CN113610632A - Bank outlet face recognition method and device based on block chain - Google Patents
Bank outlet face recognition method and device based on block chain Download PDFInfo
- Publication number
- CN113610632A CN113610632A CN202110918206.2A CN202110918206A CN113610632A CN 113610632 A CN113610632 A CN 113610632A CN 202110918206 A CN202110918206 A CN 202110918206A CN 113610632 A CN113610632 A CN 113610632A
- Authority
- CN
- China
- Prior art keywords
- face recognition
- bank
- outlet
- parameter threshold
- transaction
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000006870 function Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 230000003247 decreasing effect Effects 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Abstract
The invention discloses a bank outlet face recognition method and a device based on a block chain, which relate to the technical field of block chains, and the method comprises the following steps: acquiring historical transaction data of each bank outlet; determining transaction risk coefficients of all banking outlets according to historical transaction data of all banking outlets; estimating a face recognition parameter threshold of each bank outlet according to a transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on a block chain network, wherein the face recognition parameter threshold of each bank outlet is a parameter threshold used when each bank outlet performs face recognition on a client; and according to the face recognition parameter threshold value of each bank outlet, carrying out face recognition on the customer in the edge computing system of each bank outlet to generate a face recognition result. The invention can effectively reduce the waiting time for the face recognition of the client and reduce the pressure of the face recognition system of the bank.
Description
Technical Field
The invention relates to the technical field of block chains, in particular to a bank outlet face recognition method and device based on a block chain.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, the face recognition of a client at a bank outlet is usually completed at a bank background server. This approach not only results in a long time for face recognition, but also centralized face recognition puts a lot of stress on the backend server. When the network of a bank outlet is not good, the face recognition takes more time, and the customer experience is poor.
With the advance of edge computing technology, it is possible to directly perform face recognition at bank outlets or at bank self-service equipment. However, because of uncertainty of factors such as location, the risk of face recognition at a bank outlet is much higher than that of face recognition at a bank background server, and if face parameters are configured unreasonably, various transaction risks can be caused.
Disclosure of Invention
The embodiment of the invention provides a bank outlet face recognition method based on a block chain, which is used for solving the technical problems that in the prior art, the time consumption of a face recognition process is long and the system pressure of a background server is high when a bank background server carries out face recognition on a client, and comprises the following steps: acquiring historical transaction data of each bank outlet; determining transaction risk coefficients of all banking outlets according to historical transaction data of all banking outlets; estimating a face recognition parameter threshold of each bank outlet according to a transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on a block chain network, wherein the face recognition parameter threshold of each bank outlet is a parameter threshold used when each bank outlet performs face recognition on a client; and according to the face recognition parameter threshold value of each bank outlet, carrying out face recognition on the customer in the edge computing system of each bank outlet to generate a face recognition result.
The embodiment of the invention also provides a block chain-based bank outlet face recognition device, which is used for solving the technical problems that the time consumption of a face recognition process is longer and the system pressure of a background server is higher when a bank background server carries out face recognition of a client in the prior art, and comprises the following steps: the transaction data acquisition module is used for acquiring historical transaction data of each bank outlet; the transaction risk coefficient determining module is used for determining the transaction risk coefficient of each bank outlet according to the historical transaction data of each bank outlet; the face recognition parameter threshold estimation module is used for estimating the face recognition parameter threshold of each bank outlet according to the transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on a block chain network, wherein the face recognition parameter threshold of each bank outlet is a parameter threshold used when each bank outlet performs face recognition on a client; and the face recognition module is used for carrying out face recognition on the customer in the edge computing system of each bank outlet according to the face recognition parameter threshold of each bank outlet so as to generate a face recognition result.
The embodiment of the invention also provides computer equipment for solving the technical problems that the time consumption of a face recognition process is long and the system pressure of a background server is high when the face recognition of a client is carried out on the background server of a bank in the prior art.
The embodiment of the invention also provides a computer readable storage medium, which is used for solving the technical problems that the time consumption of a face recognition process is long and the system pressure of a background server is high when the face recognition of a client is carried out on the background server of a bank in the prior art.
After the historical transaction data of each bank outlet is obtained, the transaction risk coefficient of each bank outlet is determined according to the historical transaction data of each bank outlet, then, the intelligent contract configured in advance on the block chain network is utilized, the face recognition parameter threshold value used when the face recognition of the customer is carried out by each bank outlet is estimated according to the transaction risk coefficient of each bank outlet, and finally, the face recognition of the customer is carried out in the edge computing system of each bank outlet according to the face recognition parameter threshold value of each bank outlet, so that a face recognition result is generated.
