CN114862551A

CN114862551A - Bank branch mobile phone number risk control method and device

Info

Publication number: CN114862551A
Application number: CN202210471175.5A
Authority: CN
Inventors: 朱江波
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2022-04-28
Filing date: 2022-04-28
Publication date: 2022-08-05

Abstract

The invention provides a method and a device for controlling the risk of a mobile phone number of a bank outlet, which are suitable for the technical field of finance, and the method comprises the following steps: constructing a customer mobile phone number relation graph of a bank outlet; for each mobile phone number, determining a potential associated mobile phone number set of the mobile phone number; when a customer modifies the mobile phone number at a bank outlet, if the new mobile phone number is in the potential associated mobile phone number set of the old mobile phone number, carrying out face recognition on the customer according to the potential associated mobile phone number set and the face recognition threshold value of the customer, and judging whether the modification of the mobile phone number is supported or not according to the face recognition result; if the new mobile phone number is not in the set of potential associated mobile phone numbers of the old mobile phone number, determining the associated distance between the old mobile phone number and the new mobile phone number, correcting the face recognition threshold value of the customer according to the associated distance, carrying out face recognition on the customer according to the corrected face recognition threshold value, and judging whether the mobile phone number modification is supported or not according to the face recognition result. The invention can realize the risk control of the mobile phone number of the bank outlet.

Description

Bank branch mobile phone number risk control method and device

Technical Field

The invention relates to the technical field of finance, in particular to a bank branch mobile phone number risk control method and device.

Background

The mobile phone number is important information of a customer, and the mobile phone number is closely related to the identity of the customer to some extent, and especially when the customer pays or modifies information on a bank system, the identity information of the customer needs to be verified in modes of a mobile phone verification code and the like. Meanwhile, the risk is brought to the fund of the customer, and especially the potential risk to the customer in the bank is brought. At present, a bank outlet mobile phone number risk control method is lacked.

Disclosure of Invention

The embodiment of the invention provides a bank outlet mobile phone number risk control method, which is used for realizing the bank outlet mobile phone number risk control and comprises the following steps:

constructing a customer mobile phone number relation graph of a bank outlet;

determining a potential associated mobile phone number set of each mobile phone number according to the relation graph of the mobile phone numbers of the clients and historical modification data;

when a customer modifies the mobile phone number at a bank outlet, if the new mobile phone number is in a potential associated mobile phone number set of the old mobile phone number, carrying out face recognition on the customer according to the potential associated mobile phone number set and a face recognition threshold value of the customer, and judging whether the modification of the mobile phone number is supported or not according to a face recognition result;

if the new mobile phone number is not in the set of potential associated mobile phone numbers of the old mobile phone number, determining the associated distance between the old mobile phone number and the new mobile phone number, correcting the face recognition threshold value of the customer according to the associated distance, carrying out face recognition on the customer according to the corrected face recognition threshold value, and judging whether the mobile phone number modification is supported or not according to the face recognition result.

The embodiment of the invention provides a bank outlet mobile phone number risk control device, which is used for realizing the risk control of the bank outlet mobile phone number, and comprises the following components:

the customer mobile phone number relation graph building module is used for building a customer mobile phone number relation graph in a bank;

the potential associated person determining module is used for determining a potential associated mobile phone number set of each mobile phone number according to the customer mobile phone number relation graph and the historical modification data;

the mobile phone number modification judging module is used for carrying out face recognition on the customer according to the potential associated mobile phone number set and the face recognition threshold value of the customer when the customer modifies the mobile phone number at a bank branch point and if a new mobile phone number is in the potential associated mobile phone number set of an old mobile phone number, and judging whether the modification of the mobile phone number is supported or not according to the face recognition result;

and the face recognition threshold correction module is used for determining the association distance between the old mobile phone number and the new mobile phone number if the new mobile phone number is not in the potential association mobile phone number set of the old mobile phone number, correcting the face recognition threshold of the customer according to the association distance, carrying out face recognition on the customer according to the corrected face recognition threshold, and judging whether the mobile phone number is supported to be modified according to the face recognition result.

The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the bank branch mobile phone number risk control method when executing the computer program.

The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the risk control method for the mobile phone number of the bank branch is realized.

The embodiment of the invention also provides a computer program product which comprises a computer program, and the computer program is executed by a processor to realize the risk control method for the mobile phone number of the bank branch.

In the embodiment of the invention, a customer mobile phone number relation graph of a bank outlet is constructed; determining a potential associated mobile phone number set of each mobile phone number according to the relation graph of the mobile phone numbers of the clients and historical modification data; when a customer modifies the mobile phone number at a bank outlet, if the new mobile phone number is in a potential associated mobile phone number set of the old mobile phone number, carrying out face recognition on the customer according to the potential associated mobile phone number set and a face recognition threshold value of the customer, and judging whether the modification of the mobile phone number is supported or not according to a face recognition result; and if the new mobile phone number is not in the set of potential associated mobile phone numbers of the old mobile phone number, determining the associated distance between the old mobile phone number and the new mobile phone number, correcting the face recognition threshold value of the customer according to the associated distance, carrying out face recognition on the customer according to the corrected face recognition threshold value, and judging whether the mobile phone number modification is supported or not according to the face recognition result. In the process, whether the mobile phone number modification is supported or not is judged through a customer mobile phone number relation graph, historical modification data and a face recognition threshold value of a bank outlet, and the face recognition threshold value can be modified according to the association distance between the old mobile phone number and the new mobile phone number, so that the risk control of mobile phone number modification can be accurately carried out in real time.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:

fig. 1 is a flowchart of a method for controlling risk of a mobile phone number of a banking outlet in an embodiment of the present invention;

