CN109727056A - Financial institution's recommended method, equipment, storage medium and device - Google Patents
Financial institution's recommended method, equipment, storage medium and device Download PDFInfo
- Publication number
- CN109727056A CN109727056A CN201810747893.4A CN201810747893A CN109727056A CN 109727056 A CN109727056 A CN 109727056A CN 201810747893 A CN201810747893 A CN 201810747893A CN 109727056 A CN109727056 A CN 109727056A
- Authority
- CN
- China
- Prior art keywords
- user
- financial institution
- point set
- historical
- interest point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of financial institution's recommended method, equipment, storage medium and devices, evaluate this method comprises: obtaining historical user the historical user of each financial institution undetermined in preset range, extract historical interest point set from historical user's evaluation；Target user's evaluation that target user is extracted from historical user's evaluation, extracts target interest point set from target user's evaluation, historical user includes target user；Destination financial mechanism is determined by Collaborative Filtering Recommendation Algorithm according to historical interest point set and target interest point set；Destination financial mechanism is pushed into target user.In the present invention, according to the historical interest point set and target interest point set extracted from historical user's evaluation, destination financial mechanism is determined by Collaborative Filtering Recommendation Algorithm, so that the destination financial mechanism for pushing to target user more meets user demand, more useful information is pushed for user, improves user experience.
Description
Technical field
The present invention relates to the technical field of information push more particularly to a kind of financial institution's recommended method, equipment, storage Jie
Matter and device.
Background technique
When user needs processes financial business, existing map search is that general will search for content with user and match
The address of financial institution recommend user, without finance such as the specific requirements according to user, such as insurance, stock or bank
Field predetermined search word is that user recommends more useful content, and user needs to search symbol again in the financial institution address of recommendation
The address information of the financial institution of self-demand is closed, low efficiency, only user is not from the address information of the financial institution of recommendation
The financial institution for meeting self-demand can be filtered out well.Therefore, how to recommend the finance for more meeting user demand for user
The address of mechanism is a technical problem to be solved urgently.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of financial institution's recommended method, equipment, storage medium and devices, it is intended to
Not the technical issues of financial institution for solving to recommend in the prior art for user is not able to satisfy the specific requirements of user.
To achieve the above object, the present invention provides a kind of financial institution's recommended method, financial institution's recommended method packet
Include following steps:
It obtains historical user to evaluate the historical user of each financial institution undetermined in preset range, from the historical user
Historical interest point set is extracted in evaluation；
Target user's evaluation that target user is extracted from historical user evaluation, from target user evaluation
Target interest point set is extracted, the historical user includes the target user；
Mesh is determined by Collaborative Filtering Recommendation Algorithm according to the historical interest point set and the target interest point set
Mark financial institution；
The destination financial mechanism is pushed into the target user.
Preferably, described that collaborative filtering recommending is passed through according to the historical interest point set and the target interest point set
Algorithm determines destination financial mechanism, comprising:
Passed through described in the calculating of the first similarity formula according to the historical interest point set and the target interest point set
The first similarity between the first user in target user and each historical user other than the target user；
Select first user of the first preset quantity as second according to the first similarity descending order
User；
The second user is evaluated into highest financial institution undetermined as destination financial according to historical user evaluation
Mechanism.
Preferably, described public by the first similarity according to the historical interest point set and the target interest point set
Formula calculates between the target user and the first user in each historical user other than the target user first similar
Degree, comprising:
Count the common interest point set of the historical interest point set Yu the target interest point set；
Pass through first according to the common interest point set, the historical interest point set and the target interest point set
Similarity formula calculates between the first user in the target user and each historical user other than the target user
First similarity.
Preferably, the common interest point set of statistics the historical interest point set and the target interest point set
Later, financial institution's recommended method further include:
Obtain the access frequency of each financial institution in the common interest point set；
It is described to be passed through according to the common interest point set, the historical interest point set and the target interest point set
First similarity formula calculate the first user in the target user and each historical user other than the target user it
Between the first similarity, comprising:
According to the access frequency, the common interest point set, the historical interest point set and the target interest
Point set is calculated in the target user and each historical user other than the target user by the first similarity formula
The first similarity between first user.
Preferably, described to be made the highest financial institution undetermined of second user evaluation according to historical user evaluation
For destination financial mechanism, comprising:
The second user is evaluated into highest financial institution undetermined as gold to be chosen according to historical user evaluation
Melt mechanism；
The financial institution to be chosen that the target user has not visited is chosen as destination financial mechanism.
Preferably, described that collaborative filtering recommending is passed through according to the historical interest point set and the target interest point set
Algorithm determines destination financial mechanism, comprising:
The target user is extracted from the target interest point set evaluates highest financial institution undetermined as the
One financial institution；
The second gold medal in first financial institution and the historical interest point set is calculated by the second similarity formula
Melt the second similarity between mechanism；
According to the second similarity descending order select second financial institution of the second preset quantity as
Destination financial mechanism.
Preferably, the second similarity formula that passes through calculates first financial institution and the historical interest point set
In the second financial institution between the second similarity, comprising:
Obtain each first type of business of first financial institution, and obtain in the historical interest point set second
Each second type of business of financial institution；
Count the common service type of first type of business and second type of business；
Obtain the probability that the common service type occurs in the financial institution undetermined；
Passed through according to the probability, the common service type, first type of business and second type of business
Second similarity formula calculates between the second financial institution in first financial institution and the historical interest point set
Second similarity.
