CN108550078A - The recommendation method and terminal device of loan product - Google Patents
The recommendation method and terminal device of loan product Download PDFInfo
- Publication number
- CN108550078A CN108550078A CN201810436123.8A CN201810436123A CN108550078A CN 108550078 A CN108550078 A CN 108550078A CN 201810436123 A CN201810436123 A CN 201810436123A CN 108550078 A CN108550078 A CN 108550078A
- Authority
- CN
- China
- Prior art keywords
- customer
- loan
- candidate
- product
- grade
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000000284 extract Substances 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 59
- 230000004069 differentiation Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 230000032258 transport Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000012797 qualification Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The present invention be suitable for field of artificial intelligence, provide a kind of the recommendation method and terminal device of loan product, by obtain client customer information, according in customer information customer capital value and authenticating tag determine the customer grade belonging to client；The product information of the corresponding multiple loan products of customer grade is transferred, and extracts the restrictive condition of each loan product from product information, the corresponding discriminant function of each loan product is generated with this；If the customer information meets the corresponding discriminant function of the loan product, using the loan product as candidate products, to generate candidate products set；From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend the client, it, can automatically to lead referral, it can buy and meet the loan product of the benefit of client so that without manually analyzing the entry criteria of loan product.
Description
Technical field
The invention belongs to the recommendation methods and terminal device of artificial intelligence field more particularly to a kind of loan product.
Background technology
In recent years, with the propulsion of the continuous opening and interest rate marketing process in China's Financial market, be born it is numerous not
Same loan product, such as：Car owner borrows, wages are borrowed and house property is borrowed etc., these different loan products correspond to different
Loan limit and loan interest rate.
However the entry criteria of different loan products is different, the prior art needs staff's manual analysis, with determination
The loan product that user can buy, and be that user recommends to best suit the loan product of user benefit, therefore is produced in loan in turn
The degree of automation is relatively low in the recommendation process of product, while can waste a large amount of human cost.
Invention content
In view of this, an embodiment of the present invention provides the recommendation method and terminal device of a kind of loan product, it is existing to solve
The problem for having technology the degree of automation present in the recommendation process of loan product relatively low.
The first aspect of the embodiment of the present invention provides a kind of recommendation method of loan product, including：
The customer information of client is obtained, the customer information includes customer capital value and authenticating tag, according to the visitor
Family assets value and the authenticating tag determine the customer grade belonging to the client；
The product information of the corresponding multiple loan products of the customer grade is transferred, the product information includes loan value
Degree extracts the restrictive condition of the loan product from the product information, and generates the loan based on the restrictive condition
The corresponding discriminant function of product；
Judge whether the customer information meets the corresponding discriminant function of the loan product；
If the customer information meets the corresponding discriminant function of the loan product, using the loan product as candidate
Product, to generate candidate products set；
From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend the visitor
Family.
The second aspect of the embodiment of the present invention provides a kind of terminal device, including memory and processor, described to deposit
The computer program that can be run on the processor is stored in reservoir, when the processor executes the computer program,
Realize following steps：
The customer information of client is obtained, the customer information includes customer capital value and authenticating tag, according to the visitor
Family assets value and the authenticating tag determine the customer grade belonging to the client；
The product information of the corresponding multiple loan products of the customer grade is transferred, the product information includes loan value
Degree extracts the restrictive condition of the loan product from the product information, and generates the loan based on the restrictive condition
The corresponding discriminant function of product；
Judge whether the customer information meets the corresponding discriminant function of the loan product；
If the customer information meets the corresponding discriminant function of the loan product, using the loan product as candidate
Product, to generate candidate products set；
From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend the visitor
Family.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, the computer program to realize following steps when being executed by processor：
The customer information of client is obtained, the customer information includes customer capital value and authenticating tag, according to the visitor
Family assets value and the authenticating tag determine the customer grade belonging to the client；It is corresponding multiple to transfer the customer grade
The product information of loan product, the product information include loan limit, and the loan product is extracted from the product information
Restrictive condition, and the corresponding discriminant function of the loan product is generated based on the restrictive condition；Judge the customer information
Whether the loan product corresponding discriminant function is met；If the customer information meets the corresponding differentiation letter of the loan product
Number, then using the loan product as candidate products, to generate candidate products set；From the candidate loan product set,
The maximum loan product of the loan limit is selected to recommend the client.
Further, the client determined according to the customer capital value and the authenticating tag belonging to the client
Grade, including：Obtain correspondence and preset customer grade and one of preset customer grade and assets minimum with
The correspondence of upper authenticating tag；The customer grade that the assets minimum is less than or equal to the customer capital value is chosen, is made
For candidate customer grade, and the ratio of the assets minimum and the customer capital value of the candidate customer grade is calculated, as
The assets ratio of candidate's customer grade；It is closed according to the preset customer grade is corresponding with more than one authenticating tag
System determines the corresponding authenticating tag of each candidate's customer grade, and calculates the authenticating tag for including in the customer information
The identical number of corresponding with candidate customer grade authenticating tag, as the corresponding same label of the candidate customer grade
Number；Calculate the sum of the corresponding same label number of candidate customer grade authenticating tag corresponding with candidate's customer grade
Ratio, the same ratio as the candidate customer grade；It is greater than or equal to the assets ratio in the same ratio
In candidate customer grade, select the highest candidate customer grade of the assets minimum as the client etc. belonging to the client
Grade.
