CN109727056B - Financial institution recommendation method, device, storage medium and device - Google Patents
Financial institution recommendation method, device, storage medium and device Download PDFInfo
- Publication number
- CN109727056B CN109727056B CN201810747893.4A CN201810747893A CN109727056B CN 109727056 B CN109727056 B CN 109727056B CN 201810747893 A CN201810747893 A CN 201810747893A CN 109727056 B CN109727056 B CN 109727056B
- Authority
- CN
- China
- Prior art keywords
- financial institution
- target
- user
- historical
- point set
- 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.)
- Active
Links
Images
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 financial institution recommendation method, a financial institution recommendation device, a financial institution recommendation storage medium and a financial institution recommendation device, wherein the method comprises the following steps: obtaining historical user evaluation of historical users on each financial institution to be determined within a preset range, and extracting a historical interest point set from the historical user evaluation; extracting target user evaluation of a target user from historical user evaluation, and extracting a target interest point set from the target user evaluation, wherein the historical user comprises the target user; determining a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set; and pushing the target financial institution to the target user. According to the method and the device, the target financial institution is determined through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set extracted from the historical user evaluation, so that the target financial institution pushed to the target user is enabled to better meet the user requirements, more useful information is pushed to the user, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of information push, in particular to a financial institution recommendation method, financial institution recommendation equipment, a financial institution recommendation storage medium and a financial institution recommendation device.
Background
When a user needs to transact financial services, the existing map search only recommends the address of the financial institution matched with the search content of the user to the user in a general way, but does not recommend more useful content for the user according to the specific requirements of the user, such as specific search terms in financial fields of insurance, stocks or banks, and the like, the user needs to search the address information of the financial institution meeting the self-demand in the recommended address of the financial institution, the efficiency is low, and the financial institution meeting the self-demand can not be well screened out by the user only from the address information of the recommended financial institution. Therefore, how to recommend the address of the financial institution more meeting the user requirement for the user is an urgent technical problem to be solved.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a financial institution recommendation method, financial institution recommendation equipment, a storage medium and a financial institution recommendation device, and aims to solve the technical problem that a financial institution recommended for a user in the prior art cannot meet specific requirements of the user.
In order to achieve the above object, the present invention provides a financial institution recommendation method, including the steps of:
obtaining historical user evaluation of historical users on each financial institution to be determined within a preset range, and extracting a historical interest point set from the historical user evaluation;
extracting target user evaluation of a target user from the historical user evaluation, and extracting a target interest point set from the target user evaluation, wherein the historical user comprises the target user;
determining a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set;
pushing the target financial institution to the target user.
Preferably, the determining a target financial institution by a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set includes:
calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the historical interest point set and the target interest point set;
selecting a first preset number of first users as second users according to the sequence of the first similarity from big to small;
and taking the undetermined financial institution with the highest second user evaluation as a target financial institution according to the historical user evaluation.
Preferably, the calculating a first similarity between the target user and a first user other than the target user in each historical user according to the historical interest point set and the target interest point set by using a first similarity formula includes:
counting a common interest point set of the historical interest point set and the target interest point set;
and calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the common interest point set, the historical interest point set and the target interest point set.
Preferably, after the statistics of the common interest point set of the historical interest point set and the target interest point set, the financial institution recommendation method further includes:
acquiring the access frequency of each financial institution in the common interest point set;
the calculating a first similarity between the target user and a first user except the target user in each historical user according to the common interest point set, the historical interest point set and the target interest point set through a first similarity formula includes:
and calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the access frequency, the common interest point set, the historical interest point set and the target interest point set.
Preferably, the taking the pending financial institution with the highest second user evaluation as the target financial institution according to the historical user evaluation includes:
according to the historical user evaluation, taking the undetermined financial institution with the highest second user evaluation as a financial institution to be selected;
and selecting the financial institution to be selected which is not visited by the target user as a target financial institution.
Preferably, the determining a target financial institution by a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set includes:
extracting the undetermined financial institution with the highest evaluation of the target user from the target interest point set as a first financial institution;
calculating a second similarity between the first financial institution and a second financial institution in the historical set of points of interest via a second similarity formula;
and selecting a second preset number of second financial institutions as target financial institutions according to the sequence of the second similarity from large to small.
