CN113688324A - Bank outlet recommendation method and device - Google Patents
Bank outlet recommendation method and device Download PDFInfo
- Publication number
- CN113688324A CN113688324A CN202111043710.9A CN202111043710A CN113688324A CN 113688324 A CN113688324 A CN 113688324A CN 202111043710 A CN202111043710 A CN 202111043710A CN 113688324 A CN113688324 A CN 113688324A
- Authority
- CN
- China
- Prior art keywords
- candidate
- people
- bank
- outlets
- queuing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000007704 transition Effects 0.000 claims description 16
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000000586 desensitisation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Abstract
The embodiment of the application discloses a bank outlet recommendation method and device, which can be applied to the field of artificial intelligence, the field of big data or the field of finance. The method comprises the following steps: acquiring a target position where a target user is currently located; determining a bank outlet with a distance from the target position meeting a preset distance condition as a candidate bank outlet; for each candidate banking outlet, determining the traffic cost required for reaching the candidate banking outlet from the target position; acquiring the current queuing number of the candidate bank outlets; acquiring the probability of increasing the number of the queuing people corresponding to the candidate bank outlets, wherein the probability of increasing the number of the queuing people is used for representing the probability of increasing the number of the preset people after the preset time period, and the probability of increasing the number of the queuing people is determined according to the number of the queuing people of the candidate bank outlets in the reference historical time period; and determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank outlet.
Description
Technical Field
The application relates to the technical field of computers, in particular to a bank outlet recommendation method and device.
Background
At present, before a user goes to an off-line bank outlet to handle related services, the user can know that the user is suitable for the bank outlet to go to through a network recommendation function provided by a mobile banking Application (APP). When the mobile banking APP determines the bank outlets recommended to the user, the current position of the user is usually obtained, the bank outlets closest to the position are inquired, and the inquired bank outlets are recommended to the user.
However, in practical applications, the banking outlets recommended to the user determined by the above method are not banking outlets capable of bringing better experience to the user, that is, the banking outlets recommended to the user are determined by referring to the geographical location, and it is difficult to ensure service experience brought to the user by the recommended banking outlets.
Disclosure of Invention
The embodiment of the application provides a recommendation method and device for bank outlets, which can enable the determined bank outlets recommended to a user to bring better service experience to the user.
In view of the above, a first aspect of the present application provides a banking outlet recommendation method, where the method includes:
acquiring the current position of a target user as a target position;
according to the target position, determining a bank outlet of which the distance to the target position meets a preset distance condition as a candidate bank outlet;
determining the traffic cost required for reaching the candidate banking outlets from the target position as the traffic cost corresponding to the candidate banking outlets for each candidate banking outlet; acquiring the current queuing number of the candidate bank outlets; acquiring the number-of-queuing-people increasing probability corresponding to the candidate bank outlets, wherein the number-of-queuing-people increasing probability is used for representing the probability that the number of queuing people increases the preset number of people after a preset time period, and the number-of-queuing-people increasing probability is determined according to the number of queuing people of the candidate bank outlets in a reference historical time period;
and determining a recommended bank network from each candidate bank network according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank network.
Optionally, the obtaining of the increased probability of the number of people in line corresponding to the candidate bank outlets includes:
acquiring the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period;
constructing a transition probability matrix according to the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period through a Markov chain algorithm;
and determining the probability of increasing the number of the queuing people corresponding to the candidate bank outlets according to the current number of the queuing people of the candidate bank outlets based on the transition probability matrix.
Optionally, the determining a recommended bank branch from each candidate bank branch according to the traffic cost, the current number of people in line, and the probability of increasing the number of people in line corresponding to each candidate bank branch includes:
determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line, the probability of increasing the number of people in line and the business characteristics of each candidate bank outlet by a decision tree regression algorithm; the business characteristics are determined according to the number of people in line of the candidate bank outlets in the reference historical time period.