Further, the restrictive condition that the loan product is extracted from the product information, and it is based on the limit
Condition processed generates the corresponding discriminant function of the loan product, including：Obtain preset keyword and preset separator；It carries
Take the text between separator described in the previous separator to the latter of the keyword as restrictive condition；Described in identification
The differentiation type of restrictive condition, the differentiation type include that inequality differentiates that class and character string differentiate class；If the limitation item
The differentiation type of part is that the inequality differentiates class, then extracts the inequality descriptor in the restrictive condition and differentiate threshold
Value, to generate the discriminant function；If the differentiation type of the restrictive condition, which is the character string, differentiates class, the limit is extracted
Logical operator in condition processed and differentiation character string, to generate the discriminant function.
Further, the differentiation type of the identification restrictive condition, including：
According to preset keyword and the correspondence for differentiating type, the differentiation kind in the restrictive condition is determined
Class；
Or obtain preset differentiation set of words and preset logical operation set of words；If in the restrictive condition including institute
The differentiation word differentiated in set of words is stated, then the restrictive condition is determined as the inequality differentiates class；If the restrictive condition
The restrictive condition is then determined as the character string and differentiated by the interior logical operation word comprising in the logical operation set of words
Class.
Further, it includes loan interest rate to state product information；The recommendation method of the loan product further includes：If described
There are multiple maximum loan products of loan limit in candidate loan product set, then in the candidate loan product set
In arbitrarily select a minimum loan product of the loan interest rate to recommend the client.
In embodiments of the present invention, by obtain client customer information, according to the customer capital value in customer information with
And authenticating tag determines the customer grade belonging to client；The product information of the corresponding multiple loan products of customer grade is transferred, and
The restrictive condition that each loan product is extracted from product information generates the corresponding discriminant function of each loan product with this；If
The customer information meets the corresponding discriminant function of the loan product, then using the loan product as candidate products, with life
At candidate products set；From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend
The client so that, can automatically it can be with to lead referral without manually analyzing the entry criteria of loan product
Buy and meet the loan product of the benefit of client.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment for those of ordinary skill in the art without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation flow chart of the recommendation method of loan product provided in an embodiment of the present invention；
Fig. 2 is the specific implementation flow chart of the recommendation method S101 of loan product provided in an embodiment of the present invention；
Fig. 3 is the specific implementation flow chart of the recommendation method S102 of loan product provided in an embodiment of the present invention；
Fig. 4 is the structure diagram of the recommendation apparatus of loan product provided in an embodiment of the present invention；
Fig. 5 is the schematic diagram of terminal device provided in an embodiment of the present invention.
Specific implementation mode
In being described below, for illustration and not for limitation, it is proposed that such as tool of particular system structure, technology etc
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Fig. 1 shows the implementation process of the recommendation method of loan product provided in an embodiment of the present invention, this method flow packet
Include step S101 to S106.The specific implementation principle of each step is as follows.
S101：The customer information of client is obtained, the customer information includes customer capital value and authenticating tag, according to institute
It states customer capital value and the authenticating tag determines customer grade belonging to the client.
Specifically, for a client when providing a loan, financial institution can collect the customer information of the client, these clients letter
Breath is for describing customer portrait, to help financial institution accurately to understand each client.Optionally, in embodiments of the present invention,
Mainly use the customer capital value for including in customer information and authenticating tag, wherein customer capital value is for describing a visitor
The assessed value for the movable and immovable property that family is registered in this financial institution in whole credits and the client of this financial institution it
With；Authenticating tag user describes the client qualification of a client, such as：The qualification of one client can be the money bought life insurance and borrowed
Matter.It is to be appreciated that user's qualification is for indicating the qualified certain type of loan product of purchase of a user.Such as：One
There is life insurance to borrow the client of qualification, just there is the qualification of purchase life insurance class loan.Notably, in embodiments of the present invention, tool
Whether standby life insurance borrows the client of qualification, can not necessarily buy whole loan products in life insurance class, can specifically buy,
Follow-up step is also needed to further to judge.In embodiments of the present invention, due to entire recommendation process be by computer program from
Dynamic to complete, so the client qualification of each client is indicated by corresponding authenticating tag, computer program can lead to
Identification authenticating tag is crossed, determines the client qualification of a client.Notably, each client may correspond to multiple certification marks
Label.
In embodiments of the present invention, client institute is determined by customer capital value in customer information and authenticating tag jointly
The customer grade of category, wherein correspond to more money loan products, the loan product that a client can buy in each customer grade
The range of the corresponding loan product of customer grade belonging to it cannot be exceeded.So in embodiments of the present invention, determining a visitor
The customer grade at family is the basis that follow-up loan product is recommended.
As an embodiment of the present invention, as shown in Fig. 2, above-mentioned S101 includes：
S1011 obtains the correspondence and preset customer grade and one of preset customer grade and assets minimum
The correspondence of a above authenticating tag.
In embodiments of the present invention, each customer grade has its corresponding assets minimum, for indicating each visitor
The assets entry criteria of family grade, it is possible to understand that ground, if the customer capital value of a client is less than the money of some customer grade
Minimum is produced, then the client cannot correspond to the customer grade.