Preferably, said calculating a second similarity between said first financial institution and a second financial institution in said historical set of points of interest via a second similarity formula comprises:
acquiring each first business type of the first financial institution and each second business type of a second financial institution in the historical interest point set;
counting a common service category of the first service category and the second service category;
acquiring the probability of the common service category appearing in the financial institution to be determined;
and calculating a second similarity between the first financial institution and a second financial institution in the historical interest point set according to the probability, the common service category, the first service category and the second service category through a second similarity formula.
In addition, in order to achieve the above object, the present invention also provides a financial institution recommendation apparatus, which includes a memory, a processor and a financial institution recommendation program stored in the memory and operable on the processor, wherein the financial institution recommendation program is configured to implement the steps of the financial institution recommendation method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having a financial institution recommendation program stored thereon, which when executed by a processor, implements the steps of the financial institution recommendation method as described above.
In addition, to achieve the above object, the present invention further provides a financial institution recommendation apparatus, including: the device comprises an acquisition module, an extraction module, a determination module and a pushing module;
the acquisition module is used for acquiring historical user evaluation of each financial institution to be determined in a preset range by a historical user and extracting a historical interest point set from the historical user evaluation;
the extraction module is used for extracting target user evaluation of a target user from the historical user evaluation, and extracting a target interest point set from the target user evaluation, wherein the historical user comprises the target user;
the determining module is used for determining a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set;
the pushing module is used for pushing the target financial institution to the target user.
According to the method, historical user evaluation of a historical user on each financial mechanism to be determined in a preset range is obtained, a historical interest point set is extracted from the historical user evaluation, target user evaluation of a target user is extracted from the historical user evaluation, the target interest point set is extracted from the target user evaluation, the historical user comprises the target user, the historical interest point set reflects preference of the historical user, the target interest point set reflects preference of the target user, the target financial mechanism is determined through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set, the target financial mechanism better accords with the preference of the target user, the target financial mechanism is pushed to the target user, the target financial mechanism better accords with user requirements, more useful information is pushed for the user, and user experience is improved.
Drawings
FIG. 1 is a schematic diagram of a financial institution recommendation device for a hardware operating environment according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating a first exemplary embodiment of a financial institution recommendation method of the present invention;
FIG. 3 is a flowchart illustrating a second exemplary embodiment of a financial institution recommendation method of the present invention;
FIG. 4 is a flowchart illustrating a financial institution recommendation method according to a third embodiment of the invention;
FIG. 5 is a block diagram illustrating a first embodiment of the financial institution recommendation apparatus according to the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a financial institution recommendation device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the financial institution recommending apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a client interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The client interface 1003 may include a Display screen (Display), and the optional client interface 1003 may further include a standard wired interface and a wireless interface, and the wired interface for the client interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory or a Non-volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of the financial institution recommendation device and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
As shown in FIG. 1, a memory 1005, identified as one type of computer storage medium, may include an operating system, a network communication module, a client interface module, and a financial institution recommendation program.
In the financial institution recommendation device shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and communicating data with the background server; the client interface 1003 is mainly used for connecting the client; the financial institution recommendation apparatus calls the financial institution recommendation program stored in the memory 1005 through the processor 1001 and executes the financial institution recommendation method according to the embodiment of the present invention.
Based on the hardware structure, the embodiment of the financial institution recommendation method is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of a financial institution recommendation method according to the present invention.
In a first embodiment, the financial institution recommendation method includes the steps of:
step S10: obtaining historical user evaluation of historical users on each financial institution to be determined in a preset range, and extracting a historical interest point set from the historical user evaluation.
It should be understood that the execution subject of the present embodiment is a financial institution recommendation device, wherein the financial institution recommendation device may be an electronic device such as a personal computer, a server, and the like. The preset range may be set by the user through the financial institution recommendation device according to the user's own needs, for example, the preset range may be a city where the target user is located. Before obtaining the historical user evaluation of each financial institution to be determined in the preset range by the historical user, the historical user evaluation may be a financial institution search instruction triggered by the user through the financial institution recommendation device, or the financial institution search instruction triggered by the background server at regular time, in response to the financial institution search instruction, the preset range is extracted from the financial institution search instruction, then the historical user evaluation of each financial institution to be determined in the preset range by the obtained historical user is executed, and the historical interest point set is extracted from the historical user evaluation.