Optionally, the determining a traffic cost required for reaching the candidate banking outlet from the target location as the traffic cost corresponding to the candidate banking outlet includes:
determining a cost of transit time required to travel from the target location to the candidate banking site in a target transit manner and a cost of transit money required to travel from the target location to the candidate banking site in the target transit manner; and taking the traffic time cost and the traffic money cost as the traffic cost corresponding to the candidate bank outlets.
Optionally, the determining a recommended bank branch from each candidate bank branch according to the traffic cost, the current number of people in line, and the probability of increasing the number of people in line corresponding to each candidate bank branch includes:
determining the recommendation score corresponding to each candidate bank outlet according to the traffic cost, the current queuing number, the queuing number increase probability and the business characteristics corresponding to each candidate bank outlet; the business characteristics are determined according to the number of people who queue the candidate bank outlets in a reference historical period;
determining the recommended banking outlets according to the recommendation scores corresponding to the candidate banking outlets;
the method further comprises the following steps:
and displaying each candidate bank branch according to the recommendation score corresponding to each candidate bank branch.
A second aspect of the present application provides a recommendation apparatus for a banking outlet, the apparatus comprising:
the position acquisition module is used for acquiring the current position of the target user as a target position;
the network node primary selection module is used for determining a bank network node of which the distance from the target position meets a preset distance condition as a candidate bank network node according to the target position;
the reference data determining module is used for determining the traffic cost required by reaching the candidate banking outlets from the target position aiming at each candidate banking outlet, and the traffic cost is used as the traffic cost corresponding to the candidate banking outlets; acquiring the current queuing number of the candidate bank outlets; acquiring the number-of-queuing-people increasing probability corresponding to the candidate bank outlets, wherein the number-of-queuing-people increasing probability is used for representing the probability that the number of queuing people increases the preset number of people after a preset time period, and the number-of-queuing-people increasing probability is determined according to the number of queuing people of the candidate bank outlets in a reference historical time period;
and the network point recommending module is used for determining recommended bank network points from the candidate bank network points according to the traffic cost, the current queuing number and the probability of increasing the queuing number which correspond to the candidate bank network points.
Optionally, the reference data determining module is specifically configured to:
acquiring the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period;
constructing a transition probability matrix according to the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period through a Markov chain algorithm;
and determining the probability of increasing the number of the queuing people corresponding to the candidate bank outlets according to the current number of the queuing people of the candidate bank outlets based on the transition probability matrix.
Optionally, the website recommending module is specifically configured to:
determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line, the probability of increasing the number of people in line and the business characteristics of each candidate bank outlet by a decision tree regression algorithm; the business characteristics are determined according to the number of people in line of the candidate bank outlets in the reference historical time period.
Optionally, the reference data determining module is specifically configured to:
determining a cost of transit time required to travel from the target location to the candidate banking site in a target transit manner and a cost of transit money required to travel from the target location to the candidate banking site in the target transit manner; and taking the traffic time cost and the traffic money cost as the traffic cost corresponding to the candidate bank outlets.
Optionally, the website recommending module is specifically configured to:
determining the recommendation score corresponding to each candidate bank outlet according to the traffic cost, the current queuing number, the queuing number increase probability and the business characteristics corresponding to each candidate bank outlet; the business characteristics are determined according to the number of people who queue the candidate bank outlets in a reference historical period;
determining the recommended banking outlets according to the recommendation scores corresponding to the candidate banking outlets;
the device further comprises:
and the website display module is used for displaying each candidate bank website according to the recommendation score corresponding to each candidate bank website.