In embodiments of the present invention, each customer grade corresponds to more than one authenticating tag, such as：1 grade of client etc.
Loan that the corresponding life insurance of grade is borrowed, children see a doctor and vehicle insurance are borrowed；2 grades of customer grades correspond to life insurance loan, vehicle insurance is borrowed, accident insurance is borrowed, A grades of vehicles
It borrows；3 grades of customer grades correspond to life insurance loan, vehicle insurance loan, accident insurance loan, A grades of housing loans, children's medical treatment loan.
It is to be appreciated that the entry criteria of each customer grade can be transferred by this step, client couple is determined to be follow-up
The customer grade answered provides data and supports.
S1012 chooses the customer grade that the assets minimum is less than or equal to the customer capital value, as candidate visitor
Family grade, and the ratio of the assets minimum and the customer capital value of the candidate customer grade is calculated, as the candidate
The assets ratio of customer grade.
It as described above, should if the customer capital value of a client is less than the assets minimum of some customer grade
Client cannot correspond to the customer grade, so in this step, choosing assets minimum first and being provided less than or equal to the client
The customer grade of the output value, as candidate customer grade.Such as：The customer capital value that client A is recorded in financial institution is 150,000,
And there are 8 customer grades, respectively 1 grade of customer grade, 2 grades of customer grades, 3 grades of customer grades etc. for financial institution, it is each
The assets minimum of customer grade is respectively：The assets minimum of 1 grade of customer grade is that the assets of 50,000,2 grades of customer grades are minimum
It is the assets minimums of 150,000,4 grades of customer grades is 300,000 etc. that value, which is the assets minimum of 100,000,3 grades of customer grades,.This
Outside, customer grade is higher, and corresponding assets minimum is also higher.Therefore in the above example, due to the customer capital of user A
Value is 150,000, so according to the correspondence of preset customer grade and assets minimum, 1 grade of customer grade, 2 grades of customer grades
And the assets minimum of 3 grades of customer grades is respectively less than or the customer capital value equal to client A, so herein by 1 grade of client etc.
Grade, 2 grades of customer grades and 3 grades of customer grades are as candidate customer grade.
In embodiments of the present invention, it is also necessary to calculate the assets minimum of candidate customer grade and the customer capital value
Ratio, the assets ratio as the candidate customer grade.Illustratively, taking the above example as an example, 1 grade of customer grade is corresponding
Assets ratio is 5/15=1/3；The corresponding assets ratio of 2 grades of customer grades is 10/15=2/3；The corresponding money of 3 grades of customer grades
Production ratio is 15/15=1.
S1013 is determined each described according to the correspondence of the preset customer grade and more than one authenticating tag
The corresponding authenticating tag of candidate customer grade, and calculate the authenticating tag that includes in the customer information and the candidate client etc.
The identical number of the corresponding authenticating tag of grade, as the corresponding same label number of candidate's customer grade.
Illustratively, as described in example above, loan that 1 grade of customer grade corresponds to life insurance loan, children see a doctor and vehicle insurance are borrowed；2
Grade customer grade corresponds to life insurance loan, vehicle insurance is borrowed, accident insurance is borrowed, A grades of vehicles are borrowed；3 grades of customer grades correspond to life insurance and borrow, vehicle insurance loan, anticipate
Outer danger loan, A grades of housing loans, children see a doctor and borrow.The authenticating tag for including in the customer information of client A is：Life insurance is borrowed, vehicle insurance is borrowed, B grades
Vehicle is borrowed and A grades of housing loans, then the identical number of client A authenticating tags corresponding with 1 grade of customer grade is 2, client A and 2 grades of visitors
The identical number of the corresponding authenticating tag of family grade is 2, the identical number of client A authenticating tags corresponding with 3 grades of customer grades
It is 3.So the embodiment of the present invention can include according in the correspondence and customer information of customer grade and authenticating tag
Authenticating tag is automatically determined out by computer program：1 grade of customer grade, 2 grades of customer grades and 3 grades of customer grades correspond to
Same label number be respectively：2、2、3.
S1014 calculates the corresponding same label number of the candidate customer grade and the candidate customer grade is corresponding and recognizes
The ratio for demonstrate,proving the sum of label, the same ratio as the candidate customer grade.
Illustratively, as described in example above, it is assumed that 1 grade of customer grade, 2 grades of customer grades and 3 grades of customer grades pair
The same label number answered is respectively：2、2、3.And 1 grade of customer grade, 2 grades of customer grades and the corresponding certification of 3 grades of customer grades
Total number of labels is：3、4、5.So the embodiment of the present invention can automatically be calculated by computer program 1 grade of customer grade, 2 grades
Customer grade and the corresponding same ratio of 3 grades of customer grades are respectively：2/3、2/4、3/5.
S1015 selects the money in the candidate customer grade that the same ratio is greater than or equal to the assets ratio
The highest candidate customer grade of minimum is produced as the customer grade belonging to the client.
Illustratively, as described in example above, the corresponding assets ratio of 1 grade of customer grade is 1/3；2 grades of customer grades pair
The assets ratio answered is 2/3；The corresponding assets ratio of 3 grades of customer grades is 1.1 grade of customer grade, 2 grades of customer grades and 3 grades
The corresponding same ratio of customer grade is respectively：2/3、2/4、3/5.So in embodiments of the present invention, computer program is automatic
Using 1 grade of customer grade as the customer grade belonging to client A.