It can be understood that all financial institutions which can be searched within the preset range can be used as the to-be-determined financial institution, the historical user evaluation refers to evaluation made by all historical users who browse the to-be-determined financial institution to the to-be-determined financial institution, and the historical user evaluation comprises evaluation on various business categories and/or service attitudes and the like of the to-be-determined financial institution. The historical interest point set refers to a preference file of the historical user, historical user evaluation of the historical user on each financial institution to be determined can be obtained from browsing records and/or purchase records of the historical user, and interest points of the historical user are extracted from the historical user evaluation. And extracting a Point of Interest (abbreviated as Point of Interest) from the historical user evaluation of each historical user to form the historical Point of Interest set. In order to identify the interest points of the historical users, a track Stop and move point (SMoT) method may be used, which takes the historical user evaluations as input and outputs a core evaluation point in the historical user evaluations of each historical user as an interest point.
Step S20: and extracting target user evaluation of a target user from the historical user evaluation, and extracting a target interest point set from the target user evaluation, wherein the historical user comprises the target user.
In a specific implementation, the historical users are all users who have browsed the information related to the financial institution to be determined, and the target user is one of the historical users. The historical user evaluation comprises target user evaluation of the target user, each historical user has a unique user identification, and the target user evaluation corresponding to the target user identification can be searched from the historical user evaluation through the target user identification of the target user. Usually, there may be a plurality of target user evaluations, one core evaluation point is extracted from each target user evaluation as an interest point of the evaluation, and the plurality of target user evaluations correspond to the plurality of interest points to form the target interest point set.
Step S30: and determining a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set.
It should be noted that, the collaborative filtering recommendation algorithm is to create the recommendation content specific to the target user according to the historical interest point set and the target interest point set. The method comprises a User-based collaboratIve filtering algorithm and an Item-based collaboratIve filtering algorithm, wherein the User is the historical User, and the Item is the pending financial institution.
It should be understood that the collaborative filtering algorithm based on the historical users includes: analyzing the historical user evaluation of each historical user on the financial institution to be determined to obtain the historical interest point set; calculating according to the historical interest point sets to obtain the similarity between the target user and other historical users except the target user in the historical users; selecting a first preset number of historical users with higher similarity to the target user; recommending the pending financial institutions to the target user, wherein the pending financial institutions have the highest evaluation of the first preset number of the historical users and have not been browsed by the target user.
It is understood that the collaborative filtering algorithm based on the pending financial institution comprises: analyzing the evaluation of each historical user on the historical user of the financial institution to be determined to obtain the historical interest point set; analyzing according to the historical interest point set to obtain the similarity between the financial institutions to be determined in the historical interest point set; determining the undetermined financial institutions with the highest evaluation of the target user according to the target interest points, and finding out a second preset number of the undetermined financial institutions with the highest similarity to the financial institutions with the highest evaluation; recommending the second preset number of the financial institutions to be determined with the highest similarity to the target user.
Step S40: pushing the target financial institution to the target user.
In a specific implementation, the target financial institution screened by the collaborative filtering recommendation algorithm is evaluated based on a historical user of an undetermined financial institution within a preset range by the historical user, and is combined with the target user evaluation of the target user, so that the target financial institution better meets the requirements of the target user, and related information of the target financial institution, such as address information, main service type information and the like, can be acquired, and is pushed to the target user, so that the target user can quickly find the target financial institution for handling related financial services through the related information of the target financial institution.
In a first embodiment, historical user evaluations of historical users on various to-be-determined financial institutions in a preset range are obtained, a historical interest point set is extracted from the historical user evaluations, target user evaluations of target users are extracted from the historical user evaluations, a target interest point set is extracted from the target user evaluations, the historical users comprise the target users, the historical interest point set embodies the preferences of the historical users, the target interest point set embodies the preferences of the target users, then the target financial institutions are determined through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set, the target financial institutions are more in line with the preferences of the target users and are pushed to the target users, the target financial institutions are more in line with the user requirements, more useful information is pushed for the users, and user experience is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a financial institution recommendation method according to a second embodiment of the present invention, which is proposed based on the first embodiment shown in fig. 2.