In addition, to achieve the above object, the present invention also proposes a kind of financial institution's recommendation apparatus, the financial institution is recommended
Equipment includes that the financial institution that can run on the memory and on the processor of memory, processor and being stored in is recommended
The step of program, financial institution's recommended program is arranged for carrying out financial institution's recommended method as described above.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, finance is stored on the storage medium
Mechanism recommended program, financial institution's recommended program realize recommendation side, financial institution as described above when being executed by processor
The step of method.
In addition, to achieve the above object, the present invention also proposes a kind of financial institution's recommendation apparatus, the financial institution is recommended
Device includes: to obtain module, extraction module, determining module and pushing module；
The acquisition module comments the historical user of each financial institution undetermined in preset range for obtaining historical user
Valence extracts historical interest point set from historical user evaluation；
The extraction module, for extracting target user's evaluation of target user from historical user evaluation, from
Target interest point set is extracted in target user's evaluation, the historical user includes the target user；
The determining module was cooperateed with for being passed through according to the historical interest point set with the target interest point set
Filter proposed algorithm determines destination financial mechanism；
The pushing module, for the destination financial mechanism to be pushed to the target user.
In the present invention, the historical user of each financial institution undetermined in preset range is evaluated by obtaining historical user,
Historical interest point set is extracted from historical user evaluation, extracts target user's from historical user evaluation
Target user's evaluation extracts target interest point set from target user evaluation, and the historical user includes the mesh
User is marked, the historical interest point set embodies the preference of historical user, and the target interest point set embodies the mesh
The preference of user is marked, then Collaborative Filtering Recommendation Algorithm is passed through according to the historical interest point set and the target interest point set
Determine that destination financial mechanism, the destination financial mechanism more meet the preference of the target user, by the destination financial mechanism
The target user is pushed to, the destination financial mechanism more meets user demand, has pushed more useful information for user, has mentioned
High user experience.
Detailed description of the invention
Fig. 1 is the structural representation of the financial institution's recommendation apparatus for the hardware running environment that the embodiment of the present invention is related to
Figure；
Fig. 2 is the flow diagram of financial institution's recommended method first embodiment of the present invention；
Fig. 3 is the flow diagram of financial institution's recommended method second embodiment of the present invention；
Fig. 4 is the flow diagram of financial institution's recommended method 3rd embodiment of the present invention；
Fig. 5 is the structural block diagram of financial institution's recommendation apparatus first embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the financial institution's recommendation apparatus structure for the hardware running environment that the embodiment of the present invention is related to
Schematic diagram.
As shown in Figure 1, financial institution's recommendation apparatus may include: processor 1001, such as central processing unit
(Central Processing Unit, CPU), communication bus 1002, customer interface 1003, network interface 1004, memory
1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.Customer interface 1003 may include display
Shield (Display), optional customer interface 1003 can also include standard wireline interface and wireless interface, for customer interface
1003 wireline interface can be USB interface in the present invention.Network interface 1004 optionally may include standard wireline interface,
Wireless interface (such as Wireless Fidelity (WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random of high speed
Memory (Random Access Memory, RAM) memory is accessed, stable memory (Non-volatile is also possible to
Memory, NVM), such as magnetic disk storage.Memory 1005 optionally can also be the storage independently of aforementioned processor 1001
Device.
It will be understood by those skilled in the art that structure shown in Fig. 1 does not constitute the limit to financial institution's recommendation apparatus
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
As shown in Figure 1, regarding as in the memory 1005 of computer storage medium a kind of may include operating system, network
Communication module, customer interface module and financial institution's recommended program.
In financial institution's recommendation apparatus shown in Fig. 1, network interface 1004 is mainly used for connecting background server, with institute
It states background server and carries out data communication；Customer interface 1003 is mainly used for connecting the client；The financial institution is recommended
Equipment calls the financial institution's recommended program stored in memory 1005 by processor 1001, and executes the embodiment of the present invention and mention
Financial institution's recommended method of confession.
Based on above-mentioned hardware configuration, the embodiment of financial institution's recommended method of the present invention is proposed.
It is the flow diagram of financial institution's recommended method first embodiment of the present invention referring to Fig. 2, Fig. 2, proposes the present invention
Financial institution's recommended method first embodiment.
In the first embodiment, financial institution's recommended method the following steps are included:
Step S10: obtaining historical user and evaluate the historical user of each financial institution undetermined in preset range, from described
Historical interest point set is extracted in historical user's evaluation.
It should be understood that the executing subject of the present embodiment is financial institution's recommendation apparatus, wherein the financial institution is recommended
Equipment can be the electronic equipments such as PC, server.The preset range can pass through the gold according to self-demand by user
Melt mechanism recommendation apparatus to be configured, for example the preset range can be city locating for the target user.It is gone through in acquisition
Before history user is to historical user's evaluation of each financial institution undetermined in preset range, it can be user and pass through the financial machine
Financial institution's search instruction of structure recommendation apparatus triggering can also be the financial institution search of background server clocked flip
Instruction, in response to financial institution's search instruction, extracts the preset range from financial institution's search instruction, then
It executes the acquisition historical user to evaluate the historical user of each financial institution undetermined in preset range, from the historical user
Historical interest point set is extracted in evaluation.