Notably, in embodiments of the present invention, above-mentioned calculating process is automatically performed by computer program
's.
It is to be appreciated that due in embodiments of the present invention, the customer grade of a client be by customer capital value and
What authenticating tag determined jointly, and assets ratio is lower, it was demonstrated that the customer capital value of the client is relative to some customer grade
Assets minimum is bigger, then thinks that the assets that the client is possessed are corresponding relative to the customer grade in embodiments of the present invention
Safety higher for loan product, the possibility which breaks a contract for the customer grade is lower, so while should
The authenticating tag of client have part can not the matching of corresponding with customer grade authenticating tag, still may can buy the client
The corresponding loan product of grade.In addition, using same ratio and assets ratio as comparison other, unified client's money can be very good
The dimension of the two measurements of the output value and authenticating tag, the science that is conducive to objectively determine the customer grade belonging to a client.
S102：The product information of the corresponding multiple loan products of the customer grade is transferred, the product information includes borrowing
Amount of money degree extracts the restrictive condition of the loan product from the product information, and based on described in restrictive condition generation
The corresponding discriminant function of loan product.
As an embodiment of the present invention, as shown in figure 3, above-mentioned S102 includes：
S1021：Obtain preset keyword and preset separator.
In embodiments of the present invention, the restrictive condition in the product information of loan product is drawn by specific keyword
Go out, such as keyword can be " restrictive condition is " or " entry criteria is " or " must have the following conditions " etc..Separator can
Be ".", can also be other preset symbols.
In embodiments of the present invention, the preset keyword having had determined and preset separator are obtained first, are helped
In automatically and rapidly positioning restrictive condition in product information during subsequent.
S1022：Extract separator described in the previous separator to the latter of keyword described in the product information
Between text as restrictive condition.
It, can be with by separator it is to be appreciated that restrictive condition can be accurately positioned by above-mentioned preset keyword
The restrictive condition of complete text formatting is extracted.
S1023：Identify that the differentiation type of the restrictive condition, the differentiation type include that inequality differentiates class and character
String differentiates class.
In embodiments of the present invention, inequality differentiates that class is the classification containing inequality descriptor in restrictive condition, wherein
Inequality descriptor includes vocabulary such as " being more than ", " being less than ", " being greater than or equal to " and " being less than or equal to ", is implemented in the present invention
It is default to describe set of words there are one inequality in example.
Optionally, the differentiation type of the restrictive condition is identified, including：
It obtains preset inequality and describes set of words；If in the restrictive condition including the preset inequality descriptor
The restrictive condition is then determined as the inequality and differentiates class by the inequality descriptor in set；If in the restrictive condition
The inequality descriptor in set of words is described not comprising the preset inequality, then the restrictive condition is determined as the word
Symbol string differentiates class.
It is to be appreciated that in embodiments of the present invention, a restrictive condition cannot be determined as simultaneously inequality differentiate class and
Character string differentiates class.The embodiment of the present invention is just clear by each restrictive condition in the product information of each loan product of typing
Chu and unique one kind being set as in inequality differentiation class or character string differentiation class.
S1024 is extracted if the differentiation type of the restrictive condition, which is the inequality, differentiates class in the restrictive condition
Attribute word, inequality descriptor and discrimination threshold, and the inequality descriptor is converted to relational operator, to generate
The discriminant function.
In embodiments of the present invention, attribute word be restrictive condition in need confined attribute classification, such as：Restrictive condition
For " wages are more than 50,000 yuan ", then attribute word is " wages ", and inequality descriptor is " being more than ", and discrimination threshold is " 500000 ".
Optionally, in embodiments of the present invention, discriminant function is the function that computer program can be read automatically, it is possible to
According to preset correspondence, by inequality descriptor " being more than " be converted to relational operator ">”.Can by code language,
Attribute word in customer information is whether " wages " corresponding number is more than 50000 as a discriminant function.
S1025 is extracted if the differentiation type of the restrictive condition, which is the character string, differentiates class in the restrictive condition
Attribute word and the corresponding multiple character strings of the attribute word, to generate the discriminant function.
As described in example above, in embodiments of the present invention, attribute word is to need confined Attribute class in restrictive condition
Not, for example, restrictive condition is " work is necessary for one kind in teacher, doctor, soldier ", then attribute word is " work ", attribute word
Corresponding multiple character strings are " teacher ", " doctor ", " soldier ".It is to be appreciated that in embodiments of the present invention, said extracted mistake
Cheng Junke is automatically performed by computer.Optionally, in embodiments of the present invention, attribute word database and each category are preset with
The property corresponding string data library of word, therefore, when retrieving the vocabulary contained in a restrictive condition in attribute word database
When, then the vocabulary is identified as to the attribute word of this restrictive condition, and according to the corresponding string data library of the attribute word, identification
Go out this restrictive condition domestic demand character string to be extracted.
Optionally, the corresponding character string of attribute word in restrictive condition is combined, restricted character set of strings is generated, in the present invention
In embodiment, discriminant function is the function that computer program can be read automatically, can be by code language, will be in customer information
Attribute word is that " work " corresponding character string whether there is in the restricted character set of strings as a discriminant function.
