CN110321475A

CN110321475A - Sort method, device, equipment and the storage medium of data list

Info

Publication number: CN110321475A
Application number: CN201910426987.6A
Authority: CN
Inventors: 王凯
Original assignee: OneConnect Financial Technology Co Ltd Shanghai
Current assignee: OneConnect Financial Technology Co Ltd Shanghai
Priority date: 2019-05-22
Filing date: 2019-05-22
Publication date: 2019-10-11

Abstract

The present invention relates to the intelligent recommendation fields of big data technical field, disclose sort method, device, equipment and the storage medium of data list, for improving the sequence accuracy of data list, and then promote the purchase success rate of business.The method of the present invention includes: that creation front end is buried a little, and the front end is buried a little for capturing the operation in terminal；Acquisition Added Business information is buried by the front end；Tendency business information is determined according to the Added Business information and preset historical operational information, and the tendency business information is for being ranked up the business information in data list；Recommend business information to be ranked up each business information in the data list according to the tendency business information and preset history, obtains the first sequence；First sequence is shown in the data list.

Description

Sort method, device, equipment and the storage medium of data list

Technical field

The present invention relates to intelligent recommendation field more particularly to a kind of sort method of data list, device, equipment and storages Medium.

Background technique

With the fast development of internet, terminal industry is also fast-developing, the application program generated along with terminal (application, APP) is also more and more, and each mechanism is proposed various corresponding APP also for terminal, each to promote From service product, how to improve the user of APP experience sense and business buying rate become each mechanism to be solved it is main Problem.

Currently, most of mechanisms all simply sort sequentially in time to each business, and by corresponding APP to Client carries out the recommendation of business, and with the development of internet industry, the type of business is more and more, can generate all kinds of business numbers According to, and APP can only simply carry out classification and ordination.

And this sequencing model does not have specific aim, popular business is not distinguished in the data list of APP only simple sequence Or client it is expected higher business, the inaccuracy that puts in order of each business in obtained sorted lists.

Summary of the invention

The present invention provides a kind of sort method of data list, device, equipment and storage mediums, for improving data column The sequence accuracy of table, and then promote the purchase success rate of business.

The first aspect of the embodiment of the present invention provides a kind of sort method of data list, comprising: creation front end is buried a little, institute Front end is stated to bury a little for capturing the operation in terminal；Acquisition Added Business information is buried by the front end；According to described newly-increased Business information and preset historical operational information determine that tendency business information, the tendency business information are used for in data list Business information be ranked up；Recommend business information to the data list according to the tendency business information and preset history In each business information be ranked up, obtain first sequence；First sequence is shown in the data list.

Optionally, described according to the Added Business in the first implementation of first aspect of the embodiment of the present invention Information and preset historical operational information determine that tendency business information, the tendency business information are used for the industry in data list It includes: to bury a little to detect that user enters institute by Added Business interface or draft interface when the front end that business information, which is ranked up, When stating data list, determine that the first business information, first business information include according to the preset historical operational information Business relationship, business man-year age and business people's occupation；The data form to match is determined according to first business information； Determine that target service information, the target service are in the data form to match according to the data form to match The highest business of frequency of interaction；Using the target service information as the tendency business information.

Optionally, described according to the Added Business in second of implementation of first aspect of the embodiment of the present invention Information and preset historical operational information determine that tendency business information includes: to bury a little to detect that user passes through business when the front end When supermarket interface enters the data list, the historical data list that business people has bought is obtained；It has been bought in the business people Historical data list in select a target service information as tendency business information.

Optionally, described according to the tendency business in the third implementation of first aspect of the embodiment of the present invention Information and preset history recommend business information to be ranked up each business information in the data list, and it is suitable to obtain first Sequence includes: to recommend business information as weight order item the tendency business information and preset history；Calculate the tendency First multiple correlation coefficient of business information and other weight order items calculates the preset history and recommends business information and other Second multiple correlation coefficient of weight order item；The first inverse is generated according to the first multiple correlation coefficient, according to the second multiple correlation coefficient It is reciprocal to generate second；Respectively to described first is reciprocal and second inverse be normalized generate the first weight coefficient and Second weight coefficient, first weight coefficient are the weight coefficient of the tendency business information, and second weight coefficient is The preset history recommends the weight coefficient of business information；According to first weight coefficient and the second weight coefficient meter Calculate the ranking value of each business；The ranking value of each business is ranked up according to sequence from big to small, is obtained each First sequence of a business.

Optionally, in the 4th kind of implementation of first aspect of the embodiment of the present invention, the method also includes: it obtains every The business hot value of a business, and the second sequence is determined according to first sequence and the business hot value；By described second Sequence is shown in the data list.

Optionally, in the 5th kind of implementation of first aspect of the embodiment of the present invention, the industry for obtaining each business Business hot value, and determine that the second sequence includes: to obtain first sequence according to first sequence and the business hot value In each business business hot value；Using the business hot value as new weight order item；Calculate the tendency business letter First multiple correlation coefficient of breath and other weight order items calculates the preset history and business information and other sequences is recommended to weigh Second multiple correlation coefficient of weight item calculates the third multiple correlation coefficient of the business hot value Yu other weight order items；According to First multiple correlation coefficient generates the first inverse, the second inverse is generated according to the second multiple correlation coefficient, according to third multiple correlation coefficient It is reciprocal to generate third；Generation is normalized to described first reciprocal, the described second reciprocal and described third inverse respectively The first new weight coefficient, new the second weight coefficient and new third weight coefficient, the first new weight coefficient is institute The weight coefficient of tendency business information is stated, the second new weight coefficient is the power that the preset history recommends business information Weight coefficient, the new third weight coefficient are the weight coefficient of the business hot value；According to the first new weight system Several, described the second new weight coefficient and the new third weight coefficient recalculate the new recommendation of each business；By institute The new recommendation for stating each business is ranked up according to sequence from big to small, obtains the second sequence.