In the second embodiment, the step S30 includes:
step S301: and calculating a first similarity between the target user and a first user except the target user in each historical user according to the historical interest point set and the target interest point set through a first similarity formula.
It will be appreciated that the present embodiment proposes determining the target financial institution based on the historical user's collaborative filtering algorithm. The historical interest point set is a set formed by extracting a corresponding interest point from each historical user evaluation of each historical user, and each extracted interest point generally comprises information such as unique identification information, evaluation grade and evaluated business or service of a corresponding undetermined financial institution. The target interest point set is a set formed by extracting a corresponding interest point from each target user evaluation of the target user, and each extracted interest point generally comprises information such as unique identification information, evaluation grade and evaluated service of a corresponding undetermined financial institution. A first similarity between the target user and a first user of the historical users other than the target user may be calculated from the historical point of interest set and the target point of interest set.
Further, the step S301 includes:
counting a common interest point set of the historical interest point set and the target interest point set;
and calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the common interest point set, the historical interest point set and the target interest point set.
It should be understood that the first similarity formula is:
wherein, | POIS a I and I POIS b I respectively represents the interest point sets browsed by the historical user a and the target user b, | POIS a,b L represents the common interest point set browsed by the historical user a and the target user b simultaneously. It can be known that the target user and each history can be calculated according to the common interest point set, the history interest point set and the target interest point set through the first similarity formulaA first similarity between first ones of the users other than the target user.
Further, after the statistics of the common interest point set of the historical interest point set and the target interest point set, the method further includes:
acquiring the access frequency of each financial institution in the common interest point set;
the calculating a first similarity between the target user and a first user except the target user in each historical user according to the common interest point set, the historical interest point set and the target interest point set through a first similarity formula includes:
and calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the access frequency, the common interest point set, the historical interest point set and the target interest point set.
In a specific implementation, if two of the historical users browse together a pending financial institution that is browsed by a very small number of the historical users, the similarity between them must be higher than the similarity between them browsing the pending financial institution that is browsed by a large number of people together. For example, if a pending financial institution a visited by a plurality of historical users finds that the historical user a and the historical user b visit the pending financial institution a at the same time, and does not represent that there is a high similarity between the historical user a and the historical user b, because the pending financial institution a may be a benchmarking financial institution within the preset range, a plurality of people may choose to browse, and a pending financial institution that is rarely browsed may have a high preference similarity between the historical user a and the historical user b if they visit at the same time. Therefore, the visit frequency of a pending financial institution can also be taken into account when measuring the similarity. The following is a similarity calculation formula added to the access frequency of the pending financial institution, that is, the first similarity formula may also be:
wherein, | POIS a I and I POIS b I respectively represents the interest point sets visited by the history user a and the target user b, | POIS a,b I represents the common interest point set visited by the historical user a and the target user b simultaneously, F p Indicating the access flat rate of the pending financial institution p. It can be known that, according to the access frequency, the common interest point set, the historical interest point set and the target interest point set, a first similarity between the target user and a first user of each historical user except the target user is calculated through a first similarity formula.
Step S302: and selecting a first preset number of the first users as second users according to the sequence of the first similarity from large to small.
It should be noted that the greater the first similarity is, the closer the demands and the preferences of the historical users corresponding to the first similarity are to the target user is, the first similarities are arranged in a descending order, and a first preset number of the first users are selected as the second users according to the descending order of the first similarities, the second users are the first preset number of the historical users closest to the target user in the historical users, and the evaluation of each to-be-determined financial institution by the second users can also reflect the intention of the target user most.
Step S303: and taking the undetermined financial institution with the highest second user evaluation as a target financial institution according to the historical user evaluation.
It should be understood that the historical user evaluations include evaluations of all historical users on each pending financial institution, a second user evaluation made by the second user is found from the historical user evaluations, and the pending financial institution with the highest second user evaluation is used as the target financial institution, so that the recommended target financial institution can better meet the requirements of the target user, better public praise guarantee is provided, and the experience of the target user is improved.