According to the technical scheme, the embodiment of the application has the following advantages:
the embodiment of the application provides a recommendation method for bank outlets, which comprises the following steps: acquiring the current position of a target user as a target position; then, according to the target position, determining a bank outlet with a distance between the bank outlet and the target position meeting a preset distance condition as a candidate bank outlet; furthermore, for each candidate bank outlet, determining the traffic cost required for reaching the candidate bank outlet from the target position as the traffic cost corresponding to the candidate bank outlet, and acquiring the current number of queuing people of the candidate bank outlet and the probability of increasing the number of queuing people corresponding to the candidate bank outlet, wherein the probability of increasing the number of queuing people is used for representing the probability of increasing the number of queuing people by a preset number of people after the preset time period of energy, and is determined according to the number of queuing people of the candidate bank outlet in a reference historical time period; and finally, determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank outlet. When the bank outlet recommending method determines the bank outlet recommended to the user, the traffic cost consumed when the user goes to the bank outlet, the current number of queuing people of the bank outlet and the probability increasing rate of the number of queuing people corresponding to the bank outlet are comprehensively considered, so that the determined recommending outlet can be ensured to be more in line with the traffic requirement of the user, the determined recommending outlet can be ensured not to wait for too long time when the user transacts business, and the recommending outlet can bring better experience to the user.
Drawings
Fig. 1 is a schematic flow chart of a recommendation method for a banking outlet according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a bank outlet recommendation device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the related technology, the website recommendation function provided by the mobile banking APP generally directly obtains the current location of the user, and then queries the website recommendation closest to the current location to recommend the website recommendation to the user. However, in many cases, many people may be queued at the closest bank outlet and it is uncertain how many more users will be queued on the way to the bank outlet, and thus it can be seen that the closest outlet may not be the best choice for the user experience.
In order to solve the above problem, an embodiment of the present application provides a method for recommending a bank outlet, where in the method, a current location of a target user is obtained as a target location; then, according to the target position, determining a bank outlet with a distance between the bank outlet and the target position meeting a preset distance condition as a candidate bank outlet; furthermore, for each candidate bank outlet, determining the traffic cost required for reaching the candidate bank outlet from the target position as the traffic cost corresponding to the candidate bank outlet, and acquiring the current number of queuing people of the candidate bank outlet and the probability of increasing the number of queuing people corresponding to the candidate bank outlet, wherein the probability of increasing the number of queuing people is used for representing the probability of increasing the number of queuing people by a preset number of people after the preset time period of energy, and is determined according to the number of queuing people of the candidate bank outlet in a reference historical time period; and finally, determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank outlet. When the bank outlet recommending method determines the bank outlet recommended to the user, the traffic cost consumed when the user goes to the bank outlet, the current number of queuing people of the bank outlet and the probability increasing rate of the number of queuing people corresponding to the bank outlet are comprehensively considered, so that the determined recommending outlet can be ensured to be more in line with the traffic requirement of the user, the determined recommending outlet can be ensured not to wait for too long time when the user transacts business, and the recommending outlet can bring better experience to the user.
The following describes in detail a recommendation method for a banking outlet provided by the present application by using an embodiment of the method.
Referring to fig. 1, fig. 1 is a schematic flow chart of a recommendation method for a banking outlet according to an embodiment of the present application. For convenience of description, the following embodiments are described by taking a background server whose execution subject is a mobile banking APP as an example. As shown in fig. 1, the method includes:
step 101: and acquiring the current position of the target user as the target position.
In practical application, when detecting that a target user uses a website recommendation function of a mobile banking APP, a server may request the target user to grant permission for obtaining location information of the target user, obtain location information (such as longitude and latitude) of a mobile phone carrying the mobile banking APP, and use the location information as a current location of the target user, that is, a target location.
Step 102: and according to the target position, determining the bank outlets with the distance from the target position meeting the preset distance condition as candidate bank outlets.
After the server acquires the current target position of the target user, the server can determine the bank outlets, the distances between which and the target position meet the preset distance condition, as candidate bank outlets according to the target position.
For example, after acquiring a target position where a target user is currently located, a server may determine N banking outlets closest to the target position as candidate banking outlets; or, the server may also use a banking outlet whose distance from the target location is smaller than a preset distance threshold as a candidate banking outlet.