It is to be appreciated that in embodiments of the present invention, different differentiation types, and extracting parameter accordingly are automatically identified,
Computer-readable discriminant function is generated by code language, is realized automatically by the restrictive condition in the product information of loan product
Being converted into subsequently can the whether qualified function of automatic decision customer information.
S103：Judge whether the customer information meets the corresponding discriminant function of the loan product.
It is to be appreciated that due to having generated computer-readable discriminant function according to the method for foregoing embodiments.Institute
With in embodiments of the present invention, it is only necessary to extract the attribute word that discriminant function includes, and according to the attribute word in customer information
Retrieve its corresponding numerical value or character string, so that it may to judge whether the customer information meets the loan according to discriminant function
The corresponding discriminant function of product.
S104 does not produce the loan if the customer information does not meet the corresponding discriminant function of the loan product
Product are as candidate products.
S105 makees the loan product if the customer information meets the corresponding discriminant function of the loan product
For candidate products, to generate candidate products set.
S106 selects the maximum loan product of the loan limit to recommend institute from the candidate loan product set
State client.
Optionally, the product information includes loan interest rate；
Optionally, if there are multiple maximum loan products of loan limit in the candidate loan product set,
Then a minimum loan product of the loan interest rate is arbitrarily selected to recommend the visitor in the candidate loan product set
Family.
It is to be appreciated that in real life, it is existing that identical situation, which occurs, in loan limit, and probability is not spy
It is not low, but be different the loan interest rate of loan product also identical probability is with regard to very low, in embodiments of the present invention, if borrowed
Money interest rate is also identical, can be in addition to arbitrarily selecting a minimum loan product of the loan interest rate to recommend the client
In the following way to lead referral loan product：According to customer information, classify to client, calculate same class client for
The selection percentage of these loan interest rates while minimum loan product, user is recommended by the highest loan product of selection percentage.
In embodiments of the present invention, by obtain client customer information, according to the customer capital value in customer information with
And authenticating tag determines the customer grade belonging to client；The product information of the corresponding multiple loan products of customer grade is transferred, and
The restrictive condition that each loan product is extracted from product information generates the corresponding discriminant function of each loan product with this；If
The customer information meets the corresponding discriminant function of the loan product, then using the loan product as candidate products, with life
At candidate products set；From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend
The client so that, can automatically it can be with to lead referral without manually analyzing the entry criteria of loan product
Buy and meet the loan product of the benefit of client.
Corresponding to the recommendation method of the loan product described in foregoing embodiments, Fig. 4 shows provided in an embodiment of the present invention
The structure diagram of the recommendation apparatus of loan product illustrates only and the relevant part of the embodiment of the present invention for convenience of description.
With reference to Fig. 4, which includes：
Acquisition module 401, the customer information for obtaining client, the customer information include customer capital value and certification
Label determines the customer grade belonging to the client according to the customer capital value and the authenticating tag；
Generation module 402, the product information for transferring the corresponding multiple loan products of the customer grade, the product
Information includes loan limit, the restrictive condition of the loan product is extracted from the product information, and be based on the limitation item
Part generates the corresponding discriminant function of the loan product；
Judgment module 403, for judging whether the customer information meets the corresponding discriminant function of the loan product；
Execution module 404 will be described if meeting the corresponding discriminant function of the loan product for the customer information
Loan product is as candidate products, to generate candidate products set；
Recommending module 405, for from the candidate loan product set, selecting the maximum loan production of the loan limit
Product recommend the client.
Optionally, the acquisition module 401 includes：
Relation acquisition submodule, the correspondence for obtaining preset customer grade and assets minimum, and it is default
Customer grade and more than one authenticating tag correspondence；
Submodule is chosen, the customer grade of the customer capital value is less than or equal to for choosing the assets minimum,
As candidate customer grade, and the ratio of the assets minimum and the customer capital value of the candidate customer grade is calculated, made
For the assets ratio of the candidate customer grade；
First computational submodule, for being closed according to the preset customer grade is corresponding with more than one authenticating tag
System determines the corresponding authenticating tag of each candidate's customer grade, and calculates the authenticating tag for including in the customer information
The identical number of corresponding with candidate customer grade authenticating tag, as the corresponding same label of the candidate customer grade
Number；
Second computational submodule, for calculating the corresponding same label number of the candidate customer grade and the candidate client
The ratio of the sum of the corresponding authenticating tag of grade, the same ratio as the candidate customer grade；
Submodule is selected, is used in the candidate customer grade that the same ratio is greater than or equal to the assets ratio,
Select the highest candidate customer grade of the assets minimum as the customer grade belonging to the client.
Optionally, the generation module 402 includes：
Keyword acquisition submodule, for obtaining preset keyword and preset separator；
Extracting sub-module, for extracting the previous separator of keyword described in the product information to the latter institute
The text between separator is stated as restrictive condition；
Identify submodule, for identification the differentiation type of the restrictive condition, the differentiation type includes that inequality differentiates
Class and character string differentiate class；
Transform subblock, if the differentiation type for the restrictive condition is inequality differentiation class, described in extraction
Attribute word, inequality descriptor in restrictive condition and discrimination threshold, and convert the inequality descriptor to relationship fortune
Operator, to generate the discriminant function；
Function generates submodule, if the differentiation type for the restrictive condition, which is the character string, differentiates class, extracts
Attribute word in the restrictive condition and the corresponding multiple character strings of the attribute word, to generate the discriminant function.