FIG. 2 is a flow chart of a customer mobile phone number relationship chart of a banking outlet constructed in an embodiment of the present invention;

fig. 3 is a flowchart illustrating a process of calculating a correlation between each mobile phone number and an associated mobile phone number of the mobile phone number according to the embodiment of the present invention;

fig. 4 is a flowchart of constructing a customer mobile phone number relationship diagram according to the association distance in the embodiment of the present invention;

fig. 5 is a flowchart illustrating the determination of a set of potential associated mobile phone numbers for each mobile phone number in an embodiment of the present invention;

fig. 6 is a flowchart illustrating determining a plurality of boundary interval distances corresponding to a customer mobile phone number relationship diagram and a boundary association distance corresponding to each boundary interval distance in the embodiment of the present invention;

fig. 7 is a first flowchart illustrating a process for determining a potential associated mobile phone number for a mobile phone number according to an embodiment of the present invention;

fig. 8 is a flowchart of a second process for determining a potential associated mobile phone number for a mobile phone number in an embodiment of the present invention;

fig. 9 is a flowchart three of determining a potential associated mobile phone number for a mobile phone number in the embodiment of the present invention;

fig. 10 is a flowchart illustrating a process of determining whether or not to support mobile phone number modification through face recognition in the embodiment of the present invention;

FIG. 11 is a flow chart of modifying a face recognition threshold of a client in an embodiment of the invention;

fig. 12 is a schematic diagram of a risk control device for a mobile phone number of a banking outlet in an embodiment of the present invention;

FIG. 13 is a diagram of a computer device in an embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.

In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are used in an open-ended fashion, i.e., to mean including, but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.

Fig. 1 is a flowchart of a method for controlling risk of a mobile phone number at a bank branch in an embodiment of the present invention, including:

step 101, constructing a customer mobile phone number relation graph of a bank outlet;

102, determining a potential associated mobile phone number set of each mobile phone number according to the relation graph of the mobile phone numbers of the clients and historical modification data;

103, when the customer modifies the mobile phone number at the bank branch, if the new mobile phone number is in the potential associated mobile phone number set of the old mobile phone number, carrying out face recognition on the customer according to the potential associated mobile phone number set and the face recognition threshold value of the customer, and judging whether the mobile phone number modification is supported or not according to the face recognition result;

and 104, if the new mobile phone number is not in the potential associated mobile phone number set of the old mobile phone number, determining the associated distance between the old mobile phone number and the new mobile phone number, correcting the face recognition threshold value of the customer according to the associated distance, carrying out face recognition on the customer according to the corrected face recognition threshold value, and judging whether the mobile phone number is modified or not according to the face recognition result.

Fig. 2 is a flowchart of establishing a customer mobile phone number relationship diagram of a banking outlet in an embodiment of the present invention, where in an embodiment, establishing a customer mobile phone number relationship diagram of a banking outlet includes:

step 201, determining the associated mobile phone number of each mobile phone number;

step 202, calculating the association degree between each mobile phone number and the associated mobile phone number of the mobile phone number;

step 203, calculating the association distance between each mobile phone number and the associated mobile phone number of the mobile phone number based on the association degree between each mobile phone number and the associated mobile phone number of the mobile phone number;

and step 204, constructing a customer mobile phone number relation graph according to the association distance.

In one embodiment, determining the associated phone number for each phone number includes:

and acquiring two accounts related to each piece of transfer data, and determining two mobile phone numbers corresponding to the two accounts as the related mobile phone numbers of the opposite party.

Fig. 3 is a flowchart illustrating a process of calculating a correlation between each mobile phone number and an associated mobile phone number of the mobile phone number in an embodiment of the present invention, where calculating a correlation between each mobile phone number and an associated mobile phone number of the mobile phone number in an embodiment includes:

step 301, for each mobile phone number, determining the quantity of transfer data related between the mobile phone number and each associated mobile phone number of the mobile phone number as the associated data quantity corresponding to each associated mobile phone number of the mobile phone number;

step 302, determining the maximum value in all the related data quantities as the maximum value of the related data;

step 303, for each mobile phone number, determining the association degree between the mobile phone number and each associated mobile phone number of the mobile phone number as the ratio of the associated data amount corresponding to each associated mobile phone number of the mobile phone number to the maximum associated data value.

It should be noted that the transfer data includes transfer transactions and payment transactions.

In one embodiment, calculating the association degree between each mobile phone number and the associated mobile phone number of the mobile phone number includes:

acquiring a client and a teller related to each service handling data, and determining the mobile phone number of the client as the associated mobile phone number of the teller;

for the mobile phone number of each client, determining the quantity of service handling data related to the client and the teller as the corresponding associated data quantity of the mobile phone number of the client and the mobile phone number of the teller;

determining the maximum value in all the related data quantities as the maximum value of the related data;

and for the mobile phone number of each customer, setting the corresponding association degree of the mobile phone number of the customer and the mobile phone number of the teller as the ratio of the associated data quantity corresponding to the mobile phone number of the customer and the mobile phone number of the teller to the maximum value of the associated data.