Step 103: determining the traffic cost required for reaching the candidate banking outlets from the target position as the traffic cost corresponding to the candidate banking outlets for each candidate banking outlet; acquiring the current queuing number of the candidate bank outlets; and acquiring the probability of increasing the number of the queuing people corresponding to the candidate bank outlets, wherein the probability of increasing the number of the queuing people is used for representing the probability of increasing the number of the queuing people by a preset number after a preset time period, and the probability of increasing the number of the queuing people is determined according to the number of the queuing people of the candidate bank outlets in a reference historical time period.
Further, for each candidate banking site determined in step 102, a transportation cost (such as transportation time cost, transportation money cost, etc.) required for reaching the candidate banking site from the target location where the target user is located may be determined; in addition, the current queuing number of the candidate bank outlets can be obtained; and obtaining the probability of increasing the number of the queuing people corresponding to the candidate bank website, wherein the probability of increasing the number of the queuing people can represent the probability of increasing the number of the preset people after the preset time period, and the probability of increasing the number of the queuing people is determined according to the number of the queuing people of the candidate bank website in the reference historical time period.
When the traffic cost corresponding to the candidate bank branch is determined, the server can determine the cost of the traffic time required by the target traffic mode from the target position to the candidate bank branch and determine the cost of the traffic money required by the target traffic mode from the target position to the candidate bank branch; and then, the traffic time cost and the traffic money cost are used as the traffic cost corresponding to the candidate bank outlets. For example, the server may determine the transportation mode selected by the user as a target transportation mode, including but not limited to bus riding, driving, self-driving, and walking; then, the server can determine the time consumed by the target user from the target position of the target user to the candidate banking outlet in the target traffic mode aiming at each candidate banking outlet, and the time is used as the traffic time cost corresponding to the candidate banking outlet; determining the expenditure required by the target user from the target position of the target user to the candidate bank branch in the target traffic mode, and taking the expenditure as the traffic money cost corresponding to the candidate bank branch; and then, taking the traffic time cost and the traffic money cost corresponding to the candidate bank branch as the traffic cost corresponding to the candidate bank branch.
In addition, the server needs to acquire the current queuing number of the candidate banking outlets for each candidate banking outlet.
In addition, the server needs to determine, for each candidate banking outlet, the probability of increasing the number of people in line corresponding to the candidate banking outlet. In specific implementation, the server needs to first obtain the number of people queued in each time unit of the candidate bank network in the reference historical time period, for example, obtain the number of people queued in each hour of each day of the candidate bank network in the past month; then, constructing a transition probability matrix according to the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period through a Markov chain algorithm, wherein each element in the transition probability matrix is used for expressing the probability of transferring from the number of queuing people i to the number of queuing people j after a preset time period, namely the transition probability matrix comprises a plurality of elements Pij，Pij＝P(Xt+1＝j|XtWhere i is less than or equal to n, j is less than or equal to m, and m and n may be varied according to the factSetting the situation; the probability transition matrix may be specifically expressed as follows:
furthermore, the server may determine, according to the current number of people queued at the candidate bank outlet, a probability that the number of people at the candidate bank outlet reaches a preset number of people after a preset duration by using the probability transition matrix. For example, when the current number of people in line at the candidate bank outlet is 1, the server may determine, according to an element P12 in the probability transition matrix, the probability that the number of people in line at the candidate bank outlet reaches two people after a preset time period; by analogy, the server can determine the probability that the number of people in line of the candidate bank website reaches three, four, … …, m, and the like.
Optionally, when the data for measuring the candidate bank outlets is obtained in the embodiment of the present application, some sensitive user data may also be obtained, such as personal information of a user, bank account information, and the like, and in order to avoid sensitive information leakage caused by introducing the information in the process of determining the recommended bank outlet, the embodiment of the present application may further perform desensitization processing on the data after the data is obtained, so as to remove the sensitive user data from the obtained data.
Step 104: and determining a recommended bank network from each candidate bank network according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank network.
After the traffic cost required by the target user to reach each candidate bank outlet, the current number of queuing people of each candidate bank outlet and the probability of increasing the number of queuing people of each candidate bank outlet are determined, the server can determine a recommended bank outlet which can be recommended to the target user from each candidate bank outlet according to the traffic time cost and the traffic money cost required by the target user to reach each candidate bank outlet, the current number of queuing people of each candidate bank outlet and the probability of increasing the number of queuing people of each candidate bank outlet.
In specific implementation, the server may determine, by using a cart (classification and regression tree) regression algorithm, a recommended bank outlet from each candidate bank outlet according to the traffic time cost and the traffic money cost corresponding to each candidate bank outlet, the current number of people queued, the probability of increasing the number of people queued, and the business characteristics of the candidate bank outlet (that is, determined according to the number of people queued in each time unit of each candidate bank outlet in the reference historical time period).
Specifically, the server can regard the traffic time cost, the traffic money cost, the number of queuing people, the probability of increasing the number of queuing people and the business characteristics of the bank outlets as reference indexes; and aiming at each reference index, dividing the data under the reference index into a plurality of intervals according to the data distribution of each candidate bank branch under the reference index, wherein the data belonging to the same interval can be regarded as the data of the same class. Furthermore, the server may calculate the corresponding information gain for each reference index, and the information gain is calculated as follows:
1) first, the empirical entropy h (d) is calculated for each reference index:
where D represents the number of all data under the reference index, CkAnd the data quantity of the k-th candidate bank outlet under the reference index is represented.
2) Calculating the empirical conditional entropy H (D | a) of the reference index a:
wherein D isiIndicating the amount of data of class i under the reference index A, DikIs DiAnd CkThe union of (a).
3) Calculating an information gain G (D, A) of the reference index:
G(D,A)＝H(D)-H(D|A)
the corresponding reference index with the largest information gain can be used as a root node of the decision tree; further, combining the data under the reference index, selecting a root node of a next layer from the rest reference indexes; and repeating the steps until the recommended banking outlet is determined according to the root node of the last layer.
In the process of determining the recommended network points, the server can also determine the recommended scores corresponding to the candidate bank network points according to the traffic time cost and the traffic money cost corresponding to the candidate bank network points, the current number of people in line, the probability of increasing the number of people in line and the business characteristics of the candidate bank network points; selecting a plurality of candidate banking outlets with corresponding recommendation scores ranked at the top from the candidate banking outlets as recommendation banking outlets; and displaying each candidate bank branch to the user according to the recommendation score corresponding to each recommended bank branch.
In the method for recommending the bank outlets provided by the embodiment of the application, the current position of a target user is obtained as a target position; then, according to the target position, determining a bank outlet with a distance between the bank outlet and the target position meeting a preset distance condition as a candidate bank outlet; furthermore, for each candidate bank outlet, determining the traffic cost required for reaching the candidate bank outlet from the target position as the traffic cost corresponding to the candidate bank outlet, and acquiring the current number of queuing people of the candidate bank outlet and the probability of increasing the number of queuing people corresponding to the candidate bank outlet, wherein the probability of increasing the number of queuing people is used for representing the probability of increasing the number of queuing people by a preset number of people after the preset time period of energy, and is determined according to the number of queuing people of the candidate bank outlet in a reference historical time period; and finally, determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank outlet. When the bank outlet recommending method determines the bank outlet recommended to the user, the traffic cost consumed when the user goes to the bank outlet, the current number of queuing people of the bank outlet and the probability increasing rate of the number of queuing people corresponding to the bank outlet are comprehensively considered, so that the determined recommending outlet can be ensured to be more in line with the traffic requirement of the user, the determined recommending outlet can be ensured not to wait for too long time when the user transacts business, and the recommending outlet can bring better experience to the user.
The embodiment of the application also provides a recommendation device for the bank outlets. Referring to fig. 2, fig. 2 is a schematic structural diagram of a banking outlet recommendation device provided in an embodiment of the present application, and as shown in fig. 2, the banking outlet recommendation device includes:
a location obtaining module 201, configured to obtain a current location of a target user as a target location;
the website primary selection module 202 is configured to determine, according to the target position, a banking website whose distance from the target position meets a preset distance condition as a candidate banking website;
a reference data determining module 203, configured to determine, for each candidate banking outlet, a traffic cost required for reaching the candidate banking outlet from the target location, as a traffic cost corresponding to the candidate banking outlet; acquiring the current queuing number of the candidate bank outlets; acquiring the number-of-queuing-people increasing probability corresponding to the candidate bank outlets, wherein the number-of-queuing-people increasing probability is used for representing the probability that the number of queuing people increases the preset number of people after a preset time period, and the number-of-queuing-people increasing probability is determined according to the number of queuing people of the candidate bank outlets in a reference historical time period;
and the website recommending module 204 is configured to determine a recommended bank website from each candidate bank website according to the traffic cost, the current number of people in line, and the probability of increasing the number of people in line corresponding to each candidate bank website.
Optionally, the reference data determining module 203 is specifically configured to:
acquiring the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period;
constructing a transition probability matrix according to the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period through a Markov chain algorithm;
and determining the probability of increasing the number of the queuing people corresponding to the candidate bank outlets according to the current number of the queuing people of the candidate bank outlets based on the transition probability matrix.
Optionally, the website recommending module 204 is specifically configured to:
determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line, the probability of increasing the number of people in line and the business characteristics of each candidate bank outlet by a decision tree regression algorithm; the business characteristics are determined according to the number of people in line of the candidate bank outlets in the reference historical time period.
Optionally, the reference data determining module 203 is specifically configured to:
determining a cost of transit time required to travel from the target location to the candidate banking site in a target transit manner and a cost of transit money required to travel from the target location to the candidate banking site in the target transit manner; and taking the traffic time cost and the traffic money cost as the traffic cost corresponding to the candidate bank outlets.
Optionally, the website recommending module 204 is specifically configured to:
determining the recommendation score corresponding to each candidate bank outlet according to the traffic cost, the current queuing number, the queuing number increase probability and the business characteristics corresponding to each candidate bank outlet; the business characteristics are determined according to the number of people who queue the candidate bank outlets in a reference historical period;
determining the recommended banking outlets according to the recommendation scores corresponding to the candidate banking outlets;
the device further comprises:
and the website display module is used for displaying each candidate bank website according to the recommendation score corresponding to each candidate bank website.
When the bank outlet recommending device determines the bank outlet recommended to the user, the traffic cost consumed when the user goes to the bank outlet, the current number of queuing people of the bank outlet and the probability increasing rate of the number of queuing people corresponding to the bank outlet are comprehensively considered, so that the determined recommending outlet can be ensured to be more in line with the traffic requirement of the user, the determined recommending outlet can be ensured not to wait for too long time when the user transacts business, and the recommending outlet can bring better experience to the user.
It should be noted that the bank outlet recommendation method and device provided by the invention can be used in the field of artificial intelligence, the field of big data or the field of finance. The above is only an example, and does not limit the application field of the bank outlet recommendation method and device provided by the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing computer programs.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A banking outlet recommendation method, comprising:
acquiring the current position of a target user as a target position;
according to the target position, determining a bank outlet of which the distance to the target position meets a preset distance condition as a candidate bank outlet;
determining the traffic cost required for reaching the candidate banking outlets from the target position as the traffic cost corresponding to the candidate banking outlets for each candidate banking outlet; acquiring the current queuing number of the candidate bank outlets; acquiring the number-of-queuing-people increasing probability corresponding to the candidate bank outlets, wherein the number-of-queuing-people increasing probability is used for representing the probability that the number of queuing people increases the preset number of people after a preset time period, and the number-of-queuing-people increasing probability is determined according to the number of queuing people of the candidate bank outlets in a reference historical time period;
and determining a recommended bank network from each candidate bank network according to the traffic cost, the current number of people in line and the probability of increasing the number of people in line corresponding to each candidate bank network.
2. The method as claimed in claim 1, wherein said obtaining the probability of increasing the number of people in line corresponding to the candidate banking outlets comprises:
acquiring the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period;
constructing a transition probability matrix according to the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period through a Markov chain algorithm;
and determining the probability of increasing the number of the queuing people corresponding to the candidate bank outlets according to the current number of the queuing people of the candidate bank outlets based on the transition probability matrix.
3. The method as claimed in claim 1, wherein the determining a recommended banking outlet from each of the candidate banking outlets according to the traffic cost, the current number of people in line, and the increased probability of the number of people in line corresponding to each of the candidate banking outlets comprises:
determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line, the probability of increasing the number of people in line and the business characteristics of each candidate bank outlet by a decision tree regression algorithm; the business characteristics are determined according to the number of people in line of the candidate bank outlets in the reference historical time period.
4. The method as claimed in claim 1, wherein the determining the traffic cost required for reaching the candidate banking outlet from the target location as the traffic cost corresponding to the candidate banking outlet comprises:
determining a cost of transit time required to travel from the target location to the candidate banking site in a target transit manner and a cost of transit money required to travel from the target location to the candidate banking site in the target transit manner; and taking the traffic time cost and the traffic money cost as the traffic cost corresponding to the candidate bank outlets.
5. The method as claimed in claim 1, wherein the determining a recommended banking outlet from each of the candidate banking outlets according to the traffic cost, the current number of people in line, and the increased probability of the number of people in line corresponding to each of the candidate banking outlets comprises:
determining the recommendation score corresponding to each candidate bank outlet according to the traffic cost, the current queuing number, the queuing number increase probability and the business characteristics corresponding to each candidate bank outlet; the business characteristics are determined according to the number of people who queue the candidate bank outlets in a reference historical period;
determining the recommended banking outlets according to the recommendation scores corresponding to the candidate banking outlets;
the method further comprises the following steps:
and displaying each candidate bank branch according to the recommendation score corresponding to each candidate bank branch.
6. A bank outlet recommendation apparatus, the apparatus comprising:
the position acquisition module is used for acquiring the current position of the target user as a target position;
the network node primary selection module is used for determining a bank network node of which the distance from the target position meets a preset distance condition as a candidate bank network node according to the target position;
the reference data determining module is used for determining the traffic cost required by reaching the candidate banking outlets from the target position aiming at each candidate banking outlet, and the traffic cost is used as the traffic cost corresponding to the candidate banking outlets; acquiring the current queuing number of the candidate bank outlets; acquiring the number-of-queuing-people increasing probability corresponding to the candidate bank outlets, wherein the number-of-queuing-people increasing probability is used for representing the probability that the number of queuing people increases the preset number of people after a preset time period, and the number-of-queuing-people increasing probability is determined according to the number of queuing people of the candidate bank outlets in a reference historical time period;
and the network point recommending module is used for determining recommended bank network points from the candidate bank network points according to the traffic cost, the current queuing number and the probability of increasing the queuing number which correspond to the candidate bank network points.
7. The apparatus of claim 6, wherein the reference data determination module is specifically configured to:
acquiring the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period;
constructing a transition probability matrix according to the number of queuing people of the candidate bank outlets in each time unit in the reference historical time period through a Markov chain algorithm;
and determining the probability of increasing the number of the queuing people corresponding to the candidate bank outlets according to the current number of the queuing people of the candidate bank outlets based on the transition probability matrix.
8. The apparatus of claim 6, wherein the website recommendation module is specifically configured to:
determining a recommended bank outlet from each candidate bank outlet according to the traffic cost, the current number of people in line, the probability of increasing the number of people in line and the business characteristics of each candidate bank outlet by a decision tree regression algorithm; the business characteristics are determined according to the number of people in line of the candidate bank outlets in the reference historical time period.
9. The apparatus of claim 6, wherein the reference data determination module is specifically configured to:
determining a cost of transit time required to travel from the target location to the candidate banking site in a target transit manner and a cost of transit money required to travel from the target location to the candidate banking site in the target transit manner; and taking the traffic time cost and the traffic money cost as the traffic cost corresponding to the candidate bank outlets.
10. The apparatus of claim 6, wherein the website recommendation module is specifically configured to:
determining the recommendation score corresponding to each candidate bank outlet according to the traffic cost, the current queuing number, the queuing number increase probability and the business characteristics corresponding to each candidate bank outlet; the business characteristics are determined according to the number of people who queue the candidate bank outlets in a reference historical period;
determining the recommended banking outlets according to the recommendation scores corresponding to the candidate banking outlets;
the device further comprises:
and the website display module is used for displaying each candidate bank website according to the recommendation score corresponding to each candidate bank website.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111043710.9A CN113688324B (en) | 2021-09-07 | 2021-09-07 | Bank outlet recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111043710.9A CN113688324B (en) | 2021-09-07 | 2021-09-07 | Bank outlet recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688324A true CN113688324A (en) | 2021-11-23 |
| CN113688324B CN113688324B (en) | 2024-02-13 |
Family
ID=78585455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111043710.9A Active CN113688324B (en) | 2021-09-07 | 2021-09-07 | Bank outlet recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688324B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951979A (en) * | 2015-06-06 | 2015-09-30 | 浙江维融电子科技股份有限公司 | Bank branch recommendation method |
| CN111639271A (en) * | 2020-06-04 | 2020-09-08 | 中国银行股份有限公司 | Network information pushing method and device |
| CN112116116A (en) * | 2020-09-29 | 2020-12-22 | 中国银行股份有限公司 | Bank outlet recommendation method and device |
-
2021
- 2021-09-07 CN CN202111043710.9A patent/CN113688324B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951979A (en) * | 2015-06-06 | 2015-09-30 | 浙江维融电子科技股份有限公司 | Bank branch recommendation method |
| CN111639271A (en) * | 2020-06-04 | 2020-09-08 | 中国银行股份有限公司 | Network information pushing method and device |
| CN112116116A (en) * | 2020-09-29 | 2020-12-22 | 中国银行股份有限公司 | Bank outlet recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688324B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Beresnev | Branch-and-bound algorithm for a competitive facility location problem | |
| Mullin et al. | Local response to water crisis: Explaining variation in usage restrictions during a Texas drought | |
| Chanta et al. | The minimum p-envy location problem: a new model for equitable distribution of emergency resources | |
| US20190188742A1 (en) | Forecasting demand across groups of skills | |
| CN110782301A (en) | Order combining method and device, electronic equipment and computer readable storage medium | |
| CN105744005A (en) | Client positioning and analyzing method and server | |
| Tsui et al. | International arrivals forecasting for Australian airports and the impact of tourism marketing expenditure | |
| WO2014193700A1 (en) | Social media pricing engine | |
| CN110073382A (en) | For showing the graphic user interface of the inventory data at merchant location | |
| CN104537552B (en) | Pass through computer implemented information recommendation method and device | |
| US20190057404A1 (en) | Jobs forecasting | |
| Ayeh et al. | ‘Estimating tomorrow’s tourist arrivals’: forecasting the demand for China’s tourism using the general-to-specific approach | |
| CN112579910A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN111078997B (en) | Information recommendation method and device | |
| Lansley et al. | Challenges to representing the population from new forms of consumer data | |
| CN109829648A (en) | Performance management method and apparatus | |
| KR101312406B1 (en) | Online donation method and system | |
| US9779460B2 (en) | Systems, methods and non-transitory computer readable storage media for tracking and evaluating predictions regarding relationships | |
| CN113688324A (en) | Bank outlet recommendation method and device | |
| CN111798283A (en) | Order distribution method and device, electronic equipment and computer readable storage medium | |
| CN114741618A (en) | Offline service point recommendation method, recommendation device, equipment and medium | |
| US11270250B2 (en) | Intelligent service and customer matching using an information processing system | |
| CN112396441B (en) | Data processing method, device and readable storage medium | |
| Choong et al. | 'Grab, ride and go': an investigation into the use of ride-hailing services in a developing economy | |
| CN114372199A (en) | Business pushing method and device, storage medium and electronic equipment |
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 |