Optionally, the identification submodule is specifically used for：
It obtains preset inequality and describes set of words；
If the inequality descriptor in set of words is described comprising the preset inequality in the restrictive condition, by institute
It states restrictive condition and is determined as the inequality differentiation class；
It, will if describing the inequality descriptor in set of words not comprising the preset inequality in the restrictive condition
The restrictive condition is determined as the character string and differentiates class.
Optionally, the product information includes loan interest rate；Described device further includes：
It is arbitrary to choose module, if for there are multiple loan limits are maximum in the candidate loan product set
Loan product, the then loan product for arbitrarily selecting a loan interest rate minimum in the candidate loan product set are recommended
To the client.
In embodiments of the present invention, by obtain client customer information, according to the customer capital value in customer information with
And authenticating tag determines the customer grade belonging to client；The product information of the corresponding multiple loan products of customer grade is transferred, and
The restrictive condition that each loan product is extracted from product information generates the corresponding discriminant function of each loan product with this；If
The customer information meets the corresponding discriminant function of the loan product, then using the loan product as candidate products, with life
At candidate products set；From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend
The client so that, can automatically it can be with to lead referral without manually analyzing the entry criteria of loan product
Buy and meet the loan product of the benefit of client.
Fig. 5 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 5, the terminal of the embodiment is set
Standby 5 include：Processor 50, memory 51 and it is stored in the meter that can be run in the memory 51 and on the processor 50
Calculation machine program 52, for example, loan product recommended program.The processor 50 is realized above-mentioned when executing the computer program 52
Step in the recommendation embodiment of the method for each loan product, such as step 101 shown in FIG. 1 is to 106.Alternatively, the processing
Device 50 realizes the function of each module/unit in above-mentioned each device embodiment when executing the computer program 52, such as shown in Fig. 4
The function of unit 401 to 405.
Illustratively, the computer program 52 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 51, and are executed by the processor 50, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 52 in the terminal device 5 is described.
The terminal device 5 can be that the calculating such as desktop PC, notebook, palm PC and cloud server are set
It is standby.The terminal device may include, but be not limited only to, processor 50, memory 51.It will be understood by those skilled in the art that Fig. 5
The only example of terminal device 5 does not constitute the restriction to terminal device 5, may include than illustrating more or fewer portions
Part either combines certain components or different components, such as the terminal device can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 50 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 51 can be the internal storage unit of the terminal device 5, such as the hard disk of terminal device 5 or interior
It deposits.The memory 51 can also be to be equipped on the External memory equipment of the terminal device 5, such as the terminal device 5
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 51 can also both include the storage inside list of the terminal device 5
Member also includes External memory equipment.The memory 51 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 51 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
It, can also be above-mentioned integrated during two or more units are integrated in one unit to be that each unit physically exists alone
The form that hardware had both may be used in unit is realized, can also be realized in the form of SFU software functional unit.In addition, each function list
Member, the specific name of module are also only to facilitate mutually distinguish, the protection domain being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can be stored in a computer read/write memory medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to aforementioned reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment is modified or equivalent replacement of some of the technical features；And these are changed
Or replace, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of recommendation method of loan product, which is characterized in that including：
The customer information of client is obtained, the customer information includes customer capital value and authenticating tag, is provided according to the client
The output value and the authenticating tag determine the customer grade belonging to the client；
The product information of the corresponding multiple loan products of the customer grade is transferred, the product information includes loan limit, from
The restrictive condition of the loan product is extracted in the product information, and the loan product pair is generated based on the restrictive condition
The discriminant function answered；
Judge whether the customer information meets the corresponding discriminant function of the loan product；
If the customer information meets the corresponding discriminant function of the loan product, produced the loan product as candidate
Product, to generate candidate products set；
From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend the client.
2. the recommendation method of loan product as described in claim 1, which is characterized in that it is described according to the customer capital value with
And the authenticating tag determines the customer grade belonging to the client, including：
Obtain correspondence and preset customer grade and more than one certification of preset customer grade and assets minimum
The correspondence of label；
The customer grade that the assets minimum is less than or equal to the customer capital value is chosen, as candidate customer grade, and
The ratio for calculating the assets minimum and the customer capital value of the candidate customer grade, as the candidate customer grade
Assets ratio；
According to the correspondence of the preset customer grade and more than one authenticating tag, each described candidate client etc. is determined
The corresponding authenticating tag of grade, and calculate the authenticating tag that includes in the customer information and the candidate customer grade is corresponding and recognize
The identical number of label is demonstrate,proved, as the corresponding same label number of candidate's customer grade；
Calculate the total of the corresponding same label number of candidate customer grade authenticating tag corresponding with candidate's customer grade
Several ratio, the same ratio as the candidate customer grade；
In the candidate customer grade that the same ratio is greater than or equal to the assets ratio, the assets minimum is selected most
High candidate customer grade is as the customer grade belonging to the client.