Optionally, in the 6th kind of implementation of first aspect of the embodiment of the present invention, the method also includes: in response to The business information that user is paid close attention in the comparison operation of user is marked, and obtains the business information of multiple labels；To the multiple The business information of label is compared, and obtains comparison information；By the comparison information, button is associated compared with preset；When When detecting that user clicks the preset comparison button, the comparison information is shown on the terminal.

The second aspect of the embodiment of the present invention provides a kind of collator of data list, comprising: creating unit is used for Creation front end is buried a little, and the front end is buried a little for capturing the operation in terminal；First acquisition unit, for being buried by the front end Point obtains Added Business information；Determination unit, for being determined according to the Added Business information and preset historical operational information It is inclined to business information, the tendency business information is for being ranked up the business information in data list；Sequencing unit is used for Business information is recommended to arrange each business information in data list according to the tendency business information and preset history Sequence obtains the first sequence；First display unit, for first sequence to be shown in the data list.

Optionally, in the first implementation of second aspect of the embodiment of the present invention, determination unit is specifically used for: working as institute It states front end to bury when a little detecting that user enters the data list by Added Business interface or draft interface, according to described pre- The historical operational information set determines the first business information, first business information include business relationship, business man-year age with And business people's occupation；The data form to match is determined according to first business information；According to the tables of data to match It is single to determine that target service information, the target service are the highest business of frequency of interaction in the data form to match；It will The target service information is as the tendency business information.

Optionally, in second of implementation of second aspect of the embodiment of the present invention, determination unit is specifically also used to: when The front end, which is buried, a little detects that user passes through business supermarket interface into when the data list, and what acquisition business people had bought goes through History data list；Select a target service information as tendency business in the historical data list that the business people has bought Information.

Optionally, in the third implementation of second aspect of the embodiment of the present invention, sequencing unit is specifically used for: by institute It states tendency business information and preset history recommends business information as weight order item；Calculate the tendency business information and its First multiple correlation coefficient of his weight order item calculates the preset history and recommends business information and other weight order items Second multiple correlation coefficient；The first inverse is generated according to the first multiple correlation coefficient, it is reciprocal to generate second according to the second multiple correlation coefficient； The first weight coefficient and the second weight coefficient are generated to the described first reciprocal be normalized with second inverse respectively, First weight coefficient is the weight coefficient of the tendency business information, and second weight coefficient is the preset history Recommend the weight coefficient of business information；Each business is calculated according to first weight coefficient and second weight coefficient Ranking value；The ranking value of each business is ranked up according to sequence from big to small, obtain each business first is suitable Sequence.

Optionally, in the 4th kind of implementation of second aspect of the embodiment of the present invention, the collator of data list is also It include: second acquisition unit, for obtaining the business hot value of each business, and according to first sequence and business heat Angle value determines the second sequence；Second display unit, for showing second sequence in the data list.

Optionally, in the 5th kind of implementation of second aspect of the embodiment of the present invention, second acquisition unit is specifically used for: Obtain the business hot value of each business in first sequence；Using the business hot value as new weight order item；Meter The first multiple correlation coefficient for calculating the tendency business information and other weight order items calculates the preset history and recommends business Second multiple correlation coefficient of information and other weight order items calculates the third of the business hot value and other weight order items Multiple correlation coefficient；The first inverse is generated according to the first multiple correlation coefficient, the second inverse is generated according to the second multiple correlation coefficient, according to It is reciprocal that third multiple correlation coefficient generates third；Described first reciprocal, the described second reciprocal and described third inverse is carried out respectively Normalized generates the first new weight coefficient, new the second weight coefficient and new third weight coefficient, and described new the One weight coefficient is the weight coefficient of the tendency business information, and the second new weight coefficient is that the preset history pushes away The weight coefficient of business information is recommended, the new third weight coefficient is the weight coefficient of the business hot value；According to described New the first weight coefficient, the second new weight coefficient and the new third weight coefficient recalculates each business New recommendation；The new recommendation of each business is ranked up according to sequence from big to small, obtains the second sequence.

Optionally, in the 6th kind of implementation of second aspect of the embodiment of the present invention, the collator of data list is also It include: marking unit, the business information paid close attention to for the comparison operation in response to user user is marked, and obtains multiple marks The business information of note；Comparing unit is compared for the business information to the multiple label, obtains comparison information；Association Unit, for button to be associated compared with preset by the comparison information；Third display unit detects user for working as When clicking the preset comparison button, the comparison information is shown on the terminal.

The third aspect of the embodiment of the present invention provides a kind of sequencing equipment of data list, including memory, processor And it is stored in the computer program that can be run on the memory and on the processor, the processor executes the calculating The sort method of data list described in any of the above-described embodiment is realized when machine program.

The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, including instruction, when the finger When order is run on computers, so that computer executes the step of the sort method of data list described in any of the above-described embodiment Suddenly.

In technical solution provided in an embodiment of the present invention, creation front end is buried a little, and front end is buried a little for capturing the behaviour in terminal Make；Acquisition Added Business information is buried by front end；Tendency is determined according to Added Business information and preset historical operational information Business information, the tendency business information is for being ranked up the business information in data list；According to tendency business information Recommend business information to be ranked up each business information in data list with preset history, obtains the first sequence；By One sequence is shown in data list.The embodiment of the present invention improves the sequence accuracy of data list, and then promotes industry The purchase success rate of business.