It will be appreciated that can be using all financial institutions that can be searched in the preset range as the finance undetermined
Mechanism, historical user's evaluation refer to all historical users for browsing the financial institution undetermined to the finance undetermined
The evaluation that mechanism is made, historical user's evaluation include the various businesses type and/or clothes to the financial institution undetermined
The evaluation of attitude of being engaged in etc..The historical interest point set refers to the preference file of the historical user, can use from the history
The historical user is obtained in the browsing record and/or purchaser record at family to evaluate the historical user of each financial institution undetermined, from
The point of interest of each historical user is extracted in historical user's evaluation.From the historical user of each historical user evaluation
A point of interest (Point of Interest, write a Chinese character in simplified form PoI) is extracted, the historical interest point set is constituted.It is respectively gone through to identify
The point of interest of history user, track anchor point and transfer point can be used, and (Stop and Moves of Trajectories, writes a Chinese character in simplified form
SMoT) method, the SMoT method are evaluated as inputting with the historical user, export the history of each historical user
A core evaluation point in user's evaluation is as point of interest.
Step S20: target user's evaluation of target user is extracted from historical user evaluation, is used from the target
Target interest point set is extracted in the evaluation of family, the historical user includes the target user.
In the concrete realization, the historical user is all users for browsing financial institution's relevant information undetermined,
The target user is a user in the historical user.Historical user's evaluation includes the target of the target user
User's evaluation, each historical user have unique user identifier, can be identified by the target user of the target user from institute
It states and finds target user's evaluation corresponding with target user mark in historical user's evaluation.The usual target user comments
Valence may have the point of interest a plurality of, one core evaluation point of extraction is evaluated as this from the evaluation of target user described in every,
The a plurality of target user evaluates corresponding multiple points of interest, constitutes the target interest point set.
Step S30: it is calculated according to the historical interest point set and the target interest point set by collaborative filtering recommending
Method determines destination financial mechanism.
It should be noted that the Collaborative Filtering Recommendation Algorithm is emerging according to the historical interest point set and the target
Interesting point set creates the exclusive recommendation of the target user.Including the collaborative filtering (User-based based on user
CollaboratIve filtering) algorithm and collaborative filtering (the Item-based collaboratIve based on article
Filtering) algorithm, the user are the historical user, and the article is the financial institution undetermined.
It should be understood that the collaborative filtering based on the historical user includes: that each history of analysis is used
The historical user of the financial institution undetermined is evaluated at family, obtains the historical interest point set；It is emerging according to the history
Interesting point set is calculated other history in the target user and the historical user other than the target user and uses
Similarity between family；Select the historical user with higher first preset quantity of target user's similarity；By institute
The finance undetermined stating the evaluation highest of the historical user of the first preset quantity and the target user and not browsing
Mechanism recommends the target user.
It will be appreciated that the collaborative filtering based on the financial institution undetermined includes: to go through described in analysis is each
History user evaluates the historical user of the financial institution undetermined, obtains the historical interest point set；It is gone through according to described in
The analysis of history interest point set obtains the similarity between the financial institution undetermined in the historical interest point set；According to the mesh
Mark point of interest determines the highest financial institution undetermined of the evaluation of the target user, finds out and the highest financial institution of evaluation
Financial institution undetermined described in highest second preset quantity of similarity；By described in highest second preset quantity of the similarity to
Determine financial institution and recommends the target user.
Step S40: the destination financial mechanism is pushed into the target user.
In the concrete realization, the destination financial mechanism that will be screened by the Collaborative Filtering Recommendation Algorithm, base
It is evaluated in historical user of the historical user to the financial institution undetermined in preset range, combines the mesh of the target user
The destination financial machine can be obtained so that the destination financial mechanism more meets the demand of the target user by marking user's evaluation
The relevant information of structure, such as address information and main business information etc. push away the relevant information of the destination financial mechanism
It send to the target user, so that the target user is quickly found out the mesh by the relevant information of the destination financial mechanism
Mark financial institution carries out handling for relevant financial business.
In the first embodiment, by obtaining historical user to the historical user of each financial institution undetermined in preset range
Evaluation extracts historical interest point set from historical user evaluation, extracts target from historical user evaluation
The target user of user evaluates, and extracts target interest point set from target user evaluation, the historical user includes
The target user, the historical interest point set embody the preference of historical user, and the target interest point set embodies
The preference of the target user is then pushed away with the target interest point set by collaborative filtering according to the historical interest point set
It recommends algorithm and determines that destination financial mechanism, the destination financial mechanism more meet the preference of the target user, by the target gold
Melt mechanism and push to the target user, the destination financial mechanism more meets user demand, has pushed for user more useful
Information improves user experience.
It is the flow diagram of financial institution's recommended method second embodiment of the present invention referring to Fig. 3, Fig. 3, is based on above-mentioned Fig. 2
Shown in first embodiment, propose the second embodiment of financial institution's recommended method of the present invention.
In a second embodiment, the step S30, comprising:
Step S301: the first similarity formula is passed through according to the historical interest point set and the target interest point set
Calculate the first similarity between the first user in the target user and each historical user other than the target user.