Compared with the technical scheme of carrying out face recognition on the customer in the bank background server in the prior art, the embodiment of the invention carries out face recognition on the customer in the edge computing system of the bank branch, can effectively reduce the waiting time for the face recognition of the customer, lightens the pressure of the face recognition system of the bank, estimates the face recognition parameter threshold value used when the face recognition is carried out on the customer by each bank branch point by using the intelligent contract pre-configured on the block chain network, and can reduce the transaction risk when the face recognition is carried out on the customer by the edge computing system of the bank branch point.
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 identifying a face of a banking outlet based on a block chain according to an embodiment of the present invention;
fig. 2 is a flow chart of face recognition based on a block chain according to an embodiment of the present invention;
fig. 3 is a flowchart of a block chain-based cross-node face recognition process according to an embodiment of the present invention;
fig. 4 is a flow chart of obtaining a face recognition parameter threshold according to an embodiment of the present invention;
fig. 5 is a flow chart of adjusting a face recognition parameter threshold according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a banking outlet face recognition device based on a block chain according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a computer device provided in an embodiment of the present 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.
The embodiment of the invention provides a bank outlet face recognition method based on a block chain, and fig. 1 is a flow chart of the bank outlet face recognition method based on the block chain, as shown in fig. 1, the method comprises the following steps:
s101, obtaining historical transaction data of each bank outlet.
It should be noted that, in the embodiment of the present invention, the historical transaction data obtained through the above step S101 includes, but is not limited to: risk transaction data and customer transaction data. The customer transaction data may include a customer work address, a home address, and the like, which can predict the customer set of each banking site. From the historical transaction data for each banking site, a set of customers for each banking site may be determined.
In one embodiment, each bank branch may collect transaction data thereof in real time and upload the collected transaction data to a blockchain network, where the blockchain network may be a blockchain network formed by using each bank branch as a blockchain storage node, or may be an individual blockchain network, and each bank branch communicates with the blockchain network through a blockchain client to receive data pushed by the blockchain network or upload data to the blockchain network.
And S102, determining the transaction risk coefficient of each bank outlet according to the historical transaction data of each bank outlet.
It should be noted that the transaction risk factor is used to measure a quantitative index that may cause loss to the customer when the transaction is made at each banking outlet. Because different banking outlets are located in different environments and serve different customer groups, the transaction risk factors of different banking outlets are different. After the historical transaction data of each bank outlet is obtained, the total transaction data related to face recognition, the risk transaction data and the risk transaction data related to face recognition of each bank outlet can be counted, and then the transaction risk coefficient of each bank outlet is determined.
In one embodiment, the transaction risk factor for each banking outlet may be calculated as follows: determining risk types according to risk transaction data (or risk transaction data related to face recognition) in historical transaction data of each bank outlet, wherein the risk types account for the proportion of the risk data in the whole transaction data, and risk indexes of each risk type comprise risk coefficients and probabilities; and determining the transaction risk coefficient of each bank outlet according to the proportion of the risk data in the whole transaction data and the risk index of each risk type. The impact of different types of risk on the customer is different. The loss caused by the corresponding risk type to the client can be determined based on the data corresponding to each risk type, a large amount of data is stored in a bank database, the data can sufficiently reflect the rule that the risk causes the loss to the client by the majority theorem, and the risk value corresponding to each risk type can be measured by using the statistical average value, namely the risk coefficient corresponding to each risk type is set as the average value of the loss caused by the corresponding risk type to the client. Meanwhile, the probability of each risk type also reflects the influence of the risk type on the client, and the larger the probability is, the larger the influence is, and the larger the risk of the client is. The proportion of risk data to the overall transaction data also reflects the impact of risk on the transaction. After the risk types, the risk coefficient and the probability of each risk type, and the proportion of the risk data in the whole transaction data are determined, the transaction risk coefficient of the corresponding bank outlet can be determined, for example, the transaction risk coefficient is directly set as: t × sum (log (ri × ni)) or t × sum (ri × ni), where ri is the risk coefficient of the ith risk type, ni is the probability of the ith risk type, t is the proportion of risk data to the entire transaction data, and sum is a summation function.
And S103, estimating the face recognition parameter threshold of each bank outlet according to the transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on the block chain network, wherein the face recognition parameter threshold of each bank outlet is a parameter threshold used when the face recognition is performed on the customer by each bank outlet.
It should be noted that the intelligent contract in the embodiment of the present invention refers to a section of program pre-configured on the block chain network, and estimates a face recognition parameter threshold used when performing face recognition on a client according to a transaction risk coefficient of each bank branch by using the intelligent contract pre-configured on the block chain network.