3. the recommendation method of loan product as described in claim 1, which is characterized in that described to be extracted from the product information
The restrictive condition of the loan product, and the corresponding discriminant function of the loan product is generated based on the restrictive condition, including：
Obtain preset keyword and preset separator；
Extract the text between separator described in the previous separator to the latter of keyword described in the product information
As restrictive condition；
Identify that the differentiation type of the restrictive condition, the differentiation type include that inequality differentiates that class and character string differentiate class；
If the differentiation type of the restrictive condition, which is the inequality, differentiates class, extract attribute word in the restrictive condition,
Inequality descriptor and discrimination threshold, and convert the inequality descriptor to relational operator, to generate the differentiation
Function；
If the differentiation type of the restrictive condition be the character string differentiate class, extract the attribute word in the restrictive condition with
And the corresponding multiple character strings of the attribute word, to generate the discriminant function.
4. the recommendation method of loan product as claimed in claim 3, which is characterized in that described to identify sentencing for the restrictive condition
Other type, including：
It obtains preset inequality and describes set of words；
If the inequality descriptor in set of words is described comprising the preset inequality in the restrictive condition, by the limit
Condition processed is determined as the inequality and differentiates class；
It, will be described if describing the inequality descriptor in set of words not comprising the preset inequality in the restrictive condition
Restrictive condition is determined as the character string and differentiates class.
5. the recommendation method of loan product as described in claim 1, which is characterized in that the product information includes loan profit
Rate；
The recommendation method of the loan product further includes：
If in the candidate loan product set, there are multiple maximum loan products of loan limit, in the candidate
A minimum loan product of the loan interest rate is arbitrarily selected to recommend the client in loan product set.
6. a kind of terminal device, including memory and processor, it is stored with and can transports on the processor in the memory
Capable computer program, which is characterized in that when the processor executes the computer program, realize following steps：
The customer information of client is obtained, the customer information includes customer capital value and authenticating tag, is provided according to the client
The output value and the authenticating tag determine the customer grade belonging to the client；
The product information of the corresponding multiple loan products of the customer grade is transferred, the product information includes loan limit, from
The restrictive condition of the loan product is extracted in the product information, and the loan product pair is generated based on the restrictive condition
The discriminant function answered；
Judge whether the customer information meets the corresponding discriminant function of the loan product；
If the customer information meets the corresponding discriminant function of the loan product, produced the loan product as candidate
Product, to generate candidate products set；
From the candidate loan product set, the maximum loan product of the loan limit is selected to recommend the client.
7. terminal device as claimed in claim 6, which is characterized in that described according to the customer capital value and the certification
Label determines the customer grade belonging to the client, including：
Obtain correspondence and preset customer grade and more than one certification of preset customer grade and assets minimum
The correspondence of label；
The customer grade that the assets minimum is less than or equal to the customer capital value is chosen, as candidate customer grade, and
The ratio for calculating the assets minimum and the customer capital value of the candidate customer grade, as the candidate customer grade
Assets ratio；
According to the correspondence of the preset customer grade and more than one authenticating tag, each described candidate client etc. is determined
The corresponding authenticating tag of grade, and calculate the authenticating tag that includes in the customer information and the candidate customer grade is corresponding and recognize
The identical number of label is demonstrate,proved, as the corresponding same label number of candidate's customer grade；
Calculate the total of the corresponding same label number of candidate customer grade authenticating tag corresponding with candidate's customer grade
Several ratio, the same ratio as the candidate customer grade；
In the candidate customer grade that the same ratio is greater than or equal to the assets ratio, the assets minimum is selected most
High candidate customer grade is as the customer grade belonging to the client.
8. terminal device as claimed in claim 6, which is characterized in that described to extract the loan production from the product information
The restrictive condition of product, and the corresponding discriminant function of the loan product is generated based on the restrictive condition, including：
Obtain preset keyword and preset separator；
Extract the text between separator described in the previous separator to the latter of keyword described in the product information
As restrictive condition；
Identify that the differentiation type of the restrictive condition, the differentiation type include that inequality differentiates that class and character string differentiate class；
If the differentiation type of the restrictive condition, which is the inequality, differentiates class, extract attribute word in the restrictive condition,
Inequality descriptor and discrimination threshold, and convert the inequality descriptor to relational operator, to generate the differentiation
Function；
If the differentiation type of the restrictive condition be the character string differentiate class, extract the attribute word in the restrictive condition with
And the corresponding multiple character strings of the attribute word, to generate the discriminant function.