Further, the step S303 includes:
according to the historical user evaluation, taking the undetermined financial institution with the highest second user evaluation as a financial institution to be selected;
and selecting the financial institution to be selected which is not visited by the target user as a target financial institution.
It can be understood that, usually, the target user knows the relevant information of the financial institution to be selected that the target user has visited, and the target user searches for a financial institution more often and wants to know whether the other financial institution to be selected that has not visited has a better choice, then the financial institution to be selected that has the highest evaluation of the second user is taken as the financial institution to be selected, and then the financial institution to be selected that has not visited by the target user is selected from the financial institutions to be selected as the target financial institution, which can better meet the current requirement of the target user.
In this embodiment, a first similarity between the target user and a first user, except the target user, in each historical user is calculated according to the historical interest point set and the target interest point set through a first similarity formula, a first preset number of first users are selected as second users according to a descending order of the first similarity, the greater the first similarity is, the closer the requirements and the likes of the target user and the historical users corresponding to the first similarity are, and the undetermined financial institution with the highest evaluation of the second users is taken as the target financial institution according to the evaluation of the historical users, so that the recommended target financial institution can better meet the requirements of the target user, and better word-of-mouth guarantee is provided, thereby improving the experience of the target user.
Referring to fig. 4, fig. 4 is a flowchart illustrating a third embodiment of the financial institution recommendation method according to the present invention, and the third embodiment of the financial institution recommendation method according to the present invention is proposed based on the first embodiment shown in fig. 2.
In a third embodiment, the step S30 includes:
step S304: and extracting the undetermined financial institution with the highest evaluation of the target user from the target interest point set as a first financial institution.
It should be appreciated that the present embodiment proposes determining the target financial institution based on a collaborative filtering algorithm of the pending financial institution. The target interest point set is the most core evaluation point in each evaluation of the target user, and generally comprises information such as unique identification information of a financial institution to be evaluated, evaluation grade, evaluated business or service and the like. The pending financial institution with the highest evaluation of the target user generally best meets the requirements and preferences of the target user, and the pending financial institution with the highest evaluation of the target user is taken as the first financial institution, so that the first financial institution can represent the requirements of the target user.
Step S305: calculating a second similarity between the first financial institution and a second financial institution in the historical set of points of interest via a second similarity formula.
It is understood that the second similarity between the first financial institution and the second financial institution in the historical interest point set can be calculated by obtaining all the first business categories of the first financial institution and obtaining all the second business categories of the second financial institution according to the first business categories and the second business categories through the second similarity formula. The second similarity formula is as follows:
wherein, | POIS c | and | POIS d L represents the first and second service categories corresponding to the first and second financial institutions c and d, respectively, | poiis c,d L represents a common business category of the first financial institution c and the second financial institution d. It can be known that the first service category, the second service category and the common service category can be counted by the second similarity formulaCalculating the first similarity between the first financial institution and the second financial institution.
Further, the step S305 includes:
acquiring each first business type of the first financial institution and each second business type of a second financial institution in the historical interest point set;
counting a common service category of the first service category and the second service category;
acquiring the probability of the common service category appearing in the financial institution to be determined;
and calculating a second similarity between the first financial institution and a second financial institution in the historical interest point set according to the probability, the common service category, the first service category and the second service category through a second similarity formula.
In particular implementations, if the first financial institution and the second financial institution include a common business category that is shared by a very few pending financial institutions, then the similarity between them must be higher than the similarity that they share a business category that is shared by a very large number of the pending financial institutions. For example, if a business category B is found to be included in both the first financial institution C and the second financial institution d, and does not represent a high similarity between the first financial institution C and the second financial institution d, because the business category B may be a regular business category in the preset range, many pending financial institutions include the business category B, and a small number of pending financial institutions have a business category C, if the first financial institution C and the second financial institution d include the business category C, the preference similarity between the first financial institution C and the second financial institution d is high. Therefore, the probability of the common service category appearing in all the service categories of each pending financial institution can also be taken into account in the similarity measurement. The following is a similarity calculation formula added with the probability of the common service category appearing in the pending financial machine, that is, the second similarity formula may also be:
wherein, | POIS c | and | POIS d I represents the first and second business categories corresponding to the first and second financial institutions c and d, respectively, | POIS c,d I represents a common business category of the first financial institution c and the second financial institution d, F m Representing the probability of the common traffic class m occurring in the pending financial institution. It can be known that the first similarity between the first financial institution and the second financial institution can be calculated according to the probability, the first service category, the second service category and the common service category by the second similarity formula.