Detailed description of the invention

Fig. 1 is one embodiment schematic diagram of the sort method of data list in the embodiment of the present invention；

Fig. 2 is another embodiment schematic diagram of the sort method of data list in the embodiment of the present invention；

Fig. 3 is one embodiment schematic diagram of the collator of data list in the embodiment of the present invention；

Fig. 4 is another embodiment schematic diagram of the collator of data list in the embodiment of the present invention；

Fig. 5 is one embodiment schematic diagram of the sequencing equipment of data list in the embodiment of the present invention.

Specific embodiment

In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention The embodiment of the present invention is described in attached drawing.

Description and claims of this specification and term " first ", " second ", " third ", " in above-mentioned attached drawing The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein Or the sequence other than the content of description is implemented.In addition, term " includes " or " having " and its any deformation, it is intended that covering is not Exclusive includes, for example, the process, method, system, product or equipment for containing a series of steps or units be not necessarily limited to it is clear Step or unit those of is listed on ground, but is not clearly listed or for these process, methods, product or is set Standby intrinsic other step or units.

Referring to Fig. 1, the flow chart of the sort method of data list provided in an embodiment of the present invention, specifically includes:

101, creation front end is buried a little, which buries a little for capturing the operation in terminal.

Terminal creation front end is buried a little, which buries a little for capturing the operation in terminal.Specifically, before terminal is one newly-increased End is buried a little, which buries the operation that can a little capture client (user) on terminal APP, for example, when client is in front-end business After carrying out current operation, back office interface is accessed, terminal records business personnel, customer information and the current operation function of current operation.

It should be noted that an existing technology of burying mainly has three classes: code buries a little, leads to when some control operates and occurs Data are sent out after the code finished writing in advance；Visualization is buried a little, is configured control operation by visualization interface and is related with event； Without point (burying entirely a little) is buried, all data object that screening needs to analyze in rear end again is first collected.

Wherein, it is as follows to bury concrete principle a little for code: when APP or interface are initialized, initializing third number formulary According to the Software Development Kit (software development kit, SDK) of Analysis Service quotient, then occur in some event When just calls the inside SDK, and data transmission interface sends data accordingly.For example, wanting that the click for counting some button inside APP is secondary Number can call SDK to provide then when some button of APP is clicked inside the corresponding OnClick function of this button Data transmission interfaces sends data.

Wherein, the concrete principle that visualization is buried a little is as follows: by taking the end iOS as an example, realization details is further described.Specifically, Visualization, which is opened, in the APP for being embedded in SDK buries dot pattern, when with rear end connection, SDK can answer the requirement of rear end, periodically (such as It is per second) screenshot is done, and SDK can carry out traversing its since keyWindow object while for APP screenshot Subviews () obtains the hierarchical relationship of all UIView, UIResponder objects under active view.For appointing on screen What UIView object, such as Button, Textfield, it have one uniquely from keyWindow to its path, Each node on this path, all by ClassName, it be the attributes such as which subview .text () of father node value Deng mark.The information of the visualization aspect such as coordinate, length, width and height relative to father node is the attribute presence as this node. Terminal re-starts page rendering according to screenshotss and visual information, and according to the type of control, which control identified Can increase can bury a little, and it is identified.It can be buried when user clicks some on the screenshotss picture on backstage Point control when, may require that from the background user do some events association aspect configuration, and by configuration information carry out save and Deployment.SDK gets these configuration informations in starting or customary poll, then can pass through .addTarget:action: ForControlEvents: interface is the click of each associated control addition or the monitoring of edit action, and is returning The interface of Sensors Analytics SDK is called to send the track information of corresponding event inside function.It is understood that A scheme is buried in the visualization at the end Android, and almost the same with the end iOS, details are not described herein again.

Wherein, as follows without the concrete principle buried a little: " nothing is buried a little " buried with visualization it is a little similar, and from actual realization It sees, the difference of the two is exactly that visualization buries and a little first passes through the operation data of interface configurations which controls and need to collect；" without burying a little " It is then the operation data for first collecting all controls as far as possible, then by interface configurations, which data needs inside system again It is analyzed.The advantages of " without bury a little " buries compared to visualization, be on the one hand solve the problems, such as data " backtracking ", for example, Some day, want the analysis for increasing the click of some control suddenly, bury a scheme if it is visualization, then can only from this moment to After collect data, and if it is " without burying a little ", then from deployment SDK when data just all having collected always；On the other hand, " without burying a little " scheme can also obtain the information of many enlightenments automatically, for example, can tell this boundary of user " without burying a little " The probability that each control is clicked respectively on face be it is much, which control is worth doing further analysis etc..

102, acquisition Added Business information is buried by front end.

Terminal buries acquisition Added Business information by front end.Wherein, Added Business information can be newly-increased policy information, The embodiment of the present invention is illustrated by taking newly-increased policy information as an example.Newly-increased policy information includes insurer's information and warrantee's letter Breath.Specifically, insurer's information includes essential information, contact method, supplemental information etc., wherein essential information includes insurer Age, insurer's name, insurer's gender etc., warrantee's information equally include essential information, contact method, supplemental information etc., Wherein, warrantee's essential information may include the relationship (throwing warrantee's relationship) of warrantee and insurer, warrantee's name, be protected People's type of credential and passport NO., warrantee's date of birth, warrantee's certificate validity period, warrantee's gender, warrantee's age, quilt Guarantor's occupation etc., can also be other information, and specific details are not described herein again.