And S104, carrying out face recognition on the customer in the edge computing system of each bank outlet according to the face recognition parameter threshold of each bank outlet to generate a face recognition result.
In specific implementation, after the face recognition parameter threshold of each bank outlet is determined, the face recognition parameter threshold of each bank outlet can be stored in the edge computing system of each bank outlet, so that each bank outlet can directly perform face recognition on a customer in the edge computing system.
In order to reduce the transaction risk of website face recognition, in an embodiment, as shown in fig. 2, in the method for bank website face recognition based on a block chain provided in the embodiment of the present invention, the step S104 may generate a face recognition result by the following steps:
s201, storing the face recognition parameter threshold value of each bank outlet to a block chain network;
s202, according to the face recognition parameter threshold value of each bank outlet stored on the block chain network, face recognition is carried out on the customer in the edge computing system of each bank outlet, and a face recognition result is generated.
In the embodiment of the invention, the face recognition parameter threshold of each bank outlet is stored in the block chain network, so that the face recognition parameter threshold can be ensured not to be tampered.
The pressure of a bank background server can be greatly reduced by performing face recognition on a customer in an edge computing system of a bank outlet, but the transaction risk is higher by performing face recognition on the customer in the edge computing system of the bank outlet, so that in one embodiment, as shown in fig. 3, in the bank outlet face recognition method based on the block chain provided in the embodiment of the present invention, the above-mentioned S104 can be implemented by the following steps when being implemented specifically:
s301, when receiving a business transaction request initiated by a target customer to a target banking site, judging whether the target customer is in a customer set of the target banking site, wherein the target customer is any one customer, and the target banking site is any one banking site;
s302, if the target client is not in the client set of the target bank branch, carrying out face recognition on the target client in a bank background server according to a face recognition parameter threshold value stored in the bank background server in advance to generate a face recognition result;
s303, if the target customer is in the customer set of the target bank branch, carrying out face recognition on the target customer in the edge computing system of the target bank branch according to the face recognition parameter threshold of the target bank branch to generate a face recognition result.
The face recognition parameter threshold and the probability of the occurrence of the transaction risk in face recognition form an inverse relationship, that is, the higher the face recognition parameter threshold is set, the lower the probability of occurrence of the risk is. The greater the risk coefficient of a bank outlet is, the greater the risk of face recognition on the premise that the face recognition parameter threshold is the same, and in order to ensure that the risk of face recognition on the bank outlet is low, the face recognition parameter threshold corresponding to the bank outlet needs to be increased appropriately.
In order to ensure that the risk of face recognition of the bank outlets is low, in one embodiment, the face recognition parameter threshold of each bank outlet is estimated according to the transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on a block chain network according to formula (1):
L2＝MAXL-(MAXL-L1)×f(r) (1)
wherein L is2Representing a face recognition parameter threshold value when the face recognition is carried out on the client by each bank network point; the MAXL represents the maximum value of the face recognition parameter threshold; l1 represents the face recognition parameter threshold when the bank backend server performs face recognition on the client; f represents a monotonically decreasing function; r represents a transaction risk coefficient. The formula can ensure that the face recognition parameter threshold of the bank outlet is directly related to the transaction risk of the bank outlet, and the larger the transaction risk coefficient is, the larger the face recognition parameter threshold of the bank outlet is.
In another embodiment, the parameter threshold of the face recognition is directly related to the passing rate or the false recognition of the face recognition. As shown in fig. 4, in the method for identifying a face of a bank outlet based on a block chain provided in the embodiment of the present invention, a face identification parameter threshold of each bank outlet may be obtained through the following steps:
s401, calculating the passing rate or the false recognition rate of each bank branch according to the transaction risk coefficient of each bank branch by using an intelligent contract configured in advance on a block chain network;
s402, obtaining the face recognition parameter threshold value of each bank outlet according to the passing rate or the false recognition rate of each bank outlet.
It should be noted that, in the embodiment of the present invention, the passing rate or the recognition rate should be in a one-to-one correspondence relationship with the face recognition parameter threshold, and the larger the face recognition parameter threshold is, the lower the passing rate is, the higher the recognition rate is. s
Further, in the method for identifying a face of a bank outlet based on a block chain provided in the embodiment of the present invention, the passing rate or the false recognition rate of each bank outlet may be calculated by the following formula:
T2＝1-(1-T1)/f(r) (2)
F2＝1-(1-F1)×f(r) (3)
wherein, T2The passing rate of each bank website when the user carries out face recognition on the user by each bank website is represented; t is1Representing the passing rate of each bank outlet when the bank background server carries out face recognition on the client; f2The method comprises the steps of representing the false recognition rate of each bank website when each bank website carries out face recognition on a client; f1Representing the false recognition rate of each bank outlet when the bank background server carries out face recognition on the client; f represents a monotonically decreasing function; r represents a transaction risk coefficient. The above formula can also ensure that the face recognition parameter threshold of the bank outlet is directly related to the transaction risk of the bank outlet, and the larger the transaction risk coefficient is, the larger the face recognition parameter threshold of the bank outlet is.
Alternatively, the monotonically decreasing function used in the embodiment of the present invention may be as shown in formula (4):
f(r)＝1-r (4)
where f (r) represents a monotonically decreasing function with r as the argument.
The parameter setting of the face recognition of the bank server is mature, a large amount of data can be used, and the risk is basically controllable. The risk transaction proportion corresponding to the face recognition of the bank server can be set as a reference risk transaction proportion, and then the face recognition parameter threshold of each bank outlet is adjusted according to the reference risk transaction proportion.
In an embodiment, as shown in fig. 5, the method for identifying a face of a banking outlet based on a block chain according to the embodiment of the present invention may further adjust the face identification parameter threshold of each banking outlet by the following steps:
s501, acquiring transaction data of face recognition of a customer by each bank network;
s502, determining the risk transaction proportion of each bank website according to the transaction data of face recognition of each bank website to the client;
s503, judging whether the risk transaction proportion of each bank outlet is larger than a reference risk transaction proportion, wherein the reference risk transaction proportion is a risk transaction proportion corresponding to the face recognition of the bank server;
s504, under the condition that the risk transaction proportion of any one bank outlet is larger than the reference risk transaction proportion, the face recognition parameter threshold value of the bank outlet is increased until the risk transaction proportion of the bank outlet is smaller than or equal to the reference risk transaction proportion.
Specifically, the face recognition parameter threshold of the bank outlet or the monotonically decreasing function of the passing rate or the false recognition rate of the face recognition may be adjusted to the face recognition parameter threshold of the bank outlet, so that the risk transaction ratio of the bank outlet is smaller than or equal to the reference risk transaction ratio.
As an optional scheme, according to the method for identifying a face of a banking outlet based on a block chain provided in the embodiment of the present invention, a method for setting a face parameter of a banking transaction applicable to different transaction risks of the banking outlet may be provided, and specifically, the method may include:
1) and predicting the customer set of the banking outlet according to historical transaction data (such as the working address, the home address and the like of the customer), namely determining the customer set corresponding to the banking outlet. The method comprises the steps of obtaining face recognition data of a customer set from a bank face recognition system, downloading the data to a database of a bank outlet, and encrypting the data by using a public key of the bank outlet before downloading. The data should also include parameters for face recognition at the bank server.
2) And acquiring the proportion r of the risk data in the historical transaction data of the bank outlets. For example, the ratio of the sum of the risk data related to face recognition in the risk transaction and the sum of the data related to face recognition in the total transaction is used as the transaction risk coefficient.
3) Estimating the parameters of the client for face recognition by using the intelligent contract of the block chain, for example, setting the threshold value of the face recognition of the high-risk scene to be L according to the transaction risk coefficient2. L1 is a face recognition threshold for face recognition at the bank server, and MAXL is the maximum value of the face recognition threshold. L1 and L2Corresponding to the same client. And storing the calculated parameters into the block chain network.
4) The new threshold is estimated using the passage rate and the false positive rate. For example, the passing rate of face recognition in a bank outlet edge computing system is set as T2，T1The threshold value of the face recognition algorithm is found in the bank outlet edge computing system based on the corresponding relation between the passing rate of the face recognition algorithm and the threshold value. The false recognition rate is calculated similarly, and the false recognition rate of the face recognition in the bank outlet edge calculation system is set to be F2，F1The human face recognition error rate is the human face recognition error rate when the bank server carries out human face recognition.
5) When the customer makes a transaction at a banking outlet, whether the customer is in a customer set corresponding to the banking outlet is determined. If yes, face recognition is carried out in an edge computing system of the bank outlet based on the parameters determined in the step; if not, the user returns to the face recognition system of the bank.
6) Acquiring transaction data for face recognition in an edge computing system of a bank outlet, and confirming the proportion p of risk data of the data. If the ratio p is larger than the ratio q of the corresponding risk transaction of the bank face recognition system, the function f in the step 3 is adjusted to make L2 larger until the corresponding ratio is smaller than or equal to q.
Based on the same inventive concept, the embodiment of the invention also provides a bank outlet face recognition device based on the block chain, which is described in the following embodiment. Because the principle of solving the problems of the device is similar to the block chain-based bank outlet face recognition method, the implementation of the device can refer to the implementation of the block chain-based bank outlet face recognition method, and repeated parts are not repeated.
Fig. 6 is a schematic diagram of a block chain-based banking outlet face recognition apparatus provided in an embodiment of the present invention, and as shown in fig. 6, the apparatus includes: a transaction data acquisition module 61, a transaction risk factor determination module 62, a face recognition parameter threshold estimation module 63, and a face recognition module 64.
The transaction data acquisition module 61 is used for acquiring historical transaction data of each bank outlet;
the transaction risk coefficient determining module 62 is configured to determine a transaction risk coefficient of each banking outlet according to historical transaction data of each banking outlet;
a face recognition parameter threshold estimation module 63, configured to estimate, according to the transaction risk coefficient of each bank branch, a face recognition parameter threshold of each bank branch by using an intelligent contract pre-configured on the block chain network, where the face recognition parameter threshold of each bank branch is a parameter threshold used when each bank branch performs face recognition on a client;
and the face recognition module 64 is used for carrying out face recognition on the customer in the edge computing system of each bank outlet according to the face recognition parameter threshold of each bank outlet so as to generate a face recognition result.
In an embodiment, as shown in fig. 6, the device for identifying a face of a banking site based on a blockchain in an embodiment of the present invention may further include: the block chain data storage module 65 is used for storing the face recognition parameter threshold value of each bank outlet to the block chain network; in this embodiment, the face recognition module 64 is further configured to perform face recognition on the customer in the edge computing system of each bank branch according to the face recognition parameter threshold of each bank branch stored on the block chain network, so as to generate a face recognition result.
In an embodiment, in the block chain-based banking outlet face recognition apparatus provided in the embodiment of the present invention, the face recognition module 64 is further configured to: when a business transaction request initiated by a target customer to a first banking outlet is received, judging whether the target customer is in a first customer set of the first banking outlet, wherein the first banking outlet is any one banking outlet; when the target client is not in the first client set, inquiring a face recognition parameter threshold value of a second bank branch from the blockchain network, wherein the target client is a client in the second client set, and the second client set is a client set of the second bank branch; and carrying out face recognition on the target customer according to the face recognition parameter threshold of the second bank outlet to generate a face recognition result.
In an embodiment, as shown in fig. 6, the device for identifying a face of a banking outlet based on a blockchain according to an embodiment of the present invention further includes: the face recognition parameter threshold value acquisition module 66 is used for calculating the passing rate or the false recognition rate of each bank branch according to the transaction risk coefficient of each bank branch by using an intelligent contract configured in advance on the block chain network; and acquiring the face recognition parameter threshold of each bank outlet according to the passing rate or the false recognition rate of each bank outlet.
In an embodiment, in the block chain-based banking outlet face recognition apparatus provided in the embodiment of the present invention, the face recognition parameter threshold estimation module 63 is further configured to estimate a face recognition parameter threshold of each banking outlet according to the above formula (1).
In an embodiment, in the block chain-based face recognition device for a bank outlet provided in the embodiment of the present invention, the face recognition parameter threshold estimation module 63 is further configured to calculate a passing rate of each bank outlet according to the above formula (2), and calculate a false recognition rate of each bank outlet according to the above formula (3).
In an embodiment, in the block chain-based banking outlet face recognition apparatus provided in the embodiment of the present invention, the face recognition parameter threshold estimation module 63 is further configured to: acquiring transaction data of each bank network point for carrying out face recognition on a client; determining the risk transaction proportion of each bank website according to the transaction data of face recognition of each bank website to the client; judging whether the risk transaction proportion of each bank outlet is greater than a reference risk transaction proportion, wherein the reference risk transaction proportion is a risk transaction proportion corresponding to face recognition of a bank server; and when the risk transaction proportion of any one bank outlet is larger than the reference risk transaction proportion, increasing the face identification parameter threshold of the bank outlet until the risk transaction proportion of the bank outlet is smaller than or equal to the reference risk transaction proportion.
Based on the same inventive concept, an embodiment of the present invention further provides a computer device, so as to solve the technical problems that in the prior art, when a bank backend server performs face recognition on a client, a face recognition process takes a long time and a system pressure of the backend server is large, as shown in fig. 7, fig. 7 is a schematic diagram of a computer device provided in an embodiment of the present invention, as shown in fig. 7, the computer device 70 includes a memory 701, a processor 702, and a computer program stored in the memory 701 and capable of running on the processor 702, and when the processor 702 executes the computer program, the above bank outlet face recognition method based on a block chain is implemented.
Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, so as to solve the technical problems that in the prior art, when a bank backend server performs face recognition on a client, a face recognition process takes a long time and a system pressure of the backend server is high.
In summary, according to the method, the apparatus, the computer device, and the computer readable storage medium for bank outlets based on a block chain provided in the embodiments of the present invention, after historical transaction data of each bank outlet is obtained, a transaction risk coefficient of each bank outlet is determined according to the historical transaction data of each bank outlet, and then a face recognition parameter threshold used when a customer performs face recognition on each bank outlet is estimated according to the transaction risk coefficient of each bank outlet by using an intelligent contract pre-configured on the block chain network, and finally, the customer performs face recognition in an edge computing system of each bank outlet according to the face recognition parameter threshold of each bank outlet, so as to generate a face recognition result.
Compared with the technical scheme of carrying out face recognition on the customer in the bank background server in the prior art, the embodiment of the invention carries out face recognition on the customer in the edge computing system of the bank branch, can effectively reduce the waiting time for the face recognition of the customer, lightens the pressure of the face recognition system of the bank, estimates the face recognition parameter threshold value used when the face recognition is carried out on the customer by each bank branch point by using the intelligent contract pre-configured on the block chain network, and can reduce the transaction risk when the face recognition is carried out on the customer by the edge computing system of the bank branch point.
As will be appreciated by one skilled in the art, 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 product 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 is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products 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 (16)
1. A bank outlet face recognition method based on a block chain is characterized by comprising the following steps:
acquiring historical transaction data of each bank outlet;
determining transaction risk coefficients of all banking outlets according to historical transaction data of all banking outlets;
estimating a face recognition parameter threshold of each bank outlet according to a transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on a block chain network, wherein the face recognition parameter threshold of each bank outlet is a parameter threshold used when each bank outlet performs face recognition on a client;
and according to the face recognition parameter threshold value of each bank outlet, carrying out face recognition on the customer in the edge computing system of each bank outlet to generate a face recognition result.
2. The method as claimed in claim 1, wherein the generating of the face recognition result by performing face recognition on the customer in the edge computing system of each banking outlet according to the face recognition parameter threshold of each banking outlet comprises:
storing the face recognition parameter threshold value of each bank outlet on a block chain network;
and according to the face recognition parameter threshold value of each bank outlet stored on the block chain network, carrying out face recognition on the customer in the edge computing system of each bank outlet to generate a face recognition result.
3. The method as claimed in claim 2, wherein the generating of the face recognition result by performing face recognition on the customer in the edge computing system of each banking outlet according to the face recognition parameter threshold of each banking outlet comprises:
when a business transaction request initiated by a target customer to a target bank outlet is received, judging whether the target customer is in a customer set of the target bank outlet, wherein the target customer is any one customer, and the target bank outlet is any one bank outlet;
if the target client is not in the client set of the target bank branch, carrying out face recognition on the target client in a bank background server according to a face recognition parameter threshold value stored in the bank background server in advance to generate a face recognition result;
and if the target customer is in the customer set of the target bank outlet, carrying out face recognition on the target customer in an edge computing system of the target bank outlet according to a face recognition parameter threshold of the target bank outlet to generate a face recognition result.
4. The method of claim 1, wherein the face recognition parameter threshold for each bank outlet is estimated by the formula:
L2＝MAXL-(MAXL-L1)×f(r)；
wherein L is2Representing a face recognition parameter threshold value when the face recognition is carried out on the client by each bank network point; the MAXL represents the maximum value of the face recognition parameter threshold; l1 represents the face recognition parameter threshold when the bank backend server performs face recognition on the client; f represents a monotonically decreasing function; r represents a transaction risk coefficient.
5. The method as claimed in claim 1, wherein the estimating the face recognition parameter threshold of each banking site according to the transaction risk coefficient of each banking site by using the intelligent contract configured in advance on the blockchain network comprises:
calculating the passing rate or the false recognition rate of each bank branch according to the transaction risk coefficient of each bank branch by using an intelligent contract configured in advance on a block chain network;
and acquiring the face recognition parameter threshold of each bank outlet according to the passing rate or the false recognition rate of each bank outlet.
6. The method of claim 5, wherein the passing rate or the misrecognition rate of each banking outlet is calculated by the formula:
T2＝1-(1-T1)/f(r)；
F2＝1-(1-F1)×f(r)；
wherein, T2The passing rate of each bank website when the user carries out face recognition on the user by each bank website is represented; t is1Representing the passing rate of each bank outlet when the bank background server carries out face recognition on the client; f2The method comprises the steps of representing the false recognition rate of each bank website when each bank website carries out face recognition on a client; f1Representing the false recognition rate of each bank outlet when the bank background server carries out face recognition on the client; f represents a monotonically decreasing function; r represents a transaction risk coefficient.
7. The method of claim 1, wherein the method further comprises:
acquiring transaction data of each bank network point for carrying out face recognition on a client;
determining the risk transaction proportion of each bank website according to the transaction data of face recognition of each bank website to the client;
judging whether the risk transaction proportion of each bank outlet is greater than a reference risk transaction proportion, wherein the reference risk transaction proportion is a risk transaction proportion corresponding to face recognition of a bank server;
and under the condition that the risk transaction proportion of any one bank outlet is greater than the reference risk transaction proportion, increasing the face identification parameter threshold of the bank outlet until the risk transaction proportion of the bank outlet is less than or equal to the reference risk transaction proportion.
8. A kind of bank outlet face identification equipment based on block chain, characterized by that, including:
the transaction data acquisition module is used for acquiring historical transaction data of each bank outlet;
the transaction risk coefficient determining module is used for determining the transaction risk coefficient of each bank outlet according to the historical transaction data of each bank outlet;
the face recognition parameter threshold estimation module is used for estimating the face recognition parameter threshold of each bank outlet according to the transaction risk coefficient of each bank outlet by using an intelligent contract configured in advance on a block chain network, wherein the face recognition parameter threshold of each bank outlet is a parameter threshold used when each bank outlet performs face recognition on a client;
and the face recognition module is used for carrying out face recognition on the customer in the edge computing system of each bank outlet according to the face recognition parameter threshold of each bank outlet so as to generate a face recognition result.
9. The apparatus of claim 8, wherein the apparatus further comprises:
the block chain data storage module is used for storing the face recognition parameter threshold of each bank outlet to a block chain network;
the face recognition module is further used for carrying out face recognition on the customer in an edge computing system of each bank branch according to the face recognition parameter threshold value of each bank branch stored on the block chain network, and generating a face recognition result.
10. The apparatus of claim 9, wherein the face recognition module is further to:
when a business transaction request initiated by a target customer to a first banking outlet is received, judging whether the target customer is in a first customer set of the first banking outlet, wherein the first banking outlet is any one banking outlet;
under the condition that a target customer is not in the first customer set, inquiring a face recognition parameter threshold value of a second bank website from the blockchain network, wherein the target customer is a customer in the second customer set, and the second customer set is a customer set of the second bank website;
and carrying out face recognition on the target customer according to the face recognition parameter threshold of the second bank outlet to generate a face recognition result.
11. The apparatus of claim 8, wherein the face recognition parameter threshold estimation module is further configured to estimate the face recognition parameter threshold for each banking outlet by the following formula:
L2＝MAXL-(MAXL-L1)×f(r)；
wherein L is2Representing a face recognition parameter threshold value when the face recognition is carried out on the client by each bank network point; the MAXL represents the maximum value of the face recognition parameter threshold; l1 represents the face recognition parameter threshold when the bank backend server performs face recognition on the client; f represents a monotonically decreasing function; r represents a transaction risk coefficient.
12. The apparatus of claim 8, wherein the apparatus further comprises:
the face recognition parameter threshold value acquisition module is used for calculating the passing rate or the false recognition rate of each bank branch according to the transaction risk coefficient of each bank branch by using an intelligent contract configured in advance on a block chain network; and acquiring the face recognition parameter threshold of each bank outlet according to the passing rate or the false recognition rate of each bank outlet.
13. The apparatus of claim 12, wherein the face recognition parameter threshold estimation module is further configured to calculate a passing rate or a false recognition rate of each bank outlet according to the following formula:
T2＝1-(1-T1)/f(r)；
F2＝1-(1-F1)×f(r)；
wherein, T2The passing rate of each bank website when the user carries out face recognition on the user by each bank website is represented; t1 represents the passing rate of each bank branch when the bank background server identifies the face of the client; f2The method comprises the steps of representing the false recognition rate of each bank website when each bank website carries out face recognition on a client; f1 represents the false recognition rate of each bank website when the bank background server carries out face recognition on the customer; f represents a monotonically decreasing function; r represents a transaction risk coefficient.
14. The apparatus of claim 13, wherein the face recognition parameter threshold estimation module is further configured to:
acquiring transaction data of each bank network point for carrying out face recognition on a client;
determining the risk transaction proportion of each bank website according to the transaction data of face recognition of each bank website to the client;
judging whether the risk transaction proportion of each banking outlet is larger than a reference risk transaction proportion, wherein the reference risk transaction proportion is the risk transaction proportion of all banking outlets;
and under the condition that the risk transaction proportion of any one bank outlet is greater than the reference risk transaction proportion, increasing the face identification parameter threshold of the bank outlet until the risk transaction proportion of the bank outlet is less than or equal to the reference risk transaction proportion.
15. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the blockchain based banking site face recognition method according to any one of claims 1 to 7.
16. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the method for face recognition of a bank branch based on a blockchain according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918206.2A CN113610632A (en) | 2021-08-11 | 2021-08-11 | Bank outlet face recognition method and device based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918206.2A CN113610632A (en) | 2021-08-11 | 2021-08-11 | Bank outlet face recognition method and device based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610632A true CN113610632A (en) | 2021-11-05 |
Family
ID=78340244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110918206.2A Pending CN113610632A (en) | 2021-08-11 | 2021-08-11 | Bank outlet face recognition method and device based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610632A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062339A (en) * | 2019-12-19 | 2020-04-24 | 广州广大通电子科技有限公司 | Face recognition method, device, equipment and storage medium based on block chain |
| CN111950915A (en) * | 2020-08-18 | 2020-11-17 | 中国银行股份有限公司 | Method and device for evaluating workload of bank outlet teller |
| CN112307120A (en) * | 2020-10-29 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Information management server, information management method, and information management system |
| CN112699799A (en) * | 2020-12-30 | 2021-04-23 | 杭州趣链科技有限公司 | Face recognition method, device, equipment and storage medium based on block chain |
| WO2021104126A1 (en) * | 2019-11-27 | 2021-06-03 | 中兴通讯股份有限公司 | User verification method and apparatus, electronic device and computer-readable medium |
| CN113065866A (en) * | 2021-03-23 | 2021-07-02 | 北京邮电大学 | Internet of things edge computing system and method based on block chain |
| WO2021151279A1 (en) * | 2020-06-17 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for cloud monitoring based on edge computing, electronic device, and storage medium |
-
2021
- 2021-08-11 CN CN202110918206.2A patent/CN113610632A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021104126A1 (en) * | 2019-11-27 | 2021-06-03 | 中兴通讯股份有限公司 | User verification method and apparatus, electronic device and computer-readable medium |
| CN111062339A (en) * | 2019-12-19 | 2020-04-24 | 广州广大通电子科技有限公司 | Face recognition method, device, equipment and storage medium based on block chain |
| WO2021151279A1 (en) * | 2020-06-17 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for cloud monitoring based on edge computing, electronic device, and storage medium |
| CN111950915A (en) * | 2020-08-18 | 2020-11-17 | 中国银行股份有限公司 | Method and device for evaluating workload of bank outlet teller |
| CN112307120A (en) * | 2020-10-29 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Information management server, information management method, and information management system |
| CN112699799A (en) * | 2020-12-30 | 2021-04-23 | 杭州趣链科技有限公司 | Face recognition method, device, equipment and storage medium based on block chain |
| CN113065866A (en) * | 2021-03-23 | 2021-07-02 | 北京邮电大学 | Internet of things edge computing system and method based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022267735A1 (en) | Service data processing method and apparatus, computer device, and storage medium | |
| EP3489877A1 (en) | Risk identification method, client device, and risk identification system | |
| CN110232565B (en) | Resource clearing method, device, computer equipment and storage medium | |
| KR20180075641A (en) | Service processing method and apparatus | |
| CN111199018B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| CN110633194B (en) | Performance evaluation method of hardware resources in specific environment | |
| US9330160B2 (en) | Software application complexity analysis | |
| CN102082703A (en) | Method and device for monitoring equipment performance of service supporting system | |
| US8180716B2 (en) | Method and device for forecasting computational needs of an application | |
| CN113204692A (en) | Method and device for monitoring execution progress of data processing task | |
| CN113610632A (en) | Bank outlet face recognition method and device based on block chain | |
| CN110796379B (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| CN112035569A (en) | Merchant scoring method and system | |
| KR102284395B1 (en) | Sales estimation system based on the amount of power usage and method thereof | |
| CN113343577B (en) | Parameter optimization method, device, equipment and medium based on machine learning | |
| CN106687997B (en) | Method and system for identifying time lag index of event to be predicted | |
| KR102153834B1 (en) | Method and quantifying a data based on final value and estimate | |
| JP5650290B1 (en) | Operational risk measurement method and apparatus | |
| TWI503675B (en) | The method of predicting the number of user actions of the word and the device | |
| CN113627945A (en) | Fingerprint information verification method and device based on block chain | |
| CN111429257A (en) | Transaction monitoring method and device | |
| CN110738571A (en) | transaction risk control method and related device | |
| US20210142414A1 (en) | Measure determination system, measure determination method, and measure determination program | |
| WO2018066300A1 (en) | Validation system, validation execution method, and validation program | |
| CN113225228B (en) | Data processing method and device |
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 |