It will be appreciated that the present embodiment proposition determines the target gold based on the collaborative filtering of the historical user
Melt mechanism.The historical interest point set, which is combined into, extracts corresponding one from every historical user's evaluation of each historical user
The set that a point of interest is constituted, each point of interest extracted generally include the unique identification letter of corresponding financial institution undetermined
The information such as breath, the business of the grade of evaluation and evaluation or service.The target interest point set is from the every of the target user
The set that a corresponding point of interest is constituted is extracted in the evaluation of target user described in item, each point of interest extracted usually wraps
Include unique identification information, the grade of evaluation and the information such as the business of evaluation or service of corresponding financial institution undetermined.Can then it lead to
It crosses the historical interest point set and the target interest point set calculates in the target user and each historical user in addition to institute
State the first similarity between the first user except target user.
Further, the step S301, comprising:
Count the common interest point set of the historical interest point set Yu the target interest point set；
Pass through first according to the common interest point set, the historical interest point set and the target interest point set
Similarity formula calculates between the first user in the target user and each historical user other than the target user
First similarity.
It should be understood that the first similarity formula are as follows:
Wherein, | POISa| and | POISb| the interest point set that historical user a and target user b are browsed is respectively indicated, |
POISa,b| indicate the common interest point set of the historical user a and the target user b while browsing.It is found that according to
The common interest point set, the historical interest point set and the target interest point set are public by first similarity
Formula can calculate the first phase between the target user and the first user in each historical user other than the target user
Like degree.
Further, the common interest point set of statistics the historical interest point set and the target interest point set
After conjunction, further includes:
Obtain the access frequency of each financial institution in the common interest point set；
It is described to be passed through according to the common interest point set, the historical interest point set and the target interest point set
First similarity formula calculate the first user in the target user and each historical user other than the target user it
Between the first similarity, comprising:
According to the access frequency, the common interest point set, the historical interest point set and the target interest
Point set is calculated in the target user and each historical user other than the target user by the first similarity formula
The first similarity between first user.
In the concrete realization, if to have browsed a historical user described in only a few together clear by two historical users
The financial institution undetermined look at, then the similarity between them be certain to have browsed many people together than them it is all clear
The similarity for the financial institution undetermined look at wants high.A such as financial institution undetermined visited by many historical users
A does not represent the history and uses if it find that historical user a and historical user b has visited the financial institution A undetermined simultaneously
There is very high similarity between family a and the historical user b, because the financial institution A undetermined may be the preset range
Interior mark post financial institution, many people can select to browse, and a financial institution undetermined seldom browsed by people, if
The historical user a and historical user b is visited simultaneously, then the preference similarity between them will be very high.Therefore,
The visit frequency of one financial institution undetermined also can be taken into account when measuring similarity.Here be joined it is described
The calculating formula of similarity of financial institution's access frequency undetermined, that is to say, that the first similarity formula may also is that
Wherein, | POISa| and | POISb| the interest point set that historical user a and target user b are visited is respectively indicated, |
POISa,b| the common interest point set for indicating the historical user a and the target user b while visiting, FpIndicate to
Determine the flat rate of access of financial institution p.It is found that according to the access frequency, the common interest point set, historical interest point
Set and the target interest point set by the first similarity formula calculate in the target user and each historical user in addition to
The first similarity between the first user except the target user.
Step S302: first user of the first preset quantity is selected according to the first similarity descending order
As second user.
It should be noted that the corresponding historical user of bigger explanation first similarity of first similarity with it is described
The demand and hobby of target user is closer, first similarity is arranged according to descending order, according to described first
Similarity descending order selects first user of the first preset quantity as second user, then the second user is
With the historical user of most similar first preset quantity of the target user in the historical user, the second user is to each
The evaluation of financial institution undetermined also best embodies the intention of the target user.
Step S303: according to historical user evaluation using the second user evaluate highest financial institution undetermined as
Destination financial mechanism.
It should be understood that historical user's evaluation includes evaluation of all historical users to each financial institution undetermined, then
The second user evaluation that the second user is made is found from historical user evaluation, and the second user is evaluated
Highest financial institution undetermined is as the destination financial mechanism, to guarantee that the destination financial mechanism recommended can be accorded with more
The demand of the target user is closed, and has preferable public praise to guarantee, to promote the experience of the target user.
Further, the step S303, comprising:
The second user is evaluated into highest financial institution undetermined as gold to be chosen according to historical user evaluation
Melt mechanism；
The financial institution to be chosen that the target user has not visited is chosen as destination financial mechanism.
It will be appreciated that mesh described in the relevant information for the financial institution to be chosen that the usual target user accessed
Mark user knows quite well, target user's current search financial institution be more intended to understand other do not accessed it is described
Whether financial institution undetermined has better choice, then the second user will be evaluated to highest financial institution undetermined as to be selected
Take financial institution, then from it is described wait choose chosen in financial institution the target user have not visited described in wait choose financial machine
Structure can more meet the current demand of the target user as destination financial mechanism.
It is public by the first similarity according to the historical interest point set and the target interest point set in the present embodiment
Formula calculates between the target user and the first user in each historical user other than the target user first similar
Degree selects first user of the first preset quantity as second user according to the first similarity descending order,
The bigger demand and hobby for illustrating first similarity corresponding historical user and the target user of first similarity
It is closer, the second user is evaluated as destination financial machine by highest financial institution undetermined according to historical user evaluation
Structure to guarantee that the destination financial mechanism recommended can more meet the demand of the target user, and has preferable public praise
Guarantee, to promote the experience of the target user.