In an embodiment, calculating an association distance between each mobile phone number and an associated mobile phone number of the mobile phone number based on an association degree between each mobile phone number and the associated mobile phone number of the mobile phone number includes:

for each mobile phone number, determining the association distance between the mobile phone number and each associated mobile phone number of the mobile phone number as-lg (r), wherein r is the association degree between the mobile phone number and each associated mobile phone number of the mobile phone number, and lg is a logarithmic function with the base of 10.

Fig. 4 is a flowchart of building a customer mobile phone number relationship diagram according to the association distance in the embodiment of the present invention, and in an embodiment, building a customer mobile phone number relationship diagram according to the association distance includes:

step 401, each mobile phone number is used as a node, and if and only if two mobile phone numbers are associated mobile phone numbers of the other party, the nodes corresponding to the two mobile phone numbers have edges;

step 402, determining the association distance of the edge as the association distance between two mobile phone numbers corresponding to the edge, and determining the interval distance of the edge as 1.

Wherein, if there is no edge between two nodes, the shortest distance algorithm is needed to calculate.

Fig. 5 is a flowchart illustrating an embodiment of determining a set of potential associated mobile phone numbers for each mobile phone number, where in an embodiment of the present invention, determining a set of potential associated mobile phone numbers for each mobile phone number according to a relationship diagram of the mobile phone numbers of a customer and history modification data includes:

step 501, determining a plurality of boundary interval distances corresponding to a customer mobile phone number relation graph and a boundary association distance corresponding to each boundary interval distance according to historical modification data;

step 502, for each mobile phone number, determining a potential associated mobile phone number set of the mobile phone number according to the plurality of boundary interval distances and the boundary associated distance corresponding to each boundary interval distance.

And the historical modification data is the historical modification data of the mobile phone number.

Fig. 6 is a flowchart illustrating an embodiment of the present invention for determining a plurality of boundary separation distances corresponding to a customer mobile phone number relationship diagram and a boundary association distance corresponding to each boundary separation distance, where in an embodiment, the determining the plurality of boundary separation distances corresponding to the customer mobile phone number relationship diagram and the boundary association distance corresponding to each boundary separation distance according to history modification data includes:

step 601, for each piece of historical modification data, determining the mobile phone number related in the historical modification data;

step 602, determining the association distance and the interval distance between the mobile phone numbers related in the historical modification data according to the mobile phone number relation graph of the customer;

step 603, determining a partial order of the historical modified data according to the association distance and the interval distance, wherein for any two pieces of historical modified data, the partial order is used for determining whether a first historical modified data of the two pieces of historical modified data is larger than a second historical modified data of the two pieces of historical modified data; one of the two pieces of historical modification data is first historical modification data, and the other one is second historical modification data;

step 604, determining a plurality of maximum historical modified data in all the historical modified data according to the partial order of the historical modified data, wherein the maximum historical modified data is a maximum element of the partial order;

step 605, for each maximum historical modification data, determining the interval distance between the mobile phone numbers involved in the maximum historical modification data as a boundary interval distance, and determining the association distance between the mobile phone numbers involved in the maximum historical modification data as a boundary association distance corresponding to the boundary interval distance.

It should be noted that, in the present application, determining the association distance between the mobile phone numbers involved in the history modification data means determining the shortest distance between the involved mobile phone numbers according to the customer mobile phone number relationship diagram, and the association distance and shortest path algorithm corresponding to each edge on the diagram, and taking the shortest distance as the association distance between the involved mobile phone numbers; similarly, determining the separation distance between the mobile phone numbers involved in the historical modification data means that the shortest distance between the involved mobile phone numbers is determined according to the customer mobile phone number relationship graph and the separation distance and shortest path algorithm corresponding to each edge on the graph, and the shortest distance is used as the separation distance between the involved mobile phone numbers.

It should be noted that the partial order maximum element is in the set corresponding to the partial order, and there is no other element superior to the maximum element. In the present application, the maximum historical modification data in all the historical modification data refers to: any other historical modification data does not exist in all other historical modification data except the extremely large historical modification data in all the historical modification data, so that the other historical modification data is larger than the extremely large historical modification data.