Step S306: and selecting a second preset number of second financial institutions as target financial institutions according to the sequence of the second similarity from large to small.
It should be noted that the greater the second similarity is, the closer the service type or service of the corresponding second financial institution and the first financial institution is, the more the first financial institution evaluates the highest pending financial institution for the target user, so the greater the second similarity is, the more the second financial institution conforms to the requirement and preference of the target user, and the second financial institutions of a second preset number are selected as target financial institutions according to the descending order of the second similarity, thereby ensuring that the target financial institution conforms to the requirement and preference of the target user better, pushing the relevant information of the target financial institution to the target user, and improving the experience of the target user.
In a third embodiment, the undetermined financial institution with the highest evaluation of the target user is extracted from the target interest point set and serves as a first financial institution, a second similarity between the first financial institution and a second financial institution in the historical interest point set is calculated through a second similarity formula, and a second preset number of second financial institutions are selected as the target financial institution according to the sequence of the second similarity from large to small, so that the target financial institution is guaranteed to better meet the requirements and preferences of the target user, relevant information of the target financial institution is pushed to the target user, and the experience of the target user can be improved.
Furthermore, an embodiment of the present invention further provides a storage medium, in which a financial institution recommendation program is stored, and the financial institution recommendation program, when executed by a processor, implements the steps of the financial institution recommendation method as described above.
In addition, referring to fig. 5, an embodiment of the present invention further provides a financial institution recommendation apparatus, where the financial institution recommendation apparatus includes: the device comprises an acquisition module 10, an extraction module 20, a determination module 30 and a push module 40;
the acquisition module 10 is configured to acquire historical user evaluations of historical users on each financial institution to be determined within a preset range, and extract a historical interest point set from the historical user evaluations;
the extracting module 20 is configured to extract a target user evaluation of a target user from the historical user evaluations, and extract a target interest point set from the target user evaluation, where the historical user includes the target user;
the determining module 30 is configured to determine a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set;
the pushing module 40 is configured to push the target financial institution to the target user.
In one embodiment, the financial institution recommendation apparatus further comprises: a calculation module and a selection module;
the calculation module is used for calculating a first similarity between the target user and a first user except the target user in each historical user according to the historical interest point set and the target interest point set through a first similarity formula;
the selection module is used for selecting a first preset number of first users as second users according to the descending order of the first similarity;
the determining module 30 is further configured to take the pending financial institution with the highest second user evaluation as the target financial institution according to the historical user evaluation.
In one embodiment, the financial institution recommendation apparatus further comprises: a statistical module;
the statistical module is used for counting a common interest point set of the historical interest point set and the target interest point set;
the calculation module is further configured to calculate, according to the common interest point set, the historical interest point set, and the target interest point set, a first similarity between the target user and a first user, except the target user, of each historical user through a first similarity formula.
In an embodiment, the obtaining module 10 is further configured to obtain an access frequency of each financial institution in the common point of interest set;
the calculation module is further configured to calculate, according to the access frequency, the common interest point set, the historical interest point set, and the target interest point set, a first similarity between the target user and a first user, other than the target user, of each historical user through a first similarity formula.
In one embodiment, the financial institution recommendation apparatus further comprises: selecting a module;
the determining module 30 is further configured to use the to-be-determined financial institution with the highest second user evaluation as the to-be-selected financial institution according to the historical user evaluation;
the selection module is used for selecting the financial institution to be selected which is not visited by the target user as the target financial institution.
In an embodiment, the determining module 30 is further configured to extract, from the target point of interest set, a pending financial institution with the highest evaluation of the target user as a first financial institution;
the calculating module is further configured to calculate a second similarity between the first financial institution and a second financial institution in the historical interest point set through a second similarity formula;
the determining module 30 is further configured to select a second preset number of second financial institutions as target financial institutions according to the descending order of the second similarity.
In one embodiment, the financial institution recommendation apparatus further comprises:
the obtaining module 10 is further configured to obtain each first service category of the first financial institution, and obtain each second service category of a second financial institution in the historical interest point set;
the statistic module is further configured to count a common service category of the first service category and the second service category;
the obtaining module 10 is further configured to obtain a probability that the common service category appears in the financial institution to be determined;
the calculating module is further configured to calculate a second similarity between the first financial institution and a second financial institution in the historical interest point set according to the probability, the common service category, the first service category, and the second service category through a second similarity formula.
Other embodiments or specific implementation manners of the financial institution recommendation device of the present invention may refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order, but rather the words first, second, third, etc. are to be interpreted as names.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., a Read Only Memory (ROM)/Random Access Memory (RAM), a magnetic disk, an optical disk), and includes several instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A financial institution recommendation method, characterized in that the financial institution recommendation method comprises the steps of:
obtaining historical user evaluation of each financial institution to be determined in a preset range by a historical user, and extracting a historical interest point set from the historical user evaluation;
extracting target user evaluation of a target user from the historical user evaluation, and extracting a target interest point set from the target user evaluation, wherein the historical user comprises the target user;
determining a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set;
pushing the target financial institution to the target user;
the determining a target financial institution according to the historical interest point set and the target interest point set through a collaborative filtering recommendation algorithm includes:
calculating a first similarity between the target user and a first user except the target user in each historical user according to the historical interest point set and the target interest point set through a first similarity formula;
selecting a first preset number of first users as second users according to the sequence of the first similarity from large to small;
according to the historical user evaluation, taking the undetermined financial institution with the highest second user evaluation as a target financial institution;
the calculating a first similarity between the target user and a first user except the target user in each historical user according to the historical interest point set and the target interest point set through a first similarity formula includes:
counting a common interest point set of the historical interest point set and the target interest point set;
calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the common interest point set, the historical interest point set and the target interest point set;
after the statistics of the common interest point set of the historical interest point set and the target interest point set, the financial institution recommendation method further includes:
acquiring the access frequency of each financial institution in the common interest point set;
the calculating a first similarity between the target user and a first user except the target user in each historical user according to the common interest point set, the historical interest point set and the target interest point set through a first similarity formula includes:
and calculating a first similarity between the target user and a first user except the target user in each historical user through a first similarity formula according to the access frequency, the common interest point set, the historical interest point set and the target interest point set.
2. The financial institution recommendation method of claim 1, wherein the regarding the pending financial institution with the second user rating highest as the target financial institution according to the historical user rating comprises:
according to the historical user evaluation, taking the undetermined financial institution with the highest second user evaluation as a financial institution to be selected;
and selecting the financial institution to be selected which is not visited by the target user as a target financial institution.
3. The financial institution recommendation method of claim 1, wherein the determining a target financial institution through a collaborative filtering recommendation algorithm based on the historical point of interest set and the target point of interest set comprises:
extracting the undetermined financial institution with the highest evaluation of the target user from the target interest point set as a first financial institution;
calculating a second similarity between the first financial institution and a second financial institution in the historical interest point set through a second similarity formula;
and selecting a second preset number of second financial institutions as target financial institutions according to the sequence of the second similarity from large to small.
4. The financial institution recommendation method of claim 3, wherein the calculating a second similarity between the first financial institution and a second financial institution in the historical set of points of interest via a second similarity formula comprises:
acquiring each first service category of the first financial institution, and acquiring each second service category of a second financial institution in the historical interest point set;
counting common service types of the first service type and the second service type;
acquiring the probability of the common service category appearing in the financial institution to be determined;
and calculating a second similarity between the first financial institution and a second financial institution in the historical interest point set according to the probability, the common service category, the first service category and the second service category through a second similarity formula.
5. A financial institution recommendation apparatus, characterized in that the financial institution recommendation apparatus comprises: a memory, a processor and a financial institution recommendation program stored on the memory and executable on the processor, the financial institution recommendation program when executed by the processor implementing the steps of the financial institution recommendation method as claimed in any one of claims 1 to 4.
6. A storage medium having a financial institution recommendation program stored thereon, which when executed by a processor, implements the steps of the financial institution recommendation method as recited in any one of claims 1 to 4.
7. A financial institution recommendation apparatus, characterized in that the financial institution recommendation apparatus comprises: the device comprises an acquisition module, an extraction module, a determination module and a pushing module;
the acquisition module is used for acquiring historical user evaluation of each financial institution to be determined in a preset range by a historical user and extracting a historical interest point set from the historical user evaluation;
the extraction module is used for extracting target user evaluation of a target user from the historical user evaluation, and extracting a target interest point set from the target user evaluation, wherein the historical user comprises the target user;
the determining module is used for determining a target financial institution through a collaborative filtering recommendation algorithm according to the historical interest point set and the target interest point set;
the pushing module is used for pushing the target financial institution to the target user;
the financial institution recommendation apparatus further comprises: a calculation module and a selection module;
the calculation module is used for calculating a first similarity between the target user and a first user except the target user in each historical user according to the historical interest point set and the target interest point set through a first similarity formula;
the selection module is used for selecting a first preset number of first users as second users according to the descending order of the first similarity;
the determining module is further configured to take the undetermined financial institution with the highest second user evaluation as a target financial institution according to the historical user evaluation;
the financial institution recommendation apparatus further comprises: a statistical module;
the statistical module is used for counting a common interest point set of the historical interest point set and the target interest point set;
the calculation module is further configured to calculate, according to the common interest point set, the historical interest point set, and the target interest point set, a first similarity between the target user and a first user, other than the target user, of each historical user through a first similarity formula;
the acquisition module is further configured to acquire access frequencies of financial institutions in the common interest point set;
the calculation module is further configured to calculate, according to the access frequency, the common interest point set, the historical interest point set, and the target interest point set, a first similarity between the target user and a first user, except the target user, of each historical user through a first similarity formula.
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 CN109727056A (en) | 2019-05-07 |
| CN109727056B true 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) |
Families Citing this family (5)
| 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 |
| 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 |
| 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060266830A1 (en) * | 2005-05-31 | 2006-11-30 | Horozov Tzvetan T | Location-based recommendation system |
| 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109727056A (en) | 2019-05-07 |
| WO2020006834A1 (en) | 2020-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727056B (en) | Financial institution recommendation method, device, storage medium and device | |
| CN109189867B (en) | Relation discovery method and device based on company knowledge graph and storage medium | |
| KR101999471B1 (en) | Information recommendation methods and devices | |
| CN101990668B (en) | Recommendation information generation apparatus and recommendation information generation method | |
| KR101708444B1 (en) | Method for evaluating relation between keyword and asset value and Apparatus thereof | |
| EP3196824A1 (en) | Information processing system and method | |
| CN115098803B (en) | Book recommendation method and system based on mobile library | |
| CN107798571A (en) | Identifying system, the method and device of malice address/malice order | |
| CN108512883B (en) | Information pushing method and device and readable medium | |
| KR102116519B1 (en) | Location Based Ranking of Real World Locations | |
| KR20090033989A (en) | Local information advertising method based on location information and system for performing the above method | |
| KR20130011257A (en) | System for recommending commodity information based on social network service and service method of the same | |
| CN113360790B (en) | Information recommendation method, device and electronic equipment | |
| JP2018101260A (en) | Information processing system, information processing method, and information processing program | |
| CN112488854A (en) | Service manager personalized recommendation method and related equipment | |
| JP7673990B2 (en) | Information Processing System | |
| CN113723522A (en) | Abnormal user identification method and device, electronic equipment and storage medium | |
| CN111078997B (en) | Information recommendation method and device | |
| JP4869448B1 (en) | Name identification management system | |
| CN110825933B (en) | Relation graph display method and device, electronic equipment and readable storage medium | |
| JP7673998B2 (en) | Information Processing System | |
| JP2009230299A (en) | Related document presentation system and program | |
| CN110837951A (en) | Business channel sequencing method and device and electronic equipment | |
| CN116910129A (en) | Enterprise tag display method and device | |
| KR102343815B1 (en) | Method, device and system for measuring advertisement effect using network data |
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 |