It should be noted that newly-increased policy information can also include other insurance informations, for example, insurance type, insurance money Volume, insurance underwriting company etc., specifically herein without limitation.

103, tendency business information is determined according to Added Business information and preset historical operational information, is inclined to business information For being ranked up to the business information in data list.

Terminal determines tendency business information according to Added Business information and preset historical operational information, is inclined to business information For being ranked up to the business information in data list.Historical operational information can be history policy information, tendency business letter Breath, which can be user and insure, is inclined to product, and the embodiment of the present invention is carried out so that history policy information, user insure and be inclined to product as an example Explanation.Specifically, terminal analyzes newly-increased policy information and preset history policy information, preset history policy information It also may include that insurer's information and warrantee's information can determine difference when analyzing preset history policy information Information, for example, determine warrantee and insurer relationship, specifically, warrantee can be insurer, can also insure People parent matches occasionally children；In another example determine warrantee's age bracket, for example, under-18s, 18 to 30 (including 18, do not include , 30 to 60 30) (including 30, do not include 60), 60 to 70 (including 60, do not include 70), 70 with first-class；Determine warrantee's occupation and Insurer's occupation；Determine warrantee's work and inhabitation address；Determine insurer's work and inhabitation address；Finally obtained according to analysis Above-mentioned customer information and newly-increased policy information determine that user insures and be inclined to product.

104, business information is recommended to believe each business in data list according to tendency business information and preset history Breath is ranked up, and obtains the first sequence.

Terminal root is inclined to business information and preset history recommends business information to each business information in data list It is ranked up, obtains the first sequence.Preset history recommends business information to can be preset history recommended products, data list It can be product list, each business can be each insurance products, and the embodiment of the present invention is with preset history recommended products, production It is illustrated for product list, each insurance products.Specifically, terminal is insured according to determining user is inclined to product and preset History recommended products the recommendation of each insurance products has been determined, the preset history recommended products be business personnel forward direction The insurance products that user recommends, for example, business personnel once recommended finance product to user, but there is no buy by user； In another example business personnel once recommended savings product to user, user is successfully bought.Terminal is produced further according to each insurance The recommendation of product is ranked up according to sequence from big to small, obtains the first sequence.

It should be noted that the first sequence is ranked up according to the recommendation (ranking value of business) of each product, Different weight terms can be set, for example, two weight terms of setting, insure including user and be inclined to product and preset history recommendation Product, different weight terms assign different weight coefficients, shared in the same insurance products further according to each weight term Weight determines the specific recommendation of each insurance products, finally according to the size of recommendation (ranking value), according to from big to small Sequence is ranked up.

105, the first sequence is shown in data list.

First sequence is shown by terminal in data list.For example, terminal produces each insurance in product list Product are ranked up according to the first sequence, and finally obtained product list is shown at the terminal, so that user arranges in product It is seen in table according to first tactic multiple insurance products.

The embodiment of the present invention recommends business and the tendency business of each client according to history, different to each lead referral Business, be ranked up to obtain the first sequence according to the interaction probability sequence of business, the sequence for improving data list is quasi- True property, and then promote the purchase success rate of business.

Referring to Fig. 2, another flow chart of the sort method of data list provided in an embodiment of the present invention, specific to wrap It includes:

201, creation front end is buried a little, which buries a little for capturing the operation in terminal.

Wherein, it is as follows to bury concrete principle a little for code: when APP or interface are initialized, initializing third number formulary According to the Software Development Kit (software development kit, SDK) of Analysis Service quotient, then occur in some event When just calls the inside SDK, and data transmission interface sends data accordingly.For example, if thinking the click of some button inside statistics APP Number can call SDK to provide then when some button of APP is clicked inside the corresponding OnClick function of this button Data transmission interfaces send data.

202, acquisition Added Business information is buried by front end.

203, tendency business information is determined according to Added Business information and preset historical operational information, is inclined to business information For being ranked up to the business information in data list.

Terminal determines tendency business information according to Added Business information and preset historical operational information, is inclined to business information For being ranked up to the business information in data list.Historical operational information can be history policy information, tendency business letter Breath, which can be user and insure, is inclined to product, and the embodiment of the present invention is carried out so that history policy information, user insure and be inclined to product as an example Explanation.Specifically, when front end buries and a little detects that user enters data list by Added Business interface or draft interface, eventually End determines that the first business information, the first business information include business relationship, business man-year according to preset historical operational information Age and business people's occupation；Terminal determines the data form to match according to the first business information；Terminal is according to the number to match Determine that target service, target service are the highest business of frequency of interaction in the data form to match according to list；Terminal is by target Business is inclined to business as user.For example, when front end bury a little detect user by new single-throw guarantor interface or draft interface into When entering product list, terminal is determined according to preset history policy information throws warrantee's information, and throwing warrantee's information includes throwing quilt Guarantor's relationship, warrantee's age and throwing warrantee's occupation；Terminal determines the declaration form to match according to warrantee's information is thrown；Terminal Determine that target insurance products, target insurance products are the highest guarantor of declaration form China National Investment & Guaranty Corp. frequency to match according to the declaration form to match Dangerous product；Target insurance products are insured as user and are inclined to product by terminal.

A little detect that user protects interface by new single-throw or draft interface enters product it should be noted that burying when front end When list, terminal analyzes preset history policy information, preset history policy information include insurer's information and by Guarantor's information can determine different information when analyzing preset history policy information, for example, determine warrantee and The relationship of insurer, specifically, warrantee can be insurer, can with insurer parent, with occasionally children；Example again Such as, determine warrantee's age bracket, for example, under-18s, 18 to 30 (including 18, do not include 30), 30 to 60 (including 30, do not wrap Include 60), 60 to 70 (including 60, do not include 70), 70 with first-class；Determine warrantee's occupation and insurer's occupation；Determine warrantee Work and inhabitation address；Determine insurer's work and inhabitation address；Finally according to the obtained above-mentioned customer information of analysis and newly-increased Policy information determines that user insures and is inclined to product.

Optionally, when front end, which is buried, a little detects that user enters data list by business supermarket interface, business people is obtained The historical data list bought；A business is selected to be inclined to industry as user in the historical data list that business people has bought Business.For example, terminal obtains insurer and has purchased when front end buries and a little detects that user enters product list by product supermarket interface The insurance products list bought；Terminal selects an insurance products to throw as user in the insurance products list that insurer has bought Protect tendency product.

204, business information is recommended to believe each business in data list according to tendency business information and preset history Breath is ranked up, and obtains the first sequence.

Terminal root is inclined to business information and preset history recommends business information to each business information in data list It is ranked up, obtains the first sequence.Preset history recommends business to can be preset history recommended products, and data list can be with It is product list, each business can be each insurance products, and the embodiment of the present invention is arranged with preset history recommended products, product It is illustrated for table, each insurance products.Specifically, will be inclined to business information and preset history recommend business information as Weight order item；The first multiple correlation coefficient for calculating tendency business information and other weight order items, calculates preset history and pushes away Recommend the second multiple correlation coefficient of business information Yu other weight order items；The first reciprocal, root is generated according to the first multiple correlation coefficient It is reciprocal that second is generated according to the second multiple correlation coefficient；The first power of generation is normalized to the first inverse and the second inverse respectively Weight coefficient and the second weight coefficient, the first weight coefficient are the weight coefficient for being inclined to business information, and the second weight coefficient is preset History recommend business information weight coefficient；Terminal calculates each business according to the first weight coefficient and the second weight coefficient Ranking value；The ranking value of each business is ranked up by terminal according to sequence from big to small, obtains the first of each business Sequentially.For example, terminal, which insures user, is inclined to product and preset history recommended products as weight order item；Terminal is by user It insures and is inclined to product and preset history recommended products as weight order item；Calculating user, which insures, is inclined to product and other sequences First multiple correlation coefficient of weight term calculates the second complex phase relationship of preset history recommended products and other weight order items Number；Terminal generates the first inverse according to the first multiple correlation coefficient, and it is reciprocal to generate second according to the second multiple correlation coefficient；Terminal difference First inverse and the second inverse are normalized and generate the first weight coefficient and the second weight coefficient, the first weight coefficient It insures for user and is inclined to the weight coefficient of product, the second weight coefficient is the weight coefficient of preset history recommended products；Terminal The recommendation of each insurance products is calculated according to the first weight coefficient and the second weight coefficient；Terminal is pushed away each insurance products It recommends value to be ranked up according to sequence from big to small, obtains the first sequence of each insurance products.For example, if insurance products A First weight coefficient is 0.3, and the second weight coefficient is 0.7, then when the value of the first weight term is 100, the value of the second weight term When being 80, the calculation of recommendation are as follows: 0.3*100+0.7*80=86.If the first weight coefficient of insurance products B is 0.3, Second weight coefficient is 0.7, then when the value of the first weight term is 90, when the value of the second weight term is 90, the calculating of recommendation Mode are as follows: 0.3*90+0.7*90=90, then the recommendation of insurance products B is higher than the recommendation of insurance products A, insurance products B It comes before insurance products A, the calculating process of other insurance products is similar, and specific details are not described herein again.

Wherein, insurance products recommended to the user before preset history recommended products is business personnel, for example, business people Member once recommended finance product to user, but there is no buy by user；In another example business personnel once recommended to user Product is saved, user successfully buys.Terminal further according to each insurance products recommendation according to sequence from big to small into Row sequence obtains the first sequence.

205, the business hot value of each business is obtained, and the second sequence is determined according to the first sequence and business hot value.

Terminal obtains the business hot value of each business, and determines the second sequence according to the first sequence and business hot value. Specifically, terminal obtains the business hot value of each business in the first sequence；Terminal using the business hot value of each business as New weight order item；Terminal calculates the first multiple correlation coefficient of tendency business information and other weight order items, calculates preset History recommend business information and other weight order items the second multiple correlation coefficient, calculate business hot value and other sequence power The third multiple correlation coefficient of weight item；Terminal generates the first inverse according to the first multiple correlation coefficient, raw according to the second multiple correlation coefficient At the second inverse, it is reciprocal that third is generated according to third multiple correlation coefficient；Terminal respectively falls first reciprocal, the second inverse and third Number, which is normalized, generates the first new weight coefficient, new the second weight coefficient and new third weight coefficient, new First weight coefficient is the weight coefficient for being inclined to business information, and the second new weight coefficient is that preset history recommends business information Weight coefficient, new third weight coefficient be business hot value weight coefficient；Terminal is according to the first new weight coefficient, new The second weight coefficient and new third weight coefficient recalculate the new recommendation of each business；Terminal is new by each business Recommendation is ranked up according to sequence from big to small, obtains the second sequence.For example, terminal obtains each insurance in the first sequence The product hot value of product；Terminal is using product hot value as new weight order item；Terminal calculating user, which insures, is inclined to product With the first multiple correlation coefficient of other weight order items, the second of preset history recommended products and other weight order items is calculated Multiple correlation coefficient calculates the third multiple correlation coefficient of product hot value and other weight order items；Terminal is according to the first multiple correlation Coefficient generates the first inverse, generates the second inverse according to the second multiple correlation coefficient, generates third according to third multiple correlation coefficient and fall Number；Terminal is respectively to first reciprocal, second is reciprocal and third inverse is normalized and generates the first new weight coefficient, new The second weight coefficient and new third weight coefficient, the first new weight coefficient is that user insures and is inclined to the weight system of product Number, the second new weight coefficient are the weight coefficient of preset history recommended products, and new third weight coefficient is product temperature The weight coefficient of value；Terminal according to the first new weight coefficient, the second new weight coefficient and new third weight coefficient again Calculate the new recommendation of each insurance products；Terminal carries out the new recommendation of each insurance products according to sequence from big to small Sequence obtains the second sequence.For example, the second new weight coefficient is if the first new weight coefficient of insurance products A is 0.3 0.3, new third weight coefficient is 0.4, then the value of second weight term is 80 when the value of the first new weight term is 100, the When the value of three weight terms is 80, the calculation of new recommendation are as follows: 0.3*100+0.3*80+0.4*80=86.If insurance products B The first new weight coefficient be 0.3, the second new weight coefficient is 0.3, and new third weight coefficient is 0.4, then when new The value of the first weight term be 90, the value of the second weight term is 90, when the value of third weight term is 90, the calculating side of new recommendation Formula are as follows: 0.3*90+0.3*90+0.4*70=82.So in view of after product hot value, the new recommendation of insurance products B is than protecting The recommendation of dangerous product A is low, and insurance products B comes behind insurance products A, and the calculating process of other insurance products is similar, tool Details are not described herein again for body.

It should be noted that terminal can also be newly-increased using recommendation obtained in the first sequence as a weight term Product hot value is as another weight term, then redefines the weight coefficient of each weight term, and each insurance is calculated and produces The new recommendation of product, details are not described herein again for detailed process.

206, the first sequence or the second sequence are shown in data list.

First sequence or the second sequence are shown by terminal in data list.Specifically, behaviour of the terminal according to user It elects, for example, product hot value is not chosen if user uses default option, then terminal is by each guarantor in product list Dangerous product is ranked up according to the first sequence, and finally obtained product list is shown at the terminal, so that user is producing It is seen in product list according to first tactic multiple insurance products.In another example if user, which uses, chooses product hot value, that Each insurance products in product list are ranked up by terminal according to the second sequence, and finally obtained product list is shown Show at the terminal, so that user is seen in product list according to second tactic multiple insurance products.

Optionally, following steps can also be performed in terminal: the business that user pays close attention to is believed in the comparison operation in response to user Breath is marked, and obtains the business information of multiple labels；The business information of multiple labels is compared, comparison information is obtained, Comparison information includes insurance company, insurance period, way to pay dues, insured amount；By comparison information compared with preset button into Row association；When detecting that user clicks preset comparison button, comparison information is shown at the terminal.

The embodiment of the present invention recommends business and the tendency business of each client according to history, different to each lead referral Business, and recommend business, user to be inclined to business and business hot value according to history and obtain the first sequence and the second sequence, press It is ranked up to obtain the first sequence according to the interaction probability sequence of business or is ranked up to obtain the according to temperature sequence Two sequences improve the sequence accuracy of data list, and then promote the purchase success rate of business.

The sort method of data list in the embodiment of the present invention is described above, below in the embodiment of the present invention The collator of data list is described, referring to Fig. 3, in the embodiment of the present invention collator of data list a reality Applying example includes:

Creating unit 301 is buried a little for creating front end, and the front end is buried a little for capturing the operation in terminal；

First acquisition unit 302, for burying acquisition Added Business information by the front end；

Determination unit 303, for determining tendency business according to the Added Business information and preset historical operational information Information, the tendency business information is for being ranked up the business information in data list；

Sequencing unit 304, for recommending business information to arrange data according to the tendency business information and preset history Each business information in table is ranked up, and obtains the first sequence；

First display unit 305, for first sequence to be shown in the data list.

Referring to Fig. 4, another embodiment of the collator of data list includes: in the embodiment of the present invention

First display unit 305, for first sequence to be shown in the data list.

Optionally, determination unit 303 is specifically used for:

It is buried when the front end and a little detects that user enters the data list by Added Business interface or draft interface When, the first business information is determined according to the preset historical operational information, first business information include business relationship, Business man-year age and business people's occupation；The data form to match is determined according to first business information；According to the phase Matched data form determines target service information, and the target service is that frequency of interaction is most in the data form to match High business；Using the target service information as the tendency business information.

Optionally, determination unit 303 is specifically also used to:

When the front end, which is buried, a little detects that user enters the data list by business supermarket interface, business people is obtained The historical data list bought；A target service information is selected to make in the historical data list that the business people has bought To be inclined to business information.

Optionally, sequencing unit 304 is specifically used for:

Recommend business information as weight order item the tendency business information and preset history；Calculate the tendency First multiple correlation coefficient of business information and other weight order items calculates the preset history and recommends business information and other Second multiple correlation coefficient of weight order item；The first inverse is generated according to the first multiple correlation coefficient, according to the second multiple correlation coefficient It is reciprocal to generate second；Respectively to described first is reciprocal and second inverse be normalized generate the first weight coefficient and Second weight coefficient, first weight coefficient are the weight coefficient of the tendency business information, and second weight coefficient is The preset history recommends the weight coefficient of business information；According to first weight coefficient and the second weight coefficient meter Calculate the ranking value of each business；The ranking value of each business is ranked up according to sequence from big to small, is obtained each First sequence of a business.

Optionally, the collator of data list further include:

Second acquisition unit 306, for obtaining the business hot value of each business, and according to first sequence and described Business hot value determines the second sequence；

Second display unit 307, for showing second sequence in the data list.

Optionally, second acquisition unit 306 is specifically used for:

Obtain the business hot value of each business in first sequence；It is weighed the business hot value as new sequence Weight item；The first multiple correlation coefficient for calculating the tendency business information and other weight order items, calculates the preset history The second multiple correlation coefficient for recommending business information and other weight order items, calculates the business hot value and other weight orders The third multiple correlation coefficient of item；The first inverse is generated according to the first multiple correlation coefficient, generates second according to the second multiple correlation coefficient It is reciprocal to generate third according to third multiple correlation coefficient for inverse；Respectively to described first reciprocal, the described second reciprocal and described third Inverse, which is normalized, generates the first new weight coefficient, new the second weight coefficient and new third weight coefficient, institute The weight coefficient that the first new weight coefficient is the tendency business information is stated, the second new weight coefficient is described preset History recommend business information weight coefficient, the new third weight coefficient be the business hot value weight coefficient； It is recalculated often according to the first new weight coefficient, the second new weight coefficient and the new third weight coefficient The new recommendation of a business；The new recommendation of each business is ranked up according to sequence from big to small, obtains second Sequentially.

Optionally, the collator of data list further include:

Marking unit 308, the business information paid close attention to for the comparison operation in response to user user are marked, obtain The business information of multiple labels；

Comparing unit 309 is compared for the business information to the multiple label, obtains comparison information；

Associative cell 310, for button to be associated compared with preset by the comparison information；

Third display unit 311, for relatively being believed described when detecting that user clicks the preset comparison button Breath is shown on the terminal.

Angle of the above figure 3 to Fig. 4 from modular functionality entity fills the sequence of the data list in the embodiment of the present invention It sets and is described in detail, carried out below from sequencing equipment of the angle of hardware handles to data list in the embodiment of the present invention detailed Description.

Fig. 5 is a kind of structural schematic diagram of the sequencing equipment of data list provided in an embodiment of the present invention, the data list Sequencing equipment 500 can generate bigger difference because configuration or performance are different, may include one or more processing Device (central processing units, CPU) 501 (for example, one or more processors) and memory 509, one (such as one or more mass memories of storage medium 508 of a or more than one storage application program 507 or data 506 Equipment).Wherein, memory 509 and storage medium 508 can be of short duration storage or persistent storage.It is stored in storage medium 508 Program may include one or more modules (diagram does not mark), and each module may include setting to the sequence of data list Series of instructions operation in standby.Further, processor 501 can be set to communicate with storage medium 508, arrange in data The series of instructions operation in storage medium 508 is executed on the sequencing equipment 500 of table.

The sequencing equipment 500 of data list can also include one or more power supplys 502, one or more have Line or radio network interface 503, one or more input/output interfaces 504, and/or, one or more operation systems System 505, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD etc..Those skilled in the art can manage Solution, the restriction of the sequencing equipment structure of data list shown in Fig. 5 not sequencing equipment of structure paired data list, can wrap It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.Processor 501 can be held Creating unit 301, first acquisition unit 302, determination unit 303, sequencing unit 304, second obtain single in row above-described embodiment First 306, marking unit 308, the function of comparing unit 309 and associative cell 310.

It is specifically introduced below with reference to each component parts of the Fig. 5 to the sequencing equipment of data list:

Processor 501 is the control centre of the sequencing equipment of data list, can be according to the sequence of the data list of setting Method is handled.Processor 501 utilizes the various pieces of the sequencing equipment of various interfaces and the entire data list of connection, By running or execute the software program and/or module that are stored in memory 509, and calls and be stored in memory 509 Data, execute the sequencing equipment of data list various functions and processing data, to realize to different clients pointedly Recommend the purpose of insurance products.Storage medium 508 and memory 509 are all the carriers of storing data, in the embodiment of the present invention, are deposited Storage media 508 can refer to that storage volume is smaller, but fireballing built-in storage, and to can be storage volume big for memory 509, But the slow external memory of storage speed.

Memory 509 can be used for storing software program and module, and processor 501 is stored in memory 509 by operation Software program and module, thereby executing the various function application and data processing of the sequencing equipment 500 of data list.It deposits Reservoir 509 can mainly include storing program area and storage data area, wherein storing program area can storage program area, at least one Application program needed for a function (for example determine that user insures according to the newly-increased policy information and preset history policy information It is inclined to product) etc.；Storage data area, which can be stored, uses created data (such as front end according to the sequencing equipment of data list Bury a little etc.) etc..In addition, memory 509 may include high-speed random access memory, it can also include nonvolatile memory, A for example, at least disk memory, flush memory device or other volatile solid-state parts.It mentions in embodiments of the present invention The sort method program of the data list of confession and the data flow received store in memory, when it is desired to be used, processor 501 call from memory 509.

When loading on computers and executing the computer program instructions, entirely or partly generate according to of the invention real Apply process described in example or function.The computer can be general purpose computer, special purpose computer, computer network or its His programmable device.The computer instruction may be stored in a computer readable storage medium, or can from a computer Read storage medium transmitted to another computer readable storage medium, for example, the computer instruction can from a web-site, Computer, server or data center pass through wired (such as coaxial cable, optical fiber, twisted pair) or wireless (such as infrared, nothing Line, microwave etc.) mode transmitted to another web-site, computer, server or data center.It is described computer-readable Storage medium can be any usable medium that computer can store or include that one or more usable mediums are integrated The data storage devices such as server, data center.The usable medium can be magnetic medium, (for example, floppy disk, hard disk, magnetic Band), optical medium (for example, CD) or semiconductor medium (such as solid state hard disk (solid state disk, SSD)) etc..

It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description, The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.

In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit It closes or communicates to connect, can be electrical property, mechanical or other forms.

The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.

In addition, each functional unit in embodiments of the present invention can integrate in one processing unit, it is also possible to each A unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit was both It can take the form of hardware realization, can also realize in the form of software functional units.

If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words It embodies, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention Portion or part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic or disk etc. are various can store program The medium of code.

The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.

Claims

1. a kind of sort method of data list characterized by comprising

Creation front end is buried a little, and the front end is buried a little for capturing the operation in terminal；

Acquisition Added Business information is buried by the front end；

Tendency business information, the tendency business information are determined according to the Added Business information and preset historical operational information For being ranked up to the business information in data list；

Business information is recommended to believe each business in the data list according to the tendency business information and preset history Breath is ranked up, and obtains the first sequence；

First sequence is shown in the data list.

2. the sort method of data list according to claim 1, which is characterized in that described to be believed according to the Added Business Breath and preset historical operational information determine that tendency business information, the tendency business information are used for the business in data list Information, which is ranked up, includes:

When the front end, which is buried, a little detects that user enters the data list by Added Business interface or draft interface, root Determine that the first business information, first business information include business relationship, business according to the preset historical operational information Man-year age and business people's occupation；

The data form to match is determined according to first business information；

Determine that target service information, the target service are the tables of data to match according to the data form to match The highest business of frequency of interaction in list；

Using the target service information as the tendency business information.

3. the sort method of data list according to claim 1, which is characterized in that described to be believed according to the Added Business Breath and preset historical operational information determine that tendency business information includes:

When the front end, which is buried, a little detects that user enters the data list by business supermarket interface, obtains business people and purchased The historical data list bought；

Select a target service information as tendency business information in the historical data list that the business people has bought.

4. the sort method of data list according to claim 1, which is characterized in that described to be believed according to the tendency business Breath and preset history recommend business information to be ranked up each business information in the data list, obtain the first sequence Include:

Recommend business information as weight order item the tendency business information and preset history；

The first multiple correlation coefficient for calculating the tendency business information and other weight order items, calculates the preset history and pushes away Recommend the second multiple correlation coefficient of business information Yu other weight order items；

The first inverse is generated according to the first multiple correlation coefficient, it is reciprocal to generate second according to the second multiple correlation coefficient；

The first weight coefficient and the second weight are generated to the described first reciprocal be normalized with second inverse respectively Coefficient, first weight coefficient are the weight coefficient of the tendency business information, and second weight coefficient is described preset History recommend business information weight coefficient；

The ranking value of each business is calculated according to first weight coefficient and second weight coefficient；

The ranking value of each business is ranked up according to sequence from big to small, obtains the first sequence of each business.

5. the sort method of data list according to claim 4, which is characterized in that the method also includes:

The business hot value of each business is obtained, and the second sequence is determined according to first sequence and the business hot value；

Second sequence is shown in the data list.

6. the sort method of data list according to claim 5, which is characterized in that the business for obtaining each business Hot value, and determine that the second sequence includes: according to first sequence and the business hot value

Obtain the business hot value of each business in first sequence；

Using the business hot value as new weight order item；

The first multiple correlation coefficient for calculating the tendency business information and other weight order items, calculates the preset history and pushes away The second multiple correlation coefficient for recommending business information Yu other weight order items calculates the business hot value and other weight order items Third multiple correlation coefficient；

The first inverse is generated according to the first multiple correlation coefficient, the second inverse is generated according to the second multiple correlation coefficient, it is multiple according to third It is reciprocal that related coefficient generates third；

Described first reciprocal, the described second reciprocal and described third inverse is normalized respectively and generates the first new power Weight coefficient, new the second weight coefficient and new third weight coefficient, the first new weight coefficient are the tendency business The weight coefficient of information, the second new weight coefficient are the weight coefficient that the preset history recommends business information, institute State the weight coefficient that new third weight coefficient is the business hot value；

It is counted again according to the first new weight coefficient, the second new weight coefficient and the new third weight coefficient Calculate the new recommendation of each business；

The new recommendation of each business is ranked up according to sequence from big to small, obtains the second sequence.

7. the sort method of data list according to any one of claims 1-4, which is characterized in that the method is also wrapped It includes:

The business information that user is paid close attention in comparison operation in response to user is marked, and obtains the business information of multiple labels；

The business information of the multiple label is compared, comparison information is obtained；

By the comparison information, button is associated compared with preset；

When detecting that user clicks the preset comparison button, the comparison information is shown on the terminal.

8. a kind of collator of data list characterized by comprising

Creating unit is buried a little for creating front end, and the front end is buried a little for capturing the operation in terminal；

First acquisition unit, for burying acquisition Added Business information by the front end；

Determination unit, for determining tendency business information, institute according to the Added Business information and preset historical operational information Tendency business information is stated for being ranked up to the business information in data list；

Sequencing unit, for recommending business information to each in data list according to the tendency business information and preset history A business information is ranked up, and obtains the first sequence；

First display unit, for first sequence to be shown in the data list.

9. a kind of sequencing equipment of data list, which is characterized in that including memory, processor and be stored on the memory And the computer program that can be run on the processor, it is realized when the processor executes the computer program as right is wanted Seek the sort method of data list described in any one of 1-7.

10. a kind of computer readable storage medium, which is characterized in that including instruction, when described instruction is run on computers, So that computer executes the sort method of the data list as described in any one of claim 1-7.