In one embodiment, one method for determining the plurality of extremely large historical modification data in all the historical modification data according to the partial order of the historical modification data in step 604 is as follows:

1. initializing the maximum identification corresponding to each historical modification data in all the historical modification data to be possible, and initializing the corresponding comparison identification to be yes;

2. sequentially for each historical modification data in all the historical modification data, if the maximum identification corresponding to the historical modification data is possible, selecting a plurality of other historical modification data corresponding to the comparison identification as yes from all other historical modification data except the historical modification data in all the historical modification data, and then setting the historical modification data to be compared corresponding to the historical modification data as the selected plurality of other historical modification data; if the maximum identification corresponding to the historical modification data is not possible, continuing to execute the step 2 on the next historical modification data;

3. sequentially selecting each historical modification data to be compared corresponding to the historical modification data, if the historical modification data to be compared is superior to the historical modification data, setting the maximum identifier corresponding to the historical modification data to be negative, and then continuing to execute the step 2 on the next historical modification data; if the historical modified data is superior to the historical modified data to be compared, setting the maximum identifier corresponding to the historical modified data to be compared as no, and determining the historical modified data to be compared as the secondary historical modified data of the historical modified data; otherwise, the maximum identification corresponding to the historical modification data and the maximum identification corresponding to the historical modification data to be compared are kept unchanged;

4. if all the historical modified data to be compared of the historical modified data are determined not to be superior to the historical modified data (namely after the historical modified data and the corresponding historical modified data to be compared are sequentially compared, the maximum identification corresponding to the historical modified data is still possible), determining the historical modified data as the maximum historical modified data in all the historical modified data, and updating the comparison identification of each time of the historical modified data of the maximum historical modified data to be no;

5. and then continuing to execute the step 2 on the next historical modification data until the steps are executed on all the historical modification data.

In one embodiment, determining the partial order of the historical modification data according to the association distance and the separation distance includes:

determining the partial order of historical modification data, wherein for any two pieces of historical modification data, if the association distance between the mobile phone numbers involved in the first historical modification data of the two pieces of historical modification data is greater than or equal to the association distance between the mobile phone numbers involved in the second historical modification data of the two pieces of historical modification data, and the separation distance between the mobile phone numbers involved in the first historical modification data is greater than or equal to the separation distance between the mobile phone numbers involved in the second historical modification data, determining that the first historical modification data is greater than the second historical modification data.

Fig. 7 is a first flowchart of a process of determining a potential associated mobile phone number of a mobile phone number according to an embodiment of the present invention, where in an embodiment, for each mobile phone number, determining the potential associated mobile phone number of the mobile phone number according to a plurality of boundary separation distances and a boundary association distance corresponding to each boundary separation distance includes:

step 701, calculating the association distance between the mobile phone number and all other mobile phone numbers and the spacing distance between the mobile phone number and all mobile phone numbers for each mobile phone number in a mobile phone number relation graph of a client;

step 702, for each other mobile phone number, if a boundary interval distance and a boundary association distance corresponding to the boundary interval distance exist, so that the interval distance between the mobile phone number and the other mobile phone number is less than or equal to the boundary interval distance, and the association distance between the mobile phone number and the other mobile phone number is less than or equal to the boundary association distance corresponding to the boundary interval distance, determining the other mobile phone number as a potential associated mobile phone number of the mobile phone number.

It should be noted that the method corresponding to fig. 7 is applicable to the case when the structural complexity of the customer mobile phone number relationship diagram is smaller than the first threshold. Otherwise the complexity of the corresponding method would be very high, i.e. there is redundancy in the calculation of the method. When the structural complexity of the customer mobile phone number relation graph is not less than the first threshold value, the following method corresponding to the flow chart II and the flow chart III for determining the potential associated mobile phone number of one mobile phone number can be adopted.

Fig. 8 is a flowchart two of determining a potential associated mobile phone number of one mobile phone number in the embodiment of the present invention, where another method for determining a potential associated mobile phone number of one mobile phone number is provided. In an embodiment, for each mobile phone number, determining a potential associated mobile phone number of the mobile phone number according to a plurality of boundary separation distances and a boundary associated distance corresponding to each boundary separation distance includes:

step 801, when the structural complexity of the customer mobile phone number relational graph is not less than a first threshold, deleting the edge of which the corresponding association distance is greater than a specified threshold from the customer mobile phone number relational graph, and determining the potential associated mobile phone number of the mobile phone number in the customer mobile phone number relational graph by adopting the following steps:

step 802, for each mobile phone number, adding the associated mobile phone number of the mobile phone number into the queue in sequence from small to large according to the associated distance with the mobile phone number, determining that the first distance between the mobile phone number and each associated mobile phone number of the mobile phone number is the spacing distance between the mobile phone number and the corresponding side of the associated mobile phone number in the customer mobile phone number relation diagram, and the second distance between the mobile phone number and each associated mobile phone number of the mobile phone number is the associated distance between the mobile phone number and the corresponding side of the associated mobile phone number in the customer mobile phone number relation diagram, and repeating the following steps until the queue corresponding to the mobile phone number is empty, thereby obtaining a potential associated mobile phone number set of the mobile phone number:

step 8021, popping up a queue head mobile phone number from the queue, and adding the queue head mobile phone number into a potential association mobile phone number set of the mobile phone number;

step 8022, acquiring the associated mobile phone number of the head of the team mobile phone number, and judging whether the associated mobile phone number is added to the potential associated mobile phone number set of the mobile phone number for each associated mobile phone number of the head of the team mobile phone number; if not, determining a first distance and a second distance between the mobile phone number and the associated mobile phone number; if a boundary association distance corresponding to the boundary interval distance and a boundary interval distance exist, so that the first distance between the mobile phone number and the associated mobile phone number is smaller than or equal to the boundary interval distance, and the second distance between the mobile phone number and the associated mobile phone number is smaller than or equal to the boundary association distance corresponding to the boundary interval distance, taking the associated mobile phone number as a mobile phone number to be added of the mobile phone number at the head of the team; and adding the mobile phone numbers to be added of the mobile phone numbers at the head of the queue into the queue in sequence from small to large according to the second distance from the mobile phone numbers.

Wherein, determining a calculation manner of the first distance between the mobile phone number and the associated mobile phone number (the second distance is similar and is not described here again): is M _i IN (d1(i) + d2(i)), where d1(i) is a first distance between the mobile phone number and an ith potential associated mobile phone number IN the set of potential associated mobile phone numbers that have been added to the mobile phone number and that have direct edge connection with the associated mobile phone number IN the mobile phone number relationship diagram of the customer, and d2(i) is a distance between the associated mobile phone number and an edge that corresponds to the ith potential associated mobile phone number IN the set of potential associated mobile phone numbers that have been added to the mobile phone number and that have direct edge connection with the associated mobile phone number IN the mobile phone number relationship diagram of the customer.

Fig. 9 is a flowchart three of determining a potential associated mobile phone number of one mobile phone number in the embodiment of the present invention, where another method for determining a potential associated mobile phone number of one mobile phone number is provided. In an embodiment, for each mobile phone number, determining a potential associated mobile phone number of the mobile phone number according to a plurality of boundary separation distances and a boundary associated distance corresponding to each boundary separation distance includes:

step 901, for each mobile phone number a, adding all the associated mobile phone numbers of the mobile phone number a to-be-selected set corresponding to the mobile phone number a; initializing a third distance corresponding to each associated mobile phone number of the mobile phone number A as a spacing distance between the mobile phone number A and a corresponding edge of the associated mobile phone number in a customer mobile phone number relational graph, and initializing a corresponding fourth distance as an associated distance between the mobile phone number A and the corresponding edge of the associated mobile phone number in the customer mobile phone number relational graph; initializing the corresponding third distance to a numerical value larger than all boundary spacing distances and initializing the corresponding fourth distance to a numerical value larger than all boundary association distances for other mobile phone numbers except the mobile phone number A and the mobile phone number associated with the mobile phone number A;

step 902, selecting a corresponding mobile phone number B with the minimum association distance from the to-be-selected set corresponding to the mobile phone number A; if the boundary interval distance and the boundary association distance corresponding to the boundary interval distance exist, so that the third distance between the mobile phone number A and the selected mobile phone number B is smaller than or equal to the boundary interval distance, and the fourth distance between the mobile phone number A and the selected mobile phone number B is smaller than or equal to the boundary association distance corresponding to the boundary interval distance, adding the selected mobile phone number B into a potential association mobile phone number set of the mobile phone number A, and deleting the selected mobile phone number B from a to-be-selected set corresponding to the mobile phone number A; otherwise, stopping determining the potential associated mobile phone number of the mobile phone number A;

step 903, sequentially judging whether the associated mobile phone number C is added to a potential associated mobile phone number set of the mobile phone number A or not for each associated mobile phone number C of the selected mobile phone number B, and if not, adding the associated mobile phone number C to a to-be-selected set corresponding to the mobile phone number A;

step 904, updating the third distance of the associated mobile phone number C to min for each associated mobile phone number C of the selected mobile phone number B in turn (d 1) _Co ,d1 _B + d1(B, C)), where d1 _Co Is the third distance, d1, of the associated phone number C before the update _B Is the third distance of the selected mobile phone number B, d1(B, C) is the spacing distance of the corresponding edges of the mobile phone number B and the mobile phone number C in the mobile phone number relation graph of the client, and the fourth distance for updating the associated mobile phone number C is min (d 2) _Co ,d2 _B + d2(B, C)), where d2 _Co Is the fourth distance, d2, of the associated phone number C before updating _B The fourth distance of the selected mobile phone number B, and d2(B, C) is the association distance of the corresponding edges of the mobile phone number B and the mobile phone number C in the mobile phone number relation graph of the client;

step 905, after all the associated mobile phone numbers of the selected mobile phone number B are executed in

steps

903 and 904, step 902 is executed.

Fig. 10 is a flowchart illustrating an embodiment of determining whether to support mobile phone number modification by face recognition, where in an embodiment, if a new mobile phone number is in a set of potential associated mobile phone numbers of an old mobile phone number, face recognition is performed on a client according to the set of potential associated mobile phone numbers and a face recognition threshold of the client, and whether to support mobile phone number modification is determined according to a face recognition result, including:

step 1001, comparing the collected customer faces with the old mobile phone numbers and the customer faces in the potential associated mobile phone number set of the old mobile phone numbers one by one to obtain matching values;

step 1002, determining the face corresponding to the mobile phone number with the maximum matching value as the face of the client handling the modification of the mobile phone number;

step 1003, if the determined customer corresponding to the face and the customer corresponding to the old mobile phone number are the same customer, determining that the mobile phone number modification is supported, otherwise, not supporting the mobile phone number modification.

Fig. 11 is a flowchart of modifying a face recognition threshold of a client in an embodiment of the present invention, where in an embodiment, determining an association distance between an old mobile phone number and a new mobile phone number, and modifying the face recognition threshold of the client according to the association distance includes:

step 1101, determining the association distance between two corresponding nodes of the old mobile phone number and the new mobile phone number in the customer mobile phone number relation graph according to the shortest path algorithm;

step 1102, determining the association degree of the old mobile phone number and the new mobile phone number according to the association distance between two corresponding nodes of the old mobile phone number and the new mobile phone number in the mobile phone number relation graph of the customer;

1103, selecting historical modification data with the association degree equal to the association degree of the corresponding two mobile phone numbers from the historical modification data according to the association degree;

1104, determining a face recognition threshold corresponding to the association degree according to the selected historical modification data, so that when the face recognition threshold of the selected historical modification data is set as the face recognition threshold corresponding to the association degree, the corresponding risk coefficient is less than or equal to a set value;

step 1105, the face recognition threshold corresponding to the modified mobile phone number is modified to the face recognition threshold corresponding to the association degree of the two mobile phone numbers and the maximum value of the face recognition threshold before the client.

The association degree of the old mobile phone number and the new mobile phone number is determined according to the association distance between two corresponding nodes of the old mobile phone number and the new mobile phone number in the mobile phone number relation diagram of the customer, and the association degree can be as follows: determining the association degree of the old mobile phone number and the new mobile phone number as follows:

wherein s is ₁ The correlation distance between two corresponding nodes of the old mobile phone number and the new mobile phone number in the mobile phone number relation graph of the customer is obtained.

For each historical modification data, the association degree of the two mobile phone numbers corresponding to the historical modification data is determined according to the following method: determining the shortest distance between the two mobile phone numbers according to a relation graph of the mobile phone numbers of the customers and an associated distance and shortest path algorithm corresponding to each edge on the graph, and taking the shortest distance as an associated distance s between the two mobile phone numbers; determining the association degree of the two mobile phone numbers as 10 ^-s 。

The corresponding risk coefficient is determined as the proportion of the risk data in the selected historical modified data when the face recognition threshold of the selected historical modified data is set as the face recognition threshold corresponding to the association distance. The risk data is data with risk, for example, when the face recognition threshold is set to be low, others can tamper the mobile phone number of the customer to cause risk to the customer, and if the setting value is set to be high, the risk data (before modification) is no longer risk data (after modification). The higher the face recognition threshold, the smaller this risk factor. ). The set value can be a risk coefficient corresponding to all the mobile phone number modification service data (namely the proportion of the risk data in all the mobile phone number modification service data), and the risk coefficient is stored in the bank server.

In summary, in the method provided by the embodiment of the present invention, a customer-mobile phone number relationship diagram of a banking outlet is constructed; determining a potential associated mobile phone number set of each mobile phone number according to the relation graph of the mobile phone numbers of the clients and historical modification data; when a customer modifies the mobile phone number at a bank outlet, if the new mobile phone number is in a potential associated mobile phone number set of the old mobile phone number, carrying out face recognition on the customer according to the potential associated mobile phone number set and a face recognition threshold value of the customer, and judging whether the modification of the mobile phone number is supported or not according to a face recognition result; if the new mobile phone number is not in the set of potential associated mobile phone numbers of the old mobile phone number, determining the associated distance between the old mobile phone number and the new mobile phone number, correcting the face recognition threshold value of the customer according to the associated distance, carrying out face recognition on the customer according to the corrected face recognition threshold value, and judging whether the mobile phone number modification is supported or not according to the face recognition result. In the process, whether the mobile phone number modification is supported or not is judged through a customer mobile phone number relation graph, historical modification data and a face recognition threshold value of a bank outlet, and the face recognition threshold value can be modified according to the association distance between the old mobile phone number and the new mobile phone number, so that the risk control of mobile phone number modification can be accurately carried out in real time.

The embodiment of the invention also provides a device for controlling the risk of the mobile phone number of the bank outlet, the principle of which is similar to that of a method for controlling the risk of the mobile phone number of the bank outlet, and the detailed description is omitted.

Fig. 12 is a schematic diagram of a mobile phone number risk control device of a banking outlet in an embodiment of the present invention, including:

a customer mobile phone number relation graph building module 1201, configured to build a customer mobile phone number relation graph in a bank;

a potential associated person determining module 1202, configured to determine, for each mobile phone number, a set of potential associated mobile phone numbers of the mobile phone number according to the customer mobile phone number relationship diagram and the history modification data;

a mobile phone number modification judging module 1203, configured to, when a client modifies a mobile phone number at a banking outlet, if a new mobile phone number is in a set of potential associated mobile phone numbers of an old mobile phone number, perform face recognition on the client according to the set of potential associated mobile phone numbers and a face recognition threshold of the client, and judge whether the modification of the mobile phone number is supported according to a face recognition result;

a face recognition threshold correction module 1204, configured to determine, if the new mobile phone number is not in the set of potential associated mobile phone numbers of the old mobile phone number, an associated distance between the old mobile phone number and the new mobile phone number, correct a face recognition threshold of the customer according to the associated distance, perform face recognition on the customer according to the corrected face recognition threshold, and determine, according to a face recognition result, whether or not to support mobile phone number modification.

In an embodiment, the customer mobile phone number relationship graph building module is specifically configured to:

determining an associated mobile phone number of each mobile phone number;

calculating the association degree between each mobile phone number and the associated mobile phone number of the mobile phone number;

calculating the association distance between each mobile phone number and the associated mobile phone number of the mobile phone number based on the association degree between each mobile phone number and the associated mobile phone number of the mobile phone number;

and constructing a customer mobile phone number relation graph according to the association distance.

and acquiring two accounts related to each piece of transfer data, and determining two mobile phone numbers corresponding to the two accounts as the associated mobile phone numbers of the other party.

for each mobile phone number, determining the quantity of transfer data related between the mobile phone number and each associated mobile phone number of the mobile phone number as the associated data quantity corresponding to each associated mobile phone number of the mobile phone number;

for each mobile phone number, determining the association degree between the mobile phone number and each associated mobile phone number of the mobile phone number as the ratio of the associated data amount corresponding to each associated mobile phone number of the mobile phone number to the maximum value of the associated data.

for each mobile phone number, determining the association distance between the mobile phone number and each associated mobile phone number of the mobile phone number as-lg (r), wherein r is the association degree between the mobile phone number and each associated mobile phone number of the mobile phone number, and lg is a logarithmic function with the base 10 as the base.

each mobile phone number is used as a node;

if and only if the two mobile phone numbers are the related mobile phone numbers of the opposite party, the nodes corresponding to the two mobile phone numbers have edges;

and determining the association distance of the edge as the association distance between the two mobile phone numbers corresponding to the edge, and determining the interval distance of the edge as 1.

In an embodiment, the potential related person determining module is specifically configured to:

determining a plurality of boundary interval distances corresponding to the customer mobile phone number relation graph and a boundary association distance corresponding to each boundary interval distance according to historical modification data;

and for each mobile phone number, determining a potential associated mobile phone number set of the mobile phone number according to the plurality of boundary spacing distances and the boundary associated distance corresponding to each boundary spacing distance.

In an embodiment, the potential related person determination module is specifically configured to:

for each piece of historical modification data, determining a mobile phone number related in the historical modification data;

determining the association distance and the interval distance between the mobile phone numbers related in the historical modification data according to the mobile phone number relation graph of the customer;

determining a partial order of the historical modified data according to the association distance and the interval distance, wherein for any two pieces of historical modified data, the partial order is used for determining whether a first historical modified data of the two pieces of historical modified data is larger than a second historical modified data of the two pieces of historical modified data;

determining a plurality of maximum historical modified data in all historical modified data according to the partial order of the historical modified data, wherein the maximum historical modified data are maximum elements of the partial order;

for each maximum historical modification data, determining the interval distance between the mobile phone numbers involved in the maximum historical modification data as a boundary interval distance, and determining the association distance between the mobile phone numbers involved in the maximum historical modification data as a boundary association distance corresponding to the boundary interval distance.

when the structural complexity of the customer mobile phone number relational graph is smaller than a first threshold value, calculating the association distance between the mobile phone number and all other mobile phone numbers and the spacing distance between the mobile phone number and all mobile phone numbers for each mobile phone number in the customer mobile phone number relational graph;

and for each other mobile phone number, if a boundary interval distance and a boundary association distance corresponding to the boundary interval distance exist, so that the interval distance between the mobile phone number and the other mobile phone number is smaller than or equal to the boundary interval distance, and the association distance between the mobile phone number and the other mobile phone number is smaller than or equal to the boundary association distance corresponding to the boundary interval distance, determining the other mobile phone number as a potential associated mobile phone number of the mobile phone number.

In an embodiment, the mobile phone number modification and determination module is specifically configured to:

comparing the collected customer faces with the old mobile phone numbers and the customer faces in the potential associated mobile phone number set of the old mobile phone numbers one by one to obtain matching values;

determining the face corresponding to the mobile phone number with the maximum matching value as the face of the client handling the modification of the mobile phone number;

and if the determined customer corresponding to the face and the customer corresponding to the old mobile phone number are the same customer, determining that the mobile phone number modification is supported, otherwise, not supporting the mobile phone number modification.

In an embodiment, the face recognition threshold modification module is specifically configured to:

determining the association distance between two corresponding nodes of the old mobile phone number and the new mobile phone number in the customer mobile phone number relation graph according to the shortest path algorithm;

according to the association distance, selecting historical modification data of which the association distance of the two corresponding mobile phone numbers is equal to the association distance from the historical modification data;

determining a face recognition threshold corresponding to the association distance according to the selected historical modification data, so that when the face recognition threshold of the selected historical modification data is set as the face recognition threshold corresponding to the association distance, the corresponding risk coefficient is less than or equal to a set value;

and correcting the face recognition threshold corresponding to the modified mobile phone number to be the face recognition threshold corresponding to the association distance between the two mobile phone numbers and the maximum value of the face recognition threshold before the client.

In summary, in the apparatus provided in the embodiment of the present invention, the customer mobile phone number relationship graph building module is configured to build a customer mobile phone number relationship graph in a bank; the potential associated person determining module is used for determining a potential associated mobile phone number set of each mobile phone number according to the customer mobile phone number relation graph and the historical modification data; the mobile phone number modification judging module is used for carrying out face recognition on the customer according to the potential associated mobile phone number set and the face recognition threshold value of the customer when the customer modifies the mobile phone number at a bank branch point and if a new mobile phone number is in the potential associated mobile phone number set of an old mobile phone number, and judging whether the modification of the mobile phone number is supported or not according to the face recognition result; and the face recognition threshold correction module is used for determining the association distance between the old mobile phone number and the new mobile phone number if the new mobile phone number is not in the potential association mobile phone number set of the old mobile phone number, correcting the face recognition threshold of the customer according to the association distance, carrying out face recognition on the customer according to the corrected face recognition threshold, and judging whether the mobile phone number is supported to be modified according to the face recognition result. In the process, whether the mobile phone number modification is supported or not is judged through a customer mobile phone number relation graph, historical modification data and a face recognition threshold value of a bank outlet, and the face recognition threshold value can be modified according to the association distance between the old mobile phone number and the new mobile phone number, so that the risk control of mobile phone number modification can be accurately carried out in real time.

Fig. 13 is a schematic diagram of a computer device in an embodiment of the present invention, where the computer device 1300 includes a memory 1310, a processor 1320, and a computer program 1330 stored in the memory 1310 and operable on the processor 1320, and when the processor 1320 executes the computer program 1330, the method for controlling the risk of the mobile phone number of the bank outlet is implemented.

It will be appreciated by one skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program service system embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program business systems according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. A bank branch mobile phone number risk control method is characterized by comprising the following steps:

constructing a customer mobile phone number relation diagram of a bank outlet;

2. The method as claimed in claim 1, wherein constructing a phone number relationship diagram for a customer at a banking site comprises:

determining an associated mobile phone number of each mobile phone number;

3. The method of claim 2, wherein determining the associated phone number for each phone number comprises:

4. The method of claim 3, wherein calculating the association between each phone number and the associated phone number for that phone number comprises:

5. The method of claim 2, wherein calculating the association distance between each mobile phone number and the associated mobile phone number of the mobile phone number based on the association degree between each mobile phone number and the associated mobile phone number of the mobile phone number comprises:

6. The method of claim 2, wherein constructing a customer mobile phone number relationship graph based on the association distances comprises:

each mobile phone number is used as a node;

7. The method of claim 1, wherein determining, for each phone number, a set of potential associated phone numbers for the phone number based on the customer phone number relationship graph and the historical modification data comprises:

8. The method of claim 7, wherein determining a plurality of boundary separation distances and a boundary association distance corresponding to each boundary separation distance for the customer mobile phone number relationship graph based on historical modification data comprises:

for each piece of historical modification data, determining the mobile phone number related in the historical modification data;

determining the association distance and the interval distance between the mobile phone numbers related in the historical modification data according to the mobile phone number relation graph of the client;

determining a plurality of maximum historical modification data in all the historical modification data according to the partial order of the historical modification data, wherein the maximum historical modification data are maximum elements of the partial order;

9. The method of claim 8, wherein determining a partial order of historical modification data as a function of the correlation distance and the separation distance comprises:

10. The method of claim 9, wherein for each mobile phone number, determining the potential associated mobile phone number for the mobile phone number according to the plurality of boundary separation distances and the boundary associated distance corresponding to each boundary separation distance comprises:

in the customer mobile phone number relation graph, for each mobile phone number, calculating the association distance between the mobile phone number and all other mobile phone numbers and the spacing distance between the mobile phone number and all mobile phone numbers;

and for each other mobile phone number, if the boundary interval distance and the boundary association distance corresponding to the boundary interval distance exist, enabling the interval distance between the mobile phone number and the other mobile phone number to be smaller than or equal to the boundary interval distance, and enabling the association distance between the mobile phone number and the other mobile phone number to be smaller than or equal to the boundary association distance corresponding to the boundary interval distance, and determining the other mobile phone number as the potential association mobile phone number of the mobile phone number.

11. The method of claim 1, wherein if the new mobile phone number is in the set of potential associated mobile phone numbers of the old mobile phone number, performing face recognition on the customer according to the set of potential associated mobile phone numbers and a face recognition threshold of the customer, and determining whether the mobile phone number modification is supported according to the face recognition result comprises:

12. The method of claim 2, wherein determining an associated distance between an old phone number and a new phone number, and modifying the face recognition threshold of the customer based on the associated distance comprises:

determining the association degree of the old mobile phone number and the new mobile phone number according to the association distance between two corresponding nodes of the old mobile phone number and the new mobile phone number in the mobile phone number relation graph of the customer;

according to the association degree, selecting historical modification data of which the association degree of the corresponding two mobile phone numbers is equal to the association degree from the historical modification data;

determining a face recognition threshold corresponding to the association degree according to the selected historical modification data, so that when the face recognition threshold of the selected historical modification data is set as the face recognition threshold corresponding to the association degree, the corresponding risk coefficient is less than or equal to a set value;

and correcting the face recognition threshold corresponding to the modified mobile phone number to be the face recognition threshold corresponding to the association degree of the two mobile phone numbers and the maximum value of the face recognition threshold before the client.

13. A bank branch mobile phone number risk control device is characterized by comprising:

14. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 12 when executing the computer program.

15. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 12.

16. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 12.