It is the flow diagram of financial institution's recommended method 3rd embodiment of the present invention referring to Fig. 4, Fig. 4, is based on above-mentioned Fig. 2
Shown in first embodiment, propose the 3rd embodiment of financial institution's recommended method of the present invention.
In the third embodiment, the step S30, comprising:
Step S304: the highest financial machine undetermined of target user's evaluation is extracted from the target interest point set
Structure is as the first financial institution.
It should be understood that the present embodiment proposes to determine the mesh based on the collaborative filtering of the financial institution undetermined
Mark financial institution.The target interest point set is evaluation point most crucial in every evaluation of the target user, is usually wrapped
Include the information such as the unique identification information of financial institution undetermined of evaluation, the business of the grade of evaluation and evaluation or service.The mesh
The mark highest financial institution undetermined of user's evaluation is usually best suitable for the demand and preference of the target user, by the target user
Highest financial institution undetermined is evaluated as first financial institution, then first financial institution can represent the target
The demand of user.
Step S305: it is calculated in first financial institution and the historical interest point set by the second similarity formula
The second financial institution between the second similarity.
It will be appreciated that can be by obtaining all first types of business of first financial institution, and obtain described the
The second all types of business of two financial institutions pass through described according to first type of business and second type of business
Second similarity formula calculates between the second financial institution in first financial institution and the historical interest point set
Second similarity.The second similarity formula are as follows:
Wherein, | POISc| and | POISd| respectively indicate the first financial institution c and the second financial institution d corresponding described
One type of business and second type of business, | POISc,d| indicate the first financial institution c and the second financial institution d
Common service type.It is found that logical according to first type of business, second type of business and the common service type
First phase between first financial institution and second financial institution can be calculated by crossing the second similarity formula
Like degree.
Further, the step S305, comprising:
Obtain each first type of business of first financial institution, and obtain in the historical interest point set second
Each second type of business of financial institution；
Count the common service type of first type of business and second type of business；
Obtain the probability that the common service type occurs in the financial institution undetermined；
Passed through according to the probability, the common service type, first type of business and second type of business
Second similarity formula calculates between the second financial institution in first financial institution and the historical interest point set
Second similarity.
In the concrete realization, if first financial institution and second financial institution include one and waited for by only a few
Determine common service type possessed by financial institution, then the similarity between them be certain to than they it is common have one very
The similarity for the type of business that the mostly described financial institution undetermined all has wants high.Such as a kind of type of business B be it is many described to
The type of business that financial institution all has is determined, if it find that the first financial institution c and the second financial institution d are wrapped simultaneously
Include the type of business B, do not represent have between the first financial institution c and the second financial institution d it is very high
Similarity, because the type of business B may be the conversational traffic type in the preset range, many financial institutions undetermined are all
Including the type of business B, and the type of business C that the financial institution undetermined of a very few has, if described first
Financial institution c and the second financial institution d includes simultaneously the type of business C, then the first financial institution c and described
Preference similarity between second financial institution d will be very high.Therefore, the common service type is in each financial institution undetermined
The probability occurred in all types of business also can be taken into account when measuring similarity.Here be joined it is described to
Deposit melts the calculating formula of similarity for occurring the probability of the common service type in machine, that is to say, that second similarity
Formula may also is that
Wherein, | POISc| and | POISd| respectively indicate the first financial institution c and the second financial institution d corresponding described
One type of business and second type of business, | POISc,d| indicate the first financial institution c and the second financial institution d
Common service type, FmIndicate the probability that the common service type m occurs in the financial institution undetermined.It is found that root
Pass through above-mentioned second phase according to the probability, first type of business, second type of business and the common service type
First similarity between first financial institution and second financial institution can be calculated like degree formula.
Step S306: second finance of the second preset quantity is selected according to the second similarity descending order
Mechanism is as destination financial mechanism.
It should be noted that bigger corresponding second financial institution of explanation of the second similarity and first gold medal
Type of business or the service for melting mechanism are closer, and first financial institution is that the target user evaluates highest finance undetermined
Mechanism, so bigger second financial institution of second similarity more meets the demand and preference of the target user,
Select second financial institution of the second preset quantity as destination financial according to the second similarity descending order
Mechanism, to guarantee that the destination financial mechanism more meets the demand and preference of the target user, by the destination financial machine
The relevant information of structure pushes to the target user, is able to ascend the experience of the target user.
In the third embodiment, it is highest undetermined that target user's evaluation is extracted from the target interest point set
Financial institution calculates first financial institution and the historical interest as the first financial institution, by the second similarity formula
The second similarity between the second financial institution in point set, according to the second similarity descending order selection second
Second financial institution of preset quantity is as destination financial mechanism, so that it is described to guarantee that the destination financial mechanism more meets
The relevant information of the destination financial mechanism is pushed to the target user, is able to ascend by the demand and preference of target user
The experience of the target user.
In addition, the embodiment of the present invention also proposes a kind of storage medium, financial institution's recommendation is stored on the storage medium
Program, financial institution's recommended program realize the step of financial institution's recommended method as described above when being executed by processor
Suddenly.
In addition, the embodiment of the present invention also proposes a kind of financial institution's recommendation apparatus referring to Fig. 5, the financial institution is recommended
Device includes: to obtain module 10, extraction module 20, determining module 30 and pushing module 40；
The acquisition module 10, for obtaining historical user to the historical user of each financial institution undetermined in preset range
Evaluation extracts historical interest point set from historical user evaluation；
The extraction module 20, for extracting target user's evaluation of target user from historical user evaluation,
Target interest point set is extracted from target user evaluation, the historical user includes the target user；
The determining module 30 is cooperateed with for being passed through according to the historical interest point set with the target interest point set
Filtering recommendation algorithms determine destination financial mechanism；
The pushing module 40, for the destination financial mechanism to be pushed to the target user.
In one embodiment, financial institution's recommendation apparatus further include: computing module and selecting module；
The computing module, for passing through the first phase according to the historical interest point set and the target interest point set
The between the first user in the target user and each historical user other than the target user is calculated like degree formula
One similarity；
The selecting module, for being selected described in the first preset quantity according to the first similarity descending order
First user is as second user；
The determining module 30 is also used to be evaluated according to the historical user that second user evaluation is highest undetermined
Financial institution is as destination financial mechanism.
In one embodiment, financial institution's recommendation apparatus further include: statistical module；
The statistical module, for counting the common interest of the historical interest point set Yu the target interest point set
Point set；
The computing module is also used to according to the common interest point set, the historical interest point set and the mesh
Interest point set is marked to calculate in the target user and each historical user by the first similarity formula in addition to the target user
Except the first user between the first similarity.
In one embodiment, the acquisition module 10 is also used to obtain each financial machine in the common interest point set
The access frequency of structure；
The computing module is also used to according to the access frequency, the common interest point set, historical interest point
Set and the target interest point set by the first similarity formula calculate in the target user and each historical user in addition to
The first similarity between the first user except the target user.
In one embodiment, financial institution's recommendation apparatus further include: choose module；
The determining module 30 is also used to be evaluated according to the historical user that second user evaluation is highest undetermined
Financial institution is as financial institution to be chosen；
The selection module, for choose the target user have not visited described in financial institution to be chosen as target
Financial institution.
In one embodiment, the determining module 30 is also used to extract the mesh from the target interest point set
The highest financial institution undetermined of user's evaluation is marked as the first financial institution；
The computing module is also used to calculate first financial institution by the second similarity formula and the history is emerging
The second similarity between the second financial institution in interesting point set；
The determining module 30 is also used to select the second preset quantity according to the second similarity descending order
Second financial institution is as destination financial mechanism.
In one embodiment, financial institution's recommendation apparatus further include:
The acquisition module 10 is also used to obtain each first type of business of first financial institution, and described in acquisition
Each second type of business of the second financial institution in historical interest point set；
The statistical module is also used to count the common service kind of first type of business and second type of business
Class；
The acquisition module 10, be also used to obtain the common service type occur in the financial institution undetermined it is general
Rate；
The computing module is also used to according to the probability, the common service type, first type of business and institute
The second type of business is stated to calculate in first financial institution and the historical interest point set by the second similarity formula
The second similarity between second financial institution.
The other embodiments or specific implementation of financial institution's recommendation apparatus of the present invention can refer to above-mentioned each method
Embodiment, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.If listing equipment for drying
Unit claim in, several in these devices, which can be, to be embodied by the same item of hardware.Word first,
Second and the use of third etc. do not indicate any sequence, can be title by these word explanations.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
(such as read-only memory mirror image (Read Only Memory image, ROM)/random access memory (Random Access
Memory, RAM), magnetic disk, CD) in, including some instructions are used so that terminal device (can be mobile phone, computer,
Server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of financial institution's recommended method, which is characterized in that financial institution's recommended method the following steps are included:
It obtains historical user to evaluate the historical user of each financial institution undetermined in preset range, be evaluated from the historical user
In extract historical interest point set；
Target user's evaluation that target user is extracted from historical user evaluation, is extracted from target user evaluation
Target interest point set out, the historical user include the target user；
Target gold is determined by Collaborative Filtering Recommendation Algorithm according to the historical interest point set and the target interest point set
Melt mechanism；
The destination financial mechanism is pushed into the target user.
2. financial institution's recommended method as described in claim 1, which is characterized in that described according to the historical interest point set
Destination financial mechanism is determined by Collaborative Filtering Recommendation Algorithm with the target interest point set, comprising:
The target is calculated by the first similarity formula according to the historical interest point set and the target interest point set
The first similarity between the first user in user and each historical user other than the target user；
Select first user of the first preset quantity as second user according to the first similarity descending order；
The second user is evaluated into highest financial institution undetermined as destination financial mechanism according to historical user evaluation.
3. financial institution's recommended method as claimed in claim 2, which is characterized in that described according to the historical interest point set
With the target interest point set by the first similarity formula calculate the target user in each historical user in addition to described
The first similarity between the first user except target user, comprising:
Count the common interest point set of the historical interest point set Yu the target interest point set；
It is similar by first to the target interest point set according to the common interest point set, the historical interest point set
Degree formula calculates first between the first user in the target user and each historical user other than the target user
Similarity.
4. financial institution's recommended method as claimed in claim 3, which is characterized in that the statistics historical interest point set
After the common interest point set of the target interest point set, financial institution's recommended method further include:
Obtain the access frequency of each financial institution in the common interest point set；
It is described to pass through first according to the common interest point set, the historical interest point set and the target interest point set
Similarity formula calculates between the first user in the target user and each historical user other than the target user
First similarity, comprising:
According to the access frequency, the common interest point set, the historical interest point set and the target interest point set
Close first calculated in the target user and each historical user other than the target user by the first similarity formula
The first similarity between user.
5. financial institution's recommended method as claimed in claim 2, which is characterized in that described evaluated according to the historical user will
The second user evaluates highest financial institution undetermined as destination financial mechanism, comprising:
The second user is evaluated into highest financial institution undetermined as wait choose financial machine according to historical user evaluation
Structure；
The financial institution to be chosen that the target user has not visited is chosen as destination financial mechanism.
6. financial institution's recommended method as described in claim 1, which is characterized in that described according to the historical interest point set
Destination financial mechanism is determined by Collaborative Filtering Recommendation Algorithm with the target interest point set, comprising:
The target user is extracted from the target interest point set evaluates highest financial institution undetermined as the first gold medal
Melt mechanism；
The second financial machine in first financial institution and the historical interest point set is calculated by the second similarity formula
The second similarity between structure；
Select second financial institution of the second preset quantity as target according to the second similarity descending order
Financial institution.
7. financial institution's recommended method as claimed in claim 5, which is characterized in that described to pass through the calculating of the second similarity formula
The second similarity between the second financial institution in first financial institution and the historical interest point set, comprising:
Each first type of business of first financial institution is obtained, and obtains the second finance in the historical interest point set
Each second type of business of mechanism；
Count the common service type of first type of business and second type of business；
Obtain the probability that the common service type occurs in the financial institution undetermined；
Pass through second according to the probability, the common service type, first type of business and second type of business
Similarity formula calculates second between the second financial institution in first financial institution and the historical interest point set
Similarity.
8. a kind of financial institution's recommendation apparatus, which is characterized in that financial institution's recommendation apparatus includes: memory, processor
And it is stored in the financial institution's recommended program that can be run on the memory and on the processor, the financial institution is recommended
The step of financial institution's recommended method as described in any one of claims 1 to 7 is realized when program is executed by the processor.
9. a kind of storage medium, which is characterized in that be stored with financial institution's recommended program, the finance machine on the storage medium
The step of financial institution's recommended method as described in any one of claims 1 to 7 is realized when structure recommended program is executed by processor
Suddenly.
10. a kind of financial institution's recommendation apparatus, which is characterized in that financial institution's recommendation apparatus includes: to obtain module, extract
Module, determining module and pushing module；
The acquisition module evaluates the historical user of each financial institution undetermined in preset range for obtaining historical user,
Historical interest point set is extracted from historical user evaluation；
The extraction module, for extracting target user's evaluation of target user from historical user evaluation, from described
Target interest point set is extracted in target user's evaluation, the historical user includes the target user；
The determining module, for being pushed away with the target interest point set by collaborative filtering according to the historical interest point set
It recommends algorithm and determines destination financial mechanism；
The pushing module, for the destination financial mechanism to be pushed to the target user.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810747893.4A CN109727056B (en) | 2018-07-06 | 2018-07-06 | Financial institution recommendation method, device, storage medium and device |
| PCT/CN2018/102052 WO2020006834A1 (en) | 2018-07-06 | 2018-08-24 | Financial institution recommending method, equipment, storage medium, and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810747893.4A CN109727056B (en) | 2018-07-06 | 2018-07-06 | Financial institution recommendation method, device, storage medium and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109727056A true CN109727056A (en) | 2019-05-07 |
| CN109727056B CN109727056B (en) | 2023-04-18 |
Family
ID=66293874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810747893.4A Active CN109727056B (en) | 2018-07-06 | 2018-07-06 | Financial institution recommendation method, device, storage medium and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109727056B (en) |
| WO (1) | WO2020006834A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110197434A (en) * | 2019-05-21 | 2019-09-03 | 深圳前海微众银行股份有限公司 | Intelligent Matching processing method, device, equipment and readable storage medium storing program for executing |
| CN112395486A (en) * | 2019-08-12 | 2021-02-23 | 中国移动通信集团重庆有限公司 | Broadband service recommendation method, system, server and storage medium |
| CN115858599A (en) * | 2022-12-01 | 2023-03-28 | 中国建设银行股份有限公司 | Service recommendation method and device, electronic equipment and storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701784A (en) * | 2023-05-04 | 2023-09-05 | 中国银行股份有限公司 | Dot search method, apparatus, device, storage medium, and program product |
| CN119622123B (en) * | 2025-02-11 | 2025-05-16 | 常熟理工学院 | A lightweight point of interest recommendation method and device integrating user movement direction |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060266830A1 (en) * | 2005-05-31 | 2006-11-30 | Horozov Tzvetan T | Location-based recommendation system |
| CN105025091A (en) * | 2015-06-26 | 2015-11-04 | 南京邮电大学 | A store recommendation method based on mobile user location |
| CN106339502A (en) * | 2016-09-18 | 2017-01-18 | 电子科技大学 | Modeling recommendation method based on user behavior data fragmentation cluster |
| CN107341261A (en) * | 2017-07-13 | 2017-11-10 | 南京邮电大学 | A kind of point of interest of facing position social networks recommends method |
| CN107766462A (en) * | 2017-09-28 | 2018-03-06 | 重庆大学 | Point of interest based on user preference, social credit worthiness and geographical position recommends method |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5691735B2 (en) * | 2011-03-29 | 2015-04-01 | ソニー株式会社 | CONTENT RECOMMENDATION DEVICE, RECOMMENDED CONTENT SEARCH METHOD, AND PROGRAM |
| CN102594905B (en) * | 2012-03-07 | 2014-07-16 | 南京邮电大学 | Method for recommending social network position interest points based on scene |
| CN104111938B (en) * | 2013-04-18 | 2018-09-18 | 腾讯科技（深圳）有限公司 | A kind of method and device of information recommendation |
| CN104166648A (en) * | 2013-05-16 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Recommendation data excavation method and device based on labels |
| CN103455613B (en) * | 2013-09-06 | 2016-03-16 | 南京大学 | Based on the interest aware service recommendation method of MapReduce model |
| CN104794635A (en) * | 2015-04-17 | 2015-07-22 | 南京大学 | Cellphone model recommendation system based on collaborative filtering recommendation algorithm |
| CN106997358A (en) * | 2016-01-22 | 2017-08-01 | 中移（杭州）信息技术有限公司 | Information recommendation method and device |
| CN107909428A (en) * | 2017-11-01 | 2018-04-13 | 平安科技（深圳）有限公司 | Electronic device, Products Show method and computer-readable recording medium |
-
2018
- 2018-07-06 CN CN201810747893.4A patent/CN109727056B/en active Active
- 2018-08-24 WO PCT/CN2018/102052 patent/WO2020006834A1/en not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060266830A1 (en) * | 2005-05-31 | 2006-11-30 | Horozov Tzvetan T | Location-based recommendation system |
| CN105025091A (en) * | 2015-06-26 | 2015-11-04 | 南京邮电大学 | A store recommendation method based on mobile user location |
| CN106339502A (en) * | 2016-09-18 | 2017-01-18 | 电子科技大学 | Modeling recommendation method based on user behavior data fragmentation cluster |
| CN107341261A (en) * | 2017-07-13 | 2017-11-10 | 南京邮电大学 | A kind of point of interest of facing position social networks recommends method |
| CN107766462A (en) * | 2017-09-28 | 2018-03-06 | 重庆大学 | Point of interest based on user preference, social credit worthiness and geographical position recommends method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110197434A (en) * | 2019-05-21 | 2019-09-03 | 深圳前海微众银行股份有限公司 | Intelligent Matching processing method, device, equipment and readable storage medium storing program for executing |
| CN112395486A (en) * | 2019-08-12 | 2021-02-23 | 中国移动通信集团重庆有限公司 | Broadband service recommendation method, system, server and storage medium |
| CN112395486B (en) * | 2019-08-12 | 2023-11-03 | 中国移动通信集团重庆有限公司 | Broadband service recommendation method, system, server and storage medium |
| CN115858599A (en) * | 2022-12-01 | 2023-03-28 | 中国建设银行股份有限公司 | Service recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109727056B (en) | 2023-04-18 |
| WO2020006834A1 (en) | 2020-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727056A (en) | Financial institution's recommended method, equipment, storage medium and device | |
| CN110334289B (en) | Travel destination determining method and target user determining method | |
| US9401097B2 (en) | Method and apparatus for providing emotion expression service using emotion expression identifier | |
| CN105512180B (en) | A kind of search recommended method and device | |
| CN107526760A (en) | Interest information analysis method using rolling mode and the equipment using this method | |
| US9660947B1 (en) | Method and apparatus for filtering undesirable content based on anti-tags | |
| US20160328759A1 (en) | Method, apparatus, and a non-transitory computer-readable recording medium for providing review sharing service | |
| CN111782947A (en) | Search content display method and device, electronic equipment and storage medium | |
| CN108230113A (en) | User's portrait generation method, device, equipment and readable storage medium storing program for executing | |
| KR101519879B1 (en) | Apparatus for recommanding contents using hierachical context model and method thereof | |
| CN113360790B (en) | Information recommendation method, device and electronic equipment | |
| CN107729456A (en) | Sensitive information search method, server and storage medium | |
| CN109508879A (en) | A kind of recognition methods of risk, device and equipment | |
| CN113343109A (en) | List recommendation method, computing device and computer storage medium | |
| KR20140139623A (en) | Discovering spam merchants using product feed similarity | |
| CN110287464A (en) | Display method, device, computer equipment and computer storage medium for option data in form | |
| CN109033241A (en) | News recommended method, device and electronic equipment | |
| CN114385931A (en) | A method, device and electronic device for obtaining a recommendation form | |
| CN102880716B (en) | The active being identified the inter-related task of entity is paid | |
| KR101976056B1 (en) | System and method for recommendation | |
| CN109255676A (en) | Method of Commodity Recommendation, device, computer equipment and storage medium | |
| WO2024078143A1 (en) | Method and apparatus for displaying search result | |
| JP6898542B2 (en) | Information processing device, its control method, and program | |
| CN113342762B (en) | Intelligent processing method and related device for shared messages of friends of merchants | |
| CN110674434A (en) | A method and device for delivering browsing resources |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |