CN112116457B - Bank counter business supervision method, device and equipment - Google Patents
Bank counter business supervision method, device and equipment Download PDFInfo
- Publication number
- CN112116457B CN112116457B CN202011049698.8A CN202011049698A CN112116457B CN 112116457 B CN112116457 B CN 112116457B CN 202011049698 A CN202011049698 A CN 202011049698A CN 112116457 B CN112116457 B CN 112116457B
- Authority
- CN
- China
- Prior art keywords
- business
- counter
- teller
- text information
- verification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000006399 behavior Effects 0.000 claims abstract description 18
- 238000012795 verification Methods 0.000 claims description 62
- 238000012549 training Methods 0.000 claims description 57
- 238000003062 neural network model Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- 238000000151 deposition Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping 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
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a supervision method, device and equipment for bank counter business, which can judge whether a counter has illegal behaviors when transacting business by utilizing an expert knowledge base and a pre-constructed business supervision model so as to take corresponding measures to protect rights and interests of clients and banks. The method comprises the following steps: firstly, voice information when a teller transacts the counter business is acquired, the voice information is converted into text information, then the text information is compared with business rules in an expert knowledge base, whether the behavior of the teller transacting the counter business accords with the business rules is judged, if yes, the text information is input into a pre-constructed business supervision model, and whether the counter business transacted by the teller is normal is determined.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, and a device for monitoring a banking counter service.
Background
With the rapid development of mobile internet and socioeconomic, more and more banking clients to the website transact various banking businesses such as purchasing financial resources of a bank, depositing money into a bank, etc.
However, various potential risks are increasing at present, particularly as the amount of banking counter traffic increases, the banking counter faces various risks based on the counter personnel themselves. The risk of the bank counter is better pre-controlled, and the risk is the weight of the current counter business. How to form a unified counter risk monitoring system by utilizing the existing information is one of the main problems of each large bank nowadays, namely how to realize real-time supervision of bank counter business so as to protect the rights and interests of customers and banks, which is a problem to be solved.
Disclosure of Invention
The main purpose of the embodiments of the present application is to provide a method, an apparatus, and a device for monitoring a banking counter service, which can utilize an expert knowledge base and a pre-constructed service monitoring model to determine whether a counter has a violation when transacting a service, so as to take corresponding measures to protect rights and interests of clients and banks.
In a first aspect, an embodiment of the present application provides a method for supervising a banking counter service, including:
acquiring voice information when a teller transacts counter business, and converting the voice information into text information;
comparing the text information with business rules in an expert knowledge base, and judging whether the behavior of the counter handling counter business accords with the business rules or not;
if yes, inputting the text information into a pre-constructed business supervision model, and determining whether the counter business handled by the counter is normal.
Optionally, constructing the service supervision model includes:
acquiring training voice information when a teller transacts counter business, and converting the training voice information into training text information;
and training the initial business supervision model by using the training text information of the teller and the state identification label corresponding to the training text information of the teller to generate the business supervision model.
Optionally, the method further comprises:
acquiring verification voice information when a teller transacts counter business, and converting the verification voice information into verification text information;
inputting the verification text information of the teller into the business supervision model to obtain a state identification result of the verification text information of the teller;
and when the state identification result of the verification text information of the teller is inconsistent with the state marking result corresponding to the verification text information of the teller, the verification text information of the teller is re-used as the training text information of the teller, and the business supervision model is updated.
Optionally, the business supervision model is a BP neural network model optimized by using a genetic algorithm.
In a second aspect, an embodiment of the present application further provides a supervision apparatus for banking counter services, including:
the first acquisition unit is used for acquiring voice information when a teller transacts counter business and converting the voice information into text information;
the judging unit is used for comparing the text information with the business rules in the expert knowledge base and judging whether the behavior of the counter transacting the counter business accords with the business rules or not;
and the determining unit is used for inputting the text information into a pre-constructed business supervision model to determine whether the counter business handled by the counter is normal or not if the counter business handled by the counter is judged to be in accordance with the business rule.
Optionally, the apparatus further includes:
the second acquisition unit is used for acquiring training voice information when a teller transacts the counter business and converting the training voice information into training text information;
the training unit is used for training the initial business supervision model by utilizing the training text information of the teller and the state identification label corresponding to the training text information of the teller, so as to generate the business supervision model.
Optionally, the apparatus further includes:
the third acquisition unit is used for acquiring verification voice information when a teller transacts the counter business and converting the verification voice information into verification text information;
the obtaining unit is used for inputting the verification text information of the teller into the business supervision model to obtain a state identification result of the verification text information of the teller;
and the updating unit is used for updating the business supervision model by taking the verification text information of the teller as the training text information of the teller again when the state identification result of the verification text information of the teller is inconsistent with the state marking result corresponding to the verification text information of the teller.
Optionally, the business supervision model is a BP neural network model optimized by using a genetic algorithm.
The embodiment of the application also provides a supervision device for bank counter business, comprising: a processor, memory, system bus;
the processor and the memory are connected through the system bus;
the memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform any one of the implementations of the method of supervising banking counter traffic described above.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on the terminal equipment, the terminal equipment is caused to execute any implementation mode of the supervision method of the bank counter business.
According to the supervision method, device and equipment for the bank counter business, voice information when a counter transacts the counter business is firstly obtained, the voice information is converted into text information, then the text information is compared with business rules in an expert knowledge base, whether the counter transacts the counter business accords with the business rules is judged, if yes, the text information is input into a pre-built business supervision model, and whether the counter transacting the counter business is normal is determined. Therefore, whether the teller has illegal behaviors in business handling can be judged by utilizing the expert knowledge base and a pre-constructed business supervision model, so that corresponding measures can be taken to protect rights and interests of clients and banks.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for supervising a banking counter service according to an embodiment of the present application;
fig. 2 is a schematic diagram of a supervision apparatus for banking counter services according to an embodiment of the present application.
Detailed Description
With the rapid development of mobile internet and socioeconomic, more and more banking clients to the website transact various banking businesses such as purchasing financial resources of a bank, depositing money into a bank, etc. However, various potential risks are increasing at present, particularly as the amount of banking counter traffic increases, the banking counter faces various risks based on the counter personnel themselves. The risk of the bank counter is better pre-controlled, and the risk is the weight of the current counter business. How to form a unified counter risk monitoring system by utilizing the existing information is one of the main problems of each large bank nowadays, namely how to realize real-time supervision of bank counter business so as to protect the rights and interests of customers and banks, which is a problem to be solved.
In order to solve the above-mentioned drawbacks, the embodiment of the present application provides a method for supervising a banking counter service, which includes first obtaining voice information when a counter transacts the counter service, converting the voice information into text information, then comparing the text information with service rules in an expert knowledge base to determine whether the counter transacts the counter service accords with the service rules, if yes, inputting the text information into a pre-built service supervision model, and determining whether the counter transacts the counter service normally. Therefore, whether the teller has illegal behaviors in business handling can be judged by utilizing the expert knowledge base and a pre-constructed business supervision model, so that corresponding measures can be taken to protect rights and interests of clients and banks.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
First embodiment
Referring to fig. 1, a flow chart of a method for supervising a banking counter service according to the present embodiment is provided, and the method includes the following steps:
s101: and acquiring voice information when the teller transacts the counter business, and converting the voice information into text information.
In this embodiment, in order to accurately determine whether a teller has a violation when transacting a service, so as to take corresponding measures to protect the rights and interests of customers and banks, for banks, firstly, a teller earphone is connected with a background system through bluetooth, then a background server can be connected with a loudspeaker facing the customers through the bluetooth, and play the voice information of the teller, and simultaneously acquire and store the voice information when transacting the counter service, further, after converting the voice information into the text information, it can be determined whether the counter service transacted by the teller is normal (namely whether the violation occurs) through subsequent steps S102-S103, if the violation occurs, the relevant staff can be timely reminded, the funds safety of the website is noted, and the rights and interests of the customers and banks are protected.
S102: and comparing the text information with the business rules in the expert knowledge base, and judging whether the behavior of the counter for handling the counter business accords with the business rules.
In this embodiment, after the background system of the bank obtains the text information generated when the teller transacts the counter business through step S101, the text information can be further input into the expert system of the background, and the text information of the teller is compared with all the system business rules in the expert system knowledge base through the binary tree searching method, so as to determine whether the teller transacts the counter business according to the system business rules, that is, whether the teller transacts the counter business conflicts with all the system business rules in the system knowledge base, if the teller does not conflict with all the system business rules, the background staff is reminded to listen to the record of the teller directly, and whether the counter business transacts the counter business has illegal behaviors or not. If there is no conflict (i.e., it is determined that the counter transacting counter business is in compliance with the business rules), the subsequent step S103 may be continued.
Illustrating: after the counter transacts the text information generated during the counter business, firstly, the keywords in the text information, such as deposit and loan, can be identified, according to the relevant business rules in the deposit and loan matching expert knowledge base, such as matching the deposit business, the relevant rule information of the deposit business is queried, such as the rules that the counter cannot be related to the customer in the process of providing financial products, or the counter cannot be related to the customer in the process of discussing the interest rate, etc., after matching the corresponding rules, the keywords according to the preset rules are reversely queried to determine whether the text information of the counter relates to the relevant keywords, such as the interest rate and the keywords of the financial products, if the related statement information and the rule information are simultaneously input into the text recognition model to determine whether the text spoken by the counter really accords with the corresponding rules which cannot be related to the customer in the process of recommending financial products and the business interest rate, and if the text spoken by the counter accords with one rule, the text information is considered to be in the expert system knowledge base.
S103: if so, inputting the text information into a pre-constructed business supervision model, and determining whether the counter business handled by the counter is normal.
In this embodiment, if it is determined by step S102 that the counter business handling behavior accords with the business rule, text information may be further input into a pre-constructed business supervision model to determine whether the counter business handled by the counter is normal, that is, whether the counter has fraud during handling of the counter may be determined by the business supervision model.
The method comprises the following steps of A1-A2:
step A1: and acquiring training voice information when the teller transacts the counter business, and converting the training voice information into training text information.
Step A2: training the initial business supervision model by using the training text information of the teller and the state identification label corresponding to the training text information of the teller to generate the business supervision model.
In this embodiment, in order to construct the business supervision model, a great deal of preparation work needs to be performed in advance, first, training voice information when a teller handles a counter business needs to be collected and converted into training text information, for example, 1000 pieces of voice information sent when the teller handles the counter business can be collected in advance, each piece of collected voice information is respectively used as sample information data, and the business states (i.e., normal and abnormal) handled by the teller, which are represented by the sample information data, are marked manually in advance, so as to train the business supervision model. That is, the initial business supervision model can be trained by using training text information of the teller and manually marked state labels of the teller corresponding to the training text information of the teller, and a business supervision model is generated.
Through the above embodiment, the service supervision model can be generated by training the training voice information when the counter transacts the counter service, and further, the generated service supervision model can be verified by using the verification voice information when the counter transacts the counter service, and the specific implementation process includes the following steps B1-B3:
step B1: and acquiring verification voice information when the teller transacts the counter business, and converting the verification voice information into verification text information.
Step B2: inputting the verification text information of the teller into the business supervision model to obtain the state identification result of the verification text information of the teller.
Step B3: when the state identification result of the verification text information of the teller is inconsistent with the state marking result corresponding to the verification text information of the teller, the verification text information of the teller is used as training text information of the teller again, and the business supervision model is updated.
In practical application, in order to implement verification of the service supervision model, first, verification voice information when a teller handles counter service needs to be acquired and converted into verification text information, wherein the verification voice information when the teller handles counter service refers to the verification voice information sent when the teller handles counter service, which can be used for verification of the service supervision model, further, the verification voice information can be converted into verification text information and then is input into the service supervision model, and a state recognition result of the verification text information of the teller is obtained. When the state identification result of the verification text information of the teller is inconsistent with the state marking result of the verification text information of the teller, the verification text information of the teller is used as training text information of the teller again, and the business supervision model is updated.
In an alternative implementation manner, the initial business supervision model may be built by adopting a neural network model, training text information of a teller is used as model input, whether counter business handled by the teller is normal (i.e. whether the teller has illegal behaviors) is used as model output, and the BP neural network structure is determined according to the number of network inputs and outputs, so that the number of parameters to be optimized is determined. According to the kolmogorov principle, a three-layer BP neural network is sufficient to complete arbitrary n-dimensional to m-dimensional mapping, generally only one hidden layer is needed, the number of hidden layer nodes is determined by adopting a trial-and-error method, so that the neural network structure can be determined, the collected training voice information when a teller transacts a counter service and whether the counter service transacted by the teller is normal (namely whether the teller has illegal behaviors) is judged through manual experience to be used as training data, the training set and the verification set are divided, and an effective service supervision model is obtained by training and verifying the neural network model through the steps.
In summary, according to the method for supervising the bank counter business provided by the embodiment, firstly, voice information when a counter transacts the counter business is obtained, the voice information is converted into text information, then, the text information is compared with business rules in an expert knowledge base to judge whether the counter transacts the counter business or not, if yes, the text information is input into a pre-built business supervision model to determine whether the counter transacts the counter business normally. Therefore, whether the teller has illegal behaviors in business handling can be judged by utilizing the expert knowledge base and a pre-constructed business supervision model, so that corresponding measures can be taken to protect rights and interests of clients and banks.
Second embodiment
The embodiment will be described with respect to a supervision apparatus for banking counter services, and reference will be made to the above-mentioned method embodiments for related content.
Referring to fig. 2, a schematic composition diagram of a supervision apparatus for banking counter services according to the present embodiment is provided, where the apparatus includes:
a first obtaining unit 201, configured to obtain voice information when a teller handles a counter service, and convert the voice information into text information;
a judging unit 202, configured to compare the text information with service rules in an expert knowledge base, and judge whether the behavior of the teller for handling the counter service accords with the service rules;
and the determining unit 203 is configured to, if it is determined that the behavior of the counter handling the counter service accords with the service rule, input the text information into a service supervision model that is constructed in advance, and determine whether the counter handling the counter service is normal.
In one implementation of this embodiment, the apparatus further includes:
the second acquisition unit is used for acquiring training voice information when a teller transacts the counter business and converting the training voice information into training text information;
the training unit is used for training the initial business supervision model by utilizing the training text information of the teller and the state identification label corresponding to the training text information of the teller, so as to generate the business supervision model.
In one implementation of this embodiment, the apparatus further includes:
the third acquisition unit is used for acquiring verification voice information when a teller transacts the counter business and converting the verification voice information into verification text information;
the obtaining unit is used for inputting the verification text information of the teller into the business supervision model to obtain a state identification result of the verification text information of the teller;
and the updating unit is used for updating the business supervision model by taking the verification text information of the teller as the training text information of the teller again when the state identification result of the verification text information of the teller is inconsistent with the state marking result corresponding to the verification text information of the teller.
In one implementation manner of this embodiment, the service supervision model is a BP neural network model optimized by using a genetic algorithm.
In summary, the supervision device for bank counter business provided in this embodiment first obtains the voice information when the counter transacts the counter business, converts the voice information into text information, then compares the text information with the business rules in the expert knowledge base, and determines whether the counter transacts the counter business according with the business rules, if yes, inputs the text information into the pre-built business supervision model, and determines whether the counter transacts the counter business normally. Therefore, whether the teller has illegal behaviors in business handling can be judged by utilizing the expert knowledge base and a pre-constructed business supervision model, so that corresponding measures can be taken to protect rights and interests of clients and banks.
Further, the embodiment of the application also provides a supervision device for bank counter service, which comprises: a processor, memory, system bus;
the processor and the memory are connected through the system bus;
the memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform any of the implementations of the method of supervising banking counter traffic described above.
Further, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on a terminal device, the terminal device is caused to execute any implementation method of the supervision method of the banking counter service.
From the above description of embodiments, it will be apparent to those skilled in the art that all or part of the steps of the above described example methods may be implemented in software plus necessary general purpose hardware platforms. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to perform the methods described in the embodiments or some parts of the embodiments of the present application.
It should be noted that, in the present description, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (4)
1. A method for supervising banking counter services, comprising:
acquiring voice information when a teller transacts counter business, and converting the voice information into text information;
comparing the text information with business rules in an expert knowledge base, and judging whether the behavior of the counter handling counter business accords with the business rules or not;
if yes, inputting the text information into a pre-constructed business supervision model, and determining whether the counter business handled by the counter is normal or not;
the construction of the business supervision model comprises the following steps:
acquiring training voice information when a teller transacts counter business, and converting the training voice information into training text information;
training an initial business supervision model by using training text information of the teller and a state identification tag corresponding to the training text information of the teller to generate the business supervision model;
the method further comprises the steps of:
acquiring verification voice information when a teller transacts counter business, and converting the verification voice information into verification text information;
inputting the verification text information of the teller into the business supervision model to obtain a state identification result of the verification text information of the teller;
when the state identification result of the verification text information of the teller is inconsistent with the state marking result corresponding to the verification text information of the teller, the verification text information of the teller is re-used as training text information of the teller, and the business supervision model is updated;
the business supervision model is a BP neural network model optimized by utilizing a genetic algorithm.
2. A device for supervising banking counter services, comprising:
the first acquisition unit is used for acquiring voice information when a teller transacts counter business and converting the voice information into text information;
the judging unit is used for comparing the text information with the business rules in the expert knowledge base and judging whether the behavior of the counter transacting the counter business accords with the business rules or not;
the determining unit is used for inputting the text information into a pre-constructed business supervision model if judging that the behavior of the counter transacting the counter business accords with the business rule, and determining whether the counter transacting the counter business is normal or not;
the apparatus further comprises:
the second acquisition unit is used for acquiring training voice information when a teller transacts the counter business and converting the training voice information into training text information;
the training unit is used for training the initial business supervision model by utilizing the training text information of the teller and the state identification tag corresponding to the training text information of the teller to generate the business supervision model;
the third acquisition unit is used for acquiring verification voice information when a teller transacts the counter business and converting the verification voice information into verification text information;
the obtaining unit is used for inputting the verification text information of the teller into the business supervision model to obtain a state identification result of the verification text information of the teller;
the updating unit is used for updating the business supervision model by taking the verification text information of the teller as the training text information of the teller again when the state identification result of the verification text information of the teller is inconsistent with the state marking result corresponding to the verification text information of the teller;
the business supervision model is a BP neural network model optimized by utilizing a genetic algorithm.
3. A supervision apparatus for banking counter services, comprising: a processor, memory, system bus;
the processor and the memory are connected through the system bus;
the memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of claim 1.
4. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein instructions, which when run on a terminal device, cause the terminal device to perform the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011049698.8A CN112116457B (en) | 2020-09-29 | 2020-09-29 | Bank counter business supervision method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011049698.8A CN112116457B (en) | 2020-09-29 | 2020-09-29 | Bank counter business supervision method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116457A CN112116457A (en) | 2020-12-22 |
| CN112116457B true CN112116457B (en) | 2024-02-23 |
Family
ID=73797289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011049698.8A Active CN112116457B (en) | 2020-09-29 | 2020-09-29 | Bank counter business supervision method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116457B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112967132B (en) * | 2021-03-30 | 2024-04-16 | 中信银行股份有限公司 | Bank information management system and method based on big data cascading |
| CN114154958A (en) * | 2021-12-03 | 2022-03-08 | 北京字跳网络技术有限公司 | Information processing method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9153231B1 (en) * | 2013-03-15 | 2015-10-06 | Amazon Technologies, Inc. | Adaptive neural network speech recognition models |
| CN109087648A (en) * | 2018-08-21 | 2018-12-25 | 平安科技（深圳）有限公司 | Sales counter voice monitoring method, device, computer equipment and storage medium |
| CN110287318A (en) * | 2019-06-06 | 2019-09-27 | 秒针信息技术有限公司 | The detection method and device of business operation, storage medium, electronic device |
| CN110378562A (en) * | 2019-06-17 | 2019-10-25 | 中国平安人寿保险股份有限公司 | Voice quality detecting method, device, computer equipment and storage medium |
| CN111462735A (en) * | 2020-04-10 | 2020-07-28 | 网易（杭州）网络有限公司 | Voice detection method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210016829A (en) * | 2019-08-05 | 2021-02-17 | 엘지전자 주식회사 | Intelligent voice recognizing method, apparatus, and intelligent computing device |
-
2020
- 2020-09-29 CN CN202011049698.8A patent/CN112116457B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9153231B1 (en) * | 2013-03-15 | 2015-10-06 | Amazon Technologies, Inc. | Adaptive neural network speech recognition models |
| CN109087648A (en) * | 2018-08-21 | 2018-12-25 | 平安科技（深圳）有限公司 | Sales counter voice monitoring method, device, computer equipment and storage medium |
| CN110287318A (en) * | 2019-06-06 | 2019-09-27 | 秒针信息技术有限公司 | The detection method and device of business operation, storage medium, electronic device |
| CN110378562A (en) * | 2019-06-17 | 2019-10-25 | 中国平安人寿保险股份有限公司 | Voice quality detecting method, device, computer equipment and storage medium |
| CN111462735A (en) * | 2020-04-10 | 2020-07-28 | 网易（杭州）网络有限公司 | Voice detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116457A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11449931B2 (en) | Dynamic business governance based on events | |
| WO2019196546A1 (en) | Method and apparatus for determining risk probability of service request event | |
| CN112200660B (en) | Bank counter business supervision method, device and equipment | |
| US20110238516A1 (en) | E-commerce threat detection | |
| CN112116457B (en) | Bank counter business supervision method, device and equipment | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| CN110362689A (en) | A kind of methods of risk assessment, device, storage medium and server | |
| CN113592568B (en) | Business opportunity mining method and device, computer equipment and storage medium | |
| CN109993448A (en) | A kind of appraisal procedure and system of enterprise network public sentiment potential risk | |
| CN109919608B (en) | Identification method, device and server for high-risk transaction main body | |
| CN112348321A (en) | Risk user identification method and device and electronic equipment | |
| CN111008335A (en) | Information processing method, device, equipment and storage medium | |
| US10467632B1 (en) | Systems and methods for a multi-tiered fraud alert review | |
| CN114547475A (en) | Resource recommendation method, device and system | |
| CN106529953A (en) | Method and device for carrying out risk identification on business attributes | |
| CN111612284B (en) | Data processing method, device and equipment | |
| Basalamah | The effect of service quality and relationship marketing towards customer loyalty for Sharia banking (Sharia Banking Study in Makassar Indonesia) | |
| CN112837149A (en) | Method and device for identifying enterprise credit risk | |
| US11777874B1 (en) | Artificial intelligence conversation engine | |
| US20100042446A1 (en) | Systems and methods for providing core property review | |
| Xie et al. | A big data technique for internet financial risk control | |
| Nasr et al. | A Proposed Fraud Detection Model based on e-Payments Attributes a Case Study in Egyptian e-Payment Gateway | |
| CN114943455A (en) | Method and device for preventing rule violation of foreground and background, electronic equipment and storage medium | |
| CN114625977A (en) | Service recommendation method and device based on federal learning and related medium | |
| Kacar | Application of AI in Customer Experience Management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |