry out simplicity
Bayesian algorithm training, is mapped by data, is trained using desensitization data to NB Algorithm, by machine in algorithm
Device learning functionality modifies NB Algorithm feature according to calculated result, finds " inflection point ", completes algorithm training.
Such as: by the name in business model, identification card number, age, address, mobile phone, income, marital status, related industry
Business is bought the fields such as time, the amount of money and is substituted into NB Algorithm model, and formula is used
Change expression formula into Be converted to example: Pass through simple shellfish
This formula of leaf converts three formula preferably asked, and finds " inflection point ", to can obtain the feature of business by the classifier.
Then feature clustering is carried out to service-user to be recommended using the algorithm after training, then to having bought this
The contact user of type of service carries out carrying out data clusters by the NB Algorithm after training.
S1514: according to cluster analysis result, cluster feature value is obtained.
Specifically, more according to the number of similar features if similar features can be found according to cluster analysis result
It is few, then, will determine that cluster feature value is different preset value, by the number of similar features number from different preset value phases
It is corresponding, for example, 4 same characteristic features, 100 points；3 same characteristic features, 90 points；Etc., for example: second is not buy fund reason
The fields such as time, the amount of money are bought according to identification card number, age, address, mobile phone, income, marital status, related service in finance family
It is after clustering the result is that: 36 years old, married, Beijing, take in 20000 yuan/month；First is purchase fund financing user, simple shellfish
This algorithm of leaf obtains being characterized in: 35 years old, married, Beijing, takes in 18000 yuan/month；First and second are both greater than 30 years old, married,
One line urban life, and take in and be greater than 10000, so assert that second is the phase for the people that can be found with buy finance product
Like feature, then 100 scores are made to second.The marking situation of step S154, obtains 0.6*100+0.4*50=80, and the total score of second is
80 points.Certainly, if second by cluster obtain the result is that: 34 years old, unmarried, Beijing, take in 20000 yuan/month, then with first it
Between have 3 similar features, then the score of second can be 90 points.
S160: according to characteristic value, judge whether to recommend business to service-user to be recommended.
Step S160 is specifically, comprising: whether judging characteristic value is greater than default characteristic value；If it is, to it is described to
Service-user is recommended to recommend business.
Such as: default characteristic value is set as 75 points, second is greater than 75 points, meets recommendation and requires.
As shown in connection with fig. 4, business recommended system 200, comprising: obtain module 210, determine condition module 220, judge mould
Block 230 determines line module 240, obtains characteristic module 250, recommends business module 260.
Wherein, the personal information that module 210 is used to obtain each user in user group is obtained.Determine condition module 220
For determining the key condition of business according to type of service.Judgment module 230 is used to judge each use in user group one by one
Whether the personal information at family meets key condition.Line module is determined, for if it is, determining the use for meeting key condition
Family is service-user to be recommended.Characteristic module 240 is obtained for the personal information according to service-user to be recommended, obtains feature
Value.Business module 250 is recommended to be used to judge whether to recommend business to service-user to be recommended according to characteristic value.
In some embodiments, obtain characteristic module 250, comprising: obtain relationship characteristic value submodule, for according to
Recommend the personal information of service-user, obtains relationship characteristic value；Cluster feature value submodule is obtained, is used according to business to be recommended
The personal information at family obtains cluster feature value；Submodule is weighted, is used to especially be worth the relationship and cluster feature value carries out
Weighting processing, obtains characteristic value.
In some embodiments, relationship characteristic value submodule is obtained, is used for: being extracted and business to be recommended from user group
The trade user of customer transaction；The Transaction Information of service-user and trade user to be recommended is obtained, Transaction Information includes transaction time
Several and transaction amount；Judge to meet preset times with the presence or absence of transaction count in trade user and transaction amount meets default gold
Volume；If it is, the corresponding trade user of the maximum value for extracting the transaction count and the transaction amount；It determines most
It is worth the grade of corresponding trade user greatly；According to grade, determine that the relationship characteristic value of service-user to be recommended is setting value.
In some embodiments, cluster feature value submodule is obtained, is used for: extracting contact user from the user group；
Obtain the personal information of the contact user；Of personal information and the contact user to the service-user to be recommended
People's information carries out clustering；According to cluster analysis result, cluster feature value is obtained.
In some embodiments, recommend business module 260, be used for: whether judging characteristic value is greater than default characteristic value；Such as
Fruit is then to recommend business to the service-user to be recommended.
The technical effect and preceding method embodiment of system provided by the embodiment of the present invention, realization principle and generation
Identical, to briefly describe, system embodiment part does not refer to place, can refer to corresponding contents in preceding method embodiment.
Unless specifically stated otherwise, the opposite step of the component and step that otherwise illustrate in these embodiments, digital table
It is not limit the scope of the invention up to formula and numerical value.
In all examples being illustrated and described herein, any occurrence should be construed as merely illustratively, without
It is as limitation, therefore, other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain item exists
It is defined in one attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
The flow chart and block diagram in the drawings show system, method and the computers of multiple embodiments according to the present invention
The architecture, function and operation in the cards of program product.In this regard, each box in flowchart or block diagram can
To represent a part of a module, section or code, a part of the module, section or code include one or
Multiple executable instructions for implementing the specified logical function.It should also be noted that in some implementations as replacements, side
The function of being marked in frame can also occur in a different order than that indicated in the drawings.For example, two continuous boxes are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.?
It should be noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, it can
To be realized with the dedicated hardware based system for executing defined function or movement, or specialized hardware and meter can be used
The combination of calculation machine instruction is realized.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；
It can be mechanical connection, be also possible to be electrically connected；It can be directly connected, can also indirectly connected through an intermediary, it can be with
It is the connection inside two elements.For the ordinary skill in the art, it can understand that above-mentioned term exists with concrete condition
Concrete meaning in the present invention.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, be only for
Convenient for the description present invention and simplify description, rather than the device or element of indication or suggestion meaning there must be specific side
Position is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " the
Two ", " third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate this hair
Bright technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although right with reference to the foregoing embodiments
The present invention is described in detail, those skilled in the art should understand that: any technology for being familiar with the art
Personnel in the technical scope disclosed by the present invention, can still modify to technical solution documented by previous embodiment
Or variation or equivalent replacement of some of the technical features can be readily occurred in；And these modifications, variation or replacement,
The spirit and scope for technical solution of the embodiment of the present invention that it does not separate the essence of the corresponding technical solution, should all cover in this hair
Within bright protection scope.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of business recommended method characterized by comprising
Obtain the personal information of each user in user group；
According to type of service, the key condition of business is determined；
Judge whether the personal information of each user in user group meets the key condition one by one；
If it is, determining that the user for meeting the key condition is service-user to be recommended；
According to the personal information of service-user to be recommended, characteristic value is obtained；
According to the characteristic value, judge whether to recommend business to the service-user to be recommended.
2. business recommended method according to claim 1, which is characterized in that the individual according to service-user to be recommended
Information obtains characteristic value, comprising:
According to the personal information of service-user to be recommended, relationship characteristic value is obtained；
According to the personal information of service-user to be recommended, cluster feature value is obtained；
Processing is weighted to the relationship especially value and cluster feature value, obtains characteristic value.
3. business recommended method according to claim 2, which is characterized in that the individual according to service-user to be recommended
Information obtains relationship characteristic value, comprising:
The trade user with service-user to be recommended transaction is extracted from the user group；
Obtain the Transaction Information of the service-user to be recommended and the trade user, the Transaction Information include transaction count and
Transaction amount；
Judge in the corresponding Transaction Information of the trade user, if there are the transaction counts to meet preset times and the friendship
The easy amount of money meets preset cost；
If it is, the corresponding trade user of the maximum value for extracting the transaction count and the transaction amount；
Determine the grade of the corresponding trade user of the maximum value；
According to the grade, determine that the relationship characteristic value of service-user to be recommended is setting value.
4. business recommended method according to claim 3, which is characterized in that the individual according to service-user to be recommended
Information obtains cluster feature value, comprising:
Contact user is extracted from the user group；
Obtain the personal information of the contact user；
The personal information of personal information and the contact user to the service-user to be recommended carries out clustering；
According to cluster analysis result, cluster feature value is obtained.
5. business recommended method according to claim 1, which is characterized in that it is described according to the characteristic value, judge whether
Business is recommended to the service-user to be recommended, comprising:
Judge whether the characteristic value is greater than default characteristic value；
If it is, recommending business to the service-user to be recommended.
6. a kind of business recommended system characterized by comprising
Module is obtained, for obtaining the personal information of each user in user group；
Condition module is determined, for determining the key condition of business according to type of service；
Judgment module, for judging whether the personal information of each user in user group meets the key condition one by one；
Line module is determined, for if it is, determining that the user for meeting the key condition is service-user to be recommended；
Characteristic module is obtained, for the personal information according to service-user to be recommended, obtains characteristic value；
Recommend business module, business is recommended to the service-user to be recommended for judging whether according to the characteristic value.
7. business recommended system according to claim 6, which is characterized in that the acquisition characteristic module, comprising:
Relationship characteristic value submodule is obtained, for the personal information according to service-user to be recommended, obtains relationship characteristic value；
Cluster feature value submodule is obtained, according to the personal information of service-user to be recommended, obtains cluster feature value；
Submodule is weighted, for being weighted processing to the relationship especially value and cluster feature value, obtains characteristic value.
8. business recommended system according to claim 7, which is characterized in that the acquisition relationship characteristic value submodule is used
In: the trade user traded with service-user to be recommended is extracted from the user group；Obtain the service-user to be recommended with
The Transaction Information of the trade user, the Transaction Information include transaction count and transaction amount；Judge the trade user pair
In the Transaction Information answered, if meet preset times there are the transaction count and the transaction amount meets preset cost；Such as
Fruit is the corresponding trade user of maximum value for then extracting the transaction count and the transaction amount；Determine maximum value pair
The grade for the trade user answered；According to grade, determine that the relationship characteristic value of service-user to be recommended is setting value.
9. business recommended system according to claim 8, which is characterized in that the acquisition cluster feature value submodule is used
In: contact user is extracted from the user group；Obtain the personal information of the contact user；To the service-user to be recommended
Personal information and it is described contact user personal information carry out clustering；According to cluster analysis result, cluster feature is obtained
Value.
10. business recommended system according to claim 6, which is characterized in that the recommendation business module is used for: judgement
Whether the characteristic value is greater than default characteristic value；If it is, recommending business to the service-user to be recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711426356.1A CN109961309B (en) | 2017-12-25 | 2017-12-25 | Service recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711426356.1A CN109961309B (en) | 2017-12-25 | 2017-12-25 | Service recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961309A true CN109961309A (en) | 2019-07-02 |
| CN109961309B CN109961309B (en) | 2021-09-28 |
Family
ID=67021560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711426356.1A Active CN109961309B (en) | 2017-12-25 | 2017-12-25 | Service recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961309B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598110A (en) * | 2019-09-16 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Service pushing method and device |
| CN111127077A (en) * | 2019-11-29 | 2020-05-08 | 中国建设银行股份有限公司 | Recommendation method and device based on stream computing |
| CN111144990A (en) * | 2019-12-27 | 2020-05-12 | 支付宝(杭州)信息技术有限公司 | Recommendation method and system |
| CN113538036A (en) * | 2021-06-04 | 2021-10-22 | 深圳市英创艾伦智能科技有限公司 | 5G, AI edge calculation and Internet of things digital management system, method and device |
| CN114169976A (en) * | 2021-12-27 | 2022-03-11 | 中国建设银行股份有限公司 | Financial data recommendation method, device and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577988A (en) * | 2012-07-24 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and device for recognizing specific user |
| CN104239335A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Method and device for acquiring information of specific users |
| CN104239338A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and information recommendation device |
| US20150081520A1 (en) * | 2013-09-16 | 2015-03-19 | International Business Machines Corporation | Analytics-driven product recommendation for financial services |
| CN105931066A (en) * | 2015-09-24 | 2016-09-07 | 中国银联股份有限公司 | Transaction data processing method and device |
-
2017
- 2017-12-25 CN CN201711426356.1A patent/CN109961309B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577988A (en) * | 2012-07-24 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and device for recognizing specific user |
| CN104239335A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Method and device for acquiring information of specific users |
| CN104239338A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and information recommendation device |
| US20150081520A1 (en) * | 2013-09-16 | 2015-03-19 | International Business Machines Corporation | Analytics-driven product recommendation for financial services |
| CN105931066A (en) * | 2015-09-24 | 2016-09-07 | 中国银联股份有限公司 | Transaction data processing method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598110A (en) * | 2019-09-16 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Service pushing method and device |
| CN110598110B (en) * | 2019-09-16 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Service pushing method and device |
| CN111127077A (en) * | 2019-11-29 | 2020-05-08 | 中国建设银行股份有限公司 | Recommendation method and device based on stream computing |
| CN111144990A (en) * | 2019-12-27 | 2020-05-12 | 支付宝(杭州)信息技术有限公司 | Recommendation method and system |
| CN111144990B (en) * | 2019-12-27 | 2022-08-05 | 蚂蚁胜信(上海)信息技术有限公司 | Recommendation method and system |
| CN113538036A (en) * | 2021-06-04 | 2021-10-22 | 深圳市英创艾伦智能科技有限公司 | 5G, AI edge calculation and Internet of things digital management system, method and device |
| CN114169976A (en) * | 2021-12-27 | 2022-03-11 | 中国建设银行股份有限公司 | Financial data recommendation method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961309B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961309A (en) | Business recommended method and system | |
| CN107146089B (en) | Method and device for identifying bill swiping and electronic equipment | |
| EP3371716B1 (en) | System and method for detecting interaction and influence in networks | |
| JP6501855B1 (en) | Extraction apparatus, extraction method, extraction program and model | |
| WO2018001195A1 (en) | Method and device for controlling data risk | |
| CN109102371A (en) | Method of Commodity Recommendation, device, computer equipment and storage medium | |
| CN106803168A (en) | A kind of abnormal transfer accounts method for detecting and device | |
| CN110246007A (en) | A kind of Method of Commodity Recommendation and device | |
| CN108108861A (en) | The Forecasting Methodology and device of a kind of potential customers | |
| CN109146474A (en) | A kind of payment limit method for customizing and device | |
| CN105490823A (en) | Data processing method and device | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN106294676B (en) | A kind of data retrieval method of ecommerce government system | |
| Asali | Social media analysis for investigating consumer sentiment on mobile banking | |
| JP2019185595A (en) | Information processor, method for processing information, information processing program, determination device, method for determination, and determination program | |
| CN110427565A (en) | A kind of item recommendation method based on collaborative filtering, intelligent terminal and storage medium | |
| JP2021018466A (en) | Rule extracting apparatus, information processing apparatus, rule extracting method, and rule extracting program | |
| CN110209944A (en) | A kind of stock analysis teacher recommended method, device, computer equipment and storage medium | |
| CN104751234B (en) | A kind of prediction technique and device of user's assets | |
| Shukla et al. | Is price a significant predictor of the churn behavior during the global pandemic? A predictive modeling on the telecom industry | |
| JP2023162397A (en) | Business support device | |
| JP7173507B2 (en) | Sales support device, sales support method and program | |
| CN110458420A (en) | A kind of score value appraisal procedure, device and storage medium | |
| CN106909583A (en) | A kind of financial information processing method and device based on mobile terminal | |
| KR102692170B1 (en) | Method for REQUESTING INSURANCE |
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 |