9. terminal device as claimed in claim 8, which is characterized in that the differentiation type of the identification restrictive condition, packet
It includes：
It obtains preset inequality and describes set of words；
If the inequality descriptor in set of words is described comprising the preset inequality in the restrictive condition, by the limit
Condition processed is determined as the inequality and differentiates class；
It, will be described if describing the inequality descriptor in set of words not comprising the preset inequality in the restrictive condition
Restrictive condition is determined as the character string and differentiates class.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810436123.8A CN108550078A (en) | 2018-05-09 | 2018-05-09 | The recommendation method and terminal device of loan product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810436123.8A CN108550078A (en) | 2018-05-09 | 2018-05-09 | The recommendation method and terminal device of loan product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108550078A true CN108550078A (en) | 2018-09-18 |
Family
ID=63513719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810436123.8A Pending CN108550078A (en) | 2018-05-09 | 2018-05-09 | The recommendation method and terminal device of loan product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108550078A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447787A (en) * | 2018-10-26 | 2019-03-08 | 平安科技（深圳）有限公司 | Reference report automatically parses method, apparatus, computer equipment and storage medium |
| CN109544264A (en) * | 2018-10-17 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Financial loan product recommended method, device, computer equipment and storage medium |
| CN109636501A (en) * | 2018-10-30 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Product data processing method, device, computer equipment and computer readable storage medium |
| CN110264306A (en) * | 2019-05-21 | 2019-09-20 | 平安银行股份有限公司 | Products Show method, apparatus, server and medium based on big data |
| CN111476561A (en) * | 2020-04-07 | 2020-07-31 | 深圳市分期乐网络科技有限公司 | Account period recommendation method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427168A (en) * | 2015-12-10 | 2016-03-23 | 中国联合网络通信集团有限公司 | Loan assessment method and system |
| CN107657525A (en) * | 2017-08-29 | 2018-02-02 | 深圳市佰仟金融服务有限公司 | One kind loan measures and procedures for the examination and approval and server |
| CN107729443A (en) * | 2017-09-29 | 2018-02-23 | 平安科技（深圳）有限公司 | Loan product promotion method, device and computer-readable recording medium |
| CN107871276A (en) * | 2017-07-25 | 2018-04-03 | 平安科技（深圳）有限公司 | Inquiry unit, method and the computer-readable recording medium of loan product |
-
2018
- 2018-05-09 CN CN201810436123.8A patent/CN108550078A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427168A (en) * | 2015-12-10 | 2016-03-23 | 中国联合网络通信集团有限公司 | Loan assessment method and system |
| CN107871276A (en) * | 2017-07-25 | 2018-04-03 | 平安科技（深圳）有限公司 | Inquiry unit, method and the computer-readable recording medium of loan product |
| CN107657525A (en) * | 2017-08-29 | 2018-02-02 | 深圳市佰仟金融服务有限公司 | One kind loan measures and procedures for the examination and approval and server |
| CN107729443A (en) * | 2017-09-29 | 2018-02-23 | 平安科技（深圳）有限公司 | Loan product promotion method, device and computer-readable recording medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544264A (en) * | 2018-10-17 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Financial loan product recommended method, device, computer equipment and storage medium |
| CN109447787A (en) * | 2018-10-26 | 2019-03-08 | 平安科技（深圳）有限公司 | Reference report automatically parses method, apparatus, computer equipment and storage medium |
| CN109636501A (en) * | 2018-10-30 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Product data processing method, device, computer equipment and computer readable storage medium |
| CN110264306A (en) * | 2019-05-21 | 2019-09-20 | 平安银行股份有限公司 | Products Show method, apparatus, server and medium based on big data |
| CN110264306B (en) * | 2019-05-21 | 2023-06-30 | 平安银行股份有限公司 | Big data-based product recommendation method, device, server and medium |
| CN111476561A (en) * | 2020-04-07 | 2020-07-31 | 深圳市分期乐网络科技有限公司 | Account period recommendation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108550078A (en) | The recommendation method and terminal device of loan product | |
| CN109918511B (en) | BFS and LPA based knowledge graph anti-fraud feature extraction method | |
| CN111738001B (en) | Training method of synonym recognition model, synonym determination method and equipment | |
| US20210319280A1 (en) | Interpretable node embedding | |
| CN108804564A (en) | The combined recommendation method and terminal device of financial product | |
| CN111522979B (en) | Picture sorting recommendation method and device, electronic equipment and storage medium | |
| CN103942214B (en) | Natural image classification method and device on basis of multi-modal matrix filling | |
| CN110704803A (en) | Target object evaluation value calculation method and device, storage medium and electronic device | |
| CN111898528B (en) | Data processing method, device, computer readable medium and electronic equipment | |
| CN111259975B (en) | Method and device for generating classifier and method and device for classifying text | |
| Lo et al. | An emperical study on application of big data analytics to automate service desk business process | |
| CN111242520B (en) | Feature synthesis model generation method and device and electronic equipment | |
| Sam Abraham et al. | Readers’ affect: Predicting and understanding readers’ emotions with deep learning | |
| Mori et al. | Automated worker skill evaluation for improving productivity based on labeled LDA | |
| CN113837836A (en) | Model recommendation method, device, equipment and storage medium | |
| Yang et al. | Evaluation and assessment of machine learning based user story grouping: A framework and empirical studies | |
| CN113297378A (en) | Text data labeling method and system, electronic equipment and storage medium | |
| Gerling | Company2Vec--German Company Embeddings based on Corporate Websites | |
| CN110737749A (en) | Entrepreneurship plan evaluation method, entrepreneurship plan evaluation device, computer equipment and storage medium | |
| CN113919447B (en) | Digital asset transaction management method and system based on DNA molecular encryption and LightGBM algorithm | |
| Dinov et al. | Lazy Learning: Classification Using Nearest Neighbors | |
| CN114418752B (en) | Method and device for processing user data without type label, electronic equipment and medium | |
| Solanki et al. | Assimilate Machine Learning Algorithms in Big Data Analytics | |
| Morales-Hernández et al. | A Comparison of Multi-Label Text Classification Models in Research Articles Labeled With Sustainable Development Goals | |
| Ojo et al. | Graph Neural Network for Smartphone Recommendation System: A Sentiment Analysis Approach for Smartphone Rating